Machine learning approaches for predicting dielectric properties of banana fibers reinforced with polypropylene composites

Dielectric properties are the most crucial factor to consider when designing polymeric dielectrics for energy storage capacitors, microelectronic devices, and high-voltage insulations. Finding polymer dielectrics with the right characteristics quickly enough is still difficult, especially for high-e...

Full description

Saved in:
Bibliographic Details
Published in:Multiscale and Multidisciplinary Modeling, Experiments and Design Experiments and Design, 2025, Vol.8 (1), Article 71
Main Authors: Mahesh, D., Raju, N. V., Sen, Snigdha
Format: Article
Language:English
Subjects:
Characterization and Evaluation of Materials
Engineering
Mathematical Applications in the Physical Sciences
Mechanical Engineering
Numerical and Computational Physics
Original Paper
Simulation
Solid Mechanics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Dielectric properties are the most crucial factor to consider when designing polymeric dielectrics for energy storage capacitors, microelectronic devices, and high-voltage insulations. Finding polymer dielectrics with the right characteristics quickly enough is still difficult, especially for high-energy, high-temperature applications. Unsymmetrically positioned banana fibers reinforced with polypropylene (PP) matrix at level fractions of 20%, 30%, 40%, and 50% were used to create composites that complied with ASTM requirements. An impedance analyzer is employed to determine a dielectric parameter. In this article, we have experimented with a few tree-based models, including the ExtraTreeRegressor, XGBoostRegressor, and CatBoostRegressor, to estimate the dielectric properties of banana fibers, given that Tree-based machine learning (ML) algorithms have enormous potential in handling nonlinearity and prediction. To confirm these experimental results, we also tabulated model assessment measures such as Mean Square Error (MSE), Root Mean Square Error (RMSE), and R2 score. ExtraTreeRegressor outperforms the other models with the lowest error and the highest R2 score (0.98). Furthermore, we applied the Explainable AI technique LIME (Local Interpretable Model Agnostic Explanations) to the optimal model and presented a thorough performance analysis to comprehend the behavior of the model in a better way.
ISSN:2520-8160
2520-8179
DOI:10.1007/s41939-024-00666-2