Monitoring and characterization of combustion flames by generalized Hebbian learning

Combustion plays a central role in our everyday life. Monitoring and control of combustion processes are important to satisfy environmental constraints, as well as to reach an optimal performance. This work describes the characterization of combustion flames by using artificial neural networks. Generalized Hebbian learning (GHL) is applied to extract the meaningful components from flames images; so that the operating conditions of the combustion process can be inferred by analyzing just few components. The experimental results demonstrate that GHL can effectively characterize the flame in terms of just few components. It was found that the second principal component is correlated with the airflow rate. These results can be applied to real time monitoring and control of combustion process