基于独立成分分析预测电站锅炉NOx排放量

doi:10.11930/j.issn.1004-9649.2013.9.39.4

中国电力 ›› 2013, Vol. 46 ›› Issue (9): 39-43.DOI: 10.11930/j.issn.1004-9649.2013.9.39.4

基于独立成分分析预测电站锅炉NO_x排放量

孙保民¹, 信晶¹, 杨斌¹, 王兰忠², 王冲²

1. 电站设备状态监测与控制教育部重点实验室（华北电力大学）,北京 102206; 2. 北京京能热电股份有限公司,北京 100041

收稿日期:2013-05-16 出版日期:2013-09-23 发布日期:2015-12-10
作者简介:孙保民（1959—）,男,山东聊城人,教授,博士生导师,从事电站锅炉污染控制及计算机应用的教学与研究。
基金资助:
国家自然科学基金资助项目(51206047)

Forecasting the NO_x Emissions from Utility Boilers Based on Independent Component Analysis

SUN Bao-min¹, XIN Jing¹, YANG Bin¹, WANG Lan-zhong², WANG Chong²

1. MOE’s Key Lab of Condition Monitoring and Control for Power Plant Equipment, North China Electric Power University,Beijing 102206, China; 2. Beijing Jingneng Power Co. Ltd., Beijing 100041, China

Received:2013-05-16 Online:2013-09-23 Published:2015-12-10

摘要/Abstract

摘要： 为了解决燃煤电站锅炉低NO_x燃烧特性建模输入值高维数据众多,以及大样本处理造成模型运行速度慢、精度低的问题,将独立成分分析（ICA）应用到建模数据预处理领域,提出一种基于快速独立成分分析（FastICA）的BP（back propagation）神经网络建模方法,并用该方法对某220 MW热电机组NO_x排放浓度进行预测。研究结果表明：经FastICA降维预处理后所建的神经网络模型（ICA-BP）性能优于直接构建的神经网络（BP）模型;ICA-BP模型计算结果与实测结果相对误差仅约2.5%,说明ICA方法有助于实现降低维数的同时保留更多原始数据特性的目的,是系统建模数据前处理的有效工具。

关键词: 独立成分分析（ICA）, 神经网络, 电站锅炉, 低NOx燃烧, 排放预测

Abstract: There are many high dimensional input values in the modeling process for low NO_x combustion property of coal-fired utility boilers, Moreover, processing such a large amount of sample data may slow down the calculations and reduce forecasting accuracy. To solve these problems, the independent component analysis(ICA) is applied to data pretreatment and then the back propagation(BP) neural network model based on fastICA algorithm is established in this paper. The ICA-BP model is used to predict the NO_x emission from a 220-MW thermal power unit. The results indicated that the neural network model based on fastICA algorithm outperforms the one without data preprocessing. The relative error of the ICA-BP model was only about 2.5% between the calculation and the measured results, in which the ICA method is verified to be an effective tool for data pretreatment in system modeling in the aspect of lowering the dimensions while more original data characteristic information still retained simultaneously is.

Key words: independent component analysis, neural network, utility boiler, low NOx combustion, emission prediction

中图分类号:

TK16

孙保民, 信晶, 杨斌, 王兰忠, 王冲. 基于独立成分分析预测电站锅炉NO_x排放量[J]. 中国电力, 2013, 46(9): 39-43.

SUN Bao-min, XIN Jing, YANG Bin, WANG Lan-zhong, WANG Chong. Forecasting the NO_x Emissions from Utility Boilers Based on Independent Component Analysis[J]. Electric Power, 2013, 46(9): 39-43.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.2013.9.39.4

