Data Augmentation Using Generative Adversarial Network for Automatic Machine Fault Detection Based on Vibration Signals
Source abstract
Abstract
In the last decade, predictive maintenance has attracted a lot of attention in industrial factories because of its wide use of the Internet of Things and artificial intelligence algorithms for data management. However, in the early phases where the abnormal and faulty machines rarely appeared in factories, there were limited sets of machine fault samples. With limited fault samples, it is difficult to perform a training process for fault classification due to the imbalance of input data. Therefore, data augmentation was required to increase the accuracy of the learning model. However, there were limited methods to generate and evaluate the data applied for data analysis. In this paper, we introduce a method of using the generative adversarial network as the fault signal augmentation method to enrich the dataset. The enhanced data set could increase the accuracy of the machine fault detection model in the training process. We also performed fault detection using a variety of preprocessing approaches and classified the models to evaluate the similarities between the generated data and authentic data. The generated fault data has high similarity with the original data and it significantly improves the accuracy of the model. The accuracy of fault machine detection reaches 99.41% with 20% original fault machine data set and 93.1% with 0% original fault machine data set (only use generate data only). Based on this, we concluded that the generated data could be used to mix with original data and improve the model performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Machine Fault Diagnosis Techniques · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electronics Engineering, Kookmin University, Seoul 02707, Korea
Funding
Ministry of Trade, Industry and Energy · Korea Institute for Advancement of Technology
References (35)
Show source-provided references
1. Data-driven methods for predictive maintenance of industrial equipment: A survey10.1109/JSYST.2019.2905565 ↗
2. Onpkeep (2021, January 15). Predictive and Preventive Maintenance Statistics. Available online: https://www.onupkeep.com/learning/maintenance-metrics/maintenance-statistics.
3. Amruthnath, N., and Gupta, T. (2018, January 10–12). Fault class prediction in unsupervised learning using model-based clustering approach. Proceedings of the 2018 International Conference on Information and Computer Technologies (ICICT), Libertad City, Ecuador.10.1109/INFOCT.2018.8356831 ↗
4. Machine learning in predictive maintenance towards sustainable smart manufacturing in industry 4.010.3390/su12198211 ↗
5. Acoustic fault analysis of three commutator motors10.1016/j.ymssp.2019.07.007 ↗
6. A new dynamic predictive maintenance framework using deep learning for failure prognostics
7. A new intelligent fault identification method based on transfer locality pre-serving projection for actual diagnosis scenario of rotating machinery10.1016/j.ymssp.2019.106344 ↗
8. A new deep transfer learning based on sparse auto-encoder for fault diagnosis10.1109/TSMC.2017.2754287 ↗
9. Le Guennec, A., Malinowski, S., and Tavenard, R. (2016, January 18). Data Augmentation for time series classification using convolutional neural networks ECML. Proceedings of the PKDD Workshop on Advanced Analytics and Learning on Temporal Data, Riva Del Garda, Italy.
10. Iwana, B.K., and Uchida, S. (2020). Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher. arXiv.
11. Um, T.T., Pfister, F.M.J., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U., and Kulić, D. (2017, January 13–17). Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks. Proceedings of the 19th ACM International Conference on Multimodal Interaction, Glasgow, UK.10.1145/3136755.3136817 ↗
12. Rashid, K.M., and Louis, J. (2019, January 21–24). Time-warping: A time series data augmentation of IMU data for construction equipment activity identification. Proceedings of the 36th International Symposium on Automation and Robotics in Construction (ISARC), Banff, AB, Canada.10.22260/ISARC2019/0087 ↗
13. Ohashi, H., Al-Nasser, M., Ahmed, S., Akiyama, T., Sato, T., Nguyen, P., Nakamura, K., and Dengel, A. (2017, January 8). Augmenting wearable sensor data with physical constraint for DNN-based human-action recognition. Proceedings of the Time Series workshop at International Conference of Machine Learning (ICML), Long Beach, CA, USA.
14. Wang, J., and Perez, L. (2017). The Effectiveness of Data Augmentation in Image Classification using Deep Learning. arXiv.
15. A survey on image data augmentation for deep learning10.1186/s40537-019-0197-0 ↗
16. An overview of deep generative models10.1080/02564602.2014.987328 ↗
17. Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., and Weinberger, K.Q. (2014). Generative adversarial nets. Advances in Neural Information Processing Systems, Curran Associates, Inc.
18. Radford, A., Metz, L., and Chintala, S. (2016, January 2–4). Unsupervised representation learning with deep convolutional generative adversarial networks. Proceedings of the 4th International Conference on Learning Representations, ICLR 2016—Conference Track Proceedings, San Juan, PR, USA.
19. Goodfellow, I.J. (2017). NIPS 2016 Tutorial: Generative Adversarial Networks. arXiv.
20. Salimans, T., Goodfellow, I.J., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved Techniques for Training Gansar. arXiv.
21. (2021, January 15). Bearing Data Center. Available online: https://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing-data-center-website.
22. Openei (2021, January 15). Gearbox Fault Diagnosis Data. Available online: https://openei.org/datasets/dataset/gearbox-fault-diagnosis-data.
23. Shadow compensation for synthetic aperture radar target classification by dual parallel generative adversarial network
24. Unsupervised machine learning for networking: Techniques, applications and research challenges10.1109/ACCESS.2019.2916648 ↗
25. Goodfellow, I., Bengio, J., and Courville, A. (2016). Deep Learning, MIT Press.
26. Smola, A., and Vishwanathan, S.V.N. (2008). Introduction to Machine Learning, Cambridge University Press.
27. Mohri, M., Rostamizadeh, A., and Talwalkar, A. (2018). Foundations of Machine Learning, Cambridge University Press. [2nd ed.].
28. Christopher, M.B. (2006). Pattern Recognition and Machine Learning, Springer.
29. Das, U.K., Tey, K.S., Seyedmahmoudian, M., Idris, M.Y.I., Mekhilef, S., Horan, B., and Stojcevski, A. (2017). SVR-based model to forecast pv power generation under different weather conditions. Energies, 10.10.3390/en10070876 ↗
30. Yang, Y., Liang, K., Xiao, X., Xie, Z., Jin, L., Sun, J., and Zhou, W. (2018, January 5–8). Accelerating and compressing lstm based model for online handwritten chinese character recognition. Proceedings of the 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Niagara Falls, NY, USA.10.1109/ICFHR-2018.2018.00028 ↗
31. Machine learning for network automation: Overview, architecture, and applications
32. Van, B., Van Hoa, H., Nguyen, H., and Jang, Y.M. (2020, January 21–23). Statistical Feature Extraction in Machine Fault Detection using Vibration Signal. Proceedings of the 2020 International Conference on Information and Communication Technology Convergence (ICTC), Jeju, Korea.10.1109/ICTC49870.2020.9289285 ↗
33. Evolutionary generative adversarial networks10.1109/TEVC.2019.2895748 ↗
34. Small-sample corrections to kolmogorov–smirnov test statistic
35. Draper, N., and Smith, H. (1998). Applied Regression Analysis, Wiley. [3rd ed.].10.1002/9781118625590 ↗