A SOMNN Model for Transport Risk Assessment of Hazardous Materials by Rail

Abstract

Railway siding for transport of hazardous materials is an important way in transporting of hazardous materials in China and they often result in catastrophic consequences for environment and society with a great deal of economic loss. Risk assessment for railway siding is an effective way to ensure its operational safety. This paper focuses on the application of self-organizing neural network (SOMNN) to assess the risk of the railway siding operational system and classify its risk factors. In this work, the system analysis method based on the characteristics of railway siding for hazardous materials is first used to establish the transport risk assessment index system. A comprehensive risk assessment model of railway siding has been developed with the SOMNN theory to improve present methods available for risk assessment of rail siding’s safety. A field case study about 15 railway slides for transporting of oil in Jilin broach center of China National Petroleum Corporation is undertaken so that the effectiveness of the proposed approach could be verified. The result is in line with the actual situation and indicates that this method used is feasible and rational. This model provides a new method for transport risk assessment of hazardous materials by rail. The method is also proved more efficient for both risk assessment and safety management. The work specified in this paper can be as reference to the assessment work in China.