Next Article in Journal
GPU-Accelerated CNN Inference for Onboard DQN-Based Routing in Dynamic LEO Satellite Networks
Next Article in Special Issue
Comprehensive Thermodynamic Performance Evaluation of a Novel Dual-Shaft Solid Oxide Fuel Cell Hybrid Propulsion System
Previous Article in Journal
Effect of Pressure on the Structural and Mechanical Properties of Cubic Silicon Carbide Reinforced with Aluminum and Magnesium
Previous Article in Special Issue
A Novel Approach to Ripple Cancellation for Low-Speed Direct-Drive Servo in Aerospace Applications
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Data-Driven Feature Extraction Process of Interleaved DC/DC Converter Due to the Degradation of the Capacitor in the Aircraft Electrical System

School of Automation, Northwestern Polytechnical University, Xi’an 710072, China
*
Author to whom correspondence should be addressed.
Aerospace 2024, 11(12), 1027; https://doi.org/10.3390/aerospace11121027
Submission received: 23 October 2024 / Revised: 8 December 2024 / Accepted: 13 December 2024 / Published: 16 December 2024
(This article belongs to the Special Issue Aircraft Electric Power System: Design, Control, and Maintenance)

Abstract

In recent years, preventive maintenance has emerged as a focal point of research in the aerospace field. The concept of equipment maintenance, exemplified by prognosis and health management (PHM), has permeated every aspect of development and design. Extracting degradation features presents a fundamental and challenging task for health assessment and remaining useful life prediction. To facilitate the efficient operation of the incipient fault diagnosis model, this paper proposes a data-driven feature extraction process for converters, which consists of two main stages. First, feature extraction and comparison are conducted in the time domain, frequency domain, and time–frequency domain. By employing wavelet decomposition and the Hilbert transform method, a highly correlated time–frequency domain feature is obtained. Second, an improved feature selection approach that combines the ReliefF algorithm with the correlation coefficient is proposed to effectively minimize redundancy within the feature subset. Furthermore, an incipient fault diagnosis model is established using neural networks, which verifies the effectiveness of the data-driven feature extraction process presented herein. Experimental results indicate that this method not only maintains fault diagnosis accuracy but also significantly reduces training time.
Keywords: feature extraction; DC/DC converter; wavelet decomposition; fault diagnosis feature extraction; DC/DC converter; wavelet decomposition; fault diagnosis

Share and Cite

MDPI and ACS Style

Zhang, C.; Gao, P.; Huang, M.; Liu, W.; Li, W.; Zhang, X. A Data-Driven Feature Extraction Process of Interleaved DC/DC Converter Due to the Degradation of the Capacitor in the Aircraft Electrical System. Aerospace 2024, 11, 1027. https://doi.org/10.3390/aerospace11121027

AMA Style

Zhang C, Gao P, Huang M, Liu W, Li W, Zhang X. A Data-Driven Feature Extraction Process of Interleaved DC/DC Converter Due to the Degradation of the Capacitor in the Aircraft Electrical System. Aerospace. 2024; 11(12):1027. https://doi.org/10.3390/aerospace11121027

Chicago/Turabian Style

Zhang, Chenguang, Pengfei Gao, Ming Huang, Wenjie Liu, Weilin Li, and Xiaobin Zhang. 2024. "A Data-Driven Feature Extraction Process of Interleaved DC/DC Converter Due to the Degradation of the Capacitor in the Aircraft Electrical System" Aerospace 11, no. 12: 1027. https://doi.org/10.3390/aerospace11121027

APA Style

Zhang, C., Gao, P., Huang, M., Liu, W., Li, W., & Zhang, X. (2024). A Data-Driven Feature Extraction Process of Interleaved DC/DC Converter Due to the Degradation of the Capacitor in the Aircraft Electrical System. Aerospace, 11(12), 1027. https://doi.org/10.3390/aerospace11121027

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop