造纸过程能源管理系统中数据挖掘与能耗预测方法的研究
|
摘要
造纸是我国九大高耗能行业之一，在环境、政策与市场压力下造纸企业面临着巨大的节能压力。节能方式一般可以分为三大类：①结构节能；②技术节能；③管理节能。其中，管理节能即对结构节能与技术节能提供重要支持，又可实现能源效率的持续改进，能源管理系统（Energy Management System，EMS）是管理节能的核心。能源管理系统是一项整合自动化和信息化技术的管控一体化节能新技术，通过对企业能源转换，利用和回收实施动态监控，改进和优化能源平衡，实现系统性节能降耗。
本研究以广州造纸厂（海珠厂区）为对象，以GE智能平台为软件平台，研究并实现课题组能源管理系统(Mill Energy Optimization Platform，MEOP)中的关键模块——数据集成和能量信息实时计算，实现造纸企业能量系统的集中化、精细化管理。并通过对能源管理系统中的数据交互技术的研究，实现MEOP与基于造纸过程的各种功能模型的集成。能源管理系统的建立实现了全厂能量信息的准确、透明、实时获取，以广州造纸厂2009年PM1单位产品能耗指标为例，MEOP计算结果与人工统计结果的均方根误差为0.47GJ/t，平均相对误差为6.79%，MEOP还实现了该指标时间间隔为1分钟的实时计算，时效性远高于人工统计周期1个月。除了单位产品能耗等重要能效指标外，MEOP还支持基于物流数据的能流数据计算，这些丰富的实时能量信息提供了对生产过程能耗状况及能流流向的深入理解。在数据集成与能量信息提取的基础上，通过能源管理系统中的数据交互技术实现了MEOP与基于造纸过程的各种功能模型的集成，进而实现了能量监控、能量分析等能源管理系统重要功能，并且丰富的生产过程数据和能量信息为后续能源影响因素分析与挖掘、能耗预测提供了重要数据基础。
造纸生产过程具有海量的生产数据，但理解它们已超出了人的能力，常常使操作人员陷入“数据丰富，信息贫乏”的困境。本研究以能源管理系统为平台，以造纸过程海量生产数据为基础，对生产过程能源影响因素进行数据挖掘。针对造纸过程多变量、变量间多重相关和生产过程海量数据的特点，使用主成分分析（Principal ComponentAnalysis，PCA）、偏最小二乘分析（Partial Least Square，PLS）等多变量变换与筛选方法，对造纸过程能源影响因素的重要性进行分析与挖掘，得到了具有重要影响的能源影响因素，实现了能源影响因素的重要性排序，并根据能源影响因素的重要性分析结果，对能源影响因素进行了筛选，去除了与能耗无明显相关关系的能源影响因素。研究结果表明，合适的数据预处理和PLS相结合，可以实现对具有多重相关性的能源影响因素的重要性分析，发现与识别造纸生产过程中的主要能源影响因素，进而为各种节能技术改造、能源消耗异常分析、能耗预测等提供重要支持。
基于能源影响因素的PLS分析结果，并针对偏最小二乘分析和人工神经网络各自的优势和特点，提出用PLS-ANN预测模型预测造纸过程能耗。为了提高预测的准确性，根据造纸生产过程各个工序的能耗特点，对造纸过程能耗进行划分与分类，针对每个能耗划分类型，应用适合的预测模型——PLS-ANN或ANN，对各个工序的能耗实施预测。在工序能耗预测的基础上，实现对整个造纸过程未来1小时能耗的有效预测。结果显示，对于造纸过程电耗，预测的均方根误差为9.02kWh/t，预测值与测量值的相关系数为0.95，对于造纸过程蒸汽消耗，预测的均方根误差为0.03t/t，预测值与测量值的相关系数为0.88，达到了较好的预测效果。通过造纸过程能耗的有效预测，可以为能源转换环节的生产提供重要支持，减少能源浪费，进而实现能量系统的动态平衡。
本论文主要是关于方法和应用的研究，主要创新和特色之处为：
1)在造纸企业能源管理信息系统中引入基于物料流和物料热力学性质的能量信息实时计算，获取准确、透明、实时的能量信息；
2)针对造纸过程多变量、变量间多重相关和生产过程海量数据的特点，将PCA、PLS等多变量变换、筛选技术应用到造纸过程能源影响因素的分析与挖掘中来。通过合适的数据预处理技术与PLS相结合，实现能源影响因素的变换和重要性分析，对造纸过程的重要能源影响因素进行识别；
3)对造纸过程能量系统进行合理划分，针对各个能耗划分类型，分别建立合适的预测模型，提高能耗预测的准确度。提出偏最小二乘分析与人工神经网络相结合的PLS-ANN预测模型，该预测模型即包含PLS在数据分析与解释方面的优势，又包含人工神经网络在非线性建模、自学习和自适应方面的优势。
Paper industry is one of the nine high-energy-consumption industries in China, andnowadays paper mills are facing enormous pressure to save energy under the severe situationsof environment, policy and market. Energy saving methods can be generally classified intothe following three categories:①saving energy with structural adjustment;②saving energywith technical renovation;③saving energy with management reform. And managementmethods not only provide important support to structural and technical methods, but alsocontinuously improve energy efficiency.EMS (Energy Management System) takes a key rolein the management energy-saving methods. EMS is a new management-control integrationtechnology on energy-saving which combines automation and information technology, itapplies dynamic monitoring on energy conversion, utilization and recycling within the mills,improves and optimizes energy balance and realizes the mill-wide energy-saving.
Guangzhou Paper mill (Haizhu district) was taken as the object to carry out our research,GE Intelligent Platform was taken as the software platform, and then the core modules ofMEOP (Mill Energy Optimization Platform)——Data Integration and Real-Time Calculationof Energy Information was developed to achieve the centralized and meticulous managementof energy system in the studied paper mill. Then the specific interaction techniques in EMSwere employed to realize the integration of MEOP and functional models based onpapermaking process. The established MEOP realized the accurate, transparent and real-timeaccess to the mill-wide energy information. Taking the2009PM1specific energyconsumption indicator for an example, the RMSE (Root Mean Square Error) between MEOPand manual statistic is0.47GJ/t, MPE (Mean Percentage Error) is6.79%, and in addition,MEOP realized the real-time calculation of this indicator with interval of1minute, whosetimeliness was much higher than manual statistic of1month. Apart from the specific energyconsumption and such other energy efficiency indicators, MEOP also supported to access theenergy flow data based on material flow, this rich real-time energy information provided adeep understand to the process energy consumption and energy flow. Based on dataintegration and energy information extraction, the integration of MEOP and papermaking process functional models was achieved by data interaction techniques in EMS, and thenenergy monitoring, energy analysis and such other basic EMS functions were fulfilled,moreover rich process data and energy information provided fundamental data for furtherenergy factors analysis and mining, and energy consumption prediction.
There are a mass amount of process data in papermaking process, but comprehensiveunderstanding of these data is beyond of human’s capability, and operators are always trappedin the trouble of “rich data but poor information”. Based on the EMS, the research took themassive process data as foundation and energy consumption prediction as final goal, thenadopted data mining techniques to analyze and mine the energy influencing factors inpapermaking process. According to the process data characteristics, such as multivariable,multi-correlation among variables and massive data, PCA (Principal Component Analysis),PLS (Partial Least Square) and such multivariate transformation and selection methods wereintroduced and combined to analyze and mine the importance of energy influencing factors inpapermaking process. As a result, the important energy influencing factors were obtained andthe importance of energy influencing factors was ranked. Then according to the variablesimportance analysis result, important energy influencing factors were selected, and energyinfluencing factors with no obvious correlation to energy consumption were removed. Theresearch shows that the combination of proper data preprocessing and PLS can realize theimportance analysis of multi-correlation energy influencing factors and provide importantsupport to energy-saving technical retrofits, abnormal energy consumption analysis andenergy consumption prediction, etc.
Based on the PLS analysis results of energy influencing factors, and according to theadvantages and characteristics of PLS and ANN, a novel PLS-ANN prediction model wasdeveloped to predict process energy consumption. For improving the accuracy, thepapermaking process energy consumption was classified based on the energy consumptioncharacteristics of each process procedure, and according to each energy consumption divisiontype, appropriate prediction model——PLS-ANN or ANN, was taken to realize the energyconsumption prediction of each process procedure. Based on the energy consumptionprediction of each process procedure, the effective1hour energy consumption prediction ofthe entire papermaking process was achieved. The results show that for the power consumption of papermaking process, the prediction RMSE is9.02kWh/t and the correlationcoefficient between predicted data and measured data is0.95, and for the steam consumptionof papermaking process, the prediction RMSE is0.03t/t and the correlation coefficientbetween predicted data and measured data is0.88, it shows the proposed prediction methodhas good precision. The effective energy consumption prediction of papermaking process canprovide important support to optimize the operation in energy conversion section and reduceenergy waste, then benefit to realize the dynamic balance of process energy system.
This thesis focuses on the study of methods and applications, and its features andinnovation points are:
1) The real-time energy information calculation based on material flow and materialthermodynamic properties is introduced to the EMS of paper process, and accurate,transparent and real-time energy information are obtained;
2) According to the characteristics of papermaking process data, such as multivariable,multi-correlation among variables and massive data, PCA, PLS and suchmultivariate transformation and selection methods are employed to analyze andmine the energy influencing factors in paper process. Appropriate data preprocessingmethods and PLS are combined to realize the transformation and importanceanalysis of energy influencing factors, and to identify the primary energy influencingfactors;
3) The division and classification of energy system of paper process is introduced, andaccording to each energy consumption division type, appropriate prediction model isestablished to improve the energy consumption prediction accuracy. And aPLS-ANN prediction model is developed which combines the PLS advantages indata analysis and interpretation and the ANN advantages in nonlinear modeling,self-learning and adaptability.
本研究以广州造纸厂（海珠厂区）为对象，以GE智能平台为软件平台，研究并实现课题组能源管理系统(Mill Energy Optimization Platform，MEOP)中的关键模块——数据集成和能量信息实时计算，实现造纸企业能量系统的集中化、精细化管理。并通过对能源管理系统中的数据交互技术的研究，实现MEOP与基于造纸过程的各种功能模型的集成。能源管理系统的建立实现了全厂能量信息的准确、透明、实时获取，以广州造纸厂2009年PM1单位产品能耗指标为例，MEOP计算结果与人工统计结果的均方根误差为0.47GJ/t，平均相对误差为6.79%，MEOP还实现了该指标时间间隔为1分钟的实时计算，时效性远高于人工统计周期1个月。除了单位产品能耗等重要能效指标外，MEOP还支持基于物流数据的能流数据计算，这些丰富的实时能量信息提供了对生产过程能耗状况及能流流向的深入理解。在数据集成与能量信息提取的基础上，通过能源管理系统中的数据交互技术实现了MEOP与基于造纸过程的各种功能模型的集成，进而实现了能量监控、能量分析等能源管理系统重要功能，并且丰富的生产过程数据和能量信息为后续能源影响因素分析与挖掘、能耗预测提供了重要数据基础。
造纸生产过程具有海量的生产数据，但理解它们已超出了人的能力，常常使操作人员陷入“数据丰富，信息贫乏”的困境。本研究以能源管理系统为平台，以造纸过程海量生产数据为基础，对生产过程能源影响因素进行数据挖掘。针对造纸过程多变量、变量间多重相关和生产过程海量数据的特点，使用主成分分析（Principal ComponentAnalysis，PCA）、偏最小二乘分析（Partial Least Square，PLS）等多变量变换与筛选方法，对造纸过程能源影响因素的重要性进行分析与挖掘，得到了具有重要影响的能源影响因素，实现了能源影响因素的重要性排序，并根据能源影响因素的重要性分析结果，对能源影响因素进行了筛选，去除了与能耗无明显相关关系的能源影响因素。研究结果表明，合适的数据预处理和PLS相结合，可以实现对具有多重相关性的能源影响因素的重要性分析，发现与识别造纸生产过程中的主要能源影响因素，进而为各种节能技术改造、能源消耗异常分析、能耗预测等提供重要支持。
基于能源影响因素的PLS分析结果，并针对偏最小二乘分析和人工神经网络各自的优势和特点，提出用PLS-ANN预测模型预测造纸过程能耗。为了提高预测的准确性，根据造纸生产过程各个工序的能耗特点，对造纸过程能耗进行划分与分类，针对每个能耗划分类型，应用适合的预测模型——PLS-ANN或ANN，对各个工序的能耗实施预测。在工序能耗预测的基础上，实现对整个造纸过程未来1小时能耗的有效预测。结果显示，对于造纸过程电耗，预测的均方根误差为9.02kWh/t，预测值与测量值的相关系数为0.95，对于造纸过程蒸汽消耗，预测的均方根误差为0.03t/t，预测值与测量值的相关系数为0.88，达到了较好的预测效果。通过造纸过程能耗的有效预测，可以为能源转换环节的生产提供重要支持，减少能源浪费，进而实现能量系统的动态平衡。
本论文主要是关于方法和应用的研究，主要创新和特色之处为：
1)在造纸企业能源管理信息系统中引入基于物料流和物料热力学性质的能量信息实时计算，获取准确、透明、实时的能量信息；
2)针对造纸过程多变量、变量间多重相关和生产过程海量数据的特点，将PCA、PLS等多变量变换、筛选技术应用到造纸过程能源影响因素的分析与挖掘中来。通过合适的数据预处理技术与PLS相结合，实现能源影响因素的变换和重要性分析，对造纸过程的重要能源影响因素进行识别；
3)对造纸过程能量系统进行合理划分，针对各个能耗划分类型，分别建立合适的预测模型，提高能耗预测的准确度。提出偏最小二乘分析与人工神经网络相结合的PLS-ANN预测模型，该预测模型即包含PLS在数据分析与解释方面的优势，又包含人工神经网络在非线性建模、自学习和自适应方面的优势。
Paper industry is one of the nine high-energy-consumption industries in China, andnowadays paper mills are facing enormous pressure to save energy under the severe situationsof environment, policy and market. Energy saving methods can be generally classified intothe following three categories:①saving energy with structural adjustment;②saving energywith technical renovation;③saving energy with management reform. And managementmethods not only provide important support to structural and technical methods, but alsocontinuously improve energy efficiency.EMS (Energy Management System) takes a key rolein the management energy-saving methods. EMS is a new management-control integrationtechnology on energy-saving which combines automation and information technology, itapplies dynamic monitoring on energy conversion, utilization and recycling within the mills,improves and optimizes energy balance and realizes the mill-wide energy-saving.
