偏最小二乘回归及其在污垢预测中的应用
|
摘要
为寻求判别燃煤锅炉结渣特性的统一标准,本文选择适合我国标准的灰的软化温度、碱酸比、硅比、硅铝比、无因次炉膛平均温度和无因次炉膛切圆直径六个指标作为输入,以锅炉实际结渣程度作为输出,建立判别燃煤锅炉结渣倾向的非线性迭代PLS数字模式识别模型。把炉膛结渣程度分为轻微、中等、严重三种情况,分别记作第1类(记为1)、第2类(记为2)、第3类(记为3),并规定把预测值小于1.5的归为第1类,预测值大于或等于1.5小于2.5的归为第2类,大于或等于2.5的归为第3类。结果表明,本模型具有很好的预测效果和适用范围,其回判准确率和预报准确率均为100%。
为了更精确地预测换热设备的结垢情况,本文选择影响松花江水结垢的11个主要水质参数:铁离子、氯离子、细菌总数、pH值、溶解氧、浊度、电导率、细菌总数、碱度、硬度和时间等作为输入参数,任一组不同时刻的20组数据作为模型的训练(前15组)和检测样本(后5组),建立了板式换热器的污垢热阻预测模型,此模型预测效果良好。然后去掉模型的部分水质参数,并根据其预测结果分析水质参数对污垢的影响。
本文用60个已知煤灰变形温度的样本,以十个煤灰成份作为输入变量,利用PLS回归模型对煤灰变形温度DT进行预测。然后依次减少PLS回归模型输入变量的个数来预测灰熔点,并比较其预测结果。结果表明,采用10个煤灰成分作为输入变量时的预测结果最精确。
To seek for the uniform standards to judge characteristics of coal boiler slagging, this thesis chooses the six parameters including ash softening temperature, alkaline acid ratio, silicon ratio, silicon aluminum ratio, average temperature of non-dimensional hearth furnace and non-dimensional cut circle diameter as inputs. Boiler actual slagging degree is chosen as output, and establishes nonlinear iterative partial least squares regression (PLS) digital pattern recognition model discriminating the coal boiler slagging tendency. The degree of hearth slagging can be divided into three kinds, namely mild, moderate, and severe. These three kinds can be written as 1st class (note for 1), notes 2nd class (notes for 2) and the 3rd class (notes for 3), respectively; and the predictive value which is less than 1.5 is divided into the first category which, is equal to or greater than 1.5 less than 2.5 and is divided into the second category, which is equal to or greater than 2.5. It is gathered for the third kinds. Results show that the accuracy of forecasting and the accuracy of the back sentence to all is 100%.
In order to accurately predict the fouling of heat exchange equipment, the time and 10 main water quality parameters have effect on the scaling of Songhuajiang river are iron, chloride ion, bacteria, pH value, dissolved oxygen, turbidity, conductivity, bacteria, alkalinity, hardness, etc. They were used as input variables. This thesis chooses 20 groups of data at different times, with the former 15 groups as a model of training and the latter 5 groups as test sample, and establishes a prediction model of plate heat exchanger of fouling resistances. This model has achieved good prediction results. Then the paper establishes anti-removed part prediction model of water quality parameters, and analyses the influence of water quality parameters dirt according to its prediction results.
Adopting ten components of coal ash as input variables, the model for ash fusion which was trained by 60 samples was set up by use of partial least-square regression method. Then the PLS regression model is used to forecast ash deformation temperature (DT) of the coal with orderly decreased input variables. The predicted results with different numbers of ash component as the input variables were compared. Results show that the predicting results using ten components of coal ash as input variables are most accurate.
