Abstract: A machine learning apparatus capable of reducing an error between a machined workpiece and a target shape when the workpiece is machined based on a workpiece model modeling the target shape of the workpiece. A machine learning apparatus includes a state observation section configured to observe machining state data of a machine tool configured to machine the workpiece, and measurement data of an error between a shape of the workpiece machined by the machine tool based on the workpiece model and the target shape, as a state variable representing a current state of environment in which the workpiece is machined, and a learning section configured to learn the correction amount in association with the error by using the state variable.

Abstract: Methods for ascertaining a control strategy for a technical system using a Bayesian optimization method. The control strategy is created based on model parameters of a control model and is executable. The method includes providing a quality function whose shape corresponds to a regression function and that evaluates a quality of a controlling of the technical system based on model parameters; carrying out a Bayesian optimization method based on the quality function in order to iteratively ascertain a model parameter set having model parameters within a model parameter domain that indicates the permissible value ranges for the model parameters; and determining the model parameter domain for at least one of the model parameters as a function of an associated maximum a posteriori estimated value of the quality function.

Abstract: The present disclosure relates to a method and apparatus for cycle-based programming of a control program for a numerically controlled machine tool at a control apparatus of the machine tool. Geometrical features, which have been detected and/or identified within a data analysis processing performed on the basis of workpiece data including a 3D workpiece model, each detected and/or identified geometrical feature being associated with a respective predetermined machining operation, are associated with a respective machine control cycle which is associated with a respective predetermined machining operation with which the respective associated geometry feature is producible.

Abstract: A system for controlling air flow in an air handling unit having an air mover is provided. The system includes a first and a second sensing device, each receiving a first input indicative of electric power and a second input indicative of properties of air, respectively. The system further includes a processing unit to determine heat generated from a motor of the air mover based on the first input, determine density of air based on the heat generated from the motor based on the second input, and determine an actual air flow rate based on the density of the air, a speed of the motor, and dimensional characteristics of the air handling unit. Further, the speed of the motor is controlled when the actual air flow rate is different from a target air flow rate.

Abstract: Various embodiments manage energy generation in a power generation and distribution system. In one embodiment, a set of residual load data is obtained for a given period of time measured at one or more nodes within a power generation and distribution system. The set of residual load data encodes a set of power flow signals. The set of residual load data is analyzed. An amount of power contributed to the set of residual load data by at least one energy generator class is determined based on the analysis of the set of residual load data.

Abstract: An artificial intelligent food refrigerating device and a method for refrigerating food by using the same are disclosed. An artificial intelligent food refrigerating device according to the present disclosure identifies the size, volume, type, and quantity of food to be put into it and determines a target refrigeration temperature and refrigeration time for the food based on an identification result. The artificial intelligent food refrigerating device and method according to the present disclosure may be associated with an artificial intelligent module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, a 5G service-related device, etc.

Abstract: A fan management system includes a fan and a server. The fan includes a driving circuit, and the driving circuit is configured for driving the fan. The fan operates in an operation mode. The server is connected to the fan and is configured for controlling the operation of the fan. The driving circuit outputs a digital label signal when the fan operates abnormally, and the server obtains a production history, an operation information and a warning message of the fan through the digital label signal. The server adjusts the operation mode of the fan according to the warning message simultaneously.

Abstract: A method for controlling cold storage of an air conditioner includes acquiring an ambient temperature around the air conditioner and a pipe temperature of an exhaust pipe of a compressor of the air conditioner, acquiring a target opening degree corresponding to a current cold storage mode of the air conditioner according to the ambient temperature and the pipe temperature, and adjusting an opening degree of a throttle device of the air conditioner to be the target opening degree. The throttle device is arranged at a pipe between a cold storage box of the air conditioner and a condenser of the air conditioner.

Abstract: An arithmetic operation device includes a performance calculation unit that is configured to calculate performance of a plant before introduction of a part and the performance of the plant after the introduction of the part for each of combinations of a plurality of loads in the plant and a plurality of atmospheric temperatures around the plant, a storage unit that is configured to store a data table indicating a percentage of an operating time of the plant for each of the combinations, and a performance improvement calculation unit that is configured to calculate, on the basis of a calculation result in the performance calculation unit and the data table, how much the performance of the plant is improved compared with the performance before the introduction of the part in a case where the part is introduced and the plant is operated at the percentage indicated by the data table.

Abstract: A controller for an autonomous network includes a processor configured to execute composable and replaceable modules in an interconnected manner to configure controller components. The controller components comprise a sensing component configured to collect sensor data about at least one controlled element under control of the controller, an analyzing component configured to process the collected sensor data to derive a current state of the at least one controlled element, a deciding component configured to, based on the derived current state, decide an action to be made with respect to the at least one controlled element, and an acting component configured to carry out the decided action with respect to the at least one controlled element, by causing a change in at least one of an operation of the at least one controlled element, or a configuration of the at least one controlled element.

