基于BP-SVM模糊信息粒化掺烧煤泥循环流化床经济性建模
|
摘要
目前循环流化床(circulating fluidized bed,CFB)技术是工业综合利用低价煤泥的最佳处理方式,同时煤泥掺烧技术也是提高CFB机组经济性的重要手段。以某300MW CFB机组DCS稳态数据为样本,利用BP(back propagation)网络算法选择模型输入变量;供电煤耗经模糊信息粒化(fuzzy information granulation,FIG)提取有效信息后作为模型输出训练样本;利用支持向量机(support vector machine,SVM)建立实际运行工况参数与供电煤耗之间的BP-SVM模糊信息粒化模型。研究建立了实际运行数据驱动下的机组经济性预测模型,是优化掺烧煤泥CFB机组经济性的模型基础。
The circulating fluidized bed(CFB) technology is the best treatment method for comprehensive industrial utilization of coal slime,and mix-burning coal slime is also an important means to improve energy saving of circulating fluidized bed unit.On the basis of the 300 MW CFB steady-state operating data,back propagation(BP) algorithm was applied to choose the input variables of the model; The net coal consumption rate after fuzzy information granulation was the output training samples of the BP-FIG-SVM model; SVM was used to build the BP-FIG-SVM model which described the relationship between actual operating condition parameters and the energy cost.The energy cost forecasting model of unit is set up based on actual operation data,and the model is the basis of optimizing energy cost of circulating fluidized bed boiler mix-burning coal slime.
The circulating fluidized bed(CFB) technology is the best treatment method for comprehensive industrial utilization of coal slime,and mix-burning coal slime is also an important means to improve energy saving of circulating fluidized bed unit.On the basis of the 300 MW CFB steady-state operating data,back propagation(BP) algorithm was applied to choose the input variables of the model; The net coal consumption rate after fuzzy information granulation was the output training samples of the BP-FIG-SVM model; SVM was used to build the BP-FIG-SVM model which described the relationship between actual operating condition parameters and the energy cost.The energy cost forecasting model of unit is set up based on actual operation data,and the model is the basis of optimizing energy cost of circulating fluidized bed boiler mix-burning coal slime.
引文
[1]韩璞,乔弘,王东风,等.火电厂热工参数软测量技术的发展和现状[J].仪器仪表学报,2007,28(6):1139-1146.Han Pu,Qiao Hong,Wang Dongfeng,et al.Development and current status of thermal parameter soft-sensing technique in power plant[J].Chinese Journal of Scientific Instrument,2007,28(6):1139-1146(in Chinese).
[2]杨锡运,孙宝君,张新房,等.基于相似数据的支持向量机短期风速预测仿真研究[J].中国电机工程学报,2012,32(4):35-41.Yang Xiyun,Sun Baojun,Zhang Xinfang,et al.Short-term wind speed forecasting based on support vector machine with similar data[J].Proceedings of the CSEE,2012,32(4):35-41(in Chinese).
[3]刘吉臻,秦天牧,杨婷婷,等.基于偏互信息的变量选择方法及其在火电厂SCR系统建模中的应用[J].中国电机工程学报,2016,36(9):2438-2443.Liu Jizhen,Qin Tianmu,Yang Tingting,et al.Variable selection method based on partial mutual information and its application in power plant SCR system modeling[J].Proceedings of the CSEE,2016,36(9):2438-2443(in Chinese).
[4]黄宇,韩璞,王东风,等.基于BP神经网络整定的PID控制在过热汽温系统中的应用[J].仪器仪表学报,2006,27(S6):1980-1981.Huang Yu,Han Pu,Wang Dongfeng,et al.PID control based on BP neural network for superheated steam temperature system[J].Chinese Journal of Scientific Instrument,2006,27(S6):1980-1981(in Chinese).
[5]王恺,关少卿,汪令祥,等.基于模糊信息粒化和最小二乘支持向量机的风电功率联合预测建模[J].电力系统保护与控制,2015,43(2):26-32.Wang Kai,Guan Shaoqing,Wang Lingxiang,et al.A combined forecasting model for wind power predication based on fuzzy information granulation and least squares support vector machine[J].Power System Protection and Control,2015,43(2):26-32(in Chinese).
[6]刘海军.CFB机组降低供电煤耗综合措施分析[J].神华科技,2013,11(6):54-57.Liu Haijun.Analysis of comprehensive measures to reduce the net coal consumption rate by CFB unit[J].Shenhua Science and Technology,2013,11(6):54-57(in Chinese).
