In Situ Skin Friction Capacity Modeling with Advanced Neuro-Fuzzy Optimized by Metaheuristic Algorithms

Developing new optimization algorithms and data mining has improved traditional engineering structural analysis models (meaning basically swarm-based solutions). Additionally, an accurate quantification of in situ friction capacity (ISFC) driven piles is paramount importance design/construction geotechnical infrastructures. A number studies have underscored the use developed via artificial neural networks (ANNs) anticipation bearing piles. Nonetheless, main drawbacks implementing techniques relying on are their slow convergence rate reliable testing outputs. The current research focused establishing accurate/reliable predictive network ISFC. Therefore, adaptive neuro-fuzzy inference system (ANFIS) coupled with Harris hawk (HHO), salp swarm algorithm (SSA), teaching-learning-based (TLBO), water-cycle (WCA) employed. findings revealed that four could accurately assimilate correlation ISFC to referenced parameters. values root mean square error (RMSE) realized prediction phase were 8.2844, 7.4746, 6.6572, 6.8528 for HHO-ANFIS, SSA-ANFIS, TLBO-ANFIS, WCA-ANFIS, respectively. results depicted WCA-ANFIS as more than three other at training phase, probably be utilized a substitute laboratory/classical methods.