Search Results

Emission requirements for diesel engines are becoming increasingly strict, leading to the increase of engine architecture complexity. This evolution requires a more systematic approach in the development of control systems than presently adopted, in order to achieve improved performances and reduction of times and costs in design, implementation and calibration. To this end, large efforts have been devoted in recent years to the application of advanced Model-Based MIMO control systems. In the present paper a new MIMO nonlinear feedback control is proposed, based on an innovative data-driven method, which allows to design the control directly from the experimental data acquired on the plant to be controlled. Thus, the proposed control design does not need the intermediate step of a reliable plant model identification, as required by Model-Based methods.

A real-time approach has been developed and assessed to control BMEP (brake mean effective pressure) and MFB50 (crank angle at which 50% of fuel mass has burnt) in a Euro 6 1.6L GM diesel engine. The approach is based on the use of feed-forward ANNs (artificial neural networks), which have been trained using virtual tests simulated by a previously developed low-throughput physical engine model. The latter is capable of predicting the heat release and the in-cylinder pressure, as well as the related metrics (MFB50, IMEP - indicated mean effective pressure) on the basis of an improved version of the accumulated fuel mass approach. BMEP is obtained from IMEP taking into account friction losses. The low-throughput physical model does not require high calibration effort and is also suitable for control-oriented applications. However, control tasks characterized by stricter demands in terms of computational time may require a modeling approach characterized by a further lower throughput.