The invention discloses a road passing time prediction method of an ARIMA-BP combination model considering multiple influence factors, and the method comprises the following steps: 1, data collection: collecting road conditions, traffic conditions, traffic external environment and road passing time, the road passing time comprising road section driving time and intersection passing time; the road traffic volume in the traffic conditions comprises the total traffic volume and the traffic volume of each vehicle type; step 2, constructing a road passing time fitting model based on an ARIMA model; and step 3, carrying out residual error correction on the road passing time based on the GA-BP neural network to obtain a passing time prediction value. Compared with an existing method, the method is higher in passing time prediction value precision.
本发明公开一种考虑多种影响因素ARIMA‑BP组合模型的道路通行时间预测方法,包括如下步骤:步骤一、数据收集:收集道路条件、交通条件、交通外环境与道路通行时间,道路通行时间包括路段行使时间与交叉口通行时间;交通条件中的道路交通量包括总交通量与各车型交通量;步骤二、基于ARIMA模型构建道路通行时间拟合模型;步骤三、基于GA‑BP神经网络对道路通行时间进行残差修正,获得通行时间预测值。本发明相对于现有的方法通行时间预测值的精度更高。
Road passing time prediction method of ARIMA-BP combination model considering multiple influence factors
考虑多种影响因素ARIMA-BP组合模型的道路通行时间预测方法
2024-06-07
Patent
Electronic Resource
Chinese
Road traffic flow prediction method based on ARIMA model and kalman filtering
European Patent Office | 2016
|Short-Time Traffic Flow Prediction with ARIMA-GARCH Model
British Library Conference Proceedings | 2011
|Urban road traffic demand prediction method considering road construction influence
European Patent Office | 2025
|