共查询到20条相似文献,搜索用时 245 毫秒
1.
2.
3.
《浙江大学学报(A卷英文版)》2016,(2)
目的:相对于由能量平衡方程得到的数值预报模型和以神经网络为代表的非线性模型而言,自回归(AR)模型在波浪预报中具有计算效率高、自适应性强和建模所需的样本小等优点,但同时存在局限于平稳线性假设的缺陷。针对非线性非平稳波浪的极短期预报问题,提出一种复合的经验模态分解自回归预报模型,提高波浪预报精度。创新点:1.研究非线性非平稳波浪极短期预报问题,提出一种复合的预报方法;2.基于三个不同地理位置的海洋波浪实测数据对预测模型进行验证,并分析非线性非平稳性对波浪预报结果的影响。方法:1.在AR模型中引入经验模态分解(EMD)方法,形成复合的EMD-AR预报模型;2.分析实测波浪数据的非线性和非平稳性特点,并基于实测波浪数据获得AR模型和EMD-AR模型的预报结果;3.基于多种预报误差度量分析AR模型和EMD-AR模型的预报性能以及非线性非平稳性对波浪预报结果的影响。结论:1.波浪非线性和非平稳性会导致AR预报模型精度降低。预报误差中,幅值上的偏差主要由波浪的非线性引起,而相位上的偏差则是源于波浪的非平稳性;2.EMD方法能够有效地克服波浪非线性和非平稳性对AR模型在精度上所带来的不良影响,在精度上EMD-AR模型的预报结果较AR模型有较大提高。 相似文献
4.
5.
本文把人工神经网络方法应用于径流预报,建立了入库水量分级预报的神经网络模型,其有效性在实例中得到了验证. 相似文献
6.
为了提高灰色GM(1,1)模型在城市用水量预测中的精度,结合BP神经网络的优点,给出了两种灰色-神经网络组合模型GM-BP1和GM-BP2.模型1利用神经网络对GM(1,1)模型的误差序列进行回归训练,将得到的预测值作为原始误差的修正来减小误差;而模型2由部分数据建立了GM(1,1)模型组,通过神经网络训练得到部分数据GM(1,1)模型组与真实值之间的非线性映射关系,利用这种精准的映射关系来提高预测精度.最后实际算例表明了所给方法是有效的,该组合模型可用于城市用水量的中长期预测. 相似文献
7.
本文把人工神经网络方法应用于径流预报,建立了入库水量分级预报的神经网络模型,其有效性在实例中得到了验证。 相似文献
8.
针对粒子群算法易陷入局部最优和寻优精度比较低等缺点,提出一种基于随机惯性权重和异步变化策略的学习因子的粒子群算法优化神经网络连接权重和阈值,并以此建立月降水预报建模研究.以广西桂北地区的月降水量实例分析,并与标准粒子群优化神经网络模型、随机权重的粒子群神经网络模型和神经网络模型对比,结果表明,该方法学习能力强和预测精度高,是一种有效的建模预报方法. 相似文献
9.
改进的灰色GM(1,N)模型在经济中的预测与应用 总被引:1,自引:0,他引:1
论文就修正GM(1,N)预测模型的误差,提出了新方法.使用BP神经网络对预测模型的残差进行预测,得到的残差预测值对所建模型的预测值进行残差修正,以减少因子变量预测误差对行为变量预测的影响.实践表明这些改进模型可以有效地提高GM(1,N)模型的预测精度. 相似文献
10.
提出了主成分分析(PCA)和局部线性嵌入降维方法(LLE)组合的优化RBF神经网络降水预测模型,首先利用主成分分析(PCA)和局部线性嵌入降维方法(LLE)组合对众多气象物理因子降维提取有效因子,再将这些综合有效因子组成的特征空间矩阵作为优化的RBF神经网络的输入矩阵,从而建立网络模型.以此对广西5月三个不同区域平均日降水量进行预报实验,结果表明,该模型具有较好的收敛效果和泛化能力,在预报性能上明显优于同期的T213降水预报、PCA预报、LLE预报,预报稳定性好,预报准确率较高,具有一定的普遍适用性. 相似文献
11.
