A Gear Health Indicator Based on f-AnoGAN
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
The development of high-quality health indicators based on Artificial Intelligence (AI) for condition monitoring, reflecting the degradation process and trend, remains a key area of research. Unsupervised deep learning methods, such as deep autoencoders and variational autoencoders, are often employed to establish health indicators for rotating machinery. However, commonly used methods frequently face challenges in controlling and evaluating the quality of learned features that represent this distribution, which subsequently impacts the accuracy of the test data analysis and anomaly detection. Additionally, the empirical nature of threshold setting adds an element of uncertainty to detections.
The research propose a novel approach for constructing gear health indicators and performing anomaly detection using Generative Adversarial Networks (GAN), with a particular emphasis on the f-AnoGAN structure. The research focuses on modeling the distribution of vibration signals acquired from healthy systems using adversarial learning. By comparing test samples against this modeled distribution, the degree of similarity or dissimilarity acts as an indicator of anomalies. Owing to the generative process of the GAN architecture (creating data from randomly sampled low-dimensional noise), GAN-based modeling overcomes the limitation of autoencoders by aiming to reconstruct the continuous distribution of systems in healthy conditions from a limited set of healthy (training) samples. In this way, it offers more generalizability than traditional model learning. Moreover, this study proposes a new method for establishing thresholds based on distribution fitting by the anomaly score of healthy data. The proposed f-AnoGAN-based model and thresholding technique is applied, tested and evaluated in a gear-pitting degradation dataset and result in more accurate and timely fault detection, markedly enhancing the ability to identify subtle faults in systems over traditional methods.How to Cite
##plugins.themes.bootstrap3.article.details##
Health Indicator, Anomaly Detection, GAN
Dai, J., Wang, J., Huang, W., Shi, J., & Zhu, Z. (2020, October). Machinery Health Monitoring Based on Unsupervised Feature Learning via Generative Adversarial Networks. IEEE/ASME Transactions on Mechatronics, 25(5), 2252–2263. doi:10.1109/TMECH.2020.3012179
Ding, Y., Ma, L., Ma, J., Wang, C., & Lu, C. (2019). A Generative Adversarial Network-Based Intelligent Fault Diagnosis Method for Rotating Machinery Under Small Sample Size Conditions. IEEE Access, 7, 149736149749. doi: 10.1109/ACCESS.2019.2947194 Elasha, F., Ruiz-C´arcel, C., Mba, D., Kiat, G., Nze, I., & Yebra, G. (2014, July). Pitting detection in worm gearboxes with vibration analysis. Engineering Failure Analysis, 42, 366–376. doi:10.1016/j.engfailanal.2014.04.028
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., WardeFarley, D., Ozair, S., . . . Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems (Vol. 27). Curran Associates, Inc. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017, December). Improved training of wasserstein gans (No. arXiv:1704.00028). arXiv. doi:10.48550/arXiv.1704.00028
He, R., Tian, Z., & Zuo, M. J. (2022, April). A semi-supervised gan method for rul prediction using failure and suspension histories. Mechanical Systems and Signal Processing, 168, 108657. doi:10.1016/j.ymssp.2021.108657
4393–4402). PMLR. Salameh, J. P., Cauet, S., Etien, E., Sakout, A., & Rambault, L. (2018, October). Gearbox condition monitoring in wind turbines: A review. Mechanical Systems and Signal Processing, 111, 251–264. doi:
Hendriks, J., Dumond, P., & Knox, D. (2022, April). Towards better benchmarking using the CWRU bearing fault dataset. Mechanical Systems and Signal Processing, 169, 108732. doi: 10.1016/j.ymssp.2021.108732 Kim, Y., Na, K., & Youn, B. D. (2022, March). A health-adaptive time-scale representation (htsr) embedded convolutional neural network for gearbox fault diagnostics. Mechanical Systems and Signal Processing, 167, 108575. doi: 10.1016/j.ymssp.2021.108575 Lee, J., Wu, F., Zhao, W., Ghaffari, M., Liao, L., & Siegel, D. (2014, January). Prognostics and health management design for rotary machinery systemsreviews, methodology and applications. Mechanical Systems and Signal Processing, 42, 314–334. doi:
10.1016/j.ymssp.2018.03.052
Schlegl, T., Seeb¨ock, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G. (2017). Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In M. Niethammer et al. (Eds.), Information processing in medical imaging (pp. 146–157). Cham: Springer International Publishing.