Guangzhou Paper mill (Haizhu district) was taken as the object to carry out our research,GE Intelligent Platform was taken as the software platform, and then the core modules ofMEOP (Mill Energy Optimization Platform)——Data Integration and Real-Time Calculationof Energy Information was developed to achieve the centralized and meticulous managementof energy system in the studied paper mill. Then the specific interaction techniques in EMSwere employed to realize the integration of MEOP and functional models based onpapermaking process. The established MEOP realized the accurate, transparent and real-timeaccess to the mill-wide energy information. Taking the2009PM1specific energyconsumption indicator for an example, the RMSE (Root Mean Square Error) between MEOPand manual statistic is0.47GJ/t, MPE (Mean Percentage Error) is6.79%, and in addition,MEOP realized the real-time calculation of this indicator with interval of1minute, whosetimeliness was much higher than manual statistic of1month. Apart from the specific energyconsumption and such other energy efficiency indicators, MEOP also supported to access theenergy flow data based on material flow, this rich real-time energy information provided adeep understand to the process energy consumption and energy flow. Based on dataintegration and energy information extraction, the integration of MEOP and papermaking process functional models was achieved by data interaction techniques in EMS, and thenenergy monitoring, energy analysis and such other basic EMS functions were fulfilled,moreover rich process data and energy information provided fundamental data for furtherenergy factors analysis and mining, and energy consumption prediction.
There are a mass amount of process data in papermaking process, but comprehensiveunderstanding of these data is beyond of human’s capability, and operators are always trappedin the trouble of “rich data but poor information”. Based on the EMS, the research took themassive process data as foundation and energy consumption prediction as final goal, thenadopted data mining techniques to analyze and mine the energy influencing factors inpapermaking process. According to the process data characteristics, such as multivariable,multi-correlation among variables and massive data, PCA (Principal Component Analysis),PLS (Partial Least Square) and such multivariate transformation and selection methods wereintroduced and combined to analyze and mine the importance of energy influencing factors inpapermaking process. As a result, the important energy influencing factors were obtained andthe importance of energy influencing factors was ranked. Then according to the variablesimportance analysis result, important energy influencing factors were selected, and energyinfluencing factors with no obvious correlation to energy consumption were removed. Theresearch shows that the combination of proper data preprocessing and PLS can realize theimportance analysis of multi-correlation energy influencing factors and provide importantsupport to energy-saving technical retrofits, abnormal energy consumption analysis andenergy consumption prediction, etc.
Based on the PLS analysis results of energy influencing factors, and according to theadvantages and characteristics of PLS and ANN, a novel PLS-ANN prediction model wasdeveloped to predict process energy consumption. For improving the accuracy, thepapermaking process energy consumption was classified based on the energy consumptioncharacteristics of each process procedure, and according to each energy consumption divisiontype, appropriate prediction model——PLS-ANN or ANN, was taken to realize the energyconsumption prediction of each process procedure. Based on the energy consumptionprediction of each process procedure, the effective1hour energy consumption prediction ofthe entire papermaking process was achieved. The results show that for the power consumption of papermaking process, the prediction RMSE is9.02kWh/t and the correlationcoefficient between predicted data and measured data is0.95, and for the steam consumptionof papermaking process, the prediction RMSE is0.03t/t and the correlation coefficientbetween predicted data and measured data is0.88, it shows the proposed prediction methodhas good precision. The effective energy consumption prediction of papermaking process canprovide important support to optimize the operation in energy conversion section and reduceenergy waste, then benefit to realize the dynamic balance of process energy system.
This thesis focuses on the study of methods and applications, and its features andinnovation points are:
1) The real-time energy information calculation based on material flow and materialthermodynamic properties is introduced to the EMS of paper process, and accurate,transparent and real-time energy information are obtained;
2) According to the characteristics of papermaking process data, such as multivariable,multi-correlation among variables and massive data, PCA, PLS and suchmultivariate transformation and selection methods are employed to analyze andmine the energy influencing factors in paper process. Appropriate data preprocessingmethods and PLS are combined to realize the transformation and importanceanalysis of energy influencing factors, and to identify the primary energy influencingfactors;
3) The division and classification of energy system of paper process is introduced, andaccording to each energy consumption division type, appropriate prediction model isestablished to improve the energy consumption prediction accuracy. And aPLS-ANN prediction model is developed which combines the PLS advantages indata analysis and interpretation and the ANN advantages in nonlinear modeling,self-learning and adaptability.
