Embodiments include a computer-implemented method (and system) for performing automated batch data alignment for modeling, monitoring, and control of an industrial batch process. The method (and system) loads, scales, and screens plant historian batch data for an industrial batch process. The method (and system) selects a reference batch as basis of the batch alignment, defines and adds or modifies one or more batch phases, and selects one or more batch variables based on one or more profiles and corresponding curvatures of the batch data. The method (and system) estimates one or more weightings, adjust one or more tuning parameters and uses a sliding time window combined with DTW, DTI and GSS algorithms, performs the batch alignment in offline mode or online mode.

For determining the operability of a fluid driven safety valve, a method comprising the following steps is described: A partial stroke test is performed on the safety valve, resulting in a stroke-pressure curve. The stroke pressure curve is extrapolated (330, 340) beyond the measured range (360) up to the safety closing position (350). From the extrapolated stroke-pressure curve, the closing pressure reserve (320) can be determined. In this way, the functionality of the safety valve can be checked during operation.

The objective of the present invention is to realize an operating state classification system having a classification accuracy that continuously improves through additional learning, and which is appropriately protected from unauthorized duplication of a classification function. In this operating state classification system, in which an edge device and a server are connected by means of a communication network, and which inputs sensor data into a neural network and outputs a state label: the edge device includes a first storage unit which stores an upstream side of the neural network, and a dimensionality reduction unit which inputs the sensor data into the upstream side of the neural network and outputs intermediate data; and the server includes a second storage unit which stores a downstream side of the neural network, an inference executing unit which inputs the intermediate data into the downstream side of the neural network and outputs the state label, and a learning unit which updates the downstream side of the neural network by means of additional learning.

The disclosure provides a computer-implemented method for detecting a failure of a device, wherein the device is connected to a sensor, the method comprising: receiving, by a machine learning model, a trace signal from the sensor indicating a status of the device; encoding, by the machine learning model, the trace signal into a plurality of vector representations; and determining, by the machine learning model, whether the trace signal is valid or invalid based on the plurality of vector representations.

Industrial technical plant controlled and monitored by a process control, wherein a visualization system requests a history of selected process datum for that display period from a process control system and outputs the associated profile as a graphic forming process data points, where the visualization system determines the particular process data point as the average or median of the values of the selected process datum in a collection period characteristic of the particular process data point and where, for the particular process data point, the visualization system also determines the minimum and/or the maximum values of the selected process datum during the collection period such that whenever the minimum is below a predefined minimum value and/or the maximum exceeds a predefined maximum value, the visualization system indicates, together with the particular process data point, a secondary alarm not set by the process control system, but set by the visualization system.

Continuous condition monitoring of a pneumatic system, and in particular for early fault detection, is provided. The condition monitoring unit is formed with an interface to a memory in which a trained normal condition model is stored as a one-class model, which has been trained in a training phase with normal condition data and represents a normal condition of the pneumatic system. Furthermore, the condition monitoring unit comprises a data interface for continuously acquiring sensor data of the pneumatic system by means of a set of sensors, an extractor for extracting features from the acquired sensor data, a differentiator for determining deviations of the extracted features from learned features of the normal state model by means of a distance metric, a scoring unit for calculating an anomaly score from the determined deviations, and an output unit for outputting the calculated anomaly score.

An abnormality detection apparatus is provided, comprising a target data generation unit configured to generate, based on operation-related data resulting from an operation of a movable apparatus, a plurality of target data that are temporally separated, and a detection processing execution unit configured to execute change detection processing on the plurality of target data. An abnormality detection method that is executed by a computer for detecting an abnormality in a movable apparatus is provided, the method comprising generating, based on operation-related data resulting from an operation of the movable apparatus, a plurality of target data that are temporally separated, and executing change detection processing on the plurality of target data.

A method for using sensor data and operational data of an industrial process to identify problems includes gathering sensor data from one or more sensors sensing conditions on equipment of an industrial process, receiving command information about operational commands issued to the equipment of the industrial process, and for each sensor of the one or more sensors, comparing the sensor data with signature information for the sensor. The signature information for the sensor is relevant for operational commands issued to the equipment. The method includes determining if the sensor data of a sensor of the one or more sensors exceeds the signature information corresponding to the sensor, locating a problem with a piece of equipment of the industrial process monitored by the sensor of the one or more sensors based on the sensor data exceeding the signature information for the sensor and issuing an alert reporting the problem.

Systems, methods, and control units for diagnosis and life prediction of one or more electro-mechanical system are provided. One method includes receiving sensor data from a plurality of sensors associated with operation of the electro-mechanical system. The method includes determining at least one system response associated with at least one failure mode of the electro-mechanical system from the sensor data, wherein the sensor data is indicative of the at least one failure mode of the electro-mechanical system. The method further includes receiving at least one simulated response associated with the at least one failure mode of the electro-mechanical system, wherein the at least one failure mode is simulated on a system model of the electro-mechanical system. The method includes generating a hybrid model of the electro-mechanical system in real-time based on the at least one system response and the at least one simulated response, wherein the hybrid model combines the at least one system response and the at least one simulated. The method also includes generating a diagnosis of the electro-mechanical system based on the hybrid model, wherein the diagnosis includes identification of one or more failures in the electro-mechanical system and wherein the one or more failures indicates initiation of degradation of the one or more electro-mechanical system. The method includes predicting a life trend of the electro-mechanical system based on the diagnosis.

According to one embodiment, a monitoring apparatus includes a processing circuit. The processing circuit is configured to generate second data including a prediction value of a second sensor correlated with a first sensor from first data including a measurement value of the first sensor of which a measurement value changes suddenly in a case where the control signal changes, detect an anomaly of the system or an anomaly of at least one sensor, and make it difficult to detect the anomaly in a case where the determination signal indicates that there is a change in the control signal.