Yuksel, Suleyman B.Arslan, Musa H.2020-03-262020-03-2620120965-0911https://dx.doi.org/10.1680/stbu.10.00049https://hdl.handle.net/20.500.12395/27884A huge amount of various granular materials can be stored in and between the cells of grouped reinforced concrete cylindrical silos. The determination of design forces for reinforced concrete groups of six cylindrical silos requires significant computational effort owing to structural continuity and force transfer between adjacent silos. In this study, the efficiency of artificial neural network models in predicting the design forces and moments of groups of six cylindrical silos due to interstice loadings was investigated. Previously obtained finite-element analysis results in the literature were used to train and test the artificial neural network models. Each parameter (silo wall thickness, intersection wall thickness and the central angle spanning the intersection walls of the groups of six cylindrical silos) affecting design forces and moments was included in the input vector. The outputs of the artificial neural network models are the bending moments, hoop forces and shear forces at the supports and crowns of the interstice walls owing to interstice loadings. All artificial neural network models were trained and tested using 11 different three-layered back-propagation methods widely used in the literature. The results obtained demonstrated that all the back-propagation methods are capable of predicting the design forces and design moments at the interstice walls of the groups of six cylindrical silos.en10.1680/stbu.10.00049info:eu-repo/semantics/closedAccesscodes of practice & standardsconcrete structuressilosArticle16510567580WOS:000311676400004Q3