Neurocomputing approach for the prediction of NOx emissions from CFBC in air-fired and oxygen-enriched atmospheres

Abstract

This paper presents a way of predicting NOx emissions from circulating fluidized bed combustors (CFBC) in air-fired and oxyfuel conditions, using the Artificial Neural Network (ANN) Approach. The Original Neural Networks Model was successfully applied to calculate the NOx (i.e. NO + NO2) emissions from coal combustion under air-fired and oxygen-enriched conditions in several CFB boilers. The ANN model was shown to give quick and accurate results in response to the input pattern. The NOx emissions, evaluated using the developed ANN model are in good agreement with the experimental results.