An intelligent vision system for monitoring and control of combustion flames

An intelligent vision system for the monitoring and control of combustion flames by combining image processing and neural network techniques is evaluated. Both geometrical and luminous parameters of an entire flame are determined over a specific luminuous region of the image on a dynamic basis. Based on these parameters, a neural network is constructed, which is capable of identifying a flame over a range of air and fuel flow rates. Finally, control algorithms are established based on the outputs of the network.