多切面分类改进独立成份与支持向量机集成故障诊断方法

摘要

本文采用多切面分类方法改进独立成份（ICA）与支持向量机（SVM）集成诊断方法．在高维独立成份特征空间中采用多切面分类方法在不同切面上分别建立sVM故障分类模型．对不同切面的分类情况进行故障识别，改善ICA-SVM集成故障诊断性能．将ICA-MSVM集成故障诊断方法对动态执行器基准平（DAMADICS）的19种阀门故障模式进行仿真验证，结果表明改进的ICA-MSVM方法有效地提高了故障诊断精度．%The integrated diagnosis method of independent component analysis （ICA） and supportvectormachines （SVM） is improved by multisection classification. Fault classification model of SVM is designed for each section in the high dimensional characteristic space. By diagnosing the fault type in different section, we improve the ICASVM fault diagnosis performance. This method has been applied to diagnose 19 types of valve failures on the dynamic actuator refer ence platform （DAMADICS）. Simulation results show that the ICAMSVM fault diagnosis method based on multisection classification effectively improves the accuracy of fault diagnosis.