Prediction of SO<sub>2</sub> Emission Concentration for CFB Units Under Quick Load Change Conditions Based on MLO-HIKAN

WANG Yongquan; GAO Mingming; WANG Weihua; GUO Jiongnan; LIU Jizhen; YUE Guangxi

doi:10.19805/j.cnki.jcspe.2026.250148

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Prediction of SO₂ Emission Concentration for CFB Units Under Quick Load Change Conditions Based on MLO-HIKAN

更新时间：2026-06-11

- Prediction of SO₂ Emission Concentration for CFB Units Under Quick Load Change Conditions Based on MLO-HIKAN
- Chinese Journal of Power Engineering Vol. 46, Issue 6, Pages: 149-157,179(2026)
- 作者机构：
  
  1. 华北电力大学新能源电力系统全国重点实验室,北京,102206
  2. 清华大学能源与动力工程系,北京,100084
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2026.250148
  CLC： TM621;TP183
- Published：2026
- 稿件说明：
移动端阅览
王勇权, 高明明, 王唯铧, 郭炯楠, 刘吉臻, 岳光溪. 基于MLO-HIKAN的CFB机组快速变负荷工况SO2排放浓度预测[J]. 动力工程学报, 2026, 46(6): 149-157,179.
王勇权, 高明明, 王唯铧, 郭炯楠, 刘吉臻, 岳光溪. 基于MLO-HIKAN的CFB机组快速变负荷工况SO2排放浓度预测[J]. 动力工程学报, 2026, 46(6): 149-157,179. DOI： 10.19805/j.cnki.jcspe.2026.250148.

DOI： 10.19805/j.cnki.jcspe.2026.250148

摘要

针对循环流化床(CFB)机组快速变负荷工况下SO2排放浓度预测难题

从燃烧原理出发

剖析炉内SO2生成与还原机理

构建即燃碳燃烧、O2动态平衡及活性石灰石模型

并基于此建立SO2排放浓度预测模型。选取给煤量、床温、总风量、石灰石给料量等作为输入变量

结合多维相关性分析

引入即燃碳量、动态O2浓度、活性石灰石量等关键中间参数作为扩展输入

重构数据集。采用Kolmogorov-Arnold网络(KAN)训练重构数据集

构建混合输入神经网络(HIKAN)

并结合元学习优化器(MLO)优化模型超参数

提出MLO-HIKAN预测模型。算例结果表明

该模型在快速变负荷工况下对SO2排放浓度预测具有较高准确性

为CFB机组环保运行提供了新方法。

Abstract

To address the challenge of predicting SO2 concentration under quick load change conditions for circulating fluidized bed (CFB) units

from the principles of combustion

the mechanisms of SO2 generation and reduction within the furnace were analyzed

and models were constructed for the combustion of char

dynamic oxygen balance

and reactive limestone. Based on these models

an SO2 concentration prediction model was established. The model took coal feed rate

bed temperature

total air flow

and limestone feed rate as input variables. By integrating multidimensional correlation analysis

key intermediate parameters such as char combustion rate

dynamic O2 concentration

and reactive limestone were introduced as extended inputs to reconstruct the dataset. The reconstructed dataset was trained using the Kolmogorov-Arnold network (KAN) to build a hybrid input Kolmogorov-Arnold network (HIKAN). The model hyperparameters were optimized using the meta-learning optimizer (MLO)

resulting in the proposed MLO-HIKAN prediction model. Case study results demonstrate that this model achieves high accuracy in predicting SO2 emission concentration under quick load change conditions

providing a new method for the environmentally friendly operation of CFB units.

关键词

Keywords

references

吕俊复, 王君峰, 姜孝国, 等. 超超临界循环流化床锅炉技术研发进展[J]. 中国电机工程学报, 2024, 44(17): 6883-6899.LÜ Junfu, WANG Junfeng, JIANG Xiaoguo, et al. Research and development of ultra-supercritical circulating fluidized bed boiler[J]. Proceedings of the CSEE, 2024, 44(17): 6883-6899.

岳光溪, 张扬, 张建春, 等. 面向双碳目标的多元燃料循环流化床燃烧技术展望[J]. 中国电机工程学报, 2024, 44(17): 6844-6854.YUE Guangxi, ZHANG Yang, ZHANG Jianchun, et al. Outlook for multiple fuel circulating fluidized bed combustion technologies for the dual carbon goals[J]. Proceedings of the CSEE, 2024, 44(17): 6844-6854.

乔磊磊, 王孝全, 聂浩, 等. 循环流化床锅炉全负荷调峰特性研究[J]. 中国电机工程学报, 2025, 45(1): 184-193. QIAO Leilei, WANG Xiaoquan, NIE Hao, et al. Investigation on the operation characteristics of circulating fluidized bed boiler unit for full-load regulation[J]. Proceedings of the CSEE, 2025, 45(1): 184-193.

