基于BP人工神经网络的大庆水库水质预测研究
|
摘要
近年来随着原水污染的日益严重,建立原水水质预警系统迫在眉睫。本研究采用大庆水库水自动监测站的水质监测数据,主要研究BP神经网络模型对大庆水库水质的预测性能,重点探讨了水库冰封期对水源水质预测的影响作用,并与其他常用模型作了对比,为该市水源水质预警系统的建立提供技术支持,同时也为其它寒冷地区水源地水质预测提供参考。
本文确定了BP神经网络作为本次水质预测所用的模型;根据当地水厂的运行情况选择了水质预测参数,作为BP神经网络的网络输出;对原始数据进行灰色关联分析,确定了BP神经网络的输入变量;通过不同参数之间的对比确定了BP神经网络的训练及运行参数。通过对网络预测效果的分析得出BP神经网络能够较好地对该水库水质进行预测,但是数据规律的变化及数据样本数量的不足对预测结果会产生一定的影响。
大庆水库处于我国东北寒冷地区,每年有大约半年时间处于冰封期。本文根据大庆水库的这一特点,将原始的数据分为非冰封期与冰封期两个部分进行分析,分别建立BP神经网络,最后得出结论:对于进入冰封期后数据的变化规律有了改变的水质参数,将数据分类后再建立模型能够提升BP网络的预测效果,而对于其他的水质参数,盲目分类只会减少训练样本的数量,使网络训练不充分,造成不能对水质指标进行准确的预测。
本文还建立了自回归模型(AR)与灰色预测模型这两种常见的水质预测模型,并与BP神经网络模型做了对比。AR模型在处理复杂曲线的能力上不如BP神经网络,且模型阶数一般较高,但是当曲线的变化较为平缓时AR模型的预测效果更好;灰色预测模型则并不适用于变化幅度较大的水质预测。
The raw water warning system is thought to be more and more important these days because of the raw water pollution. This paper analyse the data from Daqin water automatic monitoring station and research the effect of forecasting water quality using BP neural network especially in frozen period. The model is also compared with other common models. This research provide technique supports for setting up a raw water warning system in the city and a reference for how to forecast water quality in cold areas.
This paper introduces BP neural network and applies it to forecast water quality of Daqin reservior. According to the technological processes of local waterworks, network outputs are decided. The author also analyzes grey association between different water parameters and choose the inputs of the BP nerual network. The best strutrure of network is established through vast comparisons. From the result we can see that BP neural network is a suitable model for water quality predicton, and the change of water quality and lack of training samples will influence the effect.
Daqin reservior locates in the Northeast China, where the frozen period persists a long time every year. This paper divides the data into two parts throughout the water temperature. And set up a BP neural network for each part. To the water parameters whose rule changes in the frozen period, seting up a network after classification can enhance the effect of forecasting. To the other water parameters, the result is even worse because of lack of samples.
This paper set up other two common models: AR model and grey model. And make a comparison between these two models and BP neural network. Only when the curve is very smooth, AR model which has a high order is better than BP neural network. Grey model is not suitable for water quality when the water parameter changes fiercely.
本文确定了BP神经网络作为本次水质预测所用的模型;根据当地水厂的运行情况选择了水质预测参数,作为BP神经网络的网络输出;对原始数据进行灰色关联分析,确定了BP神经网络的输入变量;通过不同参数之间的对比确定了BP神经网络的训练及运行参数。通过对网络预测效果的分析得出BP神经网络能够较好地对该水库水质进行预测,但是数据规律的变化及数据样本数量的不足对预测结果会产生一定的影响。
大庆水库处于我国东北寒冷地区,每年有大约半年时间处于冰封期。本文根据大庆水库的这一特点,将原始的数据分为非冰封期与冰封期两个部分进行分析,分别建立BP神经网络,最后得出结论:对于进入冰封期后数据的变化规律有了改变的水质参数,将数据分类后再建立模型能够提升BP网络的预测效果,而对于其他的水质参数,盲目分类只会减少训练样本的数量,使网络训练不充分,造成不能对水质指标进行准确的预测。
本文还建立了自回归模型(AR)与灰色预测模型这两种常见的水质预测模型,并与BP神经网络模型做了对比。AR模型在处理复杂曲线的能力上不如BP神经网络,且模型阶数一般较高,但是当曲线的变化较为平缓时AR模型的预测效果更好;灰色预测模型则并不适用于变化幅度较大的水质预测。
The raw water warning system is thought to be more and more important these days because of the raw water pollution. This paper analyse the data from Daqin water automatic monitoring station and research the effect of forecasting water quality using BP neural network especially in frozen period. The model is also compared with other common models. This research provide technique supports for setting up a raw water warning system in the city and a reference for how to forecast water quality in cold areas.
