SUMMARYThe analysis, design, and performance of buried structures associated with machinery facilities, require an understanding of soil-structure interaction (SSI). In the past, responses recorded from a structure and near-by site of a given major earthquake were studied. Few studies have been done to find the factors influencing the structure properties and massive inputs of the soil parameters when considering a regional SSI problem. The present study, more specifically, combines a simple of 2-dof structural system representing precision machinery with an extremely detailed site description. Equivalent soil parameters such as horizontal spring stiffness and the horizontal damping ratio are estimated using local soil properties. Back-propagation neural network (BPN) with extended delta bar delta (EDBD) was used as a predictor to solve SSI problems. Finally, K-mean techniques were introduced to classify the site effects.The contribution of the study shows that EDBD helps BPN to accelerate the convergent speed. It is also found that the radius of the foundation and the maximum diameter of gravel play vital roles in the maximum displacement of both the foundation and machinery. Site effect contains a local part and a global part determined by the local soil properties and geological characteristics of the area, respectively. K-mean techniques successfully cluster the stations with similar global site effects.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.