This article considers the application and refinement of artificial neural network methods for the prediction of NO _x emissions from a high-speed direct injection diesel engine over a wide range of engine operating conditions. The relative computational cost and performance of two backpropagation algorithms, Levenberg–Marquardt and Bayesian regularization, for this application are compared, with the Levenberg–Marquardt algorithm demonstrating a significant cost advantage. This work also assesses the performance of two alternative filtering approaches, a p-value test and the Pearson correlation coefficient, for reducing the required number of input variables to the model. The p-value test identified 32 input parameters of significance, whereas the Pearson correlation test highlighted 14 significant parameters while additionally providing a ranking of their relative importance. Finally, the article compares the predictive performance of the models generated by the two filtering methods. Overall, both models show good agreement to the experimental data with the model created using the Pearson correlation test showing improved performance in the low-NO _x region.

A novel combustion modelling approach is proposed here to study the transient effects of diesel spray. Conditional Source-term Estimation (CSE) is a combustion model which invokes the Conditional Moment Closure (CMC) hypothesis to provide an approximation of the mean chemical source term in an averaged transport equation. Unlike CMC, where transport equations are solved for conditional moments, CSE recovers these conditional moments through the solution of an inverse problem. Integral equations are inverted for the conditional moments, by assuming spatial homogeneity in the conditional averages where Tikhonov regularisation is applied. Previous CSE studies have shown that the model is able to predict the flame characteristics successfully for both premixed and non-premixed combustion modes. However, most of these investigations were based on methane flames. This study will be the first successful application of CSE to a complex hydrocarbon fuel, n-dodecane, under the Engine Combustion Network's (ECN) ‘Spray A’ conditions. Detailed chemistry is included in tabulated form using the Flamelet Generated Manifold (FGM) methodology. The predictions of this study include both the Favre averaged conditional mass fraction of reactive species and temperature. The results are compared with available experimental data and previous numerical results. Both RANS and LES simulations are performed under the same condition. The objectives of the paper are (i) assessment of the application of CSE on igniting diesel spray (ii) comparison of the CSE numerical results with available experimental results and previous numerical simulations. Overall, the combination of a chemical mechanism that has been tuned to predict ‘Spray A’ conditions with the CSE-FGM model is able to successfully predict autoignition delay time and lift-off length of n-dodecane spray within the scatter of the experimental data. CSE-FGM offers a feasible tool for detailed combustion analysis of diesel spray flames. Both RANS and LES can give reasonably good global predictions of the flame.

The understanding and prediction of NO_x emissions formation mechanisms during engine transients are critical to the monitoring of real driving emissions. While many studies focus on the engine out NO_x formation and treatment, few studies consider cyclic transient NO_x emissions due to the low time resolution of conventional emission analysers. Increased computational power and substantial quantities of accessible engine testing data have made ANN a suitable tool for the prediction of transient NO_x emissions. In this study, the transient predictive ability of artificial neural networks where a large number of engine testing data are available has been studied extensively. Significantly, the proposed transient model is trained from steady-state engine testing data. The trained data with 14 input features are provided with transient signals which are available from most engine testing facilities. With the help of a state-of-art high-speed NO_x analyser, the predicted transient NO_x emissions are compared with crank-angle resolved NO_x measurements taken from a high-speed light duty diesel engine at test conditions both with and without EGR. The results show that the ANN model is capable of predicting transient NO_x emissions without training from crank-angle resolved data. Significant differences are captured between the predicted transient and the slow-response NO_x emissions (which are consistent with the cycle-resolved transient emissions measurements). A particular strength is found for increasing load steps where the instantaneous NO_x emissions predicted by the ANN model are well matched to the fast-NO_x analyser measurements. The results of this work indicate that ANN modelling could strongly contribute to the understanding of real driving emissions.