Investigation of Mechanical Properties of Banana, Linen and Their Hybrid Reinforced Composite Laminates in Adverse Condition and Analyze Using ML

Year : 2026 | Volume : 14 | Special Issue 02 | Page : 25 31
    By

    H.V. Srikanth,

  • Abhijit Dandavate,

  • Aditi S. Nair,

  • Paavana Pawar,

  • S.M. Deshpriya,

  1. Professor, Department of Aeronautical Engineering, Nitte (Deemed to be University), Nitte Meenakshi Institute of Technology, Bengaluru, Karnataka, India
  2. Associate Professor, Department of Automobile Engineering, Dhole Patil College of Engineering, Pune, Maharashtra, India
  3. Student, Department of Aeronautical Engineering, Nitte (Deemed to be University), Nitte Meenakshi Institute of Technology, Bengaluru, Karnataka, India
  4. Student, Department of Aeronautical Engineering, Nitte (Deemed to be University), Nitte Meenakshi Institute of Technology, Bengaluru, Karnataka, India
  5. Student, Department of Aeronautical Engineering, Nitte (Deemed to be University), Nitte Meenakshi Institute of Technology, Bengaluru, Karnataka, India

Abstract

This research investigates the mechanical performance of composite laminates reinforced with banana and linen fibers, focusing on both individual and hybrid fiber combinations. The primary objective is to assess how these natural fiber composites behave under extreme environmental conditions, particularly high humidity and fluctuating temperatures, which are common in aerospace and automotive applications.Key mechanical properties—tensile strength, flexural strength, and impact resistance—are experimentally evaluated to assess the performance and long-term reliability of each composite design. Special attention is given to the synergistic effects that may arise when banana and linen fibers are combined, potentially leading to improved strength, toughness, and resistance to environmental degradation.To further enhance material evaluation and design, the study integrates machine learning (ML) techniques, such as regression models and classification algorithms, trained on the experimental dataset. These tools are used to predict and optimize mechanical properties based on input variables such as fiber type, environmental exposure, and fiber volume fraction. ML not only accelerates the material development process but also provides insights into performance trends, enabling designers to make informed decisions without relying solely on exhaustive physical testing. By combining experimental validation with data-driven modeling, this research offers a robust framework for the development of eco-friendly, high-performance composite materials. The findings contribute to the growing body of knowledge supporting the adoption of natural fiber-reinforced composites in structural applications, promoting sustainability and resource efficiency in engineering design. This work thus lays a foundation for future innovations in green composite technology.

Keywords: Natural fiber composites, hybrid laminates, mechanical properties, tensile strength, environmental durability, machine learning optimization

[This article belongs to Special Issue under section in Journal of Polymer & Composites (jopc)]

How to cite this article:
H.V. Srikanth, Abhijit Dandavate, Aditi S. Nair, Paavana Pawar, S.M. Deshpriya. Investigation of Mechanical Properties of Banana, Linen and Their Hybrid Reinforced Composite Laminates in Adverse Condition and Analyze Using ML. Journal of Polymer & Composites. 2026; 14(02):25-31.
How to cite this URL:
H.V. Srikanth, Abhijit Dandavate, Aditi S. Nair, Paavana Pawar, S.M. Deshpriya. Investigation of Mechanical Properties of Banana, Linen and Their Hybrid Reinforced Composite Laminates in Adverse Condition and Analyze Using ML. Journal of Polymer & Composites. 2026; 14(02):25-31. Available from: https://journals.stmjournals.com/jopc/article=2026/view=239325


References

  1. Mishra SS, Behera M. A research paper of epoxy-based composite material from the natural fiber for manufacturing of helmet. J Nat Fibers. 2015;12(3):256–67.
  2. Cerutti MD, Lacche PG. Application of genetic algorithms to optimal tailoring of composite materials. J Compos Mater. 2004;38(15):1234–45.
  3. Kapil S, Kishore N. Reliability-based optimization of laminated composite structures using genetic algorithms and artificial neural networks. Compos Struct. 2016;152:456–67.
  4. Sobieszczanski-Sobieski J, Etman BM. Preliminary aircraft design optimization using genetic algorithms. AIAA J. 1995;33(5):879–85.
  5. Ranjith AV, Kumar B. A comparative review between genetic algorithm use in composite optimization and the state-of-the-art in evolutionary computation. Mater Des. 2018;160:1–12.
  6. Li C, Wei X, He W, Guo H, Zhong J, Wu X, et al. Intelligent recognition of composite material damage based on deep learning and infrared testing. Opt Express. 2021;29:31739–53. doi:10.1364/OE.435230.
  7. Chen GL, Yanamandra K, Gupta N. Artificial neural networks framework for detection of defects in 3D-printed fiber reinforcement composites. JOM. 2021;73:2075–84. doi:10.1007/s11837-021-04708-9.
  8. Wang W, Wang H, Zhou J, Fan H, Liu H. Machine learning prediction of mechanical properties of braided-textile reinforced tubular structures. Mater Des. 2021;212:110181. doi:10.1016/j.matdes.2021.110181.
  9. Arora JS, Kaya EA. A genetic algorithm for the optimization of fiber angles in composite laminates. Compos Sci Technol. 1993;48(1–4):1–10.
  10. Doerschuk PV, Shon MA. Genetic algorithms in materials design and processing. J Mater Process Technol. 2000;103(2):200–10.
  11. Wu TL, Fang HY. Equivalent morphology concept in composite materials using machine learning and genetic algorithm coupling. Compos Part B Eng. 2020;198:108225.
Special Issue Subscription Review Article
Volume 14
Special Issue 02
Received 26/03/2025
Accepted 11/10/2025
Published 28/03/2026
Publication Time 367 Days
91

Login


My IP

PlumX Metrics