Search Results

As an important means of engine development and optimization, modelbuilding plays an increasingly important role in reducing carbon dioxide emissions of the internal combustion engines (ICEs). However, due to the non-linearity and high dimension of the engine system, a large amount of data is required to obtain high model accuracy. Therefore, a modelling approach combining the experimental data and prior knowledge was proposed in this study. With this method, an artificial neural network (ANN) model simulating the engine brake specific fuel consumption (BSFC) was established. With mean square error (MSE) and Kullback-Leibler divergence (KLD) serving as the fitness functions, the 86 experimental samples and constructed physical models were used to optimize the ANN weights through genetic algorithms.

Particulates and nitrogen oxides comprise the main emission components of the Diesel combustion and therefore are subject to exhaust emission legislation in respective applications. Yet, with ever more stringent emission standards and test-procedures, such as in passenger vehicle applications, resulting exhaust gas after-treatment systems are quite complex and costly. Hence, new technologies for emission control have to be explored. The application of non-thermal plasma (NTP) as a means to perform exhaust gas after-treatment is one such promising technology. In several publications dealing with NTP exhaust gas after-treatment the plasma state was generated via dielectric barrier discharges. Another way to generate a NTP is by a corona high-frequency discharge. Hence, in contrast to earlier publications, the experiments in this publication were conducted on an operated series-production Diesel engine with an industrial pilottype corona ignition system.