燃煤锅炉低氮氧化物燃烧特性的神经网络预报

大型燃煤电站锅炉的低NO_x燃烧技术日益受到关注,但NO_x的排放特性复杂,受煤种、锅炉设计结构和操作参数等多种因素影响.在对某台600MW四角切圆燃煤电站锅炉的NO_x排放特性和飞灰含碳量特性进行多工况热态测试的基础上,应用人工神经网络的非线性动力学特性及自学习特性,建立了大型四角切圆燃烧锅炉NO_x排放特性和燃烧经济性的神经网络模型,并对此模型进行了校验.结果表明,该模型能根据燃煤特性及各种操作参数准确预报锅炉在不同工况下的NO_x排放和飞灰含碳量特性,可为大型电站锅炉通过燃烧调整降低NO_x排放和提高锅炉燃烧效率提供有效手段.

Predicting Low NOx Combustion Property of a Coal-Fired Boiler

More attention was paid to the low NO_x combustion property of the high capacity tangential firing boiler, but the NO_x emission and unburned carbon content in fly ash of coal burned boiler were complicated, they were affected by many factors, such as coal character, boiler's load, air distribution, boiler style, burner style, furnace temperature, excess air ratio, pulverized coal fineness and the uniformity of the air and coal distribution, etc. In this paper, the NO_x emission property and unburned carbon content in fly ash of a 600MW utility tangentially firing coal burned boiler was experimentally investigated, and taking advantage of the nonlinear dynamics characteristics and self learning characteristics of artificial neural network, an artificial neural network model on low NO_x combustion property of the high capacity boiler was developed and verified. The results illustrated that such a model can predicate the NO_x emission concentration and unburned carbon content under various operating conditions, if combined with the optimization algorithm, the operator can find the best operation condition of the low NO_x combustion.