Search Results

A calibration and validation workflow will be presented in this paper, which utilizes common static global models for fuel consumption, NOx and soot. Due to the applicability for warm-up tests, e. g. New European Driving Cycle (NEDC), the models need to predict the temperature influence and will be fitted with measuring data from a conditioned engine test bed. The applied model structure - consisting of a number of global data-based sub-models - is configured especially for the requirements of multi-injection strategies of common rail systems. Additionally common global models for several constant coolant water temperature levels are generated and the workflow tool supports the combination and segmentation of global nominal map with temperature correction maps for seamless and direct ECU setting.

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.