VIRTUAL SENSOR FOR VIRTUAL ASSET

Abstract

Provided are systems and methods for monitoring a physical asset using virtual sensors sensing data of a virtual asset corresponding to the physical asset. In one example, the method includes executing a virtual model in virtual space, the virtual model including a digital model of a physical asset located in physical space and being executed based on sensor data sensed of an operation of the physical asset, determining a position of a virtual sensor on a structure of the virtual model, sensing an observable attribute of the virtual model in virtual space at the position of the virtual sensor on the structure of the virtual model, the observable attribute of the virtual model in virtual space corresponding to an actual attribute of the physical asset in physical space, and transmitting information about the virtually sensed attribute sensed via the virtual sensor to a system associated with the physical asset.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the benefit under 35 USC § 119(e) of U.S. Provisional Patent Application No. 62/446,033, filed on Jan. 13, 2017, and of U.S. Provisional Patent Application No. 62/446,374, filed on Jan. 14, 2017, filed in the United States Patent and Trademark Office, both of which are incorporated herein by reference for all purposes.

BACKGROUND

The Internet of Things (IoT) provides an integrated network that brings together edge systems with a cloud environment where edge data can be monitored, analyzed, and used to control edge systems. An edge machine may communicate with a physical asset and the cloud platform may generate a simulation or virtual model that mimics the behavior of the physical asset from a remote location. For example, virtual modeling has grown in the fields of energy (e.g., oil platforms, wind turbines, power plants, solar panels, etc.), healthcare (e.g., diagnostic equipment, treatment equipment, etc.), transportation (e.g., aircraft, locomotives, automobiles, etc.) as well as many others. The virtual model, or digital twin, refers to a computerized simulation model of a physical asset such as a machine, equipment, group of machines/equipment, and the like. The virtual model may be generated based on computer animated design (CAD) models, design drawings, construction details, measurements, and the like, of the asset. Also, the virtual model may be calibrated based on sensor data from the asset disposed on the edge. In many cases, the data is obtained from sensors (i.e., hardware) installed on the asset which can measure various parameters such as acceleration, velocity, force, power, movement, and the like. The sensor data can be used to simulate a status, working condition, position, or the like, of the physical asset in virtual space. This pairing of the virtual and physical worlds allows analysis of data and monitoring of physical assets to address problems before they even occur, prevent downtime, develop new opportunities, and plan for the future based on simulations.

The virtual model is often meant to be an up-to-date and accurate digital replica of the properties and states of the physical asset, which may include one or more of shape, position, gesture, status, motion, and the like. However, related art virtual modeling approaches are limited due to the type and location of physical sensor installations within a physical structure. Another issue with physical sensors is that the physical sensors cost money to acquire, install, and maintain. Furthermore, sensor data can be vast and difficult to sift through in real-time. Because of this, current sensor analysis does not provide sufficient real-time analysis of sensor readings and results in a poor assessment of the state of a physical structure at a given time. In addition, preprogrammed and simplified (generic) mathematical algorithms used for digital conversion and structure analysis become inadequate upon changed needs or conditions, for example, when the physical structure begins to deteriorate or complex scenarios develop in and around the physical asset. Accordingly, what is needed is an improved way of monitoring and diagnosing a physical asset through a virtual asset in real-time.

BRIEF DESCRIPTION OF THE DRAWINGS

Features and advantages of the example embodiments, and the manner in which the same are accomplished, will become more readily apparent with reference to the following detailed description taken in conjunction with the accompanying drawings.

FIG. 1 is a diagram illustrating a simulation system including a virtual asset in accordance with an example embodiment.

FIG. 2 is a diagram illustrating a user interface for attaching a virtual sensor to a virtual asset in accordance with an example embodiment.

FIG. 3 is a diagram illustrating virtual sensors capturing data from a virtual asset in accordance with an example embodiment.

FIG. 4 is a diagram illustrating a method for sensing data from a virtual asset using a virtual sensor in accordance with an example embodiment.

FIG. 5 is a diagram illustrating a computing system for sensing data from a virtual asset using a virtual sensor in accordance with an example embodiment.

Throughout the drawings and the detailed description, unless otherwise described, the same drawing reference numerals will be understood to refer to the same elements, features, and structures. The relative size and depiction of these elements may be exaggerated or adjusted for clarity, illustration, and/or convenience.