This paper introduces BP neural network and applies it to forecast water quality of Daqin reservior. According to the technological processes of local waterworks, network outputs are decided. The author also analyzes grey association between different water parameters and choose the inputs of the BP nerual network. The best strutrure of network is established through vast comparisons. From the result we can see that BP neural network is a suitable model for water quality predicton, and the change of water quality and lack of training samples will influence the effect.
Daqin reservior locates in the Northeast China, where the frozen period persists a long time every year. This paper divides the data into two parts throughout the water temperature. And set up a BP neural network for each part. To the water parameters whose rule changes in the frozen period, seting up a network after classification can enhance the effect of forecasting. To the other water parameters, the result is even worse because of lack of samples.
This paper set up other two common models: AR model and grey model. And make a comparison between these two models and BP neural network. Only when the curve is very smooth, AR model which has a high order is better than BP neural network. Grey model is not suitable for water quality when the water parameter changes fiercely.
引文
[1]苏征耀.我国水资源形势及其应对策略[J].水资源研究, 2007, 28(1):11-13
[2]张锡辉,郑振华,欧阳二明等.水源水质在线监测预警统的建设[J].中国给水排水, 2005, 21(11):14-17
[3]董志颖,王娟,李兵.水质预警理论初探[J].水土保持研究, 2002, 9(3):224-226
[4]熊德琪.环境系统模糊预测、评价、规划、决策理论模式与应用研究[D].大连理工大学土木系, 1994
[5]史根香,郭海生.指数平滑法在地下水水质预测中的尝试[J].湖北地矿,1998. 12(1):35-40
[6]翟颢瑾,高晶.长江未来水质污染的时间序列分析[J].沈阳师范大学学报(自然科学版), 2006, 24(1):22-24
[7] T Inoul. Prediction of Nitrogen Oxide Concentration by A Regression Model[J]. Atmospheric Environment, 1986, 20:2325-2337
[8]吴宏斌.地下水水质预测的多元线性回归分析模型研究[J].山西建筑, 2007, 33(32):201-202
[9]史复有.黄河兰州段耗氧有机污染物浓度统计预测模型的建立[J].环境科学, 1989, 10(3):72-74
[10]邓聚龙.灰色预测与决策[M].武汉:华中工学院出版社, 1986
[11]苗成林,周宏.基于灰色模型的水质预测[J].中国农村水利水电, 2007,(2):126-128
[12]邱淑芳,周其华,王泽文.改进的GM(1,1)模型及其在地下水环境预测中的应用[J].东华理工学院学报, 2006, 29(2):176-180
[13]朱长军,卢军燕,郝振纯等.应用灰色新阵代理GM(1,1)模型预测河流水质[J].河北工程大学学报(自然科学版), 2007, 24(1):45-47
[14]宛筝,李晔.多元线性回归与灰色联合模型在湖泊水质预测中的应用[J].江苏环境科技(增刊), 2006, 19(2):59-61
[15] Marina Campolo. Forecasting River Flow Rate during Low-flow Perio-d Using Neural Network[J]. Water Resource Research, 1999, 35(11): 3547-3552
[16] T. R. Neelakantan, N. V. Pundarikanthan. Neural Network-Based Sim-ulation-Optimization Model for Reservoir Operation[J]. Journal of Wat-er Resources Planning and Management, 2000, 126(2):57-64