Abstract: A control method includes obtaining historical operation records for a plurality of indoor units of an air conditioner system, and determining control parameters of the at least two indoor units according to the historical operation records to control the at least two indoor units. The air conditioner system further includes an outdoor unit.

Abstract: An embodiment includes a system for automatic depth positioning of wire conveyed operations using proportional-integral-derivative (PID) control loops.

Abstract: Various embodiments relate to an electronic device for brain-inspired adaptive control of resolving the bias-variance tradeoff and a method thereof. The method may include estimating a prediction error baseline for an environment, based on a first prediction error of a low-variance intelligent system for the environment and a second prediction error of a low-bias intelligent system for the environment; and implementing an adaptive control system by combining the low-variance intelligent system and the low-bias intelligent system based on the estimated prediction error baseline.

Abstract: Disclosed is a large-scale dynamic double-effect scheduling method for a flexible job shop based on genetic programming (GP). In a GP implementation process of the present disclosure, in addition to features related to workpieces, processing robots and automated guided vehicles (AGVs), such as processing time of working procedures and buffer area waiting time, features of a ratio of processing time to transfer time and a ratio of processing energy consumption to transfer energy consumption are also added in a terminal set to cause job shop environment features to be more comprehensively applied to a scheduling rule design, thereby automatically designing a more consistent and accurate scheduling rule. A double-effect scheduling rule of the present disclosure overcomes the shortcomings of slow convergence speed, difficulty in rapid corresponding changes and unfit scheduling rules, and can quickly produce a more efficient and energy-saving production scheduling scheme.

Abstract: A method includes finding, in subplant performance data points defined by values of an independent variable and values of a dependent variable, a first point for which a convexity metric of the dependent variable with respect to the independent variable exceeds a threshold, creating a subplant curve by providing a first convex region on a first side of the first point and a second convex region on a second side of the first point, and controlling the campus subplant based on the subplant curve.

Abstract: A method and device for processing wafer detection tasks, a system, and a storage medium. The method includes that: the resource manager node receives the wafer detection task from the storage server, selects the target work node from the plurality of work nodes according to weight values of the work nodes connected to the resource manager node, and allocates the wafer detection task to the target work node. The target work node selects the idle GPU from the resource pool and allocates the wafer detection task to the idle GPU for execution. The GPU preprocesses the wafer map in the wafer detection task and inputs the processed wafer map into the wafer detection model to obtain the detection result.

Abstract: A method, device, and system for configuring a coating machine for coating a surface of a product using a coating substance are provided. The method includes determining a value associated with one or more parameters from a plurality of parameters associated with the coating operation. The method also includes predicting a value associated with at least one attribute associable with the coating substance based on the determined value associated with the one or more parameters using a trained machine learning model. The method includes configuring the coating machine for coating the surface using the coating substance based on the predicted value associated with the at least one attribute associable with the coating substance. The method also includes initiating a coating operation at the configured coating machine for coating the surface of the product using the coating substance.

Abstract: The present application provides a fault risk analysis system, a fault risk analysis method, an air conditioner and a computer readable storage medium, and the fault risk analysis system comprises: a memory for storing computer programs; a processor for executing the computer programs to implement: obtaining debugging information and/or system operation information, and determining fault inducing factors corresponding to the debugging information and/or the system operation information; and adjusting a fault risk level of the fault category corresponding to the fault inducing factors according to the fault inducing factors. By collecting the debugging information, potential fault inducing factors of the current unit can be accurately reflected; by collecting the system operation information to analyze the fault inducing factors, the fault risk analysis system can obtain more accurate and reliable fault inducing factors.

Abstract: For etching tools, a neural network model is trained to predict optimum scheduling parameter values. The model is trained using data collected from preventive maintenance operations, recipe times, and wafer-less auto clean times as inputs. The model is used to capture underlying relationships between scheduling parameter values and various wafer processing scenarios to make predictions. Additionally, in tools used for multiple parallel material deposition processes, a nested neural network based model is trained using machine learning. The model is initially designed and trained offline using simulated data and then trained online using real tool data for predicting wafer routing path and scheduling. The model improves accuracy of scheduler pacing and achieves highest tool/fleet utilization, shortest wait times, and fastest throughput.

Abstract: A building management system includes building equipment operable to affect a physical state of a building. The building management system includes a system manager coupled to the building equipment via a system bus, the system manager comprising a schedule manager configured to control an operation schedule of the building equipment. A client device is configured to communicate with the schedule manager to modify operation schedules of the building equipment or add new operation schedules for the building equipment. The schedule manager comprises a list of available schedules for the building equipment and is configured to, in response to modification of the operation schedules or addition of new operation schedules, update the list of available schedules to include the modification or the new operation schedule.