This research aims to explore the method of health monitoring for operational subway structures based on point cloud data. Utilizing advanced ground-based 3D laser scanning technology, precise point cloud data of the operational subway structure has been successfully obtained. Through in-depth analysis and processing of this data, key geometric information and features of the subway structures are extracted. The lining deformation, cracks, and other potential defects in the subway structures are accurately identified through point cloud data. Through application verification on actual operational subway lines, this method demonstrates outstanding detection performance and reliability, providing robust support for the health assessment of subway structures. The method boasts advantages such as high precision, efficiency, and non-contact characteristics, allowing for more accurate detection of subtle changes in subway structures. It can rapidly acquire a large amount of data, enhancing the efficiency and accuracy of detection. The method has been validated in practical projects, offering more reliable technical support for ensuring the safe operation of the subway.