Indexes having local features are automatically selected from sensor data of a plurality of sensors. Sensor data of the plurality of sensors, each associated with the plurality of indexes, is partitioned into a plurality of blocks. A principal component analysis is applied to the sensor data of each of the partitioned blocks and a plurality of principal components are extracted from each of the blocks. A migration distance evaluation unit extracts, from two different blocks, two principal components that form a principal component pair, and calculates a migration distance between each of the principal components regarding the extracted principal component pair. A migration factor index detection unit detects, as a migration factor index, an index among the plurality of indexes configuring the principal components having a large migration distance among the migration distances between each of the principal components calculated by the migration distance evaluation unit.

Currently solutions for early detection of failures in manufacturing utilize predefined threshold levels of the process variables associated with equipment in manufacturing unit/industry plants. The pre-defined threshold and levels thereof are compared with the real values obtained from the manufacturing unit to check behavior of process variables (also referred as ‘process parameters’) and thus are prone to error. The present disclosure provides systems and method for predicting early warning of operating mode of equipment operating in industry plants which is based on transforming conditions on process parameters into conditions on corresponding fuzzy indices based on their thresholds. The fuzzy indices (concordance index, discordance index) of individual conditions are combined into a composite fuzzy index (composite index or degree of credibility) that describes the failure scenario in the process parameter space. A fuzzy logic-based detection is useful for detecting a failure mode early and providing alerts to operators for necessary action.

Disclosed is an approach to implement improved anomaly detection. Improved anomaly detection is provided using MSET-SPRT via Monte Carlo simulation that can address problems with conventional MSET-SPRT approaches and provide improved system performance and accuracy.

An equipment performance modeling platform is disclosed. In certain embodiments, an adaptive sensing coordinator acquires sensor measurements, configures and processes the sensor measurements for a specific statistical model, and sends the measurements to a server. A server performs data processing, provides storage (e.g., local or in a database), and provides an interface for data extraction. Statistical models are used to interpreting sensor values for a type of equipment, and a labeling mechanism labels performance occurrences.

Embodiments of the invention provide a method and system for machine failure prediction. The method comprises: identifying a plurality of basic memory depth values based on a composite sequence of machine failure history; ascertaining weight values for at least one of the identified basic memory depth values according to a pre-stored table which includes a plurality of mappings wherein each mapping relates a basic memory depth value to one set of weight values; and predicting a future failure using a Back Propagation Through Time (BPTT) trained Recurrent Neural Network (RNN) based on the ascertained weight values, wherein weight values related to a first basic memory depth value in the pre-stored table is ascertained based on a second set of weight values related to a second basic memory depth value which is less than the first basic memory depth value by a predetermined value.

This disclosure relates to a method and system for monitoring health and predicting failure of an electro-mechanical machine. In an embodiment, the method may include receiving a plurality of operational parameters with respect to the electro-mechanical machine and determining a set of features and a set of events, based on the plurality of operational parameters. The method may further include detecting one or more fault signatures associated the electro-mechanical machine based on at least one of the plurality of operational parameters, the set of features, or the set of events. The method may further include determining at least one of a time to the possible failure and a remaining useful life of the electro-mechanical machine based on at least one of the plurality of operational parameters, the set of features, the set of events, or the one or more fault signature, by using a hybrid machine learning model.

Systems and methods for real-time monitoring and control of well site operations employ well site edge analytics to detect abnormal operations. The systems and methods receive well site data from a remote programmable automation (PAC) controller at the well site, the well site data representing one or more operational parameters related to the well site operations. A probability is derived for a given slope for each one of the one or more operational parameters as correlated to a different one of the one or more operational parameters to produce correlated probabilities for the one or more operational parameters. A resultant probability is derived from the correlated probabilities for the one or more operational parameters and it is determined whether the resultant probability meets a preselected threshold probability value. A responsive action is initiated if the resultant probability fails to meet the preselected threshold probability value.

A press machine includes: a learning-model generating unit that uses one data from among data collected from sensors, as an objective variable, and uses data other than the one data as an explanatory variable to perform machine learning to generate a learning model for the one data, the generation being performed for all the data; a predicted-value calculating unit that inputs an actually measured value of data other than one data from among the data collected from the sensors, into the learning model for the one data to calculate a predicted value of the one data, the calculation being performed for all the data; a degree-of-abnormality calculating unit that calculates a degree of abnormality based on a difference between an actually measured value and a predicted value of the data; and a degree-of-abnormality outputting unit that outputs the calculated degree of abnormality.

A method and computer program product including training a machine learning model by means of input data and score data, wherein the machine learning model is an artificial neural net, ANN; running the trained machine learning model by applying the first time-series to the trained machine learning model; and outputting, by the trained machine learning model, an output value, comprising at least a second criticality value of the at least one predicted observable process-value indicative of the abnormal behaviour of the industrial process in a predefined temporal distance.

A method of controlling and managing a process control system having a plurality of control loops includes implementing a plurality of control routines to control operation of the plurality of control loops, respectively, wherein the control routines may include at least one non-adaptive control routine. The method then collects operating condition data in connection with the operation of each control loop, and identifies a respective process model for each control loop from the respective operating condition data collected for each control loop. The identification of the respective process models may be automatic as a result of a detected process change or may be on-demand as a result of an injected parameter change. The process models are then analyzed to measure or determine the operation of the process control loops.