Hydraulic Servo System Fault Diagnosis Based on SVM

作     者：LiTieying, LuanJiahui, ShanTianmin School of Reliability and Systems Engineering,BUAA,Beijing 100191,China 

会议名称：《2012 International Conference on Future Information Technology and Management Science & Engineering(FITMSE 2012)》

会议日期：2012年

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 082503[工学-航空宇航制造工程] 0835[工学-软件工程] 0825[工学-航空宇航科学与技术] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China (Grant No. 61074083, 50705005) as well as the Technology Foundation Program of National Defense (Grant No. Z132010B004) 

关 键 词：fault diagnosis, SVM, Hydraulic servo system, support vector observer, support vector classifier. 

摘      要：Hydraulic servo system plays an important role in aircraft power supply system. It is of great significance to study the fault diagnosis method for aircraft health management. This paper introduces a Support Vector Machine (SVM) approach to build an observer on Hydraulic servo system and obtain the fault diagnosis results by identifying of the residuals. A support vector observer estimates the output of the system. By comparing with system output, the residual is generated and then clustered by a support vector classifier for fault detection. Finally we use MATLAB/Simulink to establish fault diagnosis model and verify the correctness of this method.