基于人工神经网络的泵站技术经济指标体系评价模型研究
|
摘要
长期以来泵站工程作为水利工程的重要组成部分在我国国民经济各部门发展中发挥着重要作用。在我国,泵站一方面广泛应用于灌溉和排水工程,为农业生产和减灾防灾服务;另一方面也大量地用于城市和乡镇的供排水工程及工业供水工程。
泵站技术经济指标作为衡量泵站运行的重要指标在评价泵站过程中起到重要作用。随着计算机技术的快速发展,模糊数学、随机模型、灰色系统和人工神经网络等理论方法与计算机技术相结合已被广泛地应用于综合评价之中。本文基于人工神经网络理论,将BP神经网络模型运用于泵站技术经济指标综合评价,建立评价模型。
本文采用Visual Basic语言调用Matlab神经网络工具箱,采用BP神经网络算法,结合水利部灌排中心《大中型泵站综合评价体系》以及相关理论确定评价标准,采用水利部灌排中心《泵站调查统计表》作为样本数据,建立泵站技术经济指标体系综合评价模型。以山西大禹渡提水工程作为工程实例计算,测试BP神经网络训练函数,对比采用神经网络评价模型与模糊综合评判模型在泵站技术经济指标综合评价中结果,说明人工神经网络模型在解决这类问题具有的优势。
本论文将人工神经网络理论运用于泵站技术经济指标体系综合评价中,丰富了泵站评价的手段,具有明显的理论价值与现实意义。
Pump station project,as an major composition of the water conservancy project, has long played an important part in the development of the national economy. In our country, pump station is widely used in irrigation and drainage works on one hand,providing service for the agricultural production and disaster reduction and defense;on the other hand,it is also widely used in water supply and sewerage works in towns and villages and the water supply in industry.
Pump station’s economic norms, as an important part in judging the function of pump station, plays a significant role in evaluating the pump station. Along with the quick development of computer tecnology, theory methods,such as fuzzy mathematics, random model, grey system and ANN etc.,will be widely used in comprehensive evaluation integrated with it. This essay will set up a evaluation model by applying the BP neural network model into the comprehensive evaluation on the pump station’s technical and economic norms and using the theory of artificial neural network.
Visual Basic language will be adopted in this essay as well as the Matlab neural network tool box and BP neural network algorithm. Integrated with the book named“the comprehensive evaluation system of large and middle-sized pump station”published by Irrigation and drainage Center of the Ministry of Water Resources and other relative theories, this essay will set up the evaluation standard, and a comprehensive evaluation model of pump station technical economic norms system by using the“investigation and statistics of pump station”as sample datas. This essay will take the pumping project of Shanxi Dayudu as engineering examples to do tabulation , test the BP neural network training function, and compare the results of adopting neural network evaluation model and fuzzy comprehensive evaluation model in pump station technical economic norms system, to illustrate the advantages which artificial neural network model possesses in solving problems of this kind. This essay applies the ANN theory systematically in the comprehensive evaluation of pump station’s technical and economic norms system, enrich the methods for pump station’s evaluation, which has an obvious theoretical value and practical significance.
泵站技术经济指标作为衡量泵站运行的重要指标在评价泵站过程中起到重要作用。随着计算机技术的快速发展,模糊数学、随机模型、灰色系统和人工神经网络等理论方法与计算机技术相结合已被广泛地应用于综合评价之中。本文基于人工神经网络理论,将BP神经网络模型运用于泵站技术经济指标综合评价,建立评价模型。
本文采用Visual Basic语言调用Matlab神经网络工具箱,采用BP神经网络算法,结合水利部灌排中心《大中型泵站综合评价体系》以及相关理论确定评价标准,采用水利部灌排中心《泵站调查统计表》作为样本数据,建立泵站技术经济指标体系综合评价模型。以山西大禹渡提水工程作为工程实例计算,测试BP神经网络训练函数,对比采用神经网络评价模型与模糊综合评判模型在泵站技术经济指标综合评价中结果,说明人工神经网络模型在解决这类问题具有的优势。
本论文将人工神经网络理论运用于泵站技术经济指标体系综合评价中,丰富了泵站评价的手段,具有明显的理论价值与现实意义。
Pump station project,as an major composition of the water conservancy project, has long played an important part in the development of the national economy. In our country, pump station is widely used in irrigation and drainage works on one hand,providing service for the agricultural production and disaster reduction and defense;on the other hand,it is also widely used in water supply and sewerage works in towns and villages and the water supply in industry.
