Defect detection in battery electrode production using supervised and unsupervised learning with laser speckle photometry data

• Autorzy: Klarák Jaromír , Chen Lili , Cikalova Ulana , Malík Peter , Andok Robert , Bendjus Beatrice

Identyfikatory

DOI

10.12913/22998624/200823

• Języki publikacji: EN

Abstrakty

EN

The direction for zero-emission transport is largely driven by the adoption of battery-powered vehicles. A critical aspect of a successful battery storage system is the production of high-quality electrodes, which necessitates rigorous inspection processes and defect detection systems. In this paper, we present data obtained using Laser Speckle Photometry (LSP) technology and perform defect detection using two approaches: the YOLOv4 model and the newly developed U2S-CNNv2 model. The U2S-CNNv2 model combines unsupervised and supervised learning to identify defects beyond the training dataset. Our goal is to develop an efficient detection of defects for battery electrode production to meet stringent quality control standards. Our findings show that YOLOv4 is highly effective for deployment in inspection processes, capturing very small defects and operating at 50 frames per second (fps). YOLOv4 achieved an impressive 93.82% accuracy in correctly detecting and 91.10% in correctly labeling defects. Conversely, the U2S-CNNv2 model excels in precisely localizing defect areas and identifying unknown defects or patterns not included in the training dataset. However, it operates at a slower pace of around 3 fps and has a detection accuracy of 83.83% and correct labeling rate of 54.84%.

Słowa kluczowe

EN

defect detection; anomaly detection; battery; electrode; supervised learning; unsupervised learning; deep learning

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2025
• Tom: Vol. 19, no. 4
• Strony: 258--269
• Opis fizyczny: Bibliogr. 27 poz., fig., tab.

Twórcy

autor

Klarák Jaromír

• Institute of Informatics, Slovak Academy of Sciences, 845 07 Bratislava, Slovakia

• https://orcid.org/0000-0002-7154-6313

autor

Chen Lili

• Fraunhofer Institute for Ceramic Technologies and Systems IKTS, Maria-Reiche-Strasse 2, 01109 Dresden, Germany

autor

Cikalova Ulana

• Fraunhofer Institute for Ceramic Technologies and Systems IKTS, Maria-Reiche-Strasse 2, 01109 Dresden, Germany

autor

Malík Peter

• Institute of Informatics, Slovak Academy of Sciences, 845 07 Bratislava, Slovakia

autor

Andok Robert

• Institute of Informatics, Slovak Academy of Sciences, 845 07 Bratislava, Slovakia

autor

Bendjus Beatrice

• Fraunhofer Institute for Ceramic Technologies and Systems IKTS, Maria-Reiche-Strasse 2, 01109 Dresden, Germany

