Artificial intelligence to enhance BIM-BEPS integration via IFC: Challenges, solutions, and future directions

Abstract

In the Architecture, Engineering, and Construction (AEC) domain, integrating Building Information Modeling (BIM) and Building Performance Simulations (BEPS) is essential for optimizing building design and performance. This study investigates the potential of AI to enhance the integration of BIM and BEPS through Industry Foundation Classes (IFC). This study also examines the challenges inherent in the BIM-BEPS workflow and the barriers to AI adoption in this domain. The paper aims to present solutions that support IFC-based interoperability, identifying the most effective approaches within the categories of the mapped problems. These include tools for extracting geometry from IFC models, algorithms for geometric enrichment, ontologies for rule-based model verification, machine learning techniques for space classification, external libraries, and IFC extensions for property addition to models. The integration of AI demonstrates significant potential to improve BIM-BEPS workflows, particularly in automating geometry extraction from BIM, enriching model data, and detecting inconsistencies in IFC models. The study also explores opportunities to enhance the BIM-BEPS workflow through IFC4 and future IFC generations, focusing on combining ontology frameworks with machine learning. Furthermore, the study emphasizes the industry’s role in developing better user support solutions, underscoring the need for users to adhere to well-defined design requirements and workflows to maximize the benefits of these advancements.