Boiler combustion control model of large-scale coal-fired power plant with asymmetric artificial neural networks

摘要

Key problems in coal-fired boiler combustion modeling were discussed in large-scale power plants. An asymmetric artificial neural network (ANN) model is proposed, where general forward multilayer ANN model structure is transformed to the domestic problems. Which greatly reduces the demands for the number of modeling samples. The comparison results show that the proposed model is more effective than the classical ones. It was applied on optimization of the combustion control in a 660MW supercritical boiler and good performances had been observed.