New Fuzzy-Heuristic Methodology for Analyzing Compression Load Capacity of Composite Columns

Predicting the mechanical strength of structural elements is a crucial task for efficient design buildings. Considering shortcomings experimental and empirical approaches, there growing interest in using artificial intelligence techniques to develop data-driven tools this purpose. In research, empowered machine learning was employed analyze axial compression capacity (CC) circular concrete-filled steel tube (CCFST) composite columns. Accordingly, adaptive neuro-fuzzy inference system (ANFIS) trained four metaheuristic techniques, namely earthworm algorithm (EWA), particle swarm optimization (PSO), salp (SSA), teaching learning-based (TLBO). The models were first applied capture relationship between CC column characteristics. Subsequently, they requested predict new conditions. According results both phases, all could achieve dependable accuracy. However, PSO-ANFIS tangibly more than other terms computational time accuracy attain accurate predictions extreme This model with relative error below 2% correlation exceeding 99%. therefore recommended as an effective tool practical applications analyzing behavior CCFST