AI-powered fire engineering design and smoke flow analysis for complex-shaped buildings

Abstract

Abstract This paper aims to automatize the performance-based design of fire engineering and the fire risk assessment of buildings with large open spaces and complex shapes. We first establish a database of high-quality fire simulations for diverse building shapes with heights up to 60 m and complex atriums with volumes up to 22 400 m³. Then, artificial intelligence (AI) models are trained to predict the soot visibility slices for new fire cases in buildings of different atrium shapes, symmetricities, and volumes. Two deep learning models were demonstrated: the pix2pix generative adversarial network (GAN) and image-prompt diffusion model. Compared with high-fidelity computational fluid dynamics fire modeling, the available safe egress time predicted by both models shows a high accuracy of 92% for random atrium shapes that are not distinct from the training cases, proving their performance in actual design practices. The diffusion model reproduces more flow details of the smoke visibility profiles than GAN, but it takes a longer computational time to render the fire scene. This work demonstrates the potential of leveraging AI technologies in building fire safety design, offering significant cost and time reductions and optimal solution identification.