Title: Fault diagnosis of hydraulic system based on D-S evidence theory and SVM

Authors: Hang Yin; Yongfeng Wang; Wushu Sun; Lintao Wang

Addresses: School of Mechanical Engineering, Dalian University of Technology, Dalian, Liaoning, 116024, China ' SINOTRUK Jinan Special Vehicle Co. Ltd, Jinan, Shandong, 250000, China ' School of Mechanical Engineering, Dalian University of Technology, Dalian, Liaoning, 116024, China ' School of Mechanical Engineering, Dalian University of Technology, Dalian, Liaoning, 116024, China

Abstract: Aiming at the problems of complex fault causes and low diagnosis efficiency of marine valve remote control hydraulic system, a fault diagnosis method combining D-S evidence theory and support vector machine (SVM) classification is adopted. Firstly, the Amesim simulation model of marine valve remote control hydraulic system is established, and the original fault characteristic parameters are obtained by injecting fault operation simulation. Then, the principal component analysis (PCA) method is used to reduce the dimension of the data, and the principal component is used to form the feature vector to train the support vector machine model. Finally, the D-S evidence theory is used to make decision rules for fault judgment, and finally the fault diagnosis is realised. The results show that the accuracy of D-S evidence theory method based on multi-sensor information can be improved by about 3.26% compared with PCA-SVM diagnosis method based on single sensor information.

Keywords: fault diagnosis; feature extraction; D-S evidence theory; PCA-SVM.

DOI: 10.1504/IJHM.2024.135976

International Journal of Hydromechatronics, 2024 Vol.7 No.1, pp.1 - 15

Received: 13 Feb 2023
Accepted: 20 Mar 2023
Published online: 11 Jan 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article