Power Station Coal-fired Boiler Multi-objective Optimization Algorithm Research To

With the developing demand of environmental protection, power generators are being confronted with two requirements to reduce its operation costs and to lower its emissions. NOx emission is a main factor that has great impacts on the environment. Combustion optimization for the boilers in power station is required by reduce NOx and other pollutants emissions which based on ensure combustion efficiency.Aim at the complex properties of the boiler combustion system, such as multi-variables, close coupling, strong disturbances and long-time delay etc. In this paper, a support vector machine model is used to set up a boiler combustion response property model, parameters of the SVM model optimized by Genetic Arithmetic,best parameters were obtained and good predicting performance was achieved. Combined with the optimization of combustion characteristics, a new algorithm combin of reduction learning and incremental learning was presented. It discarded uselesss condition samples and kept the accuracy mean while reduced the training time. Optimized operating parameters are found in the model by use of Genetic algorithm, to meet the two requirements of hige efficiency and low NOx emission, a scheme with adjustable coefficient based on accmmondation function was put forward, thus the multi-objective optimized model can treated as a one-objective optimization problem.So that we can give guidance to boiler combustion adjustment and realize optimized operation of the boiler combustion system.The boiler combustion optimizing system was developed, applying the above theory to simulation studies and productive practice, the results show that the system based on these algorithms is effective, which can achieve optimum searching of high efficiency and low NOx combustion in the boiler.