How to measure and control indoor air quality based on intelligent digital twin platforms: A case study in China

Abstract

In order to address the current disparity between indoor air quality assessment, prediction, and control, this study proposes an intelligent management approach for indoor air quality based on digital twin platforms. By collecting and fusing multi-level, and multi-dimensional data at the physical level, a comprehensive data integration and analysis platform is established in the digital realm, encompassing the ‘Sense-Integrate-Retrieve-Analyze-Feedback’ framework. Various digital technologies, such as the Internet of Things (IoT), Building Information Modeling (BIM), and machine learning, are utilized to integrate and visualize multi-source heterogeneous data through a lightweight web-based interface so that data retrieval, rapid prediction, and intelligent control are feasible based on various backend algorithm models. Compared to traditional measurement methods, this system offers broader spatiotemporal coverage, increased mobility, and less disruption to physical infrastructure, which underscores the sophistication of monitoring technology, data integration, and environmental management. The proposed intelligent platform has been validated in a traditional Chinese dwelling, and practical results demonstrate that most air quality problems occur in the early morning of winter while this system can swiftly predict and issue control signals for adjustments in occupied spaces exceeding predefined healthy thresholds. Field measurements confirmed that most air quality problems can be solved within 30 min after their appearance. By eliminating data silos through real-time synchronization and remote intelligent control via the digital platform, it bridges the gap between problem identification by managers and problem resolution by end-users, ensuring timely responses to indoor air quality concerns.