WASHING MACHINE AND METHOD FOR CONTROLLING THE SAME

Abstract

The present disclosure relates to a washing machine and a method for controlling the same. The washing machine according to an embodiment of the present disclosure includes a washing tub to accommodate clothes and rotatably installed, a motor to rotate the washing tub, and a control unit to control the motor to rotate the washing tub, wherein the control unit measures a plurality of types of data previously set while the washing tub accelerates from a first rotation velocity to a second rotation velocity which is faster than the first rotation velocity, inputs the plurality of types of data into a pre-learned artificial neural network as an input value and calculates an expected UB pattern as a result value, and controls the motor so that the washing tub is rotated in a preset manner based on a type of the calculated UB pattern.

Description

CROSS-REFERENCE TO RELATED APPLICATION

Pursuant to 35 U.S.C. § 119(a), this application claims the benefit of the earlier filing date and the right of priority to Korean Patent Application No. 10-2019-0014055, filed on Feb. 1, 2019, the contents of which is incorporated by reference herein in its entirety.

BACKGROUND

1. Technical Field

The present disclosure relates to a washing machine and a method for controlling the same, and more particularly, to a washing machine, capable of performing machine learning-based clothes dispersion, and a method for controlling the same.

2. Description of the Related Art

Generally, a washing machine is a device that removes contaminants from laundry (hereinafter, also referred to as “clothes”) such as clothing, bedding and the like using chemical decomposition between water and detergent, physical interaction between water and the laundry, etc.

Washing machines are mainly classified into a stirring type, a vortex type and a drum type. Among others, the drum type washing machine includes a water storage tank (or a tub) containing water and a washing tub (or a drum) rotatably installed in the tub to receive the laundry.

The washing tub (or drum) is provided with a plurality of through holes through which water flows. A washing operation is generally divided into a washing stroke, a rinsing stroke and a dehydration (dewatering) stroke. The processing of such strokes can be confirmed through a control panel (or a display) provided outside the washing machine.

The washing stroke is to remove contaminants from the laundry by frictional force between water stored in the tub and the laundry stored in the drum, and chemical action of detergent contained in water.

The rinsing stroke is to rinse the clothes by supplying water into the tub, in which detergent is not dissolved in the water, and in particular, the detergent absorbed in the clothes during the washing stroke is removed. In the rinsing stroke, a fabric softener may be supplied together with water.

The dehydration stroke is to dehydrate the clothes by rotating the washing tub at a high velocity after the rinsing stroke is completed. Typically, as the dehydration stroke is completed, all the operations of the washing machine are terminated. On the other hand, in a case of a washing machine for dry combined use, a drying stroke may be further added after the dehydration stroke.

In general, a washing operation is set to operate under different conditions according to an amount of laundry put into the drum (hereinafter, also referred to as ‘amount of clothes’). For example, settings such as a water supply level, a washing strength, a drainage time, and a dehydration time may vary depending on the amount of clothes.

On the other hand, since washing performance may vary depending on not only the amount of clothes but also a type of laundry (hereinafter, also referred to as ‘quality of clothes’), a sufficiently high quality washing performance cannot be expected when only considering the amount of clothes in setting the washing operation.

Meanwhile, in the dehydration stroke after the washing stroke and the rinsing stroke are completed in the washing operation, the clothes need to be effectively dispersed. When the clothes are not evenly dispersed and are driven to either side, UB (Unbalance) is generated and shaking of the drum gets bigger, thereby increasing a dehydration stroke time and making a noise bigger.

Therefore, a clothes dispersion process for dispersing the clothes is performed in the dehydration stroke, and various technologies are developed to ensure proper and even dispersion of the clothes.

Recently, interest in machine learning such as artificial intelligence and deep learning has been increasing greatly.

The related art machine learning was focusing on statistics-based classification, regression, and clustering models. In particular, in supervised learning for classification and regression models, a human has previously defined learning models that distinguish characteristics of learning data and new data based on these characteristics. Deep learning, on the other hand, is for computers to find and identify the characteristics on their own.

One of factors that has accelerated development of deep learning is a deep learning framework offered as an open source. For example, the deep learning frameworks include Theano at the University of Montreal in Canada, Torch at the New York University, USA, Caffe at the University of California, Berkeley, and TensorFlow from Google.

Due to disclosure of deep learning frameworks, in addition to deep learning algorithms, extraction and selection of data used in learning processes, learning methods, and learning are becoming more important for effective learning and recognition.

In addition, researches for using artificial intelligence and machine learning in various products and services are increasing.

In addition, development for performing an optimized dehydration stroke by applying artificial intelligence and machine learning to the dehydration stroke is actively progressing.

SUMMARY

Embodiments of the present disclosure are to provide a washing machine and a method for controlling the same capable of performing optimized clothes dispersion in order to solve the above problems.

In addition, embodiments of the present disclosure are to provide a washing machine and a method for controlling the same capable of shortening a dehydration stroke time.

Furthermore, embodiments of the present disclosure are to provide a washing machine and a method for controlling the same capable of preventing a prolongation of the dehydration stroke time by applying an artificial neural network learned by machine learning and extending sections that perform the clothes dispersion.

Aspects of the present disclosure are not limited to the above-mentioned aspects, and other aspects that are not mentioned will be clearly understood by those skilled in the art by the following description.

To achieve the above aspects, the washing machine of the present disclosure may include the washing tub to accommodate clothes and rotatably installed, the motor to rotate the washing tub, and the control unit to control the motor to rotate the washing tub, wherein the control unit measures a plurality of types of data previously set while the washing tub accelerates from a first rotation velocity to a second rotation velocity which is faster than the first rotation velocity, inputs the plurality of types of data into a pre-learned artificial neural network as an input value and calculates an expected UB pattern as a result value, and controls the motor so that the washing tub is rotated in a preset manner based on a type of the calculated UB pattern.

In an embodiment, the clothes dispersion may be performed in a way that the clothes are raised up by a predetermined height then fall in a maintaining section in which a rotation of the washing tub is maintained at the first rotation velocity and in an accelerating section in which the washing tub accelerates from the first rotation velocity to the second rotation velocity.

In an embodiment, the clothes dispersion may be performed before a rotation velocity of the washing tub reaches the second rotation velocity, and when the rotation velocity of the washing tub reaches the second rotation velocity, the clothes are stuck to the washing tub, and this may hinder the clothes dispersion from being performed.

In an embodiment, the plurality of types of data may include at least one among an average value of UB values for a predetermined time, an average value of rotation velocity values of the washing tub for a predetermined time, an average value of current values applied to the motor for a predetermined time, and an average value of vibration values measured by a vibration sensor for a predetermined time.

In an embodiment, the control unit may measure the plurality of types of data at every predetermined time in the accelerating section in which the washing tub accelerates from the first rotation velocity to the second rotation velocity.

In an embodiment, the control unit may determine whether to accelerate, decelerate or maintain the rotation velocity of the washing tub at every predetermined time, based on a type of UB pattern calculated through an artificial neural network by measuring the plurality of types of data at every predetermined time and using the calculated plurality of types of data.

In an embodiment, the calculated UB pattern may include a UB increase pattern in which a UB value is expected to increase, a UB maintenance pattern in which the UB value is expected to maintain, and a UB decrease pattern in which the UB value is expected to decrease.

In an embodiment, the control unit, when the calculated UB pattern is the UB increase pattern in which the UB value is expected to increase, may decrease the rotation velocity of the washing tub.

In an embodiment, the control unit, when the calculated UB pattern is the UB decrease pattern in which the UB value is expected to decrease, may increase the rotation velocity of the washing tub.

In an embodiment, the control unit, when the calculated UB pattern is the UB maintenance pattern in which the UB value is expected to maintain, may maintain the rotation velocity of the washing tub.

In an embodiment, the control unit, when the UB value measured in an accelerating section in which the washing tub is accelerated from the first rotation velocity to the second rotation velocity exceeds a preset reference value, may short-circuit the rotation of the washing tub.

In an embodiment, the control unit, when the washing tub fails to reach the second rotation velocity within a predetermined time duration since a time when the washing tub starts accelerating from the first rotation velocity to the second rotation velocity, may short-circuit the rotation of the washing tub.

A control method of the washing machine according to an embodiment of the present disclosure may include measuring a plurality of types of data previously set while the washing tub accelerates from the first rotation velocity to the second rotation velocity which is faster than the first rotation velocity, inputting the plurality of types of data into a pre-learned artificial neural network as an input value and calculating an expected UB pattern as a result value, and controlling the motor so that the washing tub rotates in a preset manner based on the type of the calculated UB pattern.

