Computational Methods for Blade Icing Detection of Wind Turbines
Description
This book thoroughly explores the realm of data-driven blade-icing detection for wind turbines, focusing on multivariate time series classification to enhance the reliability and efficiency of wind energy utilization. The widespread prevalence of sensor technology in wind turbines, coupled with substantial data collection, has paved the way for advanced data-driven methodologies, which do not require extensive domain knowledge or additional mechanical tools. The interdisciplinary appeal of this study has drawn attention from experts in fields like computer science, mechanical engineering, and renewable energy systems. Adopting a comprehensive approach, the book lays down a foundational framework for blade-icing detection, stressing the critical role of sensor data integration and the profound impact of machine learning techniques in refining the detection processes. The book is designed for undergraduate and graduate students keen on renewable energy technologies, researchers delving into machine learning applications in energy systems, and engineers focusing on sustainable solutions for enhancing wind turbine performance.
More details
Other editions
Additional editions
Persons
Xu Cheng (Senior Member, IEEE) received his Ph.D. degree in Engineering from the Department of Ocean Operations and Civil Engineering, Intelligent Systems Laboratory, Norwegian University of Science and Technology (NTNU), Ålesund, Norway, in June 2020. From June 2020 to March 2022, he worked as a Postdoctoral fellow, and researcher at the Department of Manufacturing and Civil Engineering, Gjøvik, Norway. From April 2022, he worked at Smart Innovation Norway as a permanent researcher. He has applied for and coordinated more than 5 projects supported by the Norwegian Research Council (NFR), the EU, and industry. He has published more than 80 papers as first and co-author in his research interests, including data analysis and artificial intelligence in maritime operations, time series analysis, and predictive maintenance of wind turbines.
Fan Shi (Member, IEEE) is a Professor at the School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China. Dr. Shi received his Ph.D. degree from Nankai University, Tianjin, China, in 2012. From June 2018 to August 2019, he was a research scholar in West Virginia University. His research interests include machine vision, pattern recognition and optics.
Xiufeng Liu received the Ph.D. degree in computer science from Aalborg University, Denmark, in 2012. He was a post-doctoral researcher at the University of Waterloo and a research scientist at IBM, Canada, from 2013 to 2014. He is currently a senior researcher at the Department of Technology, Management and Economics at the Technical University of Denmark. His research interests include smart meter data analysis, data warehousing, energy informatics, and big data.
Shengyong Chen (Senior Member, IEEE) is a full professor at Tianjin University of Technology and the director of the Engineering Research Center of Learning-Based Intelligent System (Ministry of Education). He has been conducting research on vision sensors for robotics for more than 20 years. He obtained the Ph.D. degree in computer vision from City University of Hong Kong. From 2006 to 2007, he received a fellowship from the Alexander von Humboldt Foundation of Germany and worked at University of Hamburg, Germany. From 2008 to 2012, he worked as a visiting professor at Imperial College London and University of Cambridge, U.K. He has published over 300 scientific papers in international journals and conferences, including 80 papers in IEEE Transactions. He also published 10+ books in the past years and applied 100+ patents. He received the National Outstanding Youth Foundation Award of NSFC. He organized about 20 international conferences and serves as associate editors of 3 international journals, e.g. IEEE Transactions on Cybernetics.
Content
Introduction.- State of the art.- Modeling of time series.- Attention-based convolutional neural network for blade icing detection.- Multiscale Graph-based neural network for blade icing detection.- Multiscale Wavelet-Driven Graph Convolutional Network for Blade Icing Detection.- Prototype-based Semi-supervised blade icing detection.- Class Imbalanced Federated Learning Model for Blade Icing Detection.- Heterogeneous Federated Learning Model for Blade Icing Detection.- Blockchain-enhanced Federated Learning Model for Blade Icing Detection.- Concluding remarks.
