Research on Surface Defect Detection Algorithm of Lithium Battery Based on Multi-Modal Deep Learning

DOI: https://doi.org/10.62517/jes.202602105

Author(s)

Yuze Yang

Affiliation(s)

Jinan Jinqiu International School, Jinan, Shandong, China

Abstract

With the rapid advancement of new energy technologies, lithium-ion batteries as core energy storage components have been widely adopted in electric vehicles, portable devices, and energy storage systems, becoming a vital component of modern energy solutions. However, surface defects in lithium-ion batteries significantly compromise their performance, lifespan, and safety-particularly under high-energy-density conditions and frequent usage scenarios where these defects may trigger short circuits, overheating, or even explosions. Current traditional detection methods for lithium-ion battery surface defects primarily rely on manual inspection or conventional computer vision technologies. These approaches demonstrate notable limitations in precision and efficiency, especially when handling various defect types and performing complex defect detection in intricate scenarios. To address the challenges in surface defect detection of lithium batteries, this study proposes an intelligent detection algorithm based on multimodal deep learning. We have designed and implemented an innovative model framework that combines image processing with text analysis to comprehensively improve the accuracy and robustness of defect detection. This method utilizes deep learning models to extract visual features of surface defects and incorporates defect-related textual descriptions as auxiliary information, significantly enhancing the precision in identifying and localizing various types of defects. Experimental results show that the proposed detection algorithm achieves an accuracy of 95.6%, representing a significant performance improvement over existing methods, especially demonstrating strong adaptability and generalization capability in complex scenarios. This research not only provides an efficient and precise technical solution for defect detection in lithium battery production but also offers important theoretical and methodological support for other industrial defect detection tasks.

