Obtain the Coupling Relationships among Hazardous Chemicals Road Transportation Incident Factors to Assist Incident Rate Calculation

Abstract

With the growth of traffic volume of hazardous chemical substances, incidents take place more frequently. The causes of incidents are numerous, and the relationships among factors are complex. In order to control the inherent laws of accidents and identify the complex coupling relationship of factors, this paper puts forward a method which is based on statistical analysis of incident databases. The R language is used for data mining. The required incident information is catalogued from PHMSA database. After classifying the consequence and cause types, the most likely types can be gained by statistical analysis. The coupled relationships between the causes and consequences can be obtained. Acquire the value of support, confidence and lift of the association rules by R. According to the results of analysis, the coupling relationships with weak influence could be filtered out. The incident rate can be accurately calculated.