With the rapid development of technology and the increasing complexity of engineering projects, the need for effective methods to monitor and assess the structural health of buildings has become more critical than ever. This has led to the emergence of structural health monitoring (SHM) as a vital field of study within civil engineering. Structural health monitoring is a symbol of the development of engineering theory, which has increasingly become an important guarantee for the design verification, construction control, safe operation, and maintenance management of major engineering structures. Based on the basic theory of machine learning, this paper takes the high-rise building as the test carrier to design and deploy the health monitoring system. Through real-time monitoring, data acquisition and processing, the stability and reliability of the high-rise building in normal use and service conditions are verified. In this paper, the damage theory of the high-rise building is analyzed based on the modal parameter identification principle of the wavelet method, which provides a reference for the stress analysis and deformation analysis of the high-rise building under strong wind and earthquake.