Hao Deng

Traditional construction progress management is hindered by reliance on manual monitoring, delayed information feedback, and a lack of proactive correction capabilities. To address these issues, this study proposes a data-driven closed-loop framework for dynamic progress management leveraging Building Information Modeling (BIM) and Digital Twin (DT). The proposed framework is operationalized through three integrated modules: (i) a dynamic perception layer that synchronizes on-site conditions via IoT and digitized construction logs; (ii) a stochastic prediction engine coupling machine learning with Monte Carlo Simulation (MCS) to quantify delay risks; and (iii) an optimization module based on a Constraint Satisfaction Problem (CSP) model for automated strategy generation. The system’s efficacy was preliminarily evaluated through a prototype application on a primary school building project. Findings from this case indicate that the framework enables near real-time synchronization for schedule deviation warnings, effectively compressing the information latency from days to within a single management cycle. Furthermore, within the empirical scope of the case study, the implementation of DT-driven strategies was associated with a 3-day schedule advancement relative to the simulated baseline and a 15% reduction in the resource idle rate compared to the pre-deployment phase. This study provides a potential pathway for enhancing progress control precision in similar construction environments.