ANALYSIS OF RESOLVING HIGH FREQUENCY ISSUES BASED DYNAMIC ISOGEOMETRIC ANALYSIS FOR STRUCTURES WITH DISSIMILAR MATERIALS USING AI

Resolving high-frequency issues in structures with dissimilar materials poses significant challenges in engineering and design. Traditional methods often struggle to accurately capture the complex behaviour of these structures, leading to compromised performance and increased risks. In this study, we propose a novel approach based on dynamic Isogeometric Analysis combined with artificial intelligence (AI) techniques to address these challenges. The proposed methodology leverages the superior modelling capabilities of which is a computational framework that integrates Computer-Aided Design (CAD) and Finite Element Analysis (FEA) seamlessly. By employing NURBSbased geometry representation, provides a more accurate description of complex geometries and material interfaces. Moreover, it enables the analysis of high-frequency phenomena with reduced computational effort, making it a suitable candidate for the analysis of structures with dissimilar materials. To enhance the predictive capabilities of we harness the power of AI techniques. Machine learning algorithms are trained using historical data from similar structures, incorporating material properties, boundary conditions, and performance measures. The trained AI models learn the relationships and patterns hidden within the data, enabling them to make accurate predictions of the dynamic response of structures with dissimilar materials. This integration of AI with enhances the accuracy and efficiency of the analysis process, enabling engineers to tackle high-frequency issues effectively. To evaluate the effectiveness of the proposed methodology, we conduct a series of numerical experiments and compare the results with traditional analysis methods. The experiments involve structures with dissimilar materials, such as composite laminates, sandwich panels, or hybrid structures. The performance metrics considered include natural frequencies, mode shapes, and dynamic responses under various loading conditions. The results demonstrate that the combined AI approach outperforms traditional methods in terms of accuracy, computational efficiency, and predictive capabilities for resolving high-frequency issues. The implications of this research are significant for the design and analysis of structures with dissimilar materials.