Computational Predictions for Predicting the Performance of Structure
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.
Damage Prediction in Reinforced Concrete Tunnels under Internal Water Pressure
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.
Computational Modeling of Steel Plate Shear Wall (SPSW) Behavior
This course equips engineers with the tools to design and analyze Steel Plate Shear Wall (SPSW) and Reinforced Concrete Shear Walls (RCSW) subjected to explosive loads. Traditional Finite Element (FE) simulation is time-consuming and requires numerous samples for accurate results. This package offers a more efficient approach using Artificial Intelligence (AI) models trained on FEA data. You'll learn to develop FE models of SPSW and RCSW in ABAQUS software, considering material properties, interactions, and boundary conditions. The Taguchi method optimizes the number of samples needed for FE analysis, and this method is used with SPSS after explanation its concept.
We then delve into AI modeling using MATLAB. Explore various methods like regression, Machine Learning (ML), Deep Learning (DL), and ensemble models to predict the behavior of SPSW and RCSW under blast loads. Statistical analysis helps compare model accuracy. By combining FE analysis with AI models, you'll gain a powerful tool for designing blast-resistant structures while saving time and resources.
Machine Learning for Composite Materials with Abaqus
This tutorial package delves into an advanced inverse modeling approach for predicting carbon fiber properties in composite materials using a machine learning (ML) technique. Specifically, it covers the use of Gaussian Process Regression (GPR) to build a surrogate model for accurate predictions of fiber properties based on data from unidirectional (UD) lamina. By leveraging Finite Element (FE) homogenization, synthetic data is generated for training the GPR model, accounting for variations in fiber, matrix properties, and volume fractions. This framework’s efficiency and accuracy are validated using real-world data, highlighting its potential as a computational alternative to traditional experimental methods. The package includes detailed explanations, case studies, and practical exercises, equipping users with hands-on experience in applying this ML-based approach to composite material analysis.