基于时频分析的阶次谱在齿轮故障诊断中的应用研究（英文）  

Research and application in gear fault diagnosis based on time-frequency analysis of order spectrum

作　　者：王睿鑫 裴扬[1] 王星宇[1] 张涛[1] 

机构地区：[1]武汉理工大学能源与动力工程学院,武汉430063

出　　处：《机床与液压》2016年第12期23-30,共8页Machine Tool & Hydraulics

基　　金：supported by National Innovation and Entrepreneurship Training Program of China (20151049712002)

摘　　要：对于变转速状态下的机械设备,所产生的信号大部分为非稳态信号。使用频谱分析其信号特征时,会随分析时间长度的变化而变化,无法突显重要的信号特征,导致在故障诊断或辨识上的困难。为了改善此缺点,提出时频阶次谱的分析方法,此方法结合短时傅立叶转换与转速频率阶次,拾取非稳态信号的阶次特征,再结合主成份分析法进行降维,将提取的时频阶次谱主成份输入BP神经网络中,进行齿轮-转子实验平台在非稳态运转下的故障诊断。研究结果表明:此种信号特征不因转速变化而改变,可有效作为机械设备在非稳态状态运转下的故障辨识,其辨识正确率可由93.8%提高至98.9%以上;训练速度由196 s加快至139 s,提高了29%,能达到快速故障诊断的效果。For mechanical equipment under the condition of variable speed,the majority signal which produced is non-stationary signal.And when using the spectral method to analyze the characteristics of signal,it will change with the time,and not to highlight the important signal features,which lead in the difficulties of fault diagnosis and identification.In order to improve this shortcoming,proposed the time-frequency analysis of order spectrum method,this method combines short-time FFT and frequency order of the speed to get the characteristics of non-stationary signals,and also combined with the method of principal component analysis to reduce the dimensions of the extracted time-frequency order spectrum in the BP neural network,which have a fault diagnosis of gear-rotor experimental platform in the non-stationary operation conditions.The results show that：The signal characteristic is not changed by the variable speed,which can be effectively identify the fault of mechanical equipment in the non-stationary operation conditions,and the identification accuracy can be increased from 93.8％ to above 98.9％;the training speed increased from 196 seconds to 139 seconds,increased by 29％,which can achieve the fast fault diagnosis.

关 键 词：非稳态信号 时频阶次谱方法 主成份分析法 BP神经网络 故障诊断 

分 类 号：TH165.3[机械工程—机械制造及自动化]