A new method to investigate the intermediate crack-induced debonding strain

In order to investigate the interfacial debonding (IC) strain of the reinforced concrete structures strengthened by fiber-reinforced polymer (FRP), this paper proposed some data-driven models to explore it, considering the effect of random factors both in material and environment. The concrete strength, shear span proportion, the proportion of anchorage length to shear width, tensile reinforcement proportion, steel yield strength, stirrup reinforcement ratio, FRP stiffness, the proportion of sheet span to beamwidth, ratios of environmental temperature to the maintenance standard temperature, and ratios of environmental humidity to the relative humidity were regarded as the inputs, the IC debonding strain was regarded as the output. The results indicate that the neural network optimized by the sparrow search algorithm not only has a relatively small error but also has stronger robustness. In addition, a study on the importance of the inputs on the IC debonding strain indicates that the concrete strength, FRP stiffness, and ratios of environmental temperature to the maintenance standard temperature are the most significant factor to influence the IC debonding strain.