Filter-Coupled Heteroscedastic Gaussian Process Regression for S–N Curve Prediction of Injection-Molded Short Glass-Fiber-Reinforced Thermoplastics
- 1School of Engineering and Sciences, Tecnologico de Monterrey, Via Atlixcayotl 5718, Puebla 72453, Mexico
- 2Artificial Intelligence for Manufacturing and Supply Chain Institute, Calle del Puente 222 Col. Ejidos de Huipulco Tlalpan, Ciudad de Mexico 14380, Mexico
- 3School of Engineering and Sciences, Tecnologico de Monterrey, Blvd. Felipe Ángeles 2003, Venta Prieta, Pachuca de Soto 42080, Mexico
Abstract
Predicting the fatigue behavior of injection-moulded short glass-fiber-reinforced thermoplastics is hindered by the large, irreducible scatter of fatigue data and by the strong dependence of the response on the moulding conditions, which conventional point-estimate models neither reproduce nor quantify. This study presents a physics-informed heteroscedastic Gaussian process regression model (Pi-HGPR) that reconstructs the S–N curve of a given processing condition by predicting the fatigue stress amplitude as a function of the number of cycles, the injection temperature, the packing pressure, the specimen orientation, and the stress ratio, and that returns a 95% prediction band rather than a single value. The model combines a damage process-type physical mean, an anisotropic Matérn 5/2 covariance with Automatic Relevance Determination, and a local dispersion filter coupled to the process likelihood, which makes the noise level input-dependent. Trained on S–N curves compiled from the literature and assessed under two out-of-fold validation protocols (point-wise interpolation and leave-condition-out extrapolation), the model reaches a coefficient of determination of R2=0.839 in interpolation and R2=0.649 in leave-condition-out extrapolation, outperforming Random Forest and gradient-boosting baselines in both regimes, with a global empirical coverage of the prediction band of 92.9% and 86.2%, respectively, slightly below its nominal value and lower (76–81%) in sparsely sampled regions of the processing space. Automatic Relevance Determination identifies the packing pressure and the injection temperature as the most influential inputs, ahead of the stress ratio and the specimen orientation. Framing the task as predicting the stress amplitude along the low-scatter direction of the S–N field, and incorporating an input-dependent uncertainty, yields an accurate model within the tested processing window and provides reliable extrapolation limits governed by experimental data coverage rather than the learner.
Related
- From Reinforcement to Prediction: Mechanical Behavior and Modeling of CNT-Reinforced Cementitious Composites
- Spatial Applicability of Fictitious Point Feedback for Frequency Response Prediction in Unidirectional Carbon Fiber-Reinforced Polymer Plates
- A review on lignocellulosic fillers for sustainable thermoplastics
- Explainable CatBoost–TabPFN Hybrid for Mode-Resolved Interlaminar Fracture Toughness Prediction in Fiber-Reinforced Polymer Composites
- ANN-based prediction of torsional fatigue behavior in an injection-molded compliant mechanism component
BibTeX
@article{jimenezarmendariz2026filtercoupled,
title = {{Filter-Coupled Heteroscedastic Gaussian Process Regression for S–N Curve Prediction of Injection-Molded Short Glass-Fiber-Reinforced Thermoplastics}},
author = {Jorge Jiménez-Armendáriz and Mariel Alfaro-Ponce and Cristopher A. Muñoz-Ibañez and Moises Jimenez-Martinez},
journal = {Polymers},
year = {2026},
month = oct,
doi = {10.3390/polym18212627},
url = {https://www.mdpi.com/2073-4360/18/21/2627},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Filter-Coupled Heteroscedastic Gaussian Process Regression for S–N Curve Prediction of Injection-Molded Short Glass-Fiber-Reinforced Thermoplastics
AU - Jorge Jiménez-Armendáriz
AU - Mariel Alfaro-Ponce
AU - Cristopher A. Muñoz-Ibañez
AU - Moises Jimenez-Martinez
PY - 2026
DA - 2026/10/23
JO - Polymers
DO - 10.3390/polym18212627
UR - https://www.mdpi.com/2073-4360/18/21/2627
AB - Predicting the fatigue behavior of injection-moulded short glass-fiber-reinforced thermoplastics is hindered by the large, irreducible scatter of fatigue data and by the strong dependence of the response on the moulding conditions, which conventional point-estimate models neither reproduce nor quantify. This study presents a physics-informed heteroscedastic Gaussian process regression model (Pi-HGPR) that reconstructs the S–N curve of a given processing condition by predicting the fatigue stress amplitude as a function of the number of cycles, the injection temperature, the packing pressure, the specimen orientation, and the stress ratio, and that returns a 95% prediction band rather than a single value. The model combines a damage process-type physical mean, an anisotropic Matérn 5/2 covariance with Automatic Relevance Determination, and a local dispersion filter coupled to the process likelihood, which makes the noise level input-dependent. Trained on S–N curves compiled from the literature and assessed under two out-of-fold validation protocols (point-wise interpolation and leave-condition-out extrapolation), the model reaches a coefficient of determination of R2=0.839 in interpolation and R2=0.649 in leave-condition-out extrapolation, outperforming Random Forest and gradient-boosting baselines in both regimes, with a global empirical coverage of the prediction band of 92.9% and 86.2%, respectively, slightly below its nominal value and lower (76–81%) in sparsely sampled regions of the processing space. Automatic Relevance Determination identifies the packing pressure and the injection temperature as the most influential inputs, ahead of the stress ratio and the specimen orientation. Framing the task as predicting the stress amplitude along the low-scatter direction of the S–N field, and incorporating an input-dependent uncertainty, yields an accurate model within the tested processing window and provides reliable extrapolation limits governed by experimental data coverage rather than the learner.
SN - 2073-4360
ER -