Fault diagnosis of EHA with few-shot data augmentation technique
Source abstract
Abstract
Abstract As an emerging object in aerospace actuators, electro-hydrostatic actuator (EHA) has the advantages of heavy load capacity and high reliability. An EHA fault diagnosis method based on a few-shot data augmentation technique is proposed to diagnose and isolate possible faults. The sensitive parameters of typical failure modes are demonstrated based on the mathematical model of EHA. By converting multi-dimensional experimental data into two-dimensional grayscale data and extracting local features, the time series characteristics and correlation between different signals can be highlighted. The Wasserstein deep convolutional generative adversarial network (WDCGAN) is used to enhance the EHA small sample data. The diagnostic model WDCGAN-stacked denoised auto encoder (SDAE) combined with WDCGAN and SDAE is proposed to differentiate between multiple types of EHA failures. Compared with the five commonly used fault classification methods, the proposed method can effectively identify the typical fault modes of EHA, with the highest accuracy of fault classification and strong feature extraction ability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Machine Fault Diagnosis Techniques · Hydraulic and Pneumatic Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (31)
Show source-provided references
1. Present development statue and key technology research of airborne electro-hydrostatic actuation system
2. Fault diagnosis of electrohydraulic actuator based on multiple source signals: an experimental investigation10.1016/j.neucom.2020.05.102 ↗
3. Analysis of China’s manned launch vehicle servo mechanism technology development
4. Xiao · 2019
5. Fault detection and diagnosis of an electro hydrostatic actuator using a novel interacting multiple model approach
6. Lan · 2017
7. Zhao · 2014
8. Analytical method for fault detection & isolation in electro-hydrostatic actuator using bond graph modelling
9. Wind turbine blade health monitoring with piezoceramic-based wireless sensor network10.1080/19475411.2013.836577 ↗
10. Application of principal component analysis in fault diagnosis of electro-hydrostatic actuators
11. Yu · 2020
12. Xu · 2020
13. Learning how to learn: meta learning approach to improve deep learning10.17577/IJERTCONV8IS10001 ↗
14. A survey on recent advances in meta-learning
15. Bearing few-shot fault diagnosis based on data generation and transfer learning
16. Generative adversarial networks for data augmentation in machine fault diagnosis10.1016/j.compind.2019.01.001 ↗
17. Data augmentation method for power transformer fault diagnosis based on conditional Wasserstein generative adversarial network
18. Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis10.1016/j.measurement.2020.108371 ↗
19. Imbalanced fault diagnosis of rolling bearing based on generative adversarial network10.1109/ACCESS.2018.2890693 ↗
20. Unsupervised representation learning with deep convolutional generative adversarial networks
21. Data augmentation for bearing fault detection with a light weight CNN
22. A simple data augmentation algorithm and a self-adaptive convolutional architecture for few-shot fault diagnosis under different working conditions10.1016/j.measurement.2020.107539 ↗
23. Machinery fault diagnosis with imbalanced data using deep generative adversarial networks10.1016/j.measurement.2019.107377 ↗
24. Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty10.1016/j.neucom.2018.10.109 ↗
25. Wasserstein generative adversarial networks
26. Mohammed · 2012
27. Model parameter identification of an electro-hydrostatic actuator base on genetic algorithm
28. The study on the dynamic capability of an electro-hydrostatic actuator to drive a large inertia load
29. Deep residual shrinkage networks for fault diagnosis10.1109/TII.2019.2943898 ↗
30. Deep Convolutional Neural Networks [Lecture Notes]10.1109/MSP.2018.2842646 ↗
31. Zhou · 2016 · 121