Various embodiments of the present technology generally relate to solutions for integrating machine learning models into industrial automation environments. More specifically, embodiments of the present technology include systems and methods for implementing machine learning models within industrial control code to improve performance, increase productivity, and add capability to existing control programs. In an embodiment, a system comprises an interface component configured to display a graphical representation of a machine learning asset in an industrial automation environment, wherein the graphical representation includes a visual indicator representative of an output from the machine learning asset. The interface component is further configured to adjust the visual indicator based on the output from the machine learning asset. In addition, a process control component is configured to control an industrial process in the industrial automation environment based at least in part on the output from the machine learning asset.

The non-limiting technology described herein is a failure managing framework for complex systems that determines and restores functionality of failing systems and sub-systems using a function-based intervention approach having ontological content such as provided in a System State Graph directed graph. An integration framework allows integration of multiple intervention definition paradigms and selects the best for the current scenario; modifies procedures according to current context by encapsulating operator's tacit knowledge; provides an additional safety net during application of intervention and allows both autonomous operations and assistance to a human operator in the loop.

A computer implemented method of analyzing measurement results of a target system, such as an industrial process or communication network. The method includes receiving a data sample with a plurality of variables representing the measurement results, detecting that the data sample is an anomalous sample using an anomaly detection model, processing the data sample by applying an imputation model to selected subsets of variables of the data sample to obtain imputed samples, and applying the anomaly detection model to the imputed samples, determining anomalous variables of the data sample based on results from the processing of the data sample, and outputting the anomalous variables of the data sample for management operations in the target system.

Provided is a display device including a display screen, in which a plurality of evaluation models are configured to be displayed in a selectable manner in a first display area of the display screen, an evaluation result of evaluation data, which is obtained by using a selected first evaluation model, is configured to be displayed in a second display area of the display screen, and an evaluation result of the evaluation data, which is obtained by using a selected second evaluation model, is configured to be displayed in a third display area of the display screen.

Provided is a work machine maintenance management system capable of predicting replacement timing of a component of a work machine early. The work machine maintenance management system of this disclosure includes a maintenance management DB server 110 that accumulates maintenance management information of a plurality of work machines and a maintenance management control device 120 that predicts replacement timing of each component of each of the work machines based on the maintenance management information. The maintenance management information includes an actual durable period from start of use to replacement each component of each work machine. The maintenance management control device 120 includes a replacement-factor determining section 121, a service life model creator 122, a failure model creator 123, and a replacement time predictor 126. The replacement-factor determining section 121 determines whether a replacement factor of each component is a service life factor or a failure factor based on an actual durable period of each component of the plurality of work machines. The service life model creator 122 creates a service life model of the component whose replacement factor is determined to be the service life factor by the replacement-factor determining section 121. The failure model creator 123 creates a failure model of the component whose replacement factor is determined to be the failure factor by the replacement-factor determining section 121. The replacement time predictor 126 predicts the replacement timing of each component of each work machine based on the service life model and the failure model.

An irregularity detection apparatus (100) converts a multi-valued-signal value of each of one or more multi-valued-signals at each time point into a binary-signal-value group. The irregularity detection apparatus calculates a forecast-signal-value group at a subject time point by computing a forecast model with use of, as input, a past-signal-value group which is a collection of a binary-signal value of each of one or more binary signals at each past time point and the binary-signal-value group of each of the one or more multi-valued signals at each past time point. The irregularity detection apparatus compares with the forecast-signal-value group, a collection of the binary-signal value of each of the one or more binary signals at the subject time point and the binary-signal-value group of each of the one or more multi-valued signals at the subject time point, and determines a state of a subject system (220) at the subject time point.

A method for detecting a cyberattack on a control system of a wind turbine includes providing a plurality of classification models of the control system. The method also includes receiving, via each of the plurality of classification models, a time series of operating data from one or more monitoring nodes of the wind turbine. The method further includes extracting, via the plurality of classification models, a plurality of features using the time series of operating data. Each of the plurality of features is a mathematical characterization of the time series of operating data. Moreover, the method includes generating an output from each of the plurality of classification models and determining, using a decision fusion module, a probability of the cyberattack occurring on the control system based on a combination of the outputs. Thus, the method includes implementing a control action when the probability exceeds a probability threshold.

A method for controlling a wind turbine includes detecting, via a controller, a plurality of analytic outputs of the wind turbine from a plurality of different analytics. The method also includes analyzing, via the controller, the plurality of analytic outputs of the wind turbine. Further, the method includes generating, via the controller, at least one computer-based model of the wind turbine using at least a portion of the analyzed plurality of analytic outputs. Moreover, the method includes training, via the controller, the at least one computer-based model of the wind turbine using annotated analytic outputs of the wind turbine. As such, the method includes checking the plurality of analytic outputs for anomalies using the at least one computer-based model. Accordingly, the method includes implementing a control action when at least one anomaly is detected.

A condition monitoring system which collects operation data from a machine and monitors a condition of the machine includes: a storage unit that stores information indicating components of a first machine for which a model for a sensor data analysis has been created and components of a second machine for which the model is newly created, information indicating a correspondence relationship between the components of the first machine and the components of the second machine, and information relating to the model; a model creation unit that creates model candidates of the second machine from the model similar to the second machine by using the information stored in the storage unit, and creating information relating to a model candidate selected via an input unit out of the model candidates as the model of the second machine; and a display unit that displays the model candidates.

A method for correlating data from different sensors for product lifecycle management includes receiving sensor information from an additional sensor of a plurality of sensors of an industrial operation. The additional sensor is different from component sensors used for functionality of a component of the industrial operation. Sensor information from the additional sensor monitors conditions of a portion of the industrial operation different from sensor information of the component sensors used for the functionality of the component. The method includes deriving, using the sensor information, a correlation between an operational parameter of the component and sensor information of the additional sensor. The operational parameter is related to a predicted operational lifetime of the component. The method includes identifying an abnormal operating condition of the component based on a comparison between additional sensor information from the additional sensor and the operational parameter, and sending an alert with the abnormal operating condition.