基于PSO-SVR-LSTM水位预测模型研究  

Research on water level prediction model based on PSO-SVR-LSTM

作　　者：顾乾晖 胡翌 涂振宇[1] GU Qianhui;HU Yi;TU Zhenyu(College of Information Engineering,Nanchang Institute of Technology,Nanchang 330096,China;Jiangxi Provincial Ganfu Plain Water Conservancy Engineering Administration,Jiangxi Nanchang 330096,China)

机构地区：[1]南昌工程学院信息工程学院,江西南昌330099 [2]江西省赣抚平原水利工程管理局,江西南昌330096

出　　处：《江西水利科技》2021年第4期278-284,共7页Jiangxi Hydraulic Science & Technology

基　　金：江西省水利厅科技项目(KT201639);江西省科技厅重点研发项目(20151BBE50077).

摘　　要：河流的水位变化受到众多复杂因素的影响,水位数据不仅显现非线性特点还具有时序性和复杂性等特点。水位预测的精度提高对河道管理、水利建设、水资源调度、防洪减灾和航运安全等方面具有重大意义。本文利用长短时记忆神经网络(LSTM)在处理长时间序列问题上的优势和支持向量回归机(SVR)能够很好地处理非线性数据的优势以及粒子群优化算法(PSO)自适应全局搜索的优势,提出了将PSO-SVR-LSTM组合模型应用于南昌市潦水万家埠段的水位预测中。仿真实验结果表明:相对于LSTM模型、SVR模型和BP等模型,本文提出的PSO-SVR-LSTM模型的预测精确度更高。The change of river water level is affected by many complex factors.The water level data not only shows nonlinear characteristics,but also features with time sequence and complexity.Improving the accuracy of water level prediction is of great significance to river management,water conservancy construction,water resources scheduling,flood control and disaster reduction,and shipping safety.This paper makes use of the advantages of long-term memory neural network(LSTM)in dealing with long-time series problems,the advantages of support vector regression(SVR)in dealing with nonlinear data,and the advantages of particle swarm optimization(PSO)in adaptive global search.The pso-svr-lstm combination model is applied to the water level prediction of WanJiaBu section of Xiuhe river.The simulation results show that the prediction accuracy of the proposed pso-svr-lstm model is higher than that of LSTM model,SVR model and BP model.

关 键 词：河流水位 预测模型 LSTM BP神经网络 支持向量机 水资源有效配置 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]