Reliable estimation of the confined compressive strength of fiber-reinforced polymer (FRP)-wrapped concrete is essential for the safe design and assessment of strengthened structural members. This study proposes an adaptive neuro-fuzzy inference system (ANFIS) model to predict the confined compressive strength of FRP-confined circular concrete cylinders. The model is trained using the Levenberg-Marquardt backpropagation algorithm, combined with an early-stopping strategy, to enhance generalization and prevent overfitting. Four physically meaningful parameters-unconfined compressive strength, cylinder diameter, FRP thickness, and FRP elastic modulus-are employed as input variables, while the confined compressive strength is taken as the output. A comprehensive database of 812 experimental results from the literature was compiled and used for model training, validation, and testing. The predictive capability of the proposed ANFIS framework was evaluated against five widely used analytical confinement models using statistical performance indicators. The developed model demonstrated superior predictive consistency and reduced scatter relative to existing confinement equations, indicating improved reliability across a broad range of strengths. The results confirm that the proposed ANFIS approach provides a stable and practical tool for estimating the confined compressive strength of FRP-wrapped concrete, supporting preliminary structural assessment and strengthening design applications.
T. A. Tawfik, Z. Akbulut, M. A. Arvas et al.· Scientific Reports· 0 citations
This study examines the fracture and mechanical performance of hybrid fiber-reinforced high-strength concrete (HFRHSC) with different water-to-binder (W/B) ratios. Six mixtures incorporating hybrid combinations of steel, polymer, glass, and basalt fibers were investigated at W/B ratios of 0.42, 0.31, and 0.25. The synergistic effects of the fiber systems were evaluated in terms of compressive strength, splitting tensile strength, flexural behavior, fracture energy, residual strength, and toughness indices. Fracture properties were assessed using three-point bending tests on notched beams, where load-crack mouth opening displacement (CMOD) and load–deflection curves were used to characterize post-cracking behavior. In addition, bilinear softening and multi-exponential models were applied to reproduce the experimental load–CMOD response and estimate fracture energy. The multi-exponential model provided a more accurate representation of the nonlinear post-peak response, with coefficients of determination generally exceeding 0.95, whereas the bilinear model remained simpler and more suitable for practical engineering interpretation. The results show that hybridization substantially improved fracture resistance, particularly at lower W/B ratios. The steel–glass fiber system achieved approximately 54% higher fracture energy, a 40% improvement in toughness index, and 35% higher peak load-carrying capacity compared to the control mixture. The steel-polymer system at W/B = 0.31 exhibited the highest energy absorption capacity, with a 124% increase in total energy absorbed up to 10 mm deflection. These findings demonstrate that properly selected hybrid fiber systems can significantly improve crack resistance and post-cracking energy dissipation in HFRHSC, while analytical modeling provides a useful tool for interpreting load-CMOD behavior and fracture energy.
P. Smarzewski, T. A. Tawfik, Mohamed Abdellatief· International Journal of Civ...· 0 citations