基于核极限学习机的电厂锅炉NO_x排放建模与预测  

Modeling and Forecasting of Boiler NO_x Emissions from Power Plants Based on New Grey Wolf Optimization Algorithm

作　　者：李俊甫 吕红芳[1] 何力 俞立春 

机构地区：[1]上海电机学院电气学院,上海201306

出　　处：《工业控制计算机》2018年第9期85-86,89,共3页Industrial Control Computer

摘　　要：为了能够准确地预测电厂锅炉的NO_x排放量质量浓度,以某电厂330 MW亚临界循环流化床锅炉为研究对象,利用灰狼优化算法(GWO)和核极限学习机(KELM)进行综合建模,并将该模型的预测值与基本极限学习机、粒子群算法和风驱动算法优化的极限学习机模型预测值进行比较。结果表明:新的双种群灰狼算法(DGWO)可以更好地找到优化参数,同时新的核极限学习机模型具非常良好的预测精度和泛化能力,可以准确、高效地预测电站锅炉的NO_x排放量。In order to accurately predict the NOx emission mass concentration of power plant boilers,a 330 MW subcritical CFB boiler from a power plant is used as the research object,using the Grey Wolf Group Optimization（GWO） Algorithm and the Kernel Extreme Learning Machine（KELM）.Comprehensive modeling,and comparing the predicted values of this model with the basic limit learning machine,particle swarm optimization and wind driven algorithm optimization limit machine model prediction results.The results show that the new dual population gray wolf Optimization（DGWO） algorithm can be better.

关 键 词：NOX排放 循环流化床锅炉 核极限学习机 灰狼优化算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] X773[自动化与计算机技术—控制科学与工程]