[17]罗定贵.基于MATLAB实现的ANN方法在地下水质评价中的应用[J].北京大学学报, 2004, 40(2):296-302
[18] H R Maier, G C Dandy. The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters[J]. Water Resources Resea-rch, 1996, 32(4):1013-1022
[19]陈丽华,马生全.运用BP神经网络研究河水中溶解氧的影响因素[J].兰州交通大学学报(自然科学版), 2005, 24(1):55-58
[20]杨琴,谢淑云. BP神经网络在洞庭湖氨氮浓度预测中的应用[J].水资源与水工程学报, 2006, 17(1):65-70
[21]高卫峰,姚志红.基于BP神经网络的藻类生长预测研究[J].微计算机信息, 2005, 21(10):167-169
[22] D P Loucks, W R Lynn. Probabilistic Models for Predicting Stream Quality[J]. Water Resources Research, 1996,(3):593-605
[23] G Q Tabios. Nonlinear Stochastic Modeling of River Dissolved-Oxyg-en[D]. Colorado State University, 1984
[24] C Baffaut, J L Chamean. Estimation of Pollutant Loads with Fuzzy Sets[J]. Civil Engineering Systems, 1990,7(1):51-61
[25]夏军,张祥伟.河流水质灰色非线性规划的理论与应用[J].水利学报, 1993, (12):1-9
[26] Huang Guohe, Xia Jun. Barriers to Sustainable Water-quality Manage-ment. Journal of Envionmental Management, 2001,61:1-23
[27] Geld of G D. Adaptive Water Mangement: Integrated Water Manage-ment on the Edge of Chaos. Water Science Technology,1995, 32(1): 7-13
[28] J M Zaldivar, E Gutirrez. Forecasting High waters at Venice Lagoon Using Chaotic Time Series Analysis and Nonlinear Neural Networks. Journal of Hydroinformatics, 2000, (2):61-84
[29]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社, 2000
[30] W S McCulloch, W H Pitts. A Logical Calculus of the Ideas Imman-ent in Neuron Activity. Bulletin Mathematical Biophysics, 1943,Vo1.5,115-133
[31] D O Hebb. The Organization of Behavior, Wiley, New York, 1949
[32] F Rosenblatt. The Perception: A Probabilistic Model for Information Storage and Organization in the Brain, Psychological Review, 1958, Vo1.65: 386-408
[33] B Widrow, W Hoff. Adaptive Switching Circuits, Wescon Convention Record, 1960
[34] J J Hopfield. Neural Networks and Physical System with Emergent Collective Computational Abilities. Proceedings of the National Acade-my of Sciences. 1982, Vo1.79: 2554-2558
[35] D E Rumelhart, J L McClelland. Parallel Distributed Processing: Expl-orations in the Microstructure of Cognition, Cambridge Bradford Boo-ks, MIT Press, 1986:1-112
[36] P Werbos. Beyond Regression: New Tools for Prediction and Analysisin the Behavioral Sciences. PhD Dissertation, Harvard University, 1974
[37] D B Parker. Learning-logic, Technical Report TR-47. Center for Com-putational Res, in Economics and Management Sci. MIT, 1985
[38] D E Rumelhart, G E Hinton, R J Williams. Learning Internal Repres-entations by Error Propagation in Parallel Distributed Processing. Vol.1.
