Nitrogen oxide emission modeling for boiler combustion using accurate online support vector regression

Abstract

Using the data of boiler combustion, an accurate online support vector regression (AOSVR) model of the Nitrogen Oxide (NOx) emission property is built. After the training and the testing, the result shows that AOSVR is a good tool for modeling with small sample data, compared with the method of SVR and artificial neural network (ANN). The model can estimate the NOx emission accurately under different conditions when the load or other parameters changes. The accuracy of this model can also meets the demand of the combustion optimization. The result shows that this new model has a good learning efficiency and prediction accuracy because the algorithm can update the parameters of the model by itself as time and other parameters change.