Estimating accident-prone freeway sections: simulation and accident prediction model

Abstract

Accident-prone sections are usually the most dangerous areas on a freeway. Identifying and studying them is therefore very important. In this study, accident-prone sections were estimated using a 77 km long freeway section in Zhejiang province, China as an example. Accident data and horizontal alignment data of the freeway were obtained. Two statistical methods – the improved cumulative frequency method considering equivalent accident numbers and the accident matrix method – were used to identify the accident-prone sections of the freeway. Additionally, a new method that combines vehicle dynamic simulation (using the CarSim software program) and speed consistency theory was developed and used to estimate the accident-prone sections of the freeway. To provide design advice, an accident prediction model was established by analysing the relationships between horizontal alignment geometric parameters and accident data. Shown to have a certain reliability, the proposed method can be used by designers to verify the safety condition of newly designed freeways and thus enhance freeway safety. The established model, which is logically reasonable and has a certain precision, could be a valuable reference for freeway designers.