CAJ | 학술논문

针对道路交通事故的形成机理进行定性、定量研究,根据我国道路交通事故记录数据特征,应用贝叶斯网对事故发生概率进行定量分析.引入"驾驶员紧张度"和"道路线形合理度"两个隐节点,建立了事故分析的贝叶斯网多层隐类模型,采用最大似然估计方法确定了模型的边缘概率和条件概率.将贝叶斯网模型应用于国道104二级公路(K1310+000～K1330+000)的事故分析中,运用贝叶斯网分析软件包Netica对其历史事故记录数据进行分析.结果表明: 贝叶斯网不仅可以定量计算某种道路交通状态下的事故发生概率,而且可以找出影响事故概率的关键原因和最不利状态组合(事故概率最大时的道路交通状态).
침대도로교통사고적형성궤리진행정성、정량연구,근거아국도로교통사고기록수거특정,응용패협사망대사고발생개솔진행정량분석.인입"가사원긴장도"화"도로선형합리도"량개은절점,건립료사고분석적패협사망다층은류모형,채용최대사연고계방법학정료모형적변연개솔화조건개솔.장패협사망모형응용우국도104이급공로(K1310+000～K1330+000)적사고분석중,운용패협사망분석연건포Netica대기역사사고기록수거진행분석.결과표명: 패협사망불부가이정량계산모충도로교통상태하적사고발생개솔,이차가이조출영향사고개솔적관건원인화최불리상태조합(사고개솔최대시적도로교통상태).
The paper is to propose a method for qualitative and quantitative analysis on road accidents. As is known, many factors are likely to conduce to traffic accidents, such as unreasonable road alignment, vehicle running away, drivers' carelessness and adverse weather influences and so on. Also, the interaction and interdependence among these factors constitute the complexity of accident formation. To describe this interaction and interdependence, Bayesian Network (BN) was applied to analyze the mechanism of road accident formation. While introducing two hidden nodes: Y_0, which denotes Driver's Nervousness and Y_1, Alignment Rationality, we have built a Bayesian Network Hierarchical Latent Class model with eight nodes built-in for the road accident analysis. The other six observable nodes include X_0 (level of driver's familiarity with road condition), X_1 (time), X_2 (traffic volume), X_3 (weather condition), X_4 (horizontal radius) and X_5 (longitudinal gradient). Then the Marginal Probability and Conditional Probability were determined by Maximum Likelihood Estimation. During the estimation, prior probability was firstly let to be determined by the prior knowledge, such as historical accident data and experts experience. In addition, posterior probability was supposed to be calculated by the prior probability and likelihood function, with Marginal Probability and Conditional Probability being modified. And, finally, trial applications were conducted on the historical accidents data of the national highway G104 in China from K1310+000 to K1330+000, by using the common soft package of Netica. Primary applications study were conducted to estimate the probability of road accidents under some certain conditions with special road geometry, traffic volume, drivers' performance and weather condition. Next applications were conducted to test fault diagnosis of the accident reasons. Afterwards, parameter sensitivity analysis and comparative analysis of different factors in leading to the accident probability were analyzed to find the key liability reasons for such accidents. The results show that Bayesian Network can not only help to work out the probability of road accidents under the certain circumstances, but also contributes greatly to the analysis of the key reasons causing road accidents.