引文
[1]中华人民共和国国务院.国务院关于印发“十二五”节能减排综合性工作方案的通知[EB/OL]. www.gov.cn,2011
[2]中华人民共和国国务院.国务院关于进一步加大工作力度确保实现“十一五”节能减排目标的通知[EB/OL]. www.gov.cn,2010
[3]中华人民共和国国务院.中华人民共和国国民经济和社会发展第十一个五年规划纲要[EB/OL]. www.gov.cn,2006
[4]工业和信息化部.工业节能“十二五”规划[EB/OL]. www.miit.gov.cn,2012
[5]国家发展与改革委员会,工业和信息化部,国家林业局.造纸工业发展十二五规划
[EB/OL]. www.sdpc.gov.cn,2011
[6]国家发展与改革委员会.节能中长期专项规划[EB/OL]. www.sdpc.gov.cn,2004
[7]方春阳.节能减排途径——结构节能+技术节能+管理节能[J].中国电力教育,2007,(8):20-21
[8]国家发展和改革委员会.重点节能技术推广目录（第一批）[EB/OL].www.sdpc.gov.cn,2007
[9]国家发展和改革委员会.国家重点节能技术推广目录（第四批）[EB/OL].www.sdpc.gov.cn,2011
[10]工业和信息化部.钢铁企业能源管理中心建设实施方案[EB/OL]. www.miit.gov.cn,2009
[11]李继庚,刘焕彬.造纸企业节能关键共性技术——过程能量系统的综合优化与集成技术[J].造纸科学与技术,2008,27(6):22-25
[12] Natural Resources Canada. Process Integration[EB/OL].http://canmetenergy.nrcan.gc.ca,2009
[13]王金林.论造纸工业的本质和特点[J].国际造纸,1997,16(2):3-7
[14]中国造纸学会.中国造纸年鉴2010[M].北京:中国轻工业出版社,2010
[15]中国造纸学会.中国造纸年鉴2011[M].北京:中国轻工业出版社,2011
[16]国家发展和改革委员会,美国劳伦斯伯克利国家实验室.国外工业节能最佳实践
[EB/OL]. http://china.lbl.gov,2008
[17]奥地利环境培训与国际咨询中心,北京节能环保中心,中国21世纪议程管理中心.重点耗能行业能效水平对标管理项目——制浆和造纸行业参考手册[EB/OL].www.most.gov.cn,2009
[18] Worrell E., Price L., Neelis M., et al. World Best Practice Energy Intensity Values forSelected Industrial Sectors[EB/OL]. www.china.lbl.gov,2008
[19] Wikipedia. Energy Management System[EB/OL].http://en.wikipedia.org/wiki/Energy_management_system,2012
[20] Kroposki B., Garrett B., Macmillan S., et al. Energy Systems Integrations[EB/OL].www.osti.gov/bridge,2012
[21] Hooke J.H., Landry B.J., Hart D. Energy Management Information Systems:Achieving Improved Energy Efficiency: a Handbook for Managers, Engineers andOperational Staff[M]. Ottawa: Office of Energy Efficiency of Natural ResourcesCanada,2004
[22]吴玮.提高能源利用效率钢铁业率先启动能源管理中心建设[N].中国工业报,2009年12月16日
[23]工业和信息化部.工业节能“十二五”规划[EB/OL].www.miit.gov.cn,2012
[24]王宏安,荣冈,冯梅,等.化工生产执行系统MES[M].北京:化学工业出版社,2006
[25]蔡韵.制浆造纸企业生产调度系统建模与优化研究[D].杭州:浙江大学,2005
[26]荣冈.节能降耗MES任重道远[J].中国制造业信息化,2007(9):53
[27]荣冈. MES的现状及发展[J].自动化博览,2008(3):4-18
[28] Office of Energy Efficiency&Renewable Energy, U.S. Department of Energy (DOE).DOE Best Practice Software Tools[EB/OL].https://save-energy-now.org/EM/tools/Pages/HomeTools.aspx,2012
[29] CanmetEnergy. CanmetEnergy Software Tools[EB/OL].http://canmetenergy.nrcan.gc.ca/software-tools/775,2011
[30] John C. Van Gorp. Maximizing Energy Savings With Enterprise Energy ManagementSystems[J]. IEEE Power&Energy,2005,24(3):175-181
[31] Swords B, Coyle E., Norton B. An Enterprise Energy Information System[J]. AppliedEnergy,2008,85(1):61-69
[32] Chen Y.P., Mu X.M., Zhang J.L., et al. Development of Monitoring System ofBuilding Energy Consumption[C]. International Forum on ComputerScience-Technology and Applications.2009, IFCSTA: Chongqing.363-366
[33] Li D.F., Liu L., Zhu W., et al. Material-Flow Modeling Technology and Its Applicationin Manufacturing Execution Systems of Petrochemical Industry[J]. Chinese Journal ofChemical Engineering,2008,16(1):71-78
[34] Lampret M., Venceslav B., Andrej P., et al. Industrial Energy-Flow Management[J].Applied Energy,2007,84(7-8):781-794
[35] Maghsoodlou F., Masiello R., Ray T. Energy Management Systems. IEEE Power&Energy,2004,2(5):49-57
[36] Liao Y., Interface Paradigms in Energy Management System[C]. Southeastcon,2008Proceedings of IEEE.2008, Huntsville, Alabama.485-490
[37]冯晶,田小果. EMS系统在钢铁厂能源中心的应用[J].自动化与仪器仪表,2005,119(3):35-37,44
[38]徐玉婷. MES车间生产调度系统及其数据挖掘方法的研究[D].南京:南京航空航天大学,2007
[39]刘同明.数据挖掘技术及其应用[M].北京:国防工业出版社,2001
[40] Han J.W., Kamber M. Data Mining: Concepts and Techniques[M].2ed. Oxford, UK:ELSEVIER,2006
[41] Kantardzic M.数据挖掘：概念、模型、方法和算法[M].闪四清,陈茵,程雁.北京:清华大学出版社,2003
[42]靳碧.数据挖掘算法及其生产优化应用研究[D].杭州:浙江大学,2006
[43]杨善升.基于数据挖掘的若干化工过程优化和化合物构效关系研究[D].上海:上海大学,2008
[44]李智勇.电力系统运行信息的数据挖掘研究[D].杭州:浙江大学,2009
[45]韩家炜,堪博.数据挖掘：概念与技术[M].北京:机械工业出版社,2000
[46]宋彦波,彭小奇.数据挖掘技术在工业生产中的应用[J].计算机测量与控制,2004,12(10):944-947
[47] Cardenas J.J., Romeral L., Garcia A., et al. Load Forecasting Framework of ElectricityConsumptions for An Intelligent Energy Management System in the User-Side[J].Expert Systems with Applications,2012,39(5):5557-5565
[48]程其云.基于数据挖掘的电力短期负荷预测模型及方法的研究[D].重庆:重庆大学,2004
[49]冯丽.数据挖掘和人工智能理论在短期电力负荷预测中的应用研究[D].杭州:浙江大学,2005
[50]赵敏.高炉冶炼过程的复杂性机理及其预测研究[D].杭州:浙江大学,2008
[51]张华美.企业能耗智能组合预测系统应用研究[D].长沙:湖南大学,2007
