Optimizing Facilities Management Through Artificial Intelligence and Digital Twin Technology in Mega-Facilities

Abstract

Mega-facility management has long been inefficient due to manual, reactive approaches. Current facility management systems face challenges such as fragmented data integration, limited predictive systems, use of traditional methods, and lack of knowledge of new technologies, such as Building Information Modeling and Artificial Intelligence. This study examines the transformative integration of Artificial Intelligence and Digital Twin technologies into Building Information Modeling (BIM) frameworks using IoT sensors for real-time data collection and predictive analytics. Unlike previous research, this study uses case studies and simulation models for dynamic data integration and scenario-based analyses. Key findings show a significant reduction in maintenance costs (25%) and energy consumption (20%), as well as increased asset utilization and operational efficiency. With an F1-score of more than 90%, the system shows excellent predictive accuracy for equipment failures and energy forecasting. Practical applications in hospitals and airports demonstrate the developed ability of the platform to integrate the Internet of Things and Building Information Modeling technologies, shifting facilities management from being reactive to proactive. This paper presents a demo platform that integrates BIM with Digital Twins to improve the predictive maintenance of HVAC systems, equipment, security systems, etc., by recording data from different assets, which helps streamline asset management, enhance energy efficiency, and support decision-making for the buildings’ critical systems.