[7]黄中,潘贵涛,张品高,等.300MW大型循环流化床锅炉运行分析与发展建议[J].锅炉技术,2014,45(6):35-41.Huang Zhong,Pan Guitao,Zhang Pingao,et al.Operating condition and development proposal of 300 MW large-scale circulating fluidized bed boiler[J].Boiler Technology,2014,45(6):35-41(in Chinese).
[8]王晓峰.提高循环流化床锅炉经济性分析[J].中国科技纵横,2014(1):189.Wang Xiaofeng.The economic analysis of circulating fluidized bed boiler[J].China Science&Technology Panorama Magazine,2014(1):189(in Chinese).
[9]秦建亭.浅谈300MW循环流化床锅炉如何提高效率、降低发电煤耗[C]//全国电力行业CFB机组技术交流服务协作网第十二届年会,淮南,2013.Qin Jianting.Discussion on how to improve the efficiency of 300mw circulating fluidized bed boiler to reduce the coal consumption of power generation[C]//Operation Management of Circulating Fluidized Bed Power Generation in China,Huannan,2013(in Chinese).
[10]薛少华.300MW循环流化床锅炉机组的节能降耗[J].锅炉制造,2014(3):9-11.Xue Shaohua.Energy saving and consumption reducing in300MW CFB boiler[J].Boiler Manufacturing,2014(3):9-11(in Chinese).
[11]钱志永,周智华,陈念祖.两种不同入炉煤颗粒度下210MW循环流化床机组的性能比较[J].锅炉技术,2009,40(1):34-37.Qian Zhiyong,Zhou Zhihua,Chen Nianzu.Performance comparison of 210 MW CFB unit under two different particle size of burning coal[J].Boiler Technology,2009,40(1):34-37(in Chinese).
[12]曾建微.循环流化床锅炉运行经济性分析及节能途径[J].节能技术,2005,23(4):378-381.Zeng Jianwei.Analysis of operation economic and the approach of economize on energy of the circulating fluidized bed boiler[J].Energy Conservation Technology,2005,23(4):378-381(in Chinese).
[13]高大明,陈鸿伟,谷俊杰,等.富氧燃烧循环流化床锅炉烟气动态特性与运行经济性分析[J].中国电机工程学报,2014,34(S1):112-121.Gao Daming,Chen Hongwei,Gu Junjie,et al.Flue gas dynamic characteristics and operation economic analysis of oxy-fuel combustion circulating fluidized bed boiler[J].Proceedings of the CSEE,2014,34(S1):112-121(in Chinese).
[14]崔超,杨婷婷,刘吉臻,等.基于BP网络变量选择与LSSVM结合的锅炉脱硝经济性建模[J].中国电机工程学报,2015,35(24):6413-6420.Cui Chao,Yang Tingting,Liu Jizhen,et al.Denitration cost modeling for boilers based on BP variable selection and LSSVM[J].Proceedings of the CSEE,2015,35(24):6413-6420(in Chinese).
[15]张华,曾杰.基于支持向量机的风速预测模型研究[J].太阳能学报,2010,31(7):928-932.Zhang Hua,Zeng Jie.Wind speed forecasting model study based on support vector machine[J].Acta Energiae Solaris Sinica,2010,31(7):928-932(in Chinese).
[16]王书舟,伞冶.支持向量机的训练算法综述[J].智能系统学报,2008,3(6):467-475.Wang Shuzhou,San Ye.A survey on training algorithms for support vector machine[J].CAAI Transactions on Intelligent Systems,2008,3(6):467-475(in Chinese).
[17]刘彦鹏.临涣中利发电有限公司2号锅炉掺烧煤泥燃烧调整试验报告[R].合肥:安徽新力电业科技咨询有限责任公司,2009.Liu Yanpeng.Adjustment test report on linhuan joinlion power Co.,LTD.2#boiler mix-burning coal slime[R].Hefei:Anhui Xinli Electric Technology Consulting Co.,Ltd,2009(in Chinese).
[18]刘彦鹏,李建民,余永生,等.300MW循环流化床锅炉掺烧煤泥试验研究[J].热力发电,2010,39(10):60-64,76.Liu Yanpeng,Li Jianmin,Yu Yongsheng,et al.Test study on mixedly burning coal slime in 300 MW CFB boiler[J].Thermal Power Generation,2010,39(10):60-64,76(in Chinese).