DETAILED DESCRIPTION

In the following description, specific details are set forth in order to provide a thorough understanding of the various example embodiments. It should be appreciated that various modifications to the embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the disclosure. Moreover, in the following description, numerous details are set forth for the purpose of explanation. However, one of ordinary skill in the art should understand that embodiments may be practiced without the use of these specific details. In other instances, well-known structures and processes are not shown or described in order not to obscure the description with unnecessary detail. Thus, the present disclosure is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

The example embodiments relate to virtual sensors which may be used to compliment physical sensors or used instead of physical sensors in a system which performs real-time structural analysis of a physical asset based on simulations performed on a virtual model (also referred to as a digital twin) of the physical asset. The asset may be any type of asset used that may be included in an Internet of Things (IoT) environment or a stand-alone environment, and may include, for example, a wind turbine, a crane, a winch, an oil platform, an aircraft, a locomotive, a gas turbine, a building, a bridge, and the like. It should be appreciated that the type of asset is not limited. Data of the physical asset, for example, data sensed by on one or more physical sensors placed on or about the asset may be transmitted to a host system of the virtual model. The sensors may include proximity sensors, accelerometers, temperature, pressure, image, gas, chemical, gauges, and others. In one example, the sensor data may be acquired by multiple sensors attached at various locations dispersed throughout a surface of the physical asset. The sensor data from the physical asset may be used to generate and apply a virtual force to a corresponding virtual asset. The virtual force may be used to mimic the force being applied to the physical asset. Accordingly, monitoring and analysis may be performed on the virtual asset to assess productivity, generate alerts, and determine corrective action associated with the physical asset.

Related art monitoring approaches are limited in the number, type and location of physical sensor installations on a physical structure. For example, a person typically has access to the top of a wind turbine where the power supply is located. However, it may be difficult to gain access to the rotor and the blades of the wind turbine, especially while the wind turbine is active. In addition to the difficulty accessing locations on the physical asset, physical sensors can be expensive to acquire, install, and maintain. Therefore, from a monitoring perspective, hardware monitoring can be costly and difficult to adequately measure all areas of an asset. From a software perspective, current technology does not provide sufficient real-time analysis of sensor readings and thus creates a poor assessment of the state of a structure in real time. In addition, preprogrammed and simplified (generic) mathematical algorithms can become inadequate when conditions change or complex scenarios associated with the asset occur.

The example embodiments are directed to virtual sensors that can be attached or otherwise associated with a virtual model of a physical asset. Virtual sensors do not have a cost associated therewith nor do they consume time by requiring a physical install. Instead, virtual sensors can be added from a remote location (e.g., via a user interface, etc.) Furthermore, increasing the amount of virtual sensors does not increase hardware costs. In addition, virtual sensors can be placed at dynamic monitoring locations (e.g., hot spots) based on a current state of the physical asset rather than predefined locations as with physical sensors. Through the use of virtual sensors on the virtual model, the amount of physical sensors on the physical structure can be reduced in comparison to previous monitoring techniques thus reducing sensor hardware costs, installation costs, and maintenance costs.

Data from the physical sensors may be transformed into virtual information (e.g., motion, translation, rotation, position, reactionary force, etc.) and applied to a structure of a corresponding virtual asset in real-time. For example, the data sensed from the physical asset may be used to generate and apply a virtual force to the virtual asset that mimics the real world force being applied to the physical asset. Meanwhile, in the simulated environment, virtual sensors may be used to detect translations, rotations, stresses, etc. that occur as a result of the virtual force being applied to the virtual structure of the virtual asset. The virtual sensors can be placed anywhere along the virtual asset and can be used to acquire data from the simulation. As mentioned, there are no hardware, installation, or maintenance costs associated with adding virtual sensors. Accordingly, increasing the number of virtual sensors does not increase cost. Furthermore, virtual sensors can be added at locations on the virtual asset that differ from locations at which physical sensors are located on the physical structure and even places that are not accessible on the physical structure (e.g., inside of a beam made of steel, etc.).