In an embodiment, the calculated UB pattern may include the UB increase pattern in which the UB value is expected to increase, the UB maintenance pattern in which the UB value is expected to maintain, and the UB decrease pattern in which the UB value is expected to decrease.

In an embodiment, the controlling, when the calculated UB pattern is the UB increase pattern in which the UB value is expected to increase, may decrease the rotation velocity of the washing tub.

In an embodiment, the controlling, when the calculated UB pattern is the UB decrease pattern in which the UB value is expected to decrease, may increase the rotation velocity of the washing tub.

In an embodiment, the controlling, when the calculated UB pattern is the UB maintenance pattern in which the UB value is expected to maintain, may maintain the rotation velocity of the washing tub.

Details of other embodiments are included in detailed descriptions and drawings.

According to embodiments of the present disclosure, there are at least one of the following effects.

First, the present disclosure performs the clothes dispersion not only in the maintaining section in which the washing tub maintains the rotation at the first rotation velocity but also in the accelerating section in which the washing tub accelerates from the first rotation velocity to the second rotation velocity which is faster than the first rotation velocity to widen a section where the clothes dispersion is performed. This may result in performing an optimized clothes dispersion and thereby reducing the dehydration stroke time duration.

Second, the present disclosure further performs a control not only accelerating or maintaining but also decelerating the rotation of the washing tub based on an expected UB pattern by using an artificial neural network learned through machine learning in the accelerating section accelerating from the first rotation velocity to the second rotation velocity. This may reduce a number of dehydration strokes that are short-circuited, and thereby significantly reducing the dehydration stroke time duration.

Third, the present disclosure determines a method for controlling the rotation velocity of the washing tub by using a plurality of types of data measured for a predetermined time rather than using one type of data measured at any one moment to short-circuit the dehydration stroke when one datum measured at one moment is an error value, thereby preventing the dehydration stroke time duration from being prolonged.

Effects of the present disclosure are not limited to the above-mentioned effects, and other effects that are not mentioned will be clearly understood by those skilled in the art by the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a side sectional view of a washing machine according to an embodiment of the present disclosure.

FIG. 2 is a block diagram illustrating a controlling relationship among main components of the washing machine of FIG. 1.

FIG. 3 is a view illustrating the related art dehydration stroke process.

FIG. 4 is a view illustrating a dehydration stroke process according to an embodiment of the present disclosure.

FIG. 5 is a flowchart illustrating a representative control method according to the present disclosure.

FIGS. 6, 7, and 8 are conceptual views illustrating the control method illustrated in FIG. 5.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings, and the same reference numerals are used to designate the same/like components and redundant description thereof will be omitted. In general, a suffix such as “module” and “unit” may be used to refer to elements or components. Use of such a suffix herein is merely intended to facilitate description of the specification, and the suffix itself is not intended to give any special meaning or function. In describing the present disclosure, if a detailed explanation for a related known technology or construction is considered to unnecessarily divert the gist of the present disclosure, such explanation has been omitted but would be understood by those skilled in the art. The accompanying drawings are used to help easily understand the technical idea of the present disclosure and it should be understood that the idea of the present disclosure is not limited by the accompanying drawings. The idea of the present disclosure should be construed to extend to any alterations, equivalents and substitutes besides the accompanying drawings.

It will be understood that although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.

It will be understood that when an element is referred to as being “connected with” another element, the element can be connected with the another element or intervening elements may also be present. In contrast, when an element is referred to as being “directly connected with” another element, there are no intervening elements present.

A singular representation may include a plural representation unless it represents a definitely different meaning from the context.

Terms such as “include” or “has” are used herein and should be understood that they are intended to indicate an existence of several components, functions or steps, disclosed in the specification, and it is also understood that greater or fewer components, functions, or steps may likewise be utilized.

FIG. 1 is a side sectional view of the washing machine according to an embodiment of the present disclosure, and FIG. 2 is a block diagram illustrating the controlling relationship among main components of the washing machine of FIG. 1.

Referring to FIG. 1, the washing machine according to an embodiment of the present disclosure includes a casing 1 defining an outer appearance, a water storage tank 3 (or a tub) disposed in the casing 1 and storing washing water therein, a washing tub 4 rotatably installed in the water storage tank 3 to accommodate laundry, and a motor 9 to rotate the washing tub 4.

The washing tub 4 includes a front cover 41 provided with an opening to put in and out laundry, a cylindrical drum 42 disposed substantially horizontally so that a front end thereof is coupled to the front cover 41, and a rear cover 43 coupled to a rear end of the drum 42. A rotating shaft of the motor 9 may be connected to the rear cover 43 by passing through a rear wall of the water storage tank 3. A plurality of through holes may be formed in the drum 42 so that water may be exchanged between the washing tub 4 and the water storage tank 3.

A lifter 20 may be provided on an inner circumferential surface of the drum 42. The lifter 20 protrudes from the inner circumferential surface of the drum 42, extends long in a lengthwise direction (forward and backward direction) of the drum 42, and a plurality of lifters 20 may be spaced apart in a circumferential direction. When the washing tub 4 rotates, the clothes may be carried up by the lifter 20.

Although not necessarily limited thereto, a height to which the lifter 20 protrudes from the drum 42 may preferably be 30 mm (or 6.0% of a diameter of the drum) or less, and more preferably 10 to 20 mm. In particular, when the height of the lifter 20 is 20 mm or less, even if the washing tub 4 is continuously rotated in one direction at approximately 80 rpm, the clothes may flow not being stuck to the washing tub 4. That is, when the washing tub 4 is rotated in one direction in more than one rotation, clothes at a lowermost side in the washing tub 4 may be raised up by a predetermined height by the rotation of the washing tub 4, then dropped as being separated from the washing tub 4.

The washing tub 4 rotates centering on a horizontal axis. Here, the “horizontal” does not mean a geometric horizontal in a strict sense. Since a position of the washing tub 4 is more like horizontal than vertical even when tilted by a predetermined angle with respect to the horizontal as illustrated in FIG. 1, it is said that the washing tub 4 rotates centering on the horizontal axis.

A laundry inlet is provided on a front surface of the casing 1, and a door 2 to open and close the laundry inlet is rotatably provided on the casing 1. A water supply valve 5, a water supply pipe 6, and a water supply hose 8 may be installed inside the casing 1. When the water supply valve 5 is opened to supply water, the washing water passed through the water supply pipe 6 may be mixed with a detergent in a dispenser 7, and then supplied to the water storage tank 3 through the water supply hose 8.

An input port of a pump 11 is connected to the water storage tank 3 by a discharge hose 10, and a discharge port of the pump 11 is connected to a drain pipe 12. Water discharged from the water storage tank 3 through the discharge hose 10 is pumped by the pump 11 and flows through the drain pipe 12, and then discharged outside the washing machine.

Referring to FIG. 2, the washing machine according to an embodiment of the present disclosure may include a control unit 60 to control an overall operation of the washing machine, a motor driving unit 71 controlled by the control unit 60, an output unit 72, a communication unit 73, a velocity detecting unit 74, a current detecting unit 75, a vibration detecting unit 76, a UB detecting unit 77, and a memory 78.

The control unit 60 may control a series of washing process of washing, rinsing, dehydrating and drying. The control unit 60 may proceed with washing, rinsing, dehydrating and drying strokes according to a preset algorithm, and the control unit 60 may control the motor driving unit 71 according to the algorithm.

The motor driving unit 71 may control a driving of the motor 9 in response to a control signal applied from the control unit 60. The control signal may be a signal to control a target velocity, an acceleration gradient (or acceleration), a driving time, and the like of the motor 9.

The motor driving unit 71 is to drive the motor 9, and may include an inverter (not shown) and an inverter control unit (not shown). Further, the motor driving unit 71 may be a concept further including a converter to supply a direct current power input to the inverter.

For example, when the inverter control unit (not shown) outputs a pulse width modulation (PWM) type switching control signal to the inverter (not shown), the inverter (not shown) may perform a fast switching operation to supply alternating current power of a predetermined frequency to the motor 9.

A description in which the control unit 60 controls the motor 9 in a specific manner in the present disclosure means that the control unit 60 applies a control signal to the motor driving unit 71 so that the motor 9 is controlled in a specific manner, and the motor driving unit 710 controls the motor 9 in the specific manner based on the control signal. Here, the specific manner may include various embodiments described herein.

The velocity detecting unit 74 detects a rotation velocity of the washing tub 4. The velocity detecting unit 74 may detect a rotation velocity of a rotor of the motor 9. When a planetary gear train to rotate the washing tub 4 by converting a rotation ratio of the motor 9 is provided, the rotation velocity of the washing tub 4 may be a value in which the rotation velocity of the rotor detected by the velocity detecting unit 74 is converted in consideration of a velocity decrease ratio or a velocity increase ratio of the planetary gear train.

