The image processing device is provided with: a first input unit which, with respect to one or more virtual models including a virtual model of an operation machine, receives an input of a first parameter for identifying a type; a second input unit which receives an input of a second parameter relating to a stochastic distribution having, as a random variable, a characteristic of an element constituting the one or more virtual models; a virtual model generation unit which, using the first parameter and the second parameter, generates the one or more virtual model stochastically; a determination unit which determines the correctness of an operation of the virtual model of the operation machine when operated in a virtual space including the one or more stochastically generated virtual models; and a learning unit which learns a control module for the operation machine for achieving a predetermined operation.

An extension device for one or more automation devices in an industrial system is provided. Industrial data processing units capable of performing data processing based on one or more artificial neural networks are provided. To enable and/or accelerate one or more computations in an industrial system, thereby simplifying integration of artificial intelligence into the industrial system, and to simplify data exchange between an extension device capable of processing data using artificial intelligence and an automation device, one or more results of the one or more computations are obtained. The results indicate one or more states of the industrial system. The one or more results are provided via a process state model shared with the automation device to monitor and/or control the industrial system.

The invention relates to a method for generating a control system for a target system, wherein: operational data is received; a first neural model component is trained with the received operational data for generating a prediction on a state of the target system based on the received operational data; a second neural model component is trained with the operational data for generating a regularizer for use in inverting the first neural model component; and the control system is generated by inverting the first neural model component by optimization and arranging to apply the regularizer generated with the second neural model component in the optimization. The invention relates also to a system and a computer program product.

A system for the maritime shipping industry to aid enforcement of the Sulfur Dioxide (SO.sub.2) exhaust emissions regulations which uses neural networks and a novel sampling process to detect and record compliant operation of a ship regarding the fuel switching aspect of the regulation. The processing load of neural network training can be distributed over multiple identical self-contained, self-powered, self-communicating sensor units on each of the monitored ships.

The system generally includes a crosspoint switch in the local data collection system having multiple inputs and multiple outputs including a first input connected to the first sensor and a second input connected to the second sensor. The multiple outputs include a first and second output configured to be switchable between a condition in which the first output is configured to switch between delivery of the first sensor signal and the second sensor signal and a condition in which there is simultaneous delivery of the first sensor signal from the first output and the second sensor signal from the second output. Multiple inputs of the crosspoint switch include a third input connected to the second sensor and a fourth input connected to the second sensor. The first sensor signal is from a single-axis sensor at an unchanging location associated with the first machine. The second sensor is a three-axis sensor. The local data collection system is configured to record gap-free digital waveform data simultaneously from at least the first input, the second input, the third input, and the fourth input. The platform is configured to determine a change in relative phase based on the simultaneously recorded gap-free digital waveform data. The second sensor is configured to be movable to a plurality of positions associated with the first machine while obtaining the simultaneously recorded gap-free digital waveform data.

A method includes collecting a first dataset of input-output data for a first building, training a deep learning model using the first dataset, initializing parameters of a target model for a second building using parameters of the deep learning model, collecting a second dataset of input-output data for a second building, training the target model for the second building using the initialized parameters of the target model and the second dataset, and controlling building equipment using the target model. Controlling the building equipment affects a variable state or condition of the building.

The system generally includes a crosspoint switch in the local data collection system having multiple inputs and multiple outputs including a first input connected to the first sensor and a second input connected to the second sensor. The multiple outputs include a first output and a second output configured to be switchable between a condition in which the first output is configured to switch between delivery of the first sensor signal and the second sensor signal and a condition in which there is simultaneous delivery of the first sensor signal from the first output and the second sensor signal from the second output. Each of multiple inputs is configured to be individually assigned to any of the multiple outputs. Unassigned outputs are configured to be switched off producing a high-impedance state. The local data collection system includes multiple data acquisition units each having an onboard card set configured to store calibration information and maintenance history of a data acquisition unit in which the onboard card set is located. The local data collection system is configured to manage data collection bands.

A method for operating an automated system, the system comprising: a controlled device for performing an action as a function of received control data; a first control device for receiving system data and generating control data for controlling the controlled device as a function of the received system data; and a second control device for receiving input data and generating output data as a function of the input data according to a computer-implemented mapping algorithm; wherein the method comprises: adapting the computer-implemented mapping algorithm such that the second control device, upon receiving the system data as input data generates output data that is similar to the control data generated by the first control device with a predetermined similarity degree, wherein the computer-implemented mapping algorithm includes a neural network algorithm and/or a machine learning algorithm.

A method of manufacturing a composite structure includes accessing design data for the composite structure that is manufactured according to a process including forming a layup of plies of fibers using a machine tool. The method includes applying the design data to an ANN classifier to classify a localized inconsistency of a type of inconsistency on the composite structure, the localized inconsistency spatially referenced to a location on the composite structure. The method includes performing a root cause analysis to identify one or more of process parameters as a potential cause of the type of inconsistency, and modifying one or more of the geometric model, the layup design, or values of the one or more of the process parameters to address the potential cause.

The methods and systems for data collection, processing, and utilization of signals with a platform monitoring at least a first element in a first machine in an industrial environment generally include obtaining, automatically with a computing environment, at least a first sensor signal and a second sensor signal with a local data collection system that monitors at least the first machine and connecting a first input of a crosspoint switch of the local data collection system to a first sensor and a second input of the crosspoint switch to a second sensor in the local data collection system. The methods and systems also include switching between a condition in which a first output of the crosspoint switch alternates between delivery of at least the first sensor signal and the second sensor signal and a condition in which there is simultaneous delivery of the first sensor signal from the first output and the second sensor signal from a second output of the crosspoint switch and switching off unassigned outputs of the crosspoint switch into a high-impedance state. The local data collection system includes multiple data acquisition units each having an onboard card set that store calibration information and maintenance history of a data acquisition unit in which the onboard card set is located.