The data that is sensed by the virtual sensors may be used to compliment data that is sensed by physical sensors or it may be used instead of the data from physical sensors. Virtual sensors can be used to sense data from a virtual component of the virtual model as if connected to the physical asset. In this case, the overall motion of the virtual component may be determined by data from a physical sensor. Virtual sensors attached to the virtual model can include different sensor types than the physical sensors attached to the physical structure. Examples of physical and virtual sensors include motion, force and moment sensors or strain gauges. Virtual sensors can be added remotely to the monitoring system at any time, without interrupting the operation. As a result, a re-analysis based on historical data is capable of being performed for locations which have not previously been considered.

The physical sensor measurements acquired from the real asset may be processed onsite or in a remote environment (e.g., a cloud computing environment) in a real-time structural analysis via a multi-body simulation based on a corresponding virtual asset. Readings from virtual sensors sensing data from and about the virtual asset may be extracted from the simulation model and made available for an online access system. Measurements from virtual sensors can be extracted with a same format, type and communication protocol as measurements taken from physical sensors of traditional monitoring solutions. Accordingly, existing programs and user interfaces can still be used, replacing feed from physical sensors by feed from virtual sensors. Real-time data feed and analysis enables operational decision making. Control actions such as yawing direction of a wind turbine can be simulated in advance of a control decision, considering consequences for both power production and structural lifetime. In addition, by recording an accurate and reliable history of structural responses (overview over extreme and fatigue events) enables cost-efficient prolongation of life beyond design lifetime.

FIG. 1 illustrates a simulation system 100 including a virtual asset 120 in accordance with an example embodiment. According to various aspects, the virtual asset 120 is a digital replica, or digital model of a physical asset 110. In this example, the real asset 110 is a wind turbine, however, the embodiments are not limited thereto and the asset may be any desired asset or structure such as a bridge, a crane, a winch, a platform, a rig, and the like. The software described herein (e.g., application, program, service, code, etc.) for controlling the virtual asset 120 and virtual sensors is based on the principle of observations and stimulations. The asset 110 may be coupled to or otherwise in communication with an industrial edge computing system 112. The industrial edge system 112 may include an edge device, an asset control system, an intervening edge server, and the like. Meanwhile, the virtual asset 120 may be hosted by a host platform 122 such as a web server, a cloud platform, an on-premises server, or the like. The host platform 122 may communicate with the edge system 112 via a network to receive data about the physical asset 110 and the provide control signals for controlling the physical asset 110.

Observations and measurements captured or sensed by physical sensors attached to or otherwise associated with the physical asset 110 may be fed by the edge system 112 to the host platform 122. An actuator 124 may generate motions in a virtual environment according to the physical sensor measurement data and applied in a simulation model to the virtual asset 120 by stimulating the virtual asset 120 with a corresponding force. In the example of the system 100 of FIG. 1, the real asset 110 is a physical system in the real world. In contrast, the virtual asset 120 (also referred to as digital twin) is a numerical model established by a simulation software. That is, the virtual asset 120 is a digital copy or replica of the real asset 110 and may have the same virtual dimensions, material properties, constraints, etc. as the physical characteristics of the real asset 110. In operation, the virtual asset 120 may be a numerical representation of the real asset 110 and may follow or otherwise mimic its motions and dynamical behavior. According to various aspects, the virtual behavior of the virtual asset 120 may be captured by one or more virtual sensors 125 described herein.

Physical sensors 115 may be used to observe the response of the physical asset 110 and may be used to measure the dynamical motions, material deformations, and the like, of the physical asset 110. Likewise, the virtual sensors 125 may be used to observe the response of the virtual asset 120 and measure the same motions and deformations. The physical sensors 115 can be of any physical kind (when installed on the real system), and likewise, the virtual sensors 125 can be any virtual kind (when placed on the digital twin). In some embodiments, the physical sensors 115 may be less in number than the virtual sensors 125. That is, the virtual sensors 125 may be placed at different and additional locations on the virtual asset 120 than the physical sensors 115 are placed on the real asset 110. Accordingly, the system 100 enables the virtual asset 120 to be monitored and analyzed at more locations and at a finer level than the physical asset 110. Furthermore, the virtual sensors 125 may be of different types of sensors than the physical sensors 115 attached to the physical asset 110, and are not limited to being of the same type as the physical sensors 115.

