基于WOA的循环流化床锅炉SO<sub>2</sub>排放浓度VMD-Transformer预测模型

彭桐超; 高明明; 郭炯楠; 韩禹烁; 闫莘; 岳光溪

doi:10.19805/j.cnki.jcspe.2026.250449

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WOA的循环流化床锅炉SO₂排放浓度VMD-Transformer预测模型

绿色低碳 | 更新时间：2026-09-15

- 基于WOA的循环流化床锅炉SO₂排放浓度VMD-Transformer预测模型
- VMD-Transformer Prediction Model of SO₂ Emission Concentration Based on WOA in Circulating Fluidized Bed Boiler
- 动力工程学报 2026年46卷第9期页码：171-179
- 作者机构：
  
  1. 新能源电力系统全国重点实验室(华北电力大学),北京,102206
  2. 热科学与动力工程教育部重点实验室(清华大学能源与动力工程系),北京,100084
- 作者简介：
  
  彭桐超(2001—),男,河北保定人,硕士研究生,研究方向为深度学习在CFB机组中的应用。高明明(通信作者),男,教授,博士,E-mail:gmml@ncepu.edu.cn。
- 基金信息：
  
  国家自然科学基金资助项目（62276096）
- DOI：10.19805/j.cnki.jcspe.2026.250449
  中图分类号： TM621;TP183
- 纸质出版：2026
- 稿件说明：
移动端阅览
彭桐超, 高明明, 郭炯楠, 韩禹烁, 闫莘, 岳光溪. 基于WOA的循环流化床锅炉SO2排放浓度VMD-Transformer预测模型[J]. 动力工程学报, 2026, 46(9): 171-179.
彭桐超, 高明明, 郭炯楠, 韩禹烁, 闫莘, 岳光溪. 基于WOA的循环流化床锅炉SO2排放浓度VMD-Transformer预测模型[J]. 动力工程学报, 2026, 46(9): 171-179. DOI： 10.19805/j.cnki.jcspe.2026.250449.

DOI： 10.19805/j.cnki.jcspe.2026.250449

摘要

构建了基于鲸鱼优化算法（WOA）的循环流化床（CFB）锅炉SO2排放浓度变分模态分解（VMD）-Transformer预测模型。首先，采用平均影响值（MIV）方法筛选输入变量，通过四分位距（IQR）法剔除异常值后进行归一化。然后，运用WOA同步优化时间步长、VMD和Transformer模型超参数。最后，利用优化后的VMD模型提取SO2浓度时间序列信号，结合优化后的Transformer模型多头自注意力机制构建时间序列SO2排放浓度预测模型。以某300 MW CFB机组为研究对象，选取4段变负荷工况开展SO2排放浓度预测，经消融实验进一步验证了VMD的信号分解与Transformer的时序建模协同可提升预测精度。结果表明：在变负荷工况下，模型预测值与实际值的平均绝对误差（MAE）最低为1.336 9 mg/m3，决定系数R2为0.960 9。所建模型可为CFB机组污染物控制的在线优化提供支持，推动CFB机组向智能化方向发展。

Abstract

A variational modal decomposition (VMD)-Transformer prediction model for SO2 emission concentration in circulating fluidized bed (CFB) boiler based on whale optimization algorithm (WOA) was constructed. First

the mean impact value (MIV) method was adopted to screen input variables

outliers were eliminated through inter quartile range (IQR) method

and normalization was subsequently performed. Then

WOA was used to synchronously optimize the time step

as well as the hyperparameters of the VMD and Transformer models. Finally

the optimized VMD model was applied to extract the time series signals of SO2 concentration

and the multi-head self-attention mechanism of the optimized Transformer model was combined to build the time-series prediction model for SO2 emission concentration. Taking a 300 MW CFB unit as the research object

four segments of variable-load operating conditions were selected to carry out the prediction of SO2 emission concentration. Ablation experiments further verify that the synergy between VMD for signal decomposition and Transformer for temporal modeling can improve the prediction accuracy. Results show that under variable load conditions

the minimum mean absolute error (MAE) between the predicted value and the actual value of the model is 1.336 9 mg/m3

and the determination coefficient R2 is 0.960 9. The established model can provide a support for the online optimization of pollutant control in CFB units and promote the intelligent development of CFB units.

