Prediction of NOx emissions throughflame radical imaging and neural network based soft computing

Abstract

The characteristics of reacting radicals in a flame are crucial for an in-depth understanding of the formation process of combustion emissions. This paper presents an algorithm for the prediction of NOx (NO and NO2) emissions in flue gas through flame radical imaging, flame temperature monitoring and application of Neural Network techniques. Radiation images of flame radicals OH*, CN*, CH* and C2* are captured using an intensified multi-wavelength imaging system. Flame temperature is determined using a spectrometer and two-color pyrometry. Based on these images, the characteristic values of the flame radicals are extracted. These characteristic values, together with the flame temperature, are then used to predict NOx emissions. Experimental results from a laboratory-scale gas-fired combustion rig have shown the effectiveness of the proposed method for the prediction of NOx emissions.