Search Results

This paper describes a novel approach for modeling an automotive HVAC unit. The model consists of black-box models trained with experimental data from a self-developed measurement setup. It is capable of predicting the temperature and mass flow of the air entering the vehicle cabin at the various air vents. A combination of temperature and velocity sensors is the basis of the measurement setup. A measurement fault analysis is conducted to validate the accuracy of the measurement system. As the data collection is done under fluctuating ambient conditions, a review of the impact of various ambient conditions on the HVAC unit is performed. Correction models that account for the different ambient conditions incorporate these results. Numerous types of black-box models are compared to identify the best-suited type for this approach. Moreover, the accuracy of the model is validated using test drive data.

Reliably calibrated simulation and combustion models not only enable the prediction of non-validated operating points, but also compensate for the time that would be required for costly test bench measurements. Under the premise of investigating various turbocharging concepts for a combustion engine without the need for recalibration, the present work will discuss the influence of two different exhaust gas turbocharger systems on model calibration. Replacing turbochargers is a practical way to test the predictive performance of simulations, since they can drastically affect and change the thermodynamic boundary conditions for comparable operating points. On the one hand, the choice of the appropriate calibration strategy and, on the other hand, the interchangeability of the respective calibration will be discussed.