More and more stringent emission regulations require advanced control technologies for combustion engines. This goes along with increased monitoring requirements of engine behaviour. In case of emissions behaviour and fuel consumption the actual combustion efficiency is of highest interest. A key parameter of combustion conditions is the in-cylinder pressure during engine cycle. The measurement and detection is difficult and cost intensive. Hence, modelling of in-cylinder conditions is a promising approach for finding optimum control behaviour. However, on-line controller design requires real-time scenarios which are difficult to model and current modelling approaches are either time consuming or inaccurate.This paper presents a new approach of in-cylinder condition prediction. Rather than reconstructing in-cylinder pressure signals from vibration transferred signals through cylinder heads or rods this approach predicts the conditions. It is described what possible impacting parameters are used in order to virtually sense and simulate the in-cylinder conditions during an upcoming cycle. The modelling methods that are used in this context are artificial neural networks. The key parameters for modelling of in-cylinder pressure are identified as inputs and a network structure is trained with data generated from an engine model that is validated against data from a real medium-duty diesel engine. The resulting network can be used either for controller design or in case of available measurements for input as on-board monitoring and diagnostic tool. The resulting model structure shows some sufficient and promising correlation results.
In-Cylinder Pressure Modelling with Artificial Neural Networks
Sae Technical Papers
SAE 2011 World Congress & Exhibition ; 2011
2011-04-12
Aufsatz (Konferenz)
Englisch
In-Cylinder Pressure Modelling with Artificial Neural Networks
British Library Conference Proceedings | 2011
|Modelling and Control by Artificial Neural Networks
British Library Online Contents | 1992
|Application of artificial neural networks in engine modelling
Online Contents | 2004
|In-car modelling of emissions with dynamic artificial neural networks
Tema Archiv | 2001
|