[52] QB1022-91,制浆造纸企业综合能耗计算细则[S].北京:中华人民共和国轻工业部,1991
[53] Smook G.A.制浆造纸工程大全[M].2ed.曹邦威.北京:中国轻工业出版社,2001
[54]王忠厚.制浆造纸工艺[M].2ed.北京:中国轻工业出版社,2006
[55]周景辉.制浆造纸工艺设计手册[M].北京:化学工业出版社,2004
[56]陈克复.制浆造纸机械与设备(上)[M].2ed.北京:中国轻工业出版社,2003
[57]陈克复.制浆造纸机械与设备(下)[M].2ed.北京:中国轻工业出版社,2003
[58] Jacobs Engineering Group, Georgia Institute of Technology. Pulp and Paper IndustryEnergy Bandwidth Study[R]. Grenville, SC: JACOBS, Institute of Paper Science andTechnology at Georgia Institute of Technology,2006
[59] European Commission-Integrated Pollution Prevention and Control. ReferenceDocument on Best Available Techniques in the Pulp and Paper Industry[R]. Seville,Spain: European IPPC Bureau,2001
[60] Francis D.W., Towers M.T., Browne T.C. Energy Cost Reduction in the Pulp andPaper Industry-An Energy Benchmarking Perspective[R]. Quebec: Pulp and PaperResearch Institue of Canada,2002
[61]杨旭,陈克复,王蓓.现代纸机能耗构成特点及节能途径初探[J].中国造纸,2011,30(2):58-62
[62]王忠厚.制浆造纸工业计算手册(上册)[M].北京:中国轻工业出版社,1994
[63]工业和信息化部,科技部，财政部.工业清洁生产推行“十二五”规划[EB/OL].www.miit.gov.cn,2012
[64] Dowrueng A., Hingst J.Z., Wehrmann E.A., et al.Decentralised Energy ManagementSystem with Comprehension of Fluctuated Renewable Energy Resources[C]. CleanElectrical Power,2009International Conference.2009, Capri, Italy.316-319
[65]李继庚,刘焕彬,吴波,等.造纸企业全厂能量系统优化信息平台的设计与开发[J].造纸科学与技术,2009,28(6):14-19
[66]高可平,王秀兰.能源管理信息系统的设计技术[J].化学工业与工程技术,1995,16(3):53-56
[67]赵芸.基于OPC技术的造纸信息集成平台设计与开发[D].杭州:浙江工业大学,2008
[68]邓铭.面向造纸企业信息集成系统的研究与开发[D].杭州:浙江工业大学,2007
[69]杨先娣,彭智勇,刘君强,等.信息集成研究综述[J].计算机科学,2006,33(7):55-59,80
[70]陶峥.监控与数据采集系统在能源管理中的应用研究[D].重庆:重庆大学,2009
[71]卫宏.能源中心数据采集的设计与应用[D].济南:山东大学,2009
[72]谷应鲲.基于分布式对象技术和架构模式的企业信息系统研究[D].杭州:浙江大学,2005
[73] IEC61970-405, Energy Management System Application Program Interface[S].Geneva, Switzerland: International Electrotechnical Commision(IEC),2007
[74] IEC61968-11, System Interfaces for Distribution Management[S]. Geneva,Switzerland: International Electrotechnical Commision(IEC),2010
[75]张辉.造纸工业节能减排增效与向低碳产业经济发展之途径[J].江苏造纸,2010,98(1):2-10
[76] Mercangoz M., Doyle F.J. Real-Time Optimization of the Pulp Mill BenchmarkProblem[J]. Computers&Chemical Engineering,2008,32:789-804
[77] Thomas F.E., Himmelblau D.M., Lasdon L.S.化工过程优化[M].2ed.张卫东,任钟旗,刘光虎.北京:化学工业出版社,2005
[78]冯文卓.能介管理系统设计与实现[J].上海节能,2010,(7):35-39
[79] Adriana C.M., Paris J., Trepanier M. Strategic Simulation of the Energy Managementin a Kraft Mill[J]. Energy Conversion&Management,2010,51(5):988-997
[80]姚玉英,陈常贵,曾敏静,等.化工原理(下).天津:天津大学出版社,1999
[81]姚玉英,黄凤廉,陈常贵,等.化工原理(上).天津:天津大学出版社,1999
[82] Himmelblau D.M, Riggs J.B. Basic Principles and Calculations in ChemicalEngineering.7ed. Upper Saddle River, New Jersey: Prentice Hall,2003
[83]周艳明,李继庚,刘焕彬,等.水和水蒸汽热力性质IAPWS-IF97计算模型分析及算法设计[J].热能动力工程,2010,25(2):166-171
[84] Wagner W., Cooper J.R., Dittmann A., et al. The IAPWS Industrial Formulation1997for the Thermodynamic Properties of Water and Steam[J]. Journal of Engineering forGas Turbines and Power,2000,122:150-182
[85] International Association for the Properties of Water and Steam(IAPWS). RevisedRelease on the IAPWS Industrial Formulation1997for the Thermodynamic Propertiesof Water and Steam.2007[EB/OL]. www.iapws.org,1997
[86]陈志田,崔华,朱春雁.能源管理体系中的能源因素分析[J].世界标准化与质量管理,2007,(9):4-5
[87] Pitt B.D, Kirschen D.S. Application of Data Mining Techniques to Load Profiling[C].Proceedings of IEEE Conference on Power Industry Computer Applications(PICA'99).1999, California.131-136
[88] Tribble A.N. The Relationship Between Weather Variables and Electricity Demand toImprove Short-Term Load Forecasting[D]. Norman, Oklahoma: University ofOklahoma,2003
[89] Hanselman D., Littlefield B.精通Matlab7[M].朱仁峰.北京:清华大学出版社,2006
[90]包研科,李娜.数理统计与Matlab数据处理[M].沈阳:东北大学出版社,2008
[91]王正林,刘明.精通Matlab7[M].北京:电子工业出版社,2009
[92]张德丰,周燕.详解Matlab在统计与工程数据分析中的应用[M].北京:电子工业出版社,2010
[93]刘云霞.数据预处理——数据归约的统计方法研究及应用[M].厦门:厦门大学出版社,2011
[94]陈鑫.化工工艺数据挖掘中数据预处理技术的研究与应用[D].上海:上海交通大学,2010
[95]费业泰.误差理论与数据处理[M].4ed.北京:机械工业出版社,2000
[96]沙定国.实用误差理论与数据处理[M].北京:北京理工大学出版社,1993
[97]魏霞.智能化数据预处理系统的研究与实现[D].广州:华南理工大学,2010
[98]朱文金.数据预处理在预测模型中的应用[D].兰州:兰州大学,2010
[99]邓自立.卡尔曼滤波与维纳滤波——现代时间序列分析方法[M].哈尔滨:哈尔滨工业大学出版社,2001
[100] Bernstein S., Bernstein R.统计学原理（下册）——推断性统计学[M].史道济.北京:科学出版社,2002
[101] Bernstein S., Bernstein R.统计学原理（上册）——描述性统计学与概率[M].史道济.北京:科学出版社,2002
[102]王惠文.偏最小二乘回归方法及其应用[M].北京:国防工业出版社,1999
