ENHANCING COMPOSITE MATERIALS BY COMPUTATIONAL INTELLIGENCE TECHNIQUES

Abstract

The pursuit of advanced composite materials with superior mechanical properties and performance characteristics has become increasingly critical in various engineering applications. This study presents a novel approach that leverages computational intelligence algorithms—specifically particle swarm optimization and flower pollination—to optimize the design and performance of composite materials used in dynamic systems, such as in the geometry and design of complex structures of airplane and bioreactor applications. By integrating computational intelligence with material science, we developed a framework to predict and enhance the properties of composite materials under various operational conditions. The proposed method involves a single objective and multi-objective optimization process that simultaneously considers factors such as weight reduction, tensile strength, and thermal stability. Through simulations and experimental validations, we demonstrate how the optimization of fiber orientation, matrix selection, and layering configurations can lead to significant improvements in the performance of composite materials. Additionally, we explore the application of sensor fusion techniques to monitor real-time performance metrics of these materials in dynamic environments, allowing for adaptive responses to varying operational conditions. The results indicate a marked improvement in the resilience and functionality of composite materials, paving the way for their enhanced application in aerospace engineering and bioprocessing. This work underscores the potential of computational intelligence in revolutionizing the design and application of composite materials, offering promising pathways for future research and industrial implementation.