Pump station’s economic norms, as an important part in judging the function of pump station, plays a significant role in evaluating the pump station. Along with the quick development of computer tecnology, theory methods,such as fuzzy mathematics, random model, grey system and ANN etc.,will be widely used in comprehensive evaluation integrated with it. This essay will set up a evaluation model by applying the BP neural network model into the comprehensive evaluation on the pump station’s technical and economic norms and using the theory of artificial neural network.
Visual Basic language will be adopted in this essay as well as the Matlab neural network tool box and BP neural network algorithm. Integrated with the book named“the comprehensive evaluation system of large and middle-sized pump station”published by Irrigation and drainage Center of the Ministry of Water Resources and other relative theories, this essay will set up the evaluation standard, and a comprehensive evaluation model of pump station technical economic norms system by using the“investigation and statistics of pump station”as sample datas. This essay will take the pumping project of Shanxi Dayudu as engineering examples to do tabulation , test the BP neural network training function, and compare the results of adopting neural network evaluation model and fuzzy comprehensive evaluation model in pump station technical economic norms system, to illustrate the advantages which artificial neural network model possesses in solving problems of this kind. This essay applies the ANN theory systematically in the comprehensive evaluation of pump station’s technical and economic norms system, enrich the methods for pump station’s evaluation, which has an obvious theoretical value and practical significance.
引文
[1]孙雪燕.浅谈人工智能的应用与发展[J].电脑知识与技术, 2007,(20) ,522-523
[2]蒋新松、宋国宁.人工智能综论[J].自然杂志, 1984,(09)
[3]沈威.国内人工智能应用研究进展[J].软件导刊, 2007,(21) .
[4]胡守仁.神经网络导论[M],第1版.国防科技大学1993,22-27.
[5]谷萩隆嗣.人工神经网络与模糊信号处理[M].科学出版社,2003,2-4.
[6]严登丰.泵站工程[M].中国水利水电出版社2005
[7]丘传忻.泵站[M].中国水利水电出版社2004
[8]刘超.水泵及水泵站[M].科学技术文献出版社2002.8
[9]胡晓军.水泵与水泵站[M].中国水利水电出版社2003.1
[10]刘竹溪,冯广志主编.中国泵站工程[M].水利电力出版社1993
[11]陈善广、鲍勇.BP神经网络学习算法的研究.应用基础与工程科学学报, 1995,3:437-442.
[12]李建峰、史逸芬.BP算法的改进及其在CAPP中的应用.成组技术与生产现代化,1995,21:62-66.
[13]宋云龙、张万年、季海涛、盛春泉,周有骏、朱驹渴.人工神经网络改进及其在喜树碱类化合物定量构效关系研究中的应用.中国药学杂志,2003,38:60-63.
[14]杨海澜、吴毅雄.主成分分析结合人工神经网络用于焊接过程质量控制.2003,33-58.
[15] Hemmateenejad B,Akhond M,Miri R,Shamsipur M.Genetic Algorithm Applied to the Selection of Factors in Principal Component-Artificial Neural Networks: Application to QSAR Study of Calcium Channel Antagonist Activity of 1,4-Dihydropyridines(Nifedipine Analogous) [J]. Chem.Inf.Sci,2003,43,1328-1334.
[16] Shamsipur M,Hemmateenejad B,Akhond M.Multicomponent Acid-Base Titrationby incipal Component-Artificial NeuralNetwork Calibration [J].Anal.Chim.Acta, 2002,461:147-153.
[17]王雪琴.大型泵站技术经济指标体系及综合评价方法研究[D].扬州大学硕士论文2007.6
[18]姜承启.大型泵站老化模糊综合评价体系[D].扬州大学硕士论文2005.2
[19]储训,陈履,钱钧.大型泵站科学管理对策[J].排灌机械2001,3-7
[20]泵及泵站专业委员会.泵及泵站工程科技进步综述[J].中国水利2004.10,23-25
[21]我国水泵技术发展与展望[J].上海博生泵业公司网2008.3
[22]刘卫伟.泵技术的发展趋势分析[J].网络收集2006.2
[23]窦以松.泵站新设备、新成果和新机遇[J].中国泵站网2007.4
[24]陈坚张雷.国外泵站发展及运行管理情况综述[J].水利工程网2005.5
[25]武汉水利电力大学. SL255-2000泵站技术管理规程[M].中国水利水电出版社2000.10
[26]邵正荣,储训,姜成启.大型泵站现代化标准初探[J].中国农村水利水电2003.8,90-92
[27]闻新、周露、李翔、张宝伟.Matlab神经网络仿真与应用[J].北京:科学出版社出版,2003.
[28] DonaldHebb、KhalilM.Groups and neural networks based streamfiow data infilling Procedures [J].JournalofHydology.1962.2:153-176.
[29] Berhard Widrow、Marcian Hoff.Optimal groundwater remediation using artificial neural networks [J].Journal of Hydology.1964.5:15-17.
[30] MarvinMinsky、SeymourPaPert.Regional drought analysis based on neural networks [J].Journal of Hydrologieal Engineering,1970.32(4):1013-1022.
[31] John Ho Pfield.Identifieation of Pollution sources via neural networks [J]. Journal of Hydrological Engineering,1988,35(2):1012-1025.
[32] D.E.Rumelhart、G.E.Hinton.R.J.Williams.Learning representations by Back-ProPagating errors [J].Nature,1986.323:533-536
[33]加卢什金、阎平凡.神经网络理论[M].北京:清华大学出版社,2002.
[34]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
[35]蒋宗礼.人工神经网络导论[J].北京:高等教育出版社出版,2001
[36]杨行峻、郑君里.人工神经网络[M].北京:高等教育出版社,1992.
[37] Simon Haykin著,叶世伟、史忠植译.神经网络原理[M].北京:机械工业出版社出版,2004. infillingProcedures.JournalofHydology,1962.2:153-176.
[38]张国忠等.人工神经网络在上海电力负荷预测中的应用[J].华北电力,2002,(2): 7-9.
[39]史国庆、赵庆生.一种神经网络模型算法控制的研究[J].太原工业大学学报, 1994,25(3):41-46.
[40]聂永萍.人工神经网络与计算机[J].重庆邮电学院学报.1998,10(4):3 3-86.
[41]李朝安.电力系统负荷模型辨识和预报[J].中国电机工程学报,1998,8(3):31-36.
[42] ANDERSON J A .An Introduction to Neural Networks [M].London:MIT Press,1995.1-62.
[43] BISHOP C M. Neural Networks for Panm Recognition [M].Oxford:Chrendon Press,1995.5-28
[44]蒋裕丰、何仙峰、金永强.BP网络监测模型的Matlab&Delphi混合编程[J].2006,34(1):88-91.
[45]楼文高.海水水质评价的人工神经网络模型研究[J].2001,20(4):49-53.
[46]孙洪波等.用于短期电力负荷预报的人工神经网络方法[J].重庆大学学报(自然科学版),1995,18(4):42-47.
[47]李林川等.应用人工神经网络进行短期负荷预测[J].电力系统及其自动化学报,1994,6(3):33-41.
[48]中华人民共和国水利部,GB/T50265-97泵站设计规范[M].中国计划出版社,1997
[49]刘法贵,赵娟.模糊贴近度及应用[J].华北水利水电学院学报2006
[50] Satty T L. Applications of Analytical Hierarchies[J]. Math. And Comp. in Simulation 1979
[51] Satty T L. A scaling method for priorities in Hierarchical Siruchical[J].J.Math.Psychol. 1977
[52]刘万里,王金艳. AHP和齐次马尔可夫链[J].系统工程2001
[53]汪培庄.模糊集合论及其应用[M].上海科学技术出版社1983
[54]魏海坤.神经网络结构设计的理论与方法.北京:国防工业出版社,2005.
