Machine learning methods for wind turbine condition monitoring: A review

RENEWABLE ENERGY

卷:133

Review

Stetco, Adrian¹  Dinmohammadi, Fateme²  Zhao, Xingyu²  Robu, Valentin²  Flynn, David²  Barnes, Mike³  Keane, John¹  Nenadic, Goran¹ 

[1] Univ Manchester, Sch Comp Sci, Manchester, Lancs, England

[2] Heriot Watt Univ, Sch Engn & Phys Sci, Edinburgh, Midlothian, Scotland

[3] Univ Manchester, Sch Elect & Elect Engn, Manchester, Lancs, England

关键词: Renewable energy;    Wind farms;    Condition monitoring;    Machine learning;    Prognostic maintenance;   

DOI  :  10.1016/j.renene.2018.10.047

来源: Elsevier

【 摘 要 】

This paper reviews the recent literature on machine learning (ML) models that have been used for condition monitoring in wind turbines (e.g. blade fault detection or generator temperature monitoring). We classify these models by typical ML steps, including data sources, feature selection and extraction, model selection (classification, regression), validation and decision-making. Our findings show that most models use SCADA or simulated data, with almost two-thirds of methods using classification and the rest relying on regression. Neural networks, support vector machines and decision trees are most commonly used. We conclude with a discussion of the main areas for future work in this domain. (C) 2018 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licensesiby/4.0/).

【 授权许可】

Free