Providing a comprehensive approach to oil well blowout risk assessment.
An object of class bn.fit. Refer to the documentation of bnlearn for details.
A discrete Bayesian network for risk assessment of oil well blowout (Fig. 4 of the referenced paper). Probabilities were given within the referenced paper. The vertices are:
(F, S);
Mud volume/ flow change (F, S);
Circulation pressure change (F, S);
Gas-cut (F, S);
Mud property change (F, S);
Rate of Penetration (ROP) change Failure (F, S);
Mud tank (F, S);
Flow Failure (F, S);
Pump Failure (F, S);
Pump Rate (Stroke Per Minute: SPM) (F, S);
Mud density (F, S);
Mud conductivity (F, S);
Failure of tank level indicator (float system) (F, S);
Failure of an operator to notice the tank level change (F, S);
Failure of flow meter (F, S);
Failure of an operator to notice the flow meter (F, S);
Failure of pressure gage (F, S);
Failure of an operator to notice a change in SPM (F, S);
Failure of stroke meter (F, S);
Failure of an operator to notice a change in P.R (F, S);
Failure of gas detector (F, S);
Failure of an operator to notice the gauge (F, S);
Failure of the density meter (F, S);
Failure of an operator to the density meter (F, S);
Failure of resistivity (F, S);
Failure of an operator to notice the conductivity change (F, S);
Failure of the ROP indicator (F, S);
Failure of the ROP change (F, S);
Satiarvand, M., Orak, N., Varshosaz, K., Hassan, E. M., & Cheraghi, M. (2023). Providing a comprehensive approach to oil well blowout risk assessment. Plos One, 18(12), e0296086.