[39] D E Rumelhart, J L McClelland. Cambridge, MA:MIT Press, 1986: 318-362
[40]张志涌.精通MATLAB[M].北京:北京航空航天大学出版社, 2008
[41]邓聚龙.灰理论基础[M].武汉:华中科技大学出版社, 2002
[42]刘思峰,郭天榜,党耀国.灰色系统理论及其应用(第二版)[M].北京:科学出版社, 1999
[43]邓聚龙.灰色系统(社会经济)[M].北京:国防工业出版社, 1985
[44]袁嘉祖.灰色系统理论及其应用[M].北京:科学出版社, 1991
[45] Simon Haykin. NEURAL NETWORK A Comprehensive Foundation (Second Edition)[M]. Tsinghua University Press, 2001
[46]廖宁放,高稚允. BP神经网络用于函数逼近的最佳隐层结构[J].北京理工大学学报, 1998, 18(4):476-480
[47]树锦.人工神经网络模型在黄河水质预测中的应用[D].南京:河海大学,2006
[48]崔宝侠.神经网络在水质模型中的应用[J].沈阳工业大学学报, 2003, 25(3):44-46
[49]郑秋红,伍永秋,张永光.冰封期河流中污染物损耗估算模型[J].北京师范大学学报(自然科学版), 2006, 42(6):615-617
[50]张丹丹,徐振.基于MATLAB的AR模型参数估计[J].中国水运, 2006, 4(11):109-110
[51]赵雪辉,郑新秀.灰色系统GM(1,1)残差模型在水质预测中的应用与探讨[J].干旱环境监测. 1997, 11(2):118-120
[2]张锡辉,郑振华,欧阳二明等.水源水质在线监测预警统的建设[J].中国给水排水, 2005, 21(11):14-17
[3]董志颖,王娟,李兵.水质预警理论初探[J].水土保持研究, 2002, 9(3):224-226
[4]熊德琪.环境系统模糊预测、评价、规划、决策理论模式与应用研究[D].大连理工大学土木系, 1994
[5]史根香,郭海生.指数平滑法在地下水水质预测中的尝试[J].湖北地矿,1998. 12(1):35-40
[6]翟颢瑾,高晶.长江未来水质污染的时间序列分析[J].沈阳师范大学学报(自然科学版), 2006, 24(1):22-24
[7] T Inoul. Prediction of Nitrogen Oxide Concentration by A Regression Model[J]. Atmospheric Environment, 1986, 20:2325-2337
[8]吴宏斌.地下水水质预测的多元线性回归分析模型研究[J].山西建筑, 2007, 33(32):201-202
[9]史复有.黄河兰州段耗氧有机污染物浓度统计预测模型的建立[J].环境科学, 1989, 10(3):72-74
[10]邓聚龙.灰色预测与决策[M].武汉:华中工学院出版社, 1986
[11]苗成林,周宏.基于灰色模型的水质预测[J].中国农村水利水电, 2007,(2):126-128
[12]邱淑芳,周其华,王泽文.改进的GM(1,1)模型及其在地下水环境预测中的应用[J].东华理工学院学报, 2006, 29(2):176-180
[13]朱长军,卢军燕,郝振纯等.应用灰色新阵代理GM(1,1)模型预测河流水质[J].河北工程大学学报(自然科学版), 2007, 24(1):45-47
[14]宛筝,李晔.多元线性回归与灰色联合模型在湖泊水质预测中的应用[J].江苏环境科技(增刊), 2006, 19(2):59-61
[15] Marina Campolo. Forecasting River Flow Rate during Low-flow Perio-d Using Neural Network[J]. Water Resource Research, 1999, 35(11): 3547-3552
[16] T. R. Neelakantan, N. V. Pundarikanthan. Neural Network-Based Sim-ulation-Optimization Model for Reservoir Operation[J]. Journal of Wat-er Resources Planning and Management, 2000, 126(2):57-64
[17]罗定贵.基于MATLAB实现的ANN方法在地下水质评价中的应用[J].北京大学学报, 2004, 40(2):296-302
[18] H R Maier, G C Dandy. The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters[J]. Water Resources Resea-rch, 1996, 32(4):1013-1022
[19]陈丽华,马生全.运用BP神经网络研究河水中溶解氧的影响因素[J].兰州交通大学学报(自然科学版), 2005, 24(1):55-58
[20]杨琴,谢淑云. BP神经网络在洞庭湖氨氮浓度预测中的应用[J].水资源与水工程学报, 2006, 17(1):65-70
[21]高卫峰,姚志红.基于BP神经网络的藻类生长预测研究[J].微计算机信息, 2005, 21(10):167-169
[22] D P Loucks, W R Lynn. Probabilistic Models for Predicting Stream Quality[J]. Water Resources Research, 1996,(3):593-605
[23] G Q Tabios. Nonlinear Stochastic Modeling of River Dissolved-Oxyg-en[D]. Colorado State University, 1984