https://www.electricpower.com.cn/CN/Y2013/V46/I9/39

参考文献

[1] 赵欢,王培红,陆璐. 电站锅炉热效率与NO x 排放响应特性建模方法[J]. 中国电机工程学报,2008,28（32）：96-100.
ZHAO Huan, WANG Pei-hong, LU Lu. Response characteristics modeling of efficiency and NO x emission for power station boiler[J]. Proceedings of the CSEE, 2008, 28(32): 96-100.
[2] CAO L J, CHUA K S, CHONG W K, et al . A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine [J]. Neurocomputing, 2003, 55(1-2): 321-336.
[3] HYVARINEN A. Fast and robust fixed-point algorithms for independent component analysis [J]. IEEE Transactions on Neural Networks, 1999, 8(3): 622-634.
[4] 葛晓霞,缪国钧,毕小龙,等. 基于独立成分分析的火电厂数据重构方法[J]. 华东电力,2012,40（6）：1071-1074.
GE Xiao-xia, MIAO Guo-jun, BI Xiao-long, et al . Power plant data reconstruction based on independent component analysis [J].East China Electric Power, 2012, 40(6): 1071-1074.
[5] 司风琪,周建新,仇晓智,等. 独立成分分析方法在电站热力过程数据检验中的应用[J]. 中国电机工程学报,2008,28（26）：77-81.
SI Feng-qi, ZHOU Jian-xin, QIU Xiao-zhi, et al . Application of independent component analysis on the data validation of thermodynamic system in power plant[J]. Proceedings of the CSEE, 2008, 28(26): 77-81.
[6] 张曦,朱亚清,阎威武,等. 基于独立主元分析的汽轮机性能监测与评估[J]. 控制工程,2012,19（1）：30-32.
ZHANG Xi, ZHU Ya-qing, YAN Wei-wu, et al . Performance monitoring and assessment of generator based on independent component analysis [J]. Control Engineering of China, 2012, 19(1): 30-32.
[7] LIUKKONEN M, HEIKKINEN M, HILTUNEN T, et al . Artificial neural networks for analysis of process states in fluidized bed combustion [J]. Energy, 2011, 36(1): 339-347.
[8] 司风琪,周建新,仇晓智,等. 在线监测燃煤锅炉NO x 排放的自适应支持向量机模型[J]. 动力工程,2008,28（6）：896-900.
SI Feng-qi, ZHOU Jian-xin, QIU Xiao-zhi, et al . An adaptive support vector machine model for the on-line monitoring of boiler NO x emissions in coal-fired boiler[J]. Journal of Power Engineering, 2008, 28(6): 896-900.
[9] 吴锋,周昊,郑立刚,等. 基于非支配排序遗传算法的锅炉燃烧多目标优化[J]. 中国电机工程学报,2009,29（29）：7-12.
WU Feng, ZHOU Hao, ZHENG Li-gang, et al . Multi-objective optimization of coal-fired boiler combustion based on nondominated sorting genetic algorithm[J]. Proceedings of the CSEE, 2009, 29(29): 7-12.
[10] YANG Q, GUO J, ZHANG X. FastICA-SVM fault diagnosis for batch process[C]//Seventh International Conference on Natural Computation. Shanghai, IEEE Xplore 2011: 1649-1653.
[11] LI Y, ADALI T, CALHOUN V D. Feature-selective ICA and its convergence properties[C]//International Conference on Acoustics, Speech, and Signal Processing. Philadelphia, IEEE Xplore, 2005: 265-268.
[12] OJA E, HYVARINEN A. Independent component analysis: algorithms and opplications [J]. Networks, 2000, 13(4-5): 411-430.
[13] BERMEJO S. Finite sample effects of the fast ICA algorithm[J].Neurocomputing, 2007, 71(1-3): 392-399.
[14] 周宗潭. 独立成分分析[M]. 北京：电子工业出版社,2007.
[15] 韩敏,姜力文,赵耀. 基于PSO-ICA和RBF神经网络的转炉炼钢终点预报模型[J]. 信息与控制,2010,39（1）：82-87.
HAN Min, JIANG Li-wen, ZHAO Yao. Endpoint prediction model of basic oxygen furnace steelmaking based on PSO-ICA and RBF neural network [J]. Information and Control, 2010, 39(1): 82-87.
[16] 陈鸿伟,祁海波,梁占伟,等. 基于LM算法的双流化床循环流率预测模型研究[J]. 动力工程学报,2012,32（1）：15-20.
CHEN Hong-wei, QI Hai-bo, LIANG Zhan-wei, et al . Study on prediction model for solid circulation rate in a dual circulating fluidized bed based on LM algorithm[J]. Journal of Chinese Society of Power Engineering, 2012, 32(1): 15-20.
[17] 高小涛,黄磊,张恩先,等. 600 MW前后墙布置燃烧器锅炉的NO x 排放特性及其影响因素的分析[J]. 动力工程,2009,29（9）：806-812.
GAO Xiao-tao, HUANG Lei, ZHANG En-xian, et al . NO x emission and influence factors of 600 MW boilers with burners arranged in front and back walls[J]. Journal of Power Engineering, 2009, 29(9): 806-812.

