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.

Optimal zero-crossing group selection method of the absolute gravimeter based on improved auto-regressive moving average model

An absolute gravimeter is a precision instrument for measuring gravitational acceleration, which plays an important role in earthquake monitoring, crustal deformation, national defense construction, etc. The frequency of laser interference fringes of an absolute gravimeter gradually increases with the fall time. Data are sparse in the early stage and dense in the late stage. The fitting accuracy of gravitational acceleration will be affected by least-squares fitting according to the fixed number of zero-crossing groups. In response to this problem, a method based on Fourier series fitting is proposed in this paper to calculate the zero-crossing point. The whole falling process is divided into five frequency bands using the Hilbert transformation. The multiplicative auto-regressive moving average model is then trained according to the number of optimal zero-crossing groups obtained by the honey badger algorithm. Through this model, the number of optimal zero-crossing groups determined in each segment is predicted by the least-squares fitting. The mean value of gravitational acceleration in each segment is then obtained. The method can improve the accuracy of gravitational measurement by more than 25% compared to the fixed zero-crossing groups method. It provides a new way to improve the measuring accuracy of an absolute gravimeter.

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.

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。

用对称映射ARMA模型的零极点研究子波相位对反射系数序列反演的影响

为研究地震子波相位对反射系数序列反演的影响,在自回归滑动平均(ARMA)模型描述子波的基础上,提出采用z域对称映射ARMA模型零极点的方法构造了一系列相同振幅谱、不同相位谱的地震子波,并结合谱除法对人工合成地震记录进行反射系数序列反演.理论分析表明,子波相位估计不准时反射系数序列反演结果中残留一个纯相位滤波器,该纯相位滤波器的相位谱为真实子波和构造子波的相位谱之差.采用丰度和变分作为评价方法,在反演结果中确定出真实的或准确的反射系数序列.仿真实验和实际数据处理结果也验证了子波相位对反射系数序列反演的影响规律和评价方法的有效性,为进一步提高反射系数序列反演结果精度指明了研究方向.

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。

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。

设备故障评估新指标及基于ARMA的预测系统

设备故障停机时间受生产调度的影响较大,不能真实反映设备的自身性能,且具有很强的随机性和波动性,不适于直接用来进行自回归移动平均(auto-regressive moving average,ARMA)建模。针对此问题,提出一种设备故障评估指标——设备不可用度,将设备故障停机时间转换为设备不可用度,通过异常点替代和数据平稳化等两种数据预处理,建立零均值平稳随机序列进行ARMA建模,并把预测结果转换为设备在一定时间内的故障发生概率。在某半导体芯片封装测试工厂的试验结果表明该方法能以70%的精度预测设备状态,在一个班(12 h)里设备不可用度平均降低2.62%,设备故障停机时间平均减少14.8 min。

基于AR和ARMA模型的多变量非高斯风压模拟

基于多变量非高斯随机过程间的相关性,将发展的单变量非高斯过程自回归和自回归滑动平均(AR和ARMA)模型模拟算法扩展至多变量非高斯过程的数值模拟。通过AR和ARMA模型系数考虑多变量非高斯过程间的相关性,建立多变量非高斯过程AR和ARMA模型的模拟算法。多变量非高斯风压的数值模拟表明:AR和ARMA模型算法能有效地模拟低斜度、中斜度和高斜度的多变量非高斯随机过程。

带有色公共干扰噪声的ARMA模型多传感器信息融合系统辨识

针对带未知参数的有色公共干扰噪声的自回归滑动平均(ARMA)模型,专门提出一种多段辨识算法:首先用递推辅助变量法获得自回归参数的局部估值,并采用平均局部的方法得到融合估值,再用带死区的GeversWouters算法和求解线性方程组得到滑动平均参数和噪声方差的局部和平均融合估值,并证明估值结果以概率1收敛于真实值。通过Matlab仿真显示单传感器得到的辨识结果均收敛于真实值,并且综合多个传感器的信息可以得到更为精确的结果。

融合HOG与ARMA模型的粒子滤波跟踪

传统的粒子滤波算法在跟踪目标受到相似背景干扰和遮挡或跟踪目标高速运动时,容易造成跟踪误差增大或跟踪失效的影响。针对室外运动目标跟踪的复杂性,提出一种对于干扰适应性较强的融合梯度方向直方图与自回归移动平均(ARMA)模型的粒子滤波跟踪方法。建立ARMA运动模型,用前两帧目标的位姿状态预测目标下一帧的状态,解决目标跟踪的角度变化与部分遮挡问题。实验结果表明,该模型能克服光照突变引发目标色彩突变的问题。

基于小波优化LSTM-ARMA模型的岩土工程非线性时间序列预测

为了更精确地预测岩土工程应力、变形等的非线性时间序列,提出了基于小波优化的长短时记忆神经网络-自回归滑动平均模型(LSTM-ARMA)预测模型。首先使用小波分析将监测序列分解成趋势项和噪声项,采用LSTM网络滚动预测趋势项、ARMA模型预测噪声项,并将趋势项预测值与噪声项预测值之和作为总的时间序列预测值。在此基础上,以上海云岭超深基坑工程为案例进行了基坑地表沉降分析,结果表明组合模型的预测精度要高于单一LSTM模型且更加稳定;进一步采用弹塑性有限元对基坑开挖诱发的地表沉降进行了预测,并与人工智能预测结果进行对比,验证了人工智预测模型的合理性。分析表明,当后续工况与前置工况所诱发的变形机理突变时,人工智能预测误差增大,但伴随后续工况的推进,人工智能预测误差将逐渐减小。

ARMA模型及参数识别技术在脉动风仿真中的应用

随着高层建筑、高耸结构及悬索结构等相对较柔的结构物在工程中日益广泛使用,结构物在脉动风作用下的响应分析愈来愈受到工程界的重视,有效地给出具有一定统计规律的脉动风记录对结构风振分析及工程抗振设计都是十分必要的。本文研究了采用自回归滑动平均(ARMA)模型和参数识别技术模拟给定条件(如功率谱或某种统计特征)的脉动风记录的计算机仿真方法。结果表明,本文提出的模拟方法是一种有效的脉动风仿真方法。