基于峭度和小波包能量特征的齿轮箱早期故障诊断及抗噪研究  

Investigation on Incipient Fault Diagnosis of Gears based on Kurtosis and Wavelet Package Energy Features

作　　者：陈水宣[1] 邹俊[2] 易际明[1] 谢丹[1] 

机构地区：[1]厦门理工学院机械工程系,福建厦门361024 [2]浙江大学流体传动及控制国家重点实验室,浙江杭州310027

出　　处：《机械传动》2012年第11期9-14,共6页Journal of Mechanical Transmission

基　　金：国家自然科学基金资助项目(51205336);厦门市科技计划项目(3502Z20123039)

摘　　要：针对齿轮故障发生早期信号微弱、难以诊断和现场干扰的问题,提出了一种基于时域峭度和频域小波能量特征提取并结合区分性权重概率神经网络的齿轮早期故障诊断方法。该方法在特征提取方面利用了峭度统计在冲击负载特征提取上的优点,又保留了小波包分解在频域信号获取上的优势,同时考虑到现场的噪声污染问题,在概率神经网络中引入了区分性权重方法,最终实现了齿轮早期故障的诊断。试验研究表明,该方法不仅能够有效地实现齿轮早期故障的诊断,同时对噪声干扰具有很强的鲁棒性。It is difficult to dectect the gear fault signal in early stage because of weak intensity and strong interference. To solve this problem, a method for incipient fault diagnosis of gears is proposed based on vibration signals using kurtosis, wavelet packet energy features extraction and discriminative weighted probabilistic neural networks. The method uses the advantages of the kurtosis statistics on the impact load feature extraction method in feature extraction and reserves the merit of wavelet packet decomposition in extracting energy characteristics of various frequency bands. Meanwhile, the discriminative weight probabilistic neural network （DWPNN） is introduced to solve the problem of the scene noise pollution. The experimental results show that the method achieves a good identification of incipient faults of gears and has strong robustness against noise disturbance.

关 键 词：峭度 小波包变换 区分性权重 概率神经网络 早期故障诊断 

分 类 号：TH165.3[机械工程—机械制造及自动化]