基于小波包和Elman神经网络的液压泵故障诊断  

Fault diagnosis based on wavelet package and Elman neural network for a hydraulic pump

作　　者：刘红梅[1] 王少萍[1] 欧阳平超[1] 

机构地区：[1]北京航空航天大学自动化科学与电气工程学院,北京100083

出　　处：《北京航空航天大学学报》2007年第1期67-71,共5页Journal of Beijing University of Aeronautics and Astronautics

基　　金：北京市自然科学基金资助项目(4012009)

摘　　要：针对液压泵出口故障检测信号信噪比低、难以进行故障特征提取的特点,及传统的BP网络进行故障诊断时网络学习具有收敛速度慢和学习、记忆不稳定的缺陷,提出了一种将小波包变换和改进Elman神经网络相结合,进行液压泵故障诊断的新方法.利用具有紧支结构的小波函数对信号进行分解,削减小波系数以滤除信号中的噪声;单支重构以有效提取各频带的故障特征,并以频带能量作为识别故障的特征向量;应用改进的E lman神经网络建立从特征向量到故障模式之间的映射,实现液压泵故障分类.试验结果表明,采用小波包和改进E lman神经网络相结合的方法可有效的实现液压泵故障的诊断.Considering the low signal-to-noise, faint failure characteristics of hydraulic pump, and slow convergence speed and the instability of BP network, a new fault diagnosis method based on the wavelet package analysis and Elman neural network is presented. The wavelet package analysis is adopted to eliminate the noise in the actual signals and to extract the fault characteristics. Through signal decomposition and single reconfiguration with wavelet package, the noise can be eliminated from signals to strengthen the failure signal and to extract fault feature in every frequency bands effectively. Energy of various frequency bands acting as the fault feature vector is input into the improved Elman neural network to realize the mapping between the feature vector and the fault mode. The experiment results verified the effectiveness of the proposed method in the hydraulic pump fault diagnosis.

关 键 词：小波包分析 ELMAN神经网络 液压泵 故障诊断 

分 类 号：TH137[机械工程—机械制造及自动化]