[19]吕游,刘吉臻,赵文杰,等.基于分段曲线拟合的稳态检测方法[J].仪器仪表学报,2012,33(1):194-200.LüYou,Liu Jizhen,Zhao Wenjie,et al.Steady-state detecting method based on piecewise curve fitting[J].Chinese Journal of Scientific Instrument,2012,33(1):194-200(in Chinese).
[20]吕游,刘吉臻,杨婷婷,等.基于PLS特征提取和LS-SVM结合的NOx排放特性建模[J].仪器仪表学报,2013,34(11):2418-2424.LüYou,Liu Jizhen,Yang Tingting,et al.NOx emission characteristic modeling based on feature extraction using PLS and LS-SVM[J].Chinese Journal of Scientific Instrument,2013,34(11):2418-2424(in Chinese).
[21]蒋士正,许榕,陈启美.基于变量选择-神经网络模型的复杂路网短时交通流预测[J].上海交通大学学报,2015,49(2):281-286.Jiang Shizheng,Xu Rong,Chen Qimei.Complex network short-term traffic forecasting based on lasso-NN model[J].Journal of Shanghai Jiaotong University,2015,49(2):281-286(in Chinese).
[2]杨锡运,孙宝君,张新房,等.基于相似数据的支持向量机短期风速预测仿真研究[J].中国电机工程学报,2012,32(4):35-41.Yang Xiyun,Sun Baojun,Zhang Xinfang,et al.Short-term wind speed forecasting based on support vector machine with similar data[J].Proceedings of the CSEE,2012,32(4):35-41(in Chinese).
[3]刘吉臻,秦天牧,杨婷婷,等.基于偏互信息的变量选择方法及其在火电厂SCR系统建模中的应用[J].中国电机工程学报,2016,36(9):2438-2443.Liu Jizhen,Qin Tianmu,Yang Tingting,et al.Variable selection method based on partial mutual information and its application in power plant SCR system modeling[J].Proceedings of the CSEE,2016,36(9):2438-2443(in Chinese).
[4]黄宇,韩璞,王东风,等.基于BP神经网络整定的PID控制在过热汽温系统中的应用[J].仪器仪表学报,2006,27(S6):1980-1981.Huang Yu,Han Pu,Wang Dongfeng,et al.PID control based on BP neural network for superheated steam temperature system[J].Chinese Journal of Scientific Instrument,2006,27(S6):1980-1981(in Chinese).
[5]王恺,关少卿,汪令祥,等.基于模糊信息粒化和最小二乘支持向量机的风电功率联合预测建模[J].电力系统保护与控制,2015,43(2):26-32.Wang Kai,Guan Shaoqing,Wang Lingxiang,et al.A combined forecasting model for wind power predication based on fuzzy information granulation and least squares support vector machine[J].Power System Protection and Control,2015,43(2):26-32(in Chinese).
[6]刘海军.CFB机组降低供电煤耗综合措施分析[J].神华科技,2013,11(6):54-57.Liu Haijun.Analysis of comprehensive measures to reduce the net coal consumption rate by CFB unit[J].Shenhua Science and Technology,2013,11(6):54-57(in Chinese).
[7]黄中,潘贵涛,张品高,等.300MW大型循环流化床锅炉运行分析与发展建议[J].锅炉技术,2014,45(6):35-41.Huang Zhong,Pan Guitao,Zhang Pingao,et al.Operating condition and development proposal of 300 MW large-scale circulating fluidized bed boiler[J].Boiler Technology,2014,45(6):35-41(in Chinese).
[8]王晓峰.提高循环流化床锅炉经济性分析[J].中国科技纵横,2014(1):189.Wang Xiaofeng.The economic analysis of circulating fluidized bed boiler[J].China Science&Technology Panorama Magazine,2014(1):189(in Chinese).
[9]秦建亭.浅谈300MW循环流化床锅炉如何提高效率、降低发电煤耗[C]//全国电力行业CFB机组技术交流服务协作网第十二届年会,淮南,2013.Qin Jianting.Discussion on how to improve the efficiency of 300mw circulating fluidized bed boiler to reduce the coal consumption of power generation[C]//Operation Management of Circulating Fluidized Bed Power Generation in China,Huannan,2013(in Chinese).
