Diesel engine fault data augmentation method based on artificial data fusion

PDF(2291 KB)

Journal of Vibration and Shock ›› 2023, Vol. 42 ›› Issue (13) : 278-286.

HUANG Meng1, BI Xiaoyang2, YANG Xiao1, LI Xin1, TANG Daijie1, BI Fengrong1

Author information +

History +

Abstract

Aiming at the problems of over-fitting and low accuracy of the data-driven diesel engine fault diagnosis method caused by the lack of data, a data augmentation method based on artificial data fusion was proposed to augment the training set. This method introduced the Wasserstein distance and gradient penalty into the auxiliary classifier generative adversarial network (ACGAN) in order to overcome the training instability of the original ACGAN. Two kinds of artificial data generated by the ACGANs before and after optimization were introduced into the original training set in proportion, and the training set was augmented from two perspectives: enhancement of the original data and optimization of the judgment range of diagnostic network. The analysis results of the measured vibration signals of the diesel engine show that the diagnosis accuracy under different fault types is improved by this data augmentation method, and the optimization effect is better than the other comparison method in this article.

Key words

generative adversarial network / data fusion / diesel engine / data augmentation

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

HUANG Meng1, BI Xiaoyang2, YANG Xiao1, LI Xin1, TANG Daijie1, BI Fengrong1. Diesel engine fault data augmentation method based on artificial data fusion[J]. Journal of Vibration and Shock, 2023, 42(13): 278-286

References

[1] 王霞. 非平稳信号特征提取方法研究及其在内燃机故障诊断中的应用[D]. 天津：天津大学，2015.
Wang X. Non-stationary signal feature extractior method and its application in internal combustion engine fault diagnosis[D]. Tianjin: Tianjin University, 2015.
[2] 吉哲. 基于声信号的柴油机故障诊断研究[D]. 合肥：中国科学技术大学，2017.
Ji Z. Research on fault diagnosis of diesel engine based on acoustic signal[D]. Hefei: University of science and technology of China, 2017.
[3] Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 1998, 454(1971): 903-995.
[4] Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE transactions on signal processing, 2013, 62(3): 531-544.
[5] 孙志军，薛磊，许阳明，等. 深度学习研究综述[J]. 计算机应用研究，2012, 29(08): 2806-2810.
Sun Z, Xue L, Xu Y, et al. Overview of deep learning[J]. Application Research of Computers. 2012, 29(08): 2806-2810.
[6] 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 H, Zhang Q, Qin X, et al. Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network[J]. Journal of Vibration and Shock. 2018, 37: 124-131.
[7] 朱浩，宁芊，雷印杰，等. 基于注意力机制-Inception-CNN模型的滚动轴承故障分类[J]. 振动与冲击，2020, 39(19): 84-93.
Zhu H, Ning Q, Lei Y, et al. Fault classification of rolling bearing based on attention mechanism-inception-CNN Model[J]. Journal of Vibration and Shock. 2020, 39: 84-93.
[8] Li X, Zhang W, Ding Q, et al. Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation[J]. Journal of Intelligent Manufacturing, 2020, 31(2): 433-452.
[9] Batista G E, Prati R C, Monard M C. A study of the behavior of several methods for balancing machine learning training data[J]. ACM SIGKDD explorations newsletter, 2004, 6(1): 20-29.
[10] Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of artificial intelligence research, 2002, 16: 321-357.
[11] Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[J]. Advances in neural information processing systems, 2014, 27.
[12] Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv preprint arXiv:1511.06434, 2015.
[13] Mirza M, Osindero S. Conditional generative adversarial nets[J]. arXiv preprint arXiv:1411.1784, 2014.
[14] Odena A, Olah C, Shlens J. Conditional image synthesis with auxiliary classifier gans[C]//International conference on machine learning. PMLR, 2017: 2642-2651.
[15] Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks[C]//International conference on machine learning. PMLR, 2017: 214-223.
[16] Luo J, Huang J, Li H. A case study of conditional deep convolutional generative adversarial networks in machine fault diagnosis[J]. Journal of Intelligent Manufacturing, 2021, 32(2): 407-425.
[17] Peng P, Wang Y, Zhang W, et al. Imbalanced process fault diagnosis using enhanced auxiliary classifier gan[C]//2020 Chinese Automation Congress (CAC). IEEE, 2020: 313-316.
[18] Li Y, Zou W, Jiang L. Fault diagnosis of rotating machinery based on combination of Wasserstein generative adversarial networks and long short term memory fully convolutional network[J]. Measurement, 2022, 191: 110826.
[19] Liu H, Zhou J, Xu Y, et al. Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks[J]. Neurocomputing, 2018, 315: 412-424.
[20] 肖雄,肖宇雄,张勇军,等.基于二维灰度图的数据增强方法在电机轴承故障诊断的应用研究[J].中国电机工程学报,2021,41(02):738-749.
Xiao X, Xiao Y, Zhang Y, et al. Research on the application of the data augmentation method based on 2D gray pixel images in fault diagnosis of motor bearing[J]. Proceedings of the CSEE. 2021, 41: 738-749.
[21] 朱克凡,王杰贵,刘有军.小样本条件下基于数据增强和WACGAN的雷达目标识别算法[J].电子学报,2020,48(06):1124-1131.
Radar Target Recognition Algorithm Based on Data Augmentation and WACGAN with a Limited Training Data[J]. Acta Electronica Sinica.2020,48(06):1124-1131.
[22] Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of wasserstein gans[J]. Advances in neural information processing systems, 2017, 30.
[23] Van der Maaten L, Hinton G. Visualizing data using t-SNE[J]. Journal of machine learning research, 2008, 9(11).