Equipment fault diagnosis method, device and system based on multi-source monitoring data fusion

Abstract

The embodiment of this specification discloses a method, device and system for equipment fault diagnosis based on multi-source monitoring data fusion. The method includes acquiring multi-source monitoring data of the target equipment; The monitoring data is subjected to data segmentation processing, and the multi-source monitoring data after segmentation processing based on different time window lengths are stored in different data sets respectively, and the multi-source monitoring data sets corresponding to each time window length are obtained; Feature extraction is performed on the multi-source monitoring data after the multi-source monitoring data is centrally segmented to obtain multi-source feature data corresponding to the corresponding time window length; the first fusion processing is performed on the multi-source feature data corresponding to each time window length to obtain multi-time window Fusing data: performing fault diagnosis on the target device by using the multi-time window fusion data, and obtaining a fault diagnosis result of the target device. Therefore, the accuracy of fault diagnosis of the target device can be greatly improved.

Description

technical field [0001] This specification relates to the technical field of equipment fault diagnosis, and in particular, relates to a method, device and system for equipment fault diagnosis based on multi-source monitoring data fusion. Background technique [0002] Motor-driven equipment is widely deployed in various scenarios in the industry and is the main device driving various important production activities. As an important part of the production system, the safe and reliable operation of motor-driven equipment is the basis for continuous and stable production. Once the motor-driven equipment fails, it will affect the overall performance of the production equipment, affect production efficiency, cause economic losses, and even cause catastrophic accidents in severe cases. Therefore, it is of great significance to ensure the safe operation of the production system to carry out early fault diagnosis and traceability of motor-driven equipment through monitoring informati...

AI Technical Summary

Problems solved by technology

[0004] When processing fused data, it is usually necessary to segment the data with a fixed-length time window for subsequent analysis and identification, but it is usually difficult to determine the optimal time window length in practical applications

At the same time, even if the optimal time window length can be determined, for different equipment, different failure modes, and different parameter types, it is difficult to extract characteristic data that accurately characterizes different failure modes of different equipment based on a single time window length. Thus affecting the accuracy of equipment fault diagnosis and the universality of diagnostic methods

Images