Study on Framework of Traffic Operational Safety Assurance Program and Real-time Crash Risk Prediction Model of Shenzhen-Zhongshan Channel

摘要

Shenzhen-Zhongshan Channel (Shen-Zhong Channel) is designed as a 24-km long channel (8-lane freeway with design speed as 100 km/h) across the sea outfall of Pearl River. This mega channel will be encountered with significant traffic operational safety concerns due to extremely high traffic volume, high portion of trucks, and extraordinarily high exposure of dangerous goods and over-sized vehicles. A research project was funded to develop an operational safety assurance program to minimize the crash and congestion risks. This paper is for framework design of this program and a real-time crash risk prediction model, as the foundation of this program. The program was designed with different advanced traffic management (ATM) modules including variable lane management, changeable speed limit, and smart signal control. The risk prediction model was developed with traffic operational features, including volume, speed and density as inputs. Within 20 historical collisions to test the model, 16 were correctly alarmed. That is to say, the model gained 65% accuracy rate.