Researchers at the National Cheng Kung University in Taiwan have developed an AI model that can simulate the whole life cycle of a building, including its environmental impact and the effect of building performance optimisation (BPO) measures. The new AI model aims to address the need for effective modelling of the impact of material production, construction, operation and demolition throughout a building’s entire life cycle on its environmental impact. By developing an integrated learning model that combines a new set of optimisation algorithms, the researchers aim to improve design, management and optimisation of buildings’ carbon emissions from the planning stage onwards.

The researchers identified 28 features as input parameters for an office in the Qingdao international academician park. They sampled the parameters using five different Monte Carlo methods and prepared the data set. They applied an ensemble learning model (ELM) to make predictions. The model was trained using 70% of the data set and the remainder was used as test data.

After picking out the sampling method with the best prediction performance and shortest search time, it was used to select important parameters for BPO via sensitivity analysis. Among these parameters, air infiltration rate, wall thermal transmittance, and air conditioning set-points were found to have the most influence on LCCE, LCC, and IDH, respectively. The randomised search was found to be optimal for hyper-parameter optimisation, with the corresponding coefficient of determination R^2 of 0.980.

The researchers applied a two-archive evolutionary algorithm for constrained multi-objective optimisation (C-TAEA) to BPO to propose various schemes. Compared with the base case, the single best solution schemes reduced LCCE, LCC, and IDH by 54.6%, 18.7%, and 64.5%, respectively. The best equilibrium solution reduced LCCE, LCC, and IDH by 34.7% (1946.3 kg carbon dioxide/m^2), 13.9%, and 26.6% (2082.1 hours), respectively, surpassing the performance of existing methods. It was found to solve the problem of different optimisation ranges of other objectives.

“This work introduces artificial intelligence into architecture, representing an emerging trend of intelligent building construction. It can directly predict life cycle carbon emissions (LCCE), life cycle costs (LCC), and indoor discomfort hours (IDH) at the design stage, producing a scheme for best building performance,” said Dr Yaw-Shyan Tsay of National Cheng Kung University, who led the research.

“The present work provides an intelligent and efficient BPO strategy. It can automatically generate building schemes and improve building performance quickly by evaluating the best design approaches from the life cycle perspective. The proposed techniques will be convenient for architects and engineers to work with and will help improve the quality of life of building residents,” said Dr Tsay.