A Study of Wind Statistics Through Auto-Regressive and Moving-Average (ARMA) Modeling

Statistical properties of winds near the Taichung Harbour are investigated. The 26 years'incomplete data of wind speeds, measured on an hourly basis, are used as reference. The possibility of imputation using simulated results of the Auto-Regressive (AR), Moving-Average (MA), and/ or Auto-Regressive and Moving-Average (ARMA) models is studied. Predictions of the 25-year extreme wind speeds based upon the augmented data are compared with the original series. Based upon the results, predictions of the 50- and 100-year extreme wind speeds are then made.

Application of Seasonal Auto-regressive Integrated Moving Average Model in Forecasting the Incidence of Hand-foot-mouth Disease in Wuhan,China

Outbreaks of hand-foot-mouth disease（HFMD） have occurred many times and caused serious health burden in China since 2008. Application of modern information technology to prediction and early response can be helpful for efficient HFMD prevention and control. A seasonal auto-regressive integrated moving average（ARIMA） model for time series analysis was designed in this study. Eighty-four-month（from January 2009 to December 2015） retrospective data obtained from the Chinese Information System for Disease Prevention and Control were subjected to ARIMA modeling. The coefficient of determination（R^2）, normalized Bayesian Information Criterion（BIC） and Q-test P value were used to evaluate the goodness-of-fit of constructed models. Subsequently, the best-fitted ARIMA model was applied to predict the expected incidence of HFMD from January 2016 to December 2016. The best-fitted seasonal ARIMA model was identified as（1,0,1）（0,1,1）12, with the largest coefficient of determination（R^2=0.743） and lowest normalized BIC（BIC=3.645） value. The residuals of the model also showed non-significant autocorrelations（P_（Box-Ljung（Q））=0.299）. The predictions by the optimum ARIMA model adequately captured the pattern in the data and exhibited two peaks of activity over the forecast interval, including a major peak during April to June, and again a light peak for September to November. The ARIMA model proposed in this study can forecast HFMD incidence trend effectively, which could provide useful support for future HFMD prevention and control in the study area. Besides, further observations should be added continually into the modeling data set, and parameters of the models should be adjusted accordingly.

CONSTRUCTION OF POLYNOMIAL MATRIX USING BLOCK COEFFICIENT MATRIX REPRESENTATION AUTO-REGRESSIVE MOVING AVERAGE MODEL FOR ACTIVELY CONTROLLED STRUCTURES

The polynomial matrix using the block coefficient matrix representation auto-regressive moving average(referred to as the PM-ARMA)model is constructed in this paper for actively controlled multi-degree-of-freedom(MDOF)structures with time-delay through equivalently transforming the preliminary state space realization into the new state space realization.The PM-ARMA model is a more general formulation with respect to the polynomial using the coefficient representation auto-regressive moving average(ARMA)model due to its capability to cope with actively controlled structures with any given structural degrees of freedom and any chosen number of sensors and actuators.(The sensors and actuators are required to maintain the identical number.)under any dimensional stationary stochastic excitation.

Forecasting risk using auto regressive integrated moving average approach: an evidence from S&P BSE Sensex

The primary objective of the paper is to forecast the beta values of companies listed on Sensex,Bombay Stock Exchange(BSE).The BSE Sensex constitutes 30 top most companies listed which are popularly known as blue-chip companies.To reach out the predefined objectives of the research,Auto Regressive Integrated Moving Average method is used to forecast the future risk and returns for 10 years of historical data from April 2007 to March 2017.Validation accomplished by comparison of forecasted and actual beta values for the hold back period of 2 years.Root-Mean-Square-Error and Mean-Absolute-Error both are used for accuracy measurement.The results revealed that out of 30 listed companies in the BSE Sensex,10 companies’exhibits high beta values,12 companies are with moderate and 8 companies are with low beta values.Further,it is to note that Housing Development Finance Corporation(HDFC)exhibits more inconsistency in terms of beta values though the average beta value is lowest among the companies under the study.A mixed trend is found in forecasted beta values of the BSE Sensex.In this analysis,all the p-values are less than the F-stat values except the case of Tata Steel and Wipro.Therefore,the null hypotheses were rejected leaving Tata Steel and Wipro.The values of actual and forecasted values are showing the almost same results with low error percentage.Therefore,it is concluded from the study that the estimation ARIMA could be acceptable,and forecasted beta values are accurate.So far,there are many studies on ARIMA model to forecast the returns of the stocks based on their historical data.But,hardly there are very few studies which attempt to forecast the returns on the basis of their beta values.Certainly,the attempt so made is a novel approach which has linked risk directly with return.On the basis of the present study,authors try to through light on investment decisions by linking it with beta values of respective stocks.Further,the outcomes of the present study undoubtedly useful to academicians,researchers,and policy makers in their respective area of studies.