In the real world, actuators are devices which convert energy into motions such as a motor, and the like. In the simulation software, the actuator 124 may be used to prescribe motions of a numerical model based on input data received from the measurements of the physical asset 110. In the example of FIG. 1, observations may be made in the real world by physical sensor 115 measurements, which are transferred to the numerical model of the digital twin. To perform the transform, the actuators 124 may be placed on the virtual asset 120 and used to stimulate the virtual asset 120 with motions according to sensor measurements taken from the physical asset 110. Furthermore, the virtual sensors 125 may determine stress and/or damage that occurs to the virtual asset 120 based on the stimulation.

According to various embodiments, to establish a simulation-based system monitoring that is performed in real-time, a fast and accurate numerical solver is provided for the simulation model. Sensor measurements on the physical asset 110 can trigger a numerical solver process in the simulation model, updating the state of the virtual asset 120. Hence, the solver process may be as fast as, or faster than, the sensor measurement sampling of the physical sensors 115 to be capable of keeping track with the physical asset 110. Another aspect of the system 100 is the ability to predict structural responses of the physical asset 110 based on future events. For example, by estimating the development of a future load situation, different control decisions can be simulated in advance of the performed actions, evaluating consequences for both power production and structural loading.

The system and method described herein may be used to perform real-time based structural analysis of a physical asset based on analysis of a corresponding virtual asset. Data acquired from the physical asset may be fed into the simulation model such as shown in FIG. 1, in real-time. The application software described herein may convert the physical measurements and other data acquired from the real asset into movement data or position data (e.g., rotations, translations, position, acceleration, strain, force, etc.) in the virtual space. In order to stimulate the virtual asset, the application may create input data for the simulation model based on sensor data acquired from the real asset.

The physical asset described herein may correspond to a machine or equipment for use in industry, healthcare, manufacture, etc. Examples of assets include a wind turbine, a winch, a crane, a bridge, an oil platform, and the like, which include materials such as metal, concrete, and the like. During processing of the data acquired from the real asset, the application may generate input data for the simulation model (e.g., the virtual asset) during a pre-processing step. In order to generate the input data, the application may determine a beam deformation of the real asset which may be used to identify virtual forces that can be used to drive the simulation model such that it mimics the behavior of the real asset. In some of the examples herein, position and movement data such as accelerometer data from the real asset is used to generate an observable attribute of the virtual asset such as position or movement data for the virtual asset. For example, acceleration data may be used to generate position data in the virtual environment. Although, it should be appreciated that other types of observable attribute data may be generated and applied to the virtual model based on data from the physical asset. Other examples of observable attributes include rotation, translation, acceleration, orientation, a fixed position, strain, force, pressure, sound, and the like. The transformation process uses information about a structure of the real asset to generate a transfer function that transforms the acquired data into the observable attribute or attributes in the virtual environment. Based on the structure of the real asset, a determination of how the structure of the real asset reacts to movement (e.g., measured by accelerometers, motion sensors, etc.) can be mapped into position and movement data in the virtual environment.

FIG. 2 illustrates an example of a user interface 200 which enables a user the ability to insert or otherwise attach virtual sensors (e.g., virtual sensor 220) to a virtual model 210 of an asset. For example, a user may move a cursor 230 to a position of the virtual model 210 at which the user desires to add a virtual sensor, and the user may press a selection (e.g., input pad, mouse click, vocal command, etc.) which causes the software to add a virtual sensor 220 to the virtual model 210 of the asset. The addition of the virtual sensor 220 creates position for data to be sensed and output. The virtual sensor 220 may start working immediately after being added to the virtual model 210. The data sensing may include measuring an observable attribute such as position, movement, velocity, strain, pressure, sound, etc., of the virtual model 210 in virtual space. Although not shown, the user interface may also provide a menu that gives the user the ability to determine the type of data (i.e., attribute or attributes) to be sensed, the data format that the data is to be provided in, and other details. In the example of FIG. 2, the von Mises stress is selected as the data to be sensed.

