• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2023, Vol. 59 ›› Issue (13): 175-183.doi: 10.3901/JME.2023.13.175

• 机械动力学 • 上一篇    下一篇

扫码分享

冲击响应机理驱动稀疏表示自编码网络的滚动轴承故障特征提取

郑琛1, 丁康1, 何国林1,2, 林慧斌1, 蒋飞1   

  1. 1. 华南理工大学机械与汽车工程学院 广州 510640;
    2. 人工智能与数字经济广东省实验室 广州 510640
  • 收稿日期:2022-09-06 修回日期:2023-02-19 出版日期:2023-07-05 发布日期:2023-08-15
  • 通讯作者: 何国林(通信作者),男,1986年出生,博士,副教授。主要研究方向为齿轮故障诊断、信号处理及数字孪生技术。E-mail:hegl@scut.edu.cn
  • 作者简介:郑琛,男,1997年出生。主要研究方向为NVH与信号处理。E-mail:201920100162@mail.scut.edu.cn
  • 基金资助:
    国家自然科学基金(52075182、51875207)和广东省自然科学基金(2020A1515010972)资助项目。

Fault Feature Extraction of Rolling Bearing with Sparse Representation Auto-Encoder Driven by Impact Response Mechanism

ZHENG Chen1, DING Kang1, HE Guolin1,2, LIN Huibin1, JIANG Fei1   

  1. 1. School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640;
    2. Pazhou Lab, Guangzhou 510640
  • Received:2022-09-06 Revised:2023-02-19 Online:2023-07-05 Published:2023-08-15

摘要: 由于时域滑移、非承载区信号丢失、噪声等因素的干扰,滚动轴承故障特征难以准确提取,而智能诊断方法提取的多为抽象特征,不具备可解释性。首先,联合冲击响应机理与稀疏表示理论,设计了具备可解释性的稀疏表示自编码网络,将自编码网络的编码层和解码层分别等效为稀疏向量的求解与过完备字典的学习;其次,基于冲击响应参数的损失函数特征设计了自适应优化算法,有效实现了特征参数的快速全局寻优;结合设计的稀疏表示自编码网络与滚动轴承冲击信号特征构建了二层神经网络,对轴承故障信号进行高精度的特征重构。最后,仿真分析表明该方法特征提取精度高、抗噪性能好,能够提取具有明确物理意义的冲击故障特征参数,并进一步通过实验验证了所提方法的有效性。

关键词: 滚动轴承, 特征提取, 自编码网络, 稀疏表示

Abstract: Due to the interference of slipping, signal loss in non-bearing area, noise and other factors, it is hard to accurately extract the fault feature of rolling bearings. Additionally, the abstract features extracted by intelligent diagnosis methods are not interpretable. Firstly, combined the impact response mechanism and sparse representation theory, an interpretable sparse representation sparse representation Auto-Encoder network is designed, which regards the coding and decoding layer of Auto-Encoder as the solution of sparse vector and the learning of over complete dictionary respectively. Secondly, an adaptively optimization algorithm is designed based on the loss function characteristics of impact response parameters, which effectively realizing the fast global optimization of characteristic parameters. Combined with the designed sparse representation Auto-Encoder network and the rolling bearing signal features, a two-layer neural network is built to perform high-precision feature reconstruction of bearing fault signals. Finally, simulation analysis shows that the proposed method can extract impact fault feature parameters with clear physical meaning, which has high feature extraction accuracy and good anti-noise performance. Moreover, experimental signals further verify the effectiveness of the proposed method.

Key words: rolling bearing, feature extraction, Auto-Encoder, sparse representation

中图分类号: