基于负荷划分数据和支持向量机的火电厂燃烧过程建模

doi:10.3969/j.issn.0438-1157.2013.12.034

化工学报 ›› 2013, Vol. 64 ›› Issue (12): 4496-4502.DOI: 10.3969/j.issn.0438-1157.2013.12.034

基于负荷划分数据和支持向量机的火电厂燃烧过程建模

王占能, 徐祖华, 赵均, 邵之江

浙江大学工业控制国家重点实验室, 工业控制研究所, 浙江杭州 310027

收稿日期:2013-08-01 修回日期:2013-08-10 出版日期:2013-12-05 发布日期:2013-12-05
通讯作者: 徐祖华
作者简介:王占能（1988- ），男，硕士研究生。
基金资助:
国家自然科学基金项目（61273145，61273146，60934007）；浙江省重点科技创新团队计划项目（2009R50007）。

Coal-fired power plant boiler combustion process modeling based on support vector machine and load data division

WANG Zhanneng, XU Zuhua, ZHAO Jun, SHAO Zhijiang

State Key Laboratory of Industrial Control Technology, Institute of Industrial Process Control, Zhejiang University, Hangzhou 310027, Zhejiang, China

Received:2013-08-01 Revised:2013-08-10 Online:2013-12-05 Published:2013-12-05
Supported by:
supported by the National Natural Science Foundation of China (61273145，61273146，60934007) and the Program for Zhejiang Leading Team of S&T Innovation (2009R50007).

摘要/Abstract

摘要： 为建立燃烧过程稳态模型，首先利用稳态检测算法提取稳态样本；针对稳态数据中的不均衡性，提出了一种基于负荷划分数据的方法，即根据负荷工况将样本划分成训练子集与测试子集，以提高模型的泛化性能。利用单因素图形分析方法确定3个模型参数的搜索范围，将网格搜索与交叉验证相结合选择最优的模型参数，在此基础上建立了一个300 MW燃煤火电厂机组锅炉燃烧过程的支持向量机模型，包括锅炉效率、NO_x排放量、排烟温度和飞灰含碳量4个过程输出。结果表明，经过参数优化的4个输出模型均具有很好的泛化性能。

关键词: 燃烧过程建模, 支持向量回归, 稳态检测, 参数选择

Abstract: Boiler combustion process modeling is critical for the accuracy and reliability of combustion optimization.Firstly,a steady-state detection (SSD) algorithm is used to extract steady-state samples for building steady-state combustion process model.Considering the unbalance of samples over power load,a new method of data division,which divides the available data into training subset and test subset according to load,is proposed to improve model generalization.Then,a single factor graph analysis is conducted to determine searching range of three SVM model structural parameters.After choosing the model parameters by combining grid search with cross validation,four multiple inputs single output SVM models,including boiler efficiency,NO_x emission,flue gas temperature and the unburned carbon in fly ash,are established based on the divided data.The results are demonstrated that four models all have a good generalization capability.

Key words: combustion process modeling, support vectors regression, steady-state detection, parameter selection

中图分类号:

IP274

王占能, 徐祖华, 赵均, 邵之江. 基于负荷划分数据和支持向量机的火电厂燃烧过程建模[J]. 化工学报, 2013, 64(12): 4496-4502.

WANG Zhanneng, XU Zuhua, ZHAO Jun, SHAO Zhijiang. Coal-fired power plant boiler combustion process modeling based on support vector machine and load data division[J]. CIESC Journal, 2013, 64(12): 4496-4502.

