Sensitivity analysis in Gaussian Bayesian networks using a symbolic-numerical technique.
An object of class bn.fit
. Refer to the documentation of bnlearn
for details.
A Gaussian Bayesian network to assess the damage of reinforced concrete structures of buildings. Probabilities were given within the referenced paper. The vertices are:
Damage assessment;
Cracking state;
Cracking state in shear domain;
Steel corrosion;
Cracking state in flexure domain;
Shrinkage cracking;
Worst cracking in flexure domain;
Corrosion state;
Weakness of the beam;
Deflection of the beam;
Position of the worst shear crack;
Breadth of the worst shear crack;
Position of the worst flexure crack;
Breadth of the worst flexure crack;
Length of the worst flexure cracks;
Cover;
Structure age;
Humidity;
pH value in the air;
Content of chlorine in the air;
Number of shear cracks;
Number of flexure cracks;
Shrinkage;
Corrosion;
Castillo, E., & Kjærulff, U. (2003). Sensitivity analysis in Gaussian Bayesian networks using a symbolic-numerical technique. Reliability Engineering & System Safety, 79(2), 139-148.