基于AMCNN-BiGRU的滚动轴承故障诊断方法研究

徐鹏1,皋军2,邵星2

振动与冲击 ›› 2023, Vol. 42 ›› Issue (18) : 71-80.

PDF(3215 KB)
PDF(3215 KB)
振动与冲击 ›› 2023, Vol. 42 ›› Issue (18) : 71-80.
论文

基于AMCNN-BiGRU的滚动轴承故障诊断方法研究

  • 徐鹏1,皋军2,邵星2
作者信息 +

Fault diagnosis method for rolling bearings based on AMCNN-BiGRU

  • XU Peng1,GAO Jun2,SHAO Xing2
Author information +
文章历史 +

摘要

为克服传统滚动轴承故障诊断方法需要人工提取特征的缺点,提出一种基于注意力模块的卷积神经网络-双向门控循环单元(AMCNN-BiGRU)的滚动轴承故障诊断方法。该方法利用下采样后的原始振动信号作为输入,通过具有两种不同核大小的并行卷积块从采样后的数据中提取特征,并使用注意力模块对提取的特征进行加权融合处理,最后将具有不同权重的特征输入到双向门控循环单元进行故障分类,从而实现端到端的诊断。为了理解所提出模型的诊断过程,对所学习的特征进行可视化,分析发现模型可以有效映射不同类型的故障。经实验表明,本模型使用下采样后的原始数据有效缩短了网络的训练时间,同时还可以保持100%的诊断准确率。

Abstract

In order to overcome the disadvantage of manual feature extraction in traditional rolling bearing fault diagnosis methods, a rolling bearing fault diagnosis method based on convolution neural network-bi-directional gated cycle unit (AMCNN-BiGRU) based on attention module is proposed. In this method, the original vibration signal after downsampling is used as input, features are extracted from the original data by parallel convolution blocks with two different core sizes, and the extracted features are weighted and fused by attention module. Finally, the features with different weights are input to the bi-directional gated cycle unit for fault classification, so as to realize end-to-end diagnosis. In order to understand the diagnosis process of the proposed model, the learned features are visualized, and it is found that the model can effectively map different faults. The experimental results show that the model can effectively shorten the network training time and maintain 100% diagnostic accuracy by using the downsampled original data.

关键词

卷积神经网络 / 门控循环单元 / 注意力机制 / 轴承故障诊断 / 可视化

Key words

convolutional neural network / gate recurrent unit / attention mechanism / bearing fault diagnosis / visualization

引用本文

导出引用
徐鹏1,皋军2,邵星2. 基于AMCNN-BiGRU的滚动轴承故障诊断方法研究[J]. 振动与冲击, 2023, 42(18): 71-80
XU Peng1,GAO Jun2,SHAO Xing2. Fault diagnosis method for rolling bearings based on AMCNN-BiGRU[J]. Journal of Vibration and Shock, 2023, 42(18): 71-80

