Research on Data-Driven Building Form Performance-Based Design Method of Libraries

Abstract With the prevalence of the concept of low-carbon sustainable development in the building industry, building form performance-based design has garnered widespread attention from related scholars. This research takes a public library building located in a hot summer and cold winter region of China as its case study. Its objective is to enhance traditional building performance-based design by employing a data-driven building form performance-based design method based on the processes of “data acquisition, data mining, and data decision-making.” This methodology aims to improve the efficiency of building performance optimization. Specifically, through investigation and survey of target building cases, the research identifies the building form composition strategy for the corresponding public library, the value range of building form design parameters, and formulates a building performance evaluation index system focusing on three aspects: building daylight index, radiation index, and outdoor thermal comfort. Simultaneously, employing a parametric design method, this research achieves the generation of complex library building forms within the constraints of a rectangular plane. It conducts building performance simulations for the generated results, obtains datasets comprising generated building form parameters and performance simulation results, trains a machine learning model using this dataset, and uses the trained agent model for predicting building performance workflows. Finally, the research evaluates the impact of different building form design parameters on performance prediction through interpretable machine learning (IML) analysis. It obtains the optimized library building form through multi-objective genetic algorithm (MOGA) optimization experiments. Through analysis of the optimization results, a building form optimization strategy is proposed for libraries located in hot summer and cold winter regions. This strategy aims to enhance the effectiveness of low-carbon and energy-saving measures during the early design stages of building programs.