AI-based shear capacity of FRP-reinforced concrete deep beams without stirrups. (1st August 2022)

• Record Type: Journal Article
• Authors: AlHamaydeh, Mohammad; Markou, George; Bakas, Nikos; Papadrakakis, Manolis
• Is Part Of: Engineering structures. Volume 264(2022)
• Publication Date: 2022-08-01
• Subjects: Nonlinear FEA -- Artificial Intelligence -- FRP -- Deep Beams without Stirrups; Structural engineering -- Periodicals; Structural analysis (Engineering) -- Periodicals; Construction, Technique de la -- Périodiques; Génie parasismique -- Périodiques; Pression du vent -- Périodiques; Earthquake engineering; Structural engineering; Wind-pressure; Periodicals; 624.105
• DOI: 10.1016/j.engstruct.2022.114441
• Languages: English
• ISSNs: 0141-0296

Abstract

Highlights: A Nonlinear Finite Element Analysis (NLFEA) modeling approach is developed for simulating FRP-reinforced deep beams without shear reinforcement. Extensive database of experimental and NLFEA data is established for developing AI-algorithm. AI-model is benchmarked against several design standards [EC, ACI 440.1R-15 and the modified ACI 440.1R-15 (for size effect)] for blind predictions. The AI-model demonstrated superior generalization on the blind prediction dataset, in comparison to the design codes. Abstract: The presented work utilizes Artificial Intelligence (AI) algorithms, to model and interpret the behavior of the fiber reinforced polymer (FRP)-reinforced concrete deep beams without stirrups. This is done by first running an extensive nonlinear finite element analysis (NLFEA) investigation, spanning across the practical ranges of the different input parameters. The FEA modeling is meticulously validated against published experimental results. A total of 93 different models representing a multitude of possible FRP-reinforced deep beam designs are rigorously analyzed. The results are then utilized in building an AI-model that describes the shear capacity for FRP-reinforced deep beams. The study investigates the effect of several factors on the shear capacity and identifies the vital parameters to be used for further model development. Additionally, the developed AI-model is benchmarked against several design standards for blind predictions on new unseen data and design codes, namely: the EC, ACI 440.1R-15, and the modified ACI 440.1R-15 (for size effect). The AI-model demonstrated superior generalization on the blind prediction dataset in comparison to the design codes.