融合多注意力机制的卷积神经网络轴承故障诊断方法

康涛; 段蓉凯; 杨磊; 薛久涛; 廖与禾

doi:10.7652/xjtuxb202212007

您当前的位置：

首页 >

文章列表页 >

融合多注意力机制的卷积神经网络轴承故障诊断方法

—————————————————————— | 更新时间：2025-07-09

- 融合多注意力机制的卷积神经网络轴承故障诊断方法
- Bearing Fault Diagnosis Using Convolutional Neural Network Based on a Multi-Attention Mechanism
- 西安交通大学学报 2022年56卷第12期页码：68-77
- 作者机构：
  
  1. 西安交通大学现代设计及转子轴承系统教育部重点实验室,西安,710049
  2. 西安交通大学陕西省机械产品质量保障与诊断重点实验室,西安,710049
- 作者简介：
  
  : 2022-04-20。作者简介: 康涛(1998—),男,硕士生
  廖与禾(通信作者),男,副教授,博士生导师。基金项目: 国家自然科学基金资助项目(51575424)
- 基金信息：
  
  : 2022-04-20。作者简介: 康涛(1998—),男,硕士生;廖与禾(通信作者),男,副教授,博士生导师。基金项目: 国家自然科学基金资助项目(51575424);装备预研教育部联合基金资助项目(6141A02022113)
- DOI：10.7652/xjtuxb202212007
  中图分类号： TP277
- 网络首发：2022-12-10，
  
  纸质出版：2022
- 稿件说明：
移动端阅览
康涛, 段蓉凯, 杨磊, 等. 融合多注意力机制的卷积神经网络轴承故障诊断方法[J]. 西安交通大学学报, 2022,56(12):68-77.

KANG Tao, DUAN Rongkai, YANG Lei, et al. Bearing Fault Diagnosis Using Convolutional Neural Network Based on a Multi-Attention Mechanism[J]. 2022, 56(12): 68-77.
康涛, 段蓉凯, 杨磊, 等. 融合多注意力机制的卷积神经网络轴承故障诊断方法[J]. 西安交通大学学报, 2022,56(12):68-77. DOI： 10.7652/xjtuxb202212007.

KANG Tao, DUAN Rongkai, YANG Lei, et al. Bearing Fault Diagnosis Using Convolutional Neural Network Based on a Multi-Attention Mechanism[J]. 2022, 56(12): 68-77. DOI： 10.7652/xjtuxb202212007.

摘要

针对卷积神经网络学习关键故障特征的能力不足从而影响轴承故障诊断准确率的问题

提出一种融合多注意力机制的卷积神经网络自适应抗噪模型(MACNN)。利用通道和时间的复合注意力机制优化学习机制

从不同角度抑制噪声及无关信号分量等干扰信息的影响

并自适应地增强故障特征的响应; 引入残差连接

防止网络性能退化。采用多尺度特征提取方法

通过通道注意力机制自适应融合不同尺度下提取的特征。使用分类器进行滚动轴承故障诊断。实验结果表明:与没有实施注意力机制的模型相比

轴承故障诊断准确率平均提升了22.12%; 所提方法在各噪声背景下的故障识别准确率均在98.5%以上

验证了其自适应抗噪能力; 在跨载荷实验中

模型故障诊断准确率保持在88%以上

相比其他方法

MACNN的抗噪性能和稳定性更优。

Abstract

The convolutional neural network does not work well in learning the key fault characteristics affecting the accuracy of bearing fault diagnosis. To address this problem

this paper proposes an adaptive anti-noise model using the convolutional neural network based on a multi-attention mechanism(MACNN). The model uses the channel-time composite attention mechanism to optimize the learning mechanism so as to suppress the influence of noise and irrelevant signal components from different aspects and adaptively enhance the fault features. In addition

residual connection is introduced in this module to prevent network performance degradation. The multi-scale feature extraction method is used to extract the features from different scales and adaptively fuse them by the channel attention mechanism. Finally

a classifier is applied for rolling bearing fault diagnosis. According to the experimental results the accuracy of the proposed model is increased by 22.12% on average compared with the model without an attention mechanism. The recognition accuracy of the model is above 98.5% in all noise backgrounds

which verifies its adaptive anti-noise ability. In the cross-load experiment

the accuracy of the model is above 88%. Compared with other methods

MACNN has better anti-noise performance and stability.

关键词

Keywords

references

GEORGOULAS G, LOUTAS T, STYLIOS C D, et al. Bearing fault detection based on hybrid ensemble detector and empirical mode decomposition [J]. Mechanical Systems and Signal Processing, 2013, 41(1/2): 510-525.

OJAGHI M, YAZDANDOOST N. Oil-whirl fault modeling, simulation, and detection in sleeve bearings of squirrel cage induction motors [J]. IEEE Transactions on Energy Conversion, 2015, 30(4): 1537-1545.

WANG Ziwei, ZHANG Qinghua, XIONG Jianbin, et al. Fault diagnosis of a rolling bearing using wavelet packet denoising and random forests [J]. IEEE Sensors Journal, 2017, 17(17): 5581-5588.

YAN Tao, LEI Yaguo, WANG Biao, et al. Joint maintenance and spare parts inventory optimization for multi-unit systems considering imperfect maintenance actions [J]. Reliability Engineering System Safety, 2020, 202: 106994.

金国强. 基于深度学习的复杂工况下端到端的滚动轴承故障诊断算法研究 [D]. 合肥: 中国科学技术大学, 2020.

雷亚国, 贾峰, 孔德同, 等. 大数据下机械智能故障诊断的机遇与挑战 [J]. 机械工程学报, 2018, 54(5): 94-104.

