AI and BIM Integration for Enhanced Construction Management Performance: A Systematic Review

Abstract

The increasing complexity of construction projects has made traditional planning methods inadequate for managing dynamic variables. In this context, the integration of building information modelling (BIM) and artificial intelligence (AI) has been increasingly investigated as a promising approach to improve estimation accuracy, decision-making, and sustainable project execution. This systematic literature review, conducted according to the PRISMA guidelines, analysed 47 articles on BIM-AI integration for construction cost and time planning, categorising them into three clusters: time-oriented, cost-oriented, and multi-objective planning. The reviewed studies indicate that BIM-AI workflows may improve planning efficiency, estimation accuracy, and resource allocation. A limited subset of studies directly incorporated energy consumption, carbon emissions, or lifecycle performance into the optimisation objectives. By contrast, broader benefits related to material waste, rework, equipment idle time, and safety were mainly inferred from improvements in scheduling and resource management rather than directly quantified across the reviewed studies. Artificial Neural Networks (ANNs) and Genetic Algorithms (GAs) emerged as the most frequently adopted and consistently reported techniques, while Revit was the most adopted BIM platform. Despite its potential, BIM-AI integration still faces challenges related to software interoperability, data quality, interdisciplinary coordination, and the limited integration of explicit sustainability indicators within optimisation models. Future research should focus on developing standardised and adaptable frameworks that jointly address cost, time, resource efficiency, environmental impact, and lifecycle performance across different construction contexts.