AN INTEGRATED DIGITAL TWIN FRAMEWORK AND EVACUATION SIMULATION SYSTEM FOR ENHANCED SAFETY IN SMART BUILDINGS

Abstract

Fire hazards in buildings continue to pose a substantial risk to human life and property safety despite declining deaths, injuries, and damages over the past decade. Consequently, fire safety management (FSM) is crucial to effectively preventing and controlling fire hazards. However, several challenges need to be addressed to ensure optimal FSM in buildings, such as the lack of effective integration of advanced technologies such as Internet of Things (IoT) sensors, fire detection systems, and automated response mechanisms, the reliance on insufficient fire safety equipment (FSE) maintenance and a lack of operational skills among occupants. In particular, traditional manual methods of searching for information, such as using two-dimensional drawings and relying on paper documents, have become inefficient and costly as buildings have become larger and more complex. This leaves room for improvement in current FSM practices— specifically, high-efficiency evacuation- the best approach for minimizing mortality and property loss. Digital twin (DT) technologies have been widely used in other industries, such as manufacturing and transportation, to improve efficiency, reduce costs, and enhance safety. However, the FSM sector has been a slow adopter of DT technology. This study investigated the adoption of DT technologies in the FSM sector. This research aims to explore the limitations, opportunities, and challenges associated with adopting DT technology in the FSM sector and further develop a DT-based FSM framework towards smart facility management (FM). This framework lets decision-makers obtain comprehensive information about the building's communication and safety systems. It can also enable the real time monitoring of FSE and provide predictive maintenance. Toward this objective, several DTs for FSM were first reviewed, including building information modeling (BIM), the Internet of Things (IoT), artificial intelligence (AI), and augmented reality (AR). These technologies can be used to enhance the efficiency and safety of FSM in smart buildings. The framework was then synthesized based on the literature review, application requirements, and industry needs. A questionnaire survey was conducted for FM professionals to evaluate the framework and identify the challenges of adopting DT and the proposed framework in the FSM sector. The survey results identify the current state of DT technology in the FSM sector, provide insights into the perception of DT technology among FM practitioners, and validate its expected benefits and potential challenges. The main barriers to adopting DTs in FSM are a lack of knowledge about DTs, their initial costs, user acceptance, difficulties in systems integration and data management, education training costs, a lack of competence, development complexity, and data security. Furthermore, the research develops a building fire evacuation simulation system based on the validated framework, i.e., smart lighting. This system integrates the data from the BIM platform, Fire Dynamic Simulator (FDS), and Agent-Based Simulation (ABS) platform for evacuation through customized developments. Real-time fire situation is transmitted to the evacuation simulation platform to assess the impact of dynamic fire spread on the evacuation of people. A model for optimizing evacuation route planning is designed to improve the utilization of each evacuation exit and provide a visualization of evacuation routes as smart lighting in Dynamo. This proposed system was validated by conducting a case study on three fire evacuation scenarios. An average of 20.9 % increases the evacuation efficiency in three scenarios. The main contributions of this research include (1) Developing a DT-based FSM framework for smart buildings, (2) Developing a fire emergency evacuation simulation system for buildings by integrating DT technologies, and 3) Achieving the integration and interoperability of BIM data, fire data, and evacuation data from different platforms.