基于小波消噪的混沌神经网络月径流预报模型
The Chaotic Neural Network Model of Monthly Runoff Forecast Based on Wavelet De-Noising

作者: 周建中 :华中科技大学水电与数字化工程学院; 张娟娟 , 郭 俊 , 张勇传 :;

关键词: 径流预报小波消噪饱和嵌入维数混沌神经网络Runoff Forecast Wavelet Do-Noising Saturated Embedding Dimension Chaotic Neural Network

摘要: 受天气系统和流域下垫面系统综合作用的影响,径流过程具有高度的非线性特征。针对径流时间序列强相关性和复杂特性,本文综合运用小波变换、混沌理论和神经网络非线性理论对水文时间序列进行分析和预测。首先通过小波变换对月径流序列进行消噪处理,然后推求出大于零的李雅普诺夫指数,证实了宜昌站的月径流序列具有混沌特性,为此引入混沌理论中的相空间重构方法计算出宜昌站1882~2008年月径流序列的最佳延迟时间和饱和嵌入维数,进而以相空间重构后的时间序列作为神经网络的输入进行网络训练得到最佳的混沌神经网络径流预报模型。实例研究结果表明,该模型能较好地处理复杂非线性径流序列,预测精度高,具有实际工程应用价值。

Abstract: Runoff process is highly nonlinear characteristics under the synthetic action of weather system and underlying surface system. Considering the strong correlation and high complexity of runoff time series, the wavelet transform is applied to eliminate noise in the monthly runoff time series in this paper, of which the Lyapunov index method is used to recognize the chaotic feature of the monthly runoff time series. On this basis, the phase space restructure of chaos theory is used to calculate the best delay time and saturated embedding dimension of the runoff time series from 1882 to 2008 of the Yichang station. At last, taking the times series computed by the phase space restructure as the input of chaotic neural network model to get the proposed model by network training. Prediction results show that this model can process a complex hydrological data series better, and is of higher prediction accuracy and good prospect of engineering application.

文章引用: 周建中 , 张娟娟 , 郭 俊 , 张勇传 (2012) 基于小波消噪的混沌神经网络月径流预报模型。 水资源研究, 1, 65-71. doi: 10.12677/JWRR.2012.13010

参考文献

[1] 丁刚, 钟诗胜. 基于过程神经网络的时间序列预测及其应用研究[J]. 控制与决策, 2006, 21(9): 1037-1040. DING Gang, ZHONG Shisheng. Time series prediction based on process neural networks and its applications. Control and Decision, 2006, 21(9): 1037-1040. (in Chinese)

[2] 王秀杰, 费守明. 小波分析方法在水文径流模拟中的应用[J]. 水电能源科学, 2007, 25(6): 1-3. WANG Xiujie, FEI Shouming. Application of wavelet analysis to hydrological runoff simulation. Water Resources and Power, 2007, 25(6): 1-3. (in Chinese)

[3] 姜翔程. 水文时间序列的混沌特性及预测方法[M]. 北京: 中国水利水电出版社, 2011. JIANG Xiangcheng. Chaotic characteristics and forecasting method of hydrological time series. Beijing: China Water Power Press, 2011. (in Chinese)

[4] 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 Jinhu, LU Junan and CHEN Shihua. Chaos time series analysis and its applications. Wuhan: Wuhan University Press, 2002. (in Chinese)

[5] 张晓伟, 沈冰, 黄领梅. 基于BP神经网络的灰色自记忆径流预测模型[J]. 水力发电学报, 2009, 1: 68-71. ZHANG Xiaowei, SHEN Bing and HUANG Lingmei. Grey self-memory model based on BP neural network for annual runoff prediction. Journal of Hydroelectric Engineering, 2009, 1: 68-71. (in Chinese)

[6] 潘泉, 张磊, 孟晋丽, 等. 小波滤波方法及应用[M]. 北京: 清华大学出版社, 2005. PAN Quan, ZHANG Lei, MENG Jinli, et al. Wavelet filtering method and its applications. Beijing: Tsinghua University Press, 2005. (in Chinese)

[7] 成礼智, 王红霞, 罗永. 小波的理论与应用[M]. 北京: 科学出版社, 2004. CHENG Lizhi, WANG Hongxia and LUO Yong. Wavelet theory and its applications. Beijing: Science Press, 2004. (in Chinese)

[8] 刘国华, 钱镜林, 王建江. 小波软阈值技术和人工神经网络在洪水预报中的研究[J]. 水力发电学报, 2004, 23(1): 6-9. LIU Guohua, QIAN Jinglin and WANG Jianjiang. Study of flood forecast based on wavelet soft-threshold technology and ANN. Journal of Hydroelectric Engineering, 2004, 23(1): 6-9. (in Chinese)

[9] 杨俊杰, 周建中, 喻菁, 等. 混合混沌优化方法及其在非线性规划问题中的应用[J]. 计算机应用, 2004, 24(10): 118-120. YANG Junjie, ZHOU Jianzhong, YU Jing, et al. Hybrid chaos optimization algorithm for nonlinear programming problem. Computer Applications, 2004, 24(10): 118-120. (in Chinese)

[10] TAKENS, F. Dynamical systems and turbulence. In: RAND, D. A., YOUNG, L. S., Eds., Lecture Notes in Mathematics, Berlin: Springer, 1981, 898: 365-382.

[11] GIBSON, J. F., FARMER, J., CASDAGLI, M., et al. An analytic approach to practical state space reconstruction. Physica D, 1992, 57: 1-30.

[12] 汤成友, 官学文, 张世明. 现代中长期水文预报方法及其应用[M]. 北京: 中国水利水电出版社, 2008. TANG Chengyou, GUAN Xuewen and ZHANG Shiming. Modern mid-to-long-term hydrological forecasting method and its applications. Beijing: China Water Power Press, 2008. (in Chinese)

[13] HE, X. R., CHEN, B. Z. Study on improving testing results of BP neural networks. Journal of Qinghua University, 1995, 35(3): 31-36.

[14] BRITO, N. S. P., SOUZA, B. A. and PIRES, F. A. C. Daubechies wavelets in quality of electrical power. The International Conference on Harmonics and Quality of Power, Piscataway: IEEE, 1998: 511-515.

[15] 李荣峰, 沈冰, 张金凯. 基于相空间重构的水文自记忆预测模型[J]. 水利学报, 2006, 37(5):583-587. LI Rongfeng, SHEN Bing and ZHANG Jinkai. Self-memory hydrologic prediction model based on phase-space reconstitution. Journal of Hydraulic Engineering, 2006, 37(5): 583-587. (in Chinese)

[16] CAO, L. Y. Practical method for determining the minimum embedding dimensions of a scalar time series. Physical D, 1997, 110(1-2): 43-50.

[17] 王东生, 曹磊. 混沌、分形及其应用[M]. 北京: 中国科学技术大学出版社, 1995. WANG Dongsheng, CAO Lei. Chaos, fractals and its applications. Beijing: China Science and Technology University Press, 1995. (in Chinese)

[18] 卢宇, 陈宇红, 贺国光. 应用改进型小数据量法计算交通流量的最大Lyapunov指数[J]. 系统工程理论与实践, 2007, 1: 85-90. LU Yu, CHEN Yuhong and HE Guoguang. The computing of maximum Lyapunov exponent in traffic flow applying the im-proved small-data method. Systems Engineering-Theory & Practice, 2007, 1: 85-90. (in Chinese)

分享
Top