蒸汽管网散热损失计算分析与负荷预测研究
|
摘要
本文根据蒸汽管道与外界环境的换热过程特点和热平衡原理建立了蒸汽管网散热计算数学模型。模型由管内蒸汽温降方程、不同敷设方式蒸汽管道的单位长度散热损失方程、总传热热阻计算方程组成。同时,对总传热热阻各组成部分的影响因素进行了详细分析,并利用散热损失计算公式对蒸汽保温管道不同敷设方式、不同管径的散热损失进行了计算分析,并得到了数据表格,利用表格中的数据可使管道散热损失的计算得到简化。
通过实际调研得到了蒸汽管网沿途散热的测试数据,对测试数据数据进行了归纳整理。对蒸汽热网的蒸汽产量和销售量进行了统计和分析,得出了蒸汽负荷的总体变化规律和总的管网蒸汽损失。通过对蒸汽管网沿途散热测试数据的计算处理,得出了管网各部分的散热损失。同时,根据对测试数据的分析和对管网系统的实际调研提出了降低蒸汽管网热损失的方法和建议,为管网系统的节能优化提供了支持。
通过对蒸汽用户蒸汽负荷短期变化规律的分析,得出了影响蒸汽负荷变化的因素,并对几种典型的蒸汽用户负荷规律进行了说明。通过对热电公司的蒸汽负荷历史数据的整理分析,采用统计法和BP人工神经神经网络法对蒸汽的生产进行了短期负荷预测,并对该方法进行了分析。本文最后提出了采用蒸汽负荷预测和蓄热调节法相结合的方法来优化蒸汽负荷调节,其对工程运行具有较大的实用价值。
The paper according to process characteristics of the external environment of the steam pipe and the thermal equilibrium principle established the steam heat loss mathematic model. The model was made up of inner steam temperature drop equations, the steam pipe laying different ways of unit length heat loss equations, total heat resistance calculation equations. At the same time, each part of the influence factors of total heat resistance were analyzed in detail, and using the formula for calculating the heat loss calculated and analyzed the heat loss of steam pipe laying different ways and different diameters, and, using the data of the data table form can make the pipe heat loss calculation simplified
Through the practical investigation got the heat loss test data along the steam piping network, the test data were arranged through inducing. Through statistics and analysis dealt with the steam output and sales, and got the overall change rules of steam load and the steam pipe heat loss. Based on the test data of the steam piping network heat loss, along with the calculation, got the heat loss of each piping network sections. In addition, according to the analysis of test data and the actual investigation of pipeline system to propose methods and suggestions for pipeline system reduce the heat loss of the steam piping network, provided supports for the energy saving and optimization.
Through the analysis of steam load variation regularity of steam users, got factors that affect the steam load, and explained several typical steam user load variation rules; Based on tidying up and analyses the steam power company’s history data of load, through statistics and analysis of BP artificial neural network forecasted the short-term load of the steam output, and this two methods were analyzed, provided references for energy saving and operation optimizing of the steam piping network. At the end proposed the method of using steam load forecasting and method of heat accumulation adjustment to optimize steam load adjusting, to project operation has great practical value.
