• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2021, Vol. 57 ›› Issue (1): 110-120.doi: 10.3901/JME.2021.01.110

• 机械动力学 • 上一篇    下一篇

扫码分享

基于多通道加权卷积神经网络的齿轮箱振动信号特征提取

叶壮, 余建波   

  1. 同济大学机械与能源工程学院 上海 201804
  • 收稿日期:2019-10-10 修回日期:2020-06-05 出版日期:2021-01-05 发布日期:2021-02-06
  • 通讯作者: 余建波(通信作者),男,1978年出生,博士,教授,博士研究生导师。主要研究方向为机械故障诊断、设备智能维护。E-mail:jbyu@tongji.edu.cn
  • 作者简介:叶壮,男,1996年出生,博士研究生。主要研究方向为深度学习、机械故障诊断。E-mail:yezhuang@tongji.edu.cn
  • 基金资助:
    国家自然科学基金(71777173)、上海科委“科技创新行动计划”高新技术领域项目(19511106303)和中央高校基本业务经费资助项目。

Feature Extraction of Gearbox Vibration Signals Based on Multi-Channels Weighted Convolutional Neural Network

YE Zhuang, YU Jianbo   

  1. School of Mechanical Engineering, Tongji University, Shanghai 201804
  • Received:2019-10-10 Revised:2020-06-05 Online:2021-01-05 Published:2021-02-06

摘要: 为了解决单通道振动信号输入不能全面表达故障特征信息及齿轮箱故障早期诊断问题,提出了一种新的深度神经网络(Deep neural network,DNN)模型—多通道加权卷积神经网络(Multi-channels weighted convolutional neural network,MCW-CNN),并应用于齿轮箱振动信号特征学习和故障诊断。首先,采用经验模态分解(Empirical mode decomposition,EMD)对振动信号进行处理,得到多通道一维信号突出振动信号的故障特征,并将其转化为多通道图像输入,从而充分发挥CNN在图像特征提取上的优良性能,将齿轮箱故障诊断问题进一步转化为CNN更为擅长的多通道图像识别问题;其次,针对各通道图像频率和带宽的不同,在卷积层采用动态感受野进行图像特征提取,全面提取多通道图像特征细节;针对各通道图像携带冲击特征的强弱不同,提出了基于峭度加权的多通道融合方法,增强了冲击特征强的通道故障特征。最后,通过故障诊断仿真试验和齿轮箱故障诊断试验验证所提方法的有效性。试验结果表明,MCW-CNN可有效提取振动信号的故障特征,识别正确率明显高于典型的深度学习方法和传统的分类器。

关键词: 齿轮箱故障诊断, 多通道信号, 特征学习, 卷积神经网络, 信息融合

Abstract: A new DNN model,called multi-channels weighted convolutional neural network (MCW-CNN) is proposed in order to solve the feature extraction problem of CNNs that use single-channel signal as input,which can not express the fault characteristics hidden in the vibration signals effectively. Firstly,empirical mode decomposition (EMD) is used to obtain multi-channel one-dimensional signals to highlight the fault characteristics,which is converted into multi-channel image as input of MCW-CNN. So that the image feature extraction of CNN can be fully utilized,and the gearbox diagnosis is further converted into an image recognition issue that CNN is good at dealing with. Secondly,due to the difference of frequency and bandwidth of each channel,a dynamic receptive field is proposed in MCW-CNN to extract the detailed features from these images. In addition,the intensity of the impact feature of each channel image is different,so the fusion weight is determined based on the kurtosis,which can highlight the channels that have strong impact characteristics. Finally,the effectiveness of the proposed method is verified on a gearbox fault diagnosis case. Experimental results show that the MCW-CNN can effectively extract the fault characteristics of the vibration signal. It has a significantly higher recognition accuracy rate than other typical deep learning methods and traditional classifiers.

Key words: gearbox fault diagnosis, multi-channels signal, feature learning, convolutional neural network, information fusion

中图分类号: