Prediction of transmission line temperature based on improved genetic neural network

Transmission lines play an important role in social production and development, so it is very important to detect the safety of transmission lines. In this paper, GANN and attentional mechanism is introduced to predict the temperature of transmission lines. simulation data containing characteristics such as ambient temperature, humidity and solar radiation are generated, and the temperature of the transmission line is calculated. the data is preprocessed using standardization techniques and feature selection is performed using LassoCV. In order to optimize the structure and hyperparameters of the neural network, genetic algorithm is introduced to optimize the neural network model generation by generation through the steps of population initialization, fitness calculation, selection, crossover and variation. In the neural network, an attention mechanism is added to enable the model to automatically focus on the features that are most important to the prediction. In the prediction stage, the individual with the best fitness is selected as the final model, and the model is evaluated by MSE, $R^{2}$ and MAE. The experimental results show that the improved genetic neural network model combined with the attention mechanism can predict the temperature of the transmission line more effectively, with higher accuracy and stability.