文档介绍：摘要
故障诊断无论在生产安全还是在国民经济当中无疑具有重要的意义。近年来,由于计算机技术、信号处理、人工智能、模式识别等技术的发展,促进了故障诊断技术的不断发展。针对小波神经网络精度高,学习速度快的特点,我们将小波神经网络应用于机械故障诊断中。
在查阅大量文献的基础上,本文对故障诊断技术及故障诊断领域比较活跃的理论和方法,包括小波变换、神经网络以及近年来在故障诊断领域中的研究热点——小波神经网络进行了综述。
针对设备运行中存在的大量的非线性现象和快速傅立叶变换在非线性信号的处理中存在一定的局限性,同时由于小波变换具有时频特性,而且是对信号进行分析和处理的一个有效的工具,所以本文在介绍小波变换理论的同时,还阐述了它在机械故障诊断中的应用以及小波在分析非平稳信号时的优越性。
由于将小波函数作为神经网络的激发函数的小波神经网络可以获得更好的诊断效果,本论文主要研究了由morlet小波函数来代替神经网络中的传统激发函数(S函数)的
“紧支型”小波神经网络及其在旋转机械故障诊断中的应用。传统的前馈神经网络多采用BP算法对网络进行训练,但是BP算法具有容易陷入局部极小值,收敛速度慢等局限性。针对这些局限性,本文对传统的BP算法进行了改进,引入了动量项,经过实例证明其收敛速度有很大的提高。
最终通过实例证明,本文所研究的基于小波神经网络的故障诊断方法在旋转机械故障诊断中能够很好的进行故障诊断并且具有较快的收敛速度。
关键词:故障诊断,小波变换;神经网络;BP算法;小波神经网络
Abstract
It is out of question that default diayosis is very important both in safety production andin national recent years,with the development puter technology,signal processing,artificial intelligence,mode identification and etc,the fault diagnosis technology has been continuously promoted. Because wavelet neural nefwork has the following merits: high precision and learning rate fast, we use wavelet work in the field of fault diagnosis.
Based on a multitude of literature,this paper reviewes that the fault diagnosis technology and the active theory and methods in the field of fault diagnosis which include wavelet transform,work and wavelet work. The wavelet work has e a focus in the field of fault diagnosis recently.
In view of the many nonlinear vibration of running-machine and Fast Fourier Transform has some limits in the dispose of nonlinear signal,at the same time,because wavelet transform has the time-frequency characteristics and wavelet analysis is an effective tool to process signals,this paper not only introduce the theory of wavelet transform,but also set forth its application in fault diagnosis and its superiority of processing nonlinear signal.
Because wavelet work has the better diagnosis effect while using wavelet function work's excitation function,so this paper mainly studies pact wavelet work