基于LSTM网络的掺氨燃烧SCR脱硝控制

刘渊; 崔立明; 施梁; 李明; 刘平; 周末; 王文海; 范燕荣; 周黎明; 王印松

doi:10.19805/j.cnki.jcspe.2026.250032

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于LSTM网络的掺氨燃烧SCR脱硝控制

数字化与智能化 | 更新时间：2026-10-10

- 基于LSTM网络的掺氨燃烧SCR脱硝控制
- SCR Denitration Control for Ammonia Doped Combustion Based on LSTM Network
- 动力工程学报 2026年46卷第5期页码：127-136
- 作者机构：
  
  1. 华北电力大学自动化系,河北,保定,071003
  2. 神华集团有限责任公司,北京,100011
  3. 国能粤电台山发电有限公司,广东,江门,529228
  4. 烟台龙源电力技术股份有限公司,山东,烟台,264006
- 作者简介：
  
  刘渊(2001—),男,甘肃天水人,硕士研究生,研究方向为掺氨燃烧相关系统的建模与控制,E-mail:220232216042@ncepu.edu.cn
- 基金信息：
  
  国家科技支撑资助项目 (GJNY-2023-9)
- DOI：10.19805/j.cnki.jcspe.2026.250032
  中图分类号： X701
- 纸质出版：2026
- 稿件说明：
移动端阅览
刘渊, 崔立明, 施梁, 李明, 刘平, 周末, 王文海, 范燕荣, 周黎明, 王印松. 基于LSTM网络的掺氨燃烧SCR脱硝控制[J]. 动力工程学报, 2026, 46(5): 127-136.
刘渊, 崔立明, 施梁, 李明, 刘平, 周末, 王文海, 范燕荣, 周黎明, 王印松. 基于LSTM网络的掺氨燃烧SCR脱硝控制[J]. 动力工程学报, 2026, 46(5): 127-136. DOI： 10.19805/j.cnki.jcspe.2026.250032.

DOI： 10.19805/j.cnki.jcspe.2026.250032

摘要

针对传统燃煤机组碳排放量大、环境污染较为严重等问题

深入研究了煤氨混合燃烧技术在减排降污方面的潜力

探讨了NOx生成机理

构建了一种SCR脱硝系统入口NOx

并基于此提出SCR脱硝系统的控制方法。首先

通过分析掺氨燃烧过程中NOx的生成机理

确定影响NOx浓度变化的特征变量

利用主元分析法优化特征变量

建立长短期记忆(LSTM)网络预测模型

并利用结合退火思想的粒子群算法 (SA-PSO算法) 优化模型结构参数

提高SCR入口NOx浓度预测的准确性;其次

基于预测模型设计了一种SCR脱硝系统的前馈-串级控制方法

并与其他传统控制方法进行比较;最后

利用某电厂600 MW燃煤机组在100%负荷、掺氨10%工况下与50%负荷、掺氨20%工况下的运行数据进行仿真验证。结果表明:所构建的预测模型能够有效地预测SCR脱硝入口NOx浓度

为脱硝系统的控制提供了可靠的数据支持

提升了SCR脱硝系统的脱硝效率和稳定性。

Abstract

To address the problems of high carbon emissions and severe environmental pollution in traditional coal-fired power units

the potential of coal ammonia mixed combustion technology in emission reduction and pollution mitigation was deeply studied. The mechanism of NOx(nitrogen oxides) generation was explored

and a prediction model for the NOx concentration at the inlet of the SCR denitration system was established. Based on the model

a control method for SCR denitrification system was proposed. Firstly

by analyzing the mechanism of NOx generation during ammonia doped combustion

the characteristic variables influencing NOx concentration variations were determined. Principal component analysis method was used to optimize the characteristic variables

and a long short-term memory (LSTM) network prediction model was established. Furthermore

The particle swarm optimization algorithm combined with annealing idea (SA-PSO algorithm) was used to optimize the model's structure parameters

thereby improving the accuracy of predicting the SCR inlet NOx concentration. Secondly

a feedforward cascade control method for the SCR denitrification system was designed based on the prediction model and compared with other traditional control methods. Finally

simulation verification was conducted using the operation data of a 600 MW coal-fired unit under two conditions: 100% load with 10% ammonia doped ratio and 50% load with 20% ammonia doped ratio. The results indicate that the constructed prediction model can effectively predict the NOx concentration at the SCR denitrification inlet

providing reliable data support for the control of the denitration system and enhancing both the denitration efficiency and stability of the SCR denitrification system.

关键词

Keywords

references

WANG Qing, HU Zhongyuan, SHAO Wenbin, et al. The present situation, challenges, and prospects of the application of ammonia-coal co-firing technology in power plant boilers[J]. Journal of the Energy Institute, 2024, 113: 101531.

牛涛, 张文振, 刘欣, 等. 燃煤锅炉氨煤混合燃烧工业尺度试验研究[J]. 洁净煤技术, 2022, 28(3): 193-200.NIU Tao, ZHANG Wenzhen, LIU Xin, et al. Industrial-scale experimental investigation of ammonia-coal cofiring in coal-fired boiler[J]. Clean Coal Technology, 2022, 28(3): 193-200.

张鹤严. 660 MW煤粉炉混氨燃烧特性研究[D]. 吉林: 东北电力大学, 2024.

ISHIHARA S, ZHANG Juwei, ITO T. Numerical calculation with detailed chemistry of effect of ammonia co-firing on NO emissions in a coal-fired boiler[J]. Fuel, 2020, 266: 116924.

