AK_MCSAlgorithm¶
- class otak.AK_MCSAlgorithm(event, n_MC, n_DoE, sim_budget, basis, cov_model, u_criterion=2, verbose=False)¶
Class implementing AK MCS algorithm
- Event
ThresholdEvent based on composite vector of input variables on limit state function
- N_MC
integer, number of MCS samples
- N_DoE
integer, number of samples in initial Kriging DoE
- Sim_budget
integer, total simulation budget available
- Basis
basis of kriging model
- Cov_model
covariance model of kriging
- U_criterion
float, threshold value for u criterion
- Verbose
verbosity parameter
Methods
compute_U
(my_krig, list_id_evaluated)Function computing the infill criterion
Function computing failure probability using AK-IS
Accessor to Coefficient of Variation
getDoE
()Accessor to the Design of Experiments,
openturns.Sample
Accessor to the computed failure probability
Accessor to the Kriging model,
openturns.KrigingResult
Accessor to Monte-Carlo samples,
openturns.Samples
Accessor to the simulation budget
- __init__(event, n_MC, n_DoE, sim_budget, basis, cov_model, u_criterion=2, verbose=False)¶
- compute_U(my_krig, list_id_evaluated)¶
Function computing the infill criterion
- My_krig
Kriging models,
openturns.KrigingResult
- List_id_evaluated
list of evaluated
openturns.Sample
- compute_proba()¶
Function computing failure probability using AK-IS
- getCoefficientOfVariation()¶
Accessor to Coefficient of Variation
- getDoE()¶
Accessor to the Design of Experiments,
openturns.Sample
- getFailureProbability()¶
Accessor to the computed failure probability
- getKrigingModel()¶
Accessor to the Kriging model,
openturns.KrigingResult
- getMonteCarloSamples()¶
Accessor to Monte-Carlo samples,
openturns.Samples
- getSimBudget()¶
Accessor to the simulation budget