基于BP神经网络的二级公路线形事故风险判别

BP neural network-based risk discrimination for secondary road alignment accidents

为探究二级公路平纵线形指标与事故之间的关系,构建基于反向传播(back propagation, BP)神经网络的公路平纵线形指标风险指数模型,判别事故路段风险变化情况及风险路段区间.通过收集历史事故数据,分析各线形指标下的路段事故率,依据路段事故率对平纵8个线形指标进行风险评级;基于BP神经网络模型综合考虑各线形指标影响,得到各线形指标权重系数;综合线形指标权重系数及风险评级建立风险指数模型,分析二级公路事故多发段范围内的平纵面线形风险指数变化情况.结果表明,当二级公路为双向两车道公路,设计速度为60 km/h时,综合双向路段事故率可知道路纵坡为3%时具有较高安全性;事故风险路段具有一定规律性,即事故桩号点前100 m内为导致事故的风险路段,事故桩号点前200 m内为事故潜在风险路段.研究结果可为二级公路线形设计以及公路事故黑点的研究提供理论支持,进而优化道路线形设计,精确判别事故黑点,减少道路交通事故,提升道路安全品质.

In order to investigate the relationship between horizontal and vertical alignment indicators and accidents of second-class highway,a risk index model based on the back propagation(BP)neural network is constructed to identify the risk change analysis of accident sections and the risk section interval.By collecting historical accident data,we calculate the roadway accident rate under each alignment indicator,and based on the road accident rate,we perform risk ratings of the eight horizontal and vertical alignment indexes.By comprehensively considering the impact of each alignment indicator,we obtain the weight coefficients of each alignment index based on the BP neural network model.By combining the weight coefficient of alignment indicators and risk ratings,we establish the risk index model,and further analyze the horizontal and vertical linear risk index changes within the accident prone section of second-class highway.The results show that when the second-class highway is a two-lane highway in both directions with a design speed of 60 km/h,combined with the accident rate of the bi-directional road section,it can be seen that the road longitudinal slope of 3%has a higher safety;The accident risk section has a certain regularity,i.e.,the section within 100 m before the accident staking point is the risk section leading to an accident,and the section within 200 m before the accident staking point is the accident potential risk section.The results of the study can provide theoretical support for the design of second-class highway alignment and the study of road accident black spots,and then optimize the design of road alignment,accurately identify the accident black spots,reduce road traffic accidents,and improve the quality of road safety.