[10]薛少华.300MW循环流化床锅炉机组的节能降耗[J].锅炉制造,2014(3):9-11.Xue Shaohua.Energy saving and consumption reducing in300MW CFB boiler[J].Boiler Manufacturing,2014(3):9-11(in Chinese).
[11]钱志永,周智华,陈念祖.两种不同入炉煤颗粒度下210MW循环流化床机组的性能比较[J].锅炉技术,2009,40(1):34-37.Qian Zhiyong,Zhou Zhihua,Chen Nianzu.Performance comparison of 210 MW CFB unit under two different particle size of burning coal[J].Boiler Technology,2009,40(1):34-37(in Chinese).
[12]曾建微.循环流化床锅炉运行经济性分析及节能途径[J].节能技术,2005,23(4):378-381.Zeng Jianwei.Analysis of operation economic and the approach of economize on energy of the circulating fluidized bed boiler[J].Energy Conservation Technology,2005,23(4):378-381(in Chinese).
[13]高大明,陈鸿伟,谷俊杰,等.富氧燃烧循环流化床锅炉烟气动态特性与运行经济性分析[J].中国电机工程学报,2014,34(S1):112-121.Gao Daming,Chen Hongwei,Gu Junjie,et al.Flue gas dynamic characteristics and operation economic analysis of oxy-fuel combustion circulating fluidized bed boiler[J].Proceedings of the CSEE,2014,34(S1):112-121(in Chinese).
[14]崔超,杨婷婷,刘吉臻,等.基于BP网络变量选择与LSSVM结合的锅炉脱硝经济性建模[J].中国电机工程学报,2015,35(24):6413-6420.Cui Chao,Yang Tingting,Liu Jizhen,et al.Denitration cost modeling for boilers based on BP variable selection and LSSVM[J].Proceedings of the CSEE,2015,35(24):6413-6420(in Chinese).
[15]张华,曾杰.基于支持向量机的风速预测模型研究[J].太阳能学报,2010,31(7):928-932.Zhang Hua,Zeng Jie.Wind speed forecasting model study based on support vector machine[J].Acta Energiae Solaris Sinica,2010,31(7):928-932(in Chinese).
[16]王书舟,伞冶.支持向量机的训练算法综述[J].智能系统学报,2008,3(6):467-475.Wang Shuzhou,San Ye.A survey on training algorithms for support vector machine[J].CAAI Transactions on Intelligent Systems,2008,3(6):467-475(in Chinese).
[17]刘彦鹏.临涣中利发电有限公司2号锅炉掺烧煤泥燃烧调整试验报告[R].合肥:安徽新力电业科技咨询有限责任公司,2009.Liu Yanpeng.Adjustment test report on linhuan joinlion power Co.,LTD.2#boiler mix-burning coal slime[R].Hefei:Anhui Xinli Electric Technology Consulting Co.,Ltd,2009(in Chinese).
[18]刘彦鹏,李建民,余永生,等.300MW循环流化床锅炉掺烧煤泥试验研究[J].热力发电,2010,39(10):60-64,76.Liu Yanpeng,Li Jianmin,Yu Yongsheng,et al.Test study on mixedly burning coal slime in 300 MW CFB boiler[J].Thermal Power Generation,2010,39(10):60-64,76(in Chinese).
[19]吕游,刘吉臻,赵文杰,等.基于分段曲线拟合的稳态检测方法[J].仪器仪表学报,2012,33(1):194-200.LüYou,Liu Jizhen,Zhao Wenjie,et al.Steady-state detecting method based on piecewise curve fitting[J].Chinese Journal of Scientific Instrument,2012,33(1):194-200(in Chinese).
[20]吕游,刘吉臻,杨婷婷,等.基于PLS特征提取和LS-SVM结合的NOx排放特性建模[J].仪器仪表学报,2013,34(11):2418-2424.LüYou,Liu Jizhen,Yang Tingting,et al.NOx emission characteristic modeling based on feature extraction using PLS and LS-SVM[J].Chinese Journal of Scientific Instrument,2013,34(11):2418-2424(in Chinese).
[21]蒋士正,许榕,陈启美.基于变量选择-神经网络模型的复杂路网短时交通流预测[J].上海交通大学学报,2015,49(2):281-286.Jiang Shizheng,Xu Rong,Chen Qimei.Complex network short-term traffic forecasting based on lasso-NN model[J].Journal of Shanghai Jiaotong University,2015,49(2):281-286(in Chinese).