Feature Extraction and Diagnosis of Periodic Transient Impact Faults Based on a Fast Average Kurtogram–GhostNet Method
Processes · 28.01.2024 · 12 (2) · 287
DOI: 10.3390/pr12020287 ↗Kurz gefasst
Fachartikel in der Zeitschrift Processes, online erschienen am 28.01.2024. Verfasst von Wan-Lu Jiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Province Natural Science Foundation of Hebei, China.
Abstract (Originalsprache)
This paper proposes an improved fault diagnosis algorithm that combines a modified fast kurtogram (FK) method with the lightweight convolutional neural network GhostNet. The FK algorithm can adaptively select resonance demodulation bands for envelope demodulation to extract fault features, but it may be disturbed by non-Gaussian noise. Hence, the fast average kurtogram (FAK) method based on sub-band averaging was introduced. This method effectively weakens the impact of pulse noise on the kurtosis graph by splitting the signal into equal-length sub-signals and calculating the average kurtosis value of all sub-signal filters. Simultaneously, to fully utilize the advantages of deep learning technology in feature extraction and classification, this study used the FAK to convert vibration signals from one-dimensional to two-dimensional kurtosis graphs as the input for the GhostNet model. This combination not only achieved accurate fault diagnosis and classification but also showed significant advantages in processing efficiency and resource utilization. The experimental results indicate that the algorithm excelled in extracting features and diagnosing periodic transient impact faults, and compared with traditional methods, it exhibited noticeable improvements in computational efficiency and resource management.
Förderung
- National Natural Science Foundation of China
- Province Natural Science Foundation of Hebei, China
Zitieren
APA
Jiang, W., Zhao, Y., Zang, Y., Qi, Z., & Zhang, S. (2024). Feature Extraction and Diagnosis of Periodic Transient Impact Faults Based on a Fast Average Kurtogram–GhostNet Method. Processes, 12(2), 287. https://doi.org/10.3390/pr12020287
Vancouver
Jiang W, Zhao Y, Zang Y, Qi Z, Zhang S. Feature Extraction and Diagnosis of Periodic Transient Impact Faults Based on a Fast Average Kurtogram–GhostNet Method. Processes. 2024;12(2):287. doi:10.3390/pr12020287
BibTeX
@article{Jiang2024,
author = {Jiang, Wan-Lu and Zhao, Yong-Hui and Zang, Yan and Qi, Zhi-Qian and Zhang, Shu-Qing},
title = {Feature Extraction and Diagnosis of Periodic Transient Impact Faults Based on a Fast Average Kurtogram–GhostNet Method},
journal = {Processes},
year = {2024},
volume = {12},
number = {2},
pages = {287},
doi = {10.3390/pr12020287}
}
EUVIMED