Cyclic moving average control approach to cylinder pressure and its experimental validation

Cyclic variability is a factor adversely affecting engine performance. In this paper a cyclic moving average regulation approach to cylinder pressure at top dead center （TDC） is proposed, where the ignition time is adopted as the control input. The dynamics from ignition time to the moving average index is described by ARMA model. With this model, a one-step ahead prediction-based minimum variance controller （MVC） is developed for regulation. The performance of the proposed controller is illustrated by experiments with a commercial car engine and experimental results show that the controller has a reliable effect on index regulation when the engine works under different fuel injection strategies, load changing and throttle opening disturbance.

Parameter Estimation of Time-Varying ARMA Model

The auto-regressive moving-average (ARMA) model with time-varying parameters is analyzed. The time-varying parameters are assumed to be a linear combination of a set of basis time-varying functions, and the feedback linear estimation algorithm is used to estimate the time-varying parameters of the ARMA model. This algorithm includes 2 linear least squares estimations and a linear filter. The influence of the order of basis time-(varying) functions on parameters estimation is analyzed. The method has the advantage of simple, saving computation time and storage space. Theoretical analysis and experimental results show the validity of this method.

ARMA-GM combined forewarning model for the quality control

Three forecasting models are set up: the auto\|regressive moving average model, the grey forecasting model for the rate of qualified products P t, and the grey forecasting model for time intervals of the quality catastrophes. Then a combined forewarning system for the quality of products is established, which contains three models, judgment rules and forewarning state illustration. Finally with an example of the practical production, this modeling system is proved fairly effective.

Online Fault Prediction Based on Combined AOSVR and ARMA Models

Accurate fault prediction can obviously reduce cost and decrease the probability of accidents so as to improve the performance of the system testing and maintenance. Traditional fault prediction methods are always offline that are not suitable for online and real-time processing. For the complicated nonlinear and non-stationary time series, it is hard to achieve exact predicting result with single models such as support vector regression （SVR）, artifieial neural network （ANN）, and autoregressive moving average （ARMA）. Combined with the accurate online support vector regression （AOSVR） algorithm and ARMA model, a new online approach is presented to forecast fault with time series prediction. The fault trend feature can be extracted by the AOSVR with global kernel for general fault modes. Moreover, its prediction residual that represents the local high-frequency components is synchronously revised and compensated by the sliding time window ARMA model. Fault prediction with combined AOSVR and ARMA can be realized better than with the single one. Experiments on Tennessee Eastman process fault data show the new method is practical and effective.

基于ARMA模型的隧道变形预测及参数估计分析

以北京市海淀区某地铁站一体化棚户区改造项目为例,运用ARMA模型对高层建筑盖挖逆作法施工过程中邻近既有地铁隧道变形进行预测。以既有地铁隧道沉降实时监测数据为原始数据集,对原始数据集进行适当插补处理后,通过极大似然估计法对模型进行参数估计,给出了模型关键参数,构建了合理的预测模型。将模型预测结果与实测数据进行对比,显示预测结果与实测数据变化趋势高度吻合,充分验证了预测模型的可行性、有效性与稳定性。

基于改进灰色ARMA模型的卫星钟差短期预报研究

导航卫星钟差的精度直接影响导航定位性能。针对卫星钟差由趋势项和随机项组成的特点,提出一种改进灰色模型和ARMA模型的钟差预报组合模型。对传统灰色模型进行改进并建立趋势项预报模型,提取钟差随机项建立ARMA模型,最后将预报结果相加。在算例中采用IGS提供的精密钟差进行预报,仿真结果表明钟差精度较高。

基于类噪声信号和ARMA-P方法的振荡模态辨识

弱阻尼低频振荡是影响互联电网安全稳定运行的主要因素,振荡模态是表征系统振荡特性的重要参数,反映了各节点对振荡模式的参与情况。目前基于测量信号一般在振荡发生后进行模态分析,缺乏在系统正常运行情况下的分析手段。大量广域实测数据表明,因负荷的随机变化,电网内持续存在类似噪声信号的小幅波动。文中提出一种自回归滑动平均-Prony(ARMA-P)方法对这种类噪声信号进行处理,在采用ARMA模型拟合类噪声信号估计低频振荡模式参数的基础上,进一步建立信号的Prony模型,最终实现对低频振荡模态的辨识。将该方法用于对新英格兰系统仿真数据进行处理,其辨识结果与小干扰稳定计算结果进行了比较,并进一步将该方法用于处理南方电网实测数据,证明了其有效性。

基于ARMA预测模型的交叉口车辆碰撞风险评估

车辆进入交叉口前的速度时间序列可用于预测车辆进入交叉口后若干步数速度值,利用车速预测值推算冲突方向车辆在交叉口内的行驶位移及其车间距离,可评估车辆发生碰撞的风险.针对交叉口附近车速分布符合随机序列特征,采用自回归滑动平均(ARMA)理论进行车速时序预测建模,步骤包括时序数据相关性检查、模型p-q定阶、解析式系数估计、适用性检验.试验结果表明:利用实测车速中的前40个时序数据建立ARMA模型,预测出的20个车速值与实测值贴近,冲突方向两车车速归一化平均绝对误差分别为0.006 56和0.003 4;利用全部60个实测数据建立预测模型,检测预测值残差自相关函数发现其绝对值均小于0.258 2,表明所建车速预测方法适用.

基于ARMA模型模拟高架桥的脉动风速时程

强风是高架桥设计与防灾减灾分析的控制性荷载之一。风与高架桥相互作用十分复杂,可以通过风洞试验、现场实测、数值模拟获取可靠的风速(风荷载)数据。尽管如此,时域分析可以使人们更全面地了解高架桥的风振响应特性,也能更直观地反映高架桥风致振动控制的有效性。因此,使用线性滤波法即白噪声滤波法(WNFM)中的自回归滑动平均(ARMA)模型模拟高架桥的脉动风速时程。首先,考虑高架桥脉动风速的时间和空间相关性,导出自回归(AR)模型阶数与滑动回归(MA)模型阶数不相等时ARMA模型的表达式。接着,基于Kaimal风速谱,使用ARMA模型来模拟一座实际高架桥的脉动风速时程。最后,通过比较模拟风速功率谱、自相关和互相关函数与目标风速功率谱、自相关和互相关函数的吻合程度,验证基于ARMA模型模拟高架桥脉动风速时程的可行性。

基于Mallat算法与ARMA模型的露天矿卡车故障率预测

为提高露天矿山运输卡车故障率预测精度、降低因非平稳时间序列数据造成的精度损失及有效解决模型参数估计困难等问题,提出一种基于小波分析与自回归滑动平均模型(ARMA)的露天矿山卡车故障率预测方法。首先,根据矿山时间序列数据的非平稳特征,采用Mallat算法分频处理原始数据,将原始的时间序列分解为一组近似系数和多组细节系数;然后,采用ARMA模型拟合与预测单支重构后的小波系数;其次,引入模型的相关变量,将ARMA模型的参数估计问题转化为带有相关变量的多维高斯分布参数估计问题;最后,通过计算模型中的典型相关变量实现ARMA模型的定阶与参数估计并与其他算法模型进行对比。结果表明:采用此法预测测试集数据,绝对误差的平均值为0. 322,相对误差的平均值为5. 49%;这说明此种组合模型具有更高的拟合精度,应用该模型进行卡车故障率预测是可行且有效的。

基于ARMA模型的心电聚类算法

对心电信号(ECG)这种高维的时间序列进行聚类,最重要的方面之一即进行特征提取。本研究提出利用自回归和移动平均(ARMA)模型拟合ECG信号,以拟合系数的欧氏距离为结构不相似测度征进行聚类。但此方法没有考虑样本数据的各维特征对聚类的不同贡献率,所以本文提出可以把首次聚类每维特征在聚类中的贡献率作为其权值,对每维数据加权后重新进行聚类。以MIT-BIH标准数据库中的正常窦性心率(NSR)和心室早期收缩(PVC)样本数据进行聚类分析,结果表明利用改进后的方法进行聚类的准确度达到93.10%,从而证明了所提方法的有效性。

