Risk index assessment for urban natural gas pipeline leakage based on artificial neural network

Abstract

With large-scale construction of urban natural gas pipelines, the occurrence of accidents such as fire, explosion owing to natural gas pipeline leakage has increased. How to make appropriate response strategy for urban natural gas pipeline leakage is an important topic for urban safety planner. This paper proposed an assessment program to evaluate risk of urban natural gas pipeline leakage. This system uses artificial neural network mode, which includes 10 inputs such as methane concentration, weather, corrosion, to simulate risk index of pipeline leakage. The 97-day field operation results showed that the risk index match well with field situation, which indicates the reliability and practicability of the assessment program.