摘要
为了解决自确认气动执行器的故障诊断问题,提出了一种基于最小二乘支持向量机(LS-SVM)回归建模和支持向量多分类机(SVM)的执行器故障诊断方法,该方法利用LS-SVM回归建立气动执行器的正常模型,将实际输出与模型输出比较,产生残差作为气动执行器的非线性故障特征向量。利用聚类方法设计了层次支持向量多分类机结构,以残差作为输入建立支持向量多分类机,判断气动执行器故障类型。利用DABLib生成的故障数据对所研究方法进行了验证,并与基于PCA-SVM的故障诊断方法进行了比较,结果表明该方法有效的解决了气动执行器故障诊断的小样本和非线性问题。
To solve the fault diagnosis problem of self-validating pneumatic actuator, an actuator fault diagnosis approach based on least square support vector machine(LS-SVM)regression modeling and support vector machines (SVM) multi-classifier is proposed. The LS-SVM regression is used to establish the normal models of the pneumatic actuator. The residuals generated by comparing the output of the models and the actual actuator are used as the nonlinear features of the pneumatic actuator. Then, the structure of the hierarchical support vector machines for multi-classification is designed using clustering method, which is used as fault classifiers to identify the condition and fault pattern of the actuator. The proposed approach is verified using fault data generated by DABLib model and compared with PCA-SVM fault diagnosis approach. The results indicate that the proposed approach resolves the small sample and nonlinear problem in pneumatic actuator fault diagnosis.
出处
《传感技术学报》
CAS
CSCD
北大核心
2013年第11期1610-1616,共7页
Chinese Journal of Sensors and Actuators
基金
国家自然科学基金青年基金项目(61104023)
关键词
执行器故障诊断
最小二乘支持向量机
支持向量多分类机
残差
特征提取
actuator fault diagnosis
least square support vector machine (LS-SVM)
support vector machine (SVM)multi-classifier
residuals
feature extraction