Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. At the sensor node, an indication is received to initiate training by the sensor node to detect anomalies in the environment based on sensor data generated by a sensor that resides on such sensor node and is operable to detect sensor signals from the environment. After training is initiated, the sensor node automatically trains a model that resides on the sensor to detect anomalies in the environment, and such training is based on the sensor data. After the model is trained, the model to detect anomalies in the environment is executed by the sensor node.

A method of continuously determining a measure of quality for a control device of a technical device or for a system model of a technical system, from an input variable and an output variable. Time series of the input variable and the output variable are acquired up to a time step. A discrete ARMAX model structure is adapted for the ascertained, corresponding time series of the input variable and output variable, in order to determine a first set of parameters for modeling the time series of the input variable and a second set of parameters for modeling the time series of the output variable. The measure of quality is determined for the time step as a function of the first and the second set of parameters.

A system and method for automatically detecting anomalies in an industrial control system (ICS) is provided. A behavioral model is provided, the model comprising groups of learned sets of interdependent ICS signals of parameters associated with an operation of the ICS. For each of the groups, the learned sets in the respective group include at least one independent signal and one or more dependent signals that are dependent on the independent signal in accordance with a common type of dependency. Monitoring signals of given parameters are obtained, the monitoring signals corresponding to a given learned set of the learned sets in one of the groups. Upon determining a nonconformance of an observed interdependency of the monitoring signals with a predicted interdependency of the monitoring signals, the predicted interdependency being in accordance with the type of dependency associated with the given learned set, an anomaly is automatically detected.

A method and system for analyzing the cause of faults in a process engineering installation, wherein engineering information of the engineering installation, where the information contains information about the engineering installation components as well as their interconnection in the engineering installation, is provided in digital form in order to use the engineering information to create an inference model in the form of a probabilistic physical model of the engineering installation with probability distributions and prior variables, where measurement data from the engineering installation are used to perform Bayesian inference of fault probabilities during a diagnosis mode of the inference model.

A notification device is provided with: an abnormality estimation unit for estimating a state relating to an abnormality of a plant and a factor relating to the abnormality of the plant; an item specifying unit for specifying inspection items on the basis of the abnormality of the plant and the state relating to the factor relating to the abnormality of the plant estimated by the abnormality estimation unit; a notification unit for notifying of the inspection items specified by the item specifying unit; a stop-time item specifying unit for specifying the inspection items which should be checked at a time of a stop out of the inspection items specified by the item specifying unit; a check result acquisition unit for receiving a check result for the inspection items notified of by the notification unit; and a stop-time item output unit for outputting the inspection items which should be checked at the time of stop.

A method of temporal anomaly detection includes accessing sensor data readings obtained at a monitored industrial asset, performing a data cleanup operation on at least a portion of the accessed sensor data readings, transforming at least the cleaned-up portion of the accessed sensor data readings to time series feature space sensor data, applying a multi-kernel-based projection algorithm to the time series feature space sensor data, computing a respective anomaly score and a respective ranking for one or more variables of the sensor data readings, and providing at least the computed respective anomaly score or the respective ranking for at least one of the one or more variables to a user. Ranking the anomaly score includes comparing each anomaly score to a threshold and then assigning a ranking to scores with a magnitude greater than the threshold based on its magnitude. A system and a non-transitory computer-readable medium are also disclosed.

A coordinator for use in a system for monitoring a vehicle-borne probe includes a first communication interface configured to exchange data with at least one edge device of a plurality of edge devices, a second communication interface configured to exchanged data with a cloud infrastructure and at least one vehicle system, and a processing unit. The processing unit is configured to analyze synthesized data comprising first data outputs from at least one edge device of the plurality of edge devices, second data outputs from at least one edge device of the plurality of edge devices, and data from the at least one vehicle system. The processing unit is further configured to implement a data processing application to analyze the synthesized data to generate a third data output, and incorporate the synthesized data and the third data output into a data package.

The present disclosure relates to a system, an apparatus, and a method for managing health condition of at least one rotating system. The method includes receiving, by a processing unit, operational data associated with the rotating system in real-time, from one or more sensing units. The operational data includes parameter values corresponding to an operation of the rotating system. Further, a virtual replica of the rotating system is configured using the operational data. A behavior of the rotating system is simulated on a simulation instance of the rotating system based on the configured virtual replica. The simulation results are analyzed to determine an abnormality in the health condition of the rotating system. The abnormality corresponds to a health status of an internal component of the rotating system. Further, a notification indicating the abnormality is generated, on a Graphical User Interface.

A data-series group includes data series which is a series of data obtained by observing the same object at discrete times. Time labels are time information added to respective data included in the data-series group. State labels are added to some of the data included in the data-series group. A loss-function control unit determines a loss function to be used for learning based on the time labels and the state labels. A threshold is used to adjust a branch condition of the loss-function control unit. A regressor is a model, and is used to detect an abnormality or predict a remaining life span. A dictionary stores parameters of the regressor. A regressor training unit trains the regressor based on the loss function determined by the loss-function control unit.

A method for predicting energy consumption of a vehicle using a statistical model. The method includes (i) predicting a set of future input vectors for the vehicle at defined time intervals corresponding to a plurality of future points in time based on a subset of a plurality of reference input vectors previously generated at the defined time intervals at a plurality of previous points in time, (ii) predicting a change in the energy level of the vehicle using a processor and the statistical model, and (iii) providing results corresponding to the predicted change in the energy level to an output unit of the vehicle. Each reference input vector comprises a vehicle input vector and a database input vector associated with each point in time of the plurality of previous points in time. The database input vector for each defined time interval may be based on at least one of a plurality of environmental data and information about a road condition.