丁先, 李汪繁, 马达夫. 燃煤机组耦合氨燃料燃烧特性及经济性探讨[J]. 热力发电, 2022, 51(8): 20-28.DING Xian, LI Wangfan, MA Dafu. Discussion on coal-fired units coupled with ammonia fuel: combustion characteristics and economy[J]. Thermal Power Generation, 2022, 51(8): 20-28.

陈萍, 花昌豪, 王佩佩, 等. 氨煤混燃NO生成机理研究[J]. 煤炭转化, 2023, 46(4): 51-58.CHEN Ping, HUA Changhao, WANG Peipei, et al. Study on NO formation mechanism of ammonia-coal co-combustion[J]. Coal Conversion, 2023, 46(4): 51-58.

CHEN Ping, HUA Changhao, JIANG Boyu, et al. Influence mechanism of ammonia mixing on NO formation characteristics of pulverized coal combustion and N oxidation in ammonia-N/coal-N[J]. Fuel, 2023, 336: 126813.

康志忠, 张震卓, 丁先, 等. 氨煤混燃气相中NO生成的化学反应动力学分析[J]. 动力工程学报, 2024, 44(6): 844-850.KANG Zhizhong, ZHANG Zhenzhuo, DING Xian, et al. Chemical reaction kinetics analysis of NO generation in gas phase of ammonia-coal co-firing[J]. Journal of Chinese Society of Power Engineering, 2024, 44(6): 844-850.

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, 501.XU Zhuang, KANG Yingwei. Modeling of the SCR denitration reactor in a thermal power unit based on random forest algorithm[J]. Journal of Chinese Society of Power Engineering, 2020, 40(6): 486-491, 501.

杨冬, 徐鸿. SCR烟气脱硝技术及其在燃煤电厂的应用[J]. 电力环境保护, 2007, 23(1): 49-51.YANG Dong, XU Hong. Discussion on the application of the SCR technology in coal-fired power plants[J]. Electric Power Environmental Protection, 2007, 23(1): 49-51.

赵宗让. 电厂锅炉SCR烟气脱硝系统设计优化[J]. 中国电力, 2005, 38(11): 69-74.ZHAO Zongrang. Design optimization of SCR system for coal-fired boilers[J]. Electric Power, 2005, 38(11): 69-74.

董建勋. 燃煤电厂SCR烟气脱硝试验研究及数学模型建立[D]. 保定: 华北电力大学, 2007.

马双忱, 金鑫, 孙云雪, 等. SCR烟气脱硝过程硫酸氢铵的生成机理与控制[J]. 热力发电, 2010, 39(8): 12-17.MA Shuangchen, JIN Xin, SUN Yunxue, et al. The formation mechanism of ammonium bisulfate in SCR flue gas denitrification process and control thereof[J]. Thermal Power Generation, 2010, 39(8): 12-17.

林伟俊, 李敏, 赵畅, 等. 基于延迟特性的NOx浓度软测量与喷氨优化[J]. 动力工程学报, 2023, 43(10): 1352-1362.LIN Weijun, LI Min, ZHAO Chang, et al. NOx concentration soft measurement and ammonia injection optimization based on delay features[J]. Journal of Chinese Society of Power Engineering, 2023, 43(10): 1352-1362.

王林, 王小成, 郭亦文, 等. 基于深度主元分析的电站锅炉NOx质量浓度预测模型研究[J]. 热力发电, 2017, 46(12): 68-74.WANG Lin, WANG Xiaocheng, GUO Yiwen, et al. Research and application of prediction model for NOx concentration in utility boilers based on deep component analysis[J]. Thermal Power Generation, 2017, 46(12): 68-74.

余印振, 韩哲哲, 许传龙. 基于深度卷积神经网络和支持向量机的NOx浓度预测[J]. 中国电机工程学报, 2022, 42(1): 238-247.YU Yinzhen, HAN Zhezhe, XU Chuanlong. NOx concentration prediction based on deep convolution neural network and support vector machine[J]. Proceedings of the CSEE, 2022, 42(1): 238-247.

刘岳, 于静, 金秀章. 基于特征优化和改进长短期记忆神经网络的NOx质量浓度预测[J]. 热力发电, 2021, 50(7): 162-169.LIU Yue, YU Jing, JIN Xiuzhang. NOx mass concentration prediction based on feature optimization and improved LSTM network[J]. Thermal Power Generation, 2021, 50(7): 162-169.

ZSOY V S, ÜNSAL M G, RKCÜ H H. Use of the heuristic optimization in the parameter estimation of generalized gamma distribution: comparison of GA, DE, PSO and SA methods[J]. Computational Statistics, 2020, 35(4): 1895-1925.

SANKARANANTH S, KARTHIGA M, E S, et al. AI-enabled metaheuristic optimization for predictive management of renewable energy production in smart grids[J]. Energy Reports, 2023, 10: 1299-1312.

李刚, 胡森, 武宝会. 基于模糊自适应Smith的SCR喷氨量串级控制系统[J]. 热力发电, 2014, 43(8): 147-150.LI Gang, HU Sen, WU Baohui. Fuzzy self-adaptive Smith cascade control system for spraying ammonia in SCR reactors[J]. Thermal Power Generation, 2014, 43(8): 147-150.

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

芦竹与典型煤协同燃烧过程中灰成分与结渣特性研究

650℃下TP321不锈钢多轴蠕变行为与失效准则研究

奇异值分解用于早期摩擦故障诊断的研究

煤-氨混燃锅炉建模及近邻传播-最小支持向量机多模态验证优化

基于多通道特征提取与深度交互融合网络的IES多元负荷短期预测