李仕成, 马素霞. 300 MW循环流化床锅炉SO2生成与控制的建模研究[J]. 中国电机工程学报, 2021, 41(17): 5966-5972.LI Shicheng, MA Suxia. Model study on SO2 generation and control of 300 MW CFB boiler[J]. Proceedings of the CSEE, 2021, 41(17): 5966-5972.

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.

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.

KE Xiwei, LI Dongfang, LI Yiran, et al. 1-Dimensional modelling of in-situ desulphurization performance of a 550 MWe ultra-supercritical CFB boiler[J]. Fuel, 2021, 290: 120088.

SHEN Xin, LI Jing, JIA Li, et al. Numerical simulation of NO and SO2 emission dynamic characteristics during thermal start-up of CFB boiler[J]. Particulate Science and Technology, 2023, 41(1): 53-63.

YU Haoyang, GAO Mingming, ZHANG Hongfu, et al. Dynamic modeling of key operating parameters for supercritical circulating fluidized bed units based on data-knowledge-driven method[J]. Journal of Thermal Science, 2024, 33(3): 1216-1230.

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.

CHEN Jing, ZHONG Wenqi, ZHOU Guanwen, et al. Desulfurization characteristics of slaked lime and regulation optimization of circulating fluidized bed flue gas desulfurization process—a combined experimental and numerical simulation study[J]. Chinese Journal of Chemical Engineering, 2024, 73(9): 163-175.

张国华. 循环流化床SO2排放模型研究与优化[D]. 北京: 华北电力大学, 2023.

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.

VACA-RUBIO C J, BLANCO L, PEREIRA R, et al. Kolmogorov-arnold networks (Kans) for time series analysis[C] //Proceedings of 2024 IEEE Globecom Workshops. Cape Town, South Africa: IEEE, 2024.

常绍波, 陈泽伟, 余建庚, 等. 基于KAN与动态上采样器的流场预测模型[J]. 计算物理, 2024, 41(6): 804-813.CHANG Shaobo, CHEN Zewei, YU Jiangeng, et al. Flow field prediction model based on KAN and dynamic upsample[J]. Chinese Journal of Computational Physics, 2024, 41(6): 804-813.

LEE K, MAJI S, RAVICHANDRAN A, et al. Meta-learning with differentiable convex optimization[C] //Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019.

BENESTY J, CHEN Jingdong, HUANG Yiteng, et al. Pearson correlation coefficient[M] //COHEN I, HUANG Yiteng, CHEN Jingdong, et al. Noise Reduction in Speech Processing. Berlin, Heidelberg: Springer, 2009: 1-4.

CROUX C, DEHON C. Influence functions of the Spearman and Kendall correlation measures[J]. Statistical Methods & Applications, 2010, 19(4): 497-515.

ABDI H. The Kendall rank correlation coefficient[J]. Encyclopedia of Measurement and Statistics, 2007, 2: 508-510.

王玮, 王子欣, 孔德安, 等. 灵活性驱动下的热电联产机组多目标协同控制策略[J]. 动力工程学报, 2024, 44(12): 1907-1915.WANG Wei, WANG Zixin, KONG De'an, et al. Flexibility-driven multi-objective cooperative control strategy for combined heat and power units[J]. Journal of Chinese Society of Power Engineering, 2024, 44(12): 1907-1915.

CHICCO D, WARRENS M J, JURMAN G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. PeerJ Computer Science, 2021, 7: e623.

刘忠, 周泽华, 邹淑云, 等. 基于迁移学习和CNN-LSTM的水轮机空化状态识别方法[J]. 动力工程学报, 2024, 44(10): 1533-1540.LIU Zhong, ZHOU Zehua, ZOU Shuyun, et al. Cavitation state recognition method of hydraulic turbine based on transfer learning and CNN-LSTM[J]. Journal of Chinese Society of Power Engineering, 2024, 44(10): 1533-1540.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Boiler Reheater Wall Temperature Prediction Model Based on CNN-BiLSTM-SSA

Spatio-temporal Graph Attention Network-based Fault Warning of Coal Mill

Day-ahead Irradiance Forecasting Framework Based on CEEMDAN-KDBSCAN-Informer

Mooring-line Tension Prediction Based on Re-decomposition and Deep Learning

Research on Acoustic Path Tracing in Furnace Based on Acoustic Tomography

Related Author

周怀春

刘洋

曲舒杨

王俊略

范景玮

商忠宝

彭献永

何至谦

Related Institution

江苏省智慧能源技术及装备工程研究中心

华能营口热电有限责任公司

中国矿业大学低碳能源与动力工程学院

Beijing Huairou Laboratory

School of Control and Computer Engineering, North China Electric Power University

AI问答

⁰

Prediction of SO2 Emission Concentration for CFB Units Under Quick Load Change Conditions Based on MLO-HIKAN

DOI：10.19805/j.cnki.jcspe.2026.250148

摘要

Abstract

关键词

Keywords

references

Prediction of SO₂ Emission Concentration for CFB Units Under Quick Load Change Conditions Based on MLO-HIKAN