The virtual sensor 220 may perform a special kind of readout from the virtual model 210. For example, the virtual sensor 220 (instead of an output from a model) may be referred to as a box which is placed on the object (e.g., virtual asset) being monitored. Upon this placement, a spot on the model is determined at which data is to be extracted from. Here, the placement of the virtual sensor 220 opens a channel to the underlying runtime. Upon opening this channel, the data desired may be selected (e.g., velocity, positions, inclinations, reaction forces, etc.) via a menu of the user interface. The user may also select a frequency at which the data is to be read and the packaging standard that the data should be encapsulated with. The spot at which the virtual sensor 220 is placed may receive a unique identification from the system. Accordingly, any application or device can access the model/sensor using the ID and read this virtual sensor like the application would when reading a physical sensor data stream. The naming of a virtual sensor is more of branding.

FIG. 3 illustrates a process of virtual sensors capturing data from a virtual asset in accordance with an example embodiment. Referring to FIG. 3, a virtual asset is simulated in 320 based on asset data sensed in 310. The simulated movement may be performed in 320 based on a physical sensor measurements captured from the real asset in 310. In this example, the sensed movement is captured from a physical sensor disposed on a top of the real asset during the sensed asset movement in 310. However, the virtual asset includes multiple virtual sensors (VS1, VS2, VS3) positioned at different vertical positions of the virtual asset. In the example of FIG. 3, deflection versus angle ratios 330 for three vertical positions on a virtual asset reacting to a concentrated force acting on a tower top of a physical asset are identified and plotted as a graph in 330. In this example, deflection versus angle (R_y) is plotted on the graph 330.

The application described herein may also perform analytical estimation of linear acceleration compensation (dynamic factor). When using an accelerometer to measure inclination, one method is to measure the direction of the gravitational pull on the accelerometer. This is used in simpler inclinometer designs as an accelerometer typically has a superior quality to cost ratio. In an accelerated system, measuring the direction of the gravitational pull is not straightforward because it is difficult if not impossible to separate it directly from the total acceleration. However, with some a priori information about the system, the linear acceleration may in certain systems be compensated for.

According to various embodiments, the use of virtual sensors can reduce the number of hardware sensors that are needed to measure physical locations on the real asset. As described herein, virtual forces that are created based on the real asset can be applied to the virtual asset enabling virtual sensors to be added on the virtual model at different places than at which physical sensors are located on the real asset. Furthermore, there is no need for maintenance, calibration, expense of paying for physical hardware, etc. with virtual sensors as they do not have a cost associated therewith. As a result, the virtual sensors reduce cost and resources. In the example of the wind turbine, an operator may have access to the very top of the wind turbine in the physical (real) world allowing real sensors to be placed at the to of the turbine. However, the remainder of the wind turbine is difficult to access, especially while in operation. According to various aspects, virtual sensors can be used in any location on the virtual asset that are difficult to access with real sensors on the real, physical asset.

Hot spots are points on a virtual structure where virtual sensors (e.g., strain gauges) can be placed based on previous knowledge where damage will likely occur on the physical structure. One of the advantages provided by this method is that new virtual sensors can be positioned at other places on the virtual structure where physical sensors are not present or not capable of being placed on the real structure. In operation, it is desirable to run a wind turbine in strong winds to generate the most energy, but the strong winds create the most stress on the turbine and also the most stress cycles. The example embodiments can be used as an operational tuning to fine tune the balance between damage assessment and energy acquired to find a cost efficient balance between the two such that the wind turbine is not running in conditions that are cost negative from a damage to the wind turbine perspective.

FIG. 4 illustrates a method 400 for sensing data from a virtual asset using a virtual sensor in accordance with an example embodiment. For example, the method 400 may be performed by a computing system that hosts a virtual asset. The computing system may include a cloud platform, a server, an industrial computing system, an asset controller, an intervening industrial server, and the like. Referring to FIG. 4, in 410, the method includes executing a virtual model in virtual space. The virtual model may include a digital model of a physical asset located in physical space and may be executed based on sensor data sensed of the physical asset in operation. Here, the sensor data may include raw data received directly from a sensor attached or otherwise associated with the physical asset, or it may include data from an analytic application, or the like, which monitors the operation of the physical asset. According to various aspects, the virtual model may include a three-dimensional (3D) simulation of the physical asset, and an observable attribute being sensed from the virtual asset may correspond to a change in position or a change in state of the 3D simulation in virtual space.

