Reliability, sensitivity

Sensitivity analysis methods can be used to analyze the respective importance of each uncertainty source with respect to a probabilistic criterion. This covers ranking methods for probabilistic criterion on central dispersion (expectation and variance) and probability of exceeding a threshold / failure probability.

Central dispersion

• Low Discrepancy Sequence
• Design of Experiments
• Optimal LHS design
• Taylor variance decomposition
• Estimating moments with Monte Carlo

Sensitivity analysis

• Taylor decomposition importance factors
• Uncertainty ranking: SRC and SRRC
• Uncertainty ranking: PCC and PRCC
• Sensitivity analysis using Sobol’ indices
• Sensitivity analysis using Sobol’ indices from polynomial chaos expansion
• Sensivity analysis with correlated inputs
• Sensitivity analysis by Fourier decomposition
• Importance factors from FORM method
• Sensitivity Factors from FORM method
• Sensitivity analysis using Hilbert-Schmidt Indepencence Criterion (HSIC)

Probability of crossing a threshold

Approximation methods

• FORM
• SORM
• Reliability Index
• Strong Maximum Test

Sampling methods

• Monte Carlo simulation
• Importance Simulation
• Directional Simulation
• Latin Hypercube Simulation
• Quasi Monte Carlo
• Subset sampling method