为了更精确地预测换热设备的结垢情况,本文选择影响松花江水结垢的11个主要水质参数:铁离子、氯离子、细菌总数、pH值、溶解氧、浊度、电导率、细菌总数、碱度、硬度和时间等作为输入参数,任一组不同时刻的20组数据作为模型的训练(前15组)和检测样本(后5组),建立了板式换热器的污垢热阻预测模型,此模型预测效果良好。然后去掉模型的部分水质参数,并根据其预测结果分析水质参数对污垢的影响。
本文用60个已知煤灰变形温度的样本,以十个煤灰成份作为输入变量,利用PLS回归模型对煤灰变形温度DT进行预测。然后依次减少PLS回归模型输入变量的个数来预测灰熔点,并比较其预测结果。结果表明,采用10个煤灰成分作为输入变量时的预测结果最精确。
To seek for the uniform standards to judge characteristics of coal boiler slagging, this thesis chooses the six parameters including ash softening temperature, alkaline acid ratio, silicon ratio, silicon aluminum ratio, average temperature of non-dimensional hearth furnace and non-dimensional cut circle diameter as inputs. Boiler actual slagging degree is chosen as output, and establishes nonlinear iterative partial least squares regression (PLS) digital pattern recognition model discriminating the coal boiler slagging tendency. The degree of hearth slagging can be divided into three kinds, namely mild, moderate, and severe. These three kinds can be written as 1st class (note for 1), notes 2nd class (notes for 2) and the 3rd class (notes for 3), respectively; and the predictive value which is less than 1.5 is divided into the first category which, is equal to or greater than 1.5 less than 2.5 and is divided into the second category, which is equal to or greater than 2.5. It is gathered for the third kinds. Results show that the accuracy of forecasting and the accuracy of the back sentence to all is 100%.
In order to accurately predict the fouling of heat exchange equipment, the time and 10 main water quality parameters have effect on the scaling of Songhuajiang river are iron, chloride ion, bacteria, pH value, dissolved oxygen, turbidity, conductivity, bacteria, alkalinity, hardness, etc. They were used as input variables. This thesis chooses 20 groups of data at different times, with the former 15 groups as a model of training and the latter 5 groups as test sample, and establishes a prediction model of plate heat exchanger of fouling resistances. This model has achieved good prediction results. Then the paper establishes anti-removed part prediction model of water quality parameters, and analyses the influence of water quality parameters dirt according to its prediction results.
Adopting ten components of coal ash as input variables, the model for ash fusion which was trained by 60 samples was set up by use of partial least-square regression method. Then the PLS regression model is used to forecast ash deformation temperature (DT) of the coal with orderly decreased input variables. The predicted results with different numbers of ash component as the input variables were compared. Results show that the predicting results using ten components of coal ash as input variables are most accurate.
引文
[1]杨善让,徐志明,孙灵芳.换热设备的污垢与对策.2版.北京:科学出版社,2004.8～14
[2] S M Cho . Uncertainty analysis of heat exchanger thermal-hydraulic designs.Heat Transfer Engineering,1987,8(2):63～74
[3] N Epstein.Fouling in Heat Exchangers.Heat Transfer 1978-Proc 6th IHTC,1979,6:235～253
[4]张明玉.特氟龙涂层特性对CaCO3污垢影响的研究:[工学硕士学位论文].吉林:东北电力大学,2009. 1～2
[5] P A Pilarachi,J D Isdate.European Community R&D Strategy in the Field of Heat Exchanger Fouling Projects.Fouling Mechanisms,1992,13～20
[6] D Chaudagne.Fouling Costs in the Field of Heat Exchanger Equipment in the French Market.Fouling Mechanisms,1992.21～25
[7]徐志明,杨善让,郭淑青等.电站凝汽器污垢费用估算.中国动力工程学报,2005,25(1):102～106
[8]樊泉桂,阎维平.锅炉原理.北京:中国电力出版社,2004.21～22
[9]樊绍圣.凝汽器污垢的灰色预测.电力科学与技术学报,2007,22(2):12～15
[10]樊绍胜,王耀南.基于T-S模型的冷凝器污垢预测.传感技术学报,2005,18(1):123～128
[11]樊绍胜,王耀南.基于多模型组合的冷凝器中污垢预测.传感技术学报,2005,18(6):225～228
[12]柴海棣,王维航,张连生.基于径向基神经网络的污垢预测方法研究.东北电力大学学报,2006,26(4):46～49
[13]彭珍,张充,吴立锋等.基于RBF神经网络的换热管污垢热阻预测.煤气与热力,2008,28(6):A26～A28.
