Prediction of the Most Fire-Sensitive Point in Building Structures with Differentiable Agents for Thermal Simulators

TL;DR

This paper introduces a machine learning framework using Graph Neural Networks to efficiently identify the most fire-sensitive point in building structures, improving fire safety assessment accuracy and speed.

Contribution

It presents a novel differentiable agent for FEA simulators, incorporating a GNN with edge updates and transfer learning to predict the worst-case fire impact point.

Findings

Framework accurately identifies the MFSP in large-scale simulations

GNN-based approach reduces computational costs compared to traditional methods

Open-sourced datasets and code facilitate further research

Abstract

Fire safety is crucial for ensuring the stability of building structures, yet evaluating whether a structure meets fire safety requirement is challenging. Fires can originate at any point within a structure, and simulating every potential fire scenario is both expensive and time-consuming. To address this challenge, we propose the concept of the Most Fire-Sensitive Point (MFSP) and an efficient machine learning framework for its identification. The MFSP is defined as the location at which a fire, if initiated, would cause the most severe detrimental impact on the building's stability, effectively representing the worst-case fire scenario. In our framework, a Graph Neural Network (GNN) serves as an efficient and differentiable agent for conventional Finite Element Analysis (FEA) simulators by predicting the Maximum Interstory Drift Ratio (MIDR) under fire, which then guides the training and evaluation of the MFSP predictor. Additionally, we enhance our framework with a novel edge update mechanism and a transfer learning-based training scheme. Evaluations on a large-scale simulation dataset demonstrate the good performance of the proposed framework in identifying the MFSP, offering a transformative tool for optimizing fire safety assessments in structural design. All developed datasets and codes are open-sourced online.