通过实际调研得到了蒸汽管网沿途散热的测试数据,对测试数据数据进行了归纳整理。对蒸汽热网的蒸汽产量和销售量进行了统计和分析,得出了蒸汽负荷的总体变化规律和总的管网蒸汽损失。通过对蒸汽管网沿途散热测试数据的计算处理,得出了管网各部分的散热损失。同时,根据对测试数据的分析和对管网系统的实际调研提出了降低蒸汽管网热损失的方法和建议,为管网系统的节能优化提供了支持。
通过对蒸汽用户蒸汽负荷短期变化规律的分析,得出了影响蒸汽负荷变化的因素,并对几种典型的蒸汽用户负荷规律进行了说明。通过对热电公司的蒸汽负荷历史数据的整理分析,采用统计法和BP人工神经神经网络法对蒸汽的生产进行了短期负荷预测,并对该方法进行了分析。本文最后提出了采用蒸汽负荷预测和蓄热调节法相结合的方法来优化蒸汽负荷调节,其对工程运行具有较大的实用价值。
The paper according to process characteristics of the external environment of the steam pipe and the thermal equilibrium principle established the steam heat loss mathematic model. The model was made up of inner steam temperature drop equations, the steam pipe laying different ways of unit length heat loss equations, total heat resistance calculation equations. At the same time, each part of the influence factors of total heat resistance were analyzed in detail, and using the formula for calculating the heat loss calculated and analyzed the heat loss of steam pipe laying different ways and different diameters, and, using the data of the data table form can make the pipe heat loss calculation simplified
Through the practical investigation got the heat loss test data along the steam piping network, the test data were arranged through inducing. Through statistics and analysis dealt with the steam output and sales, and got the overall change rules of steam load and the steam pipe heat loss. Based on the test data of the steam piping network heat loss, along with the calculation, got the heat loss of each piping network sections. In addition, according to the analysis of test data and the actual investigation of pipeline system to propose methods and suggestions for pipeline system reduce the heat loss of the steam piping network, provided supports for the energy saving and optimization.
Through the analysis of steam load variation regularity of steam users, got factors that affect the steam load, and explained several typical steam user load variation rules; Based on tidying up and analyses the steam power company’s history data of load, through statistics and analysis of BP artificial neural network forecasted the short-term load of the steam output, and this two methods were analyzed, provided references for energy saving and operation optimizing of the steam piping network. At the end proposed the method of using steam load forecasting and method of heat accumulation adjustment to optimize steam load adjusting, to project operation has great practical value.
引文
[1]孙玉宝.蒸汽管网水力热力联合计算方法及其应用研究[D].山东:山东建筑大学,2006.
[2]王东.城市蒸汽采暖系统热力与水力计算的研究[D].山东:山东建筑大学,2007.
[3]刘大山.不容忽视的节能领域--蒸汽管网系[J].中国机械工程,2002,13(19):20~22.
[4]宋许辉.我国蒸汽系统现状及节能潜力[J].节能与环保,2007,(1):52～54.
[5]刘志真.热电联产[M].北京:中国电力出版社,2006:1~12.
[6]陈和平.我国热电联产政策及状况的评述[J].热力发电,2001,(2):2~11.
[7]王振铭,郁刚.坚持科学发展观探讨热电联产的发展方针[J].热电技术,2009,(1):1~5.
[8] The International Association for the ProPerties of Water and Steam Release on the IAPWS lndustrial Formulation 1997 for the Thermodynamic ProPerties of Water and Steam[C]. Erlangen,Germany,1997.
[9] Mavromatisl.S.P,KokossisA.C. A logic based model for the analysis and optim- isation of steam turbine network [J]. Computers in Industry,1998,36:165~179.
[10] Sylvie Lorente,Wishsanuruk Wechsatol,Adrian Bejan. Fundamentals of treesh- aped networks of insulated pipes for hot water and energy [J]. Exergyan lnterna- tional journal,2002,2:227~236.
[11] Kawashima M,Dorgan C E,Mitchell J W. Hourly thermal load prediction for the next 24 hours by Arima Ewma L R and an artificial neural network[J]. ASHRAE Transactions,1995,101(1):186~200.
[12] Abu-Ei-Magd M A,Sinka N K. Short-Term Load Demand Modeling and Foreca- sting[J]. IEEE Trans on System,1982,12(3):370~382
[13] Toyoda J,et al. An Application of State Estimation to Short-Term Load Forecast- ing[J]. IEEE Trans on Power APP Syestem,1970,89(7):1678~1688.
[14] Martin T. The Time Series Approach to Short Term Load Forecasting[J]. IEEE Trans on Power Syestems,2(2),1987,785~791.
