ANALYSIS OF GEOMETRICALLY EXACT ISOGEOMETRIC BEAM FOR LARGE DISPLACEMENTS USING MACHINE LEARNING

Geometrically exact Isogeometric analysis (IGA) has emerged as a promising technique for accurately capturing large displacements and rotations in beam structures. In this study, we explore the application of machine learning (ML) methods to enhance the analysis of geometrically exact Isogeometric beams under large displacement conditions. Geometrically exact IGA relies on mathematical formulations and numerical techniques to solve the governing equations. However, these methods often suffer from limitations in computational efficiency and accuracy when dealing with large displacements. To overcome these challenges, ML techniques have recently gained attention for their potential to provide efficient and accurate solutions for complex problems. A novel approach that combines the geometrically exact isogeometric beam formulation with ML algorithms. The ML model is trained using a dataset generated from a set of finite element simulations considering various loading and boundary conditions. The dataset includes both the input parameters (e.g., geometric properties, loading conditions) and the corresponding beam deformations under large displacements. The trained ML model can then accurately predict the beam deformations for new sets of input parameters, thus providing an efficient and fast alternative to traditional numerical methods. The predictions obtained from the ML model are compared with benchmark solutions obtained from finite element simulations, demonstrating the accuracy and reliability of the proposed approach. The results show that the MLenhanced geometrically exact Isogeometric beam analysis can accurately capture the large displacements and rotations, while significantly reducing the computational cost compared to traditional numerical methods. The proposed approach has the potential to revolutionize the analysis and design of beam structures subjected to large displacements, enabling engineers to quickly evaluate and optimize structural performance.