基于FDVI和CDDPM的小样本岸桥齿轮箱多类故障诊断

PDF(3042 KB)

振动与冲击 ›› 2025, Vol. 44 ›› Issue (6) : 306-317.

故障诊断分析

基于FDVI和CDDPM的小样本岸桥齿轮箱多类故障诊断

袁九海，张氢*，张建群，冯文宗，孙远韬

作者信息 +

Multi-class and small-sample fault diagnosis of shore bridge gearboxes based on FDVI and CDDPM

YUAN Jiuhai, ZHANG Qing*, ZHANG Jianqun, FENG Wenzong, SUN Yuantao

Author information +

文章历史 +

摘要

岸桥齿轮箱零部件数量多、故障类型丰富，且故障数据难以获取，其诊断面临小样本、多分类的问题。针对上述问题，提出了一种基于频域振动图（frequency domain vibration image，FDVI）和条件去噪扩散概率模型（conditional denoising diffusion probabilistic model，CDDPM）的故障诊断方法。首先将获取的振动信号转为FDVI图像，充分表征各故障的振动信号的特征信息。然后，使用CDDPM对小样本数据进行扩充，将标签信息输入到模型以控制生成故障样本类别，同时采用跳层采样加快样本生成速度。将扩充后的样本集输入卷积神经网络分类器中进行训练，提升分类器对小样本多类故障诊断的效果。在对CWRU数据集的17种故障类型和岸桥缩尺实验台数据集的29种故障类型的小样本诊断实验表明：样本扩充后CWRU数据集故障识别率由89.86%提高到99.30%；岸桥数据集故障识别率由68.63%提高到95.75%。上述分析表明所提方法能完成小样本条件下岸桥齿轮箱多类故障诊断任务。

Abstract

The number of components and fault types of the shore bridge gearbox is large, and the fault data is difficult to obtain, and its diagnosis faces the problem of small sample and multiple classification. To address the above problems, a fault diagnosis method based on frequency domain vibration image (FDVI) and conditional denoising diffusion probabilistic model (CDDPM) is proposed. Firstly, the obtained vibration signals are transformed into images using the FDVI method, fully characterizing the characteristic information of vibration signals for each fault. Then, the CDDPM is used to expand the small sample data, and the labeling information is input to the model to control the generation of fault sample categories, while skip-layer sampling is used to accelerate the sample generation speed. Input the expanded sample set into a convolutional neural network classifier for training to improve the classifier's performance in diagnosing multi class faults with small samples. The small-sample diagnostic experiments on the 17 faults in the CWRU dataset and the 29 faults in the shore bridge scaling experimental platform dataset show that: after the sample expansion, the fault recognition rate of the CWRU dataset is increased from 89.86% to 99.30%; the fault recognition rate of the shore bridge dataset is increased from 68.63% to 99.30%. The above analysis shows that the proposed method can accomplish the task of multi-class fault diagnosis for shore bridge gearboxes under small sample conditions.

导出引用

袁九海, 张氢, 张建群, 冯文宗, 孙远韬. 基于FDVI和CDDPM的小样本岸桥齿轮箱多类故障诊断[J]. 振动与冲击, 2025, 44(6): 306-317

YUAN Jiuhai, ZHANG Qing, ZHANG Jianqun, FENG Wenzong, SUN Yuantao. Multi-class and small-sample fault diagnosis of shore bridge gearboxes based on FDVI and CDDPM[J]. Journal of Vibration and Shock, 2025, 44(6): 306-317