[15]胡文斌,华贲,杨昌智,等.灰色理论在城市供热负荷预测中的应用[J].煤气与热,2002,22(1):28.
[16] Ferrano F J,Wong K V. Prediction of thermal storage loads using a neural net- work [J]. ASHRAE Transactions,1990,96(2):723~726.
[17] Sidhu T S,Singh H,Sachdev M S. Designimplementation and testing of an arti- ficial neural network based fault direction discriminator for protecting transmissi- on lines [J]. IEEE Transactions on Power Delivery,1995,10(2):697~706.
[18]马涛,徐向东.基于小波网模型的区域供热系统负荷预测[J].清华大学学报(自然科学版),2005,45(5):34~37.
[19] Hou Z J,Lian Z W,Yao Y,et al. Cooling load prediction based on the combinati- on of rough set theory and support vector machine [J]. HVAC &R Research,2006,12(2):337~352.
[20] Soteris A,Kalogirou. Applications of Artificial Neural Networks for Energy Sys- tems[J]. Applied Energy,2000,67(1):17~35.
[21]吕泽华,黄志明.蒸汽管道的传递函数及工程应用[J].清华大学学报(自然科学版),1997,37(2):103~107.
[22]赵钦,王志勤,史挺进,等.大型蒸汽管网仿真的数学模型研究[J]. 1997,12(3):173~175.
[23]田子平,鲍福民.特大型热网的计算机实时仿真[J].上海交通大学学报,2000,34(4):486~490.
[24]李世武.蒸汽管网运行工况模拟计算方法[J].煤气与热力,2001,21(6):552~556.
[25]姜永顺.蒸汽供热管道沿程阻力损失简易计算法[J].暖通空调,2000,30(5):77~7.
[26]周传辉,符永正.一种管道保温热力计算的新方法—组合优化法[J].节能,1998,(5):28~30.
[27]宋扬,程芳真,蔡瑞忠,等.蒸汽供热管道的动态仿真建模[J].清华大学学报,2001,41(10):101~104.
[28]刘金平,华责.考虑蒸汽密度变化的长距离供热蒸汽管道的优化设计[J].中国电机学报,2003,23(1):150~154.
[29]樊洪明,江亿,何钟怡.直埋管道的热力分析[J].清华大学学报(自然科学版),2002,42(6):806~809.
[30]王成强,崔建跃,马晓茜.有空气保温层的蒸汽直埋管道保温层厚度计算与分析[J].节能技术,2007,143(3):223~226.
[31]高岩,梁太龙.并列运行工业锅炉的复合优化分配[J].北京理工大学学报,2002,22(3):318~320.
[32]王利宝,刘瑞霞,马艳军.冬季如何平衡蒸汽管网[J].内蒙古石油化工,2002,(26):35~37.
[33]杨自奋,洪波,耿海宁.工业蒸汽系统的优化[J].节能技术,1996,(4):15~19.
[34]周恩泽,方修睦.供暖热水锅炉房的热负荷预测[J].哈尔滨建筑大学学报,2000,33(3):56~60.
[35]彭岚,何大鹏,李友荣.基于BP神经网络的工业锅炉房负荷预测[J].工业加热,2006,35(5):31~50.
[36]贾力,方肇洪,钱兴华.高等传热学[M].北京:高等教育出版社,2003,21~23.
[37]章熙民,任泽需.传热学(第四版)[M].北京:中国建筑工业出版社,2001,32~38.
[38]杨世铭.传热学[M](第二版).北京:高等教育出版社,1993,199~202.
[39]王亦昭,刘雄.供热工程[M].北京:机械工业出版社,2007,243~251.
[40]王宇清.供热工程[M].北京:机械工业出版社,2005,239~243.
[41]王飞,张建伟.直埋供热管道工程设计[M].北京:中国建筑工业出版社,2006,3~4.
