IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Design and Implementation of a Lightweight On-Device AI-Based Real-time Fault Diagnosis System using Continual Learning

연속학습을 활용한 경량 온-디바이스 AI 기반 실시간 기계 결함 진단 시스템 설계 및 구현

  • Youngjun Kim (University of Seoul ) ;
  • Taewan Kim (University of Seoul ) ;
  • Suhyun Kim (University of Seoul) ;
  • Seongjae Lee (University of Seoul ) ;
  • Taehyoun Kim (University of Seoul )
  • 김영준 ;
  • 김태완 ;
  • 김수현 ;
  • 이성재 ;
  • 김태현
  • Received : 2024.01.26
  • Accepted : 2024.04.13
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

Keywords

Acknowledgement

이 논문은 정부 (과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임 (No. 2022R1F1A1060231).

References

  1. P. Zhang, Y. Du, T. G. Habetler, B. Lu, "A Survey of Condition Monitoring and Protection Methods for Medium-voltage Induction Motors," IEEE Transactions on Industry Applications, Vol. 47, No. 1, pp. 34-46, 2010. 
  2. J. P. Yun, M. S. Kim, G. Koo, C. Sin, "Fault Diagnosis and Analysis Based on Transfer Learning and Vibration Signals," IEMEK J. Embed. Sys. Appl., Vol. 14, No. 6, pp. 287-294, 2019 (in Korean). 
  3. C. Y. Lee, G. L. Zhuo, T. A. Le, "A Robust Deep Neural Network for Rolling Element Fault Diagnosis Under Various Operating and Noisy Conditions," Sensors, Vol. 22, No. 13, pp. 4705, 2022. 
  4. D. T. Hoang, H. J. Kang, "A Survey on Deep Learning Based Bearing Fault Diagnosis," Neurocomputing, Vol. 335, pp. 327-335, 2019. 
  5. W. Zhang, G. Peng, C. Li, Y. Chen, Z. Zhang, "A New Deep Learning Model for Fault Diagnosis with Good Anti-noise and Domain Adaptation Ability on Raw Vibration Signals," Sensors, Vol. 17, No. 2, pp. 425, 2017. 
  6. W. Zhang, C. Li, G. Peng, Y. Chen, Z. Zhang, "A Deep Convolutional Neural Network with New Training Methods for Bearing Fault Diagnosis Under Noisy Environment and Different Working Load," Mechanical Systems and Signal Processing, Vol. 100, pp. 439-453, 2018. 
  7. S. Dhar, J. Guo, J. Liu, S. Tripathi, U. Kurup, M. Shah, "A Survey of On-device Machine Learning: An Algorithms and Learning Theory Perspective," ACM Transactions on Internet of Things, Vol. 2, No. 3, pp. 1-49, 2021. 
  8. H. Hua, Y. Li, T. Wang, N. Dong, W. Li, J. Cao, "Edge Computing with Artificial Intelligence: A Machine Learning Perspective," ACM Computing Surveys, Vol. 55, No. 9, pp. 1-35, 2023. 
  9. S. Lu, J. Lu, K. An, X. Wang, Q. He, "Edge Computing on IoT for Machine Signal Processing and Fault Diagnosis: A Review," IEEE Internet of Things Journal, Vol. 10, No. 13, pp. 11093-11116, 2023. 
  10. L. Fu, K. Yan, Y. Zhang, R. Chen, Z. Ma, F. Xu, T. Zhu, "EdgeCog: A Real-time Bearing Fault Diagnosis System Based on Lightweight Edge Computing," IEEE Transactions on Instrumentation and Measurement, Vol. 72, pp.1-11, 2023. 
  11. S. Afrasiabi, M. Afrasiabi, B. Parang, M. Mohammadi, "Real-Time Bearing Fault Diagnosis of Induction Motors with Accelerated Deep Learning Approach," 2019 10th International Power Electronics, Drive Systems and Technologies Conference (PEDSTC), pp. 155-159, 2019. 
  12. B. Chen, C. Shen, J. Shi, L. Kong, L. Tan, D. Wang, Z. Zhu, "Continual Learning Fault Diagnosis: A Dual-branch Aaptive Aggregation Residual Network for Fault Diagnosis with Machine Increments," Chinese Journal of Aeronautics, Vol. 36, No. 6, pp. 361-377, 2023. 
  13. C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, C. Liu, "A Survey on Deep Transfer Learning," ICANN 2018: 27th International Conference on Artificial Neural Networks, pp. 270-279, 2018. 
  14. Y. Bengio, "Deep Learning of Representations for Unsupervised and Transfer Learning," Proceedings of ICML Workshop on Unsupervised and Transfer Learning, PMLR, Vol. 27, pp. 17-36, 2012. 
