河流水位的变化过程是一个复杂的非线性过程,传统的神经网络预测存在误差较大、收敛速度慢、稳定性差等问题。为了实现对河流水位的有效预测,提出基于遗传算法(GA)优化Elman神经网络的河流水位预测模型。将GA与Elman网络进行有效结合,解决了单一Elman网络存在的不足。选取永定河的监测站点水文数据对河流水位进行预测与检验,并分别将其与Elman网络与BP网络预测结果进行对比。对比结果表明:GA-Elman水位预测模型的收敛速度快、精度高,可根据预测结果实现对水库、拦河闸合理调用,实现对河流水资源的有效配置,以满足灌溉、发电、防洪等工作的需求。
Abstract
The fluctuation of river water level is a complex nonlinear process. Traditional neural network prediction is of slow convergence and poor stability with large error. To effectively predict river water level, a prediction model based on Elman neural network optimized by genetic algorithm (GA) is proposed. The effective combination of GA and Elman network solves the deficiencies of Elman neural network. The water level at Yongding river monitoring station is predicted by the proposed model and validated according to measured hydrological data, and the prediction results are compared with those obtained by Elman neural network and BP neural network. Results imply that the GA-Elman water level prediction model is of fast convergence and high precision. According to the prediction results, reservoirs and river barrages can be operated rationally for an effective allocation of water resources to meet the demands of irrigation, power generation and flood control.
关键词
河流水位 /
预测模型 /
GA算法 /
Elman网络 /
BP网络 /
河流水资源有效配置
Key words
river water level /
prediction model /
GA algorithm /
Elman network /
BP network /
effective allocation of river water resources
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李 欣,王 超, 赵虎川. 基于时空序列模型的RBF神经网络在河流水位预测中的应用[J].城市勘测, 2016,(5):34-39.
[2] 苑希民,刘树坤,陈 浩. 基于人工神经网络的多泥沙洪水预报[J].水科学进展,1999,10(4):393-398.
[3] 丁 红,董文永,吴德敏.基于LM算法的双隐含层BP神经网络的水位预测[J].统计与决策,2014,(15):16-19.
[4] HUANG G, HEPING H U, TIAN F. Flood Level Forecast Model for Tidal Channel Based on the Radial Basis Function-Artificial Neural Network[J]. Advances in Water Science, 2003, 14(2):158-162.
[5] 陈 进,黄 薇.长江水库群联合调度可能性分析[J].raybet体育在线
院报,2008, 25(2):1-5.
[6] 李界家,孙璐璐,王 奔,等. 基于Elman神经网络阳极效应故障预报方法[J].沈阳建筑大学学报(自然科学版), 2010, 26(5):1012-1016.
[7] 魏 桢,邓院昌,杨正浩. 基于Elman神经网络的风电场噪声预测模型[J].水电能源科学, 2015,(5):203-206.
[8] 李康顺, 李 凯, 张文生. 一种基于改进BP神经网络的PCA人脸识别算法[J].计算机应用与软件, 2014,(1):158-161.
[9] 关学忠,宋韬略,徐延海,等. 污水处理中BP神经网络与Elman神经网络的预测比较[J].自动化技术与应用, 2014, 33(10):1-3.
[10]胡小平,梁承华,杨之为,等. 植物病虫害BP神经网络预测系统的研制与应用[J].西北农林科技大学学报(自然科学版), 2001, 29(2):73-76.
[11]胡 任, 韩赞东, 王克争. 基于BP神经网络预测静置电池的剩余电量[J].电池, 2006, 36(1):58-59.
[12]蔡时连. BP神经网络和Elman神经网络模型的图书复本量预测分析[J].图书情报工作, 2014,(增1):157-159.
[13]党小超,郝占军. 基于改进Elman神经网络的网络流量预测[J].计算机应用, 2010, 30(10):2648-2652.
[14]MADHIARASAN M, DEEPA S N. ELMAN Neural Network with Modified Grey Wolf Optimizer for Enhanced Wind Speed Forecasting[J]. Circuits & Systems,2016, 7(10):2975-2995.
[15]阿 娜. 基于Elman神经网络的在线信息产品定价策略研究[J].电子科学技术, 2016, 3(5):638-642.
[16]REN S, GAO L. Resolve of Overlapping Voltammetric Signals in Using a Wavelet Packet Transform Based Elman Recurrent Neural Network[J]. Journal of Electroanalytical Chemistry, 2006, 586(1):23-30.
[17]李建华, 王孙安, 杜海峰. 一种改进的遗传算法:Family GA[J].控制与决策, 2004, 19(9):999-1003.
[18]胡飞虎, 马贝龙, 杨 丽,等. 基于改进遗传算法的应急物资配送车辆调度优化问题研究[J].计算机应用研究, 2014, 31(10):2928-2932.
[19]田中大, 高宪文, 李树江,等. 遗传算法优化回声状态网络的网络流量预测[J].计算机研究与发展, 2015, 52(5):1137-1145.
[20]张 帝, 姜久春, 张维戈,等. 基于遗传算法的电动汽车换电站经济运行[J]. 电网技术, 2013, 37(8):2101-2107.
基金
国家自然科学基金面上项目(51179002);北京市市属高校创新能力提升计划项目(PXM2014_014213_000033);北京市教委科技计划重点项目(KZ201510011011)
PDF(2305 KB)
