Physics-inspired feature engineering and explainable machine learning for tensile strength prediction of CNT–Si₃N₄ reinforced FWTPET joints
- 1School of Computer Science and Engineering, Vellore Institute of Technology , ,
- 2School of Mechanical Engineering, Vellore Institute of Technology , ,
Abstract
Introduction: The prediction of the tensile strength of carbon nanotube (CNT)–silicon nitride (Si₃N₄) reinforced friction welding of tube-to-tube plate using an external tool (FWTPET) joints is crucial for improving joint performance.
Methods: A physics-inspired machine learning framework was developed using 25 experimentally derived observations to investigate the relationships between welding parameters, engineered process descriptors, and tensile strength. Physically motivated descriptors were constructed to represent thermal input, reinforcement interaction, material flow, and dispersion effects. Hyperparameter optimization was performed for multiple regression models to improve predictive performance.
Results: The XGBoost model showed the best performance, with an MAE of 5.70, an RMSE of 7.74, and an R² of 0.9772. SHAP analysis identified CNT content and the dispersion-related descriptor as the most influential predictors. Ablation analysis showed that the combination of the original experimental process variables provided greater predictability than the engineered variables alone or their combination, while the physics-inspired process variables provided further physically interpretable representations of the welding process.
Discussion: The results indicate that small-data machine learning, domain-based feature engineering, and explainable analysis are potential techniques for predicting the tensile strength of FWTPET joints.
Related
- Explainable machine learning for shear capacity prediction of reinforced concrete deep beams
- Explainable Machine Learning with Optimized Tree-Based Models and Statistical Validation for Data-Driven Wear Prediction of Carburized and Non-Carburized Engineering Steels
- Explainable CatBoost–TabPFN Hybrid for Mode-Resolved Interlaminar Fracture Toughness Prediction in Fiber-Reinforced Polymer Composites
- Bayesian optimization-driven machine learning for compressive strength prediction of hybrid fiber-reinforced recycled aggregate concrete
- Physics-inspired feature engineering and interpretable machine learning for thermoelectric properties of multicomponent materials
BibTeX
@article{venkatachalam2026physicsinspired,
title = {{Physics-inspired feature engineering and explainable machine learning for tensile strength prediction of CNT–Si₃N₄ reinforced FWTPET joints}},
author = {Krishnan Venkatachalam and Senthil Kumaran Selvaraj and R. Lokeshkumar and G. Sundaramali},
journal = {Frontiers in artificial intelligence},
year = {2026},
month = oct,
doi = {10.3389/frai.2026.1952539},
url = {https://europepmc.org/article/PMC/PMC13727735},
note = {CC BY},
}
RIS
TY - JOUR
TI - Physics-inspired feature engineering and explainable machine learning for tensile strength prediction of CNT–Si₃N₄ reinforced FWTPET joints
AU - Krishnan Venkatachalam
AU - Senthil Kumaran Selvaraj
AU - R. Lokeshkumar
AU - G. Sundaramali
PY - 2026
DA - 2026/10/20
JO - Frontiers in artificial intelligence
DO - 10.3389/frai.2026.1952539
UR - https://europepmc.org/article/PMC/PMC13727735
AB - Introduction: The prediction of the tensile strength of carbon nanotube (CNT)–silicon nitride (Si₃N₄) reinforced friction welding of tube-to-tube plate using an external tool (FWTPET) joints is crucial for improving joint performance. Methods: A physics-inspired machine learning framework was developed using 25 experimentally derived observations to investigate the relationships between welding parameters, engineered process descriptors, and tensile strength. Physically motivated descriptors were constructed to represent thermal input, reinforcement interaction, material flow, and dispersion effects. Hyperparameter optimization was performed for multiple regression models to improve predictive performance. Results: The XGBoost model showed the best performance, with an MAE of 5.70, an RMSE of 7.74, and an R² of 0.9772. SHAP analysis identified CNT content and the dispersion-related descriptor as the most influential predictors. Ablation analysis showed that the combination of the original experimental process variables provided greater predictability than the engineered variables alone or their combination, while the physics-inspired process variables provided further physically interpretable representations of the welding process. Discussion: The results indicate that small-data machine learning, domain-based feature engineering, and explainable analysis are potential techniques for predicting the tensile strength of FWTPET joints.
SN - 2624-8212
ER -