Estimation of NOx emissions in thermal power plants using neural networks

In this paper a neural network-based strategy is proposed for the estimatio n of the NOx emissions in thermal powerplants, fed with both oil and methan e fuel. A detailed analysis based on a three-dimensional simulated of the c ombustion chamber has pointed out the local nature of the NOx generation pr ocess, which takes place mainly in the burners' zones. This fact has been s uitably exploited in developing a compound estimation procedure, which make s use of the trained neural network together with a classical one-dimension al model of the chamber. Two different learning procedures have been invest igated, bath based on the external inputs to the burners and a suitable mea n cell temperature, while using local and global NOx flow rates as learning signals, respectively. The approach has been assessed with respect to both simulated and experimental data.