[103] Hyman B., Reed T. Energy Intensity of Manufacturing Processes[J]. Energy,1994,20(7):593-606
[104] Giraldo L., Hyman B. Energy End-Use Models for Pulp, Paper, and PaperboardMills[J]. Energy,1995,20(10):1005-1019
[105] Ozalp N, Hyman B. Energy End-Use Model of Paper Manufacturing in the U.S.[J].Applied Thermal Engineering,2006,26(5-6):540-548
[106] Jebaraj S., Iniyan S. A Review of Energy Models[J]. Renewable&Sustainable EnergyReviews,2006,10(4):281-311
[107]何晓群.多元统计分析[M].北京:中国人民大学出版社,2004
[108] JMacGregor J.F, Jaeckle C. Process Monitoring and Diagnosis by Multiblock PLSMethods[J]. AIChE Journal,1994,40(5):826-838
[109] Kettaneh N., Berglund A., Wold S. PCA and PLS with Very Large Data Sets[J].Computational Statistics&Data Analysis,2005,48:69-85
[110] Wold S., Kettaneh N., Tjessern K. Hierarchical Multiblock PLS and PC Models ForEasier Model Interpretation and As an Alternative to Variable Selection[J]. Journal ofChemometrics,1996,10:463-482
[111]王惠文,吴载斌,孟洁.偏最小二乘回归的线性与非线性方法[M].北京:国防工业出版社,2006
[112]王惠文,杨湘龙.两种成分提取回归方法的比较分析[J].北京航空航天大学学报,1998,24(5):575-578
[113]杜友武.钢铁企业能源管理与数据校正系统设计与实现[D].长沙:中南大学,2010
[114]邱东.基于节能目标的钢铁企业能源集成管理系统的研究与实现[D].长春:吉林大学,2009
[115]唐昱佳.基于EMD-BP神经网络预测模型的能源管理系统设计与实现[D].上海:复旦大学,2011
[116]方仍存.电力系统负荷区间预测[D].武汉:华中科技大学,2008
[117]李光珍.电网短期母线负荷数据预处理及预测模型研究[D].北京:华北电力大学,2009
[118]田志强,黄孝彬.工业生产过程的数据挖掘技术[J].控制工程,2009,16(增刊):120-123
[119]王志勇.数据挖掘方法在短期负荷预测中的应用研究[D].杭州:浙江大学,2007
[120]张伏生,汪鸿.基于偏最小二乘回归分析的短期负荷预测[J].电网技术,2003,27(3):36-40
[121]张曦.基于统计理论的工业过程综合性能监控、诊断及质量预测方法研究[D].上海:上海交通大学,2008
[122] Peter J.B., Davis R.A.时间序列的理论与方法[M].2ed.田铮.北京:高等教育出版社,2001
[123]艾玲.时间序列短期预测的方法和技术[D].上海:华东师范大学,2010
[124]李锁花.时间序列挖掘技术及其在短期电力负荷预测中的应用研究[D].上海:东南大学,2006
[125]胡宏宇.基于人工和模糊神经网络的电力系统负荷预测[D].南昌:南昌大学,2005
[126]荣辉著.基于前馈神经网络的电力系统负荷预测研究[D].北京:清华大学,1998
[127]蒋宗礼.人工神经网络导论[M].北京:高等教育出版社,2001
[128]沈文浩,谢益民,刘焕彬.人工神经网络在纸浆卡伯值光学定量分析中的应用[J].高等学校化学学报,2000,21(8):1208-1210
[129]沈文浩.光谱技术在制浆蒸煮过程纸浆卡伯值在线测量中的应用研究[D].广州:华南理工大学,2000
[130]宋玉强.人工神经网络在时间序列预测中的应用研究[D].西安:西安建筑科技大学,2005
[131]李国勇.智能控制及其MATLAB实现[M].北京:电子工业出版社,2005
[132]于尔铿,刘广一,周京阳.能源管理系统：EMS[M].北京:科学出版社,1998
[133]周玉佳.城市能耗的短期预测组合模型研究[D].广州:华南理工大学,2010
[2]中华人民共和国国务院.国务院关于进一步加大工作力度确保实现“十一五”节能减排目标的通知[EB/OL]. www.gov.cn,2010
[3]中华人民共和国国务院.中华人民共和国国民经济和社会发展第十一个五年规划纲要[EB/OL]. www.gov.cn,2006
[4]工业和信息化部.工业节能“十二五”规划[EB/OL]. www.miit.gov.cn,2012
[5]国家发展与改革委员会,工业和信息化部,国家林业局.造纸工业发展十二五规划
[EB/OL]. www.sdpc.gov.cn,2011
[6]国家发展与改革委员会.节能中长期专项规划[EB/OL]. www.sdpc.gov.cn,2004
[7]方春阳.节能减排途径——结构节能+技术节能+管理节能[J].中国电力教育,2007,(8):20-21
[8]国家发展和改革委员会.重点节能技术推广目录（第一批）[EB/OL].www.sdpc.gov.cn,2007
[9]国家发展和改革委员会.国家重点节能技术推广目录（第四批）[EB/OL].www.sdpc.gov.cn,2011
[10]工业和信息化部.钢铁企业能源管理中心建设实施方案[EB/OL]. www.miit.gov.cn,2009
[11]李继庚,刘焕彬.造纸企业节能关键共性技术——过程能量系统的综合优化与集成技术[J].造纸科学与技术,2008,27(6):22-25
[12] Natural Resources Canada. Process Integration[EB/OL].http://canmetenergy.nrcan.gc.ca,2009
[13]王金林.论造纸工业的本质和特点[J].国际造纸,1997,16(2):3-7
[14]中国造纸学会.中国造纸年鉴2010[M].北京:中国轻工业出版社,2010
[15]中国造纸学会.中国造纸年鉴2011[M].北京:中国轻工业出版社,2011
[16]国家发展和改革委员会,美国劳伦斯伯克利国家实验室.国外工业节能最佳实践
[EB/OL]. http://china.lbl.gov,2008
[17]奥地利环境培训与国际咨询中心,北京节能环保中心,中国21世纪议程管理中心.重点耗能行业能效水平对标管理项目——制浆和造纸行业参考手册[EB/OL].www.most.gov.cn,2009
[18] Worrell E., Price L., Neelis M., et al. World Best Practice Energy Intensity Values forSelected Industrial Sectors[EB/OL]. www.china.lbl.gov,2008
[19] Wikipedia. Energy Management System[EB/OL].http://en.wikipedia.org/wiki/Energy_management_system,2012
[20] Kroposki B., Garrett B., Macmillan S., et al. Energy Systems Integrations[EB/OL].www.osti.gov/bridge,2012
[21] Hooke J.H., Landry B.J., Hart D. Energy Management Information Systems:Achieving Improved Energy Efficiency: a Handbook for Managers, Engineers andOperational Staff[M]. Ottawa: Office of Energy Efficiency of Natural ResourcesCanada,2004
[22]吴玮.提高能源利用效率钢铁业率先启动能源管理中心建设[N].中国工业报,2009年12月16日
[23]工业和信息化部.工业节能“十二五”规划[EB/OL].www.miit.gov.cn,2012
[24]王宏安,荣冈,冯梅,等.化工生产执行系统MES[M].北京:化学工业出版社,2006
[25]蔡韵.制浆造纸企业生产调度系统建模与优化研究[D].杭州:浙江大学,2005
[26]荣冈.节能降耗MES任重道远[J].中国制造业信息化,2007(9):53
[27]荣冈. MES的现状及发展[J].自动化博览,2008(3):4-18
[28] Office of Energy Efficiency&Renewable Energy, U.S. Department of Energy (DOE).DOE Best Practice Software Tools[EB/OL].https://save-energy-now.org/EM/tools/Pages/HomeTools.aspx,2012