In 420, the method includes determining a position of a virtual sensor on a structure of the virtual model. The position of the virtual sensor in virtual space may be determined based on pixel coordinates of the virtual sensor position within a visual interface that is simulating and displaying the virtual asset. The position may include an X coordinate, a Y coordinate, or multiple X coordinates and/or multiple Y coordinates.

In some embodiments, the method may further include attaching the virtual sensor to the virtual asset such as to a virtual component which corresponds to a physical component of the physical asset. For example, the method may include displaying the virtual model via a user interface, and detecting a command, via the user interface, for attaching the virtual sensor at a position of a component on the virtual model. The detecting, via the user interface, may also include detecting a selection of a type of data to be sensed by the virtual sensor from among a plurality of types of data such as velocity, inclination, acceleration, reactionary forces, and the like. Physical sensors are often limited in their locations on a physical asset. For example, it may not be possible to embed a physical sensor with a steel beam of a wind turbine. However, the example embodiments provide the ability for embedding the virtual sensor within an interior of the virtual component which is not accessible to a physical sensor on the corresponding physical component of the physical asset. For example, the virtual sensor may be embedded within a steel beam in the virtual space.

In 430, the method includes sensing an observable attribute of the virtual model in virtual space at the position of the virtual sensor on the structure of the virtual model, and in 440, transmitting information about the virtually sensed attribute sensed via the virtual sensor to a system associated with the physical asset. For example, the observable attribute of the virtual model in virtual space may correspond to an actual attribute of the physical asset that is observer by mimicking a movement of the physical asset in physical space based on data being fed to the virtual model from the edge including the physical asset. As a non-limiting example, the observable attribute of the virtual asset may include one or more of a movement, a position, a force, a strain, a pressure, a sound, a radiation, and/or the like which may be observed from the virtual model in virtual space. For example, the virtual sensor may be placed on or otherwise attached to a virtual structure of the virtual model. The position may be determined by detecting movement information of a virtual structure of the virtual asset based on transformed and applied virtual position information. For example, the detecting of the movement of the virtual structure of the virtual asset may be performed by one or more virtual sensors that are positioned on the virtual asset. The virtual sensors may detect a change in position (e.g., X axis, Y axis, and Z axis) of structural components of the virtual asset.

Although not shown in FIG. 4, in some embodiments the method may further include assigning a unique identifier to the virtual sensor based on the position of the virtual model at which the virtual sensor is attached. The identifier may be a code, a serial number, a tag, etc., which uniquely identifies the sensor and its position on the virtual model. Furthermore, the method may include receiving a request from an application for registering with the virtual sensor based on the unique identifier, and transmitting the virtually sensed movement to the registered application.

FIG. 5 illustrates a computing system 500 for sensing data from a virtual asset using a virtual sensor in accordance with an example embodiment. For example, the computing system 500 may be a database, cloud platform, streaming platform, a workstation, an on-premises computing system, and the like. In some embodiments, the computing system 500 may be distributed across multiple devices. Referring to FIG. 5, the computing system 500 includes a network interface 510, a processor 520, an output 530, and a storage device 540 such as a memory. Although not shown in FIG. 5, the computing system 500 may include other components such as a display, an input unit, a receiver, a transmitter, and the like.

The network interface 510 may transmit and receive data over a network such as the Internet, a private network, a public network, and the like. The network interface 510 may be a wireless interface, a wired interface, or a combination thereof. The processor 520 may include one or more processing devices each including one or more processing cores. In some examples, the processor 520 is a multicore processor or a plurality of multicore processors. Also, the processor 520 may be fixed or it may be reconfigurable. The output 530 may output data to an embedded display of the computing system 500, an externally connected display, a display connected to the cloud, another device, and the like. The storage device 540 is not limited to a particular storage device and may include any known memory device such as RAM, ROM, hard disk, and the like, and may or may not be included within the cloud environment. The storage 540 may store software modules or other instructions which can be executed by the processor 520 to perform the method 400 shown in FIG. 4.

