EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multiple Attention Convolutional Neural Networks for Diesel Engine Fault Diagnosis

Xiao Yang iD, Fengrong Bi, Jiangang Cheng, Daijie Tang, Pengfei Shen, Xiaoyang Bi

Sensors · 24.04.2024 · 24 (9) · 2708

DOI: 10.3390/s24092708 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.04.2024. Verfasst von Xiao Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Engines, Tianjin University, Tianjin 300350, China. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Research Project of Higher Education in Hebei province of China, State Key Laboratory of Reliability and Intelligence Electrical Equipment, State Key Laboratory of Reliability and Intelligence Electrical Equipment in Hebei University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fault diagnosis can improve the safety and reliability of diesel engines. An end-to-end method based on a multi-attention convolutional neural network (MACNN) is proposed for accurate and efficient diesel engine fault diagnosis. By optimizing the arrangement and kernel size of the channel and spatial attention modules, the feature extraction capability is improved, and an improved convolutional block attention module (ICBAM) is obtained. Vibration signal features are acquired using a feature extraction model alternating between the convolutional neural network (CNN) and ICBAM. The feature map is recombined to reconstruct the sequence order information. Next, the self-attention mechanism (SAM) is applied to learn the recombined sequence features directly. A Swish activation function is introduced to solve “Dead ReLU” and improve the accuracy. A dynamic learning rate curve is designed to improve the convergence ability of the model. The diesel engine fault simulation experiment is carried out to simulate three kinds of fault types (abnormal valve clearance, abnormal rail pressure, and insufficient fuel supply), and each kind of fault varies in different degrees. The comparison results show that the accuracy of MACNN on the eight-class fault dataset at different speeds is more than 97%. The testing time of the MACNN is much less than the machine running time (for one work cycle). Therefore, the proposed end-to-end fault diagnosis method has a good application prospect.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismdiesel engineend-to-end fault diagnosismachine learningself-attention mechanism

Autor:innen und Institutionen

  • State Key Laboratory of Engines, Tianjin University, Tianjin 300350, China.
  • State Key Laboratory of Reliability and Intelligence Electrical Equipment, Hebei University of Technology, Tianjin 300130, China.

ORCID-Profile: Xiao Yang

Förderung

  • Science and Technology Research Project of Higher Education in Hebei province of China
  • State Key Laboratory of Reliability and Intelligence Electrical Equipment
  • State Key Laboratory of Reliability and Intelligence Electrical Equipment in Hebei University of Technology

Zitieren

APA

Yang, X., Bi, F., Cheng, J., Tang, D., Shen, P., & Bi, X. (2024). A Multiple Attention Convolutional Neural Networks for Diesel Engine Fault Diagnosis. Sensors, 24(9), 2708. https://doi.org/10.3390/s24092708

Vancouver

Yang X, Bi F, Cheng J, Tang D, Shen P, Bi X. A Multiple Attention Convolutional Neural Networks for Diesel Engine Fault Diagnosis. Sensors. 2024;24(9):2708. doi:10.3390/s24092708

BibTeX
@article{Yang2024,
  author = {Yang, Xiao and Bi, Fengrong and Cheng, Jiangang and Tang, Daijie and Shen, Pengfei and Bi, Xiaoyang},
  title = {A Multiple Attention Convolutional Neural Networks for Diesel Engine Fault Diagnosis},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {9},
  pages = {2708},
  doi = {10.3390/s24092708}
}
Kostenlos starten →