Advancements in Digital Twin Applications for Intelligent Construction Quality Management

The construction industry is shifting toward a human-centered approach for quality management, with digital twins (DT) facilitating this transition. However, DT applications in construction quality management are still in their early stages, and systematic reviews on this topic are lacking. This paper provides a comprehensive review of the existing research on DT-based quality management, analyzing the frameworks, methodologies, and applications. The study proposes an overarching framework comprising four layers: data acquisition layer; DT layer; data inference layer; and feedback layer, which collectively address quality issues across the construction lifecycle. Further, the paper categorizes four primary methods for DT-based quality inference: machine vision; numerical simulation; rule-based approaches; and predictive parameter derivations. Key challenges, including real-time feedback integration, cost efficiency, and scalability, are identified, along with potential research directions to address these issues. This review aims to provide a foundation for advancing DT applications in construction quality management and fostering future innovation in the field. By establishing a structured framework and synthesizing key DT-enabled methods across construction phases, this study offers theoretical insights for academic research and practical guidance for industry stakeholders seeking to enhance inspection accuracy, reduce rework, and enable proactive, real-time quality control.