RESEARCH PAPER
Fault diagnosis of gear based on URP-CVAE-MGAN under imbalanced and small sample conditions
More details
Hide details
1
Shenyang University of Technology, China
2
Northeastern University, China
Submission date: 2024-08-29
Final revision date: 2024-10-21
Acceptance date: 2024-12-20
Online publication date: 2024-12-22
Publication date: 2024-12-22
Corresponding author
Jie Liu
Shenyang University of Technology, China
Eksploatacja i Niezawodność – Maintenance and Reliability 2025;27(3):199417
HIGHLIGHTS
- The Un-threshold Recurrence Plots (URP) and Vision Transformer (ViT) improved by Dropkey are used for diagnosing gear fault types and severities.
- A new generated model, the Variational Autoencoder added Conditional variable (CVAE) combined with Generative Adversarial Network improved Mean feature difference function (MGAN), is used for data augmentation of un-threshold recurrence plots from gear under imbalanced and small sample conditions.
- Dropkey-ViT has more advantages in comprehensively capturing fault information compared with the comparison method.
KEYWORDS
TOPICS
ABSTRACT
To improve diagnosis accuracy for gear fault diagnosis under imbalanced and small sample conditions, a method combining the Un-threshold Recurrence Plots - Conditional Variational Autoencoder-Mean Generative Adversarial Network (URP-CVAE-MGAN) combined with Dropkey-Vision Transformer (DViT) is proposed. First, gear vibrational signals are transformed into Recurrence Plots (RP) images to extract more fault features without threshold effect. Then, a conditional variable and mean feature difference function are incorporated into VAE-GAN to improve the quality and diversity of generated samples, balancing the imbalanced and small sample sets. Dropkey is applied to the diagnosis model Vision Transformer to capture more fault information, improving diagnosis accuracy across various fault types and severities for gear. Finally, the proposed method is verified based on two datasets, demonstrating a significant accuracy improvement of up to 7.84% under the imbalanced and small samples, and confirming its feasibility and superiority.
REFERENCES (55)
1.
Liu R, Yang B, Zio E, Chen X. Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing 2018; 108: 33-47,
https://doi.org/10.1016/j.ymss....
2.
Ning J, Chen Z, Wang Y, Wang Y, Li F, Zhai W. Vibration feature of spur gear transmission with non-uniform depth distribution of tooth root crack along tooth width. Engineering Failure Analysis 2021; 129: 105713,
https://doi.org/10.1016/j.engf....
3.
Parey A, Pachori R. Variable cosine windowing of intrinsic mode functions: Application to gear fault diagnosis. Measurement 2012; 45(3): 415-426,
https://doi.org/10.1016/j.meas....
4.
Praveenkumar T, Sabhrish B, Saimurugan M, Ramachandran K. Pattern recognition based on-line vibration monitoring system for fault diagnosis of automobile gearbox. Measurement 2018; 114: 233-242,
https://doi.org/10.1016/j.meas....
5.
Li D Z, Wang W, Ismail F. An enhanced bispectrum technique with auxiliary frequency injection for induction motor health condition monitoring. IEEE Transactions on Instrumentation Measurement 2015; 64(10): 2679-2687,
https://doi.org/10.1109/TIM.20....
6.
Chaari F, Bartelmus W, Zimroz R, Fakhfakh T, Haddar M. Gearbox vibration signal amplitude and frequency modulation. Shock and Vibration 2012; 19(4): 635-652,
https://doi.org/10.3233/SAV-20....
7.
Yu K, Lin T, Ma H, Li H, Zeng J. A combined polynomial chirplet transform and synchro extracting technique for analyzing nonstationary signals of rotating machinery. IEEE Transactions on Instrumentation and Measurement 2019; 69(4): 1505-1518,
https://doi.org/10.1109/TIM.20....
9.
Li H, Liu T, Wu X, Chen Q. A bearing fault diagnosis method based on enhanced singular value decomposition. IEEE Transactions on Industrial Informatics 2020; 17(5): 3220-3230,
https://doi.org/ 10.1109/TII.2020.3001376.
10.
Peng Z, Chu F. Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography. Mechanical Systems and Signal Processing 2004; 18(2): 199-221,
https://doi.org/10.1016/S0888-....
11.
Lei Y, Lin J, He Z, Zuo M. A review on empirical mode decomposition in fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing 2013; 35(1-2): 108-126,
https://doi.org/10.1016/j.ymss....
12.
Zhao W, Liu J, Zhao W, Zheng Y. An investigation on vibration features of a gear-bearing system involved pitting faults considering effect of eccentricity and friction. Engineering Failure Analysis 2022; 131: 105837,
https://doi.org/10.1016/j.engf....
13.
Wang J, Li S, Xin Y, An H. Gear fault intelligent diagnosis based on frequency-domain feature extraction. Journal of Vibration Engineering & Technologies 2019; 7(2): 159-166,
https://doi.org/ 10.1007/s42417-019-00089-1.