基于小波变换和GM-ARMA的导弹备件消耗预测

针对导弹备件消耗呈现"小样本、非平稳"的特点,为了克服传统预测方法依靠大样本数据进行建模的不足,提出了把基于小波变换和改进GM-ARMA的组合预测方法应用于导弹备件消耗预测的构想.在利用小波分解和其他模型建立组合模型的过程中,提出了先对小波基方程和分解层数2个特征进行参数化,再定量地对所有子模型的特征参数进行统一、综合的评估,以达到建立最佳组合模型的目的;然后对具有平稳特性的高频信息用阻尼最小二乘法优化的ARMA(Autoregressive and Moving Average)模型进行预测,对反映整体趋势体现非平稳的低频信息用背景值优化和数据变换技术改进的GM(1,1)模型进行预测.实例结果表明所提出的组合预测方法大大降低了预测误差,说明了该方法的有效性、可行性和实用性.

基于ARMA误差修正和自适应粒子群优化的SVM短期负荷预测

利用最小二乘支持向量机(LS-SVM)进行短期负荷预测的精度及其泛化性能很大程度上取决于其参数选择。对于支持向量机中的核参数σ和惩罚系数C采用基于适应度函数惯性权重自适应调整的粒子群优化算法进行选择。在对LS-SVM回归模型参数优化的基础上,建立自回归滑动平均(ARMA)误差预测模型来修正负荷预测结果从而提高预测精度。选择某地区夏季96点负荷数据作为训练样本和测试样本进行分析,并且选择SVM模型进行对比。实验结果表明,同标准的SVM回归模型相比,APSO-ARMA-SVM负荷预测模型能明显改善预测精度,能够推广到电价预测等其他预测领域。

生成粉红噪声的ARMA模型

针对现有粉红噪声的生成方法所存在的计算过程复杂,与理想粉红噪声相比偏差较大等问题,本文提出了一种利用自回归滑动平均(Auto-regressive moving average,ARMA)模型法生成粉红噪声的新方法。首先,构造一个待定系数的ARMA模型,并通过Z变换和功率谱估计的公式进行推导;其次,利用已知的粉红噪声模拟滤波器的传递函数H(s)和双线性Z变换法推导出IIR数字滤波器的传递函数H(z),进而得到粉红噪声的ARMA模型;最后,利用MATLAB对生成的粉红噪声进行功率谱估计并与理想的粉红噪声进行对比。由MATLAB仿真结果可知,利用该方法生成的粉红噪声与理想的粉红噪声拟合度更高,完全符合粉红噪声的各项性能要求。

一种改进的ARMA模型参数估计方法

针对自回归滑动平均(auto-regressive moving average,简称ARMA)模型参数谱估计容易出现谱峰漂移问题,提出一种基于组合目标函数和遗传算法的ARMA模型参数估计方法。通过最小均方误差准则获得ARMA模型参数初始估计,依据现代谱估计理论和连续函数极值存在的必要条件推导模型参数的频域约束方程,构造组合目标函数并采用遗传算法对模型参数初始估计值进行优化获得模型参数的最优解。将该方法用于车削状态下尾顶尖垂直方向振动加速度时间序列建模和谱估计,结果表明了方法的有效性。

基于ARMAV模型的国内海洋捕捞与海水养殖产量的分析

为了揭示国内海洋捕捞和海水养殖产量的相关关系,准确地跟踪并预测海洋捕捞和海水养殖产量的短期未来趋势,利用时序分析方法对1954—2006年国内海洋捕捞和海水养殖产量数据建立了多维自回归滑动平均(ARMAV)模型。该方法不仅避免了分别使用自回归滑动平均(ARMA)模型对两序列建模未考虑序列间关系的弊端,还通过数据的先期平稳化处理而使得算法的运用更具有针对性。图像与误差计算结果均表明,用本研究中给出的ARMAV(2,1,2)算法对两序列进行跟踪及预测具有效性。