|
|
|
| Compound fault decoupling diagnosis method based on improved Transformer |
Yu-xiang WANG1,2( ),Zhi-wei ZHONG1,2,Peng-cheng XIA1,2,Yi-xiang HUANG1,2,*(),Cheng-liang LIU1,2 |
1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2. State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, China |
|
|
|
Abstract Most of the compound fault diagnosis methods regard the compound fault as a new single fault type, ignoring the interaction of internal single faults, and the fault analysis is vague in granularity and poor in interpretation. An improved Transformer-based compound fault decoupling diagnosis method was proposed for industrial environments with very little compound fault data. The diagnosis process included pre-processing, feature extraction and fault decoupling. With introducing the decoder of the Transformer, the cross-attention mechanism enables each single fault label to adaptively in the extracted feature layer focus on the discriminative feature region corresponding to the fault feature and predicts the output probability to achieve compound fault decoupling. Compound fault tests were designed to verify the effectiveness of the method compared with the advanced algorithms. The results showed that the proposed method had high diagnostic accuracy with a small number of single fault training samples and a very small number of compound fault training samples. The compound fault diagnosis accuracy reached 88.29% when the training set contained only 5 compound fault samples. Thus the new method has a significant advantage over other methods.
|
|
Received: 25 July 2022
Published: 09 May 2023
|
|
|
| Fund: 国家自然科学基金资助项目(51975356) |
|
Corresponding Authors:
Yi-xiang HUANG
E-mail: me_wyx@sjtu.edu.cn;huang.yixiang@sjtu.edu.cn
|
基于改进Transformer的复合故障解耦诊断方法
大多复合故障诊断方法视复合故障为一种新的单一故障类型，忽视了内部单一故障的相互作用、故障分析粒度含糊和解释性差. 为了解决复合故障难解耦的问题，针对工业环境中复合故障数据极少的情况，提出一种基于改进Transformer的复合故障解耦诊断方法. 诊断流程分为预处理、特征提取和故障解耦3个步骤. 故障解耦引入Transformer的解码器，利用交叉注意力机制使得每个单一故障标签可以在提取的特征层中，自适应地关注到与故障特征相对应的判别特征区域，进一步预测每个单一故障标签的输出概率以实现复合故障解耦. 设计多组复合故障试验与业界先进算法进行对比，以验证方法的有效性. 结果表明，所提方法在少量单一故障训练样本和极少量复合故障训练样本情况下，有较高的诊断准确度. 当训练集中复合故障样本数仅为5时，复合故障诊断准确度达到88.29%，与其他方法比较更具有显著优势.
关键词：
复合故障诊断,
故障解耦分类器,
Transformer,
卷积神经网络,
旋转机械
|
|
| [1] |
乔美英, 汤夏夏, 闫书豪, 等 基于改进稀疏滤波与深度网络融合的轴承故障诊断[J]. 浙江大学学报: 工学版, 2020, 54 (12): 2301- 2309
QIAO Mei-ying, TANG Xia-xia, YAN Shu-hao, et al Bearing fault diagnosis based on improved sparse filter and deep network fusion[J]. Journal of Zhejiang University: Engineering Science, 2020, 54 (12): 2301- 2309
|
|
|
| [2] |
FENG Z, GAO A, LI K, et al Planetary gearbox fault diagnosis via rotary encoder signal analysis[J]. Mechanical Systems and Signal Processing, 2021, 149: 107325
doi: 10.1016/j.ymssp.2020.107325
|
|
|
| [3] |
XIA P, HUANG Y, XIAO D, et al. Ball screw health indicator construction with limited monitoring data and health assessment based on global context network[C]// 2021 IEEE International Conference on Sensing, Diagnostics, Prognostics and Control (SDPC). Weihai: IEEE, 2021: 168-173.
|
|
|
| [4] |
姚锡凡, 景轩, 张剑铭, 等 走向新工业革命的智能制造[J]. 计算机集成制造系统, 2020, 26 (9): 2299- 2320
YAO Xi-fan, JING Xuan, ZHANG Jian-ming, et al Towarads smart manufacturing for new industrial revolution[J]. Computer Integrated Manufacturing Systems, 2020, 26 (9): 2299- 2320
|
|
|
| [5] |
李杰, 李响, 许元铭, 等 工业人工智能及应用研究现状及展望[J]. 自动化学报, 2020, 46 (10): 2031- 2044
LI Jie, LI Xiang, XU Yuan-ming, et al Recent advances and prospects in industrial AI and applications[J]. Acta Automatica Sinica, 2020, 46 (10): 2031- 2044
doi: 10.16383/j.aas.200501
|
|
|
| [6] |
吴守军, 冯辅周, 吴春志, 等 复合行星轮系故障诊断方法研究进展[J]. 机械科学与技术, 2019, 38 (12): 1910- 1920
WU Shou-jun, FENG Fu-zhou, WU Chun-zhi, et al Research progress on fault diagnosis methods of compound planetary gear train[J]. Mechanical Science and Technology for Aerospace Engineering, 2019, 38 (12): 1910- 1920
|
|
|
| [7] |
LI G, LIANG X, FANGYI L Model-based analysis and fault diagnosis of a compound planetary gear set with damaged sun gear[J]. Journal of Mechanical Science and Technology, 2018, 32: 3081- 3096
doi: 10.1007/s12206-018-0611-0
|
|
|
| [8] |
LYU X, HU Z, ZHOU H, et al Application of improved MCKD method based on QGA in planetary gear compound fault diagnosis[J]. Measurement, 2019, 139: 236- 248
doi: 10.1016/j.measurement.2019.02.071
|
|
|
| [9] |
陈仁祥, 唐林林, 孙健, 等. 一维深度子领域适配的不同转速下旋转机械复合故障诊断[J]. 仪器仪表学报, 2021, 42(5): 227-234.
