As an important part of the power system, the structural status of transmission towers is directly related to the safe and stable operation of the power grid. With the development of smart grids, the demand for accurate prediction and health assessment of the structural status of transmission towers is becoming increasingly urgent. Traditional transmission tower structural status assessment methods mainly rely on manual inspections and empirical judgments, which have problems such as strong subjectivity and low efficiency. At the same time, there is a lack of effective data-driven methods to achieve real-time monitoring and prediction of the transmission tower structural status. This paper proposes a data-driven method for transmission tower structural state prediction and health assessment. Firstly, the background and current challenges of transmission tower structure condition monitoring are introduced; secondly, the research progress and existing deficiencies in related fields are reviewed; then, the method proposed in this paper is elaborated in detail, including key steps such as data acquisition and processing, feature extraction and selection, model construction and training; then, the effectiveness and accuracy of the method are verified through experiments; finally, the experimental results are discussed, and the deficiencies of the research and the direction of future improvement are pointed out. Experimental results show that the data-driven method proposed in this paper can achieve accurate prediction and health assessment of the structural status of transmission towers, and the damage detection accuracy of transmission tower structures fluctuates between 80% and 98%.