Forecasting of Shear Strength of Concrete Beam Reinforced with FRP Bar

Abstract

This study develops a new approach for forecasting shear Strength of concrete beam without stirrups based on the artificial neural networks (ANN). Proposed ANN considers geometric and mechanical properties of cross section and FRP bars, and shear span-depth ratio. The ANN model is constructed from a set of experimental database available in the past literature. Efficiency of the ANN model was compared with existing approaches in the literature using comprehensive database. ANN is powerful tools in solving complex problems of civil engineering. The Levenberg–Marquardt (LM) method was applied for training algorithm. These existing approach include the American Concrete Institute design guide (ACI 440.1R-06), ISIS Canadian design manual (ISIS-M03-07), the British Institution of Structural Engineers guidelines (BISE), JSCE Design Recommendation, CNR-DT 203-06 Task Group, and Kara. The results demonstrate that ANN method has good agreement in calculating the shear strength of concrete beam reinforced with FRP bar among existing equations in recent decades.