MISSA-BPNN-Based Surrogate Model for Wind-Induced Stress Prediction in Vulnerable Regions of Transmission Towers

Contact sensor-based stress monitoring of transmission towers under strong winds is often limited by complex installation and maintenance procedures and the risk of local structural damage. With the development of non-contact displacement monitoring technologies, such as laser measurement and machine vision, this study proposes a wind-induced stress surrogate model for transmission towers using MISSA-BPNN, aiming to rapidly calculate stresses in vulnerable regions from macroscopic displacement responses. First, finite element analysis is conducted to investigate the wind-induced responses of a tower-line system under different operating conditions, identify vulnerable regions, and construct a dataset using displacement and stress responses. Then, a multi-strategy improved sparrow search algorithm (MISSA) is developed to optimize the initial weights and biases of the BP neural network, thereby establishing the MISSA-BPNN model. The constructed dataset is used to train the model and build the wind-induced stress surrogate model. Results show that the vulnerable regions are mainly located at the leeward tower foot and the middle-lower tower body. Compared with the conventional BPNN model, the proposed MISSA-BPNN surrogate model reduces the MAE, RMSE, and MAPE by 22.43–24.33%. This method provides a new approach for health monitoring of transmission lines under strong winds.