Gas Path Fault Diagnosis Method Under Small Samples With Interclass Imbalance

被引：0
作者：
Wang, Kun [1 ]
He, Ai [1 ]
Liu, Yuan [2 ]
Xiao, Tingyu [1 ]
Chen, Zhixiong [2 ]
Hu, Zhongzhi [1 ]
机构：
[1] Institute for Aero Engine, Tsinghua University, Haidian District, Beijing
[2] AECC Hunan Aviation Powerplant Research Institute, Lusong District, Zhuzhou
来源：
Journal of Engineering for Gas Turbines and Power | 2025年 / 147卷 / 07期
关键词：
data-driven gas path fault diagnosis; Gaussian mixture models; interclass imbalance; small samples; transfer learning; variational autoencoder;
D O I：
10.1115/1.4067739
中图分类号：
学科分类号：
摘要：
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. Copyright © 2025 by ASME.
引用
收藏
相关论文
共 35 条
  • [21] Li R., Li S., Xu K., Zeng M., Li X., Gu J., Chen Y., Auxiliary Generative Mutual Adversarial Networks for Class-Imbalanced Fault Diagnosis Under Small Samples, Chin. J. Aeronaut, 36, 9, pp. 464-478, (2023)
  • [22] Li C., Li S., Zhang A., He Q., Liao Z., Hu J., Meta-Learning for Few-Shot Bearing Fault Diagnosis Under Complex Working Conditions, Neurocomputing, 439, pp. 197-211, (2021)
  • [23] Zhong S., Fu S., Lin L., A Novel Gas Turbine Fault Diagnosis Method Based on Transfer Learning With CNN, Measurement, 137, pp. 435-453, (2019)
  • [24] Shao S., McAleer S., Yan R., Baldi P., Highly Accurate Machine Fault Diagnosis Using Deep Transfer Learning, IEEE Trans. Ind. Inform, 15, 4, pp. 2446-2455, (2019)
  • [25] Ding H., Sun Y., Huang N., Shen Z., Wang Z., Iftekhar A., Cui X., RVGAN-TL: A Generative Adversarial Networks and Transfer Learning-Based Hybrid Approach for Imbalanced Data Classification, Inf. Sci, 629, pp. 184-203, (2023)
  • [26] He W., Chen J., Zhou Y., Liu X., Chen B., Guo B., An Intelligent Machinery Fault Diagnosis Method Based on GAN and Transfer Learning Under Variable Working Conditions, Sensors, 22, 23, (2022)
  • [27] Kingma D. P., Welling M., Auto-Encoding Variational Bayes, (2013)
  • [28] Meskin N., Naderi E., Khorasani K., A Multiple Model-Based Approach for Fault Diagnosis of Jet Engines, IEEE Trans. Control Syst. Technol, 21, 1, pp. 254-262, (2013)
  • [29] Naderi E., Meskin N., Khorasani K., Nonlinear Fault Diagnosis of Jet Engines by Using a Multiple Model-Based Approach, ASME J. Eng. Gas Turbines Power, 134, 1, (2012)
  • [30] Li Y. G., Nilkitsaranont P., Gas Turbine Performance Prognostic for Condition-Based Maintenance, Appl. Energy, 86, 10, pp. 2152-2161, (2009)
1234