MODELING AND IMPLEMENTATION OF QUALITY INSPECTION SYSTEM USING SYSTEM THEORY AND MACHINE LEARNING FOR HUMAN-INCLUDED SMART MANUFACTURING
저자
발행사항
울산 : Graduate School of UNIST, 2018
학위논문사항
학위논문(박사)-- Graduate School of UNIST : Engineering 2018.2
발행연도
2018
작성언어
영어
주제어
발행국(도시)
울산
형태사항
112 ; 26 cm
일반주기명
지도교수: Kim, Namhun
UCI식별코드
I804:31001-200000009163
소장기관
Modeling, implementation ,and control of human-involved smart manufacturing systems poses a huge challenge on how to understand all possible interactions among system components for smart manufacturing and quality assurance. As the manufacturing environment is getting more complicated, the importance of human roles in the manufacturing system gets spotlighted to incorporate the manufacturing flexibility for smart environment of human-machine cooperation. In this regard, the automated and strategic approaches to product quality monitoring, also, are regarded as an important basis for smart manufacturing applications. The quality control and assurance programs, therefore, are becoming a major consideration in the manufacturing industries to ensure customer satisfaction and market needs.
In reality, however, the quality monitoring and assessment in many production processes still highly relies on manual inspections due to a lack of proper data and an effective method to classify defects in a systematic way. The quality assessment in smart manufacturing is necessary not only for having higher inspection accuracy but also for considering the system efficiency. This study, thus, focuses on implementation and analysis of the quality inspection system for smart manufacturing in the view point of human-machine co-existing manufacturing environment. The case study of the automotive part manufacturing and inspection presents the performance enhancement of quality inspection system with an emphasis on effective cooperation between human operator and artificial intelligence (AI) based automated inspection systems. The proposed quality inspection system is based on both system theories for human-included manufacturing system and machine learning algorithm for the quality analysis of gathered manufacturing data. The proposed system consists of three chapters as follows.
First, this chapter presents a formal modeling methodology of affordance-based MPSG for a human-machine collaboration system. Further, the chapter includes supervisory control scheme for flexible manufacturing systems in an automotive industry. The expression using system theory and formal modeling enhances to exchange the current process for flexible manufacturing systems and to adopt the smart manufacturing. It is, also, important that the existing model of affordance-based MPSG is extended to apply the real industrial manufacturing process including human-machine cooperative environments. The proposed extension with the real industrial example is illustrated in four steps; first, the manufacturing process and relevant data are analyzed using perspectives of Men Are Better At- Machines are Better At (MABA-MABA) and the supervisory control; second, the task allocation and the manufacturing process consider the concept of MABA-MABA for collaboration between human and machine; third, the unified modeling language (UML) verifies the manufacturing process application including the concept of the affordance-based MPSG ; and fourth, affordance-based MPSG simulates using a discrete event simulation-agent based modeling (DES-ABM) model to present and analyze the performance of a human in a human-machine cooperative manufacturing process. The simulation approach enables this model to be utilized for further development in controller toward the supervisory control.
Second, this chapter presents the cost effectiveness (CE) framework. In contrast to using the lowest inspection error rate criterion commonly used in the literature to reduce an overall error rate, the modified CE assessment (CEadj) is used. The CEadj explicitly incorporates the warranty cost as a function of the product performance and customer expectation, which is shown to decrease also the number of Type-II error. Next, an experimental design with a sensitivity analysis is performed to understand better on the impact of cost parameters used in the proposed framework. The proposed analysis is expected to aid an implementation of automated quality monitoring tools for better cost saving and higher customer satisfaction. It could also be used as an alternative or complementary tool for the traditional quality inspection system.
Lastly, this chapter proposes the automated quality assessment system based on the SVM including human intervention training. This chapter investigates defective patterns in a manufacturing process by analyzing real-time infrared thermal image of sealer dispensing, which contains multi-modal data of dimensional information and temperature deviation from the dispensing patterns, to enhance the quality monitoring capability of the production system. At the end of this study, an industrial case study of a primer-sealer dispensing process in a sunroof assembly line of an automobile is illustrated to verify and validate the proposed quality assessment system.
분석정보
서지정보 내보내기(Export)
닫기소장기관 정보
닫기권호소장정보
닫기오류접수
닫기오류 접수 확인
닫기음성서비스 신청
닫기음성서비스 신청 확인
닫기이용약관
닫기학술연구정보서비스 이용약관 (2017년 1월 1일 ~ 현재 적용)
학술연구정보서비스(이하 RISS)는 정보주체의 자유와 권리 보호를 위해 「개인정보 보호법」 및 관계 법령이 정한 바를 준수하여, 적법하게 개인정보를 처리하고 안전하게 관리하고 있습니다. 이에 「개인정보 보호법」 제30조에 따라 정보주체에게 개인정보 처리에 관한 절차 및 기준을 안내하고, 이와 관련한 고충을 신속하고 원활하게 처리할 수 있도록 하기 위하여 다음과 같이 개인정보 처리방침을 수립·공개합니다.
주요 개인정보 처리 표시(라벨링)
목 차
3년
또는 회원탈퇴시까지5년
(「전자상거래 등에서의 소비자보호에 관한3년
(「전자상거래 등에서의 소비자보호에 관한2년
이상(개인정보보호위원회 : 개인정보의 안전성 확보조치 기준)개인정보파일의 명칭 | 운영근거 / 처리목적 | 개인정보파일에 기록되는 개인정보의 항목 | 보유기간 | |
---|---|---|---|---|
학술연구정보서비스 이용자 가입정보 파일 | 한국교육학술정보원법 | 필수 | ID, 비밀번호, 성명, 생년월일, 신분(직업구분), 이메일, 소속분야, 웹진메일 수신동의 여부 | 3년 또는 탈퇴시 |
선택 | 소속기관명, 소속도서관명, 학과/부서명, 학번/직원번호, 휴대전화, 주소 |
구분 | 담당자 | 연락처 |
---|---|---|
KERIS 개인정보 보호책임자 | 정보보호본부 김태우 | - 이메일 : lsy@keris.or.kr - 전화번호 : 053-714-0439 - 팩스번호 : 053-714-0195 |
KERIS 개인정보 보호담당자 | 개인정보보호부 이상엽 | |
RISS 개인정보 보호책임자 | 대학학술본부 장금연 | - 이메일 : giltizen@keris.or.kr - 전화번호 : 053-714-0149 - 팩스번호 : 053-714-0194 |
RISS 개인정보 보호담당자 | 학술진흥부 길원진 |
자동로그아웃 안내
닫기인증오류 안내
닫기귀하께서는 휴면계정 전환 후 1년동안 회원정보 수집 및 이용에 대한
재동의를 하지 않으신 관계로 개인정보가 삭제되었습니다.
(참조 : RISS 이용약관 및 개인정보처리방침)
신규회원으로 가입하여 이용 부탁 드리며, 추가 문의는 고객센터로 연락 바랍니다.
- 기존 아이디 재사용 불가
휴면계정 안내
RISS는 [표준개인정보 보호지침]에 따라 2년을 주기로 개인정보 수집·이용에 관하여 (재)동의를 받고 있으며, (재)동의를 하지 않을 경우, 휴면계정으로 전환됩니다.
(※ 휴면계정은 원문이용 및 복사/대출 서비스를 이용할 수 없습니다.)
휴면계정으로 전환된 후 1년간 회원정보 수집·이용에 대한 재동의를 하지 않을 경우, RISS에서 자동탈퇴 및 개인정보가 삭제처리 됩니다.
고객센터 1599-3122
ARS번호+1번(회원가입 및 정보수정)