首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 234 毫秒
1.
Song和Chisson于1993年提出模糊时间序列预测理论.虽然至今已经提出许多模糊时间序列预测模型,但是迄今为止尚未给出预测未知年数据的模糊时间序列预测模型.提出基于逆模糊数的模糊时间序列预测的新方法该模型对广西大学已知的2001~2012年的注册数进行预测分析,平均预报误差率比相关文献的方法有所改善.还对广西大学未知的2013年和2014年注册数进行预测研究.方法是短期预测的一种模糊时间序列预测方法.  相似文献   

2.
依据CPI经济序列数据确定性混沌原理,探讨自适应神经模糊推理系统模型构造,并给出此类混沌数据列预测的ANFIS系统结构形式,进行CPI经济序列数据预测.并用实例拟合、预测数据证明:ANFIS模型是一种精度较高的混沌数据序列预报系统.为CPI数据预测提供了一种计算方法.  相似文献   

3.
灰色时序组合模型及其在地下水埋深预测中的应用   总被引:1,自引:0,他引:1  
地下水埋深的变化过程是一个复杂的非线性过程,这种具有复杂的非线性组合特征的序列,使用某一种模型进行预测,结果往往不理想.在分析了灰色GM(1,1)模型、灰色GM(1,1)周期性修正模型和时序AR(n)模型的优点和缺点基础上,提出了一种新的灰色时序组合预报模型.该方法利用了GM预测所需原始数据少、方法简单的优点,用周期修正方法反映其地下水位埋深周期性波动的特征,用AR(n)模型预报其地下水位埋深的随机变化.实例研究表明,这种方法方便简洁实用且预测结果接近于实际观测值,为其它地区的地下水位埋深和相关时间序列的分析研究提供参考与借鉴作用.  相似文献   

4.
针对副热带高压的动力预报模型难以准确构建的困难,基于T106数值预报产品500hPa位势高度场序列,用经验正交函数(EOF)分解方法对位势场序列进行了时、空分解,引入了动力系统重构思想,以EOF分解的空间模态的时间系数序列作为动力模型变量,用遗传算法全局搜索和并行计算优势,进行了动力模型参数的优化反演,建立了客观合理的非线性动力模型.通过对动力模型积分和EOF的时、空重构,实现了副热带高压的中、长期预报.试验结果表明.本文反演的动力模型的副热带高压预报效果优于常规的数值预报产品,该研究工作为副热带高压等复杂天气系缔和萼索场预报提供了新的方法恩路和技术途径.  相似文献   

5.
介绍了组合预测的方法,并利用最优组合和递归方差倒数方法对组合预测方法进行改进;提出通过GMDH方法首先对影响经济预测模型的各变量进行筛选然后再建立回归模型、神经网络模型等单项预测模型的思想;最后结合GMDH方法建立的时间序列模型,建立正权重组合预测模型.  相似文献   

6.
准确预测一个地区未来的降水量,可以提高该地区防灾减灾的能力,更好地为工农业生产生活提供决策参考。本文以新疆1957年至2007年四季降水时间序列为研究对象,基于自动聚类区间划分方法建立模糊时间序列模型,并将该模型应用于新疆2008~2012年的四季降水预报。最后,从拟合精度和预测精度对预测结果进行分析。结果表明,基于模糊时间序列的降水预测模型具有较高预报精度,可用于新疆的季度降水预报。  相似文献   

7.
应用基于Box-Jenkins方法的时间序列分析技术,对青南高原的四个典型地区1961-2005年降水量序列进行ARMA建模分析:验证了四地区年降水量序列的时间序列特性,研究并选择了这些序列的最佳ARMA模型,本文也通过模型对未来降水量进行了预测.模型实证分析的结果表明:在青藏高原降水量时间序列分析建模与预测方面,Box-Jenkins方法及其模型是一种精度较高且切实有效的方法模型.  相似文献   

