FAI: Fast, accurate, and intelligent approach and prediction tool for flexural capacity of FRP-RC beams based on super-learner machine learning model

Fiber-reinforced polymer (FRP) composites have recently been considered in the field of structural engineering as one best alternatives to conventional steel reinforcement due their high tensile strength, lightweight, cost-effectiveness, and superior corrosion resistance. However, variation FRP physical mechanical characteristics among different types manufacturers makes it difficult predict strength FRP-reinforced concrete (RC) members. For that reason, an efficient prediction tool was developed for a fast, accurate, intelligent (FAI) flexural capacity FRP-RC beams based on result optimized super-learner machine learning (ML) model. A database experimental results compiled randomly split into 80% training 20% test sets. Six factors were model; namely, width effective depth beam, compressive ratio, modulus elasticity, ultimate strength. Grid search is combined with 10-fold cross-validation optimize hyperparameters ML models. The capability proposed model benchmarked against boosting- tree-based models, such classification regression trees, adaptive boosting, gradient boosted decision extreme boosting. Moreover, comparison existing code guideline equations showed provided most desirable beams.