基于小波包神经网络的轴承故障识别模型  

Bearing Fault Identification Model Based on Wavelet Packet Neural Network

作　　者：曹现刚[1] 张鑫媛 吴少杰 姜韦光 雷一楠 CAO Xiangang;ZHANG Xinyuan;WU Shaojie;JIANG Weiguang;LEI Yinan(College of Mechanical Engineering,Xi’an University of Science andTechnology,Xi’an Shaanxi 710054,China)

机构地区：[1]西安科技大学机械工程学院,陕西西安710054

出　　处：《机床与液压》2019年第5期174-179,共6页Machine Tool & Hydraulics

基　　金：国家自然科学基金资助项目(51875451)

摘　　要：针对传统故障特征提取过程复杂、诊断方案单一且准确性差等问题,提出了基于多阈值小波包和深度置信网络(DBN)的轴承故障识别方案。本文作者采用最优小波基函数和软硬阈值结合方法对原始振动信号进行三层分解降噪处理,得到8个从低频到高频段的信号成分,对其进行组合重构作为神经网络的输入样本;通过DBN在数据处理上的特征重构优势,建立了DBNBP神经网络的轴承故障识别模型,确定模型的各类参数。经多次实验,探究不同样本输入对模型识别率的影响,并与传统的浅层神经网络识别模型做对比分析,结果表明:经训练的DBNBP轴承故障识别模型可从原始数据、小波包分解信号实现轴承故障信号的准确特征学习和分类,结合识别率和诊断时间考虑,经小波包分解信号输入具有更优的诊断效率。Aiming at the problems of complex process in traditional fault feature extraction, single diagnosis and poor accuracy, a bearing fault identification scheme based on multi-threshold wavelet packet and deep belief network ( DBN) was proposed. The optimal wavelet basis function and soft-hard threshold combination method were used to perform three-layer decomposition and noise reduction on the original vibration signal, and eight signal components from low frequency to high frequency band were obtained. The combined reconstruction of 8 frequency bands was used as the input sample of the neural network. Based on the advantages of DBN in data processing, the bearing fault identification model of DBNBP neural network was established and various parameters of the model were determined. The effects of different sample inputs on the identification rate of the model was explored and compared with the traditional neural network model. The results show that the trained DBNBP bearing fault identification model can accurately predict the bearing fault signal from the original data and wavelet packet decomposition signals. Feature learning and classification, combined with recognition rate and diagnostic time considerations, have better diagnostic efficiency through wavelet packet decomposition signal input.

关 键 词：深度置信网络 BP神经网络 监督学习 小波分析 多阈值 故障识别 轴承 

分 类 号：TH133[机械工程—机械制造及自动化]