Artificial neural network modeling of water quality of the Yangtze River system: a case study in reaches crossing the city of Chongqing 总被引:2,自引:0,他引:2
An effective approach for describing complicated water quality processes is very important for river water quality management. We built two artificial neural network (ANN) models, a feed-forward back-propagation (BP) model and a radial basis function (RBF) model, to simulate the water quality of the Yangtze and Jialing Rivers in reaches crossing the city of Chongqing, P. R. China. Our models used the historical monitoring data of biological oxygen demand, dissolved oxygen, ammonia, oil and volatile phenolic compounds. Comparison with the one-dimensional traditional water quality model suggest that both BP and RBF models are superior; their higher accuracy and better goodness-of-fit indicate that the ANN calculation of water quality agrees better with measurement. It is demonstrated that ANN modeling can be a tool for estimating the water quality of the Yangtze River. Of the two ANN models, the RBF model calculates with a smaller mean error, but a larger root mean square error. More effort to identify out the causes of these differences would help optimize the structures of neural network water-quality models. 相似文献
12.
A one-dimensional BOD-DO coupling model for water quality simulation is presented,which adopts Streeter-Phelps equations and the theory of back-propagation artificial neural network.The water quality data of Yangtze River in the Chongqing region in the year of 1989 are divided into 5 groups and used in the learning and testing courses of this model.The result shows that such model is feasible for water quality simulation and is more accurate than traditional models. 相似文献
13.
WANG Rui-min CAO Guang-yi ZHU Xin-jian 《浙江大学学报(A卷英文版)》2007,8(5):741-747
Model and simulation are good tools for design optimization of fuel cell systems. This paper proposes a new hybrid model of proton exchange membrane fuel cell (PEMFC). The hybrid model includes physical component and black-box com-ponent. The physical component represents the well-known part of PEMFC, while artificial neural network (ANN) component estimates the poorly known part of PEMFC. The ANN model can compensate the performance of the physical model. This hybrid model is implemented on Matlab/Simulink software. The hybrid model shows better accuracy than that of the physical model and ANN model. Simulation results suggest that the hybrid model can be used as a suitable and accurate model for PEMFC. 相似文献
14.
15.
A comparison of conventional linear regression methods and neural networks for forecasting educational spending 总被引:1,自引:0,他引:1
This study presents an application of neural network methods for forecasting per pupil expenditures in public elementary and secondary schools in the United States. Using annual historical data from 1959 through 1990, forecasts were prepared for the period from 1991 through 1995. Forecasting models included the multivariate regression model developed by the National Center for Education Statistics for their annual Projections of Education Statistics Series, and three neural architectures: (1) recurrent backpropagation; (2) Generalized Regression; and (3) Group Method of Data Handling. Forecasts were compared for accuracy against actual values for educational spending for the period. Regarding prediction accuracy, neural network results ranged from comparable to superior with respect to the NCES model. Contrary to expectations, the most successful neural network procedure yielded its results with an even simpler linear form than the NCES model. The findings suggest the potential value of neural algorithms for strengthening econometric models as well as producing accurate forecasts. [JEL C45, C53, I21] 相似文献
16.
17.
18.
BP算法是人工神经网络研究的一个常用方法,但从本质上说是属于局部寻优法,容易陷入局部极小点,且存在着学习速度与精度之间的矛盾;遗传算法是一种全局优化算法,具有并行计算能力.本文采用遗传算法来训练前向神经网络,建立一个基于遗传算法和BP算法的神经网络预测模型.试验结果表明它是一个成功较高的预测模型. 相似文献
19.
1 Introduction Inrecentyears,manynewpowerswitchingsemiconductorshaveemergedduetotherapiddevelopmentofpowerelectronics.Itisnotstrangethatthemodelofanewlydevelopeddevicecannotbefoundinthelibraryofacircuitsimulator.Theusershavetoestablishthesimulationmode… 相似文献
20.
为了提高大坝变形分析模型的预测精度并检验模型的泛化能力,研究了大坝变形分析的BP神经网络模型,并基于神经网络BP算法和传统的统计模型建立了大坝变形分析的融合模型.结合陈村大坝多年的变形观测数据,对上述3种模型进行了试算及分析.分析结果表明,统计模型的平均预测精度为±0.477mm.BP神经网络模型的平均预测精度为±0.390mm,融合模型的平均预测精度为±0.318mm,相比统计模型和BP神经网络模型分别提高了33%和18%,且泛化能力较强,具有广泛的适用性. 相似文献