  15. J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A.A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska, D. Hassabis, C. Clopath, D. Kumaran, R. Hadsell, "Overcoming Catastrophic Forgetting in Neural Networks," Proceedings of the National Academy of Sciences, Vol. 114, No. 13, pp. 3521-3526, 2017. 
  16. R. Kemker, M. McClure, A. Abitino, T. Hayes, C. Kanan, "Measuring Catastrophic Forgetting in Neural Networks," Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, No. 1, pp. 3390-3398 2018. 
  17. J. Chuya-Sumba, L. M. Alonso-Valerdi, D. I. Ibarra-Zarate, "Deep-learning Method Based on 1D Convolutional Neural Network for Intelligent Fault Diagnosis of Rotating Machines," Applied Sciences, Vol. 12, No. 4, pp. 2158, 2022. 
  18. X. Liu, Q. Zhou, H. Shen. "Real-Time Fault Diagnosis of Rotating Machinery Using 1-D Convolutional Neural Network," 2018 5th International Conference on Soft Computing & Machine Intelligence (ISCMI), pp.104-108, 2018. 
  19. L. Hou, L. Liu, G. Mao, "Machine Fault Diagnosis Method Using Lightweight 1-D Separable Convolution and WSNs with Sensor Computing," IEEE Transactions on Instrumentation and Measurement, Vol. 71, pp. 1-8, 2022. 
  20. O. Gultekin, E. Cinar, K. Ozkan, A. Yazici, "Real-Time Fault Detection and Condition Monitoring for Industrial Autonomous Transfer Vehicles Utilizing Edge Artificial Intelligence," Sensors, Vol. 22, No. 9, p. 3208, 2022. 
  21. G. Qian, S. Lu, D. Pan, H. Tang, Y. Liu, Q. Wang, "Edge Computing: A Promising Framework for Real-time Fault Diagnosis and Dynamic Control of Rotating Machines Using Multi-sensor Data," IEEE Sensors Journal, Vol. 19, No. 11, pp. 4211-4220, 2019. 
  22. X. Ding, H. Wang, Z. Cao, X. Liu, Y. Liu, Z. Huang, "An Edge Intelligent Method for Bearing Fault Diagnosis Based on a Parameter Transplantation Convolutional Neural Network," Electronics, Vol. 12, No. 8, pp. 1816, 2023. 
  23. G. M. van de Ven, T. Tuytelaars, A. S. Tolias, "Three Types of Incremental Learning," Nature Machine Intelligence, Vol. 4, No. 12, pp. 1185-1197, 2022. 
  24. D. Rolnick, A. Ahuja, J. Schwarz, T. Lillicrap, G. Wayne, "Experience Replay for Continual Learning," Advances in Neural Information Processing Systems, Vol. 32, pp. 1-11, 2019. 
  25. D. Lopez-Paz, M.A. Ranzato, "Gradient Episodic Memory for Continual Learning," Advances in Neural Information Processing Systems, Vol. 30, pp.1-10, 2017. 
  26. A. Chaudhry, M.A. Ranzato, M. Rohrbach, M. Elhoseiny, "Efficient Lifelong Learning with A-GEM," arXiv:1812.00420, 2019. 
  27. N. Vodisch, K. Petek, W. Burgard, A. Valada, "CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation," arXiv:2303.10147, 2023. 
  28. Z. Li, D. Hoiem, "Learning Without Forgetting," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 40, No. 12, pp. 2935-2947, 2017. 
  29. B. Maschler, H. Vietz, N. Jazdi, M. Weyrich, "Continual Learning of Fault Prediction for Turbofan Engines Using Deep Learning with Elastic Weight Consolidation," 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vol. 1, pp. 959-966, 2020. 
  30. https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/ 
  31. https://grafana.com/ 
  32. https://engineering.case.edu/bearingdatacenter/ 
  33. https://www.mfpt.org/fault-data-sets/ 
  34. H. Huang, N. Baddour, "Bearing Vibration Data Collected Under Time-varying Rotational Speed Conditions," Data in Brief, Vol. 21, pp. 1745-1749, 2018. 
  35. R. B. Randall, J. Antoni, "Rolling Element Bearing Diagnostics-A Tutorial," Mechanical Systems and Signal Processing, Vol. 25, No. 2, pp. 485-520, 2011.