Deep learning methods have become popular among researchers in the field of fault detection. However, their performance depends on the availability of big datasets. To overcome this problem researchers started applying transfer learning to achieve good performance from small available datasets, by leveraging multiple prediction models over similar machines and working conditions. However, the influence of negative transfer limits their application. Negative transfer among prediction models increases when the environment and working conditions are changing continuously. To overcome the effect of negative transfer, we propose a novel deep transfer learning method, coined deep boosted transfer learning, for wind turbine gearbox fault detection that prevents negative transfer and only focuses on relevant information from the source machine. The proposed method is an instance-based deep transfer learning method that updates the weights of the source and the target machine training samples separately. The weights of different source training samples are gradually decreased to reduce the impact on the final model. The proposed method is verified by the Case Western Reserve University bearing and real field wind farm datasets. The results show that the proposed method ignores negative transfer and achieves higher accuracy compared to standard deep learning and deep transfer learning methods.
Jamil, F , Verstraeten, T , Nowé, A , Peeters, C & Helsen, J 2022, ' A deep boosted transfer learning method for wind turbine gearbox fault detection ', Renewable Energy , vol. 197, pp. 331-341.
Jamil, F. , Verstraeten, T. , Nowé, A. , Peeters, C. , & Helsen, J. (2022). A deep boosted transfer learning method for wind turbine gearbox fault detection . Renewable Energy , 197 , 331-341.
@article{0c6855d9c6064a4b9ca9ccdfbd3e9987,
title = " A deep boosted transfer learning method for wind turbine gearbox fault detection " ,
abstract = " Deep learning methods have become popular among researchers in the field of fault detection. However, their performance depends on the availability of big datasets. To overcome this problem researchers started applying transfer learning to achieve good performance from small available datasets, by leveraging multiple prediction models over similar machines and working conditions. However, the influence of negative transfer limits their application. Negative transfer among prediction models increases when the environment and working conditions are changing continuously. To overcome the effect of negative transfer, we propose a novel deep transfer learning method, coined deep boosted transfer learning, for wind turbine gearbox fault detection that prevents negative transfer and only focuses on relevant information from the source machine. The proposed method is an instance-based deep transfer learning method that updates the weights of the source and the target machine training samples separately. The weights of different source training samples are gradually decreased to reduce the impact on the final model. The proposed method is verified by the Case Western Reserve University bearing and real field wind farm datasets. The results show that the proposed method ignores negative transfer and achieves higher accuracy compared to standard deep learning and deep transfer learning methods. " ,
keywords = " Fault detection, Deep transfer learning, Vibrations, Gearbox " ,
author = " Faras Jamil and Timothy Verstraeten and Ann Now{'e} and C{'e}dric Peeters and Jan Helsen " ,
note = " Funding Information: The authors would like to acknowledge FWO (Fonds Wetenschappelijk Onderzoek) for their support through the postdoctoral grant of Cedric Peeters ( #1282221N ) and the SBO Robustify project ( #S006119N ). This research was supported by funding from the Flemish Government under the “Onderzoeksprogramma Artifici{ " e}le Intelligentie (AI) Vlaanderen” programme and under the VLAIO/Blue Cluster Supersized 4.0 ICON project. This work was also financed by the European Union under the H2020 PLATOON project ( #872592 ). Publisher Copyright: { extcopyright} 2022 Elsevier Ltd Copyright: Copyright 2022 Elsevier B.V., All rights reserved. " ,
year = " 2022 " ,
month = sep,
doi = " 10.1016/j.renene.2022.07.117 " ,
language = " English " ,
volume = " 197 " ,
pages = " 331341 " ,
journal = " Renewable Energy " ,
issn = " 0960-1481 " ,
publisher = " Elsevier BV " ,
}