Rolling bearing fault diagnosis with multi-scale multi-task attention convolutional neural network

WANG Zhaowei; LIU Chuanshuai; ZHAO Wenxiang; SONG Xiangjin

doi:10.15938/j.emc.2024.07.007

您当前的位置：

首页 >

文章列表页 >

Rolling bearing fault diagnosis with multi-scale multi-task attention convolutional neural network

更新时间：2025-06-26

- Rolling bearing fault diagnosis with multi-scale multi-task attention convolutional neural network
- Electric Machines and Control Vol. 28, Issue 7, Pages: 65-76(2024)
- 作者机构：
  
  江苏大学电气信息工程学院，江苏镇江 212013
- 作者简介：
- 基金信息：
- DOI：10.15938/j.emc.2024.07.007
  CLC： TM34
- Received：03 March 2023，
  
  Published：2024-07
- 稿件说明：
移动端阅览
WANG Zhaowei, LIU Chuanshuai, ZHAO Wenxiang, et al. Rolling bearing fault diagnosis with multi-scale multi-task attention convolutional neural network[J]. Electric Machines and Control, 2024, 28(7): 65-76.
DOI：

WANG Zhaowei, LIU Chuanshuai, ZHAO Wenxiang, et al. Rolling bearing fault diagnosis with multi-scale multi-task attention convolutional neural network[J]. Electric Machines and Control, 2024, 28(7): 65-76. DOI： 10.15938/j.emc.2024.07.007.

摘要

针对振动信号时间尺度不一、故障特征分布差异及信息冗余等问题，提出一种多尺度多任务注意力卷积神经网络（MSTACNN）的滚动轴承故障诊断方法。首先，在参数共享单元构建多尺度卷积神经网络，提取多任务之间共享信息的多尺度通用特征；其次，利用多任务学习机制对故障类型、故障尺寸以及运行工况同时训练，规避单任务学习效率低下问题；然后，采用注意力机制对多尺度特征信息进行筛选，识别并保留有效特征；最后，设计了一种自适应损失权重算法，动态调整子任务的损失权重，控制不同任务的学习进度，实现了对轴承故障类型、故障尺寸以及运行工况同时识别的目标。在西储大学数据集和帕德博恩大学数据集分别对方法有效性进行验证，其中故障类型的识别准确率分别达到了99.95%和98.41%。实验结果表明，所提方法均展现出较高的识别准确率、良好的收敛速度和稳定性，具有较强的特征提取学习能力和泛化性能。

Abstract

Aiming at the problems of different time scales，inconsistent characteristic distribution，and information redundancy of vibration signals，a rolling bearing fault diagnosis method with a multi-scale multi-task attention convolutional neural network（MSTACNN）was proposed. Firstly，a multi-scale convolutional neural network was constructed in the parameter sharing unit，and multi-scale common features containing information shared between different tasks in vibration signals were extracted. Secondly，the multi-task learning mechanism was employed to simultaneously accomplish three tasks：fault type，fault size，and operation conditions. Thus，the inefficiency of single-task learning was solved. Then，the attention mechanism was used to enhance the feature expression and the influence of useless information was eliminated. Finally，an adaptive loss weight algorithm was designed to dynamically adjust the loss weight and the learning progress of three tasks，the goal of simultaneously identifying bearing fault type，fault size，and operating conditions was achieved. The effectiveness of the proposed method was verified in the dataset of Western Reserve University and the University of Paderborn，respectively. The recognition accuracy of fault types achieved 99.95% and 98.41% in different datasets. The experimental results show that the proposed method shows high recognition accuracy，good convergence speed and stability，which proves that the proposed method has strong feature extraction learning ability and generalization performance.

关键词

Keywords

references

宋向金,赵文祥.交流电机信号特征分析的滚动轴承故障诊断方法综述[J].中国电机工程学报, 2022, 42(4): 1582.

SONG Xiangjin, ZHAO Wenxiang. A review of rolling bearing fault diagnosis approaches using AC motor signature analysis[J]. Proceedings of the CSEE, 2022, 42(4): 1582.

PAN Z, MENG Z, CHEN Z, et al. A two-stage method based on extreme learning machine for predicting the remaining useful life of rolling-element bearings[J]. Mechanical Systems and Signal Processing, 2020, 144: 106899.