[42]陆亚俊,马最良,邹平华.暖通空调[M].北京:中国建筑工业出版社,2002,312~315.
[43]王亦昭,刘雄.供热工程[M].北京:机械工业出版社,2007,261~266.
[44]韩彦荣,谢华.热力管道保温材料的选用分析[J].制冷与空调,2006,(4):59~61.
[45]金樟其.合理选择蒸汽管道保温材料[J].新型建筑材料,2006,(8):75~77.
[46]席德粹,刘松林,王可仁,等.城市燃气管网设计与施工[M].上海:上海科技出版社,1988:127~151.
[47]汤惠芬,范季贤,等.城市供热说册[M].天津:天津科学技术出版社,1991,492~498.
[48]章熙民,任泽需.传热学(第四版)[M].北京:中国建筑工业出版社,2001,146~158.
[49]宋永军,吕君.蒸汽直埋复合保温管的热工计算[J].电站系统工程,2003,19(3):21~22.
[50]陈鸿恩,莫理京.高土壤热阻地区供热管道直埋敷设的保温问题[J].区域供热,1999,5:14~18.
[51]莫理京,张骥.关于直埋保温管道传热计算方法的探讨[J].石油工程建设,2002,28(1):13~17.
[52] BARTON.R.N. Thermal Transfer Calculation Methods for Insulated Underground Piping Systems and Comparisons of Results[J]. Jane B. Wheeler Managing. THERMAL INSULATION PERFORMANCE,Baltimore,Md:AMERICAN SOCIETY FOR TESTING AND MATERIALS,1980,475~493.
[53]章熙民,任泽需.传热学(第四版)[M].北京:中国建筑工业出版社,2001,158~163.
[54]章熙民,任泽需.传热学(第四版)[M].北京:中国建筑工业出版社,2001,163~173.
[55]汤惠芬,范季贤,等.城市供热说册[M].天津:天津科学技术出版社,1991,503~513.
[56]翟彤彤,邓国民.钢套钢直埋蒸汽管道增设排潮管的必要性[J].管道技术与设备,2006,4:43~44.
[57]莫理京,马家滋.直埋蒸汽管道保温层外表面温度的探讨[J].煤气与热力,2000,20(3):178~183.
[58]王亦昭,刘雄.供热工程[M].北京:机械工业出版社,2007,305~310.
[59]李友荣,无双.供热蒸汽管道及其保温层的同步设计法[J].中国电机学报,2003,23(1):150~154.
[60]李爱华.直埋蒸汽管道保温层厚度选择计算的研究[J].水力电力机械,2004,26(6):3~5.
[61]杜元顺.煤气日负荷短期预测用的回归分析法[J].煤气与热力,1982,4:26~30.
[62]朱麟,张玉润,吴明光,等.城市煤气负荷预报[J].煤气与热力,1998,18(2):27~39.
[63]田一梅,赵元,赵新华.城市煤气负荷的预测[J].煤气与热力,1998,18(4):20~23.
[64]谭羽非,陈家新,焦文玲,等.基于人工神经网络的城市煤气短期负荷预测[J].煤气与热力,2001,3:199~202.
[65]焦文玲,严铭卿,廉乐明.城市燃气负荷的灰色预测[J].煤气与热力,2001,(5):387~389.
[66]张倩,冯良,厉戌吟.城市燃气负荷预测技术[J],上海煤气,2004,(2):1~29.
[67]郝有志,李德英.热负荷预测方法的评析与研究发展方向[J].全国暖通空调制冷2002年学术年会资料集,2002,526~528.
[68]彭岚,何大鹏,李友荣.基于BP神经网络的工业锅炉房负荷预测[J].工业加热,2006,36(5):31~50.
[69]郝有志,李德英.基于神经网络的供热计量系统热负荷短期预测[J].暖通空调,2003,33(6):105~107.
[70] LIPPMAN R P. An Introduction to Computing with Neural Networks [J]. IEEE ASSP Magazine,1987,4:4~32.