[29] CanmetEnergy. CanmetEnergy Software Tools[EB/OL].http://canmetenergy.nrcan.gc.ca/software-tools/775,2011
[30] John C. Van Gorp. Maximizing Energy Savings With Enterprise Energy ManagementSystems[J]. IEEE Power&Energy,2005,24(3):175-181
[31] Swords B, Coyle E., Norton B. An Enterprise Energy Information System[J]. AppliedEnergy,2008,85(1):61-69
[32] Chen Y.P., Mu X.M., Zhang J.L., et al. Development of Monitoring System ofBuilding Energy Consumption[C]. International Forum on ComputerScience-Technology and Applications.2009, IFCSTA: Chongqing.363-366
[33] Li D.F., Liu L., Zhu W., et al. Material-Flow Modeling Technology and Its Applicationin Manufacturing Execution Systems of Petrochemical Industry[J]. Chinese Journal ofChemical Engineering,2008,16(1):71-78
[34] Lampret M., Venceslav B., Andrej P., et al. Industrial Energy-Flow Management[J].Applied Energy,2007,84(7-8):781-794
[35] Maghsoodlou F., Masiello R., Ray T. Energy Management Systems. IEEE Power&Energy,2004,2(5):49-57
[36] Liao Y., Interface Paradigms in Energy Management System[C]. Southeastcon,2008Proceedings of IEEE.2008, Huntsville, Alabama.485-490
[37]冯晶,田小果. EMS系统在钢铁厂能源中心的应用[J].自动化与仪器仪表,2005,119(3):35-37,44
[38]徐玉婷. MES车间生产调度系统及其数据挖掘方法的研究[D].南京:南京航空航天大学,2007
[39]刘同明.数据挖掘技术及其应用[M].北京:国防工业出版社,2001
[40] Han J.W., Kamber M. Data Mining: Concepts and Techniques[M].2ed. Oxford, UK:ELSEVIER,2006
[41] Kantardzic M.数据挖掘：概念、模型、方法和算法[M].闪四清,陈茵,程雁.北京:清华大学出版社,2003
[42]靳碧.数据挖掘算法及其生产优化应用研究[D].杭州:浙江大学,2006
[43]杨善升.基于数据挖掘的若干化工过程优化和化合物构效关系研究[D].上海:上海大学,2008
[44]李智勇.电力系统运行信息的数据挖掘研究[D].杭州:浙江大学,2009
[45]韩家炜,堪博.数据挖掘：概念与技术[M].北京:机械工业出版社,2000
[46]宋彦波,彭小奇.数据挖掘技术在工业生产中的应用[J].计算机测量与控制,2004,12(10):944-947
[47] Cardenas J.J., Romeral L., Garcia A., et al. Load Forecasting Framework of ElectricityConsumptions for An Intelligent Energy Management System in the User-Side[J].Expert Systems with Applications,2012,39(5):5557-5565
[48]程其云.基于数据挖掘的电力短期负荷预测模型及方法的研究[D].重庆:重庆大学,2004
[49]冯丽.数据挖掘和人工智能理论在短期电力负荷预测中的应用研究[D].杭州:浙江大学,2005
[50]赵敏.高炉冶炼过程的复杂性机理及其预测研究[D].杭州:浙江大学,2008
[51]张华美.企业能耗智能组合预测系统应用研究[D].长沙:湖南大学,2007
[52] QB1022-91,制浆造纸企业综合能耗计算细则[S].北京:中华人民共和国轻工业部,1991
[53] Smook G.A.制浆造纸工程大全[M].2ed.曹邦威.北京:中国轻工业出版社,2001
[54]王忠厚.制浆造纸工艺[M].2ed.北京:中国轻工业出版社,2006
[55]周景辉.制浆造纸工艺设计手册[M].北京:化学工业出版社,2004
[56]陈克复.制浆造纸机械与设备(上)[M].2ed.北京:中国轻工业出版社,2003
[57]陈克复.制浆造纸机械与设备(下)[M].2ed.北京:中国轻工业出版社,2003
[58] Jacobs Engineering Group, Georgia Institute of Technology. Pulp and Paper IndustryEnergy Bandwidth Study[R]. Grenville, SC: JACOBS, Institute of Paper Science andTechnology at Georgia Institute of Technology,2006
[59] European Commission-Integrated Pollution Prevention and Control. ReferenceDocument on Best Available Techniques in the Pulp and Paper Industry[R]. Seville,Spain: European IPPC Bureau,2001
[60] Francis D.W., Towers M.T., Browne T.C. Energy Cost Reduction in the Pulp andPaper Industry-An Energy Benchmarking Perspective[R]. Quebec: Pulp and PaperResearch Institue of Canada,2002
[61]杨旭,陈克复,王蓓.现代纸机能耗构成特点及节能途径初探[J].中国造纸,2011,30(2):58-62
[62]王忠厚.制浆造纸工业计算手册(上册)[M].北京:中国轻工业出版社,1994
[63]工业和信息化部,科技部，财政部.工业清洁生产推行“十二五”规划[EB/OL].www.miit.gov.cn,2012
[64] Dowrueng A., Hingst J.Z., Wehrmann E.A., et al.Decentralised Energy ManagementSystem with Comprehension of Fluctuated Renewable Energy Resources[C]. CleanElectrical Power,2009International Conference.2009, Capri, Italy.316-319
[65]李继庚,刘焕彬,吴波,等.造纸企业全厂能量系统优化信息平台的设计与开发[J].造纸科学与技术,2009,28(6):14-19
[66]高可平,王秀兰.能源管理信息系统的设计技术[J].化学工业与工程技术,1995,16(3):53-56
[67]赵芸.基于OPC技术的造纸信息集成平台设计与开发[D].杭州:浙江工业大学,2008
[68]邓铭.面向造纸企业信息集成系统的研究与开发[D].杭州:浙江工业大学,2007
[69]杨先娣,彭智勇,刘君强,等.信息集成研究综述[J].计算机科学,2006,33(7):55-59,80
[70]陶峥.监控与数据采集系统在能源管理中的应用研究[D].重庆:重庆大学,2009
[71]卫宏.能源中心数据采集的设计与应用[D].济南:山东大学,2009
[72]谷应鲲.基于分布式对象技术和架构模式的企业信息系统研究[D].杭州:浙江大学,2005
[73] IEC61970-405, Energy Management System Application Program Interface[S].Geneva, Switzerland: International Electrotechnical Commision(IEC),2007
[74] IEC61968-11, System Interfaces for Distribution Management[S]. Geneva,Switzerland: International Electrotechnical Commision(IEC),2010
[75]张辉.造纸工业节能减排增效与向低碳产业经济发展之途径[J].江苏造纸,2010,98(1):2-10
[76] Mercangoz M., Doyle F.J. Real-Time Optimization of the Pulp Mill BenchmarkProblem[J]. Computers&Chemical Engineering,2008,32:789-804
[77] Thomas F.E., Himmelblau D.M., Lasdon L.S.化工过程优化[M].2ed.张卫东,任钟旗,刘光虎.北京:化学工业出版社,2005
