文章基本信息

标题：Sensor Fault Diagnosis Based on Ensemble Empirical Mode Decomposition and Optimized Least Squares Support Vector Machine
本地全文：下载
作者：Ding, Guojun ; Wang, Lide ; Shen, Ping 等
期刊名称：Journal of Computers
印刷版ISSN：1796-203X
出版年度：2013
卷号：8
期号：11
页码：2916-2924
DOI：10.4304/jcp.8.11.2916-2924
语种：English
出版社：Academy Publisher
摘要：A fault diagnosis method for sensor fault based on ensemble empirical mode decomposition (EEMD) energy entropy and optimized structural parameters least squares support vector machine (LSSVM) is put forward in this paper. Firstly, the original output fault signals are pretreatment with EEMD, and then the EEMD energy entropy is extracted as the fault feature vector. Then the radial basis function (RBF) kernel function parameters and the regularization parameter of LSSVM are optimized by using chaotic particle swarm optimization (CPSO) algorithm. Finally, with the applying of proposed diagnosis method, the model of sensor fault diagnosis is built for identification and decision. The diagnostic results show that the proposed method can identify sensor fault effectively and accurately.
关键词：Fault diagnosis;EEMD energy entropy;LSSVM;CPSO;Pressure sensor