Canadian Journal of Chemical Engineering, Vol.78, No.2, 408-417, 2000
Evaluation of an artificial neural network for NOx emission prediction from a transient diesel engine as a base for NOx control
For an adequate control of the reductant flow in selective catalytic reduction of NOx in diesel exhaust, a tool has to be available to predict accurately and fast the engine's NOx emission, in this article the application of a neural network is proposed. Measurements were performed on a transient diesel engine. The average absolute deviation between the measured NOx emission and the emission predicted by the neural network is 6.7%. The high accuracy of the neural network predictions, combined with the short computation times (0.2 ms/data point), makes the neural network a very promising tool in automotive NOx control.