EUVIMEDEUVIMED entdecken
Crossref

Gas Path Fault Diagnosis Method Under Small Samples With Interclass Imbalance

Kun Wang, Ai He, Yuan Liu, Tingyu Xiao, Zhixiong Chen, Zhongzhi Hu

Journal of Engineering for Gas Turbines and Power · 01.07.2025 · 147 (7)

DOI: 10.1115/1.4067739 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Engineering for Gas Turbines and Power, online erschienen am 26.02.2025. Verfasst von Kun Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current data-driven methods for diagnosing gas path faults in aero-engines often rely on large, costly fault sample sets and face challenges related to class imbalances. These include disparities in the quantity of normal and fault data, differences among fault types, and variations in fault severity levels. This paper proposes a novel generative model, TL-GMVAE, which integrates Gaussian mixture models (GMM) with variational auto-encoders (VAE) and incorporates a transfer learning (TL) strategy. Using a large dataset of normal operational data, the VAE learns latent feature mappings of engine behavior and establishes a joint probability distribution across sensor measurements. To account for complexity in engine operating conditions, the GMM is used as the sampling distribution of the VAE. This enhances the model’s ability to represent diverse operating scenarios. The pretrained model is then fine-tuned with a small dataset of gas path fault data, transferring knowledge to fault domains. Each fault-specific TL-GMVAE model serves as an independent generator for synthetic fault samples. The proposed approach is validated using several established classifiers. The impact of different Fault-Normal ratios and imbalances across fault categories on classification accuracy is analyzed. Additionally, the robustness of the method to individual engine variability is evaluated. Results demonstrate that the TL-GMVAE generates high-quality fault samples and significantly improves fault diagnosis accuracy. These findings highlight its potential application in aero-engine health monitoring and fault diagnosis systems.

Zitieren

APA

Wang, K., He, A., Liu, Y., Xiao, T., Chen, Z., & Hu, Z. (2025). Gas Path Fault Diagnosis Method Under Small Samples With Interclass Imbalance. Journal of Engineering for Gas Turbines and Power, 147(7). https://doi.org/10.1115/1.4067739

Vancouver

Wang K, He A, Liu Y, Xiao T, Chen Z, Hu Z. Gas Path Fault Diagnosis Method Under Small Samples With Interclass Imbalance. Journal of Engineering for Gas Turbines and Power. 2025;147(7). doi:10.1115/1.4067739

BibTeX
@article{Wang2025,
  author = {Wang, Kun and He, Ai and Liu, Yuan and Xiao, Tingyu and Chen, Zhixiong and Hu, Zhongzhi},
  title = {Gas Path Fault Diagnosis Method Under Small Samples With Interclass Imbalance},
  journal = {Journal of Engineering for Gas Turbines and Power},
  year = {2025},
  volume = {147},
  number = {7},
  doi = {10.1115/1.4067739}
}
Kostenlos starten →