Subjective evaluation and modeling of human ride comfort of electric vehicle using tools based on artificial neural networks

Abstract

This article presents an application of the human comfort objectification tool developed based on the Artificial Neural Networks (ANNs) to support the development of drive train system. The main objective of this study is to apply the developed tool to predict the subjective comfort rating of different driver types during the start-up procedure, i.e. the process of starting to drive from standstill with releasing of the brake and reaching of constant travel speed. In this case, test drives performed by drivers representing potential customers are carried out with a commercial electric vehicle. The subjective evaluation in terms of customer satisfaction is executed based on the 5-digit scale. During the experimental investigation, the predefined objective parameters are captured. They are the resulting longitudinal acceleration measured at the different locations of the driver seat, the vehicle velocity, the vehicle acceleration as well as the standardized courses of the accelerator pedal and the brake pedal. The human sensation modeling is carried out by determination of the relationship between the objective parameters, like the power spectral density (PSD) values of the longitudinal acceleration captured at passenger seat and the subjective comfort ratings. An ANN is applied to interconnect output data (subjective rating) with input data (objective parameters) by "trained" weighted network connections. The results of the investigation have demonstrated that the objective values are efficiently correlated with the subjective sensation. Thus, the presented approach can be effectively applied to support the drive train development of electric vehicle. © Springer-Verlag 2013.