Intelligent substation fault diagnosis based on optimization support vector machine. Issue 1 (June 2020)

• Record Type: Journal Article
• Authors: Chen, Bin; Liu, Guangzhen; Mu, Zongjun; Xu, Huibo; Tian, Zhao; She, Wei; Liu, Wei
• Is Part Of: IOP conference series. Volume 526:Issue 1(2020)
• Publication Date: 2020-06
• Subjects: Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/526/1/012101
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: In view of the present intelligent substation fault diagnosis of complicated structure, sample data acquisition difficult, randomness of failure and other issues, build a kind of intelligent substation fault diagnosis based on the optimization of support vector machine (SVM) model, first of all, through the principal component analysis (pca) to simplify the fault source and key fault feature extraction, reduce the complexity of fault diagnosis.Then, based on the characteristics of the operation mode of the substation, the multi-classification SVM classifier is constructed and optimized by the imperial competition algorithm to find the optimal parameters. At last, the fault events of real substation are verified by experiments. The results show that the proposed fault diagnosis method can effectively solve the problem of less training samples and has a better diagnosis effect.