Journal of Korean Society for Quality Management (품질경영학회지)

Korean Society for Quality Management (한국품질경영학회)
권호 표지
DOI QR코드

DOI QR Code

A Case Study on Quality Improvement of Electric Vehicle Hairpin Winding Motor Using Deep Learning AI Solution

딥러닝 AI 솔루션을 활용한 전기자동차 헤어핀 권선 모터의 용접 품질향상에 관한 사례연구

  • Lee, Seungzoon (Department of IT Policy and Management, Graduate School of Soongsil University) ;
  • Sim, Jinsup (Department of IT Policy and Management, Graduate School of Soongsil University) ;
  • Choi, Jeongil (College of Business Administration, Soongsil University)
  • 이승준 ( 숭실대학교 대학원 IT정책경영학과) ;
  • 심진섭 ( 숭실대학교 대학원 IT정책경영학과) ;
  • 최정일 (숭실대학교 경영학부)
  • Received : 2023.03.24
  • Accepted : 2023.04.07
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: The purpose of this study is to actually implement and verify whether welding defects can be detected in real time by utilizing deep learning AI solutions in the welding process of electric vehicle hairpin winding motors. Methods: AI's function and technological elements using synthetic neural network were applied to existing electric vehicle hairpin winding motor laser welding process by making special hardware for detecting electric vehicle hairpin motor laser welding defect. Results: As a result of the test applied to the welding process of the electric vehicle hairpin winding motor, it was confirmed that defects in the welding part were detected in real time. The accuracy of detection of welds was achieved at 0.99 based on mAP@95, and the accuracy of detection of defective parts was 1.18 based on FB-Score 1.5, which fell short of the target, so it will be supplemented by introducing additional lighting and camera settings and enhancement techniques in the future. Conclusion: This study is significant in that it improves the welding quality of hairpin winding motors of electric vehicles by applying domestic artificial intelligence solutions to laser welding operations of hairpin winding motors of electric vehicles. Defects of a manufacturing line can be corrected immediately through automatic welding inspection after laser welding of an electric vehicle hairpin winding motor, thus reducing waste throughput caused by welding failure in the final stage, reducing input costs and increasing product production.

