Fault diagnosis method based on Swin Transformer with path aggregation networks

PDF(2366 KB)

Journal of Vibration and Shock ›› 2024, Vol. 43 ›› Issue (18) : 258-266.

LIU Chenyu1， LI Zhinong1， XIONG Pengwei1， GU Fengshou2

Author information +

History +

Abstract

To address the insufficient spatial information feature modeling capability and high computational complexity of the Transformer in aero-engine fault diagnosis, a fault diagnosis approach was proposed based on the Swin Transformer with path aggregation networks (PANet). In the proposed method, the Swin Transformer with PANet improves the efficiency by fusing the multiscale feature pyramid from top and bottom information. Then, window-based multi-head self-attention and shift window-based multi-head self-attention modules are used to reduce the computational complexity in spatial information feature extraction. Therefore, the information flow and feature transmission can be promoted effectively. Finally, the proposed method is applied in fault diagnosis for the aero-engine rolling bearings. The experimental results show that the proposed method is better than the Transformer and traditional Swin Transformer methods while guaranteeing the recognition accuracy and improving the recognition speed of the model.

Key words

fault diagnosis / Swin Transformer / Path Aggregation Network (PANet) / aeroengine / rolling bearings

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LIU Chenyu1, LI Zhinong1, XIONG Pengwei1, GU Fengshou2. Fault diagnosis method based on Swin Transformer with path aggregation networks[J]. Journal of Vibration and Shock, 2024, 43(18): 258-266