CHEN Ren-xiang, TANG Lin-lin, SUN Jian, et al. Composite fault diagnosis of rotating machinery under different speed based on one dimensional deep subdomain adaption [J]. Chinese Journal of Scientific Instrument. 2021, 42(5): 227-234.
|
|
|
| [10] |
HUANG R, LI W, CUI L. An intelligent compound fault diagnosis method using one-dimensional deep convolutional neural network with multi-label classifier [C]// 2019 IEEE International Instrumentation and Measurement Technology Conference (i2mtc). New York: IEEE. 2019: 97-102.
|
|
|
| [11] |
HUANG R, LI J, LI W, et al Deep ensemble capsule network for intelligent compound fault diagnosis using multisensory data[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69 (5): 2304- 2314
doi: 10.1109/TIM.2019.2958010
|
|
|
| [12] |
JIN Y, QIN C, HUANG Y, et al Actual bearing compound fault diagnosis based on active learning and decoupling attentional residual network[J]. Measurement, 2021, 173: 108500
doi: 10.1016/j.measurement.2020.108500
|
|
|
| [13] |
LIANG P, DENG C, WU J, et al Compound fault diagnosis of gearboxes via multi-label convolutional neural network and wavelet transform[J]. Computers in Industry, 2019, 113: 103132
doi: 10.1016/j.compind.2019.103132
|
|
|
| [14] |
ZHANG J, ZHANG Q, HE X, et al Compound fault diagnosis of rotating machinery: a fused imbalance learning method[J]. IEEE Transactions on Control Systems Technology, 2021, 29 (4): 1462- 1474
doi: 10.1109/TCST.2020.3015514
|
|
|
| [15] |
齐咏生, 刘飞, 李永亭, 等 基于MK-MOMEDA和Teager能量算子的风电机组滚动轴承复合故障诊断[J]. 太阳能学报, 2021, 42 (7): 297- 307
QI Yong-sheng, LIU Fei, LI Yong-ting, et al Compound fault diagnosis of wind turbine rolling bearing based on MK-MOMEDA and teager energy operator[J]. Journal of Solar Energy, 2021, 42 (7): 297- 307
doi: 10.19912/j.0254-0096.tynxb.2019-0276
|
|
|
| [16] |
杜丽君, 丁康, 蒋飞 基于变速工况稀疏调频字典的齿轮复合故障诊断[J]. 重庆理工大学学报: 自然科学版, 2021, 35 (9): 92- 102
DU Li-jun, DING Kang, JIANG Fei Gear compound faults diagnosis based on sparse frequency modulation dictionary under variable speed[J]. Journal of Chongqing University of Technology: Natual Science, 2021, 35 (9): 92- 102
|
|
|
| [17] |
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
doi: 10.1016/j.eswa.2020.114094
|
|
|
| [18] |
LIU S, ZHANG L, YANG X, et al. Query2Label: a simple transformer way to multi-label classification [EB/OL]. [2022-07-01]. https://doi.org//0.48550/arXiv.2017.10834.
|
|
|
| [19] |
卢昱奇. 基于卷积神经网络的行星齿轮箱复合故障诊断方法研究[D]. 电子科技大学, 2020: 1-20.
LU Yu-qi. Research on Compound Fault Diagnosis Method of Planetary Gearbox Based on Convolutional Neural Network [D]. University of Electronic Science and Technology of China, 2020: 1-20.
|
|
|
| [20] |
VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Advances in Neural Information Processing Systems 30 (nips 2017). La Jolla: NIPS, 2017: 6000-6010.
|
|
|
| [21] |
HAN K, WANG Y, CHEN H, et al A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (1): 87- 110
|
|
|
| [22] |
CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers [C]// Computer Vision – ECCV 2020. Cham: SIP, 2020: 213-229.
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
