A main focus of development in modern SI engine technology is variable valve timing, which implies a high potential of improvement regarding fuel consumption and emissions. Variable opening, period and lift of inlet and outlet valves enable numerous possibilities to alter gas exchange and combustion. However, this additional variability generates special demands on the calibration process of specific engine control devices, particularly under cold start and warm-up conditions.
This paper presents procedures, based on Hardware-in-the-Loop (HiL) simulation, to support the classical calibration task efficiently. An existing approach is extended, such that a virtual combustion engine is available including additional valve timing variability.
Engine models based purely on physical first principles are often not capable of real time execution. However, the definition of initial parameters for the ECU requires a model with both real time capability and sufficient accuracy. Therefore, new approaches are necessary, which combine physical and neuronal network models. Neural networks can predict the response of a real physical system to varying input conditions once they have received adequate training. This enables one to describe the engine behavior due to valve variability in extreme transient and non-linear conditions.
This paper presents such an approach, which is verified by example of cold start and warm-up behavior of a reference engine with advanced valve train variability.