LITHIUM BATTERY SURFACE DEFECT DETECTION BASED ON REINFORCEMENT ADVERSARIAL LEARNING

De Chen, Wenbo Qiu, Zhiwen Zeng, Xuexian Li, Qingdong Yan, Qin Zou

References

  1. [1] Y. Guo, S. Wu, Y.B. He, F. Kang, L. Chen, H. Li, andQ.H. Yang, Solid-state lithium batteries: Safety and prospects,EScience, 2(2), 2022, 138–163.
  2. [2] X. Lai, J. Yao, C. Jin, X. Feng, H. Wang, C. Xu, and Y.Zheng, A review of lithium-ion battery failure hazards: teststandards, accident analysis, and safety suggestions, Batteries,8(11), 2022, 248.
  3. [3] Y. Zhang, MAFD-Net: Multi-scale attention fusion for real-timedefect detection in automated manufacturing, InternationalJournal of Robotics and Automation, 42(1), 2024, 45–62.
  4. [4] L. Chen and J. Park, TopoGAN: Topology-preservingadversarial learning for robust organ segmentation in roboticsurgery, International Journal of Robotics and Automation,43(3), 2025, 211–228.
  5. [5] R. Gupta, AdvNeRF-Road: Adversarial neural radiance fieldsfor robust road scene simulation, International Journal ofRobotics and Automation, 41(8), 2023, 901–918.
  6. [6] Y. Li, AgriSegFormer: 3.2MB vision transformer for real-time crop segmentation on edge devices, InternationalJournal of Robotics and Automation, 42(4), 2024,331–349.
  7. [7] C.F.R. Chen, Q. Fan, and R. Panda, Crossvit: Cross-attentionmulti-scale vision transformer for image classification, inProceedings of the IEEE/CVF International Conference onComputer Vision, 2021, 357–366.
  8. [8] G. James, D. Witten, T. Hastie, R. Tibshirani, and J.Taylor, Unsupervised learning, in An Introduction to StatisticalLearning: With Applications in Python (Cham: SpringerInternational Publishing, 2023), 503–556.
  9. [9] M. Zheng, S. You, L. Huang, F. Wang, C. Qian, andC. Xu, Simmatch: Semi-supervised learning with similar-ity matching, in Proceedings of the IEEE/CVF Confer-ence on Computer Vision and Pattern Recognition, 2022,14471–14481.
  10. [10] H. Qi, H. Zhou, J. Dong, and X Dong, Small sample imagesegmentation by coupling convolutions and transformers, IEEETransactions on Circuits and Systems for Video Technology,34(7), 2024, 5282–5294.
  11. [11] H. Jeong, C. Yoon, H. Lim, J. Chang, S. Misra, and C.Kim, MT-Former: Multi-task hybrid transformer and deepsupport vector data description to detect novel anomalies duringsemiconductor manufacturing, Light: Advanced Manufacturing,6(32), 2025, 1–13.
  12. [12] Y. Ke and Y. Fu, Transformer-based instance segmenta-tion network for multi-source images of composite mate-rials, Acta Materiae Compositae Sinica, 42(3), 2025,1124–1135.
  13. [13] X. Xia, X. Pan, N. Li, X. He, L. Ma, X. Zhang, and N. Ding,GAN-based anomaly detection: A review, Neurocomputing,493, 2022, 497–535.
  14. [14] M. Arjovsky, S. Chintala, and L. Bottou, Wassersteingenerative adversarial networks, in Proceedings ofInternational Conference on Machine Learning, 2017,214–223.
  15. [15] Y. Gong, X. Yu, Y. Ding, X. Peng, J. Zhao, and Z. Han, Effectivefusion factor in FPN for tiny object detection, in Proceedingsof the IEEE/CVF Winter Conference on Applications ofComputer Vision, 2021, 1160–1168.
  16. [16] N. Le, V.S. Rathour, K. Yamazaki, K. Luu, and M.Savvides, Deep reinforcement learning in computer vision: Acomprehensive survey, Artificial Intelligence Review, 55, 2022,1–87.
  17. [17] J. Schulman, S. Levine, P. Abbeel, M. Jordan, and P.Moritz, Trust region policy optimization, in Proceedingsof International Conference on Machine Learning, 2015,1889–1897.
  18. [18] A. Creswell, T. White, V. Dumoulin, K. Arulkumaran, B.Sengupta, and A. A. Bharath, Generative adversarial networks:An overview, IEEE Signal Processing Magazine, 35(1),2018,53–65.
  19. [19] L.P. Kaelbling, M.L. Littman, and A.W. Moore, Reinforcementlearning: A survey, Journal of Artificial Intelligence Research,4, 1996, 237–285.
  20. [20] M. Tan, R. Pang, and Q.V. Le, EfficientDet: Scalable andefficient object detection, 2019, arXiv:1911.09070.
  21. [21] J. Balzategui, L. Eciolaza, and D. Maestro-Watson, Anomalydetection and automatic labeling for solar cell quality inspectionbased on generative adversarial network, Sensors, 21(13), 2021,4361.
  22. [22] T. Niu, B. Li, W. Li, Y. Qiu, and S. Niu, Positive-sample-basedsurface defect detection using memory-augmented adversarialautoencoders, IEEE/ASME Transactions on Mechatronics,27(1), 2021, 46–57.
  23. [23] M. Rudolph, T. Wehrbein, B. Rosenhahn, and B. Wandt,Fully convolutional cross-scale-flows for image-based defectdetection, in Proceedings of the IEEE/CVF Winter Conferenceon Applications of Computer Vision, 2022, 1088–1097.
  24. [24] B. Liu, T. Zhang, Y. Yu, and L. Miao, A data generationmethod with dual discriminators and regularization for surfacedefect detection under limited data, Computers in Industry,151, 2023, 103963.
  25. [25] F. Zhou, Y. Chao, C. Wang, X. Zhang, H. Li, and X. Song,A small sample nonstandard gear surface defect detectionmethod, Measurement, 221, 2023, 113472.
  26. [26] B. Gao, H. Zhao, and X. Miao, A novel multi-model cascadeframework for pipeline defects detection based on machinevision, Measurement, 220, 2023, 113374.

Important Links:

Go Back