8.
时间序列分析是研究经济学和统计学的一种重要方法,通过分析实际的时间数据序列进行建立数学模型,用来预测序列的未来的发展情况。本文介绍了时间序列的发展概况和基本概念,论述了ARMA模型的自协方差函数、自相关系数、偏自相关函数的特征和Box-Jenkins建模。Box-Jenkins建模方法一般包括模型识别、参数估计、模型适用性检验和预测等步骤,该模型主要运用于单变量、同方差场合的线性模型。通过对模型的进一步研究,明确了模型的定阶与参数估计等问题。  相似文献   

9.
提出一种改进的基于逆模糊数的新模糊时间序列预测模型.应用模型研究辽宁省农机总动力预测问题,比一元线性回归模型,二次移动平均模型,指数曲线模型,灰色理论GM(1,1)模型等4种模型和它们的组合模型的平均预测误差率AFER都有较大改善,是值得推荐的一种时间序列预测方法.  相似文献   

10.
准确预测我国居民消费水平对促进经济持续协调发展具有重大的理论和现实意义。根据1952~2013年我国居民消费水平数据,本文提出了一种基于动态隶属度的模糊时间序列预测方法。首先对数据聚类并模糊化处理得到隶属度序列;然后再对隶属度序列进行时间序列分析建模得到预测值;紧接着对其去模糊化实现我国未来三年居民消费水平的预测;最后,将预测结果与传统时间序列方法预测结果相比较,新方法的预测平均绝对误差(MAE)、均方误根差(RMSE)较传统时间序列方法分别减少了23和28。结果表明,本文的预测方法相对于传统时间序列预测方法具有较高的预报精度,可用于居民消费水平的预测。  相似文献   

11.
We are going to report about methods and results of a study in which pupils of grades 10 and 11 of two grammar schools have been tested in individual examinations using problems of the QuaDiPF-test. The main focus of this investigation was to detect a correspondence between predicative versus functional explanations and patterns of typical eye-movements. While working on the test-problems, the eye-movements of the subjects were recorded. After having worked on a problem, the subjects were asked to explain their procedure and to given reasons for their results. When evaluating these explanations, they were classified according to characteristics of predicative or functional thinking. Moreover, an algorithm was developed that was used to analyse the recorded eye-movements. Both methods of classification of a predicative versus functional cognitive structure showed a very clear correspondence. This study is part of a research project about the importance of individual differences in the preference for predicative versus functional thinking and has been conducted for several years now at the Institute of Cognitive Mathematics. The results of this basic research are especially used to explain the pupils’ understanding of mathematical concepts and their problem solving behaviour in regular mathematics lessons.  相似文献   

12.
应用果蝇优化算法对径向基神经网络扩展参数的优化方法进行研究,给出了一种以标准误差计算公式为味道判定函数,以此确定最优的径向基函数的扩展参数值的方法,并建立了相应的预测模型.应用该预测模型对黑龙江省外贸出口额进行预测,结果表明:预测模型的预测精度优于径向基神经网络,从而证明了方法的有效性.  相似文献   

13.
Electricity load forecasting has become one of the most functioning tools in energy efficiency and load management and utility companies which has been made very complex due to deregulation. Due to the importance of providing a secure and economic electricty for the consumers, having a reliable and robust enough forecast engine in short‐term load management is very needful. Fuzzy inference system is one of primal branches of Artificial Intelligence techniques which has been widely used for different applications of decision making in complex systems. This paper aims to develop a Fuzzy inference system as a main forecast engine for Short term Load Forecasting (STLF) of a city in Iran. However, the optimization of this platform for this special case remains a basic problem. Hence, to address this issue, the Radial Movement Optimization (RMO) technique is proposed to optimize the whole Fuzzy platform. To support this idea, the accuracy of the proposed model is analyzed using MAPE index and an average error of 1.38% is obtained for the forecast load demand which represents the reliability of the proposed method. Finally, results achieved by this method, demonstrate that an adaptive two‐stage hybrid system consisting of Fuzzy & RMO can be an accurate and robust enough choice for STLF problems. © 2016 Wiley Periodicals, Inc. Complexity 21: 521–532, 2016  相似文献   

