Evaluation of interface shear transfer strength of steel fiber‐reinforced concrete based on artificial neural network and regression method

Abstract

AbstractTransfer of shear strength across the concrete‐to‐concrete interface is important to the strength of reinforcement concrete structures and is extensively existing in repairing and strengthening existing reinforced concrete members, the connections between prefabricated members and the connection joints between concrete sections cast in situ. Steel fibers improve the mechanical properties of concrete and steel fiber‐reinforced concrete (SFRC) has been universally applied as the repaired materials and the connection materials in reinforced concrete structures. The aim of this paper is to evaluate the interface shear transfer (IST) strength of SFRC. One hundred twenty‐seven‐group experimental results are collected from previous studies to establish a reliable database, which the investigated parameters include the compressive strength of concrete, the diameter, length and volume friction of steel fibers, and the volumetric ratio and yield strength of shear reinforcement. Based on the established database, an artificial neural network (ANN) model is developed and the parameters sensitive is analyzed based on the proposed ANN model. Based on the parametric sensitive analysis, the linear regression model is established to evaluate the IST strength of SFRC, which is applied to evaluate the design of the concrete‐to‐concrete connections.