Journal
RENEWABLE ENERGY
Volume 171, Issue -, Pages 103-115Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.renene.2021.01.143
Keywords
Wind turbine; Fault diagnosis; Transfer learning; Convolutional autoencoder; Small-scale data
Funding
- National Natural Science Foundation of China [72072114]
- Science and Technology Development Fund, Macau SAR [FDCT0033/2020/A1]
- [MYRG2018-00087-FBA]
Ask authors/readers for more resources
This paper proposes a fault diagnosis method for wind turbines based on parameter-based transfer learning and convolutional autoencoder, suitable for small-scale data. The method can transfer knowledge from similar wind turbines and shows advantages in fault diagnosis.
Condition monitoring and fault diagnosis for wind turbines can effectively reduce the impact of failures. However, many wind turbines cannot establish fault diagnosis models due to insufficient data. The operational data of similar wind turbines usually contain some universal information about failure properties. In order to make full use of these useful information, a fault diagnosis method based on parameter-based transfer learning and convolutional autoencoder (CAE) for wind turbines with small-scale data is proposed in this paper. The proposed method can transfer knowledge from similar wind turbines to the target wind turbine. The performance of the proposed method is analyzed and compared to other transfer/non-transfer methods. The comparison results show that the proposed method has advantages in diagnosing faults for wind turbines with small-scale data. (c) 2021 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available