武汉工程大学学报2011，Vol.33Issue(5)：82-88,7.DOI:10.3969/j.issn.1674-2869.2011.05.022
基于混合特征提取和WNN的齿轮箱故障诊断
Gearbox fault diagnosis based on hybrid feature extraction and wavelet neural network
摘要
Abstract
A new method of fault diagnosis for gearbox based on hybrid feature extraction and wavelet neural network (WNN) was proposed in this paper.The time domain analysis, wavelet packet decomposition and wavelet decomposition were applied to extract the fault feature information of vibration signals collected from gearbox.The extracted feature values were regarded as the feature input vector of WNN.The scale parameters, translation parameters, weight values and threshold values in WNN structure were optimized by traditional back- propagation (BP) algorithm.Three gear fault modes were simulated with different crack sizes in the experiment.The effectiveness and reliability of the presented fault diagnosis method were demonstrated through identification and classification for several fault modes.关键词
齿轮箱/特征提取/小波神经网络/故障诊断Key words
gearbox/ feature extraction/ wavelet neural network/ fault diagnosis分类
机械制造引用本文复制引用
鲁艳军,陈汉新,贺文杰,尚云飞,陈绪兵..基于混合特征提取和WNN的齿轮箱故障诊断[J].武汉工程大学学报,2011,33(5):82-88,7.基金项目
湖北省教育厅科学技术研究重大项目(Z20101501) （Z20101501）
武汉市科技局科技攻关项目(201010621237) （201010621237）
