An acquisition unit acquires a bundle of detection values for each of a plurality of sensor values pertaining to a plant. A distance calculation unit obtains the Mahalanobis distance of the bundle of detection values acquired by the acquisition unit using, as reference, a unit space constituted by a collection of bundles of detection values for each of the plurality of sensor values. A determining unit determines, based on whether the Mahalanobis distance is at or within a prescribed threshold, whether the operation state of the plant is normal or abnormal. A trend specification unit specifies a trend with regards to at least one sensor value. An abnormality cause estimation unit estimates an abnormality cause based on the trend for the sensor value(s), and a fault site estimation database for holding the relationship between abnormality causes that may occur in the plant and sensor values for each of the trends.

A system for monitoring potential failure in a machine or a component thereof, the system including: at least one optical sensor configured to be fixed on or in vicinity of the machine or the component thereof, at least one processor in communication with the sensor, the processor being executable to: receive signals from the at least one optical sensor, obtain data associated with characteristics of at least one mode of failure of the machine or the component thereof, identify at least one change in the received signals, for an identified change in the received signals, apply the at least one identified change to an algorithm configured to analyze the identified change in the received signals and to classify whether the identified change in the received signals is associated with a mode of failure of the machine or the component thereof, thereby labeling the identified change as a fault, based, at least in part, on the obtained data, and for an identified change is classified as being associated with a mode of failure, outputting a signal indicative of the identified change associated with the mode of failure.

A method of automating engineering design is provided. The method includes receiving a training set including pairings of control loop data for respective control loops identified in digitized design data and templates that were instantiated using the control loop data of the respective control loops and training, using machine learning, a knowledge base, based on the training set. The knowledge base, once trained, is configured to be queried with digitized new control loop data, predict a template to pair with the digitized new control loop data, and the predicted template, and the predicted template is configured to be instantiated with the new control loop data for implementation of a control loop in an engineering system.

Systems and methods for fault prediction through a Bayesian framework are provided. Fault prediction for a valve system may be provided by generating a Bayesian framework by collecting a plurality of historical parameters related to opening and closing of a valve across a plurality of operational legs; generating a plurality of historical feature metrics based on the plurality of historical parameters; in response to detecting a fault, defining a prefault state corresponding to the historical feature metrics; monitoring a plurality of operational parameters related to opening and closing of the valve during a given operational phase of an operational leg; generating a plurality of operational feature metrics based on the plurality of operational parameters monitored during the given operational phase; and in response to determining, using the generated Bayesian framework, that the operational feature metrics indicate the prefault state of the subsystem, generating a notification.

A diagnostic apparatus of the invention acquires normal data related to an operating state during normal operation of an industrial machine, stores the normal data, generates a learning model by learning based on the stored normal data, and performs an estimation process for normality or abnormality of an operation of the industrial machine using the learning model. The diagnostic apparatus of the invention further generates verification data including at least one piece of abnormal data based on the stored normal data to verify validity of the learning model on receiving a result of the estimation process using the learning model based on the verification data.

Computer-implemented methods for configuring an Industrial Internet of Things (IIoT) edge node in an IIoT network to perform one or more functions, comprising: performing a situation analysis to determine a required change in one or more of an analytical model, a runtime component, and a functional block of the IIoT edge node based on a change in the one or more functions; and automatically provisioning a new or updated functional module to the IIoT edge node, based on the situation analysis, the new or updated functional module including one or more components, wherein each component includes at least one of a rules set, a complex domain expression with respect to a process industry, an analytical model, and a protocol decoder.

According to an embodiment of the present disclosure, a method of training a machine learning model is provided. Input data is received from at least one remote device. A classifier is evaluated by determining a classification accuracy of the input data. A training data matrix of the input data is applied to a selected context autoencoder of a knowledge bank of autoencoders including at least one context autoencoder and the training data matrix is determined to be out of context for the selected autoencoder. The training data matrix is applied to each other context autoencoder of the at least one autoencoder and the training data matrix is determined to be out of context for each other context autoencoder. A new context autoencoder is constructed.

In one embodiment, a device in a network receives a machine learning encoder and decoder trained by a supervisory service. The service trains the encoder and decoder using vibration measurement data sent to the service by a plurality of devices. The device trains, based on the received encoder, a classifier to determine whether vibration measurement data is indicative of a behavioral anomaly. The device receives vibration measurement data captured by a particular set of one or more vibration sensors of a monitored system. The device evaluates, using the trained decoder, the received vibration measurement data to determine whether the data is indicative of a structural anomaly in the monitored system. The device evaluates, using the trained classifier, the received vibration measurement data to determine whether the data is indicative of a behavioral anomaly in the monitored system.

A machine tool that visualizes the state of a ball screw in an easy-to-understand way includes a detector that detects at least one sensed value among vibrations, sound, and a current, heat, light, and power value applied to drive a ball screw during warming-up, a feature amount extractor that extracts a first feature amount and a second feature amount from the sensed value obtained by the detector, and a display that displays a point plotting the sensed value, and at least two boundaries laid out like contour lines to represent the possibility of generation of an anomaly in the ball screw, on a plane having a first axis defined by numerical values regarding the first feature amount and a second axis defined by numerical values regarding the second feature amount.

An abnormality diagnosis method for diagnosing an abnormality in operational state of a diagnosis subject includes creating a unit space from normal operation data of the diagnosis subject, the unit space serving as a reference for determining the operational state of the diagnosis subject, acquiring data having state quantities of a plurality of evaluation items from the diagnosis subject, calculating a Mahalanobis distance of the data acquired, using the unit space created, and determining an abnormality in the operational state of the diagnosis subject based on the Mahalanobis distance calculated. The creating a unit space includes creating a plurality of unit spaces having mutually different data lengths The calculating a Mahalanobis distance includes calculating a plurality of Mahalanobis distances using the plurality of unit spaces created. The determining an abnormality includes determining an abnormality based on the plurality of Mahalanobis distances calculated.