[71] LIPPMAN R P. Pattern Classification Using Neural Networks [J]. IEEE Comm Magazine,1989,1:47~64.
[72]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1991,78~118.
[73] WATROUS R L. Learning Algorithms for Connectionist Network Applied Grad- ient Methods of Nonlinear Optimization[A]. Proceedings of IEEE International Conference on Neural Networks,New York:IEEE Press,1987,619~627.
[74] SHAR S,PALMIERI F,DATUM M. Optimal Filtering Algorithms for Fast Lear- ning in Feed Forward NeuralNetworks [J]. Neural Networks,1992,5(5):779~787.
[75]绳开太,曹家极.锅炉房一蓄热器供热系统的优化运行模式研究[J]东华大学学报(自然科学版),2003,29(6):77~80.
[76]那海涛,孙丽颖.浅谈蒸汽供热调节[J].节能技术,1999,96(4):45~46.
[2]王东.城市蒸汽采暖系统热力与水力计算的研究[D].山东:山东建筑大学,2007.
[3]刘大山.不容忽视的节能领域--蒸汽管网系[J].中国机械工程,2002,13(19):20~22.
[4]宋许辉.我国蒸汽系统现状及节能潜力[J].节能与环保,2007,(1):52～54.
[5]刘志真.热电联产[M].北京:中国电力出版社,2006:1~12.
[6]陈和平.我国热电联产政策及状况的评述[J].热力发电,2001,(2):2~11.
[7]王振铭,郁刚.坚持科学发展观探讨热电联产的发展方针[J].热电技术,2009,(1):1~5.
[8] The International Association for the ProPerties of Water and Steam Release on the IAPWS lndustrial Formulation 1997 for the Thermodynamic ProPerties of Water and Steam[C]. Erlangen,Germany,1997.
[9] Mavromatisl.S.P,KokossisA.C. A logic based model for the analysis and optim- isation of steam turbine network [J]. Computers in Industry,1998,36:165~179.
[10] Sylvie Lorente,Wishsanuruk Wechsatol,Adrian Bejan. Fundamentals of treesh- aped networks of insulated pipes for hot water and energy [J]. Exergyan lnterna- tional journal,2002,2:227~236.
[11] Kawashima M,Dorgan C E,Mitchell J W. Hourly thermal load prediction for the next 24 hours by Arima Ewma L R and an artificial neural network[J]. ASHRAE Transactions,1995,101(1):186~200.
[12] Abu-Ei-Magd M A,Sinka N K. Short-Term Load Demand Modeling and Foreca- sting[J]. IEEE Trans on System,1982,12(3):370~382
[13] Toyoda J,et al. An Application of State Estimation to Short-Term Load Forecast- ing[J]. IEEE Trans on Power APP Syestem,1970,89(7):1678~1688.
[14] Martin T. The Time Series Approach to Short Term Load Forecasting[J]. IEEE Trans on Power Syestems,2(2),1987,785~791.
[15]胡文斌,华贲,杨昌智,等.灰色理论在城市供热负荷预测中的应用[J].煤气与热,2002,22(1):28.
[16] Ferrano F J,Wong K V. Prediction of thermal storage loads using a neural net- work [J]. ASHRAE Transactions,1990,96(2):723~726.
[17] Sidhu T S,Singh H,Sachdev M S. Designimplementation and testing of an arti- ficial neural network based fault direction discriminator for protecting transmissi- on lines [J]. IEEE Transactions on Power Delivery,1995,10(2):697~706.
[18]马涛,徐向东.基于小波网模型的区域供热系统负荷预测[J].清华大学学报(自然科学版),2005,45(5):34~37.
[19] Hou Z J,Lian Z W,Yao Y,et al. Cooling load prediction based on the combinati- on of rough set theory and support vector machine [J]. HVAC &R Research,2006,12(2):337~352.
