Air path and combustion controls coordination in diesel engine

The tightening of the diesel pollutants emissions regulations has made the performances obtainable from steady-state map controls, commonly employed in Internal Combustion Engine (ICE) management, unsatisfactory. To overcome these performance limitations, control systems have to cope with the engine transient operation conditions, coupling between its subsystem dynamics, and the trade-off between different requirements to efficiently manage the engine. The work demonstrates the deployment of a reference generator that coordinates the air path and combustion control systems of a turbocharged diesel engine for heavy-duty applications. The control system coordinator is based on neural networks and allows to exploit the best performance of the two control systems. The key idea is to generate air path targets, intake O
2
concentration and Intake MAnifold Pressure (IMAP), coherent with the ones of the combustion control system, engine load and engine-out Nitrogen Oxides (NOx). In this way, the air path control system provides the global conditions for the correct functioning of the engine, while, in cooperation, the combustion control will react to fast changes in the engine operating state and compensate for the remaining deviations with respect to load and NOx targets. Reference generator networks are suitable for further real-time implementation on rapid-prototyping hardware and their performance was overall good.