参考文献

[1] Li J, Liu Y, Li Q. Intelligent fault diagnosis of rolling bearings under imbalanced data conditions using attention-based deep learning method[J]. Measurement, 2022, 189: 110500.
[2] Lv Y, Zhao W, Zhao Z, et al. Vibration signal-based early fault prognosis: Status quo and applications[J]. Advanced Engineering Informatics, 2022, 52: 101609.
[3] 刘伟, 单雪垠, 李双喜, 等. 基于并行1DCNN的滚动轴承故障诊断研究[J]. 机电工程, 2021, 38(12): 1572–1578.
LIU Wei, SHAN Xue-yin, LI Shuang-xi, et al. Research on Fault Diagnosis of Rolling Bearing Based on Parallel 1DCNN[J]. Journal of Mechanical & Electrical Engineering, 2021, 38(12): 1572-1578.
[4] 程建刚, 毕凤荣, 张立鹏, 等. 基于多重注意力-卷积神经网络-双向门控循环单元的机械故障诊断方法研究[J]. 内燃机工程, 2021, 42(04): 77-83+92.
CHENG Jian-gang, BI Feng-rong, ZHANG Li-peng, et al. Research on mechanical fault diagnosis method based on multi-attention-convolutional neural network-bidirectional gated recurrent unit [J/OL]. Chinese Internal Combustion Engine Engineering, 2021, 42(04): 77-83+92.
[5] 张训杰, 张敏, 李贤均. 基于二维图像和CNN-BiGRU网络的滚动轴承故障模式识别[J]. 振动与冲击, 2021, 40(23): 194-201+207.
ZHANG Xun-jie, ZHANG Min, LI Jun-xian. Rolling Bearing Failure Mode Recognition Based on 2D Image and CNN-BiGRU Network [J/OL]. Journal of Vibration and Shock, 2021, 40(23): 194-201+207.
[6] Zhang Ke, Wang Jingyu, Shi Huaitao, et al. A fault diagnosis method based on improved convolutional neural network for bearings under variable working conditions[J]. Measurement, 2021, 182: 109749.
[7] 沈涛, 李舜酩. 针对滚动轴承故障的批标准化C NN-LSTM诊断方法[J]. 计算机集成制造系统, : 1–16.
SHEN Tao, LI Shun-ming. Batch-standardized CNN-LSTM diagnosis method for rolling bearing faults[J]. Computer Integrated Manufacturing System: 1-16.
[8] Wei Zhang, Chuanhao Li, Gaoliang Peng, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018, 100: 439–453.
[9] 昝涛, 王辉, 刘智豪, 等. 基于多输入层卷积神经网络的滚动轴承故障诊断模型[J]. 振动与冲击, 2020, 39(12): 142-149+163.
Zan Tao, WANG Hui, LIU Zhi-hao, et al. Fault diagnosis model of rolling bearing based on multi-input layer convolutional neural network [J]. Journal of Vibration and Shock, 2020, 39(12): 142-149+163.
[10] Mirzaei S, Kang J-L, Chu K-Y. A comparative study on long short-term memory and gated recurrent unit neural networks in fault diagnosis for chemical processes using visualization[J]. Journal of the Taiwan Institute of Chemical Engineers, 2022, 130: 104028.
[11] 张立鹏, 毕凤荣, 程建刚, 等. 基于注意力BiGRU的机械故障诊断方法研究[J]. 振动与冲击, 2021, 40(05): 113–118.
ZHANG Li-peng, BI Feng-rong, CHENG Jian-gang, et al. Research on mechanical fault diagnosis method based on attention BiGRU[J/OL]. Journal of Vibration and Shock, 2021, 40(05): 113-118.
[12] Zhang Xin, He Chao, Lu Yanping, et al. Fault diagnosis for small samples based on attention mechanism[J]. Measurement, 2022, 187: 110242.
[13] Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[J]. https://arxiv.org/abs/1412.3555.
[14] Dongxiao Niu, Min Yu, Lijie Sun, et al. Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism[J]. Applied Energy, 2022, 313: 118801.
[15] 茅健, 郭玉荣, 赵嫚. 基于注意力机制的滚动轴承故障诊断方法[J]. 计算机集成制造系统, : 1–20.
MAO Jian, GUO Yu-rong, ZHAO Man. Fault diagnosis method of rolling bearing based on attention mechanism [J]. Computer Integrated Manufacturing System: 1-20.
16] Guo MengHao, Xu TianXing, Liu JiangJiang, et al. Attention Mechanisms in Computer Vision: A Survey[J]. Computational Visual Media, 2015, 14(8): 27.
[17] Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA:CVPR, 2020.
[18] Jiao J, Zhao M, Lin J, et al. A comprehensive review on convolutional neural network in machine fault diagnosis[J]. Neurocomputing, 2020, 417: 36–63.
[19] K. Li, School of Mechanical Engineering, Jiangnan University, http://mad-net.org:8765/explore.html?t=0.5831516555847212, 2020.
[20] 谢天雨, 董绍江. 基于改进CNN的噪声以及变负载条件下滚动轴承故障诊断方法[J]. 噪声与振动控制, 2021, 41(2): 111–117.
XIE Tian-yu, DONG Shao-jiang. Noise and rolling bearing fault diagnosis method under variable load conditions based on improved CNN [J]. Noise and Vibration Control, 2021, 41(2): 111-117.

PDF(3215 KB)

Accesses

Citation

Detail

段落导航
相关文章

/