Keywords

References

  1. Bocksrocker, O., Speker, N., Beranek, M., and Hesse, T. 2019. Reduction of Spatter and Pores in Laser Welding of Copper Hairpin Using Two Superimposed Laser Beams. Laser in Manufacturing Conference Munich 2019:1-8. Retrieved from https://www.wlt.de/lim/Proceedings2019/data/PDF/Contribution_370_final.pdf.
  2. Cho, Yongjoon, Rhee, Sehyun and Um, Kiwoan. 1998. A Study of Real-Time Weldability Estimation of Resistance Spot Welding Using Fuzzy Algorithm. Journal of Welding and Joining 16(5):76-85.
  3. Choi, Sehun, Han, Changmin, Kim, Taewon, and Choi, Haewoon. 2021. Assessment of Laser Joining Weld Quality by Visual Inspection, Computer Simulation, and Deep Learning. Applied Sciences 11(2):642-655. https://doi.org/10.3390/app11020642
  4. Coherent. 2019. Laser Technology for Electric Vehicles. Laser Solutions 22(2):8-11.
  5. Fleischer, J., Haag, S., and Hofmann, J. 2017. Quo Vadis Winding Technology? A Study on the State of The Art and Research on Future Trends in Automotive Engineering. Retrieved from https://www.wbk.kit.edu/downloads/2017_02_21_Studie_Wickeltechnik_final_EN.pdf.
  6. Glaessel, T., Seefried, J., and Franke, J. 2017. Challenges in the Manufacturing of Hairpin Windings and Application Opportunities of Infrared Lasers for the Contacting Process. 7th Int. Elect. Drives Prod. Conf(EDPC) 1-7.
  7. Holman, J. 2020. EVs to Make Up Third of New Cars Sold Globally by 2030: Deloitte. S&P Global Commodity Insights. July 28 2020. Retrieved from https://www.spglobal.com/commodityinsights/en/market-in-sights/latest-news/electric-power/072820-evs-to-make-up-third-of-newcars-sold-globally-by-2030-deloitte.
  8. Hwang, Dongsoo and Gho, Mihye. 2012. Development and Application of Realtime Weld Quality Monitoring System. Journal of Welding and Joining 30(1):44-50. https://doi.org/10.5781/KWJS.2012.30.1.44
  9. Jamie, H., Bryn, W., and Michael, W. 2022. Electric Vehicle Market Outlook. Deloitte Insight 7-8.
  10. Kang, Jihun and Ku, Namkug. 2019. Verification of Resistance Welding Quality Based on Deep Learning. Journal of the Society of Naval Architects of Korea 56(6):473-479. https://doi.org/10.3744/SNAK.2019.56.6.473
  11. KCS 14 00 00. 2019. Structural Materials Corporation, Welding 2019.
  12. Kim, Heewoon, Cho, Gyuwon, Ma, Junyung, and Song, Myongken. 2022. Winding Structure Design and Analysis of Traction Motor for EV using Hairpin Winding. The Transactions of the Korean Institute of Electrical Engineers 2022.07:1065-1066.
  13. Kim, Iljung, Kim, Woosoon, Kim, Joonyoung, Chae, Heesu, Woo, Jiyeong, Do, Kyungmin, Lim, Sunghoon, Shin, Minsoo, Lee, Jieun, and Kim, Heungnam. 2022. Discovering Essential AI-based Manufacturing Policy Issues for Competitive Reinforcement of Small and Medium Manufacturing Enterprises. Journal of the Korean Society for Quality Management 50(4):647-664.
  14. Kim, Kichan. 2017. Trend and Issue of Traction Motor Technology for Electric Vehicle. Journal of the Korea Society of Automotive Engineers 39(2):40-44.
  15. Kim, Kihyun, Kim, Seongmok, and Kim, Yongsoo. 2023. A Study on Optimization of Classification Performance through Fourier Transform and Image Augmentation. Journal of the Korean Society for Quality Management 51(1):119-129. https://doi.org/10.21562/kjs.2023.02.57.1.119
  16. Kim, Taewon, Han, Changmin, and Choi, Heawoon. 2020. Welding Quality Inspection Using Deep Learning. Proceedings of the Korean Society of Manufacturing Process Engineers Spring Conference 18-18.
  17. Lee, Cheoleung, Kang, Kyunghun, and Lee, Myunwoo. 1994. A Study on the Effect of Glare Amount and Exposure Time on Visual Fatigue in Visual Inspection Work. Proceedings of the Korean Operations and Management Science Society Conference, 1994.01, 569-579.
  18. Lee, Gwondong, Maeng, Juhyung, and Song, Seokil. 2019. Mobility Mode Classification Method for Trajectory Data Using CNN. Journal of Korean Institute of Information Technology 17(12):13-20, https://doi.org/10.14801/jkiit.2019.17.12.13
  19. Lee, Hyunggeun, Hong, Yongmin, and Kang, Sungwoo. 2021. Identifying Process Capability Index for Electricity Distribution System through Thermal Image Analysis. Journal of the Korean Society for Quality Management 49(3):327-340. https://doi.org/10.7469/JKSQM.2021.49.3.327
  20. Lee, Kidong, Yi, Sung, Hyun, Soonkeun and Kim, Cheolhee. 2021a. Review on the Recent Welding Research with Application of CNN-Based Deep Learning Part I: Models and Applications. Welding and Joining 39(1):10-19. https://doi.org/10.5781/JWJ.2021.39.1.1
  21. Lee, Kidong, Yi, Sung, Hyun, Soonkeun and Kim, Cheolhee. 2021b. Review on the Recent Welding Research with Application of CNN-Based Deep Learning Part II: Model Evaluation and Visualizations. Welding and Joining 39(1):20-26.  https://doi.org/10.5781/JWJ.2021.39.1.2
  22. Lee, Yonghwan and Kim, Youngseop. 2020. Comparison of CNN and YOLO for Object Detection. Journal of the Semiconductor & Display Technology 19(1):85-92.
  23. Oliver B., Nicolai S., Matthias B., and Tim H. 2020. Reduction of Spatter and Pores in Laser Welding of Copper Hairpin Using two Superimposed Laser Beams. Korean Society off Laser Processing 23(12):14-20.
  24. Tan, M. and Le, Quoc V. 2019. Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning. Long Beach, CA, PMLR 97. https://arxiv.org/pdf/1905.11946.
  25. Woo, Minyeong, Noh, Sihun, Jun, Sungbae, Kim, Yongjae, and Jung, Sangyong. 2021. Analysis of Copper Loss Characteristic According to Conductor Configuration of Hairpin Winding on EV Propulsion Motors. Proceedings of the Korean Institute of Electrical Engineers Conference 2021.11, 171-173.