[14]徐志明,文孝强,孙媛媛等.基于最小二乘支持向量回归机的光管污垢特性预测.化工学报,2009,60(7):1617～1622
[15]赵波,杨善让,刘范等.冷却水污垢热阻预测的支持向量机法动态模拟实验研究.中国电机工程学报,2010,30(11):92～97
[16]张莹,王耀南.基于局部加权偏最小二乘法的冷凝器污垢预测.仪器仪表学报,2010,31(2):299～304
[17] D Q KERN,R E SEATON.A theoretical analysis of thermal surface fouling.British Chemical Engineering,1959,2(5):252～25
[18] P CRISTIANI.Solutions to fouling in power station con-densers.Applied Thermal Engineering,2005,25(1):2630～2640
[19]徐志明,文孝强,孙媛媛等.基于最小二乘支持向量回归机的燃煤锅炉结渣特性预测.中国电机工程学报,2009,29(17):8～13
[20]陈立军,文孝强,王恭等.燃煤锅炉结渣特性预测方法综述.热力发电,2006,35(6):1～4
[21]徐乾.模糊综合评判模型预测电站燃煤结渣特性的研究.锅炉技术,2006,37(2):55～58
[22]陈春华,施发,承陈俊.电站锅炉结渣倾向性模糊综合评判.锅炉技术,2005,36(3):28～30
[23]赵显桥,曹欣玉,兰泽全等.基于粗集理论的煤灰结渣模糊综合评判权系数确定方法研究.煤炭学报,2004,29(2):222～225
[24]舒红宁,黄镇宇,董一真等.基于煤灰成分的非线性结渣模糊综合预测模型的研究.电站系统工程,2006,22(4):11～12
[25]郭嘉,曾汉才.电站燃煤结渣特性的模糊模式识别.热力发电,1994,(2):4～6
[26]赵利敏,路丕思.电站锅炉结渣的模糊数学预示分析.黑龙江电力技术,1996,18(3):129～132
[27]兰泽全,曹欣玉,周俊虎等.模糊模式识别在水煤浆锅炉结渣特性判别上的应用.中国电机工程学报,2003,23(7):216～219
[28]伍昌鸿,马晓茜,廖艳芬.基于模糊神经网络的电站燃煤锅炉结渣预测.燃烧科学与技术,2006,12(2):175～179
[29]文孝强.基于检测的燃煤锅炉积灰、结渣研究:[工学硕士学位论文].吉林:东北电力大学,2006.3
[30]张忠孝.用模糊数学方法对电厂锅炉结渣特性的研究.中国电机工程学报.2000,20(10):64～66
[31]常公鹏,支国军.电厂锅炉结渣预测模型研究.电力学报,2004,19(1):15～17
[32]丁世飞.基于信息理论的数字模式识别及应用研究:[博士学位论文].山东:山东科技大学2004.59～65
[33]煤炭工业部.全国煤质资料汇编.北京:煤炭工业出版社,1981.8～12
[34] Yin ChungenLuo,Zhongyang,Ni Mingjiang etal.Predicting coal ash fusion temperature with a back-propagation neural network model.Fuel,1998,77(15):1777～1782
[35]李建中,周昊,王春林等.支持向量机技术在动力配煤中灰熔点预测的应用.煤炭学报,2007,32(1):81～84
[36]王春林,周昊,李国能等.基于支持向量机与遗传算法的灰熔点预测.中国电机工程学报,2007,27(8):11～15
[37]刘彦鹏,仲玉芳,钱积新等.蚁群前馈神经网络在煤灰熔点预测中的应用.热力发电,2007,36(8):23～26
[38]蔡晓辉,武进猛,侯伟.600MW超临界煤粉炉燃烧过程数值模拟.应用能源技术,2009,141(9):18～21
