基于改进自适应最小二乘支持向量机的飞灰含碳量软测量方法

郭文康; 莫正阳; 李益国

doi:10.19805/j.cnki.jcspe.2025.240298

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 >

基于改进自适应最小二乘支持向量机的飞灰含碳量软测量方法

数字化与智能化 | 更新时间：2026-10-10

- 基于改进自适应最小二乘支持向量机的飞灰含碳量软测量方法
- A Soft Measurement Method of Fly Ash Carbon Content Based on Improved Adaptive Least Squares Support Vector Machine
- 动力工程学报 2025年45卷第7期页码：1082-1090
- 作者机构：
  
  东南大学大型发电装备安全运行与智能测控国家工程研究中心,江苏,南京,211189
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(51476027)
- DOI：10.19805/j.cnki.jcspe.2025.240298
  中图分类号：
- 网络首发：2025-07-14，
  
  纸质出版：2025
- 稿件说明：
移动端阅览
郭文康,莫正阳,李益国. 基于改进自适应最小二乘支持向量机的飞灰含碳量软测量方法动力工程学报, 2025, 45(7): 1082-1090 https://doi.

org/10.19805/j.cnki.jcspe.2025.240298
郭文康,莫正阳,李益国. 基于改进自适应最小二乘支持向量机的飞灰含碳量软测量方法动力工程学报, 2025, 45(7): 1082-1090 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.240298.

org/10.19805/j.cnki.jcspe.2025.240298 DOI：

摘要

飞灰含碳量是实现锅炉效率在线测量的重要参数之一

然而目前的飞灰含碳量测量装置存在测量周期长和故障率高等缺点。为此

通过改进模型更新方法提出一种新的改进自适应最小二乘支持向量机(IALSSVM)算法

并且将其用于建立某660 MW燃煤锅炉飞灰含碳量的动态软测量模型

其中采用皮尔逊相关性分析筛选出重要变量

利用核主成分分析(KPCA)法融合重要变量信息。仿真测试结果表明:该软测量模型在测试集上的平均绝对预测误差(MAE)、平均绝对百分比误差(MAPE)分别为0.171%和19.814%

拟合优度(

)为0.843

具有较高的精度和稳定性。另外

新的模型更新方法在计算速度上相比于传统方法提升30%左右

对促进该模型的在线应用和实现锅炉闭环燃烧优化具有重要作用。

Abstract

The carbon content of fly ash is one of the important parameters to realize the online measurement of boiler efficiency

but the current measurement device for fly ash carbon content has the disadvantages of a long measurement period and a high failure rate. To solve this problem

a novel improved adaptive least squares support vector machine (IALSSVM) algorithm with improved model update method was proposed

and this algorithm was used to establish a dynamic soft measurement model of fly ash carbon content for a 660 MW coal-fired boiler

in which important variables were selected by Pearson correlation analysis

while the information of important variables was fused by kernel principal component analysis (K

PCA) method. Simulation results show that

the average absolute prediction error (MAE) and mean absolute percentage error (MAPE) of the soft measurement model on the test set are 0.171% and 19.814%

respectively

and the goodness of fit (

) is 0.843

which has a high level of accuracy and stability. In addition

compared with the traditional method

the calculation speed of the novel model update method can be improved by about 30%

which plays an important role in promoting the online application of the model and realizing boiler closed-loop combustion optimization.

关键词

Keywords

references

李霞, 牛培峰, 刘建平, 等. 基于量子迭代混沌的涡流搜索算法预测锅炉飞灰含碳量[J]. 动力工程学报, 2019, 39(7): 531-540. LI Xia, NIU Peifeng, LIU Jianping, et al. Prediction of carbon content in boiler fly ash based on quantum and iterative chaos vortex search algorithm[J]. Journal of Chinese Society of Power Engineering, 2019, 39(7): 531-540.

汤根土, 吕俊复, 张建胜, 等. 循环流化床锅炉飞灰中碳的形成机理[J]. 动力工程, 2009, 29(1): 22-26. TANG Gentu, LV Junfu, ZHANG Jiansheng, et al. Carbon formation mechanism in fly ash of circulating fluidized bed boilers[J]. Journal of Power Engineering, 2009, 29(1): 22-26.

程启明, 胡晓青, 王映斐, 等. 锅炉飞灰含碳量测量方法综述[J]. 上海电力学院学报, 2011, 27(5): 519-524. CHENG Qiming, HU Xiaoqing, WANG Yingfei, et al. Summary of measurement methods of carbon content in fly ash[J]. Journal of Shanghai University of Electric Power, 2011, 27(5): 519-524.

