Equipment fault diagnosis method based on knowledge and data fusion driving

Abstract

The invention discloses an equipment fault diagnosis method based on knowledge and data fusion driving. The method comprises the following steps: S1, collecting equipment mechanism knowledge and equipment operation data of related diagnosis target equipment; s2, extracting classification indexes in the equipment mechanism knowledge, and combining the classification indexes to obtain rule nodes of the atlas; s3, marking the equipment operation data by taking the rule nodes as a classification basis; s4, carrying out classification through an improved long and short term memory network model, and extracting a relationship between rule nodes; s5, the rule nodes and the node relation are combined to construct a fault map; and S6, inputting fault equipment data into the fault map for classification, and outputting fault types and related faults. Aiming at the problem that a traditional fault diagnosis method depends on single knowledge or data, the fault graph is constructed in combination with equipment mechanism knowledge and equipment operation data for diagnosis, full utilization of the knowledge and the data is ensured, and the accuracy of equipment fault diagnosis under multiple classifications is ensured.

Description

technical field [0001] The invention relates to the field of equipment fault diagnosis, in particular to an equipment fault diagnosis method driven by knowledge and data fusion. Background technique [0002] In the context of Industry 4.0, machinery and equipment are becoming larger and larger, more complex in structure, and automated and intelligent in operation. Once some components fail abnormally, it may lead to problems in the entire equipment. Therefore, accurate and timely fault diagnosis and prediction are increasingly important and become the field of intelligent manufacturing. research hotspot. [0003] At present, equipment fault diagnosis is usually divided into mechanism modeling methods and data-driven methods. The mechanism-based modeling method only needs a small amount of detection data to analyze and diagnose, and has a high accuracy rate for judging a single fault. For example, the article [Zheng Jinde et al. Mechanical fault diagnosis method based on ada...

AI Technical Summary

Problems solved by technology

The above methods have achieved good results, but in practical applications, data-driven methods require comprehensive data coverage, and in practical applications, it takes a long time to accumulate effective data, which is difficult to meet

Images