A control system for a gas turbine includes a processor. The processor configured to access data indicative of environmental conditions of a location of the gas turbine. The processor is configured to predict an occurrence of an event associated with the gas turbine based on the environmental conditions, wherein the event comprises a change in operation of the gas turbine due to the environmental conditions. The processor is configured to send a signal indicating the occurrence of the event to an electronic device.

The present disclosure discloses an intelligent manufacturing industrial Internet of Things based on distributed control, including a user platform, a service platform, a management platform, a sensor network platform, and an object platform interacting in sequence, wherein the service platform is provided with a plurality of independent service sub-platforms; the management platform is provided with a general management platform and a plurality of independent management sub-platforms, the management sub-platforms interacting with the general management platform, and the management sub-platforms interacting with the corresponding service sub-platforms; and the sensor network platform is provided with a general sensor network platform and a plurality of independent sensor network sub-platforms, the sensor network sub-platforms interacting with the general sensor network platform, and the general sensor network platform interacting with the general management platform.

An industrial safety zone configuration system leverages a digital twin of an industrial automation system to assist in configuring safety sensors for accurate monitoring of a desired detection zone. The system renders a graphical representation of the automation system based on the digital twin and allows a user to define a desired detection zone to be monitored as a three-dimensional volume within the virtual industrial environment. Users can define the locations and orientations of respective safety sensors as sensor objects that can be added to the graphical representation. Each sensor object has a set of object attributes representing configuration settings available on the corresponding physical sensor. The system can identify sensor configuration settings that will yield an estimated detection zone that closely conforms to the defined detection zone, and generate sensor configuration data based on these settings that can be used to configure the physical safety sensors.

Embodiments provide techniques for compressing sensor data collected within a manufacturing environment. One embodiment monitors a plurality of runs of a recipe for fabricating one or more semiconductor devices within a manufacturing environment to collect runtime data from a plurality of sensors within the manufacturing environment. The collected runtime data is compressed by generating, for each of the plurality of sensors and for each of the plurality of runs, a respective representation of the corresponding runtime data that describes a shape of the corresponding runtime data and a magnitude of the corresponding runtime data. A query specifying one or more runtime data attributes is received and executed against the compressed runtime data to generate query results, by comparing the one or more runtime data attributes to at least one of the generated representations of runtime data.

A method detects a manipulation of an exhaust gas system, in which measured values are sent to an external checking unit by a control unit of the exhaust gas system. In the external checking unit, an evaluation of the exhaust gas system as “manipulated” or as “not manipulated” takes place. Model values are formed in the control unit, which are at least partially formed from the measured values which are sent to the external checking unit. The external checking unit takes the model values and the measured values into consideration in the evaluation of the exhaust gas system.

Computer-implemented methods for fault diagnosis in an industrial environment generally includes processing the plurality of sensor data values to determine a recognized pattern therefrom; retrieving at least one industrial-environment digital twin corresponding to the industrial environment, the at least one industrial-environment digital twin comprising a plurality of component digital twins, with each of the plurality of component digital twins corresponding to one of the plurality of components in the industrial environment, and wherein the at least one industrial-environment digital twin and the plurality of component digital twins are visual digital twins that are configured to be rendered in a visual manner; and rendering the at least one industrial-environment digital twin and the at least one respective component digital twin corresponding to the particular component in the client application in response to the received request and based on the operational condition of the particular component.

A computer-implemented method and system is provided. The system adaptively switches prediction strategies to optimize time-variant energy demand and consumption of built environments associated with renewable energy sources. The system analyzes a first, second, third, fourth and a fifth set of statistical data. The system derives of a set of prediction strategies for controlled and directional execution of analysis and evaluation of a set of predictions for optimum usage and operation of the plurality of energy consuming devices. The system monitors a set of factors corresponding to the set of prediction strategies and switches a prediction strategy from the set of derived prediction strategies. The system predicts a set of predictions for identification of a potential future time-variant energy demand and consumption and predicts a set of predictions. The system manipulates an operational state of the plurality of energy consuming devices and the plurality of energy storage and supply means.

An abnormality diagnosing method includes a model generation step of generating a simulation model of a monitoring target, an operation start step of starting an operation of the monitoring target, a measurement step of measuring an internal state quantity in the operating state of the monitoring target and extracting a measured value, a prediction step of inputting into the simulation model same control input value used in the operating state of the monitoring target and calculating a predicted value of the internal state quantity of the monitoring target, a Mahalanobis distance calculation step of calculating a Mahalanobis distance from a difference between the measured value and the predicted value, and an abnormality diagnosis step of diagnosing whether the operating state of the monitoring target is abnormal based on the Mahalanobis distance.

Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving a request to create a machine learning model for failure mode detection associated with an asset, retrieving historical notification data of the asset, generating an unsupervised machine learning model via unsupervised learning on the historical notification data, wherein the unsupervised learning comprises identifying failure topics from text included in the historical notification data and mapping the identified failure topics to a plurality of predefined failure modes for the asset, and storing the generated unsupervised machine learning model via a storage device.

The present disclosure provides a computer-implemented method for ranking one or more control schemes for controlling peak loading conditions and abrupt changes in energy pricing of one or more built environments associated with renewable energy sources. The computer-implemented method includes analysis of a first set of statistical data, a second set of statistical data, a third set of statistical data, a fourth set of statistical data and a fifth set of statistical data. Further, the computer-implemented method includes identification and execution of the one or more control schemes. In addition, the computer-implemented method includes scoring the one or more control schemes by evaluating a probabilistic score. Further, the computer-implemented method includes ranking the one or more control schemes to determine relevant control schemes for controlling real time peak loading conditions and abrupt changes in energy pricing associated with the one or more built environments.