[78]冯文卓.能介管理系统设计与实现[J].上海节能,2010,(7):35-39
[79] Adriana C.M., Paris J., Trepanier M. Strategic Simulation of the Energy Managementin a Kraft Mill[J]. Energy Conversion&Management,2010,51(5):988-997
[80]姚玉英,陈常贵,曾敏静,等.化工原理(下).天津:天津大学出版社,1999
[81]姚玉英,黄凤廉,陈常贵,等.化工原理(上).天津:天津大学出版社,1999
[82] Himmelblau D.M, Riggs J.B. Basic Principles and Calculations in ChemicalEngineering.7ed. Upper Saddle River, New Jersey: Prentice Hall,2003
[83]周艳明,李继庚,刘焕彬,等.水和水蒸汽热力性质IAPWS-IF97计算模型分析及算法设计[J].热能动力工程,2010,25(2):166-171
[84] Wagner W., Cooper J.R., Dittmann A., et al. The IAPWS Industrial Formulation1997for the Thermodynamic Properties of Water and Steam[J]. Journal of Engineering forGas Turbines and Power,2000,122:150-182
[85] International Association for the Properties of Water and Steam(IAPWS). RevisedRelease on the IAPWS Industrial Formulation1997for the Thermodynamic Propertiesof Water and Steam.2007[EB/OL]. www.iapws.org,1997
[86]陈志田,崔华,朱春雁.能源管理体系中的能源因素分析[J].世界标准化与质量管理,2007,(9):4-5
[87] Pitt B.D, Kirschen D.S. Application of Data Mining Techniques to Load Profiling[C].Proceedings of IEEE Conference on Power Industry Computer Applications(PICA'99).1999, California.131-136
[88] Tribble A.N. The Relationship Between Weather Variables and Electricity Demand toImprove Short-Term Load Forecasting[D]. Norman, Oklahoma: University ofOklahoma,2003
[89] Hanselman D., Littlefield B.精通Matlab7[M].朱仁峰.北京:清华大学出版社,2006
[90]包研科,李娜.数理统计与Matlab数据处理[M].沈阳:东北大学出版社,2008
[91]王正林,刘明.精通Matlab7[M].北京:电子工业出版社,2009
[92]张德丰,周燕.详解Matlab在统计与工程数据分析中的应用[M].北京:电子工业出版社,2010
[93]刘云霞.数据预处理——数据归约的统计方法研究及应用[M].厦门:厦门大学出版社,2011
[94]陈鑫.化工工艺数据挖掘中数据预处理技术的研究与应用[D].上海:上海交通大学,2010
[95]费业泰.误差理论与数据处理[M].4ed.北京:机械工业出版社,2000
[96]沙定国.实用误差理论与数据处理[M].北京:北京理工大学出版社,1993
[97]魏霞.智能化数据预处理系统的研究与实现[D].广州:华南理工大学,2010
[98]朱文金.数据预处理在预测模型中的应用[D].兰州:兰州大学,2010
[99]邓自立.卡尔曼滤波与维纳滤波——现代时间序列分析方法[M].哈尔滨:哈尔滨工业大学出版社,2001
[100] Bernstein S., Bernstein R.统计学原理（下册）——推断性统计学[M].史道济.北京:科学出版社,2002
[101] Bernstein S., Bernstein R.统计学原理（上册）——描述性统计学与概率[M].史道济.北京:科学出版社,2002
[102]王惠文.偏最小二乘回归方法及其应用[M].北京:国防工业出版社,1999
[103] Hyman B., Reed T. Energy Intensity of Manufacturing Processes[J]. Energy,1994,20(7):593-606
[104] Giraldo L., Hyman B. Energy End-Use Models for Pulp, Paper, and PaperboardMills[J]. Energy,1995,20(10):1005-1019
[105] Ozalp N, Hyman B. Energy End-Use Model of Paper Manufacturing in the U.S.[J].Applied Thermal Engineering,2006,26(5-6):540-548
[106] Jebaraj S., Iniyan S. A Review of Energy Models[J]. Renewable&Sustainable EnergyReviews,2006,10(4):281-311
[107]何晓群.多元统计分析[M].北京:中国人民大学出版社,2004
[108] JMacGregor J.F, Jaeckle C. Process Monitoring and Diagnosis by Multiblock PLSMethods[J]. AIChE Journal,1994,40(5):826-838
[109] Kettaneh N., Berglund A., Wold S. PCA and PLS with Very Large Data Sets[J].Computational Statistics&Data Analysis,2005,48:69-85
[110] Wold S., Kettaneh N., Tjessern K. Hierarchical Multiblock PLS and PC Models ForEasier Model Interpretation and As an Alternative to Variable Selection[J]. Journal ofChemometrics,1996,10:463-482
[111]王惠文,吴载斌,孟洁.偏最小二乘回归的线性与非线性方法[M].北京:国防工业出版社,2006
[112]王惠文,杨湘龙.两种成分提取回归方法的比较分析[J].北京航空航天大学学报,1998,24(5):575-578
[113]杜友武.钢铁企业能源管理与数据校正系统设计与实现[D].长沙:中南大学,2010
[114]邱东.基于节能目标的钢铁企业能源集成管理系统的研究与实现[D].长春:吉林大学,2009
[115]唐昱佳.基于EMD-BP神经网络预测模型的能源管理系统设计与实现[D].上海:复旦大学,2011
[116]方仍存.电力系统负荷区间预测[D].武汉:华中科技大学,2008
[117]李光珍.电网短期母线负荷数据预处理及预测模型研究[D].北京:华北电力大学,2009
[118]田志强,黄孝彬.工业生产过程的数据挖掘技术[J].控制工程,2009,16(增刊):120-123
[119]王志勇.数据挖掘方法在短期负荷预测中的应用研究[D].杭州:浙江大学,2007
[120]张伏生,汪鸿.基于偏最小二乘回归分析的短期负荷预测[J].电网技术,2003,27(3):36-40
[121]张曦.基于统计理论的工业过程综合性能监控、诊断及质量预测方法研究[D].上海:上海交通大学,2008
[122] Peter J.B., Davis R.A.时间序列的理论与方法[M].2ed.田铮.北京:高等教育出版社,2001
[123]艾玲.时间序列短期预测的方法和技术[D].上海:华东师范大学,2010
[124]李锁花.时间序列挖掘技术及其在短期电力负荷预测中的应用研究[D].上海:东南大学,2006
[125]胡宏宇.基于人工和模糊神经网络的电力系统负荷预测[D].南昌:南昌大学,2005
[126]荣辉著.基于前馈神经网络的电力系统负荷预测研究[D].北京:清华大学,1998
[127]蒋宗礼.人工神经网络导论[M].北京:高等教育出版社,2001
[128]沈文浩,谢益民,刘焕彬.人工神经网络在纸浆卡伯值光学定量分析中的应用[J].高等学校化学学报,2000,21(8):1208-1210
[129]沈文浩.光谱技术在制浆蒸煮过程纸浆卡伯值在线测量中的应用研究[D].广州:华南理工大学,2000
[130]宋玉强.人工神经网络在时间序列预测中的应用研究[D].西安:西安建筑科技大学,2005
[131]李国勇.智能控制及其MATLAB实现[M].北京:电子工业出版社,2005
[132]于尔铿,刘广一,周京阳.能源管理系统：EMS[M].北京:科学出版社,1998
[133]周玉佳.城市能耗的短期预测组合模型研究[D].广州:华南理工大学,2010
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |