基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模

吴磊; 顾华; 姚一鸣; 张军; 苏军; 陈依

doi:10.19666/j.rlfd.202502032

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模

热能科学研究 | 更新时间：2025-11-21

- 基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模
- Modeling of SCR denitrification reactor for thermal power units based on improved grey wolf optimization LSTM network
- 热力发电 2025年第11期页码：136-141
- 作者机构：
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目（61273190）;上海市电站自动化技术重点实验室资助项目（13DZ2273800）~~
- DOI：10.19666/j.rlfd.202502032
  中图分类号：
- 纸质出版：2025
- 稿件说明：
移动端阅览
吴磊, 顾华, 姚一鸣, 等. 基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模[J]. 热力发电, 2025,(11):136-141.

吴磊, 顾华, 姚一鸣, et al. Modeling of SCR denitrification reactor for thermal power units based on improved grey wolf optimization LSTM network[J]. Thermal Power Generation, 2025, (11): 136-141.
吴磊, 顾华, 姚一鸣, 等. 基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模[J]. 热力发电, 2025,(11):136-141. DOI： 10.19666/j.rlfd.202502032.

吴磊, 顾华, 姚一鸣, et al. Modeling of SCR denitrification reactor for thermal power units based on improved grey wolf optimization LSTM network[J]. Thermal Power Generation, 2025, (11): 136-141. DOI： 10.19666/j.rlfd.202502032.

摘要

针对传统机理建模方法预测选择性催化还原技术（SCR）脱硝反应器出口NO_x质量浓度精度不高的问题，提出了一种结合增强型灰狼优化算法（EGWO）与长短时记忆（LSTM）神经网络的混合预测模型。首先，基于主成分分析（PCA）对原始数据进行处理与筛选，实现输入变量的降维。然后，利用EGWO优化LSTM神经网络的超参数。最终，将输入变量作为EGWO-LSTM模型的输入，预测出口NO_x质量浓度。以国内某超超临界1 000 MW火电机组为例，仿真结果表明，该模型在误差控制方面表现最优，均方根误差较传统LSTM模型下降50.36%，较BP模型下降76.14%，模型平均绝对百分比误差仅为1.01%。EGWO相对于GWO收敛至最优解时的迭代次数更少，且具有更高的收敛精度。

Abstract

关键词

Keywords

references

柴有国,何晓燕,苏永健,等.考虑安全环保及补偿的火电机组调峰经济性研究[J].中国电力, 2021, 54(11):199-205.CHAI Youguo, HE Xiaoyan, SU Yongjian, et al.Economic study on peak shaving of thermal power units considering safety, environmental protection, and compensation[J]. Electric Power, 2021, 54(11):199-205.

许壮,康英伟.基于随机森林的火电机组SCR脱硝反应器建模[J].动力工程学报, 2020, 40(6):486-491.XU Zhuang, KANG Yingwei. Modeling of SCR denitrification reactor for thermal power units based on random forest[J]. Journal of Power Engineering, 2020,40(6):486-491.

张珑慧,林德海,王颖,等.机器学习在火电厂NOx减排中的应用综述[J].热力发电, 2023, 52(1):7-17.ZHANG Longhui, LIN Dehai, WANG Ying, et al.Overview of the application of machine learning in NOx reduction in thermal power plants[J]. Thermal Power Generation, 2023, 52(1):7-17.

张晓雯,向文国,陈时熠,等.基于小波去噪和PCAANFIS的SCR脱硝系统建模[J].热力发电, 2021,50(6):114-120.ZHANG Xiaowen, XIANG Wenguo, CHEN Shiyi, et al.Modeling of SCR denitrification system based on wavelet denoising and PCA-AFIS[J]. Thermal Power Generation,2021, 50(6):114-120.

徐圆圆,龚德鸿,邓传记,等. SCR反应器入口参数与反应温度对脱硝性能的交互作用[J].环境工程学报,2023, 17(11):3721-3729.XU Yuanyuan, GONG Dehong, DENG Chuanji, et al. The interaction between SCR reactor inlet parameters and reaction temperature on denitrification performance[J].Journal of Environmental Engineering, 2023, 17(11):3721-3729.

AN B, TANG M, QIU J, et al. Dynamic NOx prediction model for SCR denitrification outlet of coal-fired power plants based on hybrid data-driven and model ensemble[J]. Industrial&Engineering Chemistry Research, 2023, 62(36):14286-14299.

JUNJIE K, YUGUANG N, BO H, et al. Dynamic modeling of SCR denitration systems in coal-fired power plants based on a bi-directional long short-term memory method[J]. Process Safety and Environmental Protection,2021, 148(1):867-878.

李影,卓建坤,吴逸凡,等.可解释的变负荷下燃煤机组SCR反应器入口NOx质量浓度预测模型[J].热力发电, 2024, 53(7):119-128.LI Ying, ZHUO Jiankun, WU Yifan, et al. Explainable predictive model for NOx mass concentration at the inlet of SCR reactor in coal-fired power units under variable load[J]. Thermal Power Generation, 2024, 53(7):119-128.

陆必伟,李捷辉.基于GWO-LSTM的柴油机NOx排放预测[J].车用发动机, 2024(3):80-87.LU Biwei, LI Jiehui. Prediction of NOx emissions from diesel engines based on GWO-LSTM[J]. Automotive Engines, 2024(3):80-87.

董浩,李明星,张淑清,等.基于核主成分分析和极限学习机的短期电力负荷预测[J].电子测量与仪器学报,2018, 32(1):188-193.DONG Hao, LI Mingxing, ZHANG Shuqing, et al. Short term power load forecasting based on kernel principal component analysis and extreme learning machine[J].Journal of Electronic Measurement and Instrumentation,2018, 32(1):188-193.

胡阳,杨泽,房方,等.火电机组供电碳减排高维运行特征提取及其最优基准值确定[J].中国电机工程学报,2021, 41(增刊1):210-220.HU Yang, YANG Ze, FANG Fang, et al. High dimensional operation feature extraction and optimal benchmark value determination for carbon emission reduction in power supply of thermal power units[J]. Proceedings of CSEE,2021, 41(Suppl.1):210-220.

HOCHREITER S J, UUM L, SCHMIDHUBER R. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735.

吴磊,康英伟.基于改进粒子群优化长短时记忆神经网络的脱硫系统SO2预测模型[J].热力发电, 2021,50(12):66-73.WU Lei, KANG Yingwei. SO2 prediction model for desulfurization system based on improved particle swarm optimization long short-term memory neural network[J].Thermal Power Generation, 2021, 50(12):66-73.

MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advance in Engineering Software, 2014, 69:46-61.

左剑,张程稳,肖逸,等.基于灰狼优化算法的多机电力系统稳定器参数最优设计[J].电网技术, 2017,41(9):2987-2995.ZUO Jian, ZHANG Chengwen, XIAO Yi, et al. Optimal design of stabilizer parameters for multi machine power systems based on grey wolf optimization algorithm[J].Grid Technology, 2017, 41(9):2987-2995.

仝卫国,郭超宇,赵如意.基于变量选择和MGWOLSTM的浆液pH值预测[J].控制工程, 2024, 31(12):2140-2148.TONG Weiguo, GUO Chaoyu, ZHAO Ruyi. Prediction of pH value of slurry based on variable selection and MGWO-LSTM[J]. Control Engineering, 2024, 31(12):2140-2148.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于PCA-SVR的燃煤锅炉NO_x排放预测

掺烧氢/氨对煤粉锅炉NO_x排放的影响

300 MW燃煤锅炉掺烧氢气/氧气数值模拟

基于粒子群优化双支持向量机的SCR烟气脱硝效率预测模型

基于FOALSSVM的汽轮机热耗率预测模型研究