您的位置:首页  > 论文页面

基于决策树与神经网络结合的滚动轴承故障诊断方法

发表时间:2019-04-30  浏览量:352  下载量:21
全部作者: 贾智涵,王晨升,朱宏波,李佳,杨光
作者单位: 北京邮电大学自动化学院
摘 要: 提出一种基于决策树与神经网络方法结合的改进滚动轴承故障诊断方法。该方法对滚动轴承振动信号进行经验模态分解(empirical mode decomposition,EMD),使用决策树对分解信号进行故障预测,然后使用属性融合神经网络对决策树预测结果进行学习,将决策树故障特征融合到神经网络分类器中。结果表明,该方法具有更高的故障识别率,可以准确、有效地识别滚动轴承的故障类型。
关 键 词: 机械制造自动化;决策树;神经网络;故障诊断
Title: A rolling bearing fault diagnosis method based on the fusion of decision tree and neural network
Author: JIA Zhihan, WANG Chensheng, ZHU Hongbo, LI Jia, YANG Guang
Organization: School of Automation, Beijing University of Posts and Telecommunications
Abstract: An improved rolling bearing fault diagnosis method based on the fusion of decision tree and neural network is proposed in this paper. Empirical mode decomposition (EMD) is performed on the rolling bearing vibration signal by this method, decision tree is used to predict the failure of the decomposition signal, then the attribute fusion neural network is used to learn the prediction results from decision tree, and the fault features of the decision tree are integrated into the neural network classifier. The results show that this method has a higher fault recognition rate and can accurately and effectively identify the type of faults in rolling bearings.
Key words: mechanical manufacturing and automation; decision tree; neural network; fault diagnosis
发表期数: 2019年4月第2期
引用格式: 贾智涵,王晨升,朱宏波,等. 基于决策树与神经网络结合的滚动轴承故障诊断方法[J]. 中国科技论文在线精品论文,2019,12(2):243-249.
 
0 评论数 0
暂无评论
友情链接