Intelligent Fault Diagnosis of Hydraulic System Based on Multiscale One-Dimensional Convolutional Neural Networks with Multiattention Mechanism
Sensors · 14.11.2024 · 24 (22) · 7267
DOI: 10.3390/s24227267 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.11.2024. Verfasst von Jiacheng Sun und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shanxi Science and Technology Major Special Plan "Unveiling and Leading" Project, Shanxi Province Science and Technology Cooperation and Exchange Special Project.
Abstract (Originalsprache)
Hydraulic systems are critical components of mechanical equipment, and effective fault diagnosis is essential for minimizing maintenance costs and enhancing system reliability. In practical applications, data from hydraulic systems are collected with varying sampling frequencies, coupled with complex interdependencies within the data, which poses challenges for existing fault diagnosis algorithms. To solve the above problems, this paper proposes an intelligent fault diagnosis of a hydraulic system based on a multiscale one-dimensional convolution neural network with a multiattention mechanism (MA-MS1DCNN). The proposed method first extracts features from multirate data samples using a parallel 1DCNN with different receptive fields. Next, a Hybrid Attention Module (HAM) is proposed, consisting of two submodules: the Correlation Attention Module (CAM) and the Importance Attention Module (IAM), which aim to meticulously and comprehensively model the complex relationships between channel features. Subsequently, to effectively utilize the feature information of different frequencies, the HAM is integrated into the 1DCNN to form the MA-MS1DCNN. Finally, the proposed method is evaluated and experimentally compared using the UCI hydraulic system dataset. The results demonstrate that, compared to existing methods such as Shapelet, MCIFM, and CNNs, the proposed method shows superior diagnostic performance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China.
- Shanxi Key Laboratory of Fully Mechanized Coal Mining Equipment, Taiyuan University of Technology, Taiyuan 030024, China.
ORCID-Profile: Jiacheng Sun, Hua Ding, Ning Li, Xiaochun Sun, Xiaoxin Dong
Förderung
- National Natural Science Foundation of China
- Shanxi Science and Technology Major Special Plan "Unveiling and Leading" Project
- Shanxi Province Science and Technology Cooperation and Exchange Special Project
- Shanxi Science and Technology Innovation Talent Team Project
- Shanxi Provincial Key Research and Development Project
- Shanxi Science and Technology Major Special Plan “Unveiling and Leading” Project
Zitieren
APA
Sun, J., Ding, H., Li, N., Sun, X., & Dong, X. (2024). Intelligent Fault Diagnosis of Hydraulic System Based on Multiscale One-Dimensional Convolutional Neural Networks with Multiattention Mechanism. Sensors, 24(22), 7267. https://doi.org/10.3390/s24227267
Vancouver
Sun J, Ding H, Li N, Sun X, Dong X. Intelligent Fault Diagnosis of Hydraulic System Based on Multiscale One-Dimensional Convolutional Neural Networks with Multiattention Mechanism. Sensors. 2024;24(22):7267. doi:10.3390/s24227267
BibTeX
@article{Sun2024,
author = {Sun, Jiacheng and Ding, Hua and Li, Ning and Sun, Xiaochun and Dong, Xiaoxin},
title = {Intelligent Fault Diagnosis of Hydraulic System Based on Multiscale One-Dimensional Convolutional Neural Networks with Multiattention Mechanism},
journal = {Sensors},
year = {2024},
volume = {24},
number = {22},
pages = {7267},
doi = {10.3390/s24227267}
}
EUVIMED