GA-SVM-based soft-sensor model for oxygen content in flue gas of utility boilers

LI Jianqiang; ZHAO Kai; NIU Chenglin; YIN Xichao; CHEN Xingxu; XING Fei

English

您当前的位置：

首页 >

文章列表页 >

GA-SVM-based soft-sensor model for oxygen content in flue gas of utility boilers

Thermal Power Generation Issue 3, (2017)

更新时间：2025-09-28

- GA-SVM-based soft-sensor model for oxygen content in flue gas of utility boilers
- 作者机构：
  
  1. 华北电力大学能源动力与机械工程学院,河北,保定,071003
  2. 华北电力大学自动化系,河北,保定,071003
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP274.2
- Published Online：27 March 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
LI Jianqiang, ZHAO Kai, NIU Chenglin, et al. GA-SVM-based soft-sensor model for oxygen content in flue gas of utility boilers[J]. Thermal Power Generation, 2017, (3).
DOI：

LI Jianqiang, ZHAO Kai, NIU Chenglin, et al. GA-SVM-based soft-sensor model for oxygen content in flue gas of utility boilers[J]. Thermal Power Generation, 2017, (3). DOI：

摘要

针对电厂烟气含氧量测量存在的投资大、精度低等问题，在烟气含氧量理论研究的基础上，选择合理的二次变量，引入支持向量机（ SVM）建立二次变量与烟气含氧量的软测量模型。利用遗传算法（ GA）对模型中的惩罚系数和核函数参数进行寻优，进而利用最优值构建了 GA-SVM烟气含氧量软测量模型，并对比利用粒子群算法及网格搜索法对参数的寻优结果，对模型的准确性、泛化性进行测试。仿真结果表明：遗传算法比粒子群算法和网格搜索法更易找到全局最优解； GA-SVM软测量模型误差在 ±0.2%以内，相对误差在 ±4%以内，能满足不同负荷、不同时间段锅炉烟气含氧量的预测要求，其对烟气含氧量的测量更准确。

Abstract

关键词

Keywords

references

Views

308

下载量

CSCD

Alert me when the article has been cited

提交

Publicity Resources

SOFT MEASUREMENT OF OXYGEN CONTENT IN FLUE GAS BASED ON LEAST SQUARE SUPPORT VECTOR MACHINE AND PSO ALGORITHM

Boiler exhaust gas temperature modeling based on particle swarm algorithm and support vector machine

Multi-objective combustion optimization for a 300MW unit using support vector machine theory combining with genetic algorithm

Research status of soft measurement technology of typical thermal parameters for utility boilers

Optimization of thermoelectric load distribution in coupled multi-unit heating modes based on particle swarm algorithm

Related Author

WANG Hong-zhi1

CHEN Shuai2

CHI Hong-bo2 1.Shandong Shouguang Juneng Electric Power Group

ZHONG Yafei

WEI Hongqi

YAO Weigang

CHEN Jingwei

WANG Yupeng

Related Institution

East China University of Science and Technology

Juneng Power Group

School of Energy and Environment, Southeast University

Guangdong Power Grid Co., Ltd. Electric Power Science Research Institute

College of Energy and Power Engineering, North China Electric Power University

AI问答

⁰