Keywords

Multimodal; Surface Defect Detection; Lithium Battery; Deep Learning

References

[1] Honghong Deng. Research on Surface Defect Detection of Lithium Batteries [D]. Harbin Institute of Technology, 2018. [2] Hanwen Yu and Yiquan Wu . Research Progress on Machine Vision-Based Defect Detection of Lithium Batteries [J]. Journal of Instrumentation, 2024,45(9):1-23. [3] Xueyong Feng. A Deep Learning-Based Method for Surface Defect Recognition and Classification of cylindrical Lithium Battery Steel Shells [D]. Hefei University of Technology, 2020. [4] Liu X, Wu L, Guo X, Liu X, Wu L, Guo X, et al. A novel approach for surface defect detection of lithium battery based on improved K-nearest neighbor and Euclidean clustering segmentation[J]. The International Journal of Advanced Manufacturing Technology, 2023, 127(1): 971-985. [5] Xu C, Li L, Li J, Xu C, Li L, Li J, et al. Surface defects detection and identification of lithium battery pole piece based on multi-feature fusion and PSO-SVM[J]. Ieee Access, 2021, 9: 85232-85239. [6] Chen X, Liu M, Niu Y, Chen X, Liu M, Niu Y, et al. Deep-learning-based lithium battery defect detection via cross-domain generalization[J]. IEEE Access, 2024. [7] Chen W, Han X, Pan Y, et al. Defects in lithium-ion batteries: From origins to safety risks[J]. Green Energy and Intelligent Transportation, 2025, 4(3): 100235. [8] Huang P, Wang C, Yang S, et al. Review of Research on Battery Defect Detection and Recovery[C]//International Workshop of Advanced Manufacturing and Automation. Singapore: Springer Nature Singapore, 2024: 148-155. [9] Jia Z, Wang M, Zhao S. A review of deep learning-based approaches for defect detection in smart manufacturing[J]. Journal of Optics, 2024, 53(2): 1345-1351. [10] Jiahui Chen, Fei Wang, et al. Research progress on nondestructive testing technology of lithium battery safety performance[J]. Nondestructive Testing, 44(12): 72-75. [11] Tang B, Chen L, Sun W, et al. Review of surface defect detection of steel products based on machine vision[J]. IET Image Processing, 2023, 17(2): 303-322. [12] Chen Y, Shu Y, Li X, et al. Research on detection algorithm of lithium battery surface defects based on embedded machine vision[J]. Journal of Intelligent & Fuzzy Systems, 2021, 41(3): 4327-4335. [13] Rahmati M, Rahmati N. A multimodal deep learning framework for real-time defect recognition in industrial components using visual, acoustic and vibration signals[J]. Journal of Intelligent Man ufacturing and Special Equipment, 2025: 1-20. [14] Cheng D, Wang S, Li C, et al. BatteryGPT: Battery Anomaly Detection Based on Multimodal Large Language Model[C]//2024 5th International Conference on Power Engineering (ICPE). IEEE, 2024: 516-521. [15] Jeong J, Zou Y, Kim T, et al. Winclip: Zero-/few-shot anomaly classification and segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 19606-19616. [16] Ning Y, Yang F, Zhang Y, et al. Bridging multimodal data and battery science with machine learning[J]. Matter, 2024, 7(6): 2011-2032. [17] Jia L, Chen C, Xu S, et al. Fabric defect inspection based on lattice segmentation and template statistics[J]. Information Sciences, 2020, 512: 964-984. [18] Kumari R, Bandara G, Dissanayake M B. Sylvester Matrix‐Based Similarity Estimation Method for Automation of Defect Detection in Textile Fabrics[J]. Journal of Sensors, 2021, 2021(1): 6625421. [19] Qiu Y, Tang L, Li B, et al. Uneven illumination surface defects inspection based on saliency detection and intrinsic image decomposition[J]. IEEE Access, 2020, 8: 190663-190676. [20] Zhang A, Wang K C P, Li B, et al. Automated pixel‐level pavement crack detection on 3D asphalt surfaces using a deep‐learning network[J]. Computer‐Aided Civil and Infrastructure Engineering, 2017, 32(10): 805-819. [21] Yu Z, Wu X, Gu X. Fully convolutional networks for surface defect inspection in industrial environment[C]//Computer Vision Systems: 11th International Conference, ICVS 2017, Shenzhen, China, July 10-13, 2017, Revised Selected Papers 11. Springer International Publishing, 2017: 417-426. [22] Song G, Song K, Yan Y. Saliency detection for strip steel surface defects using multiple constraints and improved texture features[J]. Optics and Lasers in Engineering, 2020, 128: 106000. [23] Zhou P, Zhou G, Li Y, et al. A hybrid data-driven method for wire rope surface defect detection[J]. IEEE Sensors Journal, 2020, 20(15): 8297-8306. [24] Singh S A, Desai K A. Automated surface defect detection framework using machine vision and convolutional neural networks[J]. Journal of Intelligent Manufacturing, 2023, 34(4): 1995-2011. [25] Gui S, Song S, Qin R, et al. Remote sensing object detection in the deep learning era-a review[J]. Remote Sensing, 2024, 16(2): 327. [26] Manakitsa N, Maraslidis G S, Moysis L, et al. A review of machine learning and deep learning