Machine learning for polymer composites process simulation – a review. (November 2022)

• Record Type: Journal Article
• Authors: Cassola, Stefano; Duhovic, Miro; Schmidt, Tim; May, David
• Is Part Of: Composites. Number 246(2022)
• Publication Date: 2022-11
• Subjects: C. Process simulation -- Process modelling -- Finite element analysis (FEA) -- D. Process monitoring -- E. Resin flow -- Liquid composite molding -- Forming -- Compression molding; Composite materials -- Periodicals; Materials science -- Periodicals; Composite materials; Periodicals; Electronic journals; 620.118
• DOI: 10.1016/j.compositesb.2022.110208
• Languages: English
• ISSNs: 1359-8368

Abstract

Abstract: Over the last 20 years Machine Learning (ML) has been applied to a wide variety of applications in the fields of engineering and computer science. In the field of material science in particular, it has been used to help speed up predictions of structure property relationships and in general enhance the material design process. In this paper, we review the current status of ML and its specific application to polymer composites process simulation. We also review some case studies going beyond this focus, especially in the fields of computational fluid dynamics, solid mechanics and Computer Aided Engineering (CAE), to show the potential for further application in our research area. The types of ML algorithms, tools, techniques used in the various applications and their couplings with other CAE software tools are summarized and the overall result/potential of each application/method is highlighted.