机械科学与技术2018，Vol.37Issue(2)：237-243,7.DOI:10.13433/j.cnki.1003-8728.2018.0212
Adaboost_SVM集成模型的滚动轴承早期故障诊断
Early Fault Diagnosis of Rolling Bearing based on Ensemble Model of Adaboost SVM
摘要
Abstract
Aiming at the early fault features of roller bearings are too weak so that it is difficult to get effective identification,an early fault diagnosis method based on Adaboost_SVM integrated learning model for rolling beating early fault diagnosis is proposed in this paper.Firstly,those sensitive feature parameters are selected through analyzing the feature parameters developing trend based on the rolling beating vibration data in whole life process acquired by the university of Cincinnati.Then,the ensemble learning model with Adaboost_SVM is constructed,and applied to the rolling beating early fault identification.Adaboost can adaptively improve the classification performance of conventional SVM.Compared with the traditional single SVM classifier,Adaboost_SVM has the best stability and the highest early fault diagnosis accuracy.The experimental results show that the Adaboost_SVM can effectively diagnose rolling bearing early failure modes with those sensitive feature parameters.关键词
集成学习模型/支持向量机/Adaboost/滚动轴承/故障检测Key words
Ensemble learning model/support vector machine (SVM)/Adaboost/roller beating/fault detection分类
信息技术与安全科学引用本文复制引用
陈法法,杨晶晶,肖文荣,程珩,张发军..Adaboost_SVM集成模型的滚动轴承早期故障诊断[J].机械科学与技术,2018,37(2):237-243,7.基金项目
国家自然科学基金项目(51405264,51475266)与湖北省重点实验室开放基金项目(2017KJX02)资助 （51405264,51475266）
