Physical characterization and hybrid modeling of erosion wear in industrial waste-filled glass/epoxy composites using machine learning and computational fluid dynamics
5 affiliations
- 1Department of Mechanical Engineering, Graphic Era (Deemed to be University), Dehradun-248002, Uttrakhand, India
- 2Department of Mechanical Engineering, Saveetha Engineering College, Thandalam, Chennai-602105, Tamil Nadu, India
- 3School of Mechanical Engineering, Vellore Institute of Technology, Vellore-632014, Tamil Nadu, India
- 4Department of Mechanical Engineering, Karpagam Academy of Higher Education, Coimbatore-641021, India
- 5Department of Mechanical Engineering, Galgotias University, Greater Noida-203201, Uttar Pradesh, India
Abstract
Hybrid epoxy-short glass fiber (SGF) composites with Linz-Donawitz slag (LDS) were manufactured and the physical and erosion properties of the produced composites were investigated. As the LDS content increased from 0 to 22.5 wt.%, the measured density increased from 1.223 to 1.468 g/cm 3 , and the void fraction rose from 3.484% to 4.880%. In addition, the microhardness improved by 40.9%, increasing from 22.53 to 31.74 Hv. High inter-property correlation (r > 0.93) was found, and the theoretical density and void fraction showed an almost perfect correlation (r = 0.99). The LDS content was the most significant factor in the L 16 orthogonal array tests for erosion wear, and the average erosion rate decreased to 158.41 mg/kg with an increase in LDS content up to 22.5 wt.%.The highest efficiency condition (32 m/s, 90°, 22.5 wt. % LDS) showed a 73.8% reduction in the erosion wear rate. As LDS content increased, the erosion changed from brittle (peak at 90°) to semi-ductile (peak at 60°) and velocity sensitivity decreased significantly. The experimental erosion data was compared with the results obtained from computational fluid dynamics (CFD) simulations using the ANSYS Fluent software and good agreement was achieved showing slightly higher prediction in the simulation as a result of ideal assumptions. Three regression models were evaluated including Polynomial Regression (R 2 = 0.841), Random Forest (R 2 = 0.923), and Neural Network (R 2 = 0.956), where the Neural Network model demonstrated an accuracy that was 13.7% higher than the Polynomial Regression model.
Related
- Computational Prediction of Recombinant Expression Efficiency for Industrial Enzymes: An Integrated Co-Translational Sequence Analysis Platform
- A Review of Computational Modeling of Cancer Metastasis
- Computational and neuropsychiatric dimensions of motivation differentially predict everyday physical activity
- Front-end and Back-end Computational Modeling of 40-Hz Auditory Steady-State Response Abnormalities in Schizophrenia
- Computational modeling of VEGF-A signaling predicts lymphatic junction state
BibTeX
@article{pati2026physical,
title = {{Physical characterization and hybrid modeling of erosion wear in industrial waste-filled glass/epoxy composites using machine learning and computational fluid dynamics}},
author = {Pravat Ranjan Pati and S. Sathees Kumar and Gaurav Gupta and Debabrata Barik and Abhilash Purohit and Abhishek Kumar Tiwari},
journal = {Journal of Materials Research and Technology},
year = {2026},
month = jun,
doi = {10.1016/j.jmrt.2026.06.028},
url = {https://doi.org/10.1016/j.jmrt.2026.06.028},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Physical characterization and hybrid modeling of erosion wear in industrial waste-filled glass/epoxy composites using machine learning and computational fluid dynamics
AU - Pravat Ranjan Pati
AU - S. Sathees Kumar
AU - Gaurav Gupta
AU - Debabrata Barik
AU - Abhilash Purohit
AU - Abhishek Kumar Tiwari
PY - 2026
DA - 2026/06/03
JO - Journal of Materials Research and Technology
DO - 10.1016/j.jmrt.2026.06.028
UR - https://doi.org/10.1016/j.jmrt.2026.06.028
AB - Hybrid epoxy-short glass fiber (SGF) composites with Linz-Donawitz slag (LDS) were manufactured and the physical and erosion properties of the produced composites were investigated. As the LDS content increased from 0 to 22.5 wt.%, the measured density increased from 1.223 to 1.468 g/cm 3 , and the void fraction rose from 3.484% to 4.880%. In addition, the microhardness improved by 40.9%, increasing from 22.53 to 31.74 Hv. High inter-property correlation (r > 0.93) was found, and the theoretical density and void fraction showed an almost perfect correlation (r = 0.99). The LDS content was the most significant factor in the L 16 orthogonal array tests for erosion wear, and the average erosion rate decreased to 158.41 mg/kg with an increase in LDS content up to 22.5 wt.%.The highest efficiency condition (32 m/s, 90°, 22.5 wt. % LDS) showed a 73.8% reduction in the erosion wear rate. As LDS content increased, the erosion changed from brittle (peak at 90°) to semi-ductile (peak at 60°) and velocity sensitivity decreased significantly. The experimental erosion data was compared with the results obtained from computational fluid dynamics (CFD) simulations using the ANSYS Fluent software and good agreement was achieved showing slightly higher prediction in the simulation as a result of ideal assumptions. Three regression models were evaluated including Polynomial Regression (R 2 = 0.841), Random Forest (R 2 = 0.923), and Neural Network (R 2 = 0.956), where the Neural Network model demonstrated an accuracy that was 13.7% higher than the Polynomial Regression model.
SN - 2214-0697
SN - 2238-7854
ER -