NO_x emission prediction based on flame radical profiling and support vector machine

Characteristics of reacting radicals in a flame are crucial for an in-depth understanding of the formation process of combustion emissions. An algorithm for the prediction of NO_x (NO and NO₂) emissions in flue gas was presented through flame radical imaging, flame temperature monitoring and application of soft computing techniques, support vector machine. Radiation images of flame radicals OH*, CN*, CH* and C₂* were captured using an intensified multi-wavelength imaging system. Flame temperature was determined using a spectrometer and two-color pyrometry. Based on these images, the characteristic values of the flame radicals were extracted. These characteristic values (contours and ratios of radical intensities), together with the flame temperature, were then used to predict NO_x emissions. Experimental results from a laboratory-scale gas-fired combustion rig show the effectiveness of the proposed method for the prediction of NO_x emissions.