Bibliografia

• 1. Etiemble A, Besnard N, Adrien J, Tran-Van P, Gautier L, Lestriez B, et al. Quality control tool of electrode coating for lithium-ion batteries based on X-ray radiography. J Power Sources. 2015;298:285–91. https://doi.org/10.1016/j.jpowsour.2015.08.030.
• 2. Roadmap Battery Production Equipment 2030 - Update 2023. [cited 2024 Jan 18]. Available from: https://www.researchgate.net/publication/370472366_Roadmap_Battery_Production_Equipment_2030_-_Update_2023.
• 3. Roadmap Batterie-Produktionsmittel 2030 - Update 2023. [cited 2024 Jan 18]. Available from: https://www.researchgate.net/publication/370472223_Roadmap_Batterie-Produktionsmittel_2030_-_Update_2023.
• 4. Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2014;580–7. https://doi.org/10.1109/CVPR.2014.81.
• 5. Girshick R. Fast R-CNN. 2015 [cited 2022 Dec 7]. p. 1440–8. Available from: https://github.com/rb-girshick/, https://doi.org/10.1109/ICCV.2015.169.
• 6. Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell. 2017;39:1137–49. https://doi.org/10.1109/TPAMI.2016.2577031.
• 7. Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2016;2016-December:779–88. https://doi.org/10.1109/CVPR.2016.91.
• 8. Li J, Su Z, Geng J, Yin Y. Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network. IFAC-PapersOnLine. 2018;51:76–81. https://doi.org/10.1016/j.ifacol.2018.09.412.
• 9. Yu L, Wang Z, Duan Z. Detecting Gear Surface Defects Using Background-Weakening Method and Convolutional Neural Network. J Sensors. 2019;2019. https://doi.org/10.1155/2019/3140980.
• 10. Zhang W, Zhang N, Yang W, et al., Song L, Wang Y, et al. LF-YOLOv4: a lightweight detection model for enhancing the fusion of image features of surface defects in lithium batteries. Meas Sci Technol. 2023 [cited 2024 Jan 17];35:025005. Available from: https://iopscience.iop.org/article/10.1088/1361-6501/ad0690.
• 11. Choudhary N, Clever H, Ludwigs R, Rath M, Gannouni A, Schmetz A, et al. Autonomous Visual Detection of Defects from Battery Electrode Manufacturing. Adv Intell Syst. 2022 [cited 2024 Jan 17];4:2200142. Available from: https://onlinelibrary.wiley.com/doi/full/10.1002/aisy.202200142.
• 12. Tzelepakis A, Leontaris L, Dimitriou N, Koukidou E, Bollas D, Karamanidis A, et al. Automated defect detection in battery line assembly via deep learning analysis. 2023 [cited 2024 Jan 17];1196–208. Available from: www.eccomasproceedia.org.
• 13. Ma X, Tang Y, Lu Y, Liu S. Localization Algorithm of R Angle of the tab on Lithium Battery Coating Based on Faster RCNN. Proc - 2021 Int Conf Comput Inf Sci Artif Intell CISAI 2021. 2021;391–5. https://doi.org/10.1109/CISAI54367.2021.00081.
• 14. Tsai DM, Jen PH. Autoencoder-based anomaly detection for surface defect inspection. Adv Eng Informatics. 2021;48:101272. https://doi.org/10.1016/j.aei.2021.101272.
• 15. Kähler F, Schmedemann O, Schüppstuhl T. Anomaly detection for industrial surface inspection: application in maintenance of aircraft components. Procedia CIRP. 2022;107:246–51. https://doi.org/10.1016/j.procir.2022.05.197.
• 16. Niu T, Li B, Li W, Qiu Y, Niu S. Positive-Sample-Based Surface Defect Detection Using Memory-Augmented Adversarial Autoencoders. IEEE/ASME Trans Mechatronics. 2022;27:46–57. https://doi.org/10.1109/TMECH.2021.3058147.
• 17. Tao X, Zhang D, Ma W, Liu X, Xu D. Automatic metallic surface defect detection and recognition with convolutional neural networks. Appl Sci. 2018 [cited 2021 Mar 16];8:1575. Available from: http://www.mdpi.com/2076-3417/8/9/1575, https://doi.org/10.3390/app8091575.
• 18. Kuric I, Klarák J, Sága M, Císar M, Hajdučík A, Wiecek D. Analysis of the possibilities of tire-defect inspection based on unsupervised learning and deep learning. Sensors 2021, 21, 7073. [cited 2022 Jan 11];21:7073. Available from: https://www.mdpi.com/1424-8220/21/21/7073/htm, https://doi.org/10.3390/s21217073.
• 19. Klarák J, Andok R, Malík P, Kuric I, Ritomský M, Klačková I, et al. From Anomaly Detection to Defect Classification. Sensors 2024, 24, 429. [cited 2024 Feb 6];24:429. Available from: https://www.mdpi.com/1424-8220/24/2/429/htm, https://doi.org/10.3390/s24020429.
• 20. Tung PY, Sheikh HA, Ball M, Nabiei F, Harrison RJ. SIGMA: Spectral Interpretation Using Gaussian Mixtures and Autoencoder. Geochemistry, Geophysics Geosystems. 2023;24. https://doi.org/10.1029/2022GC010530.
• 21. GitHub - poyentung/sigma: Python code for phase identification and spectrum analysis of energy dispersive x-ray spectroscopy (EDS). [cited 2024 Jul 19]. Available from: https://github.com/poyentung/sigma?tab=readme-ov-file.
• 22. Chen L, Cikalova U, Münch S, Stüwe T, Dam V, Bendjus B. Artificial intelligence – A solution for inline characterization of li-ion batteries. [cited 2024 Jan 18]. Available from: https://www.ndt.net/?id=27662.
• 23. Kux F, Cikalova U, Chen L, Henschel J, Bendjus B. An Innovative Approach Using Laser Speckle Photometry for Efficient and Accurate Surface Defect Detection. 14th Ed Int Conf Adv Lithium Batter Automob Appl (ABAA-14), 2023.
• 24. Mohanty D, Hockaday E, Li J, Hensley DK, Daniel C, Wood DL. Effect of electrode manufacturing defects on electrochemical performance of lithium-ion batteries: Cognizance of the battery failure sources. J Power Sources. 2016;312:70–9. https://doi.org/10.1016/j.jpowsour.2016.02.007.
• 25. Ester M, Kriegel H-P, Sander J, Xu X. A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. 1996. Available from: www.aaai.org.
• 26. Chollet F. Xception: Deep Learning With Depthwise Separable Convolutions. 2017. p. 1251–8. https://doi.org/10.1109/CVPR.2017.195.
• 27. Clustering – scikit-learn 0.24.0 documentation. [cited 2021 Jan 14]. Available from: https://scikit-learn.org/stable/modules/clustering.html#dbscan.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).