[20] Soteris A,Kalogirou. Applications of Artificial Neural Networks for Energy Sys- tems[J]. Applied Energy,2000,67(1):17~35.
[21]吕泽华,黄志明.蒸汽管道的传递函数及工程应用[J].清华大学学报(自然科学版),1997,37(2):103~107.
[22]赵钦,王志勤,史挺进,等.大型蒸汽管网仿真的数学模型研究[J]. 1997,12(3):173~175.
[23]田子平,鲍福民.特大型热网的计算机实时仿真[J].上海交通大学学报,2000,34(4):486~490.
[24]李世武.蒸汽管网运行工况模拟计算方法[J].煤气与热力,2001,21(6):552~556.
[25]姜永顺.蒸汽供热管道沿程阻力损失简易计算法[J].暖通空调,2000,30(5):77~7.
[26]周传辉,符永正.一种管道保温热力计算的新方法—组合优化法[J].节能,1998,(5):28~30.
[27]宋扬,程芳真,蔡瑞忠,等.蒸汽供热管道的动态仿真建模[J].清华大学学报,2001,41(10):101~104.
[28]刘金平,华责.考虑蒸汽密度变化的长距离供热蒸汽管道的优化设计[J].中国电机学报,2003,23(1):150~154.
[29]樊洪明,江亿,何钟怡.直埋管道的热力分析[J].清华大学学报(自然科学版),2002,42(6):806~809.
[30]王成强,崔建跃,马晓茜.有空气保温层的蒸汽直埋管道保温层厚度计算与分析[J].节能技术,2007,143(3):223~226.
[31]高岩,梁太龙.并列运行工业锅炉的复合优化分配[J].北京理工大学学报,2002,22(3):318~320.
[32]王利宝,刘瑞霞,马艳军.冬季如何平衡蒸汽管网[J].内蒙古石油化工,2002,(26):35~37.
[33]杨自奋,洪波,耿海宁.工业蒸汽系统的优化[J].节能技术,1996,(4):15~19.
[34]周恩泽,方修睦.供暖热水锅炉房的热负荷预测[J].哈尔滨建筑大学学报,2000,33(3):56~60.
[35]彭岚,何大鹏,李友荣.基于BP神经网络的工业锅炉房负荷预测[J].工业加热,2006,35(5):31~50.
[36]贾力,方肇洪,钱兴华.高等传热学[M].北京:高等教育出版社,2003,21~23.
[37]章熙民,任泽需.传热学(第四版)[M].北京:中国建筑工业出版社,2001,32~38.
[38]杨世铭.传热学[M](第二版).北京:高等教育出版社,1993,199~202.
[39]王亦昭,刘雄.供热工程[M].北京:机械工业出版社,2007,243~251.
[40]王宇清.供热工程[M].北京:机械工业出版社,2005,239~243.
[41]王飞,张建伟.直埋供热管道工程设计[M].北京:中国建筑工业出版社,2006,3~4.
[42]陆亚俊,马最良,邹平华.暖通空调[M].北京:中国建筑工业出版社,2002,312~315.
[43]王亦昭,刘雄.供热工程[M].北京:机械工业出版社,2007,261~266.
[44]韩彦荣,谢华.热力管道保温材料的选用分析[J].制冷与空调,2006,(4):59~61.
[45]金樟其.合理选择蒸汽管道保温材料[J].新型建筑材料,2006,(8):75~77.
[46]席德粹,刘松林,王可仁,等.城市燃气管网设计与施工[M].上海:上海科技出版社,1988:127~151.
[47]汤惠芬,范季贤,等.城市供热说册[M].天津:天津科学技术出版社,1991,492~498.
[48]章熙民,任泽需.传热学(第四版)[M].北京:中国建筑工业出版社,2001,146~158.
[49]宋永军,吕君.蒸汽直埋复合保温管的热工计算[J].电站系统工程,2003,19(3):21~22.
