Research on ride comfort evaluation method of EMU based on CART algorithm

In this paper, the research team presents the findings of long-term tracking tests on power-centralized EMU. The results demonstrate clear discrepancies between the established ride comfort evaluation results and the actual vibration state of the vehicle body and the subjective experiences of the drivers and passengers. A fuzzy evaluation was employed to establish the data set, while the entropy weight method was used to determine the key indexes. The CART decision tree algorithm was then used to establish a model for the evaluation of ride comfort in power-centralized EMU. The resulting evaluation was verified through dynamic simulation and field testing. The findings of the research demonstrate that: The lateral ride index can be employed as the primary index for evaluating the vibration state of the vehicle. By implementing three consecutive lateral ride comfort evaluations of the vehicle, the false positive rate and false negative rate can be maintained below 4%. The accuracy of the evaluation results is greater than 95% when a CART decision tree model is constructed using the minimum, maximum, standard deviation, and 50th percentile of the lateral ride index of the vehicle. The results of the simulation and field tests demonstrate that the ride comfort evaluation results are highly consistent with the actual vibration state of the moving EMU, the annoyance rate, and the human subjective feeling. This paper presents a comprehensive analysis of the research content, taking into account the subjective experiences of drivers and passengers, as well as the practical considerations of railway maintenance personnel. The findings offer a valuable contribution to the decision-making process of railway maintenance professionals.