A Novel Adaptive Bayesian Model Averaging-Based Multiple Kriging Method for Structural Reliability Analysis

Reliability analysis for structural systems relies on an accurate surrogate model. Currently, several multiple Kriging methods are utilized to calculate the failure probability. However, existing multiple Kriging methods for the reliability analysis have generally not incorporated model form selection into the modeling process, resulting in inaccurate probability of failure estimates. To overcome the shortcomings of existing multiple Kriging methods, this article presents an adaptive Bayesian model averaging-based multiple Kriging method. The proposed method utilizes Bayesian model averaging to incorporate an ensemble of individual Kriging models, each composed of different basis functions. The effect heredity principle is employed to enhance the model search efficiency, and the Occam's Window selection strategy is implemented to remove the Kriging models with poor prediction performance from the candidate set. For the final ensemble predictions, each single Kriging model is weighted based on its corresponding posterior model probability. Four benchmark examples are applied to validate the proposed new methods. Results revealed that the proposed method notably improves efficiency and accuracy estimates of failure probability.