[55]张宏立,陈华,李喆.实现VB与MATLAB数据交换的新方法[J].计算机应用与软件, 2004,(12)
[56]李永曦,陶伟莲,关立行.在VB6.0中调用MATLAB程序[J].微机发展, 2004,(01)
[57]李俐玲. VB与MATLAB相结合混合编程方法的研究[J].绵阳师范学院学报, 2004,(05) ,26-30
[58]高剑. Matlab与VB混合编程的两种方法[J].微机发展, 2003,(13) ,90-92
[59]谭炎,张凌燕. MATLAB与VB混合编程技术研究[J].微计算机信息, 2006,(15)
[60]张志涌.精通MATLAB 6.5版[M],北京航空航天大学出版社,2003.
[61]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2006,5:26,44.
[62]张树兵,戴红,陈哲.Visual Basic 6.0中文版入门与提高[M].北京:清华大学出版社,2007,(25),38-41
[63]玩恺,杨巨峰,王立.人工神经网络泛化问题综述[J].计算机应用研究,2008,(25).3525 -3533
[64]葛利,陈广胜.前馈过程神经网络的网络结构与泛化能力[J].计算机科学,2008,(12),137-150
[2]蒋新松、宋国宁.人工智能综论[J].自然杂志, 1984,(09)
[3]沈威.国内人工智能应用研究进展[J].软件导刊, 2007,(21) .
[4]胡守仁.神经网络导论[M],第1版.国防科技大学1993,22-27.
[5]谷萩隆嗣.人工神经网络与模糊信号处理[M].科学出版社,2003,2-4.
[6]严登丰.泵站工程[M].中国水利水电出版社2005
[7]丘传忻.泵站[M].中国水利水电出版社2004
[8]刘超.水泵及水泵站[M].科学技术文献出版社2002.8
[9]胡晓军.水泵与水泵站[M].中国水利水电出版社2003.1
[10]刘竹溪,冯广志主编.中国泵站工程[M].水利电力出版社1993
[11]陈善广、鲍勇.BP神经网络学习算法的研究.应用基础与工程科学学报, 1995,3:437-442.
[12]李建峰、史逸芬.BP算法的改进及其在CAPP中的应用.成组技术与生产现代化,1995,21:62-66.
[13]宋云龙、张万年、季海涛、盛春泉,周有骏、朱驹渴.人工神经网络改进及其在喜树碱类化合物定量构效关系研究中的应用.中国药学杂志,2003,38:60-63.
[14]杨海澜、吴毅雄.主成分分析结合人工神经网络用于焊接过程质量控制.2003,33-58.
[15] Hemmateenejad B,Akhond M,Miri R,Shamsipur M.Genetic Algorithm Applied to the Selection of Factors in Principal Component-Artificial Neural Networks: Application to QSAR Study of Calcium Channel Antagonist Activity of 1,4-Dihydropyridines(Nifedipine Analogous) [J]. Chem.Inf.Sci,2003,43,1328-1334.
[16] Shamsipur M,Hemmateenejad B,Akhond M.Multicomponent Acid-Base Titrationby incipal Component-Artificial NeuralNetwork Calibration [J].Anal.Chim.Acta, 2002,461:147-153.
[17]王雪琴.大型泵站技术经济指标体系及综合评价方法研究[D].扬州大学硕士论文2007.6
[18]姜承启.大型泵站老化模糊综合评价体系[D].扬州大学硕士论文2005.2
[19]储训,陈履,钱钧.大型泵站科学管理对策[J].排灌机械2001,3-7
[20]泵及泵站专业委员会.泵及泵站工程科技进步综述[J].中国水利2004.10,23-25
[21]我国水泵技术发展与展望[J].上海博生泵业公司网2008.3
[22]刘卫伟.泵技术的发展趋势分析[J].网络收集2006.2
[23]窦以松.泵站新设备、新成果和新机遇[J].中国泵站网2007.4
[24]陈坚张雷.国外泵站发展及运行管理情况综述[J].水利工程网2005.5
[25]武汉水利电力大学. SL255-2000泵站技术管理规程[M].中国水利水电出版社2000.10
[26]邵正荣,储训,姜成启.大型泵站现代化标准初探[J].中国农村水利水电2003.8,90-92
[27]闻新、周露、李翔、张宝伟.Matlab神经网络仿真与应用[J].北京:科学出版社出版,2003.
[28] DonaldHebb、KhalilM.Groups and neural networks based streamfiow data infilling Procedures [J].JournalofHydology.1962.2:153-176.
