A hybrid artificial intelligence and tribological approaches for surface characterization of nanocomposites

This study presents a detailed investigation into the wear behavior and surface topography of aluminum matrix composites reinforced with boron carbide (B₄C) particles of varying sizes (90 nm to 1200 nm) and contents (2–10 wt.%), under applied loads of 10 N and 20 N. The influence of particle size, reinforcement percentage, and applied load on wear rate, coefficient of friction, and topographical features was systematically examined through experimental methods and artificial intelligence (AI)-based modeling. Results revealed that incorporating just 2 wt.% of 90 nm B₄C nanoparticles reduced the wear rate by up to 9-fold compared to unreinforced samples and outperformed composites with 10 wt.% micrometer-sized particles. Similarly, the coefficient of friction for nanocomposites was significantly lower, matching the performance of microcomposites with up to five times the reinforcement content. To further elucidate surface characteristics, 3D surface roughness and waviness values were extracted using SPIP™ software and predicted using a Gaussian Process Regression (GPR)-AI model. The AI model accurately captured trends across compositions and processing conditions, with predicted roughness values ranging from 0.20 nm to 0.46 nm and waviness from 25.07 pm to 98 pm, closely matching experimental values (0.29–0.52 nm roughness; 28.29–105 pm waviness). Morphological analysis of wear surfaces using SEM confirmed reduced deformation and crack propagation in nanocomposites, attributed to better particle dispersion and interfacial bonding. A mathematical wear model incorporating predictions and experimental data successfully characterized transitional and steady-state wear regions, with nanocomposites reaching steady-state behavior at significantly shorter distances. These findings demonstrate that combining nanoscale reinforcements with predictive modeling offers a powerful approach to designing high-performance, wear-resistant aluminum composites for structural and industrial applications.

Authors

Institutions

Publication Details

Journal
Tribology International
Published
2025-08-18
DOI
https://doi.org/10.1016/j.triboint.2025.111105
Primary Topic
Tribology and Wear Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A hybrid artificial intelligence and tribological approaches for surface characterization of nanocomposites

Mehrdad Khakbiz, Farshad Akhlaghi
Tribology International
Tribology and Wear Analysis
article

A hybrid artificial intelligence and tribological approaches for surface characterization of nanocomposites

Mehrdad Khakbiz, Farshad Akhlaghi
article en

Abstract

This study presents a detailed investigation into the wear behavior and surface topography of aluminum matrix composites reinforced with boron carbide (B₄C) particles of varying sizes (90 nm to 1200 nm) and contents (2–10 wt.%), under applied loads of 10 N and 20 N. The influence of particle size, reinforcement percentage, and applied load on wear rate, coefficient of friction, and topographical features was systematically examined through experimental methods and artificial intelligence (AI)-based modeling. Results revealed that incorporating just 2 wt.% of 90 nm B₄C nanoparticles reduced the wear rate by up to 9-fold compared to unreinforced samples and outperformed composites with 10 wt.% micrometer-sized particles. Similarly, the coefficient of friction for nanocomposites was significantly lower, matching the performance of microcomposites with up to five times the reinforcement content. To further elucidate surface characteristics, 3D surface roughness and waviness values were extracted using SPIP™ software and predicted using a Gaussian Process Regression (GPR)-AI model. The AI model accurately captured trends across compositions and processing conditions, with predicted roughness values ranging from 0.20 nm to 0.46 nm and waviness from 25.07 pm to 98 pm, closely matching experimental values (0.29–0.52 nm roughness; 28.29–105 pm waviness). Morphological analysis of wear surfaces using SEM confirmed reduced deformation and crack propagation in nanocomposites, attributed to better particle dispersion and interfacial bonding. A mathematical wear model incorporating predictions and experimental data successfully characterized transitional and steady-state wear regions, with nanocomposites reaching steady-state behavior at significantly shorter distances. These findings demonstrate that combining nanoscale reinforcements with predictive modeling offers a powerful approach to designing high-performance, wear-resistant aluminum composites for structural and industrial applications.

Tribology InternationalVol. 214
Rutgers, The State University of New Jersey (US), University of Tehran (IR)
Openalex Percentile: Top 76%
Tribology and Wear Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.