Prediction of pollutant emissions of biomass flames using digital imaging, contourlet transform and Radial Basis Function network techniques

This paper presents a method for the prediction of NOx emissions in a biomass combustion process through the combination of flame radical imaging, contourlets transform, and radial basis function network techniques. The images of four flame radicals (OH*, CN*, CH* and C2*) are captured using a spectroscopic imaging system. The features of the images are then identified based on the best M-term approximation of contourlet coefficients. The relationships between the features of radical images and NOx emissions are finally established through the use of the Radical Basis Function network. The test results obtained on a biomass-gas fired test rig show the effectiveness of the proposed technical approach for the prediction of NOx emissions.