Research on Operational State Monitoring of Maglev Train Based on Machine Learning

摘要

Maglev train is a modern rail vehicle with low energy consumption, low noise and high comfort. Due to the monitoring of the running state of the train during the operation and commissioning of the maglev train, there are some problems, such as large amount of data to be processed, long time spent, poor real-time performance, and low accuracy of monitoring. There are many stages of changes in the state of the train during normal operation, and abnormal operating conditions may occur. The data obtained by the sensors in different states have significant distinguishing characteristics, so the data collected by the maglev train suspension control system can be used to train the machine learning model, and then based on the data to determine the actual running state of the maglev train, can facilitate the debugging work of the train during operation. If the state of the train operation can achieve the effect of real-time monitoring, the suspension control system of the maglev train can adjust the control strategy according to the current running state, so that the control effect of the train can reach a better state.