Search Results

Both the rising number of electrical systems and the electrical part of the powertrain are considerably increasing the electrical power requirements of vehicles. As a consequence, multiple voltage supply levels have been introduced. However, even if only the 12V/48V configuration is considered, as in this paper, the number of possible electrical distribution system (EDS) architectures is greatly enlarged. Additional degrees of freedom are the allocation of the loads to the voltage levels, the dimensioning of new components, and the control strategy. Hence, the optimization of such architectures must be based on simulation, which allows the evaluation of a multitude of variants and test scenarios within an acceptable time frame. While strict cost, weight, and quality constraints must be upheld, the stability of the voltage supply is a major focus because a significant part of future electrical systems is highly safety-critical.

In the last two decades the abilities of neural networks as universal approximation tools of non linear functional relationships as well as identification tools for nonlinear dynamic systems have been recognized and used successfully in many applications areas like modelling, control and diagnosis of technical systems. At the same time an increasing interest in optimal design methods is observed. Design of experiment is used to cope with the growing amount of measurements needed for the calibration of engines due to the rising number of control variables to be considered and the need for more accuracy in the description of engine behaviour to derive the best control strategies. In this paper a strategy for the integration of the concept of D-optimality in the learning process of neural networks is proposed. This leads to an optimal selection of data to be presented to the training procedure of the neural network aiming to a generation of robust neural models using fewer training data.