Prediction of NOx Emissions for a Range of Engine Hardware Configurations Using Artificial Neural Networks

Abstract

The predictive ability of artificial neural networks where a large number of experimental data are available, has been studied extensively. Studies have shown that ANN models are capable of accurately predicting NOx emissions from engines under various operating conditions and different fuel types when trained well. One of the major advantages of an ANN model is its ability to relearn when new experimental data is available, thus continuously improving its accuracy. The present work explored the potential of an ANN model to predict NOx emissions for various engine configurations outside its training envelop. This work also looked into quantifying the amount of new data required to improve the accuracy of the model when exposed to unknown conditions. The chosen ANN model was constructed using data from a high-speed direct injection diesel engine and is capable of accurate NOx emissions over a wide range of operating conditions. The optimized network utilized 14 input parameters and is using 6 neurons in a single hidden layer feed-forward neural network. Experimental data from the various engine configurations tested, were then used to predict NOx from the existing ANN model. The results indicate that when the new data are within the baseline training envelop, the ANN model is capable of accurate NOx prediction even when there are substantial changes in engine configuration such as piston material. Similar results were also observed when the injector nozzle is changed. However, the model’s performance drops significantly when new data, outside the baseline training envelop, were employed indicating that additional training is required. As such, various methods for retraining the ANN model were explored with the selected method showing the best compromise between new-data accuracy and old-data accuracy retention. The retrained ANN model developed was found to be an effective tool in predicting NOx emissions for different engine configurations and operating conditions.

Comparative Evaluation of Data-Driven Approaches to Develop an Engine Surrogate Model for NOx Engine-Out Emissions under Steady-State and Transient Conditions

“…Moreover, Papaiouannou [27] proposes a Random Forest algorithm to predict particulate emissions in a GDI engine. It is a simple model, easier to understand and less computationally expensive than deep neural networks.…”

A Random Forest Algorithmic Approach to Predicting Particulate Emissions from a Highly Boosted GDI Engine

“…Desantes et al as early as 2002, predicted NOx and soot from a Euro IV heavy duty diesel engine [20], showing strong correlations. Subsequent studies from different diesel engines of all sizes have shown that ANNs can be used predictively, particularly for NOx emissions [18,[21][22][23][24][25]. Studies using ML techniques for the prediction of emissions formation from gasoline engines, particularly GDI engines are sparse in the literature, and the authors are not aware of any studies which predict PM or PN emissions from GDI engines using ML techniques in the literature.…”