将相空间重构理论引入月径流模拟中,利用C-C算法进行相空间重构,将一维径流时间序列拓展为多维,基于交叉验证支持向量机(CV-SVM)原理及方法,构建以相空间重构理论与支持向量机相结合的径流时间序列模拟模型,并构建传统BP、双隐层BP及GA-BP径流时间序列模拟模型作为对比模型,以盘龙河龙潭寨月径流时间序列为例进行分析。结果显示:基于相空间重构理论的CV-SVM模拟模型能较好地处理复杂的径流序列,在长达200个月的测试样本模拟中,平均相对误差eMRE、最大相对误差eMaxRE分别为0.571 7%,5.526 7%,决定系数DC和合格率QR分别为0.999 9和100%。表明该模型具有较高的泛化能力和模拟精度,模拟效果明显优于传统BP、双隐层BP模型,甚至优于GA-BP模型;表明研究建立的基于相空间重构理论的CV-SVM模型用于径流模拟是合理可行的,可为径流模拟提供方法和参考。
Abstract
The theory of phase space reconstruction is introduced into the monthly runoff simulation. The C-C algorithm was used for phase space reconstruction, and the one-dimensional runoff time series were expanded to multi-dimensional. Furthermore, with the association of CV-SVM (cross validation-support vector machine) principle and methods, a runoff time series model was established. Meanwhile, traditional BP, double hidden layer BP and GA-BP runoff time series simulation model were constructed for comparison. The monthly runoff time series at Longtanzhai of Panlong River was taken as analysis example. The results showed that the model based on phase space reconstruction and CV-SVM can better handle the complex runoff series. During the simulation of test sample of 200 months, the average relative error eMRE, the maximum relative error eMaxRE, the determination coefficient DC, and the qualified rate QR was respectively 0.5717%, 5.5267%, 0.9999 and 100%, which demonstrated that the model is of high generalization ability and simulation precision. The simulation result is obviously superior to those of traditional BP, double hidden layer BP model, and is even better than GA-BP model. The results indicate that the model based on phase space reconstruction and CV-SVM model for runoff simulation is feasible.
关键词
相空间重构 /
支持向量机 /
交叉验证 /
混沌 /
径流模拟
Key words
phase space reconstruction /
support vector machine /
cross validation /
chaos /
runoff simulation
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 吕金虎, 陆君安, 陈士华. 混沌时间序列分析及其应用[M].武汉:武汉大学出版社,2002.(LV Jin-hu, LU Jun-an, CHEN Shi-hua. Chaotic Time Series Analysis and Its Applications[M]. Wuhan: Wuhan University Press, 2002.(in Chinese)
[2] 于国荣,夏自强.混沌时间序列支持向量机模型及其在径流模拟中应用[J].水科学进展,2008,19(1):116-122.(YU Guo-rong, XIA Zi-qiang. Prediction Model of Chaotic Time Series Based on Support Vector Machine and Its Application to Runoff[J]. Advances in Water Science,2008,19(1):116-122.(in Chinese)
[3] 陈南祥,黄 强,曹连海,等.径流序列的相空间重构神经网络预测模型[J].河海大学学报(自然科学版),2005,33(5):490-493.(CHEN Nan-xiang, HUANG Qiang, CAO Lian-hai, et al. Neural Network Forecasting Model for Phase Space Reconstruction of Runoff Series[J]. Journal of Hohai University (Natural Sciences), 2005,33(5):490-493.(in Chinese)
[4] 战国隆,马孝义,刘继龙,等.泾河月径流量的混沌特征识别及模拟[J].水利水电科技进展,2010,30(1):7-9.(ZHAN Guo-long, MA Xiao-yi, LIU Ji-long, et al. Chaotic Feature Recognition and Simulation of Monthly Runoff of Jinghe River[J]. Advances in Science and Technology of Water Resources, 2010,30 (1): 7-9.(in Chinese)
