VISION-GUIDED FLAME CONTROL USING FUZZY-LOGIC AND NEURAL NETWORKS

This paper presents an application of fuzzy and neural network techniques to a vision-guided closed loop control for stationary luminous flames. The image processing technique is used to analyze and identify the process states. Fuzzy control strategy avoids the difficulty in establishing a mathematical model for an ill-defined process. Expert knowledge and training patterns can be incorporated into fuzzy rules, which are represented in the form of neurons. The use of a neural network makes it easy to increase the number of control parameters and provides the system the possibility to adjust its performance automatically.