基于独立成分分析预测电站锅炉NO_x排放量

Forecasting the NO_x Emissions from Utility Boilers Based on Independent Component Analysis

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴小忠, 肖立华, 童超, 夏向阳, 袁翎, 甘星, 江志文, 黄湘源. 基于传递熵与JS-BP神经网络的锂离子电池容量预测模型[J]. 中国电力, 2025, 58(2): 186-192, 215.
[2]	王宇飞, 杜桐, 边伟国, 张钊, 刘慧婷, 杨丽君. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57(6): 121-130.
[3]	吴军英, 路欣, 刘宏, 张彬, 柴守亮, 刘蕴春, 王佳楠. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140.
[4]	邵必林, 纪丹阳. 基于VMD-SE的电力负荷分量的多特征短期预测[J]. 中国电力, 2024, 57(4): 162-170.
[5]	陈巳阳, 韩利, 方济中, 丁五行, 成诚, 李文, 张源, 钱勇. 基于不确定参数的变电站碳储量预估方法[J]. 中国电力, 2024, 57(4): 200-210.
[6]	娄奇鹤, 李荣盛, 谭捷, 袁铁江. 基于卷积神经网络的暂稳极限功率计算[J]. 中国电力, 2024, 57(4): 211-219.
[7]	马汝括, 董杰, 王雅湉, 伊国鑫, 丁祥浩, 马乐. 基于神经网络的高寒地区CF₄和SF₆/CF₄检测[J]. 中国电力, 2024, 57(3): 103-112.
[8]	阎洁, 杨佳琳, 王航宇, 卢姣阳, 刘永前, 张磊. 基于风况预测误差自适应的海上风电场尾流偏转控制方法[J]. 中国电力, 2024, 57(3): 190-196.
[9]	李卓, 王胤喆, 叶林, 罗雅迪, 宋旭日, 张振宇. 从感知-预测-优化综述图神经网络在电力系统中的应用[J]. 中国电力, 2024, 57(12): 2-16.
[10]	陈庆斌, 杨耿煌, 耿丽清, 苏娟, 孙京生. 基于相似日选取和数据重构的短期光伏功率组合预测方法[J]. 中国电力, 2024, 57(12): 71-81.
[11]	陈来恩, 曾小勇, 曾子豪, 成采辰, 孙耀科. 基于物理信息与深度神经网络的锂离子电池温度预测[J]. 中国电力, 2024, 57(11): 18-25.
[12]	薛松萍, 高德荃, 赵子岩, 林彧茜, 广泽晶, 张大卫. 基于业务差异化传输需求下的电力通信网路由算法[J]. 中国电力, 2024, 57(11): 183-190.
[13]	周颖, 白雪峰, 王阳, 邱敏, 孙冲, 武亚杰, 李彬. 面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判[J]. 中国电力, 2024, 57(1): 9-17.
[14]	王大兴, 宁妍, 汪敬培, 徐洋, 毕峻, 周铭标, 王鹏. 构建新型电力系统背景下的微电网鲁棒简化建模[J]. 中国电力, 2024, 57(1): 148-157.
[15]	皮志勇, 朱益, 廖玄, 李振兴, 方豪, 吴沛. 基于深度学习的智能变电站通信链路故障定位方法[J]. 中国电力, 2023, 56(7): 136-145.

模态框（Modal）标题

基于独立成分分析预测电站锅炉NOx排放量

Forecasting the NOx Emissions from Utility Boilers Based on Independent Component Analysis

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

基于独立成分分析预测电站锅炉NO_x排放量

Forecasting the NO_x Emissions from Utility Boilers Based on Independent Component Analysis