메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
윤주섭 (한국생산기술연구원)
저널정보
한국자동차공학회 한국자동차공학회 추계학술대회 및 전시회 2019년 한국자동차공학회 추계학술대회 및 전시회
발행연도
2019.11
수록면
1,116 - 1,121 (6page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
In this paper, we developed a vision system that can collectively detect welding defects such as nut/bolt missing and nut eccentricity on heterogeneous brackets produced in automatic welding machines. Many existing auto-parts manufacturers rely entirely on manual welding inspection processes. The discrimination of OK/NG is a visual inspection by the operator and the situation is a full inspection according to the feeling of the skilled worker. This leads to optical illusions due to worker’s increased fatigue and detection errors due to randomness of the inspector’s judgment. In order to overcome the limitations of visual inspection and to increase productivity by improving the reliability and speed of inspection, it is essential to avoid qualitative judgment and establish quantitative judgment criteria in automatic welding nut/bolt inspection. Therefore, it is necessary to develop an inspection process for detecting missing and defects of nut/bolt welded to brackets using vision system. To develop the vision system for bracket batch inspection, we installed the bracket alignment transfer unit on the outlet of the parts produced by the automatic welding machine, and developed the operation/transfer/vision control technology by PLC communication between the automatic welding machine/alignment transfer unit/vision system. In order to develop an automated SW solution for the inspection process, we designed the UI for bracket registration, recognition and inspection result(OK/NG) to prevent the mixing of parts, and developed nut/bolt missing and nut(hole) eccentric measurement technology on the brackets. In addition, the control and discrimination algorithm of machine vision was evaluated for the performance of welding defect detection system, and the applicability was verified by calculating the time and economic effect on the identification of defects through the process installation of real-time inspection system. The problems were improved and optimized by designing and manufacturing sensors, components and turning chutes for each product. The real-time monitoring of the inspection process through the developed fusion module convenient for acquiring and utilizing the process data, has achieved up to 16 types of brackets, cycle time within 1.5 seconds, False Negative Rate 1.42cpk, and nut eccentricity measurement accuracy of less than 0.2㎜.

목차

Abstract
1. 서론
2. 연구 목표 및 내용
3. 연구 결과
4. 결론
References

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0