The control unit 60 may control the motor driving unit 71 so that the motor 9 follows a preset target velocity by using the rotation velocity of the washing tub transmitted from the velocity detecting unit 74 as a feedback. In other words, the control unit 60 may control the motor 9 so that the rotation velocity of the washing tub reaches the target velocity.

The current detecting unit 75 may detect a current applied to the motor 9 (or an output current flowing through the motor 9) and transmit the detected current to the control unit 60. The control unit 60 may detect an amount and a quality of the clothes by using the received current.

Here, the current values include values obtained in a process in which the washing tub 4 is accelerated up to the target velocity (or a process in which the motor 9 is accelerated up to the preset target velocity).

When a rotation of the motor 9 is controlled by a vector control based on a torque current and a magnetic flux current, the current may be a torque axis (q-axis) component of a current flowing through a motor circuit, that is, a torque current Iq.

The vibration detecting unit 76 detects vibration generated in the water storage tank 3 (or in the washing machine) by the rotation of the washing tub 4 containing clothes.

The washing machine according to an embodiment of the present disclosure may include a vibration sensor (or vibration measuring sensor). The vibration sensor may be provided at one point of the washing machine. For example, the vibration sensor may be provided at one point of the water storage tank 3. For example, the vibration sensor may be included in the vibration detecting unit 76.

The vibration detecting unit 76 may receive a vibration value (or vibration signal) measured by the vibration sensor and transmit the vibration value (or vibration signal) to the control unit 60. In addition, the vibration detecting unit 76 may calculate a vibration value (or vibration magnitude) of the water storage tank 3 (or washing machine) by using the vibration signal measured in the vibration sensor.

Meanwhile, the present disclosure may further include the UB detecting unit 77. The UB detecting unit 77 may detect an eccentric amount (amount of shaking) of the washing tub 4, that is, an unbalance (UB) of the washing tub 4. The UB detecting unit 77 may calculate a UB value numerically representing a shaking of the washing tub 4.

The UB detecting unit 77 will be described later in more detail.

The velocity detecting unit 74, the current detecting unit 75, the vibration detecting unit 76, and the UB detecting unit 77 provided in the washing machine according to an embodiment of the present disclosure may be referred to as a detecting unit or may be understood as a concept included in the detecting unit.

In addition, the detecting unit may measure (calculate) a plurality of types of data (signal, information) including a rotation velocity value (or velocity value) of the washing tub 4 measured by the velocity detecting unit 74, a current value applied to the motor 9 measured by the current detecting unit 75, a vibration value measured by the vibration detecting unit 76, and a shaking value (UB value) of the washing tub 4 measured by the UB detecting unit 77.

The plurality of types of data may refer to data related to the UB (unbalance) of the washing tub 4, data to measure the UB of the washing tub 4, data generated by the rotation of the washing tub 4, and the like. The plurality of types of data may be used to control the washing tub 4 in the dehydration stroke.

For example, the plurality of types of data may be inputted into an artificial neural network learned by machine learning as an input value to calculate a UB pattern used to determine acceleration, deceleration or maintenance of the washing tub 4 in the dehydration stroke as an output value.

Meanwhile, the velocity detecting unit 74, the current detecting unit 75, the vibration detecting unit 76, and the UB detecting unit 77 are provided separately from the control unit 60 in the drawing, but they are not limited thereto.

At least one of the velocity detecting unit 74, the current detecting unit 75, the vibration detecting unit 76, and the UB detecting unit 77 may be provided in the control unit 60. In this case, the function/operation/control method performed by the velocity detecting unit 74, the current detecting unit 75, the vibration detecting unit 76, and the UB detecting unit 77 may be performed by the control unit 60.

When the vibration detecting unit 76 is included in the control unit 60 or is performed by the control unit 60, it may be understood that the vibration sensor is not included in the vibration detecting unit 76, but is provided separately at one point of the washing machine.

The output unit 72 may output various information related to the washing machine. For example, the output unit 72 outputs an operation state of the washing machine. The output unit 72 may be an image output device such as an LCD or an LED that outputs a visual display, or a sound output device such as a speaker or a buzzer that outputs a sound. By the control of the control unit 60, the output unit 72 may output information on the amount or the quality of the clothes.

A programmed artificial neural network, current patterns for each amount and/or quality of the clothes, a database (DB) constructed by a machine learning based learning on a basis of the current patterns, a machine learning algorithm, current values detected by the current detecting unit 75, averaged values of the current values, a value obtained by processing the averaged values according to a parsing rule, data transmitted and received by the communication unit 73, and the like may be stored in the memory 78.

In addition, various control data to control the overall operation of the washing machine, washing setting data input by a user, data about a washing time duration, a washing course, and the like calculated according to the washing setting, data to determine whether the washing machine has an error, and the like may be stored in the memory 78.

The communication unit 73 may communicate with a server connected to the network. The communication unit 73 may include at least one of the communication modules, such as an internet module and a mobile communication module. The communication unit 73 may receive various types of data such as learning data, algorithm updates and the like from the server.

The control unit 60 may update the memory 78 by processing various data received by the communication unit 73. For example, when data inputs by the communication unit 73 are updated data for an operation program previously stored in the memory 78, the control unit 60 may update the memory 78 by using the updated data. In addition, when the input data is a new operation program, the control unit 60 may further store the new operation program in the memory 78.

Machine learning means that a computer learns from data and solves a problem on its own without a human directly instructing a logic to the computer.

Deep Learning is an artificial intelligence technology that teaches a computer a human's way of thinking based on an artificial neural network (ANN) to construct artificial intelligence, so that the computer learns by itself like a human. The artificial neural network (ANN) may be implemented in a form of software or in a form of hardware such as a chip.

For example, the washing machine processes current values detected by the current detecting unit 75 based on machine learning, and thus may recognize a characteristic of laundry (clothes) put in the washing tub 4 (hereinafter, referred to as a clothes characteristic).

Such clothes characteristic may include an amount and a quality of clothes.

The control unit 60 may determine a quality for each amount of clothes based on machine learning. For example, the control unit 60 may obtain an amount of clothes and determine which of categories previously classified according to the quality of clothes the amount of clothes belongs to. Such quality of clothes may be defined based on several factors such as a material, a degree of softness (e.g., soft clothes/hard clothes), an ability of the clothes to hold water (i.e., moisture content), and a difference in volume between dry clothes and wet clothes.

The control unit 60 may detect an amount of clothes by using a current value currently detected by the current detecting unit 75 by a time reaching the target velocity as input data of the artificial neural network that has been previously learned by machine learning.

In addition, the control unit 60 may determine (predict, estimate or calculate) various types of information related to an unbalance of the washing tub 4 of the present disclosure by using the artificial neural network (ANN) learned by machine learning.

For example, the control unit 60 inputs the plurality of types of data described above into the artificial neural network (ANN) as an input value to calculate information on a UB pattern (UB trend) predicting whether the UB of the washing tub 4 will be increased, decreased or maintained in the future as a result value. Afterwards, the control unit 60 may accelerate, maintain or decelerate the washing tub 4 based on the calculated UB pattern (or type of UB pattern).

Hereinafter, the UB detecting unit 77 to measure a UB of the washing tub 4 of the present disclosure will be described in more detail.

The UB detecting unit 77 may measure an unbalance (UB) of the washing tub 4 occurred when the washing tub 4 containing clothes rotates. Here, the unbalance of the washing tub 4 may refer to a shaking of the washing tub 4 or a shaking value (or shaking degree) of the washing tub 4.

The UB detecting unit 77 may measure (calculate) the shaking value (or shaking degree) of the washing tub 4 (or drum). Here, the shaking value of the washing tub 4 may be named as UB value, UB amount, unbalance value, unbalance amount or eccentric amount.

The UB (UnBalance) herein may refer to an eccentric amount of the washing tub 4, that is, unbalance of the washing tub 4 or shaking of the washing tub 4.

The UB value is a value to indicate a magnitude (or degree) of the shaking of the washing tub 4, and may be calculated based on a change amount in rotation velocity of the washing tub 4 (or the motor 9) or a change amount in acceleration of the washing tub 4.

For example, the UB detecting unit 77 may calculate the UB value by receiving a rotation velocity value of the washing tub 4 (or the motor 9) measured by the velocity detecting unit 74, and using a change amount of the received rotation velocity value. Here, the change amount in rotation velocity, for example, may refer to a difference between rotation velocities measured at every predetermined time, or a difference between rotation velocities measured each time the washing tub 4 is rotated by a predetermined angle, or a difference between a maximum rotation velocity and a minimum rotation velocity.