参考文献 20

[1]	Booth R C, Roland W B.Neural network-based combustion optimization reduces NOx emissions while improving performance//Proceedings of the American Power Conference[C].1998, 2:667-672
[2]	Zhou Hao, Cen Kefa, Fan Jianren.Modeling and optimization of the NOx emission characteristics of a tangentially fired boiler with artificial neural networks[J].Energy, 2004, 29 (1):167-183
[3]	Zheng Ligang, Zhou Hao, Wang Chunling, Cen Kefa. Combining support vector regression and ant colony optimization to reduce NOx emissions in coal-fired utility boilers[J].Energy & Fuels, 2008, 22 (2):1034-1040
[4]	Shakil M, Moustafa Elshafei, Mohamed A Habib, Maleki F A.Soft sensor for NOx and O2 using dynamic neural networks[J].Computers and Electrical Engineering, 2009, 35 (8):578-586
[5]	Gu Yanping, Zhao Wenjie, Wu Zhansong.Online adaptive least squares support vector machine and its application in utility boiler combustion optimization systems[J].Journal of Process Control, 2011, 21 (7):1040-1048
[6]	Zheng Lingang, Zhou Hao, Cen Kefa, Wang Chunlin.A comparative study of optimization algorithms for low NOx combustion modification at a coal-fired utility boiler[J].Expert Systems with Applications, 2009, 36 (2):2780-2793
[7]	Zhou Hao, Zheng Ligang, Cen Kefa.Computational intelligence approach for NOx emissions minimization in a coal-fired utility boiler[J].Energy Conversion and Management, 2010, 51 (3):580-586
[8]	Wang Chunlin (王春林), Zhou Hao (周昊), Zhou Zhanghua (周樟华), Ling Zhongqian (凌忠钱), Li Guoneng (李国能), Cen Kefa (岑可法).Support vector machine modeling on the unburned carbon in fly ash[J].Proceedings of CSEE (中国电机工程学报), 2005, 25 (20):72-76
[9]	Wang Peihong (王培红), Li Leilei (李磊磊), Chen Qiang (陈强), Dong Yihua (董益华).Research on application of artificial intelligence to combustion optimization in a coal-fired boiler[J].Proceedings of CSEE (中国电机工程学报), 2004, 24 (4):184-188
[10]	Frohlich Holger, Abdreas Zell.Efficient parameter selection for support vector machines in classification and regression via model-based global optimization//IEEE International Joint Conference on Neural Networks[C].2005, 3:1431-1436
[11]	Cherkassky Vladimir, Ma Y Q.Practical selection of SVM parameters and noise estimation for SVM regression[J].Neural Networks, 2004, 17 (1):113-126
[12]	Arlot Sylvain, Alain Celisse.A survey of cross-validation procedures for model selection[J].Statistics Surveys, 2010, 4:40-79
[13]	Jeffrey D K, Hedengren J D. A steady-state detection (SSD) algorithm to detect non-stationary drifts in process[J].Journal of Process Control, 2013, 23:326-331
[14]	Jiang Taiwen, Chen Bingzhen, He Xiaorong.Application of steady-state detection method based on wavelet transform[J].Computers and Chemical Engineering, 2003, 27 (4):569-578
[15]	Shahin M A, Maier H R, Jaksa M B.Data division for developing neural networks applied to geotechnical engineering[J].Journal of Computing in Civil Engineering, 2004, 18 (2):105-114
[16]	Refaeilzadeh Payam, Lei T, Liu H.Cross-validation//Encyclopedia of Database Systems[C].US:Springer, 2009:532-538
[17]	Chang C C, Lin C J.LIBSVM:a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology (TIST), 2011, 2 (3):27
[18]	Cortes Corinna, Vladimir Vapnik.Support-vector networks[J].Machine Learning, 1995, 20 (3):273-297
[19]	Christopher J C Burges.A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery, 1998, 2 (2):121-167
[20]	Hsu C W, Chang C C, Lin C J.A practical guide to support vector classification[EB/OL].[2013-08-05].http://www.csie.ntu.edu.tw/～cjlin/talks/freiburg.pdf

基于负荷划分数据和支持向量机的火电厂燃烧过程建模

Coal-fired power plant boiler combustion process modeling based on support vector machine and load data division

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 10

编辑推荐

Metrics

本文评价

[1]	侯延彬,高宪文,李翔宇. 采油过程多尺度状态特征生成的有杆泵动态液面预测[J]. 化工学报, 2019, 70(S2): 311-321.
[2]	张正江，曾国强，邵之江，王可心，陈曦. 过程系统变负荷下的数据校正与参数估计方法[J]. 化工学报, 2012, 63(6): 1780-1789.
[3]	李峰1，2，郑经堂1，胡燕1. 数据挖掘在纳米二氧化钛制备中的应用[J]. 化工进展, 2012, 31(07): 1571-1574.
[4]	吴文元;熊智华;吕宁;王京春;邵杰峰;钟向宏. 支持向量回归在乙烯裂解产物收率软测量中的应用 [J]. CIESC Journal, 2010, 61(8): 2046-2050.
[5]	王平, 田华阁, 田学民, 黄德先. 一种基于增量式SVR学习的在线自适应建模方法 [J]. 化工学报, 2010, 61(8): 2040-2045.
[6]	徐志明;文孝强;孙媛媛;孙灵芳. 基于最小二乘支持向量回归机的光管污垢特性预测 [J]. CIESC Journal, 2009, 60(7): 1617-1622.
[7]	梁绍华, 郑立刚, 周昊, 岑可法. 基于支持向量机与高斯分布估计的低NO_x排放 [J]. 化工学报, 2009, 60(1): 223-229.
[8]	吴国庆;颜学峰 . 基于ART-SVR的过程建模及在干点软测量中的应用 [J]. CIESC Journal, 2008, 59(4): 927-933.
[9]	李修亮, 苏宏业, 褚健. 基于在线聚类的多模型软测量建模方法 [J]. 化工学报, 2007, 58(11): 2834-2839.
[10]	刘涵, 刘丁, 郑岗, 梁炎明, 宋念龙. 基于最小二乘支持向量机的天然气负荷预测 [J]. 化工学报, 2004, 55(5): 828-832.