Multi-sensor Data Mining of Long-grouped Train Braking System Based on an LSTM Network

In this paper, an optimized model extended from single train braking predictive model is established. This model can use the data of past N
^th
trains to predict the train pipe output of (N + 1)
^th
train for long-grouped train braking system. The simulation results show that this model can predict the following time series data in accordance with the experimental results with high accuracy, which means that the model has good predictive performance. The test results can help build an intelligent semi-physical freight train braking platform with long-grouped numbers.