Predictive control of NO_x emission from flue gas of utility boilers has important influence on power plants' economic benefits and environmental pollution control. To improve the accuracy of the NO_x emission prediction model

a modeling method of boiler NO_x emission based on multi-model clustering ensemble was proposed. In this method

the data space is firstly divided according to the level of NO_x emission

and the variables that participate in clustering are determined by using the variable weight based on relevant analysis and hierarchical clustering utilized information entropy. Then

the proposed algorithm VMSC is used to obtain the new membership degree matrix of each subspace. Finally

the multiple least squares support vector machine(LS-SVM) model of each subspace is integrated by the least-squares method fused membership degree. The simulation results show that

the VMSC algorithm integrating the soft fuzzy C-means clustering(SFCM) with the genetic algorithm-soft fuzzy clustering(GA-SFCM) improves the accuracy of the clustering

and the simulation performance is better than the single model.