[5] 邵东国,刘丙军,阳书敏,等.水资源繁杂系统理论[M].北京:科学出版社,2012.(SHAO Dong-guo, LIU Bing-jun, YANG Shu-min, et al. Theory of Complex Water Systems[M]. Beijing: Science Press, 2012.(in Chinese)
[6] Vladimir N.Vapnik.统计学习理论的本质[M].张学工译.北京:清华大学出版社,2000.(VAPNIK V N. The Nature of Statistical Learning Theory [M]. Translated by ZHANG Xue-gong. Beijing: Tsinghua University Press, 2000.(in Chinese)
[7] 田景文,高美娟.人工神经网络算法研究及应用[M].北京:北京理工大学出版社,2006.(TIAN Jing-wen, GAO Mei-juan. Artificial Neural Network Algorithm Research and Application[M]. Beijing: Beijing Institute of Technology Press, 2006.(in Chinese)
[8] MATLAB中文论坛.MATLAB神经网络30个案例分析[M].北京:北京航空航天大学出版社,2010.(MATLAB Chinese Forum. 30 Case Analysis of MATLAB Neural Network[M]. Beijing: Beihang University Press,2010.(in Chinese)
[9] 崔东文. 支持向量机在湖库营养状态识别中的应用研究[J].水资源保护,2013,29(4):26-30.(CUI Dong-wen. Application of Support Vector Machine to Lake and Reservoir Trophic Status Recognition[J].Water Resources Protection,2013, 29(4): 26-30.(in Chinese)
[10]KANTZ H, SCHREIBER T. Nonlinear Time Series Analysis[M]. Cambridge: Cambridge University Press,1997.
[11]FRASER A M, SWINNEY H L. Independent Coordinates for Strange Attractors from Time Series[J]. Physical Review A, 1986, 33(2): 1134-1140.
[12]GRASSBERGER P, PROCACCIA I. Measuring the Strangeness of Strange Attractors[J]. Physica D, 1983, 9(1/2): 189-208.
[13]KENNEL M B, BROWN R, ABARBANEL H D I. Determining Embedding Dimension for Phase-Space Reconstruction Using a Geometrical Construction[J]. Physical Review A, 1992, 45(6): 3403-3407.
[14]KUGIURMTZIS D. State Space Reconstruction Parameters in the Analysis of Chaotic Time Series-the Role of the Time Window Length[J].Physica D,1996,95(1):13-28.
[15]KIM H S, EYKHOLT R, SALAS J D. Nonlinear Dynamics, Delay Times and Embedding Windows[J]. Physica D, 1999, 127(1/2): 48-60.
[16]吴学文.考虑生态多目标水电站水库混沌优化调度研究[M].北京:中国水利水电出版社,2012.(WU Xue-wen. Multi-objective Optimization Scheduling of Hydropower Station in Consideration of Ecological Chaos[M]. Beijing: China Water Power Press, 2012.(in Chinese)
[17]张德丰.MATLAB神经网络应用设计[M].北京:机械工业出版社,2009.(ZHANG De-feng. MATLAB Neural Network Design[M]. Beijing: Mechanical Industry Press, 2009.(in Chinese)
[18]张良均,曹 晶,蒋世忠.神经网络实用教程[M].北京:机械工业出版社,2008.(ZHANG Liang-jun,CAO Jing, JIANG Shi-zhong. Practical Guide to Neural Networks[M]. Beijing: Mechanical Industry Press,2008.(in Chinese)
[19]SL250—2000,水文情报预报规范[S].(SL250—2000, Standard for Hydrological Information and Hydrological Forecasting[S].(in Chinese)
[20]崔东文.基于极限学习机的长江流域水资源开发利用综合评价[J].水利水电科技进展,2013,33(2):14-19.(CUI Dong-wen. Comprehensive Evaluation of Water Resources Development and Utilization in Yangtze River Basin Based on Extreme Learning Machine[J]. Advances in Science and Technology of Water Resources, 2013, 33(2): 14-19.(in Chinese)
PDF(1261 KB)