for object detection, semantic segmentation, and human action recognition in machine and robotic vision[J]. Technologies, 2024, 12(2): 15. [27] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587. [28] Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448. [29] Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28. [30] He K, Gkioxari G, Dollár P, et al. Mask r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2961-2969. [31] Lu L, Hou J, Yuan S, et al. Deep learning-assisted real-time defect detection and closed-loop adjustment for additive manufacturing of continuous fiber-reinforced polymer composites[J]. Robotics and Computer-Integrated Manufacturing, 2023, 79: 102431. [32] Zhang Y, Zhang Z, Fu K, et al. Adaptive defect detection for 3-D printed lattice structures based on improved faster R-CNN[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-9. [33] Xia B, Luo H, Shi S. Improved Faster R‐CNN Based Surface Defect Detection Algorithm for Plates[J]. Computational intelligence and neuroscience, 2022, 2022(1): 3248722. [34] Xu Y, Li D, Xie Q, et al. Automatic defect detection and segmentation of tunnel surface using modified Mask R-CNN[J]. Measurement, 2021, 178: 109316. [35] Wang H, Li M, Wan Z. Rail surface defect detection based on improved Mask R-CNN[J]. Computers and Electrical Engineering, 2022, 102: 108269. [36] Ali M L, Zhang Z. The YOLO framework: A comprehensive review of evolution, applications, and benchmarks in object detection[J]. Computers, 2024, 13(12): 336. [37] Yuan M, Zhou Y, Ren X, et al. YOLO-HMC: An improved method for PCB surface defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 1-11. [38] Zhang Z, Zhang Y, Wen Y, et al. Intelligent defect detection method for additive manufactured lattice structures based on a modified YOLOv3 model [J]. Journal of Nondestructive Evaluation, 2022, 41: 1-14. [39] Qian X, Wang X, Yang S, et al. LFF-YOLO: A YOLO algorithm with lightweight feature fusion network for multi-scale defect detection [J]. IEEE Access, 2022, 10: 130339-130349. [40] Wen Y, Cheng J, Ren Y, et al. Complex defects detection of 3-D-Printed lattice structures: Accuracy and scale improvement in YOLO V7[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 1-9. [41] Jiang L, Yuan B, Wang Y, et al. MA-YOLO: a method for detecting surface defects of aluminum profiles with attention guidance[J]. IEEE Access, 2023, 11: 71269-71286. [42] Lei H, Wang B, Wu H, et al. Defect Detection for Polymeric Polarizer Based on Faster R-CNN[J]. J. Inf. Hiding Multim. Signal Process., 2018, 9(6): 1414-1420. [43] Badmos O, Kopp A, BernthalerT, et al. Image-based defect detection in lithium-ion battery electrode using convolutional neural networks[J]. Journal of Intelligent Manufacturing, 2020, 31: 885-897. [44] Damacharla P, Rao A, Ringenberg J, et al. TLU-net: a deep learning approach for automatic steel surface defect detection[C]//2021 International Conference on Applied Artificial Intelligence (ICAPAI). IEEE, 2021: 1-6. [45] Chazhoor A A P, Hu S, Gao B, et al. MDC-Net: Multimodal Detection and Captioning Network for Steel Surface Defects[C]//International Conference on Robotics, Computer Vision and Intelligent Systems. Cham: Springer Nature Switzerland, 2024: 316-333. [46]Wang R, Du W, Jiang Q. Quantitative estimation method for complex part surface defects based on multimodal information fusion[J]. Complex & Intelligent Systems, 2025, 11(6): 1-27. [47] Zhao Z, Hu B, Feng Y, et al. Multi-surface defect detection for universal joint bearings via multimodal feature and deep transfer learning[J]. International Journal of Production Research, 2023, 61(13): 4402-4418. [48] Wang H, Peng R, Zhu Y, et al. Few-Shot Photovoltaic Film Defect Detection With Contextual Ensemble Language-Image Multimodal Network[J]. IEEE Transactions on Industrial Informatics, 2025. [49] Lu H, Zhu Y, Yin M, et al. Multimodal fusion convolutional neural network with cross-attention mechanism for internal defect detection of magnetic tile[J]. IEEE Access, 2024, 10: 60876-60886. [50] Asad M, Azeem W, Jiang H, et al. 2M3DF: Advancing 3D Industrial Defect Detection with Multi Perspective Multimodal Fusion Network[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025. [51] Cheng D, Wang S, Li C, et al. BatteryGPT: Battery Anomaly Detection Based on Multimodal Large Language Model[C]//2024 5th International Conference on Power Engineering (ICPE). IEEE, 2024: 516-521. [52] Feng B, Xia X, Zhang L, et al. An image-text multimodal fusion of deep learning for detecting insulator defects[J]. International Journal of Parallel, Emergent and Distributed Systems, 2025: 1-17. [53] Zhai J, Sun Z, Huyan J, et al. Automatic pavement crack detection using multimodal features fusion deep neural network[J]. International Journal of Pavement Engineering, 2023, 24(2): 2086692.