Search Results

Increasing the degrees of freedom in the air path has become a popular way to reduce the fuel consumption and pollutant emissions of modern combustion engines. That is why technical definitions will usually contain components such as multi or single-stage turbocharger, throttle, exhaust gas recirculation loops, wastegate, variable valve timing or phasing, etc. One of the biggest challenges is to precisely quantify the gas flows through the engine. They include fresh and burnt gases, with trapping and scavenging phenomena. An accurate prediction of these values leads to an efficient control of the engine air fuel ratio and torque. Fuel consumption and pollutant emissions are then minimized. In this paper, we propose to use an artificial neural network- based model as a prediction tool for the engine volumetric efficiency. Results are presented for a downsized turbocharged spark-ignited engine, equipped with inlet and outlet variable valve timing.

In the past few years, the increasing market penetration of downsized engines has reduced the pollutant emissions of internal combustion engines. The addition of a turbocharger to the air path has usually enabled the dynamic performances of the vehicles to be maintained. However, in the development process, deciding on the appropriate set of components is not straightforward and a lengthy fitting process is usually required to find the right turbocharger. Car manufacturers usually have access to a limited library of compressors and turbines which have actually been built and for which measurement campaigns have been carried out. This study is motivated by the need to extend the libraries available for simulation in order to provide a substantial increase in freedom in the matching process.

Data maps are easy to put in place and require very low calculation time. As a consequence they are often valued over fully physic-based models. This is particularly true when it is question of turbochargers. However, even if these maps are directly provided by the manufacturer, they usually do not cover the entire engine operating range and are poorly discretized. That's why before implementing them into any model they need to be interpolated and extrapolated. This paper introduces a new interpolation/extrapolation method based on the idea of integrating more physics into the widespread Jensen and Kristensen's method [6]. It essentially relies on the turbo machinery equation analysis performed by Martin during his PhD thesis [9, 10, 11] and the interpolation and extrapolation strategies that he proposed. In most cases the new strategies presented in this paper rely on improvements of the models he proposed.