This package focuses on developing and applying predictive models for the structural analysis of steel and concrete components subjected to fire and subsequent earthquake loading. To accurately simulate the complex behavior of these structures, finite element analysis (FEA) using ABAQUS is employed. The Taguchi method optimizes the number of samples needed for FE analysis, and this method is used with SPSS after explanation its concept. However, due to the computational demands of FEA, various machine learning techniques, including regression models, Gene Expression Programming (GEP), Adaptive Network-Based Fuzzy Inference Systems (ANFIS), and ensemble methods, are explored as surrogate models. These models are trained on large datasets of FEA results to predict structural responses efficiently. The performance of these models is evaluated using statistical metrics such as RMSE, NMSE, and coefficient of determination.

This tutorial package equips you with the knowledge and tools to simulate the behavior of reinforced concrete tunnels (RCTs) subjected to internal water pressure. It combines the power of finite element (FE) modeling with artificial intelligence (AI) for efficient and accurate analysis. The Taguchi method optimizes the number of samples needed for FE analysis, and this method is used with SPSS after explanation its concept.

By leveraging Artificial Intelligence (AI) techniques such as regression, GEP, ML, DL, hybrid, and ensemble models,  we significantly reduce computational costs and time while achieving high accuracy in predicting structural responses and optimizing designs.