朱润孺, 王昕, 袁野, 等. 飞灰辐射特性与表面温度关联的实验研究[J]. 动力工程学报, 2021, 41(8): 645-649. ZHU Runru, WANG Xin, YUAN Ye, et al. Experimental research for correlation between radiation characteristic and surface temperature of fly ash[J]. Journal of Chinese Society of Power Engineering, 2021, 41(8): 645-649.

张扬. 锅炉飞灰含碳量软测量[D]. 保定: 华北电力大学, 2019.

周昊, 朱洪波, 曾庭华, 等. 基于人工神经网络的大型电厂锅炉飞灰含碳量建模[J]. 中国电机工程学报, 2002, 22(6): 97-100. ZHOU Hao, ZHU Hongbo, ZENG Tinghua, et al. Artificial neural network modelling on the unburned carbon in fly ash from utility boilers[J]. Proceedings of the CSEE, 2002, 22(6): 97-100.

刘鑫屏, 李波, 邓拓宇. 一种SSAE+BPNN的变工况飞灰含碳量软测量方法[J]. 热力发电, 2023, 52(1): 66-73. LIU Xinping, LI Bo, DENG Tuoyu. A soft measurement method of carbon content in fly ash under variable operating conditions of SSAE+BPNN[J]. Thermal Power Generation, 2023, 52(1): 66-73.

王子铭. 基于支持向量回归的飞灰含碳量测量方法[J]. 河南工程学院学报(自然科学版), 2020, 32(3): 50-54. WANG Ziming. Measurement of carbon content in fly ash based on support vector regression[J]. Journal of Henan University of Engineering (Natural Science Edition), 2020, 32(3): 50-54.

彭道刚, 李丹阳, 顾立群, 等. 基于ADQPSO-SVR的锅炉飞灰含碳量预测研究[J]. 计算机仿真, 2020, 37(3): 72-77. PENG Daogang, LI Danyang, GU Liqun, et al. Research on prediction of carbon content in boiler fly ash based on ADQPSO-SVR[J]. Computer Simulation, 2020, 37(3): 72-77.

XIE Dong, TONG Bo, ZHANG Shirong. An optimal sparseness algorithm for LSSVM based on global representative indicator and PSO[C]//Chinese Control and Decision Conference (CCDC). Hefei, China: IEEE, 2020.

张大海, 楼锐, 刘宇穗, 等. 基于LS-SVM稀疏化算法的飞灰含碳量软测量方法[J]. 南方能源建设, 2019, 6(4): 69-74. ZHANG Dahai, LOU Rui, LIU Yusui, et al. A soft measurement method for carbon content of fly ash based on sparseness approach for LS-SVM[J]. Southern Energy Construction, 2019, 6(4): 69-74.

ZHANG Guiwei, BAO Lin. Soft-sensing modeling of the carbon content in fly ash based on information fusion for thermal power plant[C]//2009 International Conference on Mechatronics and Automation. Changchun, China: IEEE, 2009.

陈植元, 谭厚章, 成思扬, 等. 基于机器学习的飞灰含碳量预测模型比较研究[J]. 热力发电, 2023, 52(7): 64-73. CHEN Zhiyuan, TAN Houzhang, CHENG Siyang, et al. Comparison of prediction models of carbon content of fly ash based on machine learning[J]. Thermal Power Generation, 2023, 52(7): 64-73.

LV You, LIU Jizhen, YANG Tingting, et al. A novel least squares support vector machine ensemble model for NO < i>x emission prediction of a coal-fired boiler[J ] . Energy, 2013, 55: 319-329.

SUYKENS J, VANDEWALLE J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3): 293-300.

YANG Xiaowei, LU Jie, ZHANG Guangquan. Adaptive pruning algorithm for least squares support vector machine classifier[J]. Soft Computing, 2010, 14(7): 667-680.

HAGER W W. Updating the inverse of a matrix[J]. SIAM Review, 1989, 31(2): 221-239.

TAN Peng, HE Biao, ZHANG Cheng, et a l. Dynamic modeling of NO < i>x emission in a 660 MW coal-fired boiler with long short-term memory[J ] . Energy, 2019, 176: 429-436.

李泳萱, 田亮, 董子健. 基于KPCA-FCM工况精简的机组燃烧优化[J]. 华北电力大学学报, 2024, 51(2): 135-142. LI Yongxuan, TIAN Liang, DONG Zijian. Combustion optimization of unit based on KPCA-FCM simplified operating conditions[J]. Journal of North China Electric Power University, 2024, 51(2): 135-142.

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

基于物理单调最小二乘支持向量机的锅炉燃烧NOx生成浓度预测方法

基于火焰图像的危险废物回转窑燃烧稳定性预测

热电厂耦合蒸汽储能电热特性研究与优化

大型能源基地经济-实时双层协同调度策略

基于Leckner模型的氨掺烧高水蒸气浓度烟气对燃煤锅炉传热特性的影响分析