Review of advanced techniques for manufacturing biocomposites: non-destructive evaluation and artificial intelligence assisted modeling

Date published

2022-08-30

Free to read from

Supervisor/s

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

Department

Type

Article

ISSN

0022-2461

Format

Citation

Preethikaharshini J, Naresh K, Rajeshkumar G, et al., (2022) Review of advanced techniques for manufacturing biocomposites: non-destructive evaluation and artificial intelligence assisted modeling, Journal of Materials Science, Volume 57, Issue 34, September 2022, pp. 16091-16146

Abstract

Natural fiber reinforced polymer composites (NFRPCs) are being widely used in aerospace, marine, automotive, and healthcare applications due to their sustainability, low cost and ecofriendly nature. The NFRPCs manufactured through conventional, and computer controlled intelligent manufacturing techniques may contain internal and external defects. Traditionally, the microstructure of NFRPCs at different stages of manufacturing was obtained using destructive techniques which have stringent sample size restrictions and may cause decrease in residual properties of composites due to destructive scanning. However, these complications can be overcome by using non-destructive evaluation (NDE) and artificial intelligence (AI) techniques. This review highlights the impact of NDE and AI on the improvement of emerging manufacturing systems. We have discussed the classification of biocomposites, their manufacturing techniques, recyclability and strategies to improve mechanical properties. Further, the use of different types of contact and non-contact NDE techniques in understanding the microstructural variations during manufacturing, machining and the parameters that effects the mechanical performance of NFRPCs are discussed. The use of NDE images in developing the geometrical and computational models of NFRPCs are presented. We have highlighted the importance of AI technology in enhancing the quality of NDE images, improving the microstructural information before post-processing the data, and minimizing the analysis time, and identifying the defects and damages in NFRPCs. In the end, we presented the application of NDE techniques and AI technology in efficient generation of digital material twins of NFRPCs, which will be useful to design next generation biocomposites.

Description

Software Description

Software Language

Github

Keywords

Biocomposites, natural fiber, modern manufacturing techniques, non-destructive evaluation, machine learning, deep learning

DOI

Rights

Relationships

Relationships

Supplements

Funder/s