Research on LSTM-based corrosion information prediction algorithm for sliding bed plate

The railroad switch is one of the most vulnerable components of railway tracks, and the slide bed bears the non-contact force of the train wheelset, serving as a crucial part of the switch. Due to constant exposure to harsh environmental conditions, the slide bed is susceptible to corrosion, leading to fractures and significantly reducing its lifespan. This issue poses a serious threat to the operational safety of high-speed trains. In this study, addressing the current deficiencies in corrosion detection methods, such as the use of approximate exponential functions, non-linearity, data disturbance, and complex trend changes in corrosion data due to salt spray, we employ the Long Short-Term Memory (LSTM) model to predict corrosion information on the slide bed. This approach provides a reliable method for predicting metal corrosion damage caused by salt spray. The results of the prediction model indicate that when using LSTM to predict four types of characteristic values, the error functions MSE, MAE, RMSE, and MAPE are all close to 0, demonstrating high prediction accuracy.