Shi, J., Peng, D., Peng, Z., Zhang, Z., Goebel, K., & Wu,10.1016/j.ymssp.2013.06.004
Liu, C., & Gryllias, K. (2020, January). A semi-supervised support vector data description-based fault detection method for rolling element bearings based on cyclic spectral analysis. Mechanical Systems and Signal Processing, 140. doi: 10.1016/j.ymssp.2020.106682 Mao, W., Feng, W., Liu, Y., Zhang, D., & Liang, X. (2021, March). A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis. Mechanical Systems and Signal Processing, 150, 107233. doi: 10.1016/j.ymssp.2020.107233 ¨Ozt¨urk, H., Sabuncu, M., & Yesilyurt, I. (2008, April). Early Detection of Pitting Damage in Gears using Mean Frequency of Scalogram. Journal of Vibration and Control, 14(4), 469–484. doi:10.1177/1077546307080026
D. (2022, January). Planetary gearbox fault diagnosis using bidirectional-convolutional lstm networks. Mechanical Systems and Signal Processing, 162, 107996. doi: 10.1016/j.ymssp.2021.107996 Teng, W., Wang, F., Zhang, K., Liu, Y., & Ding, X. (2014, January). Pitting Fault Detection of a Wind Turbine Gearbox Using Empirical Mode Decomposition. Strojniˇski vestnik – Journal of Mechanical Engineering, 60(1), 12–20. doi: 10.5545/sv-jme.2013.1295 Van Maele, D., Poletto, J. C., Neis, P. D., Ferreira, N. F., Fauconnier, D., & De Baets, P. (2023). Online visionassisted condition monitoring of gearboxes. In 8th european conference and exhibition on lubrication, maintenance and tribotechnology (lubmat 2023), proceedings. Wang, J., Li, S., Han, B., An, Z., Bao, H., & Ji, S. (2019). Generalization of Deep Neural Networks for Imbalanced Fault Classification of Machinery Using Generative Adversarial Networks. IEEE Access, 7, 111168111180. doi: 10.1109/ACCESS.2019.2924003 Xiang, L., Yang, X., Hu, A., Su, H., & Wang, P. (2022, January). Condition monitoring and anomaly detection of wind turbine based on cascaded and bidirectional deep learning networks. Applied Energy, 305, 117925. doi:
Peng, D., Liu, C., Desmet, W., & Gryllias, K. (2023, July). Condition monitoring of wind turbines based on anomaly detection using deep support vector data description. Journal of Engineering for Gas Turbines and Power, 145(091009). doi: 10.1115/1.4062768 Qin, Y., Wang, Z., & Xi, D. (2022, January). Tree cyclegan with maximum diversity loss for image augmentation and its application into gear pitting detection. Applied Soft Computing, 114, 108130. doi:10.1016/j.apenergy.2021.117925 10.1016/j.asoc.2021.108130
Ren, L., Sun, Y., Cui, J., & Zhang, L. (2018, July). Bearing remaining useful life prediction based on deep autoencoder and deep neural networks. Journal of Manufacturing Systems, 48, 71–77. doi:
Zhang, Y., Liu, W., Wang, X., & Gu, H. (2022, July). A novel wind turbine fault diagnosis method based on compressed sensing and dtl-cnn. Renewable Energy, 194, 249–258. doi: 10.1016/j.renene.2022.05.085 Zhou, C., & Paffenroth, R. C. (2017, August). Anomaly detection with robust deep autoencoders. In Proceedings of the 23rd acm sigkdd international conference on knowledge discovery and data mining (pp. 665–674). Halifax NS Canada: ACM. doi:
10.1145/3097983.3098052
10.1016/j.jmsy.2018.04.008
Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S. A., Binder, A., . . . Kloft, M. (2018, July). Deep one-class classification. In Proceedings of the 35th international conference on machine learning (pp.
Zhou, K., Diehl, E., & Tang, J. (2023, February). Deep convolutional generative adversarial network with semisupervised learning enabled physics elucidation for extended gear fault diagnosis under data limitations. Mechanical Systems and Signal Processing, 185, 109772. doi: 10.1016/j.ymssp.2022.109772
Zhu, R., Mousmoulis, G., & Gryllias, K. (2023, July). Wavelet-based high order spectrum for local damage diagnosis of gears under different operating conditions. In Surveillance, Vibrations, Shock and Noise. Toulouse, France: Institut Sup´erieur de l’A´eronautique et de l’Espace [ISAE-SUPAERO].
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.