Machine Learning-Assisted Estimation of Interfacial Properties from Acoustic Emission Features During Microdroplet Pull-Out Tests
Journal of Composites Science · 28.05.2026 · 10 (6) · 294
DOI: 10.3390/jcs10060294 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Composites Science, online erschienen am 28.05.2026. Verfasst von Pyeong-Su Shin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Regional Innovation System & Education (RISE) program funded by the Ministry of Education (MOE) and local governments, through the Jeonbuk RISE Center, the Regional Innovation System & Education (RISE) program funded by the Ministry of Education (MOE) and local governments, through the Gyeongsangnam-do RIS…, the Ministry of Trade, Industry and Energy (MOTIE) and the Korea Institute for Advancement of Technology (KIAT) through the International Cooperative R&D P….
Abstract (Originalsprache)
Evaluation of fiber–matrix interfacial properties is essential for understanding composite performance and exploring the feasibility of real-time diagnostic approaches. In this study, the interfacial behavior between glass fiber and epoxy resin was examined using acoustic emission (AE) features obtained during microdroplet pull-out tests. Four AE features (amplitude, energy, rise time, and Fast Fourier transform peak frequency) were used as input variables to Random Forest models for both regression and classification tasks, targeting interfacial shear strength estimation and failure mode identification (interfacial debonding vs. fiber fracture). In regression analysis, energy and amplitude showed stronger associations with interfacial shear strength, although overall regression performance remained limited. In classification analysis, amplitude alone provided the most stable discrimination between fiber fracture and interfacial debonding, while combining multiple features offered only a marginal additional benefit due to feature redundancy. These results suggest that intensity-related AE parameters are closely associated with interfacial debonding behavior and failure modes. Overall, this exploratory study indicates that AE-based machine learning can serve as a supplementary tool for indirect and trend-level assessment of fiber–matrix interfacial behavior, with potential relevance to real-time monitoring applications.
Förderung
- Regional Innovation System & Education (RISE) program funded by the Ministry of Education (MOE) and local governments, through the Jeonbuk RISE Center
- the Regional Innovation System & Education (RISE) program funded by the Ministry of Education (MOE) and local governments, through the Gyeongsangnam-do RIS…
- the Ministry of Trade, Industry and Energy (MOTIE) and the Korea Institute for Advancement of Technology (KIAT) through the International Cooperative R&D P…
Zitieren
APA
Shin, P., Baek, Y., Yang, S. B., & Kwon, D. (2026). Machine Learning-Assisted Estimation of Interfacial Properties from Acoustic Emission Features During Microdroplet Pull-Out Tests. Journal of Composites Science, 10(6), 294. https://doi.org/10.3390/jcs10060294
Vancouver
Shin P, Baek Y, Yang SB, Kwon D. Machine Learning-Assisted Estimation of Interfacial Properties from Acoustic Emission Features During Microdroplet Pull-Out Tests. Journal of Composites Science. 2026;10(6):294. doi:10.3390/jcs10060294
BibTeX
@article{Shin2026,
author = {Shin, Pyeong-Su and Baek, Yeong-Min and Yang, Seong Baek and Kwon, Dong-Jun},
title = {Machine Learning-Assisted Estimation of Interfacial Properties from Acoustic Emission Features During Microdroplet Pull-Out Tests},
journal = {Journal of Composites Science},
year = {2026},
volume = {10},
number = {6},
pages = {294},
doi = {10.3390/jcs10060294}
}
EUVIMED