Design of intelligent warning method for highway traffic congestion under extreme weather conditions

In order to improve the accuracy and timeliness of warning under adverse weather conditions, an intelligent warning method for highway traffic congestion under extreme weather conditions is proposed. Based on the Van Arede model, analyze the traffic flow characteristics under extreme weather conditions and establish a dynamic correlation model of flow velocity density. Improve the Gipps safety distance model and consider factors such as water film thickness, adhesion coefficient, and vehicle speed to establish a dynamic safety distance model to enhance the accuracy of car following safety prediction. Establish a dual warning mechanism based on velocity flow parabolic distortion, using sensitive critical values to achieve advanced warning under extreme weather conditions. The experimental results show that the minimum warning accuracy of the proposed method is 92%, the false alarm rate is always below 1.0% with minimal fluctuations, and the maximum warning delay does not exceed 5 minutes.