A diagnosis method based on depthwise separable convolutional neural network for the attachment on the blade of marine current turbine - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering Année : 2021

A diagnosis method based on depthwise separable convolutional neural network for the attachment on the blade of marine current turbine

Tianzhen Wang

Résumé

To diagnose the attachment of marine current turbine, this article proposes a method based on convolutional neural network and the concepts of depthwise separable convolution to achieve feature extraction. The method consists of three steps: data preprocessing, feature extraction and fault diagnosis. This method can diagnose the fault degree of blade imbalance and uniform attachment in underwater environment with strong currents and complex spatiotemporal variability. It can extract distinct image feature in harsh marine environments by using a convolutional neural network. In addition, this method is robust for the recognition of blurred pictures under high-speed rotation.
Fichier non déposé

Dates et versions

hal-02902934 , version 1 (20-07-2020)

Identifiants

Citer

Bin Xin, Yilai Zheng, Tianzhen Wang, Lisu Chen, Yide Wang. A diagnosis method based on depthwise separable convolutional neural network for the attachment on the blade of marine current turbine. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 2021, 235 (10), pp.1916-1926. ⟨10.1177/0959651820937841⟩. ⟨hal-02902934⟩
28 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More