LEI Yaguo, JIA Feng, KONG Detong, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era [J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104.

HE Miao, HE D. Deep learning based approach for bearing fault diagnosis [J]. IEEE Transactions on Industry Applications, 2017, 53(3): 3057-3065.

JIA Feng, LEI Yaguo, LU Na, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization [J]. Mechanical Systems and Signal Processing, 2018, 110: 349-367.

ABDELJABER O, AVCI O, KIRANYAZ S, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks [J]. Journal of Sound and Vibration, 2017, 388: 154-170.

周奇才, 刘星辰, 赵炯, 等. 旋转机械一维深度卷积神经网络故障诊断研究 [J]. 振动与冲击, 2018, 37(23): 31-37.

ZHOU Qicai, LIU Xingchen, ZHAO Jiong, et al. Fault diagnosis for rotating machinery based on 1D depth convolutional neural network [J]. Journal of Vibration and Shock, 2018, 37(23): 31-37.

ZHANG Wei, LI Xiang, DING Qian. Deep residual learning-based fault diagnosis method for rotating machinery [J]. ISA Transactions, 2019, 95: 295-305.

董绍江, 裴雪武, 吴文亮, 等. 基于多层降噪技术及改进卷积神经网络的滚动轴承故障诊断方法 [J]. 机械工程学报, 2021, 57(1): 148-156.

DONG Shaojiang, PEI Xuewu, WU Wenliang, et al. Rolling bearing fault diagnosis method based on multilayer noise reduction technology and improved convolutional neural network [J]. Journal of Mechanical Engineering, 2021, 57(1): 148-156.

张弘斌, 袁奇, 赵柄锡, 等. 采用多通道样本和深度卷积神经网络的轴承故障诊断方法 [J]. 西安交通大学学报, 2020, 54(8): 58-66.

ZHANG Hongbin, YUAN Qi, ZHAO Bingxi, et al. Bearing fault diagnosis with multi-channel sample and deep convolutional neural network [J]. Journal of Xi'an Jiaotong University, 2020, 54(8): 58-66.

朱浩, 宁芊, 雷印杰, 等. 基于注意力机制-Inception-CNN模型的滚动轴承故障分类 [J]. 振动与冲击, 2020, 39(19): 84-93.

ZHU Hao, NING Qian, LEI Yinjie, et al. Fault classification of rolling bearing based on attention mechanism-inception-CNN model [J]. Journal of Vibration and Shock, 2020, 39(19): 84-93.

WANG Zhijian, HE Xinxin, YANG Bin, et al. Subdomain adaptation transfer learning network for fault diagnosis of roller bearings [J]. IEEE Transactions on Industrial Electronics, 2022, 69(8): 8430-8439.

WANG Biao, LEI Yaguo, LI Naipeng, et al. Multiscale convolutional attention network for predicting remaining useful life of machinery [J]. IEEE Transactions on Industrial Electronics, 2021, 68(8): 7496-7504.

吕阳, 廖与禾, 王报祥, 等. 基于VMD和CNN的滚动轴承故障定量诊断方法 [J]. 中国科技论文, 2020, 15(7): 735-742.

LÜ Yang, LIAO Yuhe, WANG Baoxiang, et al. Quantitative diagnosis method for rolling bearing faults based on VMD and CNN [J]. China Sciencepaper, 2020, 15(7): 735-742.

刘威. 基于动态随机卷积神经网络的手写数字识别方法 [D]. 长春: 吉林大学, 2017.

WANG Huan, LIU Zhiliang, PENG Dandan, et al. Understanding and learning discriminant features based on multiattention 1DCNN for wheelset bearing fault diagnosis [J]. IEEE Transactions on Industrial Informatics, 2020, 16(9): 5735-5745.

PENG Dandan, LIU Zhiliang, WANG Huan, et al. A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains [J]. IEEE Access, 2019, 7: 10278-10293.

ZHANG Wei, PENG Gaoliang, LI Chuanhao, et al. A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals [J]. Sensors, 2017, 17(2): 425.

张西宁, 余迪, 刘书语. 基于迁移学习的小样本轴承故障诊断方法研究 [J]. 西安交通大学学报, 2021, 55(10): 30-37.

ZHANG Xining, YU Di, LIU Shuyu. Fault diagnosis method for small sample bearing based on transfer learning [J]. Journal of Xi'an Jiaotong University, 2021, 55(10): 30-37.

PAN Honghu, HE Xingxi, TANG Sai, et al. An improved bearing fault diagnosis method using one-dimensional CNN and LSTM [J]. Strojniki Vestnik-Journal of Mechanical Engineering, 2018, 64(7/8): 443-452.

HUANG Wenyi, CHENG Junsheng, YANG Yu, et al. An improved deep convolutional neural network with multi-scale information for bearing fault diagnosis [J]. Neurocomputing, 2019, 359: 77-92.

赵敬娇, 赵志宏, 杨绍普. 基于残差连接和1D-CNN的滚动轴承故障诊断研究 [J]. 振动与冲击, 2021, 40(10): 1-6.

ZHAO Jingjiao, ZHAO Zhihong, YANG Shaopu. Rolling bearing fault diagnosis based on residual connection and 1D-CNN [J]. Journal of Vibration and Shock, 2021, 40(10): 1-6.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

采用多尺度自适应选择卷积神经网络的轴承故障诊断研究

面向新概念学习的图像描述生成模型

利用改进卷积神经网络的滚动轴承变工况故障诊断方法

融合多小波分解的深度卷积神经网络轴承故障诊断方法

机械滥用场景下锂离子电池温度多模态神经网络预测方法