DOI QR코드

DOI QR Code

Implementation of a Micro Drill Bit Foreign Matter Inspection System Using Deep Learning

  • Jung-Sub Kim (Dept. of Industrial Engineering, National Kumoh Institute of Technology) ;
  • Tae-Sung Kim (Dept. of Industrial Engineering, National Kumoh Institute of Technology) ;
  • Gyu-Seok Lee (Dept. of Industrial Engineering, National Kumoh Institute of Technology)
  • 투고 : 2024.09.03
  • 심사 : 2024.09.25
  • 발행 : 2024.10.31

초록

본 논문은 YOLO V3 알고리즘을 기반으로 한 드릴비트 이물질 검사 시스템을 구현하고 그 성능을 평가하였다. 연구는 드릴비트의 정상 상태와 이물 상태를 구분하기 위해 600장의 학습 데이터를 사용하여 YOLO V3 모델을 학습시켰다. 구현된 검사 시스템은 자동검사를 통해 드릴비트의 상태를 정확히 분석하고 결함을 효과적으로 탐지하였다. 성능 평가는 2000회 이상 사용된 드릴비트를 대상으로 수행되었으며, 재연마 가능 여부를 판별하는 인식률 98%를 달성하였다. 세척 공정에서 이물질 제거의 목표를 99.6%로 평가하였으며, 자동 검사 시스템은 시간당 500개 이상의 드릴비트를 검사할 수 있어 기존 수동 검사 방법에 비해 약 4.3배 더 빠르고 99%의 높은 정확도를 기록하였다. 이러한 결과는 자동화된 검사 시스템이 검사 속도와 정확성을 획기적으로 개선할 수 있음을 보여주며, 제조현장에서의 품질 향상과 비용 절감에 기여할 수 있음을 알수있다. 향후 연구에서는 시스템 최적화와 성능 향상을 통해 더욱 효율적이고 신뢰성 높은 검사 기술 개발이 필요하다.

This paper implemented a drill bit foreign matter inspection system based on the YOLO V3 algorithm and evaluated its performance. The study trained the YOLO V3 model using 600 training data to distinguish between the normal and foreign matter states of the drill bit. The implemented inspection system accurately analyzed the state of the drill bit and effectively detected defects through automatic inspection. The performance evaluation was performed on drill bits used more than 2,000 times, and achieved a recognition rate of 98% for determining whether resharpening was possible. The goal of foreign matter removal in the cleaning process was evaluated as 99.6%, and the automatic inspection system could inspect more than 500 drill bits per hour, which was about 4.3 times faster than the existing manual inspection method and recorded a high accuracy of 99%. These results show that the automated inspection system can dramatically improve inspection speed and accuracy, and can contribute to quality improvement and cost reduction in manufacturing sites. In future studies, it is necessary to develop more efficient and reliable inspection technology through system optimization and performance improvement.

키워드

참고문헌

  1. Hwang Chang-wook. "Development of Automatic System for Re-grinding Drill for PCB Substrate Micro-hole Machining." Domestic Master's Thesis, Graduate School of Industry, Kumoh National Institute of Technology, 2020
  2. Na Ki-hyun. "A Study on the Design of Polishing Unit and Polishing Conditions for Re-grinding Micro Drill Bits." Domestic Master's Thesis, Kumoh National Institute of Technology, 2018
  3. Jeong Ki-young. "Implementation of Automatic Conformal Coating Inspection System Using YOLO v5." Domestic Master's Thesis, Graduate School of Industry, Kyungpook National University, 2023.
  4. Lee, Hyein, and Jinoo Joung. "Resolving Memory Bottlenecks in Hardware Accelerators with Data Prefetch." Journal of the Korea Society of Computer and Information 29.6 (2024): 1-12. https://doi.org/10.9708/jksci.2024.29.06.001
  5. Kim Jong-go. "A Study on the Implementation of Automatic Re-grinding System for Micro Drill Bits." Domestic Master's Thesis, Graduate School of Industry, Kumoh National Institute of Technology, 2009.
  6. Kwak Dong-gyu. "A Study on Measurement of Micro Drill Bits Using Image Processing." Domestic Master's Thesis, Graduate School of Kumoh National Institute of Technology, Dec. 2008.
  7. Kook Yeon-ho. "A Study on the Optimal Process Design of Waterjet-based Cleaning System for Micro Drill Bit Resharpening." Master's thesis, Kumoh National Institute of Technology, 2018.
  8. Jin-Hyeon Lee. "Design for Micro Drill Bit Ring Setting and Study on High-Precision Ring Setting." Master's thesis, Kumoh National Institute of Technology, Graduate School of Industry, 2020.
  9. Ji-Eun Hwang. "A Study on the Development of Dotting System for Improving Micro Drill Bit Resharpening Rate." Master's thesis, Kumoh National Institute of Technology, Graduate School, 2021.
  10. Jin-Hyeon Lee. "Design for Micro Drill Bit Ring Setting and Study on High-Precision Ring Setting." Master's thesis, Kumoh National Institute of Technology, Graduate School of Industry, 2020.
  11. Redmon, Joseph. "Yolov3: An incremental improvement." arXiv preprint arXiv:1804.02767 (2018). DOI: 10.48550/arXiv.1804.027
  12. Senjoba, Lesego, et al. "One-Dimensional Convolutional Neural Network for Drill Bit Failure Detection in Rotary Percussion Drilling." pp.297-314, Jan. 2021. DOI: 10.3390/mining1030019
  13. Yu, Yongchao, et al. "Application of Convolutional Neural Network to Defect Diagnosis of Drill Bits." Applied Sciences Dec. 2022. DOI: 10.3390/app122110799
  14. Yolo v3: Visual and real-time object detection model for smart surveillance systems (3s)
  15. Min-Kyun Lee. "Design and Implementation of PCB Defect Detection System through YOLO Improvement." Master's thesis, Hanyang University, Graduate School of Engineering, 2023.
  16. Akumalla, Gnana Spandana. "Failure Inference in Drilling Bits:: Leveraging YOLO Detection for Dominant Failure Analysis." (2023).