基于KPCA和模糊树模型的火电厂SCR脱硝系统建模  

Modeling of SCR Denitrification System in Thermal Power Plant Based on KPCA and Fuzzy-Tree Model

作　　者：李海军 夏静 史恒惠 王梓齐 LI Hai-jun;XIA Jing;SHI Heng-hui;WANG Zi-qi(Technical information center of Henan Electric Power Co.,Ltd.,Zhengzhou 450001 China;School of Control and Computer Engineering,North China Electric Power University,Baoding 071000 China)

机构地区：[1]国家电投集团河南电力有限公司技术信息中心,河南郑州450001 [2]华北电力大学控制与计算机工程学院,河北保定071000

出　　处：《自动化技术与应用》2020年第1期21-25,共5页Techniques of Automation and Applications

摘　　要：为了建立精确的火电厂选择性催化还原(SCR)脱硝系统模型,提出了一种基于核主成分分析(KPCA)和模糊树模型的建模方法。首先,对SCR脱硝系统的工艺流程及反应机理进行了分析;之后,以某600MW燃煤机组的变工况运行数据为例,确定了模型的输入变量并应用KPCA进行了特征提取;最后,基于模糊树模型建立了SCR脱硝系统的模型。结果表明,基于模糊树模型建立的SCR脱硝系统模型的精度较高、泛化能力强且训练速度快;在使用KPCA进行特征提取后,进一步缩短了训练的时间且对精度的影响不大。In order to establish an accurate selective catalytic reduction(SCR)denitration system model of thermal power plant,a modeling method based on kernel principal component analysis(KPCA)and fuzzy-tree model is proposed.First,the process and reaction mechanism of SCR denitration system are analyzed.Then,taking the variable condition operation data of a 600 MW coal-fired unit as an example,the input variables of the model are determined and the features are extracted by KPCA.Finally,the model of SCR denitrification system is built based on fuzzy-tree model.The results show that the model of SCR denitration system based on fuzzy-tree model has high accuracy,strong generalization ability and fast training speed.After feature extraction by using KPCA,the training time is further shortened,and the accuracy has little effect.

关 键 词：模糊树模型 核主成分分析 SCR脱硝系统 变工况 

分 类 号：TM743[电气工程—电力系统及自动化]