For example, the UB detecting unit 77 may measure the rotation velocity of the washing tub 4 measured by the velocity detecting unit 74 at each predetermined angle, and measure an acceleration by a difference in the measured rotation velocities. Thereafter, the UB detecting unit 77 may calculate the UB value by using a value corresponding to an acceleration difference obtained by subtracting a minimum acceleration from a maximum acceleration among the measured acceleration values.

For example, the UB value may refer to a predetermined value proportional to the change amount in rotation velocity or a predetermined value proportional to the acceleration difference.

The UB value may be calculated based on not only the rotation velocity of the washing tub but also a difference in current value applied to the motor or a difference in vibration value of the water storage tank 3 measured by the vibration sensor.

The UB of the washing tub 4 may be determined or changed based on a state of the clothes (or clothes characteristic) inserted into the washing tub 4 (e.g., an amount of clothes, a quality of clothes, a bunched degree of clothes, a state in which clothes are disposed, a moisture content of clothes, etc.).

For example, when the clothes are all disposed at one side in the washing tub 4 or when the clothes are stuck together, a balance becomes poor (i.e., an unbalance becomes severe), and thus, a shaking of the washing tub due to the rotation of the washing tub becomes greater and the UB value also becomes greater.

When the shaking of the washing tub becomes greater (the UB value of the washing tub becomes greater), a large current load is applied to the motor 9 for a high-velocity rotation of the washing tub 4 in the dehydration stroke, resulting in high energy consumption and noise.

On the contrary, in a case where the clothes are uniformly disposed in the washing tub 4 or bunching of the clothes is little, the balance gets better. Accordingly, even if the washing tub is rotated at a high velocity, the shaking of the washing tub is reduced, and the UB value is also reduced.

The washing machine according to an embodiment of the present disclosure may perform the clothes dispersion process reducing the UB value to reduce energy consumption and noise in the dehydration stroke.

The clothes dispersion process refers to a process to uniformly dispose the clothes inserted into the washing tub 4 or to disperse bunched clothes. When the clothes are uniformly disposed or when the bunched clothes are dispersed, the unbalance of the washing tub 4 is reduced.

The present disclosure may provide a washing machine and a method for controlling the same to perform an optimized dehydration stroke to reduce the unbalance of the washing tub 4.

Hereinafter, an optimized control method for performing the clothes dispersion process to reduce the unbalance of the washing tub in the dehydration stroke will be described in more detail with reference to the accompanying drawings.

FIG. 3 is a view illustrating the related art dehydration stroke process, and FIG. 4 is a view illustrating the dehydration stroke process according to an embodiment of the present disclosure.

The present disclosure may provide a control method for reducing the unbalance of the washing tub 4 so as to shorten the dehydration time duration when performing the dehydration stroke, after the washing stroke and the rinsing stroke. In order to reduce the unbalance of the washing tub 4, the clothes dispersion process to disperse the clothes may be proceeded.

First, referring to FIG. 3, in a case of the related art, the control unit 60 may maintain the rotation of the washing tub 4 at a first rotation velocity V1 dispersing the clothes, after passing through a first section T1 determining an amount of clothes and a second section T2 accelerating the washing tub 4 at the first rotation velocity.

A section T3 in which the rotation of the washing tub 4 is maintained at the first rotation velocity V1 may be referred to as a clothes dispersion controlling section or a first rotation velocity maintaining section S1.

In the maintaining section S1 in which the washing tub 4 is maintained at the first rotation velocity V1 in one direction, the clothes may be dispersed by being raised up by a predetermined height then falling.

For example, the clothes accommodated in the washing tub 4 may be raised up by a predetermined height by the lifter 20 provided in the washing tub 4 when the washing tub 4 is rotated. Thereafter, the clothes fall by gravity.

That is, when the rotation velocity of the washing tub 4 is the first rotation velocity V1, the clothes may flow. Accordingly, the clothes may be dispersed by maintaining the rotation velocity of the washing tub 4 at the first rotation velocity V1, and by the rise and fall of the clothes (flow of the clothes).

For example, the first rotation velocity V1 may be set to a velocity in a range between 60 rpm and 65 rpm (revolution per minute).

In the related art, in the maintaining section T3 in which the rotation of the washing tub 4 is maintained S1 at the first rotation velocity V1, the control unit 60 measured a shaking value (i.e., UB value) of the washing tub 4 generated by the rise and fall of the clothes.

A method for measuring the UB value will be replaced with the above description.

For example, when a bunch of clothes is big, the UB value is measured big, and when the bunch of clothes is small (i.e., the clothes are made of a material easily dispersed), the UB value is measured small. Here, the UB value may refer to one value (i.e., instantaneous value) measured at any one moment.

In addition, in the related art, 3 types of controls in which the rotation of the washing tub 4 is maintained [S1], accelerated [S2], or stopped [S3] have been performed based on the UB value at any one moment measured in the maintaining section T3.

For example, the washing machine may accelerate the washing tub 4 to be rotated at a second rotation velocity faster than the first rotation velocity, when the UB value at any one moment measured in the maintaining section T3 is smaller than a preset first reference value.

Here, a section that accelerates the rotation velocity of the washing tub 4 from the first rotation velocity to the second rotation velocity may be referred to as a second rotation velocity accelerating section or an accelerating section T4.

When the UB value at any one moment measured in the maintaining section T3 is a value between the first reference value and a preset second reference value that is greater than the first reference value, the washing machine may maintain [S1] the washing tub 4 to be rotated at the first rotation velocity. In this case, a duration of the maintaining section T3 may be extended.

The washing machine may short-circuit the rotation of the washing tub 4 to stop the rotation of the washing tub 4 when the UB value at any one moment measured in the maintaining section T3 is greater than the preset second reference value. In this case, the washing tub 4 may stop the rotation and restart the dehydration stroke from an initial stage of the dehydration stroke (e.g., clothes amount detecting section T1).

The first reference value and the second reference value may be preset for each amount of clothes.

That is, short-circuiting the rotation of the washing tub 4 may include pausing (stopping) the rotation of the washing tub 4 or initializing the dehydration stroke.

In addition, the washing machine measures a UB value at any one moment in the accelerating section T4 accelerating the rotation velocity of the washing tub 4 from the first rotation velocity to the second rotation velocity, and short-circuits [S4] the rotation of the washing tub 4 when the measured UB value exceeds a preset third reference value. The third reference value may be preset for each rotation velocity at which the amount of clothes or the UB value is measured.

On the other hand, when the washing tub 4 is rotated at the second rotation velocity V2, the clothes may be stuck to the washing tub 4 and not fall. That is, the second rotation velocity may be a minimum velocity at which the clothes are stuck to the washing tub 4 and not fall by centrifugal force. For example, the second rotation velocity may be 108 rpm.

In the accelerating section T4 accelerating from the first rotation velocity to the second rotation velocity, a portion of the clothes may be raised up by a predetermined height and then fall. However, as the rotation velocity of the washing tub gets closer to the second rotation velocity, a number of clothes falling is reduced.

Thereafter, the washing machine measures the UB value in the second rotation velocity maintaining section T5 in which the second rotation velocity is maintained, and when the measured UB value is less than or equal to a preset reference value associated with the second rotation velocity, the washing machine may rotate the washing tub 4 at a maximum rotation velocity Vmax in an accelerating section T6. Sections from the second rotation velocity maintaining section T5, via the accelerating section T6, to a maintaining section T7 in which the rotation is maintained at the maximum rotation velocity Vmax may be referred to as a fast dehydration process. Then, after the rotation of the washing tub is maintained at the maximum rotation velocity for a predetermined time, the dehydration stroke is terminated T8.

Meanwhile, in the related art, since only a case where the washing tub 4 was accelerated to rotate at the second rotation velocity or short-circuited in the second rotation velocity accelerating section T4 was included, the clothes were not properly dispersed in the accelerating section. In the second rotation velocity accelerating section T4, an operation in which the clothes were gradually stuck to the washing tub 4 by the acceleration of the washing tub 4 was performed. Accordingly, it was difficult to classify the accelerating section T4 into a section in which the clothes dispersion was performed.

In addition, only 3 types of operations in which an operation maintaining the rotation velocity of the washing tub 4 at a first rotation velocity in the maintaining section T3 [S1], an operation accelerating up to the second rotation velocity [S2], and an operation short-circuiting the rotation of the washing tub [S3, S4] in the clothes dispersion process could be performed in the related art.

That is, in the related art, a control operation to decelerate the rotation velocity of the washing tub was not performed in the clothes dispersion process.

In addition, in the related art, since whether or not the rotation of the washing tub 4 was short-circuited was determined only by using the UB value at any one moment, a malfunction of short-circuiting the rotation of the washing tub was occurred even in a situation where the short-circuiting was not necessary due to the UB value measured by an error.

