Source term estimation of natural gas leakage in utility tunnel by combining CFD and Bayesian inference method

As an effective way to construct and maintain various life pipelines in urban areas and industrial parks, the underground utility tunnel has been developed rapidly in China in recent years. However, the natural gas pipeline leakage in a utility tunnel may cause fire, explosion or other coupling disastrous accidents that could result in fatal consequences. The effective source term estimation (STE) of natural gas leakage can provide technical supports for emergency response during natural gas leakage accidents in utility tunnels. In this paper, a STE model with the combination of gas transport model, Bayesian inference and slice sampling method is proposed to estimate the source parameters of natural gas leakage in underground utility tunnels. The observed data can be integrated into the gas transport model and realize the inversion of natural gas leakage location and release rates. The parameter sensitivity analysis is presented to evaluate the robustness of the proposed model with good practicability, and the gas sensor layouts in the utility tunnel are analyzed and optimized. The spatio-temporal distribution of the leaked gas could be well predicted based on the estimation source parameters by the proposed STE model. The results show that the proposed model is an alternative and effective tool to provide technical supports for loss prevention and mitigation for natural gas leakage accidents in urban utility tunnels. © 2020 Elsevier Ltd