Abstract
The requirements in terms of harmonizing disparate engine characteristics are ever more demanding. Power and efficiency, dynamic response and exhaust emission quality are just four factors that need to be coordinated. To meet those requirements, engine functions and the associated calibration of the engine control models are increasingly complex. This applies in particular to one fundamental component of engine control: the air charge model. Without the use of powerful application tools, its exact calibration is no longer feasible. To manage this complexity Porsche Engineering has developed and applied an alternative method throughout the whole engine base calibration process, including thermodynamic engine optimization, employing a model-based approach. Two fundamental steps can define the core of this powerful calibration strategy: the inversion of the ECU logical path and the implementation of regression models based of modern computer algorithms, like machine learning. The optimization of engine thermodynamics characteristics is also part of this methodology because it relies also on mathematical models that predict the trades off trends between emissions, fuel consumption, torque and power when engine parameters are varied. Most of the ECU models within this project have been calibrate with this methodology and with the same set of measurements. The strategy has therefore proven to be very efficient and accurate.