基于极点对称模态分解的中长期径流预报组合模型  

Combined model for medium-and long-term runoff predictions based on Extreme-point Symmetric Mode Decomposition

作　　者：李继清[1] 刘洋[1] 张鹏[1,2] 陈景 LI Jiqing;LIU Yang;ZHANG Peng;CHEN Jing(School of Water Resources and Hydropower Engineering,North China Electric Power University,Beijing 102206,China;Guangxi Pingban Hydropower Development Co.,Ltd.,Baise 533000,China)

机构地区：[1]华北电力大学水利与水电工程学院,北京102206 [2]广西平班水电开发有限公司,广西百色533000

出　　处：《水力发电学报》2024年第7期30-40,共11页Journal of Hydroelectric Engineering

基　　金：国家自然科学基金项目(52179014);国家重点研发计划项目(2017YFC0405906)。

摘　　要：为提高径流预报精度,解决径流序列分解后高频分量波动范围大、预报精度差的问题,基于极点对称模态分解法(ESMD)平稳化处理技术将径流序列分解,通过分析不同频率分量特征,择优选取预报方法,结合粒子群优化最小二乘支持向量机(PSO-LSSVM)全局优化和非线性建模能力及适应性强的特点,对高频分量进行预测,利用BP神经网络非线性映射能力和逼近任意非线性函数的优势对中低频分量和趋势分量进行预报,构建了ESMD-PSO-LSSVM-BP组合预报模型,对西江干流上中下游三座水文站的年、月尺度径流开展中长期径流预报。结果表明,对不同频率分量采用不同预报方法的组合模型可以有效提高径流预报精度。Extreme-point Symmetric Mode Decomposition(ESMD)is used to predict runoff series based on a runoff forecasting model to solve two problems after runoff series decomposition-large fluctuation ranges of high frequency components and poor forecast accuracy.We use the stationary processing technique of the ESMD to decompose the runoff series,select the best prediction method by analyzing the characteristics of different frequency components,combine Particle Swarm Optimization(PSO)and Least Square Support Vector Machines(LSSVM)for the prediction of high-frequency components,and use the back-propogation(BP)neural network for the prediction of mid-and low-frequency components.A combined ESMD-PSO-LSSVM-BP forecasting model is constructed to forecast annual and monthly runoffs at three hydrological stations in the upper and middle reaches of the Xijiang River.The results show this model,using different forecasting methods for different frequency components,improves the runoff forecasting accuracy significantly.

关 键 词：西江流域 径流预报 非平稳序列 组合预报模型 极点对称模态分解 

分 类 号：P338.2[天文地球—水文科学]