Fault diagnosis method based on multi-feature information weighted fusion under spectral clustering analysis

Abstract

The invention relates to a fault diagnosis method based on multi-feature information weighted fusion under spectral clustering analysis. The method comprises the steps of firstly, carrying out spectral clustering analysis on fault equipment; secondly, obtaining the reliability of a local diagnosis evidence of each SVM to each fault mode; thirdly, constructing basic probability distribution througha local diagnosis hard output judgment matrix of each SVM; fourthly, performing weighted processing on the basic probability distribution; fifthly, obtaining the credibility and the uncertainty; andfinally, through a set diagnosis rule, and in combination with the credibility and the uncertainty, performing diagnosis. Compared with the prior art, the method has the advantages that the situationthat evidences of different sources have different reliability for identification of propositions in an identification framework is considered, the conflict between the local diagnosis of the SVMs isreduced, effective combination of the SVMs and an improved evidence theory is realized, and the shortcoming that a synthetic result cannot reflect an objective fact due to the unreliability of identification is overcome.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of power plant equipment, in particular to a fault diagnosis method based on weighted fusion of multi-feature information under spectral clustering analysis. Background technique [0002] When a power plant equipment fails, the monitoring system will provide a large amount of information to the operator in a relatively short period of time, which also contains a large amount of unnecessary uploaded useless information, which brings serious obstacles to the timely processing of the failure. In addition, the information that SCADA / EMS can provide is limited, and this information cannot fully meet the needs of operators for a comprehensive analysis of faults. Malfunctions and refusals of protection and switches, as well as information loss caused by communication channel interference are also unavoidable. The accuracy of fault analysis based on a single source of information will be seriously...

AI Technical Summary

Problems solved by technology

The combination of SVM and evidence theory has a good application prospect in the fault diagnosis of multi-information fusion. However, since each evidence body is regarded as equally important when evidence is synthesized, it does not take into account the impact of different sources of evidence on identification. The fact that the recognition of the propositions in the framework has different reliability, this creates the disadvantage that the synthetic results cannot reflect the objective facts

Images