XUE H, WU M, ZHANG Z, et al. Intelligent diagnosis of mechanical faults of in-wheel motor based on improved artificial hydrocarbon networks[J]. ISA Transactions, 2022, 120: 360.

GAO Z, CECATI C, DING S X. A survey of fault diagnosis and fault-tolerant techniques—Part I: fault diagnosis with model-based and signal-based approaches[J]. IEEE Transactions on Industrial Electronics, 2015, 62(6): 3757.

JIN X, ZHAO M, CHOW T W S, et al. Motor bearing fault diagnosis using trace ratio linear discriminant analysis[J]. IEEE Transactions on Industrial Electronics, 2013, 61(5): 2441.

LEI Y, LIN J, HE Z, et al. A review on empirical mode decomposition in fault diagnosis of rotating machinery[J]. Mechanical Systems and Signal Processing, 2013, 35(1-2): 108.

夏志凌,胡凯波,刘心悦,等.基于变模态分解的异步电机转子断条故障诊断[J].电工技术学报, 2023, 38(8): 2048.

XIA Zhiling, HU Kaibo, LIU Xinyue, et al. Fault diagnosis of rotor broken bar in induction motor based on variable mode decomposition[J]. Transactions of China Electrotechnical Society, 2023, 38(8): 2048.

LAU E C C, NGAN H W. Detection of motor bearing outer raceway defect by wavelet packet transformed motor current signature analysis[J]. IEEE Transactions on Instrumentation and Measurement, 2010, 59(10): 2683.

CHENG F, WANG J, QU L, et al. Rotor-current-based fault diagnosis for DFIG wind turbine drivetrain gearboxes using frequency analysis and a deep classifier[J]. IEEE Transactions on Industry Applications, 2017, 54(2): 1062.

余印振,韩哲哲,许传龙.基于深度卷积神经网络和支持向量机的NO x 浓度预测[J ] .中国电机工程学报,2022,42 (1):238.

YU Yinzhen, HAN Zhezhe, XU Chuanlong. NO x concentration prediction based on deep convolution neural network and support vector machine[J ] . Proceeding of the CSEE,2022,42(1):238.

LI C, SANCHEZ R V, ZURITA G, et al. Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals[J]. Mechanical Systems and Signal Processing, 2016, 76: 283.

李兵,韩睿,何怡刚,等.改进随机森林算法在电机轴承故障诊断中的应用[J].中国电机工程学报,2020,40(4):1310.

LI Bing, HAN Rui, HE Yigang, et al. Applications of the improved random forest algorithm in fault diagnosis of motor bearings[J]. Proceeding of the CSEE, 2020, 40(4): 1310.

WAQAR T, DEMETGUL M. Thermal analysis MLP neural network based fault diagnosis on worm gears[J]. Measurement, 2016, 86: 56.

ZHAO R, YAN R, CHEN Z, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing, 2019, 115: 213.

XING Z, ZHAO R, WU Y, et al. Intelligent fault diagnosis of rolling bearing based on novel CNN model considering data imbalance[J]. Applied Intelligence, 2022: 1.

DIBAJ A, ETTEFAGH M M, HASSANNEJAD R, et al. A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults[J]. Expert Systems with Applications, 2021, 167: 114094.

王正英,胥永刚,李强,等.机械振动信号内在模式的复杂性评估[J].振动与冲击, 2009, 28(1): 81.

WANG Zhengying, XU Yonggang, LI Qiang, et al. Empirical mode decomposition and complexity measurement of mechanical vibration signals[J]. Journal of Vibration and Shock, 2009, 28 (1): 81.

JIANG G, HE H, YAN J, et al. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox[J]. IEEE Transactions on Industrial Electronics, 2018, 66(4): 3196.

王妮妮,马萍,张宏立,等.基于多尺度深度卷积网络特征融合的滚动轴承故障诊断[J].太阳能学报,2022,43(4):351.

WANG Nini, MA Ping, ZHANG Hongli, et al. Fault diagnosis of rolling bearing based on feature fusion of multi-scale deep convolutional network[J]. Acta Energiae Solaris Sinica, 2022, 43 (4): 351.

