VEHICLE START-UP SIMULATION AND SUBJECTIVE COMFORT EVALUATION OF VIRTUAL DRIVE TRAIN BY MEANS OF NEW DRIVER MODELING TOOLS BASED ON ARTIFICIAL NEURAL NETWORKS

摘要

To be able to meet customer demands concerning comfortability, economical as well as ecological aspects, automotive industry has turned more and more interests to the subjective comfort evaluation. The goal of the project "Comfort objectification as an example of the vehicle start-up" involves an attempt to develop an understanding of vibration comfort as well as its entire drive train system during the product design. The main purpose of this study is to generate the virtual drive train by transferring the measured data from the drive tests into both the dynamic drive train test bench and the simulation models. The advantage gained by generating the virtual drive train is its ability to evaluate the dynamic properties of the future product in the early stage of the product development process. Consequently, some expensive prototypes and the subsequent drive tests can be partially replaced. It is also possible to modify any comfort-relevant parameters in the virtual drive train and follow the upcoming effects by evaluating the comfort rating from the customer feedbacks. An example of the drive train modeling can be illustrated during a start-up of the front-drive, middle class car. Different start-up characteristic features can vary according to the measured data gained from the drive tests. Longitudinal acceleration, engine throttle, power spectral density (PSD) and other predefined comfort-relevant characteristic input data can be generated. In this case, the developed clutch system with dual-mass flywheel will be inserted to the test bench. Using it in combination with the modified multi-body simulation models, the longitudinal vibration phenomena as well as their effects on the degree of comfortability can be investigated. In addition, the new driver modeling tools are developed on the basis of Artificial Neural Networks (ANNs) according to the way individual customers make their assessment. The user-friendly interface of these tools allows both advance users and engineers who still lack experience in the ANNs field to create different network structures during the training stage. The most suitable network structure for each application can be found automatically. The searching criterion is dependent on the performance of the estimation which ranges from 0 to 1. In the next step, another user-interface is used to objectify the comfort sensation from objective data derived from elaborated virtual drive train. Additionally, the developed tools are applied to verify and improve the quality of the drive train. In the long run, the satisfying comfort ratings should be obtained from the first prototypes.