14.
Wang H, Zhou Z, Zhang L, Yan R. Multiscale deep attention Q network: A new deep reinforcement learning method for imbalanced fault diagnosis in gearboxes. IEEE Transactions on Instrumentation and Measurement 2024; 73: 3503512,
https://doi.org/10.1109/TIM.20....
15.
Ye Z, Yue S, Yang P, Zhou R, Yu J. Deep morphological shrinkage convolutional auto-encoder-based feature learning of vibration signals for gearbox fault diagnosis. IEEE Transactions on Instrumentation and Measurement 2024; 73: 3510712,
https://doi.org/10.1109/TIM.20....
16.
Zhang J, Xu B, Wang Z, Zhang J. An FSK-MBCNN based method for compound fault diagnosis in wind turbine gearboxes. Measurement 2021; 172: 108933,
https://doi.org/10.1016/j.meas....
17.
Jia S, Wang P, Jia P, Hu S. Research on data augmentation for image classification based on convolution neural networks. In 2017 Chinese automation congress (CAC) IEEE 2017; 4165-4170,
https://doi.org/ 10.1109/CAC.2017.8243510.
18.
Yu K, Lin T, Ma H, Li X, Li X. A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning. Mechanical Systems and Signal Processing 2021; 146: 107043,
https://doi.org/10.1016/j.ymss....
19.
Ma L, Ding Y, Wang Z, Wang C, Ma J, Lu C. An interpretable data augmentation scheme for machine fault diagnosis based on a sparsity-constrained generative adversarial network. Expert Systems with Applications 2021; 182: 115234,
https://doi.org/10.1016/j.eswa....
20.
Wang J, Li S, Han B, An Z, Bao H, Ji S. Generalization of deep neural networks for imbalanced fault classification of machinery using generative adversarial networks. IEEE Access 2019; 7: 111168-111180,
https://doi.org/10.1109/ACCESS....
21.
Moreno-Barea F J, Jerez J M, Franco L. Improving classification accuracy using data augmentation on small data sets. Expert Systems with Applications 2020; 161: 113696,
https://doi.org/10.1016/j.eswa....
22.
Zhao D, Liu S, Gu D, Sun X, Wang L, Wei Y, Zhang H. Enhanced data-driven fault diagnosis for machines with small and unbalanced data based on variational auto-encoder. Measurement Science and Technology 2019; 31(3): 035004, 2019
https://doi.org/ 10.1088/1361-6501/ab55f8.
23.
Khan M A, Asad B, Vaimann T, Kallaste A, Pomarnacki R, Hyunh V K, Improved fault classification and localization in power transmission networks using VAE-generated synthetic data and machine learning algorithms. Machines 2023; 11(10): 963,
https://doi.org/10.3390/machin....
25.
Yao Y, Wang H, Li S, Liu Z, Gui G, Dan Y, Hu J. End-to-end convolutional neural network model for gear fault diagnosis based on sound signals. Applied Sciences 2018; 8(9): 1584,
https://doi.org/ 10.3390/app8091584.
26.
Ghulanavar R, Dama K, Jagadeesh A. Diagnosis of faulty gears by modified AlexNet and improved grasshopper optimization algorithm (IGOA). Journal of Mechanical Science and Technology 2020; 34: 4173-4182,
https://doi.org/ 10.1007/s12206-020-0909-6.
27.
Yang G, Wei Y, Li H. Acoustic diagnosis of rolling bearings fault of CR400 EMU traction motor based on XWT and GoogleNet. Shock and Vibration 2022; 2022: 2360067,
https://doi.org/10.1155/2022/2....
28.
Hu H, Feng F, Jiang F, Zhou X, Zhu J, Xue J, Jiang P, Li Y, Qian Y, Sun G, Chen C. Gear fault detection in a planetary gearbox using deep belief network. Mathematical Problems in Engineering 2022; 2022: 9908074,
https://doi.org/10.1155/2022/9....
29.
Shi H, Huang C, Zhang X, Zhao J, Li S. Wasserstein distance based multi-scale adversarial domain adaptation method for remaining useful life prediction. Applied Intelligence 2023; 53(3): 3622-3637,
https://doi.org/ 10.1007/s10489-022-03670-6.
31.
Hu A, Sun J, Xiang L, Xu Y. Rotating machinery fault diagnosis based on impact feature extraction deep neural network. Measurement Science and Technology 2022; 33(11): 114004,
https://doi.org/10.1088/1361-6....
32.
Tang X, Xu Z, Wang Z. A novel fault diagnosis method of rolling bearing based on integrated vision transformer model. Sensors 2022; 22(10): 3878,
https://doi.org/10.3390/s22103....
33.
Zhou Z, Ai Q, Lou P, et al. A novel method for rolling bearing fault diagnosis based on gramian angular field and CNN-ViT. Sensors 2024; 24(12): 3967,
https://doi.org/10.3390/s24123....
34.
