An information processing device includes: a memory; and a processor coupled to the memory and configured to: learn a classification rule that classifies an abnormal degree of a production facility from a text feature amount based on the text feature amount obtained from a number of texts included in a plurality of pieces of log data obtained in a predetermined process of the production facility and production history information of the production facility; extract a text feature amount of log data to be monitored obtained in the predetermined process of the production facility; and determine an abnormal degree of the production facility when the log data to be monitored is obtained based on the text feature amount and the classification rule.

An AI-based anomaly signatures warning recommendation system is provided. The system includes a memory having computer-readable instructions stored therein and a processor configured to execute the computer-readable instructions to access a multi-asset connected system having a plurality of production and/or process lines. Each of the plurality of production lines includes a plurality of assets. The processor is configured to access production data corresponding to a plurality of products manufactured in each of the plurality of production lines and to access sensor signal data corresponding to each of the plurality of assets. The sensor signal data is indicative of health of each of the plurality of assets. The processor is further configured to process the production data and sensor signal data for each of the plurality of assets to identify one or more anomaly instances and to perform similarity analysis on the one or more anomaly instances to identify one or more anomaly signatures. The identified anomaly signatures, anomaly signature groups, anomaly signature group representative, and corresponding sensor signal data are stored in an anomaly signature repository. The anomaly signatures are representative of one or more substantially similar anomaly instances detected prior to unplanned downtime or critical process events in the connected system. The processor is configured to provide early warnings based on the occurrence of the identified anomaly signatures present in the anomaly signature repository to an end user and receive user-feedback from the end user on the warning severity and relevance of the early warnings. The processor is also configured to generate warning recommendations for anomaly signatures that are prioritized based on the end user-feedback.

A computer-implemented method for detecting faults and events related to a system includes receiving sensor data from a plurality of sensors associated with the system. A hierarchical failure model of the system is constructed using (i) the sensor data, (ii) fault detector data, (iii) prior knowledge about system variables and states, and (iii) one or more statistical descriptions of the system. The failure model comprises a plurality of diagnostic variables related to the system and their relationships. Probabilistic reasoning is performed for diagnostic or prognostic purposes on the system using the failure model to derive knowledge related to potential or actual system failures.

A display unit 1b of a design assistance system S highlights an error section of a 3D model and displays at least one of a designation condition recognized by an elimination condition recognition unit 2f and an elimination section.

Provided is a monitoring system including an operation results acquisition unit that acquires time series data of each of a plurality of indexes that indicate operation results of a monitoring target; an overall index generation unit that produces time series data of an overall index by combining a plurality of index values at a same time point based on the time series data of each of the plurality of indexes; and a change point detection unit that analyzes the time series data of the overall index, and detects a point where a significant change appears in the overall index values, as a change point in a status of the monitoring target.

The embodiments of the present disclosure provide a fault diagnosis method, a method for building a fault diagnosis model, fault diagnosis equipment, electronic device, and non-transitory computer-readable storage medium. The fault diagnosis method, for diagnosing a fluid device, which includes a suction end and a discharge end, includes: obtaining a data set for diagnosing the fluid device, wherein the data set includes first characteristic data about the suction end, second characteristic data about the discharge end, and input-output difference data, and the input-output difference data represents data difference between the suction end and the discharge end; obtaining a fault diagnosis model; and determining whether the fluid device is in failure based on the fault diagnosis model and the data set.

In a facility state monitoring system, a sensor node includes a sensor that outputs, as sensor data, data indicating the state of a facility as a monitoring target, a communication unit, and a power supply unit that supplies power to the sensor and the communication unit. The sensor node is commonly used by multiple monitoring targets. A receiver receives the sensor data transmitted from the communication unit. A state detection unit receives the sensor data received by the receiver, and learns, as learning data, normal states of the monitoring targets based on normal sensor data corresponding to normal operations of the monitoring targets. In response to the receiver receiving the sensor data transmitted from the sensor node after learning, the state detection unit compares states of the monitoring targets indicated by the sensor data with the learning data to detect an abnormality occurrence or symptom in the monitoring targets.

Disclosed is a parametric B vs W two pack confirmation test. The test entails receiving a desired alpha risk and output sample data, processing the output sample data to generate an estimated distribution of the output variable for the population of workpieces, determining bins of equal probability in the estimated distribution to define best-of-best (BOB) and worst-of-worst (WOW) regions based on the desired alpha risk, receiving B and W samples predicted to be within, respectfully, the BOB and WOW regions, and determining whether the B sample falls in the BOB region and the W sample falls within the WOW region.

A method comprising a plurality of image acquisition units and a plurality of error detection units at a production plant. The production plant comprises a plurality of work zones, each of which are assigned at least one of the image acquisition units and at least one of the error detection units. A control unit is configured to detect a signal of at least one of the error detection units and based on this detection detect whether an error in the production plant has occurred in the work zone to which the error detection unit is assigned. When the control unit detects an error in a work zone, it provides image data from at least one image acquisition unit of that work zone to a user via an output unit. The invention also relates to a production plant using this method.

Apparatuses, systems, and techniques to monitor health data from components and predict needs for maintenance. In at least one embodiment, monitoring health data of cables having one or more known characteristics ands analyzing the health data to determine the health metrics of the one or more cable to generate profiles of the cables used to predict future health metrics of the cables and related cables sharing known characteristics.