In order to predict the mass concentration of NOx at outlet of the SCR denitrification system of coal-fired units

a dynamic modeling method for SCR denitrification system combining the extreme learning machine(ELM) with genetic algorithm(GA) is proposed in this paper. To avoid the influence of input weight matrix and random deviation of hidden layer on the ELM

the GA was adopted to optimize the input weight and hidden layer deviation of the ELM

and the SCR denitrification system model based on GA-ELM was established.Moreover

the GA-ELM model was verified by actual operation data of the SCR denitrification system of a coal-fired power plant

and the results were compared with that predicted by least squares support vector machine(LSSVM) model and the ELM model. The results show that

the GA-ELM model has the highest prediction accuracy and the stronges generalization ability

which can effectively predict the mass concentration of NOx at the SCR denitrification system outlet.