A diagnosis method based on depthwise separable convolutional neural network for the attachment on the blade of marine current turbine. (November 2021)

• Record Type: Journal Article
• Authors: Xin, Bin; Zheng, Yilai; Wang, Tianzhen; Chen, Lisu; Wang, Yide
• Is Part Of: Proceedings of the Institution of Mechanical Engineers. Volume 235:Number 10(2021)
• Page Start: 1916
• Page End: 1926
• Publication Date: 2021-11
• Subjects: Marine current turbine -- blade attachment -- convolutional neural network -- fault diagnosis -- deep neural networks; Mechanical engineering -- Periodicals; Automatic control -- Periodicals; Systems engineering -- Periodicals; 621.3
• DOI: 10.1177/0959651820937841
• Languages: English
• ISSNs: 0959-6518

Abstract

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.