References

[1] 石争浩，李成建，周亮，等. Transformer驱动的图像分类研究进展[J]. 中国图象图形学报，2023, 28(09): 2661-2692.
SHI Zheng-hao, LI Cheng-jian, ZHOU Liang, et al. Survey on Transformer for image classification [J]. Journal of Image and Graphics, 2023, 28(09): 2661-2692.
[2] Yoo S, Kwon O, Lee H. Image-to-Graph transformers for chemical structure recognition [C]// IEEE International Conference on Acoustics, Speech and Signal Processing. Singapore: ICASSP, 2022. 3393-3397.
[3] Vaswani A, Shazeer N, Parmer N, et al. Attention Is All You Need [J]. Advances in neural information processing systems, 2017, 30.
[4] 沈逸文，孙俊. 结合Transformer的轻量化中文语音识别[J]. 计算机应用研究，2023, 40(02): 424-429.
SHEN Yi-wen, SUN Jun. Lightweight Chinese speech recognition with Transformer [J]. Application Research of Computers, 2023, 40(02): 424-429.
[5] Plizzari C, Cannici M, Matteucci M. Skeleton based action recognition via spatial and temporal transformer networks [J]. Computer Vision and Image Understanding, 2021, 208/209: 103219.
[6] 朱丹宸，张永祥，潘洋洋，等. 基于多传感器信号和卷积神经网络的滚动轴承故障诊断[J]. 振动与冲击，2020, 39(04): 172-178.
ZHU Dan-chen, ZHANG Yong-xiang, PAN Yang-yang, et al. Fault diagnosis for rolling element bearings based on multi-sensor signals and CNN [J]. Journal of Vibration and Shock, 2020, 39(4): 172-178.
[7] 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. Mechanical fault diagnosis method based on attentat BiGRU [J]. Journal of Vibration and Shock, 2021, 40(19): 239-245.
[8] 刘俊锋，俞翔，万海波，等. 基于MFMD和Transformer-CNN的滚动轴承故障诊断方法[J]. 航空动力学报，2023, 38(06): 1446-1456.
LIU Jun-feng, YU Xiang, WAN Hai-bo, et al. Fault diagnosis method of rolling bearing using MFMD and Transformer-CNN [J]. Journal of Aerospace Power, 2023, 38(06): 1446-1456.
[9] Zhou K, Tong Y F, Li X T, et al. Exploring global attention mechanism on fault detection and diagnosis for complex engineering processes[J]. Process Safety and Environmental Protection, 2023, 170: 660-669.
[10] 杜康宁，宁少慧，邓功也. 基于视觉Transformer的滚动轴承智能故障诊断[J]. 组合机床与自动化加工技术，2023, (04): 96-99.
DU Kang-ning, NING Shao-hui, DENG Gong-ye. Intelligent fault diagnosis of rolling bearings based on vision Transformer [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2023, (04): 96-99.
[11] 火久元，李超杰，于春潇. 基于Transformer的多标签工业故障诊断方法研究[J]. 振动与冲击，2023, 42(18): 88-99+189.
HUO Jiu-yuan, LI Chao-jie, YU Chun-xiao. Multi-label industrial fault diagnosis method based on the Transformer network model [J]. Journal of Vibration and Shock, 2023, 42(18): 88-99+189.
[12] 邱大伟，刘子辰，周一青，等. 基于Transformer神经网络的滚动轴承故障类型识别[J]. 高技术通讯，2021, 31(01): 1-11.
QIU Da-wei, LIU Zi-chen, ZHOU Yi-qing, et al. A novel fault type detection method of rolling bearing using transformer neural networks [J]. Chinese High Technology Letters, 2021, 31(01): 1-11.
[13] 林昙涛，牛青波，马天旭，等. 基于Transformer的智能轴承声-振融合故障诊断[J]. 轴承，2023, (02): 67-73.
LIN Tan-tao, NIU Qing-bo, MA Tian-xu, et al. Acoustic-Vibration fusion fault diagnosis for intelligent bearing based on transformer [J]. Bearing, 2023, (02): 67-73.
[14] 赵洪利，杨佳强. 基于融合卷积Transformer的航空发动机故障诊断[EB/OL]. (2023-06-09)[2023-11-05]. . https://doi.org/10.13700/j.bh.1001-5965.2023.0206.
[15] Liu Z, Lin Y T, Cao Y, et al. Swin Transformer: Hierarchical vision transformer using shifted windows [C]// 2021 IEEE/CVF International Conference on Computer Vision. Canda: ICCV, 2021. 9992-10002.
[16] 夏衍，罗晨，周怡君，等. 基于Swin Transformer轻量化的TFT-LCD面板缺陷分类算法[J]. 光学精密工程，2023, 31(22): 3357-3370.
XIA Yan, LUO Chen, ZHOU Yi-jun, et al. A lightweight deep learning model for TFT-LCD circuits defect classification based on swin transformer [J]. Optics and Precision Engineering, 2023, 31(22): 3357-3370.
[17] Liu X L, Li J N, Li Z. Multiscale fusion attention convolutional neural network for fault diagnosis of aero-engine rolling bearing [J]. Sensors Journal, 2023, 23(17): 19918-19934.
[18] 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): 285-293.
KANG Yu-xiang, CHEN Guo, WEI Xun-kai, 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): 285-293.
[19] 李泽东，李志农，陶俊勇，等. 基于特征融合的注意力增强卷积神经网络的航空发动机滚动轴承故障诊断方法[J]. 兵工学报，2022, 43(12): 3228-3239.
LI Ze-dong, LI Zhi-nong, TAO Jun-yong, et al. Fault diagnosis for aero-engine rolling bearings based on an attention augmented convolutional neural network with feature fusion [J]. Acta Armamentarii, 2022, 43(12): 3228-3239.
[20] Yu J, Zhang W. Face mask wearing detection algorithm based on improved YOLO-v4[J]. Sensors, 2021, 21(9): 3263-3263.
[21] Daga A P, Fasana A, Marchesiello S, et al. The politecnico di torino rolling bearing test rig: Description and analysis of open access data [J]. Mechanical Systems and Signal Processing, 2019, 120: 252-273
[22] Zheng H, Wang G H. Li X C. Swin-MLP: a strawberry appearance quality identification method by Swin Transformer and multi-layer perceptron [J]. Journal of Food Measurement and Characterization, 2022, 16(4): 2789–2800.
[23] Kim S, Choi J H. Convolutional neural network for gear fault diagnosis based on signal segmentation approach[J]. Structural Health Monitoring, 2019, 18(5/6): 1401-1415.