共查询到20条相似文献,搜索用时 375 毫秒
1.
2.
3.
4.
为了分析多水库系统中两座水库之间灌溉用水的分配问题,建立了基到动态规划的神经网络模型。为了研究从一座上游水库取水在下游两座之库之间进行水量分配的问题,提出了3个状态变量和4个决策变量的改进的动态规划算法。采用神经网络模型,用3个状态变量动态规划算法得出调度原则,就所研究的多水库系统实例来说,新的动态规划神经网络模型的性能很好,将该模型的性能与临时凑合的标准调度原则和以前推荐使用的约束动态规划神经网络模型进行了比较。 相似文献
5.
针对水质监测数据多源、非线性、不确定性大的特点,提出了一种基于神经网络与改进D-S证据理论相结合的水质评价模型。该模型首先利用3种前馈神经网络对水质监测数据进行初步评价,将初步评价结果归一化后作为基本概率分配,然后引入证据权重修正冲突证据,根据D-S合成规则得到融合评价结果,最后利用迭代思想修正评价结果。其中,基于证据权重修正冲突证据并进行融合结果的迭代修正,能有效解决传统D-S证据理论无法处理高冲突证据的缺陷。冀南地区5个监测断面水质评价结果表明,该水质评价模型能够提高水质评价准确性。 相似文献
6.
为了分析多水库系统中两座水库之间灌溉用水的分配问题,建立了基于动态规划的神经网络模型。为了研究从一座上游水库取水在下游两座水库之间进行水量分配的问题,提出了3个状态变量和4个决策变量的改进的动态规划算法。采用神经网络模型,用3个状态变量动态规划算法得出调度原则。就所研究的多水库系统实例来说,新的动态规划神经网络模型的性能很好,将该模型的性能与临时凑合的标准调度原则和以前推荐使用的约束动态规划神经网络模型进行了比较。 相似文献
7.
采用神经网络进行土质边坡稳定性评价时,差异性较大的训练样本往往会使评价结果不太理想。针对这一问题引入 C4.5决策树算法,采用多个土质边坡工程的实测数据,运用信息增益率进行分类属性的选择,并对建立好的树体结构进行剪枝操作,建立基于决策树的土质边坡稳定性评价模型。将该模型与 BP 神经网络和 LVQ (Learning Vector Quantization,学习向量量化)神经网络进行对比分析,结果显示决策树模型分类正确率最高,达到90%,模型所用时间为2.24 s,表明把决策树用于土质边坡稳定性评价是合理的。 相似文献
8.
9.
崔东文 《水利水电科技进展》2019,39(4):41-48
采用5个标准测试函数对多组群教学优化(MGTLO)算法进行仿真验证,并将仿真结果与基本教学优化(TLBO)算法、混合蛙跳算法(SFLA)、差分进化(DE)算法和粒子群优化(PSO)算法的仿真结果进行对比。利用MGTLO算法搜寻基于广义回归神经网络(GRNN)、径向基神经网络(RBF)、支持向量机(SVM)模型单元的组合模型的最佳模型参数和组合权重系数,提出MGTLO-GRNN-RBF、MGTLO-GRNN-SVM、MGTLO-RBF-SVM、MGTLO-GRNN-RBF-SVM 4种组合预测模型,以新疆伊犁河雅马渡水文站和云南省某水文站年径流量预测为例进行了实例分析,并将预测结果与MGTLO-GRNN、MGTLO-RBF、MGTLO-SVM和GRNN、RBF、SVM 6种单一模型的结果进行对比分析。结果表明:MGTLO算法寻优精度优于TLBO、SFLA、DE和PSO算法,具有较好的收敛速度和全局极值寻优能力;组合模型融合了MGTLO算法与GRNN、RBF、SVM模型单元的优点,在预测精度、泛化能力等方面均优于单一模型;MGTLO算法能有效优化各组合模型的相关参数和权重系数,MGTLO-GRNN-RBF-SVM模型预测精度最高。 相似文献
10.
11.
造成中长期水文预报研究和预报困难的主要原因是水文现象本身的复杂性和不确定性,以及内部复杂的非线性关系,针对这些问题,本文建立了一种小波神经网络时间序列模型,并用遗传算法对小波神经网络的连接权值和伸缩变量、平移变量进行优化。使用这种模型对黄河三门峡站逐年月天然流量进行预报检验,并将检验结果与传统的小波神经网络和BP神经网络进行对比,从模型预报精度、趋势性和稳定性3个方面进行分析,分析发现,这种遗传算法优化的小波神经网络时间序列模型能够有效地克服传统的小波神经网络和BP网络容易陷入局部极小的缺陷,能够对水文现象的趋势性作出较精确的预测,具有良好的预报精度和稳定性。 相似文献
12.
BP 网络用于水文预测的几个问题探讨 总被引:84,自引:4,他引:84
近年来人工神经网络(ANN)在水文分析和水文预测中的应用越来越广泛,然而应用人工神经网络的BP模型进行水文预测却存在网络结构的确定、收敛准则的选择、训练速度较慢和预测精度等问题,本文通过两个实例发现训练样本的复杂性对BP网络结构有较大影响,讨论了收敛准则选择的问题,给出加快训练速度的几项改进措施,实例表明BP网络是一种精度较高的水文预测模型. 相似文献
13.
