风电齿轮箱故障诊断的SVM参数优化  

SVM Parameter Optimization in Fault Diagnosis for Wind Power Gear Box

作　　者：赵春华[1] 董海江[1] 钟先友[1] 

机构地区：[1]三峡大学,宜昌443002

出　　处：《中国机械工程》2015年第16期2222-2225,共4页China Mechanical Engineering

基　　金：国家自然科学基金资助项目(51075234)

摘　　要：针对风电齿轮箱易出现齿轮断齿、点蚀、磨损等故障问题,提取风电齿轮箱非平稳非线性振动信号的提升小波包能量熵,利用支持向量机(SVM)进行故障诊断。为提高算法的分类精度,利用遗传算法对参数进行优化处理,试验结果表明,优化后获得的最佳参数能够提高SVM测试样本的预测精度。In a wind turbine gearbox,gear teeth produced frequently the problems such as broken, pitting and wear failure.This paper will extract non-stationary nonlinear vibration signals of wind power gear box and enhance wavelet packet energy entropy with using SVM to fault diagnosis process-ing.To improve the classification accuracy of the algorithm,genetic algorithms was used to optimize of parameters.Tests show that the best parameters can improve the prediction accuracy of the SVM to test samples.

关 键 词：风电齿轮箱 故障诊断 支持向量机 参数优化 

分 类 号：TH17[机械工程—机械制造及自动化]