Low NO<sub>x</sub> emissions based on support vector machine and Gaussian estimation of distribution

LIANG Shaohua; ZHENG Ligang; ZHOU Hao; CEN Kefa

您当前的位置：

首页 >

文章列表页 >

Low NO_x emissions based on support vector machine and Gaussian estimation of distribution

更新时间：2025-12-10

- Low NO_x emissions based on support vector machine and Gaussian estimation of distribution
- CIESC Journal Issue 1, Pages: 223-229(2009)
- 作者机构：
  
  浙江大学能源清洁利用国家重点实验室,热能工程研究所
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Online First：05 January 2009，
  
  Published：05 January 2009
- 稿件说明：
移动端阅览
LIANG Shaohua, ZHENG Ligang, ZHOU Hao, et al. Low NO_x emissions based on support vector machine and Gaussian estimation of distribution[J]. CIESC Journal, 2009, (1): 223-229.
DOI：

LIANG Shaohua, ZHENG Ligang, ZHOU Hao, et al. Low NO_x emissions based on support vector machine and Gaussian estimation of distribution[J]. CIESC Journal, 2009, (1): 223-229. DOI：

摘要

燃烧优化的核心在于建立有效而快速的建模工具及寻优算法，以便于在线应用。为了研究新方法的适用性以及克服常用算法的缺点，本文利用支持向量回归建立了大型四角切圆燃烧电站锅炉NOx排放特性模型。利用大量的热态实炉试验NOx排放数据对模型进行了训练和验证。结果表明，支持向量回归模型能获得较神经网络模型更加准确的预测结果，相对于神经网络，支持向量回归能更好处理大样本量数据的非线性问题。随后，采用一种基于高斯概率密度 (GPDD)的分布估计优化算法对NOx排放模型进行了寻优。研究发现，与遗传算法相比，GPDD具有更好的寻优能力与更快的收敛速度。结合支持向量回归与高斯概率密度分布(GPDD)算法能有效降低燃煤锅炉NOx排放量，不到1 min的优化时间便于在线应用。研究结论可为该算法在实际电厂中推广应用提供参考依据。

Abstract

Quick and effective modeling tools and searching algorithms are the critical issues in realizing on-line combustion optimization in coal-fired utility boilers.In order to explore the applicability of novel modeling tools and optimization algorithms and to overcome the drawbacks of the existing methods

in the present study support vector regression (SYR) model was proposed to capture the functional relation between the NOx emissions and operational parameters of a utility boiler.A large number of thermal field test samples

which were recorded by DCS in the actual power plants

were employed to establish the models.It was found that the predicted NOx emissions by SVR showed better agreement with the measured than those by neural networks.SVR model was more suitable to non-linear problem with a large number of samples.Subsequently

a Gaussian probability density distribution (GPDD) based optimization algorithm was described and then applied to searching the optimal inputs of SVR model for NOx reduction.The results showed that GPDD outperformed the existing GA.Less than one minute of optimization time period required for GPDD was suitable for on-line application.The current work will lay a foundation for the further extension of GPDD’s application to actual power plants.

关键词

Keywords

references

Views

497

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Affected mechanisms of oxygen-deficient pretreatment on reduction of NO by biochar

Study on simultaneous removal of NO and soot by Fe-doped La0.9Sr0.1Co1-xFexO3 catalyst

Characteristics and product generation pathway of NO oxidation by H2O2 thermal decomposition in different size reactors

Main active substances and useless consumption path of free radicals in Fe (Ⅱ)/H2O2 system during NO oxidation process

Simulation of NOx formation in novel dual circulating fluidized-bed boiler

Related Author

ZHANG Lei

KANG Jiawei

LI Haoran

HONG Wenpeng

Wei WEI

Zhiwei QIAO

Shuhua LI

Menghan MIAO

Related Institution

School of Energy and Power Engineering, Northeast Electric Power University

Guangzhou Key Laboratory for New Energy and Green Catalysis, College of Chemistry and Chemical Engineering, Guangzhou University

Chemistry and Chemical Engineering School, Northeast Petroleum University

School of Civil Engineering & Architecture, Northeast Petroleum University

College of Energy Science and Engineering, Harbin Institute of Technology

⁰

Low NOx emissions based on support vector machine and Gaussian estimation of distribution

DOI：

摘要

Abstract

关键词

Keywords

references

Low NO_x emissions based on support vector machine and Gaussian estimation of distribution