参考文献

[1] Zheng Y, Zhao F, Wang Z. Fault diagnosis system of bridge crane equipment based on fault tree and Bayesian network[J]. The International Journal of Advanced Manufacturing Technology, 2019, 105: 3605-3618.
[2] Zhang J Q, Zhang Q, Feng W Z, et al. Gearbox fault diagnosis based on frequency-domain Gramian angular difference field and deep convolutional neural network[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2023, 237(21): 5187-5202.
[3] Lei Y G, Yang B, Jiang X W, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap[J]. Mechanical Systems and Signal Processing, 2020, 138: 106587.
[4] 李恒，张氢，秦仙蓉，等．基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J]．振动与冲击，2018，37(19)：124—131．
Li Heng，Zhang Qing，QIN Xianrong, et a1．Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network[J]. Journal of Vibration and Shock, 2018, 37(19): 124—131.
[5] Zhang J Q, Zhang Q, Qin X R, et al. Robust fault diagnosis of quayside container crane gearbox based on 2D image representation in frequency domain and CNN[J]. Structural Health Monitoring, 2024, 23(1): 324-342.
[6] Wang C H, Sun Y J, Wang X H. Image deep learning in fault diagnosis of mechanical equipment[J]. Journal of Intelligent Manufacturing, 2023: 1-41.
[7] Zhang T C, Chen J L, Li F D, et al. Intelligent fault diagnosis of machines with small & imbalanced data: A state-of-the-art review and possible extensions[J]. ISA transactions, 2022, 119: 152-171.
[8] Liu H, Liu Z Y, Jia W Q, et al. A novel imbalanced data classification method based on weakly supervised learning for fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2021, 18(3): 1583-1593.
[9] Shorten C, Khoshgoftaar T M. A survey on image data augmentation for deep learning[J]. Journal of big data, 2019, 6(1): 1-48.
[10] 司伟伟，岑健，伍银波，等．小样本轴承故障诊断研究综述[J].计算机工程与应用，2023,59(6):45-56.
Si Weiwei，Cen Jian，Wu Yinbo, et a1．Review of Research on Bearing Fault Diagnosis with Small Samples[J]. Journal of Computer Engineering & Applications, 2023, 59(6):45-56.
[11] Zhang H X, Li M F. RWO-Sampling: A random walk over-sampling approach to imbalanced data classification[J]. Information Fusion, 2014, 20: 99-116.
[12] Fernández A, Garcia S, Herrera F, et al. SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary[J]. Journal of artificial intelligence research, 2018, 61: 863-905.
[13] He H B, Bai Y, Garcia E A, et al. Adaptive synthetic sampling approach for imbalanced learning. IEEE international joint conference on neural networks[C]//IEEE World Congress On Computational Intelligence. Hong Kong, China. IEEE, 2008: 1322-1328.
[14] 李梦男,李琨,叶震,等. 结合SE-VAE与M1DCNN的小样本数据下轴承故障诊断[J]. 机械科学与技术,2024,43(5):773-780.
Li Mengnan, Li Kun, Ye Zhen, et al. Bearing Fault Diagnosis Under Small Sample Data Based on SE-VAE and M1DCNN[J]. Mechanical Science and Technology for Aerospace Engineering, 2024,43(5):773-780.
[15] Chen Z H, Chen J L, Feng Y, et al. Imbalance fault diagnosis under long-tailed distribution: Challenges, solutions and prospects[J]. Knowledge-Based Systems, 2022, 258: 110008.
[16] 谢由生,张军. 改进条件对抗网络在小样本故障诊断中的研究[J]. 机械科学与技术,2023,42(11):1904-1911.
Xie Yousheng, Zhang jun. Research on Improved Conditional Generative Adversarial Network for Small Sample Fault Diagnosis[J]. Mechanical Science and Technology for Aerospace Engineering, 2023,42(11):1904-1911.
[17] 李良钰,苏铁熊,马富康. 高压共轨系统小样本故障诊断方法[J]. 内燃机学报,2023,41(3):255-262.
Li Liangyu, Su Tiexiong, Ma Fukang. Small-Sample Fault Diagnosis Method for High Pressure Common Rail System[J]. Transactions of Csice, 2023,41(3):255-262.
[18] Gao X, Deng F, Yue X H. Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty[J]. Neurocomputing, 2020, 396: 487-494.
[19] Chen M Z, Shao H D, Dou H X, et al. Data augmentation and intelligent fault diagnosis of planetary gearbox using ILoFGAN under extremely limited samples[J]. IEEE Transactions on Reliability, 2022, 72(3): 1029-1037.