关键词

Keywords

references

姚禹歌, 黄中, 张缦, 等. 中国循环流化床燃烧技术的发展与展望[J]. 热力发电, 2021, 50(11): 13-19. YAO Yuge, HUANG Zhong, ZHANG Man, et al. Development and prospect of circulating fluidized bed combustion technology in China[J]. Thermal Power Generation, 2021, 50(11): 13-19.

李树林, 曾庭华, 范浩杰. 循环流化床锅炉深度脱硫的经济性研究[J]. 锅炉技术, 2012, 43(5): 35-39. LI Shulin, ZENG Tinghua, FAN Haojie. The economic research on deep desulfurization of circulating fluidized bed boiler[J]. Boiler Technology, 2012, 43(5): 35-39.

高明明, 岳光溪, 雷秀坚, 等. 600 MW超临界循环流化床锅炉控制系统研究[J]. 中国电机工程学报, 2014, 34(35): 6319-6328. GAO Mingming, YUE Guangxi, LEI Xiujian, et al. Research on control system of 600 MW supercritical circulating fluidized bed boiler[J]. Proceedings of the CSEE, 2014, 34(35): 6319-6328.

高明明, 岳光溪, 雷秀坚, 等. 循环流化床锅炉石灰石控制研究[J]. 动力工程学报, 2014, 34(10): 759-764, 777. GAO Mingming, YUE Guangxi, LEI Xiujian, et al. Research on limestone control of circulating fluidized bed boiler[J]. Journal of Chinese Society of Power Engineering, 2014, 34(10): 759-764, 777.

张洪福. 循环流化床机组负荷响应特性与灵活运行控制研究[D]. 北京: 华北电力大学, 2023. ZHANG Hongfu. Research on load response characteristics and flexible operation control of circulating fluidized bed unit[D]. Beijing: North China Electric Power University, 2023.

ZHANG Hongfu, GAO Mingming, LIU Chun, et al. Dynamic prediction of in-situ SO2 emission and operation optimization of combined desulfurization system of 300 MW CFB boiler[J]. Fuel, 2022, 324: 124421.

蒋海威, 高明明, 张开萍, 等. 循环流化床大气污染物机理模型及关键状态变量研究[J]. 动力工程学报, 2024, 44(4): 622-631. JIANG Haiwei, GAO Mingming, ZHANG Kaiping, et al. Study on Mechanism model and key state variables of air pollutants in circulating fluidized bed[J]. Journal of Chinese Society of Power Engineering, 2024, 44(4): 622-631.

李东雄, 徐鸿恩, 牛拥军, 等. 300 MW节能型循环流化床锅炉SO3生成和排放试验研究[J]. 动力工程学报, 2020, 40(6): 447-453.LI Dongxiong, XU Hong'en, NIU Yongjun, et al. Experimental study on SO3 generation and emission of a 300 MW energy saving CFB boiler[J]. Journal of Chinese Society of Power Engineering, 2020, 40(6): 447-453.

黄思林, 何学山, 庄文军, 等. 350 MW循环流化床锅炉不同负荷下运行特性及污染物排放试验研究[J]. 工业加热, 2023, 52(3): 26-30. HUANG Silin, HE Xueshan, ZHONG Wenjun, et al. Experimental study on operation characteristics and pollutant emissions under different loads in a 350 MW circulating fluidized bed boiler[J]. Industrial Heating, 2023, 52(3): 26-30.

倪绍佑, 姚晨蓬, 陈玲红, 等. 基于后向传播神经网络的循环流化床锅炉SO2排放预测分析[J]. 能源工程, 2021(6): 31-37. NI Shaoyou, YAO Chenpeng, CHEN Linghong, et al. Prediction analysis of SO2 emissions from circulating fluidized bed boiler based on BP neural network[J]. Energy Engineering, 2021(6): 31-37.

KRZYWANSKI J, CZAKIERT T, BLASZCZUK A, et al. A generalized model of SO2 emissions from large- and small-scale CFB boilers by artificial neural network approach part 2. SO2 emissions from large- and pilot-scale CFB boilers in O2/N2O2/CO2 and O2/RFG combustion atmospheres[J].Fuel Processing Technology,2015,13973-13985.

张砺彦, 麦永强, 张月辉, 等. 基于神经网络的大型燃煤电厂SO2和NOx的污染物预测模型[J]. 热力发电, 2008, 37(10): 9-13. ZHANG Liyan, MAI Yongqiang, ZHANG Yuehui, et al. Prediction model for pollutants SO2 and NOx from large-scale coal-fired power plant based on neural network[J]. Thermal Power Generation, 2008, 37(10): 9-13.

