MATLAB在运用系统建模处理南海气象数据过程中应用

介绍了MATLAB语言特点和系统建模方法的基本理论.根据南海气象数据的实际建模处理过程,给出了建模的详细步骤及其MATLAB实现过程以及MATLABTM的主要实现程序.试验讨论和结果表明利用MATLAB语言可以方便地对南海气象数据用系统建模方法进行建模和处理,MATLAB在运用系统建模法处理南海气象数据方面具有明显的优越性.     

随机地震动模拟的时间序列法及其工程应用

系统研究了AR和ARMA时间序列方法生成给定加速度功率谱人工地震波的新方法，根据相应理论编制了程序，并生成了人工地震加速时程曲线，然后用生成的人工地震波进行结构动力时程分析，与实际地震波分析的结果进行了对比，计算结果表明，本文用于合成人工地震波的方法是可行的，生成的人工波可以用于实际结构的地震反应分析。     

A model for the Am (Km) planetary geomagnetic activity index and application to prediction

We studied the existence of dynamical stochastic relations in the evolution of the am index. A first analysis of the autocorrelation functions showed evidence of several seasonalities. We first used linear (ARMA) models, and it was found that these do not account for the whole internal dynamics of the data series. We then used various non-linear models to provide a better fit to reality. The forecast performances of the non-linear models are not significantly different from those of the linear model. We give a tentative explanation for the failure of the non-linear predictions. Finally, ARCH models were used in order to take into account the fact that the confidence interval for the predicted value depends on past observations.     

运用改进系统建模法对南海气象数据的建模研究

在系统建模理论的基础上,运用改进的动态数据建模方法,对南海气象数据中的温度进行建模并验证了模型的适用性.根据模型推导出格林函数、逆函数和自协方差函数等,并讨论了南海气象数据中温度模型的稳定性、可逆性和合理性.对系统的频率特性和谱函数进行分析讨论,并给出建模过程中的一些图像.根据模型的适用性检验发现,对所研究的气象数据而言,ARMA(4, 3)模型是最合适的,具有平稳可逆性.所有的建模和分析过程在MATLAB上实现.实验结果表明这种建模方案简便易行,能够快速准确地确定系统的合理模型.     

基于脉冲响应数据的ARMA法建模以及模态参数识别

本文提出了基于脉冲响应数据的ARMA法建模以及模态参数识别的新方法。该方法利用单位脉冲响应函数与ARMA模型G reen函数等价的特点,通过脉冲响应函数来估计系统响应的自相关系数,然后建立推广的Yu le-W alker方程以求得ARMA模型自回归系数并进行参数识别。最后通过算例,对一个模拟系统进行了参数识别,对采样频率、识别精度、模型阶数之间的影响规律进行了分析。     

一种基于熵权法的小波去噪复合评价指标

传统的评价指标在真值未知的情况下不能满足小波去噪质量评价的要求。为此,借助变化率特征重新构建均方根误差变化量和平滑度变化量两个指标,利用熵权法定权将归一化后的两个指标线性组合,所得到的新指标即为复合评价指标。该方法借助指标的变化率随分解层数的增加表现出明显的收敛特性来确定去噪最优分解层数。实验表明,该方法能够在真值未知的情况下准确地指导小波分解,确定去噪最优分解层数,从而达到最优去噪效果。     

基于噪声随机模型的加权观测融合方法

信息融合技术中,在各局部传感器的有色观测噪声为一阶AR模型的情况下,可以利用观测扩增方法消除有色噪声的影响,得到最优加权观测融合方程,从而实现状态的最优滤波解。对于有色观测噪声为MA或ARMA模型的情况,观测扩增方法不再适用。提出了基于有色观测噪声随机模型级数展开的方法,求解出各局部传感器有色观测噪声的方差,并利用该方差对加权观测融合滤波器进行了构造。通过计算实例证明,该方法不仅适用于观测噪声为AR模型,同时适用于噪声MA或ARMA模型。     

Modeling long term lake variations by physically based stochastic dynamic models

Several physically based stochastic dynamic models (SDM) are described including year-to-year variations of water volume in terminal and non-terminal lakes, streamflow of lake-fed rivers, and salinity of an inland sea (the Sea of Azov). All of these models are based upon the SDM of water volume of terminal lakes developed by Kritzky and Menkel in 1946 in co-operation with Kolomogorov. Explicit formulae are derived for second order statistical moments of the output processes, including variance, correlation function, spectra, etc., under the assumption that the forcing functions from stationary random sequences. The least-squares prediction problem is solved for both stationary and non-stationary cases. Some of the processes are shown to possess high statistical predictability. Actual predictions are compared with independent observations. Problems for further study are stated.     

时序分析在危岩体监测数据处理中的应用

引入时间序列分析进行危岩体监测数据的处理，建立了危岩体变形的动态模型，取得了较好的拟会与预报精度。     

Exploratory spectral analysis of hydrological times series

Current methods of estimation of the univariate spectral density are reviewed and some improvements are made. It is suggested that spectral analysis may perhaps be best thought of as another exploratory data analysis (EDA) tool which complements, rather than competes with, the popular ARMA model building approach. A new diagnostic check for ARMA model adequacy based on the nonparametric spectral density is introduced. Additionally, two new algorithms for fast computation of the autoregressive spectral density function are presented. For improving interpretation of results, a new style of plotting the spectral density function is suggested. Exploratory spectral analyses of a number of hydrological time series are performed and some interesting periodicities are suggested for further investigation. The application of spectral analysis to determine the possible existence of long memory in natural time series is discussed with respect to long riverflow, treering and mud varve series. Moreover, a comparison of the estimated spectral densities suggests the ARMA models fitted previously to these datasets adequately describe the low frequency component. Finally, the software and data used in this paper are available by anonymous ftp from fisher.stats.uwo.ca.