Search Results

In order to offer a wide range of driving experiences to their customers, original equipment manufacturers implement different driving programs. The driver is capable of manually switching between these programs which alter drivability parameters in the engine control unit. As a result, acceleration forces and gradients are modified, changing the perceived driving experience. Nowadays, drivability is calibrated iteratively through road testing. Hence, the resulting set of parameters incorporated within the engine control unit is strongly dependent on the individual sentiments and decisions of the test engineers. It is shown, that implementing a set of objective criteria offers a way to reduce the influences of personal preferences and sentiments in the drivability calibration process. In combination with the expertise of the test engineers, the desired vehicle behavior can be formalized into a transient set point sequence to give final shape to the acceleration behavior.

In this investigation two different nonlinear dynamic black box modelling approaches are compared. The purpose of the models is to reproduce the transient gearshift process. The models are used to compute the torque at the sideshafts, which is highly correlated to the gearshift comfort. The first model is a Gaussian process (GP) model. The GP is a probabilistic, non-parametric approach, which is additionally capable to compute the confidence interval of the simulated output signal. The second black box model uses the artificial neural net (ANN) approach. In addition to training algorithms the resulting model configurations for both black box approaches are shown in this investigation. Furthermore the empirical error of both modeling approaches is compared to the predictive variance of the GP model and to the intrinsic uncertainty of the gearshift process.