THE ARMA MODELS APPLIED TO THE FLOW OF KARSTIC SPRINGS1

ABSTRACT: Autoregressive moving average (ABMA) models have been applied to study the flow series of the karstic springs of La Villa, Fuente Mayor (Spain), and Aliou (France). The theoretical meaning of the parameters involved in the model upon applying it to a simplified scheme of the emptying of a karstic aquifer is first analyzed. The types of transformations necessary to apply these models to the flow series that lack normality and have strong periodic components are also indicated, as are the advantages of this type of model and the physical significance of the parameters obtained, with respect to the standpoint of hydraulics, ranging from rather homogeneous aquifers (La Villa) to extremely karstic (Aliou), including aquifers with intermediate characteristics (Fuente Mayor).     

滑坡变形趋势分析

将自回归滑动平均模型引入滑坡变形分析,同时考虑了坡体变形趋势性和波动性对未来变形的影响,使得所建模型能更全面地反映坡体变形的动态。     

飞行装备ARMA滤波的电磁防护方法分析

在复杂电磁环境下,飞行装备很容易受到电磁脉冲的干扰而偏离航线或坠毁,为了增加其抗干扰能力,提出了基于ARMA滤波的电磁防护方法.该方法在装备受到电磁干扰无法控制的情况下,根据先期的轨迹和指令,通过ARMA滤波器算法,自动产生控制指令,用来剔除并更换掉无效的控制指令,使飞行装备在复杂电磁环境下,继续沿着航线飞行避免发生坠...     

Semi-parametric statistical approaches for space-time process prediction

The problem of estimation and prediction of a spatial-temporal stochastic process, observed at regular times and irregularly in space, is considered. A mixed formulation involving a non- parametric component, accounting for a deterministic trend and the effect of exogenous variables, and a parametric component representing the purely spatio-temporal random variation is proposed. Correspondingly, a two-step procedure, first addressing the estimation of the non- parametric component, and then the estimation of the parametric component is developed from the residual series obtained, with spatial-temporal prediction being performed in terms of suitable spatial interpolation of the temporal variation structure. The proposed model formula-tion, together with the estimation and prediction procedure, are applied using a Gaussian ARMA structure for temporal modelling to space-time forecasting from real data of air pollution concentration levels in the region surrounding a power station in northwest Spain.     

基于小波分解和ARMA模型的空气污染预报研究

细颗粒物PM2.5为首要污染物的空气污染严重影响了公众健康,对空气污染进行有效预报具有十分重要的意义。而目前常用的空气污染物浓度预报方法在短时事件和意外事件预测方面存在不足。利用小波多尺度分析方法改进ARMA预测模型,并将其应用于短时空气污染物浓度预测。改进模型通过小波分解方法将时间序列分解为一个近似序列和多个细节序列,分别采用ARMA模型进行预测,然后将各序列预测结果进行重构,得到最终预测结果。以天津市2014年PM2.5浓度数据为例,分别采用ARMA模型、支持向量回归(SVR)模型、人工神经网络(ANN)模型以及基于小波多尺度分解改进的SVR模型和基于小波多尺度分解改进的ARMA模型进行了对比分析。结果表明:1)小波多尺度分解能够显著提高SVR模型和ARMA模型预报精度;2)ARMA、SVR、ANN等传统模型在重污染情况下预报精度显著下降,而小波分解改进策略能够较好地解决这个问题;3)基于小波多尺度分解改进的ARMA模型预报精度较高,是城市污染物浓度预报的有效手段。     

基于ARMA模型的中国工伤事故死亡率预测研究

文中用ARMA模型,对1974年至2003年全国工业企业事故死亡率进行时间序列分析,用SAS软件检验模型的可行性,并进行预测应用.结果表明,基于ARMA模型的中国工伤事故死亡率的模拟值和真实值较吻合.     

基于多模型的区域气候变化预测方法比较研究——以厦门市为例

研究表明,气候变化对流域水资源以及生态环境造成一定影响,找到预测区域气候变化的适宜方法,可以为厦门市应对气候变化带来的影响起到积极的推动作用。文章采用英国气象局Hadley气候预测研究中心的HadCM3模式在B1情景下的输出结果,利用Delta方法对大尺度数据进行降尺度处理,得到厦门站气温和降水预测数据,与天气发生器以及统计学ARMA模型分析得到的预测结果进行比较,分析三种方式对厦门站气温和降水模拟及预测的效果,探讨各自的优点及存在的局限性。     

Research on the prediction of dangerous goods accidents during highway transportation based on the ARMA model

The COVID-19 epidemic has caused a lack of data on highway transportation accidents involving dangerous goods in China in the first quarter of 2020, and this lack of data has seriously affected research on highway transportation accidents involving dangerous goods. This study strives to compensate for this lack to a certain extent and reduce the impact of missing data on research of dangerous goods transportation accidents. Data pertaining to 2340 dangerous goods accidents in the process of highway transportation in China from 2013 to 2019 are obtained with webpage crawling software. In this paper, the number of monthly highway transportation accidents involving dangerous goods from 2013 to 2019 is determined, and the time series of transportation accidents and an autoregressive moving average (ARMA) prediction model are established. The prediction accuracy of the model is evaluated based on the actual number of dangerous goods highway transportation accidents in China from 2017 to 2019. The results indicate that the mean absolute percentage error (MAPE) between the actual and predicted values of dangerous goods highway transportation accidents from 2017 to 2019 is 0.147, 0.315 and 0.29. Therefore, the model meets the prediction accuracy requirements. Then, the prediction model is applied to predict the number of dangerous goods transportation accidents in the first quarter of 2020 in China. Twenty-two accidents are predicted in January, 23 accidents in February and 27 accidents in March. The results provide a reference for the study of dangerous goods transportation accidents and the formulation of accident prevention and emergency measures.     

污水厂出水COD预测模型的对比分析

根据污水厂日报表中的数据分别建立了ARMA、逐步回归分析、基于回归分析的神经网络模型和基于时间序列分析的神经网络模型,通过比较选择了基于时间序列分析的神经网络模型作为对污水厂出水COD的预测模型,其平均预测精度为85%,取得了满意的预测结果,有利于克服根据在线监测调整工艺参数的滞后性的缺陷,保证出水水质.     

石家庄市道路交通环境NO_x污染水平及ARMA模型预测

选择石家庄市区代表性路段作为研究对象,对其交通环境空气中NOx的污染水平进行现状监测。基于Matlab软件建立拟合模型,对下一时期的NOx污染趋势进行预测。结果表明,石家庄市交通环境中NOx小时浓度介于0.047~0.237 mg/m3之间,呈早晚高,且下午明显低于上午的日变化规律;NOx日均浓度介于0.076~0.211 mg/m3之间,其浓度与车流量呈明显的正相关性。利用matlab软件建立的ARMA模型能够较好地预测道路交通环境空气中NOx的浓度变化趋势。