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
Dong Hwi Jeong (Seoul National University) Jong Min Lee (Seoul National University)
저널정보
제어로봇시스템학회 제어로봇시스템학회 국제학술대회 논문집 ICCAS 2017
발행연도
2017.10
수록면
1,479 - 1,484 (6page)

이용수

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

초록· 키워드

오류제보하기
Batch process in the practical industry has the characteristics of having unsteady state, nonlinearity and iterative operation. For tracking a reference trajectory of batch process, several data based model predictive controllers have been proposed with the progress of sensors and machine learning. When the reference trajectories are largely different from each other and the nonlinearity of dynamics is severe, however, utilization of a single model with whole dataset may reduce the predictive capability of the model and the control performance. It is because the global model has high possibility to miss the details of process dynamics. To solve this problem, we propose to update a set of local models in the manner of just-in-time (JIT) learning and to utilize them to predict the future behaviour of process for controller design. Bi-level optimization problem while applying the proposed method to design an optimal control is solved by approximate the JIT learning step into an explicit formation. In addition, a global optimal solution of the proposed method can be found by the proposed algorithm despite the constructed JIT model is nonlinear and discontinuous when the linear latent variable model is used for the local modelling. Fed-batch bioreactor system having historical data of tracking distinct reference trajectories and severe nonlinearity is simulated to verify the efficiency of the proposed method. Simulation results show that both of predictive and control performances by the proposed method are better than the ones of the conventional latent variable model predictive controller.

목차

Abstract
1. INTRODUCTION
2. METHOD
3. ON-LINE NEAR JUST-IN-TIME MODEL PREDICTIVE CONTROL
4. SIMULATION RESULTS
5. CONCLUSION
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

UCI(KEPA) : I410-ECN-0101-2018-003-001428099