基于自回归求和移动平均的冬季路温短临预测

发布时间：2018-06-29 08:32

  本文选题：道路工程 + 路面温度　； 参考：《同济大学学报(自然科学版)》2017年12期

【摘要】：挖掘冬季路面温度在其他外部变量影响下未来短时间内的波动规律,建立冬季路面温度短临预测模型.基于交通气象监测站的冬季历史监测数据,利用统计学方法确定路面温度的主要影响因素,应用自回归求和移动平均(ARIMA)模型建模分析,对未来短时间内的路面温度进行预测.结果表明:允许误差在±0.5℃和±1.0℃范围内,未来3 h的平均预测准确率分别达到81.25%和99.65%,对应的平均绝对误差为0.21℃和0.26℃;允许误差在±0.5℃范围内,未来第1 h的平均预测准确率最高,平均绝对误差最低,分别达到92.50%和0.15℃.
[Abstract]:The short-term and impending prediction model of winter pavement temperature is established by excavating the fluctuation law of winter pavement temperature under the influence of other external variables in the future. Based on the historical monitoring data of traffic meteorological monitoring station in winter, the main influencing factors of pavement temperature are determined by statistical method, and the road surface temperature in a short period of time in the future is predicted by using autoregressive summation moving average (Arima) model. The results show that in the range of 卤0.5 鈩，

本文编号：2081519