bnRep (version 0.0.3)

corrosion: corrosion Bayesian Network

Description

Dynamic Bayesian network model to study under-deposit corrosion.

Value

An object of class bn.fit. Refer to the documentation of bnlearn for details.

Format

A discrete Bayesian network to understand different risk factors and their interdependencies in under-deposit corrosion and how the interaction of these risk factors leads to asset failure due to under-deposit corrosion. Probabilities were given within the referenced paper. The vertices are:

BurstPressure

(High, Low);

Chloride

(High, Moderate, Low);

DefectDepth

(Yes, No);

DefectLength

(Yes, No);

FlowVelocity

(High, Moderate, Low);

InorganicDeposits

(Absent, Present);

MEG

(Absent, Present);

MixedDeposits

(Absent, Present);

OD

(High, Low);

OperatingPressure

(High, Moderate, Low);

OperatingTemperature

(High, Moderate, Low);

OrganicDeposits

(Absent, Present);

PartialPressureCO2

(High, Moderate, Low);

pH

(Acid, Neutral, Basic);

PipeFailure

(Yes, No);

ShearingForce

(High, Moderate, Low);

SolidDeposits

(High, Moderate, Low);

SteelGrade

(High, Low);

SuspendedDeposits

(High, Moderate, Low);

UDCCorrRate

(High, Moderate, Low);

UnderDepositGalvanicCell

(Poor, Fair, Good, Excellent);

WallThicknessLoss

(Yes, No).

References

Dao, U., Sajid, Z., Khan, F., & Zhang, Y. (2023). Dynamic Bayesian network model to study under-deposit corrosion. Reliability Engineering & System Safety, 237, 109370.