Article: Wind turbine fault detection: a semi-supervised learning approach with two different dimensionality reduction techniques Journal: International Journal of Innovative Computing and Applications (IJICA) 2023 Vol.14 No.1/2 pp.67 - 77 Abstract: The quest to save the environment has led many countries to change their mix of energy sources, with most countries focusing on wind energy. Since wind turbines are at the centre of this revolution, ensuring their continuous operation free of faults is a key to success. Towards that end, making use live operational signals from the turbine, various data-driven methods for fault prediction using traditional machine learning have been proposed. This work adopts a novel, automatic, end-to-end AutoML approach covering aspects from features and hyperparameters selection to fault prediction using semi-supervised support vector machines guided by the multi-objective optimisation framework non-dominated sorting genetic algorithm II (NSGA-II). Experiments were carried out using a dataset containing unlabelled records of five 2.0 MW wind turbines. We found that our AutoML approach using NSGA-II for feature selection offers up to 9% improvement in solution quality over the state-of-the-art while being fully automated and requiring no costly and time-consuming feature engineering. Inderscience Publishers - linking academia, business and industry through research

Title: Wind turbine fault detection: a semi-supervised learning approach with two different dimensionality reduction techniques

Authors: Fernando P.G. de Sá; Rafaelli de C. Coutinho; Eduardo Ogasawara; Diego Brandão; Rodrigo F. Toso

Addresses: Programa de Pós-Graduação em Ciência da Computação, CEFET/RJ, Rio de Janeiro, RJ, Brazil ' Programa de Pós-Graduação em Ciência da Computação, CEFET/RJ, Rio de Janeiro, RJ, Brazil ' Programa de Pós-Graduação em Ciência da Computação, CEFET/RJ, Rio de Janeiro, RJ, Brazil ' Programa de Pós-Graduação em Ciência da Computação, CEFET/RJ, Rio de Janeiro, RJ, Brazil ' Microsoft AI & Research, 555 110th Ave NE, Bellevue, WA, 98004, USA

Abstract: The quest to save the environment has led many countries to change their mix of energy sources, with most countries focusing on wind energy. Since wind turbines are at the centre of this revolution, ensuring their continuous operation free of faults is a key to success. Towards that end, making use live operational signals from the turbine, various data-driven methods for fault prediction using traditional machine learning have been proposed. This work adopts a novel, automatic, end-to-end AutoML approach covering aspects from features and hyperparameters selection to fault prediction using semi-supervised support vector machines guided by the multi-objective optimisation framework non-dominated sorting genetic algorithm II (NSGA-II). Experiments were carried out using a dataset containing unlabelled records of five 2.0 MW wind turbines. We found that our AutoML approach using NSGA-II for feature selection offers up to 9% improvement in solution quality over the state-of-the-art while being fully automated and requiring no costly and time-consuming feature engineering.

Keywords: feature selection; fault detection; wind turbine; semi-supervised learning.

DOI: 10.1504/IJICA.2023.129359

International Journal of Innovative Computing and Applications, 2023 Vol.14 No.1/2, pp.67 - 77

Received: 15 Sep 2020
Accepted: 16 Mar 2021
Published online: 07 Mar 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Wind turbine fault detection: a semi-supervised learning approach with two different dimensionality reduction techniques

Keep up-to-date