[29] Berhard Widrow、Marcian Hoff.Optimal groundwater remediation using artificial neural networks [J].Journal of Hydology.1964.5:15-17.
[30] MarvinMinsky、SeymourPaPert.Regional drought analysis based on neural networks [J].Journal of Hydrologieal Engineering,1970.32(4):1013-1022.
[31] John Ho Pfield.Identifieation of Pollution sources via neural networks [J]. Journal of Hydrological Engineering,1988,35(2):1012-1025.
[32] D.E.Rumelhart、G.E.Hinton.R.J.Williams.Learning representations by Back-ProPagating errors [J].Nature,1986.323:533-536
[33]加卢什金、阎平凡.神经网络理论[M].北京:清华大学出版社,2002.
[34]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
[35]蒋宗礼.人工神经网络导论[J].北京:高等教育出版社出版,2001
[36]杨行峻、郑君里.人工神经网络[M].北京:高等教育出版社,1992.
[37] Simon Haykin著,叶世伟、史忠植译.神经网络原理[M].北京:机械工业出版社出版,2004. infillingProcedures.JournalofHydology,1962.2:153-176.
[38]张国忠等.人工神经网络在上海电力负荷预测中的应用[J].华北电力,2002,(2): 7-9.
[39]史国庆、赵庆生.一种神经网络模型算法控制的研究[J].太原工业大学学报, 1994,25(3):41-46.
[40]聂永萍.人工神经网络与计算机[J].重庆邮电学院学报.1998,10(4):3 3-86.
[41]李朝安.电力系统负荷模型辨识和预报[J].中国电机工程学报,1998,8(3):31-36.
[42] ANDERSON J A .An Introduction to Neural Networks [M].London:MIT Press,1995.1-62.
[43] BISHOP C M. Neural Networks for Panm Recognition [M].Oxford:Chrendon Press,1995.5-28
[44]蒋裕丰、何仙峰、金永强.BP网络监测模型的Matlab&Delphi混合编程[J].2006,34(1):88-91.
[45]楼文高.海水水质评价的人工神经网络模型研究[J].2001,20(4):49-53.
[46]孙洪波等.用于短期电力负荷预报的人工神经网络方法[J].重庆大学学报(自然科学版),1995,18(4):42-47.
[47]李林川等.应用人工神经网络进行短期负荷预测[J].电力系统及其自动化学报,1994,6(3):33-41.
[48]中华人民共和国水利部,GB/T50265-97泵站设计规范[M].中国计划出版社,1997
[49]刘法贵,赵娟.模糊贴近度及应用[J].华北水利水电学院学报2006
[50] Satty T L. Applications of Analytical Hierarchies[J]. Math. And Comp. in Simulation 1979
[51] Satty T L. A scaling method for priorities in Hierarchical Siruchical[J].J.Math.Psychol. 1977
[52]刘万里,王金艳. AHP和齐次马尔可夫链[J].系统工程2001
[53]汪培庄.模糊集合论及其应用[M].上海科学技术出版社1983
[54]魏海坤.神经网络结构设计的理论与方法.北京:国防工业出版社,2005.
[55]张宏立,陈华,李喆.实现VB与MATLAB数据交换的新方法[J].计算机应用与软件, 2004,(12)
[56]李永曦,陶伟莲,关立行.在VB6.0中调用MATLAB程序[J].微机发展, 2004,(01)
[57]李俐玲. VB与MATLAB相结合混合编程方法的研究[J].绵阳师范学院学报, 2004,(05) ,26-30
[58]高剑. Matlab与VB混合编程的两种方法[J].微机发展, 2003,(13) ,90-92
[59]谭炎,张凌燕. MATLAB与VB混合编程技术研究[J].微计算机信息, 2006,(15)
[60]张志涌.精通MATLAB 6.5版[M],北京航空航天大学出版社,2003.
[61]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2006,5:26,44.
[62]张树兵,戴红,陈哲.Visual Basic 6.0中文版入门与提高[M].北京:清华大学出版社,2007,(25),38-41
[63]玩恺,杨巨峰,王立.人工神经网络泛化问题综述[J].计算机应用研究,2008,(25).3525 -3533
[64]葛利,陈广胜.前馈过程神经网络的网络结构与泛化能力[J].计算机科学,2008,(12),137-150
© 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 |