[1]郭兰中,彭刘阳,窦 岩,等.基于小波包-AR谱和GA-BP网络的轴承故障诊断研究[J].工业仪表与自动化装置,2019,(03):3-7.[doi:1000-0682(2019)03-0000-00]
　GUO Lanzhong,PENG Liuyang,DOU Yan,et al.Research on bearing fault diagnosis based on wavelet packet –auto regressive model spectrum and GA-BP neural network[J].Industrial Instrumentation & Automation,2019,(03):3-7.[doi:1000-0682(2019)03-0000-00]

点击复制

基于小波包-AR谱和GA-BP网络的轴承故障诊断研究

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:

期数:

2019年03期

页码:

3-7

栏目:

出版日期:

2019-06-15

文章信息/Info

Title:

Research on bearing fault diagnosis based on wavelet packet –auto regressive model spectrum and GA-BP neural network

作者:

郭兰中1; 3; 彭刘阳2; 窦 岩1; 3; 姚 腾2

1.常熟理工学院 机械工程学院，江苏 常熟 215500；

2.中国矿业大学 机电工程学院，江苏 徐州221000；

3. 江苏省电梯智能安全重点建设实验室，江苏 常熟 215500

Author(s):

GUO Lanzhong1; 3; PENG Liuyang2; DOU Yan1; 3; YAO Teng2

1. School of Mechanical Engineering, Changshu Institute of Technology,Jiangsu Changshu 215500,China;

2. School of Mechatronic Engineering, China University of Mining and Technology, Jiangsu Xuzhou 221000,China；

3. Jiangsu Key Laboratory for Elevator Intelligent Safety,Jiangsu Changshu 215500,China

关键词:

小波包分解; 自回归谱估计; GA-BP神经网络; 故障诊断

Keywords:

wavelet packet decomposition;  auto-regressive spectrum estimating;  GA-BP neural network;  fault diagnosis

分类号:

TK79

DOI:

1000-0682(2019)03-0000-00

文献标志码:

A

摘要:

针对轴承振动信号具有非平稳、非线性特点，提出将小波包-AR谱和采用遗传算法 (genetic algorithm,GA)优化的BP神经网络相结合的轴承故障诊断方法。该文对滚动轴承振动信号进行小波包分解和自回归(auto-regressive,AR)谱分析以得到不同频段的能量，然后将提取到的特征向量输入到BP神经网络进行模型训练和测试。鉴于BP神经网络的诊断效果并不是很好，因此应用遗传算法对BP神经网络的权值和阈值进行优化并再次进行诊断。对比实验结果表明，经遗传算法优化后的BP神经网络的仿真误差大大降低，相关故障诊断准确率达到了100%。

Abstract:

In view of the non-stationary and non-linear characteristics of bearing vibration signals, a bearing fault diagnosis method combining the wavelet packet-AR spectrum with genetic algorithm (GA) BP neural network is proposed.In this paper,wavelet packet decomposition and auto- regressive(AR) spectrum analysis were performed on the vibration signals of rolling bearings to obtain energy of different frequency bands.The extracted feature vectors were input into BP neural network for model training and testing. Considering that the diagnosis effect of BP neural network is not very good, the weight and threshold value of BP neural network are optimized by genetic algorithm and diagnosed again.The experimental results show that the simulation error of BP neural network optimized by genetic algorithm is greatly reduced, and the relevant fault diagnosis accuracy rate reaches 100%.

参考文献/References:

[1] 孟文俊,徐光华,姜阔胜,等.基于LabVIEW的滚动轴承非平稳过程监测诊断及性能评估系统的开发[J].工业仪表与自动化装置,2015(02):18-22.

相似文献/References:

[1]寇为刚,谭等泰.基于EEMD和小波包分解在滚动轴承故障信息提取中的分析对比[J].工业仪表与自动化装置,2015,(04):101.
　KOU Weigang,TAN Dengtai.Analysis of extracting the fault information about rolling bearings based on EEMD and WPD[J].Industrial Instrumentation & Automation,2015,(03):101.

备注/Memo

备注/Memo:

收稿日期：2018-09-30

基金项目：省教育科学研究项目（17KJA460001）

作者简介：郭兰中(1965),男,陕西渭南市人,西安交通大学博士学位,常熟理工学院机电工程学院教授,研究方向是机械振动和故障诊断。

常用功能