Search Results

With ever stricter legislative requirements for CO2 and other exhaust emissions, significant efforts by OEMs have launched a number of different technological strategies to meet these challenges such as Battery Electric Vehicles (BEVs). However, a multiple technology approach is needed to deliver a broad portfolio of products as battery costs and supply constraints are considerable concerns hindering mass uptake of BEVs. Therefore, further investment in Internal Combustion (IC) engine technologies to meet these targets are being considered, such as lean burn gasoline technologies alongside other high efficiency concepts such as dedicated hybrid engines. Hence, it becomes of sound reason to further embrace diversity and develop complementary technologies to assist in the transition to the next generation hybrid powertrain. One such approach is to provide increased valvetrain flexibility to afford new degrees of freedom in engine operating strategies.

Nitrogen oxides emissions are an important aspect of engine design and calibration due to increasingly strict legislation. As a consequence, accurate modeling of nitrogen oxides emissions from Diesel engines could play a crucial role during the design and development phases of vehicle powertrain systems. A key step in future engine calibration will be the need to capture the nonlinear behavior of the engine with respect to nitrogen oxides emissions within a rapid-calculating mathematical model. These models will then be used in optimization routines or on-board control features. In this paper, an artificial neural network structure incorporating a number of engine variables as inputs including torque, speed, oil temperature and variables related to fuel injection is developed as a method of predicting the production of nitrogen oxides based on measured test data. A multi-layer perceptron model is identified and validated using data from dynamometry tests.