Advances in machine learning-aided design of reinforced polymer composite and hybrid material systems

Abstract

Reinforced composite is a preferred choice of material for the design of industrial lightweight structures. As of late, composite materials analysis and development utilizing machine learning algorithms have been getting expanding consideration and have accomplished extraordinary upgrades in both time productivity and expectation exactness. This review encapsulates recent advances in machine learning-based design of reinforced composite during the last half-decade. It summarizes the limitations of traditional methods of reinforced composite development and presents a detailed protocol of machine learning in composite materials technology; implementation of machine learning algorithms in reinforced composite material design was covered, with an emphasis on the importance of data hygiene. Machine learning integration in material and process selection, and data sourcing techniques for machine learning-based design were also examined. The evaluation also looked at emerging digital tools and platforms for implementing machine learning algorithms. In addition, an essential effort was made to identify research gaps and define areas for further research. This review is indeed designed to provide some direction for future research into the use of machine learning for composite material design.

Keywords

• Machine learning
• Design
• Reinforced composite
• Material and process selection