Research on LightGBM Algorithm for Subway Gate Fault Detection

The application of intelligent algorithms in the field of subway gate fault detection is increasingly showing its unique advantages. Aiming at the problem that subway gates are susceptible to various factors and fail in a complex environment for a long time, this study designed a subway gate fault detection model based on the LightGBM algorithm and the Gray Wolf Optimization Algorithm. The study first analyzed the types and causes of subway gate failures, and then used the LightGBM algorithm to construct a subway gate fault detection model. To further improve the performance of the model, the Gray Wolf Optimization was introduced to optimize the hyperparameters of the LightGBM. The fault detection model constructed in the study has an accuracy rate of up to 99.5% for subway gate fault detection. This shows that the method proposed in the study has a significant effect on improving the accuracy and robustness of subway gate fault identification, and can provide effective technical support for the health management of the same type of subway equipment.