On the other hand, referring to FIG. 4, the control method of the washing machine according to an embodiment of the present disclosure may provide a control method for performing the clothes dispersion even in the second rotation velocity accelerating section T4 accelerating the rotation velocity of the washing tub 4 from the first rotation velocity V1 to the second rotation velocity V2.

Specifically, the control unit 60 may perform not only an operation accelerating the washing tub 4 to perform the clothes dispersion in the second rotation velocity accelerating section T4 [S5, S8], but also an operation maintaining the rotation velocity of the washing tub 4 [S7] or an operation reducing the rotation velocity of the washing tub 4 [S6]. That is, compared with the related art, the control unit 60 of the present disclosure may further perform not only an acceleration control but also a maintenance control and a deceleration control in the second rotation velocity accelerating section T4.

In addition, the control unit 60, when the UB value measured while accelerating the washing tub in the second rotation velocity accelerating section T4 exceeds a preset reference value, may also perform a short-circuit control to short-circuit the rotation of the washing tub [S9] in the present disclosure.

Accordingly, not only the first rotation velocity maintaining section T3 but also the second rotation velocity accelerating section T4 may be defined as a clothes dispersion controlling section performing the clothes dispersion.

In addition, the present disclosure may significantly reduce dehydration stroke time duration by performing the clothes dispersion even in the second rotation velocity accelerating section T4 to reduce a number of times the rotation of the washing tub 4 is short-circuited, and also may reduce energy consumed by the short circuit of the rotation of the washing tub 4.

In addition, the control unit 60 of the present disclosure may rotate the washing tub 4 in a predetermined manner, based on a UB pattern output by measuring a plurality of types of data at every predetermined time without relying on one UB value measured at any one moment and inputting the measured plurality of types of data into an artificial neural network previously learned by machine learning.

This may result in preventing a malfunction of the washing tub 4 that occurs when accelerating or short-circuiting the washing tub 4 by relying on one type of UB value measured at any one moment and the measured UB value corresponds to an error value, thereby significantly reducing the dehydration stroke time duration in the present disclosure.

Hereinafter, the control method of the washing machine according to an embodiment of the present disclosure described above will be described in more detail with reference to the accompanying drawings.

FIG. 5 is a flowchart illustrating a representative control method according to the present disclosure, and FIGS. 6, 7, and 8 are conceptual views illustrating the control method illustrated in FIG. 5.

First, the washing machine according to an embodiment of the present disclosure may include the washing tub 4 accommodating clothes (laundry) therein and rotatably installed, the motor 9 rotating the washing tub, and the control unit 60 controlling the motor 9 to rotate the washing tub 4.

Referring to FIG. 5, the control unit 60 rotates the washing tub 4 at a first velocity (the first rotation velocity V1) after detecting the amount of clothes [S10] upon starting the dehydration stroke.

Specifically, the control unit 60 may rotate the washing tub 4 at the first rotation velocity V1 so that the clothes accommodated in the washing tub 4 are uniformly disposed in the dehydration stroke and the bunched clothes are released (i.e., the clothes are dispersed).

Here, the clothes dispersion may be performed in a way that the clothes accommodated in the washing tub 4 are raised up by a predetermined height then fall by the rotation of the washing tub 4 in the maintaining section in which the rotation of the washing tub 4 is maintained at the first rotation velocity V1.

The control unit 60 may measure the UB value while the washing tub 4 is rotated at the first rotation velocity V1 [S20]. Specifically, the control unit 60, when a flow in which the clothes are raised up by a predetermined height then fall occurs, may measure the shaking value (i.e., UB value) of the washing tub 4 generated by the flow.

Measuring (calculating) of the UB value will be replaced with the above description.

The control unit 60 may determine whether or not the measured UB value is equal to or greater than a preset reference value [S30]. Here, when the measured UB value is greater than the preset reference value, the control unit 60 may short-circuit the rotation of the washing tub 4 (or the rotation of the motor 9) [S40].

The preset reference value may refer to a limit of the UB value (or allowable UB value) to go to a next dehydration process at the first rotation velocity. The preset reference value is a reference value set for the first rotation velocity and may vary depending on the amount or quality of the clothes.

When the rotation of the washing tub 4 is short-circuited as described above, the rotation of the washing tub 4 is stopped, and the control unit 60 may restart the dehydration stroke from beginning. That is, short-circuiting the rotation of the washing tub 4 may refer to initializing the dehydration process to start again from the beginning.

On the other hand, when the measured UB value is smaller (less) than the preset reference value, the control unit 60 may start accelerating the washing tub 4 so that the washing tub 4 rotates at a second velocity (the second rotation velocity V2) which is faster than the first velocity (the first rotation velocity V1) [S50].

When the washing tub 4 is rotated at the second rotation velocity V2, the clothes may be stuck to the washing tub 4 and not fall. That is, the second rotation velocity may be a minimum velocity at which the clothes are stuck to the washing tub 4 and not fall by centrifugal force. For example, the second rotation velocity may be of 108 rpm.

In the second accelerating section T4, which accelerates from the first rotation velocity (e.g., 60 rpm) to the second rotation velocity (e.g., 108 rpm), a portion of the clothes may be raised up by a predetermined height and then fall. However, as the rotation velocity of the washing tub gets closer to the second rotation velocity, the number of clothes falling is reduced.

When the UB value measured at the first rotation velocity V1 is smaller than the preset reference value, the control unit 60 may put the washing tub 4 into the accelerating section T4 accelerating the washing tub 4 by up to the second rotation velocity V2. The accelerating section T4 may be referred to as the second rotation velocity accelerating section T4.

The clothes dispersion may be performed by the clothes being raised up by a predetermined height then fall, in the maintaining section T3 maintaining the rotation velocity of the washing tub 4 at the first rotation velocity and in the accelerating section accelerating the rotation velocity of the washing tub 4 from the first rotation velocity V1 to the second rotation velocity V2. Accordingly, the unbalance of the washing tub 4 may be solved to some extent.

That is, the clothes dispersion is performed before the rotation velocity of the washing tub 4 reaches the second rotation velocity V2, and when the rotation velocity of the washing tub 4 reaches the second rotation velocity V2, the clothes are stuck to the washing tub 4, and this may hinder the clothes dispersion from being performed.

The present disclosure may perform various controls so that the clothes dispersion is performed even in the accelerating section T4 accelerating the rotation velocity up to the second rotating velocity V2, before the rotation velocity of the washing tub 4 reaches the second rotation velocity V2.

That is, the control unit 60 of the present disclosure may perform not only the acceleration or short-circuit of the washing tub but also the maintenance or deceleration of the rotation velocity of the washing tub, so that the clothes dispersion is performed in the second rotation velocity accelerating section T4 (i.e., while the washing tub accelerates from the first rotation velocity to the second rotation velocity).

As such, in order to perform not only the acceleration or short-circuit but also the maintenance or deceleration control of the washing tub, the control unit 60 may measure (calculate) a plurality of types of data previously set while the washing tub 4 accelerates from the first rotation velocity (the first velocity) to the second rotation velocity V2 which is faster than the first rotation velocity [S60].

The preset plurality of types of data may be data related to the rotation of the washing tub. For example, the preset plurality of types of data may be measured (calculated) by the velocity detecting unit 74, the current detecting unit 75, the vibration detecting unit 76, and the UB detecting unit 77 described above.

The preset plurality of types of data may include a rotation velocity value (or velocity value) of the washing tub 4 measured by the velocity detecting unit 74, a current value applied to the motor 9 measured by the current detecting unit 75, a vibration value of the water storage tank 3 measured by the vibration detecting unit 76, and the shaking value (UB value) of the washing tub 4 measured by the UB detecting unit 77.

The plurality of types of data may refer to data related to the UB (unbalance) of the washing tub 4, data to measure the UB of the washing tub 4, data generated by the rotation of the washing tub 4, and the like. The plurality of types of data may be used to control the washing tub 4 in the dehydration stroke.

For example, the plurality of types of data may be input as an input value of an artificial neural network learned by machine learning to calculate a UB pattern used to determine acceleration, deceleration or maintenance of the washing tub 4 in the dehydration stroke as an output value.

Here, the control unit 60 of the present disclosure does not measure only one type of data (UB value) measured at any one time, but may use an average value for a predetermined time as the plurality of types of data.

In addition, the control unit 60 may calculate the plurality of types of data at every predetermined time in the accelerating section in which the washing tub 4 accelerates from the first rotation velocity V1 to the second rotation velocity V2.

For example, referring to FIG. 6, the control unit 60 may calculate an average value of UB values for a predetermined time d1 as one of a plurality of types of data. Here, the predetermined time d1 refers to a predetermined time interval, not any one moment. For example, the predetermined time d1 may be set to about 1 second.

