AI-Driven Prediction of Energy Consumption in a Building with 3D-Printed Wall Sections through Geometric and Topological Design

3D printing in construction offers unique opportunities for innovative wall designs that enhance sustainability through material savings and better performance. While research has optimized building geometry to reduce environmental impacts, the role of wall section designs in lowering energy consumption remains underexplored. This gap stems from limited studies on configurations like thickness ratios and material–air interfaces, plus the inefficiency of traditional, time-consuming simulation methods. This study tackles this by analysing wall section performance and developing machine learning models to predict energy consumption of 3D-printed walls. Results show a balanced outer-to-inner thickness ratio boosts energy efficiency, highlighting the material–air gap’s role, which varies by material. Additionally, machine learning proves effective in predicting energy use, bypassing lengthy simulations for faster design assessments. These insights advance sustainable construction by enabling energy-efficient 3D-printed wall designs.