Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Defect Detection and Cause Analysis for Copper Filter Dryer Quality Assurance

Copper Filter Dryer 품질보증을 위한 결함 검출 및 원인 분석

  • 오석민 ((주)빅아이 빅데이터개발팀) ;
  • 박진제 ((주)빅아이 기업부설연구소) ;
  • 다어반권 ((주)빅아이 기업부설연구소) ;
  • 장병호 ((주)빅아이) ;
  • 김흥재 ((주)에스디이앤티 기업부설연구소) ;
  • 김창순 ((주)빅아이 기업부설연구소)
  • Received : 2024.01.23
  • Accepted : 2024.02.07
  • Published : 2024.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

Copper Filter Dryer (CFD) are responsible for removing impurities from the circulation of refrigerant in refrigeration and cooling systems to maintain clean refrigerant, and defects in CFD can lead to product defects such as leakage and reduced lifespan in refrigeration and cooling systems, making quality assurance essential. In the quality inspection stage, human inspection and defect judgment methods are traditionally used, but these methods are subjective and inaccurate. In this paper, YOLOv7 object detection algorithm was used to detect defects occurring during the CFD Shaft pipe and welding process to replace the existing quality inspection, and the detection performance of F1-Score 0.954 and 0.895 was confirmed. In addition, the cause of defects occurring during the welding process was analyzed by analyzing the sensor data corresponding to the Timestamp of the defect image. This paper proposes a method for manufacturing quality assurance and improvement by detecting defects that occur during CFD process and analyzing their causes.

Copper Filter Dryer(CFD)는 냉동 및 냉방 시스템에서 냉매의 순환 시 불순물을 제거하여 깨끗한 냉매를 유지하는 역할을 하며, CFD의 결함은 냉동 및 냉방 시스템의 누수, 수명 저하 등 제품의 결함으로 이어질 수 있어 품질보증이 필수적이다. 기존에는 품질 검사 단계에서 작업자가 검사하고 결함을 판단하는 방법이 주로 사용되었으나, 이러한 방법은 주관적으로 판단하기 때문에 정확하지 못하다. 본 논문에서는 CFD 축관 및 용접 공정 과정에서 발생하는 결함을 검출하고 기존의 품질 검사를 대체하기 위해 YOLOv7 객체 감지 알고리즘을 사용하여 결함을 검출했고, F1-Score 0.954, 0.895의 검출 성능을 확인하였다. 또한, 결함 이미지의 Timestamp에 해당하는 센서 데이터 분석을 통해 용접 과정 중 발생하는 결함의 원인을 분석하였다. 본 논문은 CFD 공정 중 발생하는 결함을 검출하고 원인을 분석함으로써 제조 품질보증과 개선 방안을 제시한다.

Keywords

Acknowledgement

이 논문은 2023년 교육부의 재원으로 한국연구재단의 지원을 받아 수행된 지자체-대학 협력기반 지역혁신 사업의 결과입니다.(재단 과제관리번호: 2021RIS-003)

References

  1. Campbell, F. C. (Ed.). (2013). Inspection of metals: understanding the basics. ASM International.
  2. Hussain, M. (2023). YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection. Machines, 677. https://doi.org/10.3390/machines11070677
  3. Jiyeon Yim, Seong-Oak Lee, Kyoung-Pyo Kim, & Yonggyun Yu. (2021). Application of object detection algorithm for psychological analysis of children's drawing. Journal of Korea Society of Industrial Information Systems, 26(5), 1-9.
  4. Kaya, Omer & Codur, Muhammed & Mustafaraj, Enea. (2023). Automatic Detection of Pedestrian Crosswalk with Faster R-CNN and YOLOv7. Buildings, 13, 1070. https://doi.org/10.3390/buildings13041070.
  5. K., Nanthini., D., Sivabalaselvamani., K., Chitra., S., Kavinkumar. (2023). A Survey on Data Augmentation Techniques. 913-920.
  6. Moon-Seok Jeon, Yeongtae Kim, Yuseok Jeong, Hyojun Bae, Chaewon Lee, Song Lim Kim, & Inchan Choi (2023). A Study on the Artificial Intelligence-Based Soybean Growth Analysis Method. Journal of Korea Society of Industrial Information Systems, 28(5), 1-14.
  7. P. Soviany and R. T. Ionescu. (2018). "Optimizing the Trade-Off between Single-Stage and Two-Stage Deep Object Detectors using Image Difficulty Prediction," 2018 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), Timisoara, Romania, pp. 209-214.
  8. See, J. E. (2015). Visual Inspection Reliability for Precision Manufactured Parts. Human Factors, 57(8), 1427-1442. https://doi.org/10.1177/0018720815602389
  9. Sundaram, Sarvesh, and Abe Zeid. (2023). "Artificial Intelligence-Based Smart Quality Inspection for Manufacturing" Micromachines 14, no. 3: 570. https://doi.org/10.3390/mi14030570
  10. Wang, C. Y., Bochkovskiy, A., & Liao, H. Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
  11. Z. Haimer, K. Mateur, Y. Farhan and A. A. Madi,. (2023). "YOLO Algorithms Performance Comparison for Object Detection in Adverse Weather Conditions," 2023 3rd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Mohammedia, Morocco, pp. 1-7.