Comparison of wind turbine gearbox vibration analysis algorithms based on feature extraction and classification

• Published in: IET renewable power generation Vol. 13; no. 14; pp. 2549 - 2557
• Main Authors: Koukoura, Sofia, Carroll, James, McDonald, Alasdair, Weiss, Stephan
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 28.10.2019
• Subjects: classification accuracy; condition monitoring; costly components; diagnostic algorithms; diagnostic methods; fault diagnosis; feature extraction; gears; health state assessment; healthy operating condition; historic vibration data; maintenance costs; maintenance engineering; mechanical engineering computing; operational wind turbines; pattern recognition; pattern recognition algorithms; popular existing gear; Research Article; vibration condition monitoring; vibration signals; vibrations; vital aspect; wind farm operations; wind power plants; wind turbine components; wind turbine gearbox vibration analysis algorithms; wind turbines; fault diagnosis; wind turbine gearbox vibration analysis algorithms; wind turbine components; health state assessment; maintenance engineering; diagnostic methods; classification accuracy; healthy operating condition; vibration signals; popular existing gear; wind farm operations; feature extraction; vital aspect; wind power plants; vibrations; gears; pattern recognition; diagnostic algorithms; operational wind turbines; mechanical engineering computing; costly components; condition monitoring; wind turbines; pattern recognition algorithms; historic vibration data; maintenance costs; vibration condition monitoring
• ISSN: 1752-1416; 1752-1424; 1752-1424
• DOI: 10.1049/iet-rpg.2018.5313

Health state assessment of wind turbine components has become a vital aspect of wind farm operations in order to reduce maintenance costs. The gearbox is one of the most costly components to replace and it is usually monitored through vibration condition monitoring. This study aims to present a review of the most popular existing gear vibration diagnostic methods. Features are extracted from the vibration signals based on each method and are used as input in pattern recognition algorithms. Classification of each signal is achieved based on its health state. This is demonstrated in a case study using historic vibration data acquired from operational wind turbines. The data collection starts from a healthy operating condition and leads towards a gear failure. The results of various diagnostic algorithms are compared based on their classification accuracy.