Abstract: Neural network and genetic algorithm have been extensively used in boiler combustion optimization problems. But the traditional Back Propagation neural network's generalization ability is poor. The Bayesian regularization can improve the neural network's generalization ability. A boiler combustion multi-objective optimization method combining Bayesian regularization BP neural network and genetic algorithm （Bayes NN-GA）was researched. A number of field test data from a boiler was used to simulate the Bayesian neural network model. The results show that the thermal efficiency and NOx emissions predicted by the Bayesian neural network model show good agreement with the measured, and the optimal results show that hybrid algorithm by combining Bayesian regularization BP neural network and genetic algorithm can be a good tool to solve the problem of multi-objective optimization of a coal-fired combustion, which provide a theory guidance for the boiler operation in an economic and environmental way.

Key words: boiler, combustion optimization, Bayesian regularization, neural network, genetic algorithm, multi-objective optimization