[39]赵振宁,佟义英,方占岭等.300MW锅炉掺烧低灰熔点煤种的应用研究.动力工程,2009,29(6):516～521
[40]丁世飞,史忠植,靳奉祥.非线性迭代PLS信息模式识别算法.计算机工程,2008,4(1):20～22
[41]全贞花,陈永昌,马重芳等.碳酸钙于换热表面结垢影响因素的模拟分析.工程热物理学报,2008,29(11):1944～1946
[42] D H Lister,F C Cussac.Modelling of particulate fouling on heat exchanger surfaces:influence of bubbles on iron oxide deposition.Heat ExchangerFouling and Cleaning-VII,Tomar,Portugal,2007
[43]黄新平,黄春梅.循环冷却水中氮离子对板换材料选择的影响.石油化工设计,2006,23(2):44～46
[44] R Sheikholeslami,S Tan.Effects of water quality on silica fouling of desalination plants. Desalination,November,1999,126:267～280
[45]王泉清,曾蒲君.煤灰熔融性的研究现状与分析.煤炭转化,1997,20(4):32～37
[46] B K Dutta,B Rai,K R Chakravorty.SciIndustrRes,1962,ZID
[47]叶江明.电厂锅炉原理及设备.北京:中国电力出版社,2004.21～26
[48]唐启义,冯明光.实用统计分析及其DPS数据处理系统.北京:科学出版社,2002.45～52
[2] S M Cho . Uncertainty analysis of heat exchanger thermal-hydraulic designs.Heat Transfer Engineering,1987,8(2):63～74
[3] N Epstein.Fouling in Heat Exchangers.Heat Transfer 1978-Proc 6th IHTC,1979,6:235～253
[4]张明玉.特氟龙涂层特性对CaCO3污垢影响的研究:[工学硕士学位论文].吉林:东北电力大学,2009. 1～2
[5] P A Pilarachi,J D Isdate.European Community R&D Strategy in the Field of Heat Exchanger Fouling Projects.Fouling Mechanisms,1992,13～20
[6] D Chaudagne.Fouling Costs in the Field of Heat Exchanger Equipment in the French Market.Fouling Mechanisms,1992.21～25
[7]徐志明,杨善让,郭淑青等.电站凝汽器污垢费用估算.中国动力工程学报,2005,25(1):102～106
[8]樊泉桂,阎维平.锅炉原理.北京:中国电力出版社,2004.21～22
[9]樊绍圣.凝汽器污垢的灰色预测.电力科学与技术学报,2007,22(2):12～15
[10]樊绍胜,王耀南.基于T-S模型的冷凝器污垢预测.传感技术学报,2005,18(1):123～128
[11]樊绍胜,王耀南.基于多模型组合的冷凝器中污垢预测.传感技术学报,2005,18(6):225～228
[12]柴海棣,王维航,张连生.基于径向基神经网络的污垢预测方法研究.东北电力大学学报,2006,26(4):46～49
[13]彭珍,张充,吴立锋等.基于RBF神经网络的换热管污垢热阻预测.煤气与热力,2008,28(6):A26～A28.
