Search Results

The calibration of Engine Control Units (ECUs) for road vehicles is challenged by stringent legal and environmental regulations, coupled with short development cycles. The growing number of vehicle variants, although sharing similar engines and control algorithms, requires different calibrations. Additionally, modern engines feature increasingly number of adjustment variables, along with complex parallel and nested conditions within the software, demanding a significant amount of measurement data during development. The current state-of-the-art (White Box) model-based ECU calibration proves effective but involves considerable effort for model construction and validation. This is often hindered by limited function documentation, available measurements, and hardware representation capabilities. This article introduces a model-based calibration approach using Neural Networks (Black Box) for two distinct ECU functional structures with minimal software documentation.

This paper will present a multi-domain (electrical and thermal) model of a three phase voltage source converter and its implementation in Modelica language. An averaged model is utilised for the electrical domain, and a power balance method is used for linking the DC and AC sides. The thermal domain focuses in deriving the converter losses by deriving the analytical equations of the space vector modulation to derive a function for the duty cycle of each converter leg. With this, the conduction and switching losses are calculated for the individual switches and diodes, without having to model their actual switching behaviour. The model is very fast to simulate, as no switching events are needed, and allows obtaining the simulation of the electrical and thermal behaviour in the same simulation package..