Research On Modeling And Optimization Of NO_x Emission Of A Running Unit In A Power Plant

Thermal power generation occupies an important position in China’s power industry,so the research on thermal power plants always attract much attention.Because coal is the main energy in China,most of thermal plants are coal-fired power stations.During the combustion of coal,it not only releases heat but also produces large amounts of pollutants,such as nitrogen oxides(NOx),sulfur dioxide(SO2)and so on.With the development of our society and economic,the environmental standards of our country are increasingly strict,so it is necessary to seek effective methods to reduce the pollution emission of power plant boilers.Because of the rising prices of coal,reducing the cost is an effective measure to improve the profit of power plants under the conditions of current mechanism of internet electricity price.Therefore,reducing operating cost and decreasing pollutant emissions are two requirements faced by power plants,which stimulates people to pay more attention to high efficiency and low NOx technology.In order to study the high efficiency and low NOx combustion technology for boiler,a model taking NOx emission and efficiency as output is established.The model is based on support vector machine regression(SVR).Particle swarm optimization algorithm(PSO)is used to search the optimal parameters of support vector machine,and the median impact value weight(MEIVW)method is used to weigh the input variables of the model.After using the above two methods,the accuracy of the model can be improved.Test data is used to test the model.The result shows that the model can predict NOx emission and boiler efficiency.Based on the above two models,taking NOx emission and boiler efficiency as optimization objectives,the control parameters of boiler air distribution as optimization variables,the multi-objective particle swarm optimization algorithm(MOPSO)had been used to optimize NOx emission and boiler efficiency.The optimization results show that reducing the NOx emission and improving the efficiency of the boiler is a contradictory optimization direction,which is in accordance with the results of the mechanism analysis.However,as for some serious conditions which deviate from normal operation,there is huge optimization potential.MOPSO algorithm can find the suitable operation parameters to ensure high efficiency and low NOx combustion.After using MOPSO algorithm,we get an optimization set.Using multi-objective optimization selection method based on economic benefit can choose the particle with the best economic benefit from Pareto solution which can be a guide for the operation of boiler.