An intelligent system for harmonic distortions detection in wind generator power electronic devices

NEUROCOMPUTING

卷:456

Article

Jove, Esteban¹  Manuel Gonzalez-Cava, Jose²  Casteleiro-Roca, Jose-Luis¹  Alaiz-Moreton, Hector³  Baruque, Bruno⁴  Leitao, Paulo^5,6  Mendez Perez, Juan Albino²  Luis Calvo-Rolle, Jose¹ 

[1] Univ A Coruna, Dept Ind Engn, CTC, CITIC Avda,19 Febrero S-N, Ferrol 15405, A Coruna, Spain

[2] Univ La Laguna, Dept Comp Sci & Syst Engn, Avda Astrofis Francisco Sanchez S-N, San Cristobal la Laguna 38200, Spain

[3] Univ Leon, Dept Ingn Elect & Sistemas & Automat, Edificio Tecnol,Campus Vegazana S-N, Leon 24071, Spain

[4] Univ Burgos, Dept Ingn Civil, Calle Francisco de Vitoria S-N, Burgos 09006, Spain

[5] Polytech Inst Braganca, CeDRI Res Ctr Digitalizat & Intelligent Robot, Porta, Portugal

[6] INESC TEC, Porta, Portugal

关键词: Energy efficiency;    Wind generator;    One-class;    Outlier detection;   

DOI  :  10.1016/j.neucom.2020.07.155

来源: Elsevier

【 摘 要 】

The high concern about climate change has boosted the promotion of renewable energy systems, being the wind power one of the key generation possibilities in this field. In this context, with the aim of ensuring the energy efficiency, the present work deals with the fault detection in the power electronic circuits of a wind generator system placed in a bioclimatic house. To do so, different outliers that emulate harmonic distortion appearance are tested. To implement a system capable of detecting this anomalous situations, six different one-class techniques are used, whose performance is thoroughly analyzed, offering interesting performance. (c) 2021 Elsevier B.V. All rights reserved.

【 授权许可】

Free