计算机应用 ›› 2020, Vol. 40 ›› Issue (10): 2890-2898.DOI: 10.11772/j.issn.1001-9081.2020030329

• 人工智能 • 上一篇    下一篇

面向轴承早期故障检测的多尺度残差注意力深度领域适配模型

毛文涛1,2, 杨超1, 刘亚敏1, 田思雨1   

  1. 1. 河南师范大学 计算机与信息工程学院, 河南 新乡 453007;
    2. 智慧商务与物联网技术河南省工程实验室(河南师范大学), 河南 新乡 453007
  • 收稿日期:2020-03-21 修回日期:2020-05-14 出版日期:2020-10-10 发布日期:2020-06-05
  • 通讯作者: 毛文涛
  • 作者简介:毛文涛(1980-),男,河南新乡人,教授,博士,CCF会员,主要研究方向:机器学习、智能故障诊断;杨超(1994-),男,河南信阳人,硕士研究生,主要研究方向:机器学习、早期故障检测;刘亚敏(1995-),女,河南周口人,硕士研究生,主要研究方向:机器学习、故障检测;田思雨(1993-),女,河南安阳人,硕士研究生,主要研究方向:机器学习、早期故障检测。
  • 基金资助:
    国家重点研发计划重点专项(2018YFB1701400);国家自然科学基金资助项目(U1704158)。

Deep domain adaptation model with multi-scale residual attention for incipient fault detection of bearings

MAO Wentao1,2, YANG Chao1, LIU Yamin1, TIAN Siyu1   

  1. 1. School of Computer and Information Engineering, Henan Normal University, Xinxiang Henan 453007, China;
    2. Engineering Laboratory of Intelligence Business and Internet of Things in Henan Province;(Henan Normal University), Xinxiang Henan 453007, China
  • Received:2020-03-21 Revised:2020-05-14 Online:2020-10-10 Published:2020-06-05
  • Supported by:
    This work is partially supported by the Special Project of the National Key Research and Development Program of China (2018YFB1701400), the National Natural Science Foundation of China (U1704158).

摘要: 针对由工作环境和设备状况的差异引起的轴承早期故障检测模型可靠性差、误报警率高的问题,根据早期故障检测的特点和需求,提出一种多尺度注意力深度领域适配模型。首先,将监测信号处理成由原始信号、希尔伯特-黄变换边际谱、频谱组成的三通道数据;然后,通过在残差注意力模块中增加不同尺寸的滤波器以提取多尺度深度特征,使用卷积-反卷积操作来重构输入信息从而获得注意力信息,并且将注意力信息与多尺度特征融合构建了一种多尺度残差注意力模块,用于提取对早期故障表征能力更强的注意力特征;其次,在所提取到的注意力特征基础上,构建基于交叉熵和最大均值差异(MMD)正则化约束的损失函数来实现领域适配;最后,采用随机梯度下降算法进行网络参数优化,构建端到端的早期故障检测模型。在IEEE PHM-2012数据挑战赛数据集上的实验结果表明,与8种代表性的早期故障检测和诊断方法以及迁移学习算法相比,所提方法能够在不延迟报警时间点的前提下,分别比8种方法的平均误报警率降低了62.7%和61.3%,有效提高了早期故障检测的鲁棒性。

关键词: 早期故障检测, 残差注意力网络, 迁移学习, 注意力机制, 深度学习

Abstract: Aiming at the problems of poor reliability and high false alarm rate of the fault detection models of bearings caused by the differences in working environment and equipment status, a multi-scale attention deep domain adaptation model was proposed according to the characteristics and needs of incipient fault detection. First, the monitoring signal was pre-processed into a three-channel data consisting of the original signal, Hilbert-Huang transform marginal spectrum and frequency spectrum. Second, the filters of different sizes were added into the residual attention module to extract multi-scale deep features, and the convolution-deconvolution operation was used to reconstruct the input information in order to obtain attention information, then a multi-scale residual attention module was constructed by combining the attention information and multi-scale features and was used to extract the attention features with stronger ability of representing incipient faults. Third, a loss function based on the cross entropy and Maximum Mean Discrepancy (MMD) regularization constraints was constructed to achieve the domain adaptation on the basis of the extracted attention features. Finally, a stochastic gradient descent algorithm was used to optimize the network parameters, and an end-to-end incipient fault detection model was established. Comparative experiments were conducted on the IEEE PHM-2012 Data Challenge dataset. Experimental results show that, compared with eight representative incipient fault detection and diagnosis methods as well as transfer learning algorithms, the proposed method can obtain the reduction of 62.7% and 61.3% in the average false alarm rate while keeping the alarm location not delayed, and effectively improves the robustness of incipient fault detection.

Key words: incipient fault detection, residual attention network, transfer learning, attention mechanism, deep learning

中图分类号: