Machine Learning Modeling And Genetic Optimization Of Adaptive Building Facade Towards The Light Environment
Yuanyuan Li Department of Architecture, Qingdao City University
Chenyu Huang School of Architecture and Art, North China University of Technology
Gengjia Zhang Department of Architecture, Tamkang University
Jiawei Yao College of Architecture and Urban Planning, Tongji University
For adaptive facades, the dynamic integration of architectural and environmental information is essential but complex, especially for the performance of indoor light environments. This research proposes a new approach that combines computer-aided design methods and machine learning to enhance the efficiency of this process. The first step is to clarify the design factors of adaptive facade, exploring how parameterized typology models perform in simulation. Then interpretable machine learning is used to explain the contribution of adaptive facade parameters to light criteria (DLA, UDI, DGP) and build prediction models for light simulation. Finally, Wallacei X is used for multi-objective optimization, determines the optimal skin options under the corresponding light environment, and establishes the optimal operation model of the adaptive facades against changes in the light environment. This paper provides a reference for designers to decouple the influence of various factors of adaptive facades on the indoor light environment in the early design stage and carry out more efficient adaptive facades design driven by environmental performance.
Keywords: Adaptive Facades; Light Environment; Machine Learning; Light Simulation; Genetic Algorithm; Sdg 3; Sdg 12