PhysGMM-MoE: A Physics-Aware GMM-Mixture-of-Experts Framework for Small-Sample Engine Fault Classification
Applied Sciences · 02.03.2026 · 16 (5) · 2417
DOI: 10.3390/app16052417 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 02.03.2026. Verfasst von Qingang Xu und 3 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xinjiang Uygur Autonomous Region Key Research and Development Project, Xinjiang Uygur Autonomous Region Natural Science Foundation Project.
Abstract (Originalsprache)
Accurate engine fault classification with limited labeled data is critical for the safety and reliability of rotating machinery. This task is challenging because operating regimes are time-varying, and key variables must satisfy physical constraints, under which traditional feature classifier pipelines degrade and deep networks tend to overfit. We propose PhysGMM-MoE, a physics-aware Gaussian Mixture Model (GMM)-Mixture-of-Experts (MoE) framework for small-sample engine fault classification. At the data level, PhysGMM-MoE fits class-conditional, regime-aware GMMs and performs physically constrained, distance-based quality control to selectively augment minority classes while preserving engine operating semantics. At the model level, a heterogeneous pool of lightweight statistical experts and a lightweight Transformer-based deep expert (ECFT-Transformer) capture complementary neighborhood cues and high order multi-sensor correlations, and an L2-regularized logistic regression meta-learner fuses expert outputs via stacking. We evaluate fault classification on the 3500-DEFault diesel-engine dataset using the adopted eight-class cylinder-fault labeling (H, F1–F7) built from in-cylinder pressure statistics and torsional-vibration harmonics; although severity levels exist in the dataset, this study focuses on classification rather than severity estimation. With 40 training samples per class, PhysGMM-MoE achieves a mean accuracy of 0.9875, exceeding SMOTE+XGBoost by 0.0086, and attains the best macro precision/recall/F1 of 0.9878/0.9826/0.9889, demonstrating strong performance under the adopted small-sample setting.
Förderung
- Xinjiang Uygur Autonomous Region Key Research and Development Project
- Xinjiang Uygur Autonomous Region Natural Science Foundation Project
Zitieren
APA
Xu, Q., Wang, H., Wang, Y., & Chen, X. (2026). PhysGMM-MoE: A Physics-Aware GMM-Mixture-of-Experts Framework for Small-Sample Engine Fault Classification. Applied Sciences, 16(5), 2417. https://doi.org/10.3390/app16052417
Vancouver
Xu Q, Wang H, Wang Y, Chen X. PhysGMM-MoE: A Physics-Aware GMM-Mixture-of-Experts Framework for Small-Sample Engine Fault Classification. Applied Sciences. 2026;16(5):2417. doi:10.3390/app16052417
BibTeX
@article{Xu2026,
author = {Xu, Qingang and Wang, Hongwei and Wang, Yunhang and Chen, Xicong},
title = {PhysGMM-MoE: A Physics-Aware GMM-Mixture-of-Experts Framework for Small-Sample Engine Fault Classification},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {5},
pages = {2417},
doi = {10.3390/app16052417}
}
EUVIMED