Bogie Fault Identification Based on EEMD Information Entropy and Manifold Learning. Issue 1 (July 2017)

• Record Type: Journal Article
• Authors: Qin, Na; Sun, Yongkui; Gu, Pengju; Ma, Lei
• Is Part Of: IFAC-PapersOnLine. Volume 50:Issue 1(2017)
• Page Start: 315
• Page End: 318
• Publication Date: 2017-07
• Subjects: High speed train -- fault recognition -- empirical mode decomposition information entropy -- feature extraction -- manifold learning; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2017.08.052
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: In order to realize high-speed train bogie's fault intelligent identification by data driven method, this paper proposes a new fault diagnosis framework. The main idea of the framework is to use features of ensemble empirical mode decomposition entropy, to reduce the feature dimension by Isometric Feature Mapping Manifold Learning, and identify the faults using support vector machine. The proposed method increases the fault detection rate effectively. Experimental results verify that the new method increases the accuracy of fault detection rate of the bogie failure.