[50]陈鸿恩,莫理京.高土壤热阻地区供热管道直埋敷设的保温问题[J].区域供热,1999,5:14~18.
[51]莫理京,张骥.关于直埋保温管道传热计算方法的探讨[J].石油工程建设,2002,28(1):13~17.
[52] BARTON.R.N. Thermal Transfer Calculation Methods for Insulated Underground Piping Systems and Comparisons of Results[J]. Jane B. Wheeler Managing. THERMAL INSULATION PERFORMANCE,Baltimore,Md:AMERICAN SOCIETY FOR TESTING AND MATERIALS,1980,475~493.
[53]章熙民,任泽需.传热学(第四版)[M].北京:中国建筑工业出版社,2001,158~163.
[54]章熙民,任泽需.传热学(第四版)[M].北京:中国建筑工业出版社,2001,163~173.
[55]汤惠芬,范季贤,等.城市供热说册[M].天津:天津科学技术出版社,1991,503~513.
[56]翟彤彤,邓国民.钢套钢直埋蒸汽管道增设排潮管的必要性[J].管道技术与设备,2006,4:43~44.
[57]莫理京,马家滋.直埋蒸汽管道保温层外表面温度的探讨[J].煤气与热力,2000,20(3):178~183.
[58]王亦昭,刘雄.供热工程[M].北京:机械工业出版社,2007,305~310.
[59]李友荣,无双.供热蒸汽管道及其保温层的同步设计法[J].中国电机学报,2003,23(1):150~154.
[60]李爱华.直埋蒸汽管道保温层厚度选择计算的研究[J].水力电力机械,2004,26(6):3~5.
[61]杜元顺.煤气日负荷短期预测用的回归分析法[J].煤气与热力,1982,4:26~30.
[62]朱麟,张玉润,吴明光,等.城市煤气负荷预报[J].煤气与热力,1998,18(2):27~39.
[63]田一梅,赵元,赵新华.城市煤气负荷的预测[J].煤气与热力,1998,18(4):20~23.
[64]谭羽非,陈家新,焦文玲,等.基于人工神经网络的城市煤气短期负荷预测[J].煤气与热力,2001,3:199~202.
[65]焦文玲,严铭卿,廉乐明.城市燃气负荷的灰色预测[J].煤气与热力,2001,(5):387~389.
[66]张倩,冯良,厉戌吟.城市燃气负荷预测技术[J],上海煤气,2004,(2):1~29.
[67]郝有志,李德英.热负荷预测方法的评析与研究发展方向[J].全国暖通空调制冷2002年学术年会资料集,2002,526~528.
[68]彭岚,何大鹏,李友荣.基于BP神经网络的工业锅炉房负荷预测[J].工业加热,2006,36(5):31~50.
[69]郝有志,李德英.基于神经网络的供热计量系统热负荷短期预测[J].暖通空调,2003,33(6):105~107.
[70] LIPPMAN R P. An Introduction to Computing with Neural Networks [J]. IEEE ASSP Magazine,1987,4:4~32.
[71] LIPPMAN R P. Pattern Classification Using Neural Networks [J]. IEEE Comm Magazine,1989,1:47~64.
[72]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1991,78~118.
[73] WATROUS R L. Learning Algorithms for Connectionist Network Applied Grad- ient Methods of Nonlinear Optimization[A]. Proceedings of IEEE International Conference on Neural Networks,New York:IEEE Press,1987,619~627.
[74] SHAR S,PALMIERI F,DATUM M. Optimal Filtering Algorithms for Fast Lear- ning in Feed Forward NeuralNetworks [J]. Neural Networks,1992,5(5):779~787.
[75]绳开太,曹家极.锅炉房一蓄热器供热系统的优化运行模式研究[J]东华大学学报(自然科学版),2003,29(6):77~80.
[76]那海涛,孙丽颖.浅谈蒸汽供热调节[J].节能技术,1999,96(4):45~46.