基于粒子群优化算法的RBF神经网络在泾惠渠灌区地下水位埋深预测中的应用  

Groundwater Depth Prediction Model in Jinghui Irrigation District of RBF Neutral Network Based on Particle Swarm Optimization

作　　者：李慧[1,2] 周维博[1,2] 刘博洋[1,2] 李娜[1,2] 马聪[1,2] 

机构地区：[1]长安大学环境科学与工程学院,陕西西安710054 [2]长安大学旱区地下水文与生态效应教育部重点实验室,陕西西安710054

出　　处：《水电能源科学》2014年第8期127-130,共4页Water Resources and Power

基　　金："十二五"国家科技支撑计划项目(2011BAD29B0104)

摘　　要：针对不恰当地选取RBF神经网络的网络结构和参数会使网络收敛慢的问题,采用粒子群优化算法对RBF神经网络参数进行优化,建立了基于粒子群优化算法的RBF神经网络模型（PSO-RBF模型）,对泾惠渠灌区地下水位埋深进行了模拟和预测。结果表明,与单一的RBF神经网络相比,PSO-RBF模型具有较高的预测精度。再根据时间序列预测法预测的降水量、径流量、蒸发量、渠灌引水量、地下水开采量、气温等模型的输入变量,用训练好的PSO-RBF模型预测了泾惠渠灌区2009-2020年地下水位埋深,发现该灌区地下水位埋深呈下降趋势。As inappropriate parameters of RBF neural network will slow down the network convergence rate, particle swarm optimization （PSO） is used to optimize the parameters of RBF neural network. And then the PSO-RBF model is established to simulate and predict the groundwater depth of Jinghui irrigation district. Compared with single RBF neural network model, the results show that PSO-RBF model has higher prediction accuracy. Finally, based on the data of precipitation, runoff, volume of groundwater exploitation and other model input variables which were predicted by time series forecasting method, PSO-RBF model is applied to forecast groundwater depth of Jinghui irrigation district from 2009 to 2020, it finds out that the groundwater depth of this irrigation district appears downward trend.

关 键 词：地下水位埋深 预测 粒子群优化算法 径向基函数神经网络 时间序列预测法 泾惠渠灌区 

分 类 号：TV211.12[水利工程—水文学及水资源]