Advances in Constructional Engineering

With the advancement of intelligent building systems, equipment operation and maintenance management faces multiple challenges. To enhance operational efficiency and diagnostic accuracy, this study proposes a digital twin-based fault diagnosis system for building equipment. The system utilizes digital twin technology to enable real-time mapping and simulation of equipment, integrating multi-source data. Through advanced fault diagnosis algorithms such as deep learning and machine learning, it achieves precise fault localization and prediction. Practical validation demonstrates that this system significantly reduces fault diagnosis time, lowers maintenance costs, and improves operational stability and reliability of building equipment, providing robust support for smart building operations.

Digital twin; Building equipment; Operation and maintenance management; Fault diagnosis; Smart building