Transfer learning-based fault detection in wind turbine blades using radar plots and deep learning models

ABSTRACT

Faults in wind turbine blades are considered a critical issue that can affect the safety and performance of wind turbines. The proposed research aimed to monitor wind turbine blades and identify fault conditions using a transfer learning approach. The study utilized one good and four faulty blade conditions: bend, hub-blade loose connection, erosion, and pitch angle twist. Vibration signals for each blade condition were collected and converted as radar plots that were fed and analyzed using pre-trained deep learning models including ResNet-50, AlexNet, VGG-16, and GoogleNet. Hyperparameters including optimizer, train-test split ratio, batch size, epochs, and learning rate were examined to determine the optimal configuration for each network. The study’s core findings indicate that ResNet-50 outperformed all other models, achieving an impressive accuracy rate of 99.00%. The other models achieved lower accuracy rates, with AlexNet achieving 96.70%, GoogleNet achieving 97.00%, and VGG-16 achieving 95.00%. These findings highlight the potential of using deep learning models for wind turbine monitoring and fault detection, which could significantly improve the efficiency and reliability of wind turbines.

KEYWORDS:

• Wind turbine blade
• condition monitoring
• deep learning
• transfer learning
• fault identification

Acknowledgements

The authors would like to thank the Vellore Institute of Technology and Naresuan University for providing the facility to complete this research. In addition, we would like to thank Nguyen Duy Nam, Faculty of Technology, Dong Nai Technology University, Bien Hoa 76000, Dong Nai, Vietnam, for generous support in the formal analysis.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Supplemental data

Supplemental data for this article can be accessed online at https://doi.org/10.1080/15567036.2023.2246400.

Additional information

Notes on contributors

Arjun Jaikrishna M.

Arjun Jaikrishna M is a Bachelor of Engineering student in School of Mechanical Engineering at VIT University, Chennai, India. His research interests are automobiles, internal combustion engineering, machine learning and fault diagnosis.

Naveen Venkatesh S

Naveen Venkatesh S is a Post Doctoral Researcher in School of Mechanical Engineering, VIT University, Chennai, India. He earned his BE Degree in Automobile Engineering from Sri Venkateswara College of Engineering, Chennai in 2013 and his MTech at College of Engineering, Guindy Campus, Chennai, India. He pursued his doctoral studies in the area of fault diagnosis at VIT University, Chennai. He has published 12 articles in the area of fault diagnosis in solar photovoltaic modules.

Sugumaran V

Sugumaran V is a Professor of School of Mechanical Engineering, VIT University, Chennai, India. He earned his BE Degree in Mechanical Engineering from Amrita Institute of Technology and Science, Coimbatore in 1998 and his MTech at National Institute of Engineering under VTU, India. He was a gold medallist in MTech. He earned his PhD Degree in the area of fault diagnosis from Amrita Vishwa Vidyapeetham, Coimbatore, India. He has filed 15+ Indian patent applications. He has published 200+ international journals and 35+ international conference papers apart from several papers at national level. He has 17 years of teaching & research experience.

Joshuva Arockia Dhanraj

Joshuva Arockia Dhanraj is an Assistant Professor (S.G) at Hindustan Institute of Technology and Science (Hindustan University), Chennai, Tamilnadu, India, and he was a Post-Doctoral Researcher in Environmental Assessment and Technology for Hazardous Waste Management Research Center, Faculty of Environmental Management, Prince of Songkla University, Thailand. He is also the Chief Research Manager and Advisor of Smart Green Grid Solutions, India. He completed his Bachelor of Engineering in Electronics and Communication Engineering at Anna University, Tamil Nadu, India, in the year 2012. He completed his Master of Technology in Mechatronics at VIT University, Chennai Campus, Tamil Nadu, India, and his Master of Business Administration in Human Resource Management from the University of Madras, Chennai, Tamil Nadu, India in 2015. He completed his doctoral degree in Mechanical Engineering (Mechatronics specialization) from VIT University, Chennai Campus, Tamil Nadu, India in 2018. He has published 130+ papers in peer-reviewed/SCI/Scopus indexed international journals. His research area is in the field of Machine Learning, Renewable Energy, Machine Fault Diagnosis, Structural Health and Condition Monitoring.

Karthikeyan Velmurugan

Karthikeyan Velmurugan received the bachelor’s degree in electronics and communication engineering from the IFET College of Engineering, Anna University, Chennai, the master’s degree in green energy technology from Pondicherry University, Puducherry, and the Ph.D. degree in renewable energy from Naresuan University, Thailand. He currently works as a Postdoctoral Researcher at Naresuan University, Thailand. He has published several research articles in international journals and conferences. His research interests include solar PV and thermal systems, smart grid, wind energy and energy storage.

Chatchai Sirisamphanwong

Chatchai Sirisamphanwong received the B.Sc. degree in physics-energy and the M.Sc. and Ph.D. degrees in renewable energy from Naresuan University, Thailand, in 2000, 2004, and 2013, respectively. Since 2004, he has been working at Naresuan University. He is an associate professor and authored several academic articles and international conferences. His current research interests include photovoltaic systems, smart grid systems, wind energy, and hydrogen technology.

Rattaporn Ngoenmeesri

Rattaporn Ngoenmeesri received the B.ind.Tech in civil engineering from King Mongkut’s Institute of Technology North Bangkok, Thailand and the M.Sc. degree in renewable energy from Naresuan University, Thailand. Currently, he is working at the Faculty of Science, Naresuan University, Thailand. He has authored academic articles and international conferences. His current research interests include photovoltaic systems, smart grid systems, and wind energy.

Chattariya Sirisamphanwong

Chattariya Sirisamphanwong received the B.Sc. degree in Physics, Naresuan University and the M.Sc. degree in Nuclear Technology, Chulalongkorn University, Thailand, and Ph.D. degrees in renewable energy from Naresuan University, Thailand. Currently, she is working as an assistant professor at the Department of Physics and General Science, Faculty of Science, Nakhon Sawan Rajabhat University, Thailand. She has authored several academic articles and international conferences. Her current research interests include photovoltaic systems, smart grid systems, wind energy, hydrogen technology and energy materials.