首页|基于CIFE-FOA-DELM的SCR脱硝入口NOx浓度预测方法研究

基于CIFE-FOA-DELM的SCR脱硝入口NOx浓度预测方法研究

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
针对脱硝入口NOx浓度监测值作为脱硝前馈输入导致的喷氨控制滞后问题，提出了基于炉膛参数的脱硝入口NOx浓度CIFE-FOA-DELM预测方法。采用互信息特征选择方法进行预测模型的特征变量筛选;引入经果蝇寻优算法优化的深度极限学习建立NOx浓度预测模型;并利用某660 MW火电机组历史运行数据进行模型验证，与反向传播、支持向量机、深度极限学习机、FOA-SVM模型的预测结果进行对比。结果表明:CIFE-FOA-DELM预测方法具备更高的预测精度，平均绝对百分比误差SMAPE、均方根误差SRMSE、拟合优度R2分别为0。261％、1。384、0。965。与CEMS监测数据对比，脱硝入口NOx浓度预测值提前了180 s，有利于解决喷氨控制滞后问题。
A CIFE-FOA-DELM method for predicting NOx concentration at the inlet of SCR denitration system
Aiming at the lag problem of ammonia injection control caused by the monitoring value of denitrification inlet NOx concentration as the feed-forward input of denitrification,the CIFE-FOA-DELM prediction method of denitrification inlet NOx concentration based on furnace parameters is proposed. A mutual information feature selection method is used to select feature variables for the prediction model;deep limit learning optimised by Drosophila optimisation algorithm is introduced to establish the NOx concentration prediction model;and the model is validated by using the historical operation data of a 660 MW thermal power unit,and the prediction results are compared with those of the back-propagation,support vector machine,deep limit learning machine,and FOA-SVM models. The results show that the CIFE-FOA-DELM prediction method has higher prediction accuracy,and the mean absolute percentage error (SMAPE),the root mean square error (SRMSE),and the goodness of fit (R2) are 0.261％,1.384％,and 0.965％,respectively,and the prediction of the denitrification inlet NOx concentration is 180 s ahead of schedule when compared with the CEMS data,which is conducive to solving the ammonia injection control lag problem. The problem of ammonia injection control lag is solved.

SCRNOx concentration at the denitrification inletcife-foa-delmmutual information feature selectiondrosophila optimization algorithmdeep extreme learning machineammonia injection control

董威、林子杰、王雅昀

展开 >

上海金艺检测技术有限公司,上海 200000

国家能源集团科学技术研究院有限公司,江苏 南京 210023

SCR 脱硝入口NOx浓度 CIFE-FOA-DELM 互信息特征选择 果蝇优化算法 深度极限学习机 喷氨控制

国家重点研发计划

2022YFC3701504

2024

10.19944/j.eptep.1674-8069.2024.03.011

电力科技与环保
国电科学技术研究院

电力科技与环保

影响因子：0.653
ISSN：1674-8069
年,卷(期)：2024.40(3)