The control unit 60 may calculate an average value of the UB values by averaging the UB values measured during the predetermined time d1, and determine the calculated average value of the UB values as any one of the plurality of types of data.

Although not illustrated, as in FIG. 6, the control unit 60 may determine an average value of rotation velocity values of the washing tub measured for the predetermined time d1, an average value of current values applied to the motor 9 measured for the predetermined time d1, and an average value of vibration values measured by the vibration sensor for the predetermined time d1 as at least one of the plurality of types of data.

That is, the plurality of types of data may include at least one among an average value of UB values for a predetermined time d1, an average value of rotation velocity values of the washing tub for the predetermined time d1, an average value of current values applied to the motor for the predetermined time d1, and an average value of vibration values measured by the vibration sensor for the predetermined time d1.

Then, the control unit 60 may input the plurality of types of data as input values of the pre-learned artificial neural network, and calculate an expected UB pattern as a result value [S70].

Here, the control unit 60 inputs the plurality of types of data described above into the artificial neural network (ANN) as an input value to calculate information on a UB pattern (UB trend) predicting whether the UB of the washing tub 4 will be increased, decreased or maintained in the future as a result value.

Here, the UB pattern may refer to information indicating the UB trend indicating whether the UB (or UB value) of the washing tub 4 is to be increased, maintained or decreased.

The expected UB pattern may include a UB increase pattern indicating a pattern in which the UB is to be increased, a UB maintenance pattern indicating a pattern in which the UB is to be maintained, and a UB decrease pattern indicating a pattern in which the UB is to be decreased.

Thereafter, the control unit 60 may accelerate, maintain, or decelerate the rotation velocity of the washing tub 4, based on the calculated UB pattern (or a type of UB pattern) [S80 to S110]. That is, the control unit 60 may control the motor 9 to rotate the washing tub 4 in a predetermined manner based on the type of the calculated UB pattern.

Rotating the washing tub 4 in a predetermined manner may include accelerating the rotation velocity of the washing tub 4, maintaining the rotation velocity of the washing tub, and decelerating the rotation velocity of the washing tub. In addition, rotating the washing tub 4 in a predetermined manner may also include short-circuiting the rotation of the washing tub 4.

The UB maintenance pattern may refer to trend information indicating a pattern in which the UB is maintained even when the rotation velocity of the washing tub 4 increases. When the expected UB pattern is the UB maintenance pattern, the control unit 60 may predict (decide or determine) that the UB will continue to be maintained even if the rotation velocity of the washing tub 4 increases [S80]. In this case, the control unit 60 may perform the clothes dispersion by maintaining the rotation velocity of the washing tub 4 at a rotation velocity at a time when the UB pattern is calculated (e.g., any rotation velocity slower than the second rotation velocity V2) [S90].

The UB increase pattern may refer to trend information indicating a pattern in which the UB increases as the rotation velocity of the washing tub 4 increases. For example, the UB may increase when the rotation velocity of the washing tub 4 increases in a state where the clothes are bunched together at a current rotation velocity. That is, when an expected UB pattern is the UB increase pattern, the control unit 60 may predict (decide) that the UB will increase as the rotation velocity of the washing tub 4 becomes faster, and decelerate the rotation velocity of the washing tub 4 [S80, S100]. Accordingly, the control unit 60 of the present disclosure may control the rotation velocity of the washing tub 4 to be slower than the rotation velocity at a time when the UB pattern is measured to perform the clothes dispersion with certainty in the second rotation velocity accelerating section T4, thereby reducing the UB.

The UB decrease pattern may refer to trend information indicating a pattern in which the UB decreases as the rotation velocity of the washing tub 4 increases. For example, when dehydration proceeds as the rotation velocity of the washing tub 4 increases, the UB may decrease. That is, when an expected UB pattern is the UB decrease pattern, the control unit 60 may accelerate the washing tub 4 so that the rotation velocity of the washing tub 4 reaches the second rotation velocity V2 [S80, S110].

On the other hand, the present disclosure may include the artificial neural network (ANN) to calculate the expected UB pattern as a result value. Information on the artificial neural network (ANN) may be previously stored in the memory 78 or the control unit 60.

FIG. 7 is a schematic diagram illustrating an example of the artificial neural network.

Deep learning, a kind of machine learning, may refer to learning down to deep levels in multiple stages based on data.

Deep learning may represent a set of machine learning algorithms that extract key data from a plurality of data while sequentially passing through hidden layers.

A deep learning structure may include the artificial neural network (ANN). For example, the deep learning structure may be configured as a deep neural network (DNN) such as a convolutional neural network (CNN), a recurrent neural network (RNN), and a deep belief network (DBN).

Referring to FIG. 7, the artificial neural network (ANN) may include an input layer, a hidden layer, and an output layer. Having multiple hidden layers is called the deep neural network (DNN). Each layer includes a plurality of nodes, and each layer is associated with a next layer. The nodes may be connected to each other with a weight.

An output from any node belonging to a first hidden layer (Hidden Layer 1) is an input to at least one node belonging to a second hidden layer (Hidden Layer 2). Here, an input of each node may be a value to which the weight is applied to an output of the node of a previous layer. The weight may refer to a connection strength between nodes. Deep learning process may also be seen as a process finding a proper weight.

The artificial neural network (ANN) applied to the washing machine according to an embodiment of the present disclosure may refer to the deep neural network (DNN) learned by supervised learning by using the plurality of types of data (average velocity value, average current value, average vibration value, and average UB value) described above as input data, and a UB pattern measured by an experiment as result data.

The supervised learning may refer to a method of machine learning to infer one function from training data.

The artificial neural network (ANN) of the present disclosure may refer to the deep neural network (DNN) in which the hidden layer is learned by experimentally measuring a type of UB pattern (UB trend) for each of the plurality of types of data (UB increase pattern, UB maintenance pattern, and UB decrease pattern), and by inputting each of the plurality of types of data as input data and a UB pattern measured for each of the plurality of types of data as a result value. Here, the expression “the hidden layer is learned” may refer to adjusting (updating) the weight of a connection line between nodes included in the hidden layer.

Using such artificial neural network (ANN), the control unit 60 of the present disclosure may calculate (predict, determine or estimate) an expected UB pattern (UB increase pattern, UB maintenance pattern, and UB decrease pattern) by calculating a plurality of types of data at some point in time, and using the plurality of types of data into the artificial neural network as an input value.

The control unit 60 may perform learning by using a plurality of types of data corresponding to an average rotation velocity value, an average current value, an average vibration value, and an average UB value as training data. That is, the control unit 60 may update the deep neural network (DNN) structure such as the weight or a bias by adding a determined result each time the expected UB pattern is recognized or determined and the plurality of types of data input at that time to the database. In addition, the control unit 60 may update the deep neural network (DNN) structure such as the weight by performing the supervised learning process with acquired training data after acquiring a predetermined number of times of training data.

In addition, as illustrated in FIG. 6, the control unit 60 may measure (calculate) the plurality of types of data every predetermined time T′ in the accelerating section in which the washing tub 4 accelerates from the first rotation velocity V1 to the second rotation velocity V2.

The control unit 60 may measure (calculate) the plurality of types of data every predetermined time T′, and may determine a method for controlling the washing tub 4 by using the plurality of types of data.

Here, the control unit 60 may determine whether to accelerate, decelerate or maintain the rotation velocity of the washing tub 4 at every predetermined time T′, based on the type of UB pattern calculated through the artificial neural network by measuring the plurality of types of data at every predetermined time T′ and using the calculated plurality of types of data.

As described above, the calculated UB pattern (i.e., expected UB pattern) may include the UB increase pattern in which the UB value is expected to increase, the UB maintenance pattern in which the UB value is expected to maintain, and the UB decrease pattern in which the UB value is expected to decrease.

The control unit 60 may calculate the plurality of types of data at every predetermined time T′ (i.e., data corresponding to an average value for a predetermined time d1) and input the calculated plurality of types of data into the pre-learned artificial neural network (ANN) as an input value to calculate the expected UB pattern as a result value.

The control unit 60, when the calculated UB pattern is the UB increase pattern in which the UB value is expected to increase, may decrease the rotation velocity of the washing tub 4 [S80, S100]. For example, the control unit 60, when the UB pattern calculated by inputting the plurality of types of data into the artificial neural network is the UB increase pattern in which the UB value increases when accelerating the washing tub 4 to rotate at the second rotation velocity V2, may decrease the rotation velocity of the washing tub 4 [S100].