[14]徐志明,文孝强,孙媛媛等.基于最小二乘支持向量回归机的光管污垢特性预测.化工学报,2009,60(7):1617～1622
[15]赵波,杨善让,刘范等.冷却水污垢热阻预测的支持向量机法动态模拟实验研究.中国电机工程学报,2010,30(11):92～97
[16]张莹,王耀南.基于局部加权偏最小二乘法的冷凝器污垢预测.仪器仪表学报,2010,31(2):299～304
[17] D Q KERN,R E SEATON.A theoretical analysis of thermal surface fouling.British Chemical Engineering,1959,2(5):252～25
[18] P CRISTIANI.Solutions to fouling in power station con-densers.Applied Thermal Engineering,2005,25(1):2630～2640
[19]徐志明,文孝强,孙媛媛等.基于最小二乘支持向量回归机的燃煤锅炉结渣特性预测.中国电机工程学报,2009,29(17):8～13
[20]陈立军,文孝强,王恭等.燃煤锅炉结渣特性预测方法综述.热力发电,2006,35(6):1～4
[21]徐乾.模糊综合评判模型预测电站燃煤结渣特性的研究.锅炉技术,2006,37(2):55～58
[22]陈春华,施发,承陈俊.电站锅炉结渣倾向性模糊综合评判.锅炉技术,2005,36(3):28～30
[23]赵显桥,曹欣玉,兰泽全等.基于粗集理论的煤灰结渣模糊综合评判权系数确定方法研究.煤炭学报,2004,29(2):222～225
[24]舒红宁,黄镇宇,董一真等.基于煤灰成分的非线性结渣模糊综合预测模型的研究.电站系统工程,2006,22(4):11～12
[25]郭嘉,曾汉才.电站燃煤结渣特性的模糊模式识别.热力发电,1994,(2):4～6
[26]赵利敏,路丕思.电站锅炉结渣的模糊数学预示分析.黑龙江电力技术,1996,18(3):129～132
[27]兰泽全,曹欣玉,周俊虎等.模糊模式识别在水煤浆锅炉结渣特性判别上的应用.中国电机工程学报,2003,23(7):216～219
[28]伍昌鸿,马晓茜,廖艳芬.基于模糊神经网络的电站燃煤锅炉结渣预测.燃烧科学与技术,2006,12(2):175～179
[29]文孝强.基于检测的燃煤锅炉积灰、结渣研究:[工学硕士学位论文].吉林:东北电力大学,2006.3
[30]张忠孝.用模糊数学方法对电厂锅炉结渣特性的研究.中国电机工程学报.2000,20(10):64～66
[31]常公鹏,支国军.电厂锅炉结渣预测模型研究.电力学报,2004,19(1):15～17
[32]丁世飞.基于信息理论的数字模式识别及应用研究:[博士学位论文].山东:山东科技大学2004.59～65
[33]煤炭工业部.全国煤质资料汇编.北京:煤炭工业出版社,1981.8～12
[34] Yin ChungenLuo,Zhongyang,Ni Mingjiang etal.Predicting coal ash fusion temperature with a back-propagation neural network model.Fuel,1998,77(15):1777～1782
[35]李建中,周昊,王春林等.支持向量机技术在动力配煤中灰熔点预测的应用.煤炭学报,2007,32(1):81～84
[36]王春林,周昊,李国能等.基于支持向量机与遗传算法的灰熔点预测.中国电机工程学报,2007,27(8):11～15
[37]刘彦鹏,仲玉芳,钱积新等.蚁群前馈神经网络在煤灰熔点预测中的应用.热力发电,2007,36(8):23～26
[38]蔡晓辉,武进猛,侯伟.600MW超临界煤粉炉燃烧过程数值模拟.应用能源技术,2009,141(9):18～21
[39]赵振宁,佟义英,方占岭等.300MW锅炉掺烧低灰熔点煤种的应用研究.动力工程,2009,29(6):516～521
[40]丁世飞,史忠植,靳奉祥.非线性迭代PLS信息模式识别算法.计算机工程,2008,4(1):20～22
[41]全贞花,陈永昌,马重芳等.碳酸钙于换热表面结垢影响因素的模拟分析.工程热物理学报,2008,29(11):1944～1946
[42] D H Lister,F C Cussac.Modelling of particulate fouling on heat exchanger surfaces:influence of bubbles on iron oxide deposition.Heat ExchangerFouling and Cleaning-VII,Tomar,Portugal,2007
[43]黄新平,黄春梅.循环冷却水中氮离子对板换材料选择的影响.石油化工设计,2006,23(2):44～46
[44] R Sheikholeslami,S Tan.Effects of water quality on silica fouling of desalination plants. Desalination,November,1999,126:267～280
[45]王泉清,曾蒲君.煤灰熔融性的研究现状与分析.煤炭转化,1997,20(4):32～37
[46] B K Dutta,B Rai,K R Chakravorty.SciIndustrRes,1962,ZID
[47]叶江明.电厂锅炉原理及设备.北京:中国电力出版社,2004.21～26
[48]唐启义,冯明光.实用统计分析及其DPS数据处理系统.北京:科学出版社,2002.45～52