基于小波神经网络的齿轮箱故障诊断研究  

Gearbox fault diagnosis based on wavelet neural network

作　　者：汪鲁才[1] 彭滔[1] 张颖[1] 

机构地区：[1]湖南师范大学工学院,长沙410081

出　　处：《计算机工程与应用》2007年第28期203-205,226,共4页Computer Engineering and Applications

基　　金：湖南省自然科学基金(the Natural Science Foundation of Hunan Province of China under Grant No.04JJ40042)。

摘　　要：论述了小波神经网络的系统结构及算法,并根据齿轮振动信号的频域变化特征,提取特征向量作为输入,利用小波神经网络建立特征向量与故障模式之间的映射关系,建立了基于该算法的齿轮故障诊断模型。仿真结果表明:与传统的BP神经网络相比,该模型显著缩短了训练时间。该小波神经网络进行机械故障诊断是有效的。This paper focuses on the system structure and algorithms of Wavelet Neural Network.For various features of gear vibrating signals in frequency domain,feature vectors are extracted as inputs of the Wavelet Neural Network which are capable of mapping the feature vectors to the corresponding fault modes.Based on this algorithm,a gear fault diagnosis model has been designed.Simulation results indicate this model, compared with the conventional BP neural network model,can remarkably reduce the training time.It is feasible for mechanical fault diagnosis.

关 键 词：小波分析 神经网络 故障诊断 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]