[20] Zhang L, Zhang H, Cai G W. The multiclass fault diagnosis of wind turbine bearing based on multisource signal fusion and deep learning generative model[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-12.
[21] Li W, Zhong X, Shao H D, et al. Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new framework[J]. Advanced Engineering Informatics, 2022, 52: 101552.
[22] Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models[J]. Advances in neural information processing systems, 2020, 33: 6840-6851.
[23] Dhariwal P, Nichol A. Diffusion models beat GANs on image synthesis[J]. Advances in neural information processing systems, 2021, 34: 8780-8794.
[24] Yang X Y, Ye T Y, Yuan X F, et al. A Novel Data Augmentation Method Based on Denoising Diffusion Probabilistic Model for Fault Diagnosis Under Imbalanced Data[J]. IEEE Transactions on Industrial Informatics, 2024, 20:7820-7831.
[25] Nguyen D, Kang M, Kim C H, et al. Highly reliable state monitoring system for induction motors using dominant features in a two-dimension vibration signal[J]. New review of hypermedia and multimedia, 2013, 19(3-4): 248-258.
[26] Bai Y L, Yang J W, Wang J H, et al. Intelligent diagnosis for railway wheel flat using frequency-domain Gramian angular field and transfer learning network[J]. Ieee Access, 2020, 8: 105118-105126.
[27] Song J M, Meng C L, Ermon S. Denoising diffusion implicit models[J]. arXiv preprint arXiv:2010.02502, 2020.
[28] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany. Springer International Publishing, 2015: 234-241.
[29] 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: 100-131.
[30] 孙洁娣,赵彬集,温江涛,等. 压缩感知字典迁移重构的小样本轴承故障诊断[J]. 振动与冲击,2024,43(5):62-71,120.
Sun Jiedi, Zhao Binji, Wen Jiangtao, et al. Small sample bearing fault diagnosis based on compressed sensing reconstruction and dictionary transfer[J]. Journal of Vibration and Shock, 2024,43(5):62-71,120.
[31] 柳雅倩,蔡浩原,李文宽,等. 小样本条件下轴承故障的DCGAN诊断方法[J]. 振动、测试与诊断,2023,43(4):817-823.
Liu Yaqian, Cai Haoyuan, Li Wenkuan et al. Research on Deep Convolutional Generative Adversarial Networks Diagnosis Method of Bearing Fault Under Small Sample Condition[J]. Journal of Vibration，Measurement & Diagnosis, 2023,43(4):817-823.
[32] 张钊光,蒋庆磊,詹瑜滨,等. 基于VAE-GAN数据增强算法的小样本滚动轴承故障分类方法[J]. 原子能科学技术,2023,57(z1):228-237.
Zhang Zhaoguang, Jiang Qinglei, Zhan Yubin, VAE-GAN Data Enhancement Networks-based Model for Rolling Bearing Few-shot Fault Classification[J]. Atomic Energy Science and Technology, 2023,57(z1):228-237.
[33] 杨青,陆见光,唐向红,等. 基于infoGAN和CNN的轴承小样本故障诊断[J]. 兵器装备工程学报,2021,42(11):235-240.
Yang Qing, Lu Jianguang, Tang Xianghong, et al. Bearing Small Sample Fault Diagnosis Based on InfoGAN and CNN[J]. Journal of Ordnance Equipment Engineering, 2021,42(11):235-240.
[34] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE transactions on image processing, 2004, 13(4): 600-612.
[35] Gretton A, Borgwardt K M, Rasch M J, et al. A kernel two-sample test[J]. The Journal of Machine Learning Research, 2012, 13(1): 723-773.
[36] Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv preprint arXiv:1511.06434, 2015.
[37] Odena A, Olah C, Shlens J. Conditional image synthesis with auxiliary classifier gans[C]//International conference on machine learning. Sydney, Australia. PMLR, 2017: 2642-2651.
[38] Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of wasserstein gans[J]. Advances in neural information processing systems, 2017, 30.
[39] Larsen A B L, Sønderby S K, Larochelle H, et al. Autoencoding beyond pixels using a learned similarity metric[C]//International conference on machine learning. New York City, USA. PMLR, 2016: 1558-1566.
[40] Shmelkov K, Schmid C, Alahari K. How good is my GAN?[C]//Proceedings of the European conference on computer vision (ECCV). Munich, Germany. 2018: 213-229.