AI for Wind Turbine Performance and Condition Monitoring (Hardcover)

Wind power is unanimously recognized as one of the major drivers of the energy transition. Increasing renewable power generation introduces significant challenges for both the operation and planning of power systems, driven by the intrinsic uncertainty of stochastic renewable resources and by the growing spatial distribution of generation assets. Wind power presents a distinctive set of challenges in this context.

Wind turbines are complex machines operating under highly non-stationary conditions and are composed of tightly coupled mechanical, electrical, and electronic subsystems. In order to ensure reliable power system operation and to minimize the levelized cost of energy, it is essential to continuously monitor the health status of wind turbines, and to improve the efficiency of wind energy conversion as much as possible. Artificial intelligence has the potential to help address these challenges.

The objective of this book is to address the gap between domain expertise in wind energy and the rapid proliferation of machine learning techniques. While advanced data-driven models offer unprecedented flexibility and predictive capabilities, their increasing complexity can come at the cost of transparency, physical interpretability, and engineering insight. Bridging this gap demands a critical understanding of the problem at hand, a clear definition of the operational objective, and a conscious selection of the most appropriate techniques compatible with the available data sources.

Offering concise but thorough coverage of the topic, AI for Wind Turbine Performance and Condition Monitoring explores data sources from turbines and fleets, reviews the fundamentals of ML, then covers AI-based wind turbine performance analysis, AI-based detection of static misalignment and sensor errors, and condition monitoring for wind turbine maintenance.

Wind power researchers in academia and industry, grid operators, and maintenance managers will find this book offers a valuable overview and analysis of AI-based methodologies for wind generators.

Davide Astolfi is an assistant professor in power and energy systems at the University of Brescia, Italy. He holds a PhD in physics and a PhD in industrial and information engineering. His research focuses on data-driven methods and artificial intelligence for wind turbine performance assessment, condition monitoring, and fleet-wide diagnostics based on SCADA data. His interests also include renewable generation forecasting, electrical load forecasting, data imputation techniques, and the integration of renewable energy with electric mobility and vehicle-to-grid systems. He has authored more than 160 scientific publications and serves in editorial roles for leading journals in wind energy and smart grids, collaborating with major utility companies on predictive maintenance and performance optimization of multi-MW wind farms.

Silvia Iuliano is a doctoral researcher in information technologies for engineering at the University of Sannio, Benevento, Italy. She received her BSc (Magna Cum Laude with Special Mention) and MSc (Magna Cum Laude) degrees in energy engineering from the University of Sannio. Her research interests include the optimization of distributed energy resources, game-theoretic methods for power system operation, voltage regulation in large power systems with high penetration of renewable energy resources, and hybrid supervised and unsupervised Machine Learning approaches for predicting the dynamic security state of the transmission power systems.

Alfredo Vaccaro is a full professor of power and energy systems at the University of Sannio, Benevento. Italy. He is a fellow of the IEEE. He received his MSc (Hons.) degree in electronic engineering from the University of Salerno, Italy, and his PhD degree in electrical and computer engineering from the University of Waterloo, Waterloo, ON, Canada. From 1999 to 2002, he was an assistant researcher with the Department of Electrical and Electronic Engineering at the University of Salerno, Fisciano, Italy. From 2002 to 2015, he was an assistant professor of electric power systems in the Department of Engineering at the University of Sannio. His research interests include soft computing and interval-based methods applied to power system analysis, as well as self-organizing paradigms for smart grid computing. He was the Chair of the IEEE Power System Operation, Planning, and Economics Committee-Technologies and Innovations (T&I) SC. He is an associate editor of IEEE Transactions on Power Systems and IEEE Transactions on Smart Grids. He is the editor-in-chief of Smart Grids and Sustainable Energy, published by Springer Nature. He has authored more than 230 scientific publications and collaborates with the Italian Transmission System Operator and major Italian utility companies in the electric power sector.