According to various aspects, the network interface 510 may receive sensor data that is sensed in association with an operation of a physical asset in physical space. For example, the sensor data may be received from an edge device such as a device coupled to the asset, an asset control system, an industrial PC, an intervening edge server, and the like. The processor 520 may execute or otherwise run a virtual model in virtual space of the asset. For example, the virtual model may include a digital model or digital representation of the physical asset and may be executed by the processor 520 based on the received sensor data. According to various embodiments, the virtual model may have one or more virtual sensors attached thereto or otherwise associated therewith. The processor 520 may determine a position of a virtual sensor on a structure of the virtual model, sense an observable attribute of the virtual model in virtual space at the position of the virtual sensor on the structure of the virtual model, and transmit information about the virtually sensed attribute to a system (e.g., application, device, network, asset, etc.) associated with the physical asset.

In some embodiments, the processor 520 may manage a user interface through which a user can manipulate placement, data sensing types, and the like, of virtual sensors with respect to the virtual asset. For example, the processor 520 may attach a virtual sensor to a virtual component of the virtual model in response to a user command received via the user interface. The virtual sensor may be attached to an exterior of a component of the virtual asset (e.g., the exterior of a beam, stack, flare, etc.). As another example, the processor 520 may embed the virtual sensor within an interior of the virtual component which is not accessible to a physical sensor on the corresponding physical component of the physical asset. Accordingly, the virtual sensor may sense data on the virtual asset that is not capable of being sensed using a physical sensor on the physical asset.

In some embodiments, the processor 520 may detect a command, via the user interface, of a selection of a type of data to be sensed by the virtual sensor from among a plurality of types of data. The data types include velocity, movement, displacement, force, and the like. In some embodiments, the processor 520 may assign a unique identifier to the virtual sensor based on the position of the virtual model at which the virtual sensor is attached. For example, the unique identifier may be automatically assigned in response to the user attaching a virtual sensor to the virtual asset via the user interface. Furthermore, a system (e.g., analytic application, device, etc.) may connect to or otherwise link with the virtual sensor by registering with the virtual sensor using the unique identifier. In this example, the processor 520 may receive a request from the requesting system for registering with the virtual sensor based on the unique identifier, register the system for data communication, and transmit the virtually sensed movement to the registered system on a periodic basis, continuous basis, or the like.

As will be appreciated based on the foregoing specification, the above-described examples of the disclosure may be implemented using computer programming or engineering techniques including computer software, firmware, hardware or any combination or subset thereof. For example, the methods described herein may be implemented via one or more software applications (e.g., program, application, code, module, service, etc.) executing on one or more computing devices. Any such resulting program, having computer-readable code, may be embodied or provided within one or more non transitory computer-readable media, thereby making a computer program product, i.e., an article of manufacture, according to the discussed examples of the disclosure. For example, the non-transitory computer-readable media may be, but is not limited to, a fixed drive, diskette, optical disk, magnetic tape, flash memory, semiconductor memory such as read-only memory (ROM), and/or any transmitting/receiving medium such as the Internet, cloud storage, the internet of things, or other communication network or link. The article of manufacture containing the computer code may be made and/or used by executing the code directly from one medium, by copying the code from one medium to another medium, or by transmitting the code over a network.

The computer programs (also referred to as programs, software, software applications, “apps”, or code) may include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, apparatus, cloud storage, internet of things, and/or device (e.g., magnetic discs, optical disks, memory, programmable logic devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The “machine-readable medium” and “computer-readable medium,” however, do not include transitory signals. The term “machine-readable signal” refers to any signal that may be used to provide machine instructions and/or any other kind of data to a programmable processor.

The above descriptions and illustrations of processes herein should not be considered to imply a fixed order for performing the process steps. Rather, the process steps may be performed in any order that is practicable, including simultaneous performance of at least some steps. Although the disclosure has been described in connection with specific examples, it should be understood that various changes, substitutions, and alterations apparent to those skilled in the art can be made to the disclosed embodiments without departing from the spirit and scope of the disclosure as set forth in the appended claims.

Claims

1. A computing system comprising:

a network interface configured to receive sensor data that is sensed in association with an operation of a physical asset in physical space; and

a processor configured to execute a virtual model in virtual space, the virtual model comprising a digital model of the physical asset and being executed based on the received sensor data, wherein the processor is further configured to determine a position of a virtual sensor on a structure of the virtual model, sense an observable attribute of the virtual model in virtual space at the position of the virtual sensor on the structure of the virtual model, the observable attribute of the virtual model in virtual space corresponding to an actual attribute of the physical asset in physical space, and transmit information about the virtually sensed attribute sensed via the virtual sensor to a system associated with the physical asset.