The control unit 60, when the calculated UB pattern is the UB decrease pattern in which the UB value is expected to decrease, may increase (accelerate) the rotation velocity of the washing tub 4 [S80, S110]. For example, the control unit 60, when the UB pattern calculated by inputting the plurality of types of data into the artificial neural network is the UB decrease pattern in which the UB value decreases when accelerating the washing tub 4 to be rotated at the second rotation velocity V2, may increase (accelerate) the rotation velocity of the washing tub 4 [S110].

The control unit 60, when the calculated UB pattern is the UB maintenance pattern in which the UB value is expected to maintain, may maintain the rotation velocity of the washing tub 4. For example, the control unit 60, when the UB pattern calculated by inputting the plurality of types of data into the artificial neural network is the UB maintenance pattern in which the UB value maintains when accelerating the washing tub 4 to be rotated at the second rotation velocity V2, may maintain the rotation at the rotation velocity at a time when the plurality of types of data is measured [S90].

Then, the control unit 60 of the present disclosure may determine whether the rotation velocity of the washing tub 4 reaches the second rotation velocity V2 [S120].

When the rotation velocity of the washing tub 4 fails to reach the second rotation velocity V2, the control unit 60 may return to the step [S60] at every predetermined time T′.

That is, the control unit 60 may calculate (measure) the plurality of types of data for a predetermined time at every predetermined time T′, calculate the UB pattern by inputting the calculated plurality of types of data into the artificial neural network as an input value, and control the rotation of the washing tub 4 in a preset manner based on the calculated UB pattern.

As such, a series of processes (e.g., S50 to S120) performed in the second rotation velocity accelerating section T4 may be referred to as an intelligent clothes dispersing process.

The control unit 60, when the rotation velocity of the washing tub 4 reaches the second rotation velocity V2, may end the intelligent clothes dispersing process and start a fast dehydration process [S130].

The fast dehydration process may refer to a process proceeding the dehydration by rotating the washing tub 4 at a maximum rotation velocity Vmax when the UB value measured at the second rotation velocity V2 does not exceed the reference value (see T5 to T8 and FIGS. 3 and 4).

Here, the reference value may be an UB value allowed to enter the next dehydration process at the second rotation velocity V2, and may vary depending on the amount or quality of the clothes.

Meanwhile, the control unit 60, when the UB value measured in the accelerating section T4 in which the washing tub 4 accelerates from the first rotation velocity V1 to the second rotation velocity V2 exceeds the reference value, may short-circuit the rotation of the washing tub 4.

That is, the control unit 60 may perform a control to short-circuit the rotation of the washing tub 4 when the UB value calculated in the accelerating section T4 exceeds the reference value, in addition to the operations accelerating, decelerating or maintaining the rotation velocity of the washing tub 4 based on the plurality of types of data in the accelerating section T4. Here, the measured UB value may refer to an average UB value measured for a predetermined time d1.

Here, the reference value may refer to an allowable UB value set in the accelerating section T4, and may have a different reference value for each rotation velocity (or a predetermined rotation velocity section) of the washing tub 4, or may have a different reference value for the amount or quality of the clothes.

Meanwhile, the control unit 60, when the washing tub 4 fails to reach the second rotation velocity within a predetermined time since a time when starting an acceleration from the first rotation velocity V1 to the second rotation velocity V2, may short-circuit the rotation of the washing tub 4.

Specifically, the control unit 60, when the washing tub 4 fails to reach the second rotation velocity within the predetermined time (e.g., 300 seconds) in the accelerating section T4 in which the washing tub 4 accelerates from the first rotation velocity V1 to the second rotation velocity V2 (i.e., when the washing tub 4 fails to enter the second rotation velocity maintaining section T5 within the predetermined time), may short-circuit the rotation of the washing tub 4 and restart the dehydration process from the beginning.

When a duration time of the accelerating section T4 in which the washing tub 4 accelerates from the first rotation velocity V1 to the second rotation velocity V2 exceeds the predetermined time, the control unit 60 may short-circuit the rotation of the washing tub 4.

For example, the control unit 60 may perform a control to accelerate, decelerate or maintain the rotation velocity of the washing tub 4 based on the UB pattern calculated by using the plurality of types of data measured at every predetermined time in the accelerating section T4 as an input value. Here, the control unit 60, when the washing tub 4 fails to reach the second rotation velocity V2 within the predetermined time, may perform the clothes dispersion again from the beginning by starting the dehydration process from the beginning. Accordingly, the present disclosure may reduce the noise at a highest rotation velocity by entering the fast dehydration process after a more perfect clothes dispersion is performed.

As another example, when the washing tub 4 fails to reach the second rotation velocity V2 within the predetermined time by the control in the accelerating section T4, the control unit 60 may accelerate the rotation velocity of the washing tub 4 rather than short-circuit the rotation of the washing tub 4 based on the elapse of the predetermined time, so that the rotation velocity of the washing tub 4 reaches the second rotation velocity. Accordingly, the present disclosure may prevent the dehydration stroke time from being continuously prolonged.

Meanwhile, the control unit 60 of the present disclosure may apply the details described in FIGS. 5 to 7 to the first rotation velocity maintaining section T3 in the same/like manner.

For example, the control unit 60 may calculate (measure) the plurality of types of data at every predetermined time T′ in the first rotation velocity maintaining section T3.

The plurality of types of data may refer to average values of data measured for a predetermined time d1, for example, an average rotation velocity value of the washing tub, an average value of current applied to the motor, an average vibration value of the water storage tank, and an average UB value of the washing tub.

The control unit 60 may calculate an expected UB pattern as a result value by inputting the plurality of types of data measured in the first rotation velocity maintaining section T3 into the pre-learned artificial neural network as an input value.

Thereafter, the control unit 60 may enter the second rotation velocity accelerating section T4 based on the calculation of the UB pattern. Here, the control unit 60 may determine whether to accelerate, decelerate or maintain the rotation velocity of the washing tub 4 based on the calculated UB pattern when entering the second rotation velocity accelerating section T4.

That is, when the UB pattern calculated in the first rotation velocity maintaining section T3 is the UB increase pattern, the control unit 60 may enter the second rotation velocity accelerating section T4 while reducing the rotation velocity of the washing tub 4.

The control unit 60, when the UB pattern calculated in the first rotation velocity maintaining section T3 is the UB decrease pattern, may enter the second rotation velocity accelerating section T4 while accelerating the rotation velocity of the washing tub 4.

However, the control unit 60 may maintain the rotation velocity of the washing tub 4 at the first rotation velocity when the UB pattern calculated in the first rotation velocity maintaining section T3 is the UB maintenance pattern. Here, the first rotation velocity maintaining section T3 may be continuously maintained.

After a predetermined time T′ has elapsed, the control unit 60 may measure (calculate) the plurality of types of data again in the first rotation velocity maintaining section T3 and recalculate the UB pattern by inputting the same into the pre-learned artificial neural network. Thereafter, the control unit 60 may accelerate, decelerate, or maintain the rotation velocity of the washing tub 4 based on the recalculated UB pattern.

Meanwhile, so as not to stay in the first rotation velocity maintaining section T3 when the UB value measured in the first rotation velocity maintaining section T3 does not exceed a predetermined reference value but the calculated and recalculated UB pattern is still the UB maintenance pattern, the control unit 60 may start acceleration so that the washing tub 4 accelerates by the second rotation velocity V2 based on the elapse of the predetermined time (i.e., the washing tub 4 may enter the second rotation velocity accelerating section T4).

As such, a control method carried out in the intelligent clothes dispersing process [S60 to S110] performed in the second rotation velocity accelerating section T4 of the present disclosure may also be applied in the same/like manner to the first rotation velocity maintaining section T3.

The intelligent clothes dispersing process according to an embodiment of the present disclosure described above will be more clearly understood by FIG. 8.

Referring to FIG. 8, the control unit 60 of the present disclosure may enter the first rotation velocity maintaining section T3 in which the washing tub 4 maintains the rotation velocity at the first rotation velocity V1, so that the clothes dispersion is performed upon entering the dehydration stroke.

In the first rotation velocity maintaining section T3, the clothes dispersion may be performed in a way that the clothes accommodated in the washing tub 4 are raised up by a predetermined height then fall.

When the UB value measured in the first rotation velocity maintaining section T3 does not exceed (is less than or equal to) a reference value, the control unit 60 may enter the second rotation velocity accelerating section T4 so as to make the washing tub 4 to rotate at the second rotation velocity V2 which is faster than the first rotation velocity V1.

Here, the control unit 60 may measure the plurality of types of data at every predetermined time T′ in the accelerating section T4 in which the washing tub 4 accelerates from the first rotation velocity V1 to the second rotation velocity V2.

Here, the plurality of types of data may be an average value of data measured for a predetermined time (d1, see FIG. 6), not a value measured at any one moment, and may include an average rotation velocity value of the washing tub, an average value of current applied to the motor, an average vibration value of the water storage tank 3, and an average UB value of the washing tub 4.

