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
Mollaeiubli, Takhmasib (Ajou University) Yi, Hwang (Ajou University)
저널정보
대한건축학회 대한건축학회 학술발표대회 논문집 대한건축학회 2022년도 춘계학술발표대회논문집 제42권 제1호(통권 제77집)
발행연도
2022.4
수록면
215 - 218 (4page)

이용수

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

초록· 키워드

오류제보하기
Kinetic façade (KF) is an engineered solution designed to improve an environmental building performance (EBP). Despite continued interest on KF, little attention has been paid to the efficient climate-adaptive control in operation. Providing that using machine-learning (ML) techniques, dynamic adaptation of the KF morphology can be predictively and quickly informed by the simulated variation of the indoor environment, this study evaluated computational performances of different ML algorithms to construct AI surrogates of EBP simulators. Upon a 1:20 scale test model of an office room with exterior kinetic shading skin (1.73 x 1.1m), we tested nine supervised ML-regressors to predict indoor daylight comfort―represented by the unit of illuminance and the daylight glare probability (DGP). Four input features, including the facade panel angle, solar altitude, azimuth, and global illuminance, were identified, and 1,000 training samples per illuminance and glare output each were obtained from Radiance simulation on Rhino Grasshopper. The results suggest that tree-based algorithms such as decision-tree and random forest regression perform best in the illuminance prediction, whereas artificial neural network (ANN) and nearest neighbor are better suited to predicting DGP. It also finds that DNN is highly sensitive to hyperparameter combination and the accuracy of Gaussian process (GP) depends on kernel choice.

목차

Abstract
1. Introduction
2. AI in architecture and building studies
3. Methods
4. Results and discussion
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

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0