基于双树复小波和自适应权重和时间因子的粒子群优化支持向量机的轴承故障诊断  

Bearing Fault Diagnosis Based on DTCWT and AWTFPSO-optimized SVM

作　　者：张淑清[1] 胡永涛[1] 姜安琦[2] 吴迪[1] 陆超[1] 姜万录[3] 

机构地区：[1]燕山大学电气工程学院,秦皇岛066004 [2]中南大学信息科学与工程学院,长沙410006 [3]燕山大学机械工程学院,秦皇岛066004

出　　处：《中国机械工程》2017年第3期327-333,共7页China Mechanical Engineering

基　　金：国家自然科学基金资助项目(51475405;61077071);河北省自然科学基金资助项目(F2016203496;F2015203413)

摘　　要：提出了一种基于双树复小波和具有自适应权重和时间因子的粒子群算法优化支持向量机的轴承故障诊断方法。首先对机械振动信号进行DTCWT变换,提取能量熵作为特征向量。然后采用AWTFPSO算法优化SVM,实现轴承故障诊断。不同方法的对比实验及分析结果表明,该方法速度快、准确率高。Based on DTCWT and SVM improved by AWTFPSO,a new method of bearing fault diagnosis was proposed.The mechanical vibration signals were first processed by DTCWT and the energy entropy was extracted as the feature vector.Then,SVM optimized by AWTFPSO was introduced to bearing fault diagnosis.Comparions of different methods show that the proposed method has advantages of high speed and accuracy.

关 键 词：双树复小波 支持向量机 粒子群算法 自适应权重和时间因子 故障诊断 

分 类 号：TN911.6[电子电信—通信与信息系统]