基于GA GRNN数据挖掘的SCR脱硝系统建模优化研究

Research on Modeling Optimization of SCR Denitration System Based on GA GRNN Data Mining

火电厂选择性催化还原法(SCR)烟气脱硝系统是处理燃煤机组烟气排放NOx污染的主要途径,但该系统具有多输入变量、环境影响复杂、时变非线性等特征,因此建立准确的系统模型是SCR优化控制的基础。提出了一种融合遗传算法(GA)主元分析和广义回归神经网络(GRNN)数据挖掘的SCR系统建模方法。首先使用GA对运行数据进行变量选择优化计算;然后将最优变量作为GRNN的输入量,利用数据挖掘技术建立SCR系统数据模型。基于某电厂机组运行数据的实例分析表明,该方法建立的模型具有复杂度低、精度高、泛化能力强等优点。

The selective catalytic reduction(SCR)flue gas denitration system is the main way to deal with the pollution of NOx discharged from coal-fired units.The system has characteristics such as multiple input variables,complex environmental impact,and time-varying nonlinearity.Therefore,establishing an accurate system model is the basis of SCR system optimization control.A method to establish SCR system model based on genetic algorithm(GA)principal component analysis and generalized regression neural network(GRNN)data mining is proposed.Firstly,GA is used to optimize the calculation of variable selection.Then the optimal variable is used as the input of GRNN.The data model of SCR system is established by data mining.The example verification based on the running data of a power plant unit shows that the model established by this method has the advantages of low complexity,high precision and strong generalization ability.