丁雪,邓艾东,李晶,等.基于多尺度和注意力机制的滚动轴承故障诊断[J].东南大学学报(自然科学版), 2022, 52 (1): 172.

DING Xue, DENG Aidong, LI Jing, et al. Fault diagnosis of rolling bearing based on multi-scale and attention mechanism[J]. Journal of Southeast University(Natural Science Edition), 2022, 52(1): 172.

康玉祥,陈果,尉询楷,等.基于残差网络的航空发动机滚动轴承故障多任务诊断方法[J].振动与冲击,2022,41 (16):285.

KANG Yuxiang, CHEN Guo, WEI Xunkai, et al. A multi-task fault diagnosis method of rolling bearings based on the residual network[J]. Journal of Vibration and Shock,2022,41(16):285.

SMITH W A, RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64: 100.

LESSMEIER C, KIMOTHO J K, ZIMMER D, et al. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: A benchmark data set for data-driven classification[C]//PHM Society European Conference,October 3-6,2016,Denver,Colorado. 2016:1-17.

GAO H, CHENG B, WANG J, et al. Object classification using CNN-based fusion of vision and LIDAR in autonomous vehicle environment[J]. IEEE Transactions on Industrial Informatics, 2018, 14(9): 4224.

SANTOS C D, GATTI M. Deep convolutional neural networks for sentiment analysis of short texts[C]//Proceedings of the 25th International Conference on Computational Linguistics, August 23-29, 2014, Dublin, Ireland. 2014: 69-78.

NIU G, LIU E, WANG X, et al. Enhanced discriminate feature learning deep residual CNN for multitask bearing fault diagnosis with information fusion[J]. IEEE Transactions on Industrial Informatics, 2022, 19(1): 762.

肖建平,朱永利,张翼,等.基于增量学习的变压器局部放电模式识别[J].电机与控制学报, 2023, 27(2): 9.

XIAO Jianping, ZHU Yongli, ZHANG Yi, et al. Transformer partial discharge pattern recognition based on incremental learning[J]. Electric Machines and Control, 2023, 27(2): 9.

宋向金,孙文举,刘国海,等.深度子领域自适应网络电机滚动轴承跨工况故障诊断[J].电工技术学报,2024,39 (1):182.

SONG Xiangjin, SUN Wenju, LIU Guohai, et al. Across working conditions fault diagnosis for motor rolling bearing based on deep subdomain adaption network[J]. Transactions of China Electrotechnical Society, 2024, 39(1): 182.

金亮,杨柳,王艳阳.基于特征迁移的永磁同步电机性能预测[J].电机与控制学报, 2022, 26(3): 117.

JIN Liang, YANG Liu, WANG Yanyang. Performance prediction of permanent magnet synchronous motors based on feature transfer[J]. Electric Machines and Control, 2022, 26(3): 117.

ZHAO Ting, WU Xiangqian. Pyramid feature attention network for saliency detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 15-20, 2019, Long Beach, CA, USA. 2019: 3085-3094.

ZHANG W, PENG G, LI C, 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.

ZHANG W, LI X, DING Q. Deep residual learning-based fault diagnosis method for rotating machinery[J]. ISA Transactions, 2019, 95: 295.

Views

795

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Adaptive algorithm for bearing fault characterization based on multi-scale attention mechanism

Fault diagnosis on stator inter-turn short circuit in synchronous generator considering voltage unbalance

Study on fault area discrimination of ultra-high voltage three-terminal hybrid DC transmission line based on CNN-BiLSTM-Attention

Fault diagnosis of synchronous motors by fusing shaft voltage and vibration features

Fault diagnosis method for motor bearings under small sample conditions using improved infoGAN and QPSO-VGG16

Related Author

LIU Jialong

ZHANG Liyan

DONG Enyuan

WANG Yongxing

ZHANG Chuanlong

HUANG Debin

LI Junqing

YU Changliang

Related Institution

School of Electrical Engineering, Dalian University of Technology

Dalian Special Equipment Inspection and Testing Institute Co., Ltd.

School of Electric and Electronic Engineering，North China Electric Power University

School of Energy Power and Mechanical Engineering，North China Electric Power University

Chengde Power Supply Company of State Grid Jibei Electric Power Co.，Ltd.

AI问答

⁰