The control unit 60 may calculate an expected UB pattern by measuring the plurality of types of data at every predetermined time T′ and inputting the calculated plurality of types of data into the pre-learned artificial neural network.

The UB pattern may include the UB increase pattern in which the UB value is expected to increase, the UB maintenance pattern in which the UB value is expected to maintain, and the UB decrease pattern in which the UB value is expected to decrease when the rotation of the washing tub is accelerated.

The control unit 60 may calculate an expected UB pattern by measuring the plurality of types of data preset at a first time point C1 after entering the second rotation velocity accelerating section T4, and inputting the calculated plurality of types of data into the pre-learned artificial neural network.

Here, the control unit 60 may accelerate the rotation velocity of the washing tub 4 when the calculated UB pattern is the UB decrease pattern.

Thereafter, the control unit 60 may calculate the plurality of types of data again at a second time point C2 at which a predetermined time T′ has elapsed. The control unit 60 may calculate an expected UB pattern by inputting the plurality of types of data calculated at the second time point C2 into the pre-learned artificial neural network again.

Here, when the calculated UB pattern is the UB increase pattern, the control unit 60 may reduce the rotation velocity of the washing tub 4.

Afterwards, the control unit 60 may calculate the plurality of types of data again at a third time point C3 and a fourth time point C4 at which a predetermined time T′ has elapsed. When all of the UB patterns calculated by using the plurality of types of data calculated at the third time point C3 and the fourth time point C4 is the UB maintenance pattern, the control unit 60 may maintain the rotation velocity of the washing tub 4 at the second time point (and the third time point).

Thereafter, when the UB pattern calculated by recalculating a plurality of types of data at a fifth time point C5 at which a predetermined time T′ has elapsed since the fourth time point C4 and inputting the calculated plurality of types of data into the pre-learned artificial neural network is the UB decrease pattern, the control unit 60 may increase (accelerate) the rotation velocity of the washing tub 4.

In addition, the control unit 60 may accelerate the washing tub 4 to rotate at the second rotation velocity V2 when the UB value measured in the second rotation velocity accelerating section T4 does not exceed a predetermined reference value but a time duration in which the rotation velocity of the washing tub 4 maintains at a predetermined rotation velocity exceeds a predetermined first time (e.g., 2T′) or a time duration of the second rotation velocity accelerating section T4 exceeds a predetermined time (e.g., 4T′).

The above description may also be applied in the same/like manner to the control method of the washing machine. The control method of the washing machine may be performed by, for example, the control unit 60.

According to embodiments of the present disclosure, there are at least one of the following effects.

First, the present disclosure performs a clothes dispersion not only in a maintaining section in which a washing tub maintains a rotation at a first rotation velocity but also in an accelerating section in which the washing tub accelerates from the first rotation velocity to the second rotation velocity faster than the first rotation velocity to widen a section where the clothes dispersion is performed. This may result in performing an optimized clothes dispersion and thereby reducing a dehydration stroke time.

Second, the present disclosure further performs a control not only accelerating or maintaining but also decelerating the rotation of the washing tub based on a UB pattern predicted in a future by using an artificial neural network learned through machine learning in an accelerating section accelerating from the first rotation velocity to the second rotation velocity. This may reduce a number of dehydration strokes that are short-circuited, and thereby significantly reducing a dehydration stroke time duration.

Third, the present disclosure determines a method for controlling the rotation velocity of the washing tub by using the plurality of types of data measured for a predetermined time rather than using one type of data measured at any one moment to short-circuit the dehydration stroke when one data measured at one moment is an error value, thereby preventing a time duration of the dehydration stroke from being prolonged.

Effects of the present disclosure are not limited to the above-mentioned effects, and other effects that are not mentioned will be clearly understood by those skilled in the art by the claims.

The present disclosure described above can be implemented as computer-readable codes on a program-recorded medium. The computer readable medium includes all kinds of recording devices in which data readable by a computer system is stored. Examples of the computer-readable medium include a hard disk drive (HDD), a solid state disk (SSD), a silicon disk drive (SDD), a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device and the like. In addition, the computer may also include a processor or the control unit. The above detailed description should not be limitedly construed in all aspects and should be considered as illustrative. The scope of the present disclosure should be determined by rational interpretation of the appended claims, and all changes within the scope of equivalents of the present disclosure are included in the scope of the present disclosure.

Claims

1. A washing machine comprising:

a washing tub configured to accommodate clothes and rotatably installed;

a motor configured to rotate the washing tub; and

a control unit configured to control the motor to rotate the washing tub,

wherein the control unit is further configured to:

measure a plurality of types of data previously set while the washing tub accelerates from a first rotation velocity to a second rotation velocity which is faster than the first rotation velocity;

input the plurality of types of data into a pre-learned artificial neural network as an input value and calculate an expected UB pattern as a result value; and

control the motor so that the washing tub is rotated in a preset manner based on a type of the calculated UB pattern.

2. The washing machine of claim 1, wherein a clothes dispersion is performed in a way that the clothes are raised up by a predetermined height then fall in a maintaining section in which a rotation of the washing tub is maintained at the first rotation velocity and in an accelerating section in which the washing tub accelerates from the first rotation velocity to the second rotation velocity.

3. The washing machine of claim 2, wherein the clothes dispersion is performed before a rotation velocity of the washing tub reaches the second rotation velocity, and the clothes are stuck to the washing tub when the rotation velocity of the washing tub reaches the second rotation velocity, and this hinders the clothes dispersion from being performed.

4. The washing machine of claim 1, wherein the plurality of types of data comprises at least one among an average value of UB values for a predetermined time, an average value of rotation velocity values of the washing tub for a predetermined time, an average value of current values applied to the motor for a predetermined time, and an average value of vibration values measured by a vibration sensor for a predetermined time.

5. The washing machine of claim 1, wherein the control unit measures the plurality of types of data at every predetermined time in an accelerating section in which the washing tub accelerates from the first rotation velocity to the second rotation velocity.

6. The washing machine of claim 5, wherein the control unit determines whether to accelerate, decelerate or maintain the rotation velocity of the washing tub at every predetermined time, based on a type of UB pattern calculated through an artificial neural network by measuring the plurality of types of data at every predetermined time and using the calculated plurality of types of data.

7. The washing machine of claim 1, wherein the calculated UB pattern comprises a UB increase pattern in which a UB value is expected to increase, a UB maintenance pattern in which the UB value is expected to maintain, and a UB decrease pattern in which the UB value is expected to decrease.

8. The washing machine of claim 7, wherein the control unit decreases the rotation velocity of the washing tub when the calculated UB pattern is the UB increase pattern in which the UB value is expected to increase.

9. The washing machine of claim 7, wherein the control unit increases the rotation velocity of the washing tub when the calculated UB pattern is the UB decrease pattern in which the UB value is expected to decrease.

10. The washing machine of claim 7, wherein the control unit maintains the rotation velocity of the washing tub when the calculated UB pattern is the UB maintenance pattern in which the UB value is expected to maintain.

11. The washing machine of claim 1, wherein the control unit short-circuits the rotation of the washing tub when the UB value measured in an accelerating section in which the washing tub is accelerated from the first rotation velocity to the second rotation velocity exceeds a preset reference value.

12. The washing machine of claim 1, wherein the control unit short-circuits the rotation of the washing tub when the washing tub fails to reach the second rotation velocity within a predetermined time duration since a time when the washing tub starts accelerating from the first rotation velocity to the second rotation velocity.

13. A method for controlling a washing machine, the method comprising:

measuring a plurality of types of data previously set while a washing tub accelerates from a first rotation velocity to a second rotation velocity which is faster than the first rotation velocity;

inputting the plurality of types of data into a pre-learned artificial neural network as an input value and calculating an expected UB pattern as a result value; and

controlling a motor so that the washing tub is rotated in a preset manner based on a type of the calculated UB pattern.

14. The method of claim 13, wherein the calculated UB pattern comprises a UB increase pattern in which a UB value is expected to increase, a UB maintenance pattern in which the UB value is expected to maintain, and a UB decrease pattern in which the UB value is expected to decrease.

15. The method of claim 14, wherein the controlling decreases the rotation velocity of the washing tub when the calculated UB pattern is the UB increase pattern in which the UB value is expected to increase.

16. The method of claim 14, wherein the controlling increases the rotation velocity of the washing tub when the calculated UB pattern is the UB decrease pattern in which the UB value is expected to decrease.

17. The method of claim 14, wherein the controlling maintains the rotation velocity of the washing tub when the calculated UB pattern is the UB maintenance pattern in which the UB value is expected to maintain.