Systems and methods for automatically generating a set of meta-parameters used to train invariant-based anomaly detectors are provided. Data is transformed into a first set of time series data and a second set of time series data. A fitness threshold search is performed on the first set of time series data to automatically generate a fitness threshold, and a time resolution search is performed on the set of second time series data to automatically generate a time resolution. A set of meta-parameters including the fitness threshold and the time resolution are sent to one or more user devices across a network to govern the training of an invariant-based anomaly detector.

Methods and systems for monitoring a brush holder assembly and/or detecting wear of a brush in a brush holder assembly are disclosed. One method includes sending data from a plurality of remote monitoring locations to a central control unit, where the data may be evaluated in order to monitor states of brushes at a plurality of remote electrical facilities. For example, multiple images of a marker tracking longitudinal movement of the brush may be acquired. A comparison of the images, for example, a comparative imaging technique, such as pixel-by-pixel comparison, may then be performed in order to evaluate a condition of the brush, such as the wear rate, wear state, or life expectancy of the brush.

A system for automatic detection of a defect in equipment may include a binary classification model trained to classify laboratory analysis results of an oil sample according to a gradient boosting algorithm, and to output a classification indicator of good or defective for the laboratory analysis results of the oil sample. The system may include a first multiclass classification model trained to classify the laboratory analysis results according to the gradient boosting algorithm if the laboratory analysis results are classified as defective, and to output a predicted defect type for the defect in equipment. The system may include a second multiclass classification model trained to classify the laboratory analysis results according to the gradient boosting algorithm and the predicted defect type, and to output a predicted corrective action pertaining to the equipment based on the predicted defect type for the defect in equipment.

An information processing system includes a first acquisition unit configured to acquire first information indicating a state of a control system including a control device in response to an occurrence of a request or an event related to an abnormality that has occurred in the control system, an abnormality detail determination unit configured to determine details of the abnormality that has occurred on the basis of the first information, a second acquisition unit configured to request, in accordance with the details of the abnormality, a user to provide second information and acquire the second information from the user, a cause conjecture unit configured to conjecture a cause of the abnormality that has occurred on the basis of the first information and the second information, and a notification means configured to notify the user of the conjectured cause of the abnormality.

A petrochemical plant or refinery may include equipment such as pumps, compressors, valves, exchangers, columns, adsorbers, or the like. Some petrochemical plants or refineries may include one or more sensors configured to collect operation information of the equipment in the plant or refinery. A faulty condition of a process of the petrochemical plant may be diagnosed based on the operation of the plant equipment. A diagnostic system, which may receive operation information from the one or more sensors, may include a detection platform, an analysis platform, a visualization platform, and/or an alert platform.

A master processor may retrieve historical and real time machine and human data related to computer system health. The master processor may utilize machine learning and artificial intelligence to predict potential computer malfunctions. The master processor may output notifications regarding the potential computer malfunctions in order to prevent the computer malfunctions from occurring.

Provided is a method for analyzing and designing a physical system architecture of a safety-critical system, wherein a physical system analysis model representing the physical system architecture of the safety-critical system is modified incrementally until calculated failure rates of failure modes of the physical system analysis model are less or equal to failure rates of corresponding failure modes of a functional system analysis model representing a functional system architecture of the safety-critical system.

[Problem] To provide a manufacturing process analysis method for specifying a hindering factor that causes a variation in product performance and for stabilizing product performance.

[Solution ] A manufacturing process analysis method comprises: a step (S1) for collecting product data indicating the quality of a product and process data indicating manufacturing conditions of a product; a step (S2) for standardizing the process data so that the data are converted into an intermediate function; a step (S3) for performing principal component analysis on the intermediate function to derive a principal component load amount and a principal component score of the process data; a step (S4) for applying cluster analysis to the principal component score to classify manufacturing process lots into a plurality of groups; a step (S5) for determining relative merit of each group on the basis of product data soundness corresponding to the principal component score belonging to the group; and a step (S6) for specifying a hindering factor that contributes to the relative merit of the group

In a method, a database system, a computer, and a medical system for the identification of faulty structural parts to be exchanged of a medical device, an identification algorithm is executed to calculate and emit an exchange data record that identifies a structural part to be exchanged, dependent on for a read-in error message from the medical device. The identification algorithm accesses a database system with a simulation model in which automatically generated error patterns (are stored in order to perform an analysis on these stored error patterns, so as to calculate the exchange data record. An error pattern is an association between the error message, an exchange data record, and an evaluation data record.

A monitoring method, the purpose of which is, when a loss of power is detected in an aircraft engine, to generate an alarm in the form of a single message displayed on a display screen in the cockpit, in order to indicate if the level of damage suffered by the engine is critical or not. The steps implemented are based on alarm signals transmitted by a central processing unit of the engine and also on alarm signals transmitted by a diagnostic device for the onboard systems of the aircraft, in order to take account of both the situation of the engine and also the situation of the systems surrounding the engine which can be affected by damage to an engine.