基于改进的BP神经网络径流量还原计算研究
|
摘要
针对水文系统复杂性与非线性的特点,加入动量项因子对BP神经网络进行改进,加快收敛速度,将自然因素、人为因素、自然与人为混合因素分别作为输入因子,构建了大沽夹河天然径流量还原计算方案,用逐项还原法的结果验证对比选出最佳方案。结果表明:①经过改进的BP神经网络收敛速度明显加快,由平均的6 028次迭代优化到1 782次迭代;②以降雨量、蒸发量和实测径流量为输入因子的第三种方案模拟误差最小,适用于大沽夹河流域天然径流量还原计算。
Aiming at the characteristics of the complexity and nonlinear of hydrological system, the BP neural network model was improved by the introduction of momentum factor to accelerate the convergence rate, established three kinds of schemes based on different input factors which were natural factors, human factors and synthetic nature and human nature to restore natural runoff calculation in Dagujia River and selected the best scheme by comparison and analysis of successive reduction method. The results show that the improved BP neural network can accelerate the convergence rate and the iteration time is optimized from the average 6 028 to 1 782. Getting the third scheme which used the rainfall, evaporation and measured runoff as the input factors is the best scheme in the simulation error and it is suitable for the natural runoff reduction calculation in the Dagujia River basin.
Aiming at the characteristics of the complexity and nonlinear of hydrological system, the BP neural network model was improved by the introduction of momentum factor to accelerate the convergence rate, established three kinds of schemes based on different input factors which were natural factors, human factors and synthetic nature and human nature to restore natural runoff calculation in Dagujia River and selected the best scheme by comparison and analysis of successive reduction method. The results show that the improved BP neural network can accelerate the convergence rate and the iteration time is optimized from the average 6 028 to 1 782. Getting the third scheme which used the rainfall, evaporation and measured runoff as the input factors is the best scheme in the simulation error and it is suitable for the natural runoff reduction calculation in the Dagujia River basin.
引文
[1] 李兴拼,黄国如,江涛.RVA法评估枫树坝水库对径流的影响[J].水电能源科学,2009,27(3):18-21.
[2] 孔兰,陈俊贤,蒋任飞.基于情景分析和RVA法的梯级开发对水文情势的影响[J].中国农村水利水电,2015(6):56-60,65.
[3] 陈栋为,陈晓宏,李翀,等.基于RAV法的水利工程对河流水文情势改变的累积效应研究:以东江流域为例[J].水文,2011,31(2):54-57.
[4] 陆中央.关于年径流量系列的还原计算问题[J].水文,2000,20(6):9-12.
[5] 许万清,何永健.山区水文站天然年径流量的还原计算方法浅析[J].吉林水利,2009(9):41-43.
[6] 吴建生,金龙,农吉夫.遗传算法BP神经网络的预报研究和应用[J].数学的实践与认识,2005(1):83-88.
[7] ROOIJ A J F V,JOHNSON R P,JAIN L C.Neural Network Training Using Genetic Algorithms[M].New York:World Scientific,1996:1-4.
[8] 薄会娟,董晓华,邓霞.BP网络泛化能力的改进及在径流预测中的应用[J].人民黄河,2011,33(1):33-34.
[9] 王峥,马孝义,吕静渭,等.泾河年径流量BP神经网络模型研究[J].人民黄河,2012,34(4):26-29.
[10] 隋彩虹,徐宗学.人工神经网络模型在渭河下游洪水预报中的应用[J].水文,2006,26(2):38-42.
[11] 张少文,张学成,王玲,等.黄河年降雨—径流BP预测模型研究[J].人民黄河,2005,27(1):18-20.
[12] 闫宝伟,潘增,薛野,等.论水文计算中的相关性分析方法[J].水利学报,2017,48(9):1039-1046.
[13] 烟台市水文局.烟台市水资源调查评价[R].烟台:烟台市水文局,2016:1-150.
[2] 孔兰,陈俊贤,蒋任飞.基于情景分析和RVA法的梯级开发对水文情势的影响[J].中国农村水利水电,2015(6):56-60,65.
[3] 陈栋为,陈晓宏,李翀,等.基于RAV法的水利工程对河流水文情势改变的累积效应研究:以东江流域为例[J].水文,2011,31(2):54-57.
[4] 陆中央.关于年径流量系列的还原计算问题[J].水文,2000,20(6):9-12.
[5] 许万清,何永健.山区水文站天然年径流量的还原计算方法浅析[J].吉林水利,2009(9):41-43.
[6] 吴建生,金龙,农吉夫.遗传算法BP神经网络的预报研究和应用[J].数学的实践与认识,2005(1):83-88.
[7] ROOIJ A J F V,JOHNSON R P,JAIN L C.Neural Network Training Using Genetic Algorithms[M].New York:World Scientific,1996:1-4.
[8] 薄会娟,董晓华,邓霞.BP网络泛化能力的改进及在径流预测中的应用[J].人民黄河,2011,33(1):33-34.
[9] 王峥,马孝义,吕静渭,等.泾河年径流量BP神经网络模型研究[J].人民黄河,2012,34(4):26-29.
[10] 隋彩虹,徐宗学.人工神经网络模型在渭河下游洪水预报中的应用[J].水文,2006,26(2):38-42.
[11] 张少文,张学成,王玲,等.黄河年降雨—径流BP预测模型研究[J].人民黄河,2005,27(1):18-20.
[12] 闫宝伟,潘增,薛野,等.论水文计算中的相关性分析方法[J].水利学报,2017,48(9):1039-1046.
[13] 烟台市水文局.烟台市水资源调查评价[R].烟台:烟台市水文局,2016:1-150.