[24] C Baffaut, J L Chamean. Estimation of Pollutant Loads with Fuzzy Sets[J]. Civil Engineering Systems, 1990,7(1):51-61
[25]夏军,张祥伟.河流水质灰色非线性规划的理论与应用[J].水利学报, 1993, (12):1-9
[26] Huang Guohe, Xia Jun. Barriers to Sustainable Water-quality Manage-ment. Journal of Envionmental Management, 2001,61:1-23
[27] Geld of G D. Adaptive Water Mangement: Integrated Water Manage-ment on the Edge of Chaos. Water Science Technology,1995, 32(1): 7-13
[28] J M Zaldivar, E Gutirrez. Forecasting High waters at Venice Lagoon Using Chaotic Time Series Analysis and Nonlinear Neural Networks. Journal of Hydroinformatics, 2000, (2):61-84
[29]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社, 2000
[30] W S McCulloch, W H Pitts. A Logical Calculus of the Ideas Imman-ent in Neuron Activity. Bulletin Mathematical Biophysics, 1943,Vo1.5,115-133
[31] D O Hebb. The Organization of Behavior, Wiley, New York, 1949
[32] F Rosenblatt. The Perception: A Probabilistic Model for Information Storage and Organization in the Brain, Psychological Review, 1958, Vo1.65: 386-408
[33] B Widrow, W Hoff. Adaptive Switching Circuits, Wescon Convention Record, 1960
[34] J J Hopfield. Neural Networks and Physical System with Emergent Collective Computational Abilities. Proceedings of the National Acade-my of Sciences. 1982, Vo1.79: 2554-2558
[35] D E Rumelhart, J L McClelland. Parallel Distributed Processing: Expl-orations in the Microstructure of Cognition, Cambridge Bradford Boo-ks, MIT Press, 1986:1-112
[36] P Werbos. Beyond Regression: New Tools for Prediction and Analysisin the Behavioral Sciences. PhD Dissertation, Harvard University, 1974
[37] D B Parker. Learning-logic, Technical Report TR-47. Center for Com-putational Res, in Economics and Management Sci. MIT, 1985
[38] D E Rumelhart, G E Hinton, R J Williams. Learning Internal Repres-entations by Error Propagation in Parallel Distributed Processing. Vol.1.
[39] D E Rumelhart, J L McClelland. Cambridge, MA:MIT Press, 1986: 318-362
[40]张志涌.精通MATLAB[M].北京:北京航空航天大学出版社, 2008
[41]邓聚龙.灰理论基础[M].武汉:华中科技大学出版社, 2002
[42]刘思峰,郭天榜,党耀国.灰色系统理论及其应用(第二版)[M].北京:科学出版社, 1999
[43]邓聚龙.灰色系统(社会经济)[M].北京:国防工业出版社, 1985
[44]袁嘉祖.灰色系统理论及其应用[M].北京:科学出版社, 1991
[45] Simon Haykin. NEURAL NETWORK A Comprehensive Foundation (Second Edition)[M]. Tsinghua University Press, 2001
[46]廖宁放,高稚允. BP神经网络用于函数逼近的最佳隐层结构[J].北京理工大学学报, 1998, 18(4):476-480
[47]树锦.人工神经网络模型在黄河水质预测中的应用[D].南京:河海大学,2006
[48]崔宝侠.神经网络在水质模型中的应用[J].沈阳工业大学学报, 2003, 25(3):44-46
[49]郑秋红,伍永秋,张永光.冰封期河流中污染物损耗估算模型[J].北京师范大学学报(自然科学版), 2006, 42(6):615-617
[50]张丹丹,徐振.基于MATLAB的AR模型参数估计[J].中国水运, 2006, 4(11):109-110
[51]赵雪辉,郑新秀.灰色系统GM(1,1)残差模型在水质预测中的应用与探讨[J].干旱环境监测. 1997, 11(2):118-120