Digital Engineering Modelling of Bogie Drives for EMU with Embedded Physical Constraint Networks

Prognostics and Health Management （PHM） plays an important role in the operation and maintenance process of Electric Multiple Units（EMU）, and in view of the lack of PDA of key components in the future moments of the current PHM system, propose a traction force prediction method for the bogie drive system under the framework of the Long Short-Term Memory （LSTM） network. The method is based on the comprehensive analysis of the traction prediction of bogie transmission system by the Wireless Transmission Device System （WTDS） of the train set. A digital engineering model is established for traction force prediction of the traction drive system of a moving train set. The calculation results show that the root-mean-square error between the predicted value and the real value of the actual traction force is 0.865, which is a better prediction of the traction force in the future, and it is of great significance to support the construction of a perfect digital engineering model for rolling stock.