Identification of biomass co-combustion operating point using image processing

Thermal power and excess air coefficient are one of key parameters that characterize operating point of combustion process. In practice, they are hard to determine directly. The k-nearest neighbor (k-NN) regression algorithm was applied where some flame image geometric parameters were used as predictors. The model was assessed by carrying out several combustion tests for nine different settings of the laboratory combustion facility. Thermal power and excess air coefficient were kept constant and set independently for known biomass content.