A dynamic Bayesian network based methodology for fault diagnosis of subsea Christmas tree

A subsea Christmas tree (XT) is an extremely important part of a subsea production system. The safety-fault of subsea XT indicates that no major safety incidents are difficult to diagnose. To identify the faulty components and distinguishing the fault types, including the blocking, leakage, and especially safety-fault, we present a dynamic Bayesian networks (DBN)-based fault diagnosis methodology of subsea XT considering component degradation and safety-fault. As the performance of components degrades over time, the diagnosis results can differ at different times for the given identical fault symptoms. DBNs are established to model the dynamic degradation of components in a system under additional information by using the failure rate, and fault diagnosis is conducted through a backward analysis of DBNs. Three fault diagnosis cases of subsea XT system are investigated. In case 1, when safety-fault occur on surface control subsea safety valve (SCSSV) and production main valve (PWV) components, the absolute difference in the posterior and prior probabilities of safety-fault for SCSSV and PWV was >50%. In case 2, when the blocking and leakage occur in SCSSV and annular main valve (AMV) components, respectively, the absolute difference between the posterior and prior probabilities of blocking for the SCSSV was > 30%, and the absolute difference between the posterior and prior probabilities of leakage for AMV was >30%. In case 3, when the fault occur in production control valve (PCV) and chemical injection valve 1 (CIV1) components, respectively, the absolute difference between the posterior and prior probabilities of leakage for PCV and CIV1 was > 60%. Three fault diagnosis cases validate the accuracy and effectiveness of the proposed methodology. This method is appropriate in providing maintenance instructions to engineers.