An Automated Fire Code Compliance Checking Jointly Using Building Information Models and Natural Language Processing

Abstract

Fire checking is indispensable for guaranteeing the fire safety of buildings as it reviews the compliance of the building with fire codes and regulations. Automated Compliance Checking (ACC) systems that check building data utilizing Building Information Modeling (BIM) against fire codes have emerged as an active field of research. Substantial efforts have focused on analyzing the properties of the building components. However, the analysis of the spatial geometric relationships of building components has received inadequate attention. The present study proposes a novel ACC system leveraging Natural Language Processing (NLP) techniques to review the spatial geometric relationships of building components in BIM models. First, a framework for a BIM-based ACC system is delineated and decomposes ACC into three constituent subtasks: building model parsing, code knowledge translation, and compliance check result reporting. Second, an approach for structured processing of spatial geometric stipulations in fire codes using NLP is presented to review the geometric relationships between components in building models. Finally, the system’s performance is assessed by testing fire code compliance across various building types utilizing BIM models. The empirical findings demonstrate that the system achieves superior recall compared with the manually formulated gold standard, with the ACC system enabling quick, accurate, and comprehensive automated compliance checking.