Fault diagnosis using improved pattern spectrum and fruit fly optimization algorithm-support vector machine

作     者：Wang, Bing Hu, Xiong Wang, Wei Sun, Dejian 

作者机构：Shanghai Maritime Univ Logist Engn Coll Dept Mech Engn Shanghai Peoples R China 

出 版 物：《ADVANCES IN MECHANICAL ENGINEERING》 (机械工程进展)

年 卷 期：2018年第10卷第11期

核心收录：

学科分类：08[工学] 0807[工学-动力工程及工程热物理] 0802[工学-机械工程] 

基　　金：National Natural Science Foundation of China [51541506  51275524] 

主　　题：Mathematical morphology roller bearing feature extraction support vector machine fruit fly optimization algorithm 

摘      要：A fault diagnosis method using improved pattern spectrum and fruit fly optimization algorithm-support vector machine is proposed. Improved pattern spectrum is introduced for feature extraction by employing morphological erosion operator. Simulation analysis is processed, and the improved pattern spectrum curves present a steady distinction feature and smaller calculating amount than pattern spectrum method. Support vector machine with fruit fly optimization algorithm which can help seeking optimal parameters is employed for pattern recognition. Experiments were conducted, and the proposed method is verified by roller bearing vibration data including different fault types. The classification accuracy of the proposed approach reaches 87.5% (21/24) in training and 91.7% (44/48) in testing, showing an acceptable diagnosis effect.