2. The computing system of claim 1, wherein the virtual model comprises a three-dimensional (3D) simulation of the physical asset.

3. The computing system of claim 1, wherein the processor is further configured to attach the virtual sensor to a virtual component of the virtual model which corresponds to a physical component of the physical asset.

4. The computing system of claim 3, wherein the processor is configured to embed virtual sensor within an interior of the virtual component which is not accessible to a physical sensor on the corresponding physical component of the physical asset.

5. The computing system of claim 1, wherein the observable attribute sensed by the virtual sensor comprises one or more of a movement, a force, a strain, a pressure, a sound, and a radiation, observed from the virtual model in virtual space.

6. The computing system of claim 1, wherein the processor is further configured to output the virtual model for display via a user interface, and detect a command, via the user interface, for attaching the virtual sensor at the position on the virtual model.

7. The computing system of claim 6, wherein the processor is further configured to detect, via the user interface, a selection of a type of data to be sensed by the virtual sensor from among a plurality of types of data.

8. The computing system of claim 1, wherein the processor is further configured to assign a unique identifier to the virtual sensor based on the position of the virtual model at which the virtual sensor is attached.

9. The computing system of claim 8, wherein the processor is further configured to receive a request from an application for registering with the virtual sensor based on the unique identifier, and transmit the virtually sensed movement to the registered application.

10. A computer-implemented method comprising:

executing a virtual model in virtual space, the virtual model comprising a digital model of a physical asset located in physical space and being executed based on sensor data sensed of an operation of the physical asset;

determining a position of a virtual sensor on a structure of the virtual model;

sensing an observable attribute of the virtual model in virtual space at the position of the virtual sensor on the structure of the virtual model, the observable of the virtual model in virtual space corresponding to an actual attribute of the physical asset in physical space; and

transmitting information about the virtually sensed attribute sensed via the virtual sensor to a system associated with the physical asset.

11. The computer-implemented method of claim 10, wherein the virtual model comprises a three-dimensional (3D) simulation of the physical asset.

12. The computer-implemented method of claim 10, wherein the method further comprises attaching the virtual sensor to a virtual component of the virtual model which corresponds to a physical component of the physical asset.

13. The computer-implemented method of claim 12, wherein the method further comprises embedding the virtual sensor within an interior of the virtual component which is not accessible to a physical sensor on the corresponding physical component of the physical asset.

14. The computer-implemented method of claim 10, wherein the sensing of the observable attribute comprises sensing one or more of a movement, a force, a strain, a pressure, a sound, and a radiation, observed from the virtual model in virtual space.

15. The computer-implemented method of claim 10, further comprising displaying the virtual model via a user interface, and detecting a command, via the user interface, for attaching the virtual sensor at the position on the virtual model.

16. The computer-implemented method of claim 15, further comprising detecting, via the user interface, a selection of a type of data to be sensed by the virtual sensor from among a plurality of types of data.

17. The computer-implemented method of claim 10, further comprising assigning a unique identifier to the virtual sensor based on the position of the virtual model at which the virtual sensor is attached.

18. The computer-implemented method of claim 17, further comprising receiving a request from an application for registering with the virtual sensor based on the unique identifier, and transmitting the virtually sensed movement to the registered application.

19. A non-transitory computer readable medium having stored therein instructions that when executed cause a computer to perform a method comprising:

executing a virtual model in virtual space, the virtual model comprising a digital model of a physical asset located in physical space and being executed based on sensor data sensed of an operation of the physical asset;

determining a position of a virtual sensor on a structure of the virtual model;

sensing an observable attribute of the virtual model in virtual space at the position of the virtual sensor on the structure of the virtual model, the observable of the virtual model in virtual space corresponding to an actual attribute of the physical asset in physical space; and

transmitting information about the virtually sensed attribute sensed via the virtual sensor to a system associated with the physical asset.

20. The non-transitory computer-readable medium of claim 19, wherein the virtual model comprises a three-dimensional (3D) simulation of the physical asset, and the observable attribute comprises one or more of a movement, a force, a strain, a pressure, a sound, and a radiation, observed from the virtual model in virtual space.