李彩霞, 赵军, 李建伟, 等. 基于数据驱动的CFB机组变负荷工况SO2质量浓度建模[J]. 综合智慧能源, 2022, 44(3): 63-69. LI Caixia, ZHAO Jun, LI Jianwei, et al. Data-driven modeling for SO2 mass concentration of CFB units under variable load conditions[J]. Integrated Intelligent Energy, 2022, 44(3): 63-69.

CHEN Jiyu, GAO Mingming, ZHANG Hongfu, et al. Dynamic prediction of SO2 emission based on hybrid modeling method for coal-fired circulating fluidized bed[J]. Fuel, 2023, 346: 128284.

高钾, 田雪峰, 蒋甲丁, 等. 基于CNN-BiGRU-Attention的脱硫系统出口二氧化硫动态预测模型[J]. 电子测量技术, 2025, 48(12): 183-195. GAO Jia, TIAN Xuefeng, JIANG Jiading, et al. Dynamic prediction model of sulphur dioxide concentration for WFGD system based on CNN-BiGRU-Attention[J]. Electronic Measurement Technology, 2025, 48(12): 183-195.

王勇权, 高明明, 王唯铧, 等. 基于CNN-GRU-MHA的CFB机组污染物排放动态预测[J]. 热力发电, 2025, 54(7): 33-42. WANG Yongquan, GAO Mingming, WANG Weihua, et al. Dynamic prediction of pollutants emission from circulating fluidized bed unit based on CNN-GRU-MHA[J]. Thermal Power Generation, 2025, 54(7): 33-42.

YU Haoyang, GAO Mingming, ZHANG Hongfu, et al. Dynamic modeling for SO2-NOx emission concentration of circulating fluidized bed units based on quantum genetic algorithm-extreme learning machine[J]. Journal of Cleaner Production, 2021, 324: 129170.

郭明远, 吴宝杨. 基于深度信念网络的循环流化床SO2排放浓度预测[J]. 山西电力, 2024(1): 60-64. GUO Mingyuan, WU Baoyang. Study on prediction of SO2 emission concentration in circulating fluidized beds based on DBN[J]. Shanxi Electric Power, 2024(1): 60-64.

韩雨, 郭成, 方正云, 等. 基于AP-WOA-GRU的分布式光伏集群电压越限动态预测[J]. 电网与清洁能源, 2024, 40(4): 118-126. HAN Yu, GUO Cheng, FANG Zhengyun, et al. The dynamic prediction of voltage overrun of the distributed photovoltaic cluster based on AP-WOA-GRU[J]. Power System and Clean Energy, 2024, 40(4): 118-126.

DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.

VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates, 2017: 6000-6010.

王英立, 陶帅, 候晓晓, 等. 基于MIV分析的GA-BP神经网络光伏短期发电预测[J]. 太阳能学报, 2020, 41(8): 236-242. WANG Yingli, TAO Shuai, HOU Xiaoxiao, et al. GA-BP neural network photovoltaic power generation short-term forecast based on MIV analysis[J]. Acta Energiae Solaris Sinica, 2020, 41(8): 236-242.

WHALEY III D L. The interquartile range: theory and estimation[D]. Johnson City: East Tennessee State University, 2005.

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

中心风结构对350 MW锅炉旋流燃烧器流动及燃烧特性的影响

基于BSimilar优化PTransformer的光伏功率短期预测

基于BKA-Transformer-BiGRU的垃圾焚烧炉SNCR脱硝系统动态建模

基于数据驱动的600 MW煤氨混合机组协调控制

基于MLO-HIKAN的CFB机组快速变负荷工况SO2排放浓度预测

基于WOA的循环流化床锅炉SO2排放浓度VMD-Transformer预测模型

VMD-Transformer Prediction Model of SO2 Emission Concentration Based on WOA in Circulating Fluidized Bed Boiler

DOI：10.19805/j.cnki.jcspe.2026.250449

摘要

Abstract

关键词

Keywords

references

基于WOA的循环流化床锅炉SO₂排放浓度VMD-Transformer预测模型

VMD-Transformer Prediction Model of SO₂ Emission Concentration Based on WOA in Circulating Fluidized Bed Boiler