Version 1
: Received: 11 November 2018 / Approved: 16 November 2018 / Online: 16 November 2018 (09:30:04 CET)
Version 2
: Received: 3 February 2019 / Approved: 4 February 2019 / Online: 4 February 2019 (13:22:39 CET)
Version 3
: Received: 9 February 2019 / Approved: 12 February 2019 / Online: 12 February 2019 (09:59:09 CET)
How to cite:
Xin, B.; Wang, T.; Zheng, Y.; Wang, Y. A Sparse Autoencoder and Softmax Regression based Diagnosis Method for the Attachment on the Blade of Marine Current Turbine. Preprints2018, 2018110394. https://doi.org/10.20944/preprints201811.0394.v1
Xin, B.; Wang, T.; Zheng, Y.; Wang, Y. A Sparse Autoencoder and Softmax Regression based Diagnosis Method for the Attachment on the Blade of Marine Current Turbine. Preprints 2018, 2018110394. https://doi.org/10.20944/preprints201811.0394.v1
Xin, B.; Wang, T.; Zheng, Y.; Wang, Y. A Sparse Autoencoder and Softmax Regression based Diagnosis Method for the Attachment on the Blade of Marine Current Turbine. Preprints2018, 2018110394. https://doi.org/10.20944/preprints201811.0394.v1
APA Style
Xin, B., Wang, T., Zheng, Y., & Wang, Y. (2018). A Sparse Autoencoder and Softmax Regression based Diagnosis Method for the Attachment on the Blade of Marine Current Turbine. Preprints. https://doi.org/10.20944/preprints201811.0394.v1
Chicago/Turabian Style
Xin, B., Yilai Zheng and Yide Wang. 2018 "A Sparse Autoencoder and Softmax Regression based Diagnosis Method for the Attachment on the Blade of Marine Current Turbine" Preprints. https://doi.org/10.20944/preprints201811.0394.v1
Abstract
The development and application of marine current energy are attracting more and more attention in the world. Due to the hardness of its working environment, it’s important to study the fault diagnosis of marine current generation system. In this paper, underwater image is chosen as the fault diagnosing signal after different sensors are compared. The faults are set by simulating varying degrees of biological attachment in the actual working environment of marine current turbine (MCT). This paper proposes a diagnosis method based on the improved sparse autoencoder (SA) and softmax regression (SR). The improved SA is used to extract the features and SR is used to classify them. Images are used to monitor whether the blade is attached by benthos and to determine its corresponding degree of attachment. Compared with the other techniques, experiment results show that the proposed method can diagnose the blade attachment with higher accuracy.
Keywords
marine current turbine; blade attachment; sparse autoencoder; softmax regression
Subject
Engineering, Energy and Fuel Technology
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
