한국정보통신학회논문지 (Journal of the Korea Institute of Information and Communication Engineering)

  • 제25권9호
  • /
  • Pages.1144-1151
  • /
  • 2021
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

프레스 공정에서 인공지능기반 실시간 제품 불량탐지 시스템 설계 및 구현

Design and Implementation of a Real-Time Product Defect Detection System based on Artificial Intelligence in the Press Process

  • Kim, Dong-Hyun (Dong-Nam Grand ICT R&D Center, Pusan National University) ;
  • Lee, Jae-Min (School of Computer Science and Engineering, Pusan National University) ;
  • Kim, Jong-Deok (School of Computer Science and Engineering, Pusan National University)
  • 투고 : 2021.04.08
  • 심사 : 2021.05.01
  • 발행 : 2021.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

프레스 공정은 가열 또는 가열하지 않은 상태의 재료에 힘을 가해 원하는 형태로 변형시켜 제품을 만드는 압축 가공 과정이다. 짧은 시간의 연속 압축을 통해 제품을 생산하는 프레스 장비의 특성상 제품 불량은 연속적으로 발생하며 이러한 문제를 해결하기 위한 시스템은 다양한 기술을 이용하여 개발되고 있다. 본 논문은 불량을 탐지하는 인공지능 알고리즘을 기반으로 실시간 불량탐지 시스템을 제안한다. 프레스 장치에 각종 센서를 부착하여 장비의 상태와 불량과의 관계를 빅데이터 플랫폼을 기반으로 정의하고 수집한다. 수집된 데이터를 기반으로 인공지능 알고리즘을 개발하고 개발된 알고리즘을 임베디드 보드를 이용하여 구현함으로써 실제 현장에 적용하여 시스템의 실용성을 보이겠다.

The pressing process is a compression process in which a product is made by applying force to a heated or unheated material to transform it into the desired shape. Due to the characteristics of press equipment that produces products through continuous compression for a short time, product defects occur continuously, and systems for solving these problems are being developed using various technologies. This paper proposes a real-time defect detection system based on an artificial intelligence algorithm that detects defects. By attaching various sensors to the press device, the relationship between equipment status and defects is defined and collected based on a big data platform. By developing an artificial intelligence algorithm based on the collected data and implementing the developed algorithm using an embedded board, we will show the practicality of the system by applying it to the actual field.

키워드

과제정보

This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education (NRF-2020R1I1A306594711).

참고문헌

  1. D. H. Kim, J. M. Lee, and J. D. Kim, "Design and Implementation of Real Time Device Monitoring and History Management System based on Multiple devices in Smart Factory," Journal of The Korean Institute of Information and Communication Engineering, vol. 25, no. 1, pp. 124-133, Jan. 2021.
  2. S. G. Han, "Educational Contents for Concepts and Algorithms of Artificial Intelligence," The Korean Society of Computer and Information, vol. 26, no. 1, pp. 37-44, Jan. 2021.
  3. J. W. Yun, "A Study for In-process Monitoring in Press die," Korea Academy Industrial Cooperation Society, vol. 18, no. 6, pp. 692-696, Jun. 2017.
  4. Y. J. Jeon, H. S. Choi, Y. B. Ko, and D. E. Kim, "Perform Process Design to Form Sharp Wedges on Both Surfaces of Anti-loosening Washer," The Korean Society Of Automotive Engineers, vol. 28, no. 12, pp. 897-901, Dec. 2020. https://doi.org/10.7467/KSAE.2020.28.12.897
  5. D. H. Kim, S. B. Boo, H. C. Hong, W. G. Yeo, and N. Y. Lee, "Machine Vision-based Defect Detection Using Deep Learning Algorithm," Journal of The Korean Society for Nondestructive Testing, vol. 40, no. 1, pp. 47-52, Feb. 2020. https://doi.org/10.7779/jksnt.2020.40.1.47
  6. H. J. Shin, N. J. Kwak, and T. S. Song, "Detection The Behavior of Smartphone Users using Time-division Feature Fusion Convolutional Neural Network," Journal of The Korean Institute of Information and Communication Engineering, vol. 24, no. 9, pp. 1224-1230, Sep. 2020.
  7. H. C. Lee, I. H. Park, T. H. Im, and D. T. Moon, "CNN-based Building Recognition Method Robust to Image Noises," Journal of The Korean Institute of Information and Communication Engineering, vol. 24, no. 3, pp. 341-348, Mar. 2020.
  8. Raspberrypi project [Internet]. Available: https://www.raspberrypi.org/.
  9. OPC FOUNDATION [Internet]. Available: https://opcfoundation.org/.
  10. EMERSON AUTOMATION SOLUTIONS [Internet]. Available: https://www.emerson.com/en-gb/.
  11. N. Adiga, D. Govind, and M. Prasanna, "Significance of epoch identification accuracy for prosody modification," in Proceeding of the 2014 International Conference on Signal Processing and Communications (SPCOM), Bangalore, India, 2014.