An Adaptive Threshold Based on Support Vector Machine for Fault Diagnosis

摘要：

Considering the drawback of the big error when using fixed threshold in fault diagnosis for hydraulic servo system, many factors that may affect the fault threshold are analyzed.By integrating the key factors in threshold model,such as modeling error,random disturbance,input instructions,system current status and etc, an adaptive threshold scheme for fault diagnosis is proposed in this paper,which is based on a pattern recognition algorithm called support vector machine (SVM).It is very effective to adoptively adjust the fault threshold according to a variety of influencing factors.And the robustness is improved by the proposed method,which is verified by experimental results.

关键词： Adaptive threshold, Support vector machine(SVM) fault diagnosis hydraulic servo system actuator

作者: Hongmei Liu Chen Lu Wenkui Hou Shaoping Wang

作者单位: Dept.of system engineering of engineering technology Beihang University Beijing 100191.China Dept.of system engineering of engineering technology Beihang University Beijing 100191,China

会议类型: 国际会议

会议名称: 2009 8th International Conference on Reliability,Maintainability and Safety(第八届中国国际可靠性、维修性、安全性会议)

会议地点: 成都

会议语种:英文

页码: 907-911

在线出版日期: 2009-08-24（万方平台首次上网日期，不代表论文的发表时间）