Bai R, Meng Z, Xu Q, Fan F. Fractional fourier and time domain recurrence plot fusion combining convolutional neural network for bearing fault diagnosis under variable working conditions. Reliability Engineering & System Safety 2023; 232: 109076,
https://doi.org/ https://doi.org/10.1016/j.ress....
35.
Liu X P, Xia L J, Shi J, Zhang L J, Bai L Y, Wang S P. A fault diagnosis method of rolling bearing based on improved recurrence plot and convolutional neural network. IEEE Sensors Journal 2023; 23(10): 10767-10775,
https://doi.org/10.1109/JSEN.2....
36.
Yan J, Huang Y, Yuan S, Lu Y, Yu Z. Open‐circuit fault analysis and recognition in three‐level inverters based on recurrence plot and convolution neural network. International Transactions on Electrical Energy Systems 2023; 2023(1): 4755960,
https://doi.org/10.1155/2023/4....
38.
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets. In Advances in Neural Information Processing Systems 2012; 2672–2680,
https://doi.org/ 10.3156/JSOFT.29.5_177_2.
39.
Larsen A B L, Sønderby S K, Winther O. Autoencoding beyond pixels using a learned similarity metric. arXiv preprint arXiv 2015; 1512: 09300,
https://doi.org/ 10.48550/arXiv.1512.09300.
40.
Bao J, Chen D, Wen F, Li H, Hua G. CVAE-GAN: Fine-grained image generation through asymmetric training. In Proceedings of the IEEE international conference on computer vision 2017; 2745-2754,
https://doi.org/ 10.1109/ICCV.2017.299.
41.
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J. An image is worth 16x16 words: Transformers for image recognition at scale. arxiv preprint arxiv: 2020, 2010: 11929,
https://doi.org/ 10.48550/arXiv.2010.11929.
42.
Yang N, Liu J, Zhao W Q, Tan Y T. Fault diagnosis of gear based on multi-channel feature fusion and Dropkey-Vision Transformer. IEEE Sensors Journal 2024; 24(4): 4758-4770,
https://doi.org/10.1109/JSEN.2....
43.
Li B, Hu Y, Nie X, Han C, Jia X, Guo T, Liu L. DropKey. Presented at proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023; 2023,
https://doi.org/10.48550/arXiv....
44.
Chen C, Shen F, Xu J, Yan R. Model parameter transfer for gear fault diagnosis under varying working conditions. Chinese Journal of Mechanical Engineering 2021; 34(1): 13,
https://doi.org/10.1186/s10033....
45.
Meng Z, He H H, Cao W, Li J M, Cao L X, Fan J J, Zhu M, Fan F J. A novel generation network using feature fusion and guided adversarial learning for fault diagnosis of rotating machinery. Expert Systems with Applications 2023; 234: 121058,
https://doi.org/10.1016/j.eswa....
46.
Rathore M S, Harsha S P. Non-linear vibration response analysis of rolling bearing for data augmentation and characterization. Journal of Vibration Engineering & Technologies 2023; 11(5): 2109-2131,
https://doi.org/10.1007/s42417....
47.
Zhang L, Duan L, Hong X, Liu X, Zhang X. Imbalanced data enhancement method based on improved DCGAN and its application. Journal of Intelligent & Fuzzy Systems 2021; 41(2): 3485-3498,
https://doi.org/ 10.3233/JIFS-210843.
48.
Zhang L, Zhang H, Cai G. The multiclass fault diagnosis of wind turbine bearing based on multisource signal fusion and deep learning generative model. IEEE Transactions on Instrumentation and Measurement 2022; 71: 1-12, 2022
https://doi.org/ 10.1109/TIM.2022.3178483.
49.
Wang Y, Sun G, Jin Q. Imbalanced sample fault diagnosis of rotating machinery using conditional variational auto-encoder generative adversarial network. Applied Soft Computing 2020; 92: 106333,
https://doi.org/10.1016/j.asoc....
50.
Gao Y, Liu X, Xiang J. Fault detection in gears using fault samples enlarged by a combination of numerical simulation and a generative adversarial network. IEEE/ASME Transactions on Mechatronics 2021; 27(5): 3798-3805,
https://doi.org/10.1109/TMECH.....
51.
Zhou C, Wang H, Hou S, et al. A hybrid physics-based and data-driven method for gear contact fatigue life prediction. International Journal of Fatigue 2023; 175: 107763,
https://doi.org/10.1016/j.ijfa....
53.
Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. Advances in Nneural Information Processing Systems 2017; 6(60): 84-90,
https://doi.org/10.1145/306538....
54.
Maaten L V D, Hinton G. Visualizing data using t-SNE. Journal of Machine Learning Research 2008; 9(11): 2579-2605.
55.
Chen X, Zhang B, Gao D. Bearing fault diagnosis base on multi-scale CNN and LSTM model, Journal of Intelligent Manufacturing 2021; 32: 971-987,
https://doi.org/10.1007/s10845....