Aspects described herein relate to a centralized computing system that interacts with a plurality of data centers, each having an edge server. Each edge server obtains sensor information from a plurality of sensors and processes the sensor information to detect an imminent shutdown and sends emergency data to a centralized processing entity when detected. In order to make a decision, the edge server processes the sensor data based on dynamic sensor thresholds and dynamic prioritizer data by syncing with the centralized computing system. Because of the short time duration to report emergency data before an imminent complete shutdown, an edge server may utilize a quantum data pipeline and quantum data storage as a key medium for all data transfer in a normal condition and at the time of emergency for internally transporting processed sensor data and providing the emergency data to the centralized processing entity.

A system for rule management, predictive maintenance and quality assurance of a process using automatic rule formation comprising a plurality of sensors capable of being attached to at least one machine for measuring at least one information about the process and machine operation. The system comprises a server connected to the sensors over a wireless communication network and running a reconfigurable rule management program for identifying and processing the particular process and machine information related to at least one process received from the plurality of sensors. A controller in communication with the server capable of controlling the process based on a rule set by the rule engine. The rule engine automatically detects the normal process data, classifies the received data based on the dynamic rule formed by the rule engine and finds anomalies in the process or machine operation for predictive maintenance and process quality assurance.

A computer-implemented method for determining an operational state of an industrial plant includes acquiring alarms raised within the plant and adding them to a pool of important alarms, determining whether a physical state of the plant indicated by a first alarm causes a second alarm or meets a predetermined state-dependent condition and, if so, moving the first alarm to a pool of informative alarms; and determining the operational state of the plant and/or a corrective action for improving this operational state based on the alarms in the pool of important alarms.

A method is provided for diagnosing a failure on an aircraft that includes aircraft systems and monitors configured to report effects of failure modes of the aircraft systems. The method includes receiving a fault report that indicates one or more of the monitors that reported the effects of a failure mode in an aircraft system of the aircraft systems, and accessing a fault pattern library that describes relationships between possible failure modes and patterns of those of the monitors configured to report the effects of the possible failure modes. The method also includes diagnosing the failure mode of the aircraft system from the one or more of the monitors that reported, and using the fault pattern library and a greedy selection algorithm, determining a maintenance action for the failure mode; and generating a maintenance message including at least the maintenance action.

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.

Systems, methods, and processor-readable storage media for AI continued learning in electrical power grid fault analysis use historical fault record data to generate a fault cause prediction model for predicting the cause of a fault, and modify the fault cause prediction model based on additional technician data received from power grid technicians. The systems disclosed herein additionally receive an indication of a fault which has occurred in a power grid, obtain a prediction of the cause of the fault by applying the indication of the fault to the fault cause prediction model, and cause the predicted cause of the fault to be remedied.

Method for determining a reliability state of an electrical network, the electrical network comprising a plurality of interconnected electrical devices, the method including the following steps: a) identifying an undesired event at a given location in the electrical network; b) traversing at least one subset starting from the given location; c) identifying an electrical device of the electrical network; d) determining a list of events of concern that are associated with the identified electrical device and could result in the undesired event; e) determining a total unavailability value associated with the identified electrical device; f) repeating steps b) to e); and g) calculating a reliability state of the electrical network on the basis of the total unavailability values respectively associated with the traversed electrical devices.

An abnormality diagnosis method for diagnosing an abnormality in equipment includes acquiring multivariate time-series data for a plurality of measurement items from the equipment, diagnosing an abnormality in operational state of the equipment based on the multivariate time-series data, and diagnosing a cause of the abnormality. The diagnosing a cause of the abnormality includes extracting a feature of a first section before the occurrence of the abnormality from the multivariate time-series data of the first section, extracting a feature of a second section after the occurrence of the abnormality from the multivariate time-series data of the second section, obtaining an amount of change in feature from a difference between the feature of the first section and the feature of the second section, and diagnosing a measurement item that is the cause of the abnormality based on the amounts of change in features of the plurality of measurement items.

An approach for diagnosing degradations in performance and malfunctions in sensor networks is disclosed. This approach is based on so-called “fault signatures”. Such fault signatures are generated for known fault conditions through a statistical analysis process that results in each known fault having a unique fault signature. Such unique fault signatures can then point to the root cause of a problem.

One embodiment includes a monitor module for a first device, wherein the first device is configured to obtain measurement data from a second device, to compare the measurement data to a reference value, and to send a signal when the measurement data in comparison to the reference indicates an error condition. Machine learning can be used, where a head-end is capable of modifying the second device when the reference value so indicates. This enables various embodiments to fix the second device without human intervention