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.

Current progress in the development of diesel engines substantially contributes to the reduction of NOx and Particulate Matter (PM) emissions but will not succeed to eliminate the application of Diesel Particulate Filters (DPFs) in the future. In the past we have introduced a Multi-Functional Reactor (MFR) prototype, suitable for the abatement of the gaseous and PM emissions of the Low Temperature Combustion (LTC) engine operation. In this work the performance of MFR prototypes under both conventional and advanced combustion engine operating conditions is presented. The effect of the MFR on the fuel penalty associated to the filter regeneration is assessed via simulation. Special focus is placed on presenting the performance assessment in combination with the existing differences in the morphology and reactivity of the soot particles between the different modes of diesel engine operation (conventional and advanced). The effect of aging on the MFR performance is also presented.