http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
그래프를 이용한 아파트 배치 자동화를 위한 주동 형상 표현법
이진모(Rhee, Jinmo),페드로 벨로소(Veloso, Pedro),김정헌(Kim Jeong Heon) 대한건축학회 2022 대한건축학회 학술발표대회 논문집 Vol.42 No.2
This research proposes an alternative representation of apartment building mass for developing an automation tool of apartment complex layout design. An apartment building mass is a collection of residential units with required facilities and a constituent of an apartment complex. The shape of mass changes according to the configuration of the unit plans and building codes. Layout design problem is determining appropriate positions and angles by the shape variables such as in-between distance, amount of solar radiation, and angle preferences. By reviewing the precedents of computational representation of the mass, this research will address their limitations in complex layout automation and proposes a new representation which potentially responds to design feedback system in the automation of laying out the complex.
인공지능을 이용한 주택 설계 기법 자동화 연구 - 유전 알고리즘을 이용한 법규 기반 최적 공간 탐색 -
이진모(Rhee, Jinmo),정재원(Chung, Jae-won) 대한건축학회 2019 대한건축학회 학술발표대회 논문집 Vol.39 No.2
This paper reports on a generative potential of using the one algorithm of artificial intelligence (AI) techniques, genetic algorithm, in architectural design. Exploring an optimized space for housing design by responding to building codes of the given site, the paper proposes a novel housing design method with a proper representation of space to genetic algorithm. Not only can the method support architects automatically generate and review the available architectural volume options within the conditions of a specific site, but also provide an AI-based framework that architects uses in practice for housing design.
확산 제한 응집 알고리즘 기반 공간계획 - 다중 에이전트 시스템을 이용한 지하광장 디자인 실험 -
이진모(Rhee, Jinmo) 대한건축학회 2021 대한건축학회 학술발표대회 논문집 Vol.41 No.2
This research introduces diffusion-limited aggregation (DLA) algorithm as a responsive design tool in space planning. This research employs DLA algorithms to solve an architectural design problem with large space and complex variables. Developing a novel method to represent a space into DLA agents and environments, a design example presented in this research shows the diverse aggregation patterns in floor plan. Through the example, this research proposes four different steps for implementing DLA algorithm in design problems: representation, configuration, variation, and application. With these steps, this research demonstrates the generative potential of DLA algorithm in that it can cover and explore the wide range of design solution space without changing the algorithm itself.
아파트 단지 계획에서 인공지능의 적용 가능성 - 생성적 시스템 기반 아파트 단지 주동 배치의 프레임워크 -
이진모(Rhee, Jinmo),정재원(Chung, Jae-won) 대한건축학회 2019 대한건축학회 학술발표대회 논문집 Vol.39 No.2
Apartment complex (AC) in Korea is a specific type of residential architecture. It is typically organized into regular grids, adapted grids, concentric circles, or rows, which establish a formal unity of the complex and maximize the revenue under the strict zoning regulations. This paper reports on a generative system framework of building arrangement in AC. It improves the continuous efforts to automate AC design in precedents by integrating segmented process of AC layout and overcoming the limits of parametric approaches with artificial intelligence (AI). This framework proposes not only a fully-automated design workflow of AC but also a potential of AI in architectural design with high complexity of our society.
아파트 주동 배치를 위한 단일 목표 최적화 - 다섯 가지 최적화 알고리즘의 비교 적용과 실험 -
이진모(Rhee, Jinmo),페드로벨로소(Veloso, Pedro) 대한건축학회 2023 대한건축학회 학술발표대회 논문집 Vol.43 No.2
This paper explores the optimization of apartment building layouts using five different meta-heuristic optimization algorithms: Simple Genetic Algorithm (SGA), Simple Evolutionary Algorithm (SEA), Self-Adaptive Differential Evolution (SADE), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC). The study aims to compare and analyze the performance of each algorithm in solving the apartment building layout problem. The optimization process involves placing apartment buildings on a given site while considering design constraints such as floor area ratio, building separation distance, and building height. The objective function is formulated to minimize the number of buildings violating these constraints. The results show that SGA outperforms the other algorithms, achieving the lowest error rate and producing better layouts. SADE follows with a relatively slower but effective optimization performance. SEA and ABC exhibit similar patterns, while PSO demonstrates the least satisfactory results, indicating the need for further optimization. The study provides valuable insights into the characteristics of each algorithm in apartment building layout optimization and can serve as a basis for future research in this field.