EUVIMEDEUVIMED entdecken
Crossref

Multiscale dynamically parallel shrinkage network for fault diagnosis of aviation hydraulic pump and its generalizable applications

Song Fu, Lin Lin, Yue Wang, Minghang Zhao, Feng Guo, Baihong Zhong, Shisheng Zhong

ISA Transactions · 2024-11 · 154 · 57-72

DOI: 10.1016/j.isatra.2024.08.009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISA Transactions, 2024-11. Verfasst von Song Fu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China. Electronic address: fusong@hit.edu.cn. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Heilongjiang Provincial Postdoctoral Science Foundation, China Postdoctoral Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aiming to address the multiscale characteristics and noise corruption problems in the vibration signals of aviation hydraulic pumps, this article develops a novel Multiscale Dynamically Parallel Shrinkage Network (MDPSN) to learn complementary and rich fault-related multiscale features, with the ultimate goal of yielding higher diagnostic accuracy. One significant property is the development of a novel dynamically parallel shrinking module (DPSM) that adaptively generates independent soft thresholds for different scales, effectively shrinking noise-related features to zeros. On one hand, DPSM aggregates and interacts with features at all scales to construct a global feature representation containing richer fault-related information, which is served as the foundation for soft thresholding generation, significantly improving the accuracy and rationality of the generated thresholds. On the other hand, DPSM can adaptively generate individual soft threshold for each scale, allowing each scale to use an independent threshold tailored to its own characteristic to eliminate noise-related information. This avoids the issues of over-denoising or under-denoising caused by the uniform application of thresholds across all scales. Finally, the effectiveness of MDPSN is validated by a series of experiment comparisons on an aviation hydraulic pump dataset and two bearing datasets with various types of noise. The experimental results demonstrate that MDPSN achieves superior diagnostic accuracy compared to five other comparison methods.

Schlagwörter

Stichwörter der Autor:innen

Aviation hydraulic pumpsDeep learningFault diagnosisMultiscale learningSoft thresholding

Autor:innen und Institutionen

  • School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China. Electronic address: fusong@hit.edu.cn.
  • School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China.
  • School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China. Electronic address: wang_yue@hit.edu.cn.
  • Department of Mechanical Engineering, Harbin Institute of Technology, Weihai, China; Weihai Key Laboratory of Inteligent Operation and Maintenance, Harbin Institute of Technology, Weihai, China.
  • School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China; Weihai Key Laboratory of Inteligent Operation and Maintenance, Harbin Institute of Technology, Weihai, China.

Förderung

  • National Natural Science Foundation of China
  • Heilongjiang Provincial Postdoctoral Science Foundation
  • China Postdoctoral Science Foundation

Zitieren

APA

Fu, S., Lin, L., Wang, Y., Zhao, M., Guo, F., Zhong, B., & Zhong, S. (2024). Multiscale dynamically parallel shrinkage network for fault diagnosis of aviation hydraulic pump and its generalizable applications. ISA Transactions, 154, 57-72. https://doi.org/10.1016/j.isatra.2024.08.009

Vancouver

Fu S, Lin L, Wang Y, Zhao M, Guo F, Zhong B, et al. Multiscale dynamically parallel shrinkage network for fault diagnosis of aviation hydraulic pump and its generalizable applications. ISA Transactions. 2024;154:57-72. doi:10.1016/j.isatra.2024.08.009

BibTeX
@article{Fu2024,
  author = {Fu, Song and Lin, Lin and Wang, Yue and Zhao, Minghang and Guo, Feng and Zhong, Baihong and Zhong, Shisheng},
  title = {Multiscale dynamically parallel shrinkage network for fault diagnosis of aviation hydraulic pump and its generalizable applications},
  journal = {ISA Transactions},
  year = {2024},
  volume = {154},
  pages = {57--72},
  doi = {10.1016/j.isatra.2024.08.009}
}
Kostenlos starten →