14.
针对水文时间序列的非平稳性特征,以长江三峡宜昌站1904~2003年年平均流量为例,分别建立了小波分析(WA)与BP神经网络和径向基函数神经网络(RBF)耦合的预测模型,探究了两种组合模型的预测效果,并与传统的单一人工神经网络模型对比;并采用5种常见的预测性能评价指标分析预测效果。结果表明:组合模型预测成果的精度较单一模型显著提高;组合和单一模型中RBF网络模型均优于BP网络模型;小波径向基函数神经网络组合模型具有较优的预测精度和泛化能力,是提高预测精度的有效方法,在径流预测中具有可行性。 相似文献
15.
A decision support model (DSM) has been developed using the artificial neural networks (ANN) for optimal operation of a reservoir
in south India. The DSM developed is a combination of a rule based expert system and ANN models, which are trained using the
results from deterministic single reservoir optimisation algorithm. The developed DSM is also flexible to use multiple linear
regression equations instead of trained neural network models for different time periods. A new approach is tried with the
DSM based on trained neural network models, which use real time data of previous time periods for deciding operating policies.
The developed DSM based on ANN outperforms the regression based approach. 相似文献
16.
17.
Muhammad Shoaib Asaad Y. Shamseldin Sher Khan Mudasser Muneer Khan Zahid Mahmood Khan Tahir Sultan Bruce W. Melville 《Water Resources Management》2018,32(1):83-103
Considering network topologies and structures of the artificial neural network (ANN) used in the field of hydrology, one can categorize them into two different generic types: feedforward and feedback (recurrent) networks. Different types of feedforward and recurrent ANNs are available, but multilayer perceptron type of feedforward ANN is most commonly used in hydrology for the development of wavelet coupled neural network (WNN) models. This study is conducted to compare performance of the various wavelet based feedforward artificial neural network (ANN) models. The feedforward ANN types used in the study include the multilayer perceptron neural network (MLPNN), generalized feedforward neural network (GFFNN), radial basis function neural network (RBFNN), modular neural network (MNN) and neuro-fuzzy neural network (NFNN) models. The rainfall-runoff data of four catchments located in different hydro-climatic regions of the world is used in the study. The discrete wavelet transformation (DWT) is used in the present study to decompose input rainfall data using db8 wavelet function. A total of 220 models are developed in this study to evaluate the performance of various feedforward neural network models. Performance of the developed WNN models is compared with their counterpart simple models developed without applying wavelet transformation (WT). The results of the study are further compared with - multiple linear regression (MLR) model which suggest that the WNN models outperformed their counterpart simple models. The hybrid wavelet models developed using MLPNN, the GFFNN and the MNN models performed best among the six selected data driven models explored in the study. Moreover, performance of the three best models is found to be similar and thus the hybrid wavelet GFFNN and the MNN models can be considered as an alternative to the most commonly used hybrid WNN models developed using MLPNN. The study further reveals that the wavelet coupled models outperformed their counterpart simple models only with the parsimonious input vector. 相似文献
18.
针对半干旱地区次洪量预测问题,选取岔巴沟流域曹坪水文站1980-2010年中15场洪水资料,根据实测次暴雨、洪量资料,考虑淤地坝控制面积、次暴雨量、暴雨中心位置、前期影响雨量等因子,利用SPSS及MATLAB软件,建立用以预测次洪量的多元线性回归模型和BP神经网络模型。模型预测结果比较表明:多元线性回归模型和BP神经网络模型都能较好地应用于次洪量的预测,进一步得出BP神经网络模型的预测效果优于多元线性回归模型。研究结果可为淤地坝的安全度汛提供决策依据。 相似文献
19.
深基坑支护结构位移的神经网络预测 总被引:4,自引:1,他引:3
针对深基坑系统的复杂性和变形非线性,将人工神经网络技术引入其中。在分析讨论了人工神经网络中应用最为广泛的BP网络基本原理的基础上,建立了基坑变形预测的神经网络模型,并应用Bayesian方法对实例加以论证。研究表明,神经网络是解决基坑变形预测的有效方法之一。 相似文献
20.
River Flow Forecasting using Recurrent Neural Networks 总被引:4,自引:4,他引:0
Forecasting a hydrologic time series has been one of the most complicated tasks owing to the wide range of data, the uncertainties in the parameters influencing the time series and also due to the non availability of adequate data. Recently, Artificial Neural Networks (ANNs) have become quite popular in time series forecasting in various fields. This paper demonstrates the use of ANNs to forecast monthly river flows. Two different networks, namely the feed forward network and the recurrent neural network, have been chosen. The feed forward network is trained using the conventional back propagation algorithm with many improvements and the recurrent neural network is trained using the method of ordered partial derivatives. The selection of architecture and the training procedure for both the networks are presented. The selected ANN models were used to train and forecast the monthly flows of a river in India, with a catchment area of 5189 km2 up to the gauging site. The trained networks are used for both single step ahead and multiple step ahead forecasting. A comparative study of both networks indicates that the recurrent neural networks performed better than the feed forward networks. In addition, the size of the architecture and the training time required were less for the recurrent neural networks. The recurrent neural network gave better results for both single step ahead and multiple step ahead forecasting. Hence recurrent neural networks are recommended as a tool for river flow forecasting. 相似文献