Bayesian Model Updating with Adaptive Importance Sampling Using Gaussian Mixture: Case Study for Dynamic Analyses of 1-Story Moment Frame with Viscous Damper

Bayesian model updating provides a powerful and comprehensive framework for engineers to assimilate up-to-date observation data into models based on probability theory significantly reduces uncertainties. By integrating the concept of population Monte Carlo within cross-entropy method, novel adaptive importance sampling (AIS) algorithm is recently proposed conduct robust fast using Gaussian mixture. This has been proved enable constructing an density (ISD) that mimics target posterior adopted in this paper tackle seismic analyses problem 1-story moment frame with viscous damper. Results showcase distributions parameters can be successfully updated low computational cost. The results also further leveraged guide safety assessment.