大型电厂锅炉NOx排放特性的支持向量机模型

为了降低大型电厂锅炉NOx的排放,并对燃烧进行优化和控制,应用支持向量机算法建立了大型四角切圆燃烧电站锅炉NOx排放特性模型,利用NOx排放的热态实炉试验数据对模型进行了训练和校验,并对支持向量机算法模型中的参数g和C的选择进行了较深入的探讨,定性地分析了模型参数g和C的变化对模型预测能力的影响,获得了最佳的模型参数.利用该模型对不同实验工况下NOx的排放作出了预测,结果说明采用支持向量机算法建模达到了比较准确的预测效果,与其他建模方法相比具有泛化能力好、计算速度快的优点.

Support vector machine modeling on NOx emission property of high capacity power station boiler

In order to reduce the NO_x emission and optimize the burning process of high capacity power station boiler,a support vector machine model predicting the NO_x emission of a high capacity boiler was developed and verified with experimental data of NO_x emission characteristics of that boiler.How to select the model's parameter g and C was discussed,and the effects of these two parameters on model's performance were analyzed.Good predicting performance was achieved with the proper learning parameters.The modeling results showed that support vector machine is a good tool for building combustion models and has better generalization ability and higher calculation speed compared with other modeling approaches.