Estimation and impacts of model parameter correlation for seismic performance assessment of reinforced concrete structures

Consideration of uncertainties, including stochastic dependence among uncertain parameters, is known to be important for estimating seismic risk of structures. In this study, we characterize the dependence of modeling parameters that define a structure's nonlinear response at a component level, and the interactions of multiple components associated with a structure's response. We use random effects regression models to estimate correlations among parameters. The models are applied to a component test database with multiple tests conducted by differing research groups. Multiple tests that are conducted by a research group are subject to similar conditions and are conducted to investigate the impacts of particular properties of components. The set of tests can effectively represent components at different locations in a structure, and so are suitable for estimating stochastic dependence in model parameters. Regression models can be applied to the database to compute correlation coefficients that reflect statistical dependency among properties of components tested by individual research groups. It is assumed here that these correlation coefficients also reflect correlations associated with multiple components in a structure. To illustrate, correlations for reinforced concrete element parameters are estimated from a database of reinforced concrete beam-column tests, and then used to assess the effects of correlations on dynamic response of a frame structure. Increased correlations are seen to increase dispersion in dynamic response and produce higher estimated probabilities of collapse. This work provides guidance for characterization of parameter correlations when propagating uncertainty in seismic response assessment of structures. (C) 2017 Elsevier Ltd. All rights reserved.