딥러닝 AI 솔루션을 활용한 전기자동차 헤어핀 권선 모터의 용접 품질향상에 관한 사례연구
A Case Study on Quality Improvement of Electric Vehicle Hairpin Winding Motor Using Deep Learning AI Solution
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
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.
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.
참고문헌 (25)
- Bocksrocker, O., "Reduction of Spatter and Pores in Laser Welding of Copper Hairpin Using Two Superimposed Laser Beams", Laser in Manufacturing Conference Munich, 2019, pp.1~8 (2019)
- Cho, Yongjoon., "A Study of Real-Time Weldability Estimation of Resistance Spot Welding Using Fuzzy Algorithm", Journal of Welding and Joining, 16(5), pp.76~85 (1998)
- Choi, Sehun., "Assessment of Laser Joining Weld Quality by Visual Inspection, Computer Simulation, and Deep Learning", Applied Sciences, 11(2), pp.642~655 (2021)
- Coherent, "Laser Technology for Electric Vehicles", Laser Solutions, 22(2), pp.8~11 (2019)
- "Quo Vadis Winding Technology? A Study on the State of The Art and Research on Future Trends in Automotive Engineering" (2017)[URL]
- Glaessel, T, "Challenges in the Manufacturing of Hairpin Windings and Application Opportunities of Infrared Lasers for the Contacting Process", 7th Int. Elect. Drives Prod. Conf(EDPC), pp.1~7 (2017)
- "EVs to Make Up Third of New Cars Sold Globally by 2030: Deloitte. S&P Global Commodity Insights" (2020)[URL]
- 황동수, "실시간 용접품질 모니터링 시스템의 개발 및 적용 동향", 대한용접접합학회지, 30(1), pp.44~50 (2012), 대한용접접합학회
- Jamie, H, "Electric Vehicle Market Outlook", Deloitte Insight, pp.7~8 (2022)[DOI]
- 강지훈, "딥 러닝 기반의 이미지학습을 통한 저항 용접품질 검증", 대한조선학회 논문집, 56(6), pp.473~479 (2019), 대한조선학회[DOI]
- "KCS 14 00 00. 2019. Structural Materials Corporation", Welding 2019, ~ (2019)
- Kim, Heewoon., "Winding Structure Design and Analysis of Traction Motor for EV using Hairpin Winding", The Transactions of the Korean Institute of Electrical Engineers, pp.1065~1066 (2022)
- 김일중, "중소 제조기업의 경쟁력 강화를 위한 제조AI 핵심 정책과제 도출에 관한 연구", 품질경영학회지, 50(4), pp.647~664 (2022), 한국품질경영학회[DOI]
- Kim, Kichan, "Trend and Issue of Traction Motor Technology for Electric Vehicle", Journal of the Korea Society of Automotive Engineers, 39(2), pp.40~44 (2017)
- 김기현, "푸리에 변환 및 이미지 증강을 통한 분류 성능 최적화에 관한 연구", 품질경영학회지, 51(1), pp.119~129 (2023), 한국품질경영학회[DOI]
- Kim, Taewon, "Welding Quality Inspection Using Deep Learning", Proceedings of the Korean Society of Manufacturing Process Engineers Spring Conference, pp.18~18 (2020)
- Lee, Cheoleung., "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, pp.569~579 (1994)
- 이권동, "CNN을 이용한 궤적데이터에 대한 이동성 모드 분류 방법", 한국정보기술학회논문지, 17(12), pp.13~20 (2019), 한국정보기술학회[DOI]
- 이형근, "열화상 이미지 분석을 통한 배전 설비 공정능력지수 감지 시스템 개발", 품질경영학회지, 49(3), pp.327~340 (2021), 한국품질경영학회[DOI]
- 이기동, "Review on the Recent Welding Research with Application of CNN-based Deep Learning Part 1: Models and Applications", 대한용접접합학회지, 39(1), pp.10~19 (2021), 대한용접접합학회[DOI]
- 이기동, "Review on the Recent Welding Research with Application of CNN-based Deep Learning Part II: Model Evaluation and Visualizations", 대한용접접합학회지, 39(1), pp.20~26 (2021), 대한용접접합학회[DOI]
- 이용환, "객체 검출을 위한 CNN과 YOLO 성능 비교 실험", 반도체디스플레이기술학회지, 19(1), pp.85~92 (2020), 한국반도체디스플레이기술학회
- Oliver B., "Reduction of Spatter and Pores in Laser Welding of Copper Hairpin Using two Superimposed Laser Beams", Korean Society off Laser Processing, 23(12), pp.14~20 (2020)
- Tan, M., "Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks", Proceedings of the 36th International Conference on Machine Learning (2019)
- Woo, Minyeong., "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, pp.171~173 (2021)