Search Results

The trend to reduced development times represents a strong motivation for an extended use of dynamical engine test benches, which are used to reproduce driving conditions typically measured in the vehicle. To reproduce the engine load conditions a complex control system is used, which has an inherently different nature in comparison with the vehicle driving conditions and consequently also limitations. As a consequence, the set of possible transients is limited by the actuator limitations and the bandwidth of the control loops. Outside the admissible transients it is necessary to do a trade-off between goals, mainly between the precision of the reproduction of the engine speed and the precision of the load torque tracking. In this paper we discuss how to calculate the admissible set and how to do a trade off. Based on these cognitions we present a feedforward control algorithm which allows best performance transients simulation along the performance limits.

This paper deals with physical modelling of a turbocharger with variable turbine geometry (VTG) and its real-time simulation based on dynamic artificial neural networks (ANN). Thermodynamic und fluiddynamic equations, describing the basic functionality and relations between pressure, mass flow and temperature at the inlet and outlet ports of compressor and turbine, build up a multiple input multiple output model (MIMO). A special kind of ANN, namely the LoLiMoT algorithm, is used for real-time simulation. Training the network using measurement and simulated data, the dynamic behaviour can be simulated with less computational effort than the physical model. The neural network may be used in engine control systems as observer for non measurable signals, like rotor speed or turbine and compressor torque, figure 1.