|本期目录/Table of Contents|

[1]金秀章,魏琳,王真.基于核主元分析和支持向量机的火电厂炉膛温度的研究[J].工业仪表与自动化装置,2015,(05):106.
　WEI Lin,JIN Xiuzhang,WANG Zhen.Research on soft sensor method for furnace temperature in power plants based on support vector machine[J].Industrial Instrumentation & Automation,2015,(05):106.
点击复制

基于核主元分析和支持向量机的火电厂炉膛温度的研究(PDF)

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2015年05期
页码:
106
栏目:
出版日期:
2015-10-15

文章信息/Info

Title:
Research on soft sensor method for furnace temperature in power plants based on support vector machine
文章编号:
1000-0682(2015)05-0000-00
作者:
金秀章; 魏琳; 王真
（华北电力大学 控制与计算机工程学院，河北 保定 071003）
Author(s):
WEI Lin;  JIN Xiuzhang; WANG Zhen
（School of Control and Computer Engineering, North China Electric Power University,Hebei Baoding 071003,China）
关键词:
炉膛温度; 软测量模型; 燃烧优化控制
Keywords:
furnace temperature; soft measurement model; combustion optimization control
分类号:
TP13
DOI:
-
文献标志码:
A
摘要:
以华能嘉祥电厂330 MW机组为例，根据火电厂的工艺流程分析选取辅助变量以及利用LSSVM建立炉膛温度软测量模型等问题，与上海新华、山东鲁能DCS充分结合，建立炉温软测量系统。现场实测数据表明，该系统在不增加装置设备投资成本的前提下，运用该软监测效果良好，不仅避免了在测温元件损坏时对生产的弊端，还为屏式过热器入口温度的预测及受热面的安全性提供了条件，为后续的燃烧优化工作奠定基础。
Abstract:
Taking 330 MW unit in Huaneng Jiaxiang power plant as an example,according to the problem of choosing auxiliary variables and the establishment of furnace temperature soft measurement model by using LSSVM analysis process of thermal power plant,fully integrated with Shanghai Xinhua,Shandong Luneng DCS,establish the furnace temperature softmeasurement system.The measured data of the field operation shows that,the systemwithout increasing the cost of investment of equipment,the use of the soft monitoring effect is good,not only completely overcome the adverse influence on production in the temperature measurement element is damaged,also for the prediction of platen superheater inlet temperature and the safety of the heating surface provides basis and lay the foundation for subsequent combustion optimization work.

参考文献/References:

[1] Suykens J A K, Van Gestel T, Jos De Brabanter. Least Squares Support Vector Machines [M]. World Scientific Press, 2002.
[2] Vapnik V . The Nature of Statistical Learning Theory [M] .New York: Springer Verlag , 1995: 181 - 197
[3] B Sch?lkopf, A Smola, K R Müller. Nonlinear component analysis as a kernel eigenvalue problem[J].Neural Computation (S0899-7667), 1998, 10(5): 1299-1319.
[4] L J Cao, K S Chua, W K Chong, et al. A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine [J]. NeuroComputing (S0925-2312), 2003, 55(1): 321-336.
[5] Suykens J, Barbanter J De , Lukas L , et al. Weighted least squares support vector ma chines: Robustness and sparse approxima ti on[J].Neuro computing, 2002,48(1-4):85-105.
[6] 郑小霞,钱锋. 基于PCA和最小二乘支持向量机的软测量建模[J].系统仿真学报,2006.
[7] Lee J M, Yoo C, Choi S W, et al. Non-linear process monitoring using kernel principal component analysis[J]. Chemical Engineering Science,2004,59(1):223-224.
[8] Sun X D,Zhu H Q,Yang Z B,et al,Nonlinear modeling of bearingless permanent magnet synchronous motors with least aquares support vector machines[J].Control Theory &Applications,2012,29(4):524-528.

相似文献/References:

备注/Memo

备注/Memo:

收稿日期 ： 2015-03-11

作者简介 ： 魏琳（ 1990 ），女，山东省聊城市人，硕士研究生，主要研究领域为先进的控制理论。

更新日期/Last Update: 1900-01-01