Abstract: The previous research focuses on the failure of transmission tower under single disasters such as typhoon or rainstorm and neglects that typhoon often carry rainstorm as a common threat to the safety of transmission tower. To address the issue above, we establish a combined failure probability prediction model of data mechanism of transmission tower under typhoon disaster with rainfall correction, so as to accurately predict the failure probability of transmission tower under the combined actions of typhoon and rainstorm. Firstly, in data driving part, the generative adversarial network(GAN) is adopted to solve problems such as insufficient data volume and unbalanced data information. And the support vector regression, ridge regression, random forest, K-nearest neighbors, extra trees, and AdaBoost, are used to predict the failure probability of transmission tower. Secondly, in mechanism driving part, considering the impact of rainfall on transmission tower, the rainfall correction coefficient is calculated to correct the failure probability of transmission tower through rainfall pressure model. Finally, Typhoon "Muifa", which landed in Zhoushan City, Zhejiang Province, is used for simulation verification. The results show that the proposed model is more consistent with the actual situation, and can be adopted to accurately predict the failure probability of transmission tower.