A soft sensor model for NO<sub>x</sub> concentration based on CS-LSSVM

DING Xuda; LIU Xiao; JIN Xiuzhang

doi:10.19666/j.rlfd.201808139

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

A soft sensor model for NO_x concentration based on CS-LSSVM

更新时间：2025-09-28

- A soft sensor model for NO_x concentration based on CS-LSSVM
- Thermal Power Generation Vol. 47, Issue 3, Pages: 76-81(2018)
- 作者机构：
  
  华北电力大学控制与计算机工程学院
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.201808139
  CLC： TK313
- Published Online：07 March 2018，
  
  Published：2018
- 稿件说明：
移动端阅览
DING Xuda, LIU Xiao, JIN Xiuzhang. A soft sensor model for NO_x concentration based on CS-LSSVM[J]. Thermal power generation, 2018, 47(3): 76-81.
DOI：

DING Xuda, LIU Xiao, JIN Xiuzhang. A soft sensor model for NO_x concentration based on CS-LSSVM[J]. Thermal power generation, 2018, 47(3): 76-81. DOI： 10.19666/j.rlfd.201808139.

摘要

提出了一种基于压缩感知(CS)和最小二乘支持向量机(LSSVM)构成的压缩感知最小二乘支持向量机(CS-LSSVM)软测量模型

用于预测烟气中的NOx质量浓度。利用压缩感知理论中的最小二乘匹配追踪算法(LS-OMP)对LSSVM在建模过程中的映射矩阵进行压缩

采用压缩后的稀疏映射矩阵直接建立CS-LSSVM软测量模型。与传统LSSVM模型相比

本模型通过稀疏映射矩阵

降低了运算成本的同时提高了模型的计算速度;与传统稀疏化LSSVM(Sparse-LSSVM)模型相比

LSSVM模型仍需要在建模后不断稀疏新输入的支持向量

本文CS-LSSVM模型仅通过在建模过程中一次性压缩

降低了运算成本的同时提高了软测量精度

将该模型用于电厂燃煤锅炉NOx排放的软测量中

现场数据仿真结果表明

用本文提出的方法以50%的支持向量就能达到很好的表现能力

为现场NOx的在线软测量提供了数据支持。

Abstract

A soft sensor model based on compression sensing(CS) and least square support vector machine(LSSVM) was proposed to predict the NOx concentration in flue gas. The mapping matrix of the LSSVM was sparsified by the least support orthogonal matching pursuit algorithm(LS-OMP) in the compression sensing theory

and then used in soft sensor model building. Compared with the conventional LSSVM model

this model reduces the computational cost and improves the real-time performance by sparsifying the mapping matrix. Compared with the conventional sparse-LSSVM model

LSSVM model needs to make new support vectors sparse after modeling. The CS-LSSVM model reduces the computational cost and improves the soft-sensing accuracy through once compression. The model was used in soft sensor of NOx emission from a coal-fired boiler. The simulation results show that

only 50% support vectors is enough to achieve good performance with the model and provides data support for online monitoring of the NOx emission.

关键词

Keywords

references

Views

252

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

STUDY ON APPLICATION OF DMC-PID CASCADE CONTROL FOR SUPERHEATED STEAM TEMPERATURE IN THERMAL POWER PLANTS

COMPARISON AND ANALYTICAL STUDY ON NO_x EMISSION FROM VARIOUS W-SHAPED FLAME BOILERS IN SERVICE

COMBUSTION ADJUSTMENT TEST FOR SUPERCRITICAL BOILER OF 600MW UNIT

STUDY ON APPLICATION OF PREDICTIVE CONTROL BASED ON SUPERVISORY INFORMATION SYSTEM

RESEARCH ACHIEVEMENTS OF CATALYSTS FOR SCR DENITRIFICATION BY NH₃ AND HYDROCARBON

Related Author

YE Zhi

LIU Wei

YANG Xin-min

LIU Hong-gang

BAI Shao-lin (Xi’an Thermal Power Research Institute Co Ltd

LU Ying

WNAG Da-fengZhejiang Provincial Electric Power Testing & Research Institute

LUO Yi

Related Institution

Xi'an Thermal Power Research Institute Co., Ltd., Xi'an Thermal Power Research Institute Co., Ltd., Xi'an Thermal Power Research Institute Co., Ltd. Shaanxi Xi'an 710032, Shaanxi Xi'an 710032

Xi'an Thermal Power Research Institute Co., Ltd

Zhejiang Electric Power Test and Research Institute

North China Electric Power University

Tsinghua University

AI问答

⁰

A soft sensor model for NOx concentration based on CS-LSSVM

DOI：10.19666/j.rlfd.201808139

摘要

Abstract

关键词

Keywords

references

A soft sensor model for NO_x concentration based on CS-LSSVM