Abstract
The present work presents an analysis of the tensile properties of Palm as well as Luffa natural fiber composites (NFC) in high density polyethylene (HDPE), polypropylene (PP), Epoxy, and Ecopoxy (BioPoxy 36) matrixes, taking into consideration the effect of fibers volume fraction variation. Finite element analysis i.e. representative volume element (RVE) model with chopped random fiber orientation was utilized for predicting the elastic properties. Tensile test following ASTM D3039 standard was conducted. Artificial neural network, multiple linear regression, adaptive neuro-fuzzy inference system, and support vector machine were implemented for defining the design space upon the considered parameters and evaluating the reliability of these machine learning approaches in predicting the tensile strength of natural fibers composites. Furthermore, BioPoxy 36 with 0.3 luffa fibers exhibited the highest tensile strength. Finite element analysis (FEA) findings profusely agreed with the experimental results. ANFIS Machine Learning (ML) tool showed least prediction error in predicting tensile strength of natural fibers composites.
Original language | English |
---|---|
Pages (from-to) | 4377-4393 |
Number of pages | 17 |
Journal | Journal of Polymers and the Environment |
Volume | 30 |
Issue number | 10 |
Early online date | 11 Jul 2022 |
DOIs | |
Publication status | Published - 01 Oct 2022 |
Externally published | Yes |
Bibliographical note
Publisher Copyright:© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Keywords
- Finite element analysis
- Luffa fibers
- Machine learning
- Palm fibers
- Tensile properties
ASJC Scopus subject areas
- Environmental Engineering
- Polymers and Plastics
- Materials Chemistry