An industrial system event playback method based on health analysis

By using a health-based analysis method, combining performance impact weights and asset importance weights, and employing a multilayer perceptron neural network for fault diagnosis and screening, the problem of unscientific event screening in industrial system event playback is solved, enabling efficient display of critical events and decision support for managers.

CN120373663BActive Publication Date: 2025-10-17INSPUR GENERSOFT CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202510839057.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-23
Publication Date
2025-10-17
Estimated Expiration
2045-06-23

AI Technical Summary

Technical Problem

Existing technologies lack multi-level analysis in industrial system event replay, leading to unscientific event selection, inability to accurately reflect core system issues, and impacting the scientific nature of management decisions.

Method used

A health-based analysis method is adopted, which uses a multilayer perceptron neural network to diagnose faults in the real-time operating parameters of the production unit. By combining performance impact weights and asset importance weights, a severity score for fault events is calculated, and fault events are screened and replayed based on the severity score.

Benefits of technology

It enables the scientific screening and efficient playback of key events, ensuring that high-value or high-impact failure events are prioritized for display, thereby improving managers' efficiency in understanding the health status of the system and the accuracy of their decision-making.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention discloses an industrial system event playback method based on health analysis, which belongs to the field of industrial system event playback data processing technology, including: judging the fault type according to the real-time operating parameters of the production unit through a fault diagnosis model, and obtaining the health score change value corresponding to the production unit; responding to the playback start and end time settings, obtaining multiple fault events within the playback start and end time interval, and obtaining the corresponding importance score of the fault event according to the health score change value of the fault event, as well as the performance impact weight and asset importance weight of the corresponding production unit; responding to the total playback video length and the display length of a single fault event, obtaining the number of fault events for playback, and screening the fault events according to the importance score. The present invention solves the problems of unscientific event screening and poor event playback tracing effect in the prior art through multi-dimensional weight-driven event screening logic and dynamic playback strategy.
Need to check novelty before this filing date? Find Prior Art