14.
灰色预测模型是中长期负荷预测的一种有效的方法,对E型规律发展的负荷有很好的拟合性,但对有转折点的S型增长趋势或增长处于饱和阶段的负荷进行预测误差较大。本文通过对历史数据的最优分段,提出了等维递补灰色校正模型,可以很好地解决这个问题。实例表明,此模型在中长期负荷预测中是适用的,尤其对于按S型曲线增长的情况,具有很高的预测精度。  相似文献   

15.
In this study, the problem of estimating the forecast accuracy of a model is considered. A widespread practice is to approximate the population expectation of the forecast accuracy by the sample expectation, which is equivalent to the uniform consideration for the deviations of the forecast from the exact value of a quantity for all time moments. If the vector of unknown parameters is estimated at each step only from the preceding observations, the significance of the deviations is not the same at all time moments. In this study, we propose a method that takes into account the forecast errors with different weights. The problem of constructing the most accurate estimate of the forecast quality, a parameter from which the condition for the optimal weights can be derived, is formalized. Monte-Carlo experiments are used to compare the accuracy of the methods for estimating the forecast quality in the cases when the observations are taken into account with the same weights, with optimum weights, and with the weights calculated using a numerical procedure.  相似文献   

16.
The multiperiod Bayesian forecast under the normal-gamma prior assumption for univariateAR models with strongly exogenous variables is investigated. A two-stage approximate method is proposed to provide an estimator of the posterior predictive density for any future observation in a convenient closed form. Some properties of the proposed method are proven analytically for a one-step ahead forecast. The precision of the proposed method is examined by using some simulated data and two sets of real data up to lead-twelve-ahead forecasts by comparison with a path sampling method. It is found that most of the results for the two discussed methods are rather close for short period forecast. Especially when sample size is sufficiently large, the estimated predictive density provided by the two-stage method asymptotically converges to the true density. A heuristic proof of this asymptotic property is also presented.  相似文献   

17.
非线性回归模型是中长期负荷预测的一种有效的方法,对常规变化趋势的负荷有很好的拟合性,但对有转折点的突变趋势或增长处于饱和阶段的负荷进行预测误差较大.通过对历史数据的最优分段,提出了非线性回归校正模型,可以很好地解决这个问题.实例表明,此模型在中长期负荷预测中是适用的,尤其对于有转折点的突变趋势,具有很高的预测精度.  相似文献   

18.
This paper deals with the development of a numerical method to study the non-linear wave-wave interactions in oceans. Based on works from Webb-Tracy-Resio, the Hasselmann’s non-linear mathematical model is reviewed numerically. With this theory and the selection of action density domain, a program to reduce time of computation has been developed. Results from new computation are displayed graphically and compared with previous program. This work augments our understanding better about the non-linear process of wave-wave interactions and it improves the numerical computations to obtain efficiency in operational forecast.  相似文献   

19.
In this paper, we consider a mathematical model which describes the dynamic contact between an elastic body and an obstacle. The process is assumed to be dynamic and the contact is modeled with the normal compliance. We present a variational formulation of the problem and prove the existence and the uniqueness of a weak solution. An efficient numerical method is presented to analyze this dynamic contact. This approach exploits the augmented Lagrangian concept and a special time integration algorithm. This is exploited to study the dynamic contact between the rotor and the stator inside an ultrasonic motor SHINSEI USR 60. Numerical results are presented and show the interest of this method to forecast the origin of the principal failure mode of this motor.  相似文献   

20.
阳妮 《数理统计与管理》2007,26(6):1012-1018
在产品质量判定的抽样检验问题中,当目标指标需用破坏性试验才能得其值时,更为常用的是用非破坏性试验可得量值的协变指标量来预报它。但在产品抽样验收问题上,未能形成理论较为严密的方法,这是由于预报误差这个关键问题的处理尚未解决得好,即给不出抽样方案的功效计算的正确或是近似性较好的公式。本文通过建立合理的数学模型,把对目标指标的质量要求化为对协变指标量的统计要求,从而利用两者的回归关系,结合两种复杂的抽样方案,给出功效函数的计算公式和计算方法,并进行了分析。  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号