Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework

Global warming has alerted the international community to the need to of renewable and clean energy sources in the generation of electricity. In this scenario, wind energy is expanding. As this source depends on a central equipment, the wind turbine, its operation and maintenance are fundamental for...

ver descrição completa

Na minha lista:

Detalhes bibliográficos
Autor principal:	Souza, Mateus Guilherme Melo de
Outros Autores:	Gonzalez, Mario Orestes Aguirre
Formato:	Dissertação
Idioma:	pt_BR
Publicado em:	Universidade Federal do Rio Grande do Norte
Assuntos:	Artificial intelligence Operation and maintenance Systematic literature review ANN LSTM
Endereço do item:	https://repositorio.ufrn.br/handle/123456789/46814
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!

id	ri-123456789-46814
record_format	dspace
institution	Repositório Institucional
collection	RI - UFRN
language	pt_BR
topic	Artificial intelligence Operation and maintenance Systematic literature review ANN LSTM
spellingShingle	Artificial intelligence Operation and maintenance Systematic literature review ANN LSTM Souza, Mateus Guilherme Melo de Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework
description	Global warming has alerted the international community to the need to of renewable and clean energy sources in the generation of electricity. In this scenario, wind energy is expanding. As this source depends on a central equipment, the wind turbine, its operation and maintenance are fundamental for the viability of the business and, therefore, the application of technologies, such as Artificial Intelligence, can improve the competitiveness of the sector. The objective of this study is to present a framework for the application of Artificial Intelligence in the operation and maintenance of wind farms. For this, theoretical and field research were carried out. The theoretical research complemented a traditional literature review and a systematic literature review. State-of-the-art was identified through the analysis of 51 articles obtained from the Periodicos Capes Platform. The research identified the equipment studied, data, methods and metrics adopted in the application of AI. The field research was carried out by applying the framework to a wind farm, simulating an application of condition monitoring for bearings through the modelling of its temperature using SCADA data. Three neural networks models were tested: Feedforward Neural Network, Autoregressive Neural Network and Long ShortTerm Memory (LSTM). The LSTM model presented the best performance among the tested algorithms, even when compared to other studies, which shows that it can be used for this type of application. The proposed framework is composed by four macro-steps: Selecting application, data preparation, model development and evaluation of results.
author2	Gonzalez, Mario Orestes Aguirre
author_facet	Gonzalez, Mario Orestes Aguirre Souza, Mateus Guilherme Melo de
format	masterThesis
author	Souza, Mateus Guilherme Melo de
author_sort	Souza, Mateus Guilherme Melo de
title	Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework
title_short	Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework
title_full	Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework
title_fullStr	Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework
title_full_unstemmed	Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework
title_sort	aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework
publisher	Universidade Federal do Rio Grande do Norte
publishDate	2022
url	https://repositorio.ufrn.br/handle/123456789/46814
work_keys_str_mv	AT souzamateusguilhermemelode aplicationofartificialintelligenceforwindturbineoperationandmaintenanceproposalofframework
_version_	1773966991612182528
spelling	ri-123456789-468142022-05-02T15:30:27Z Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework Souza, Mateus Guilherme Melo de Gonzalez, Mario Orestes Aguirre http://lattes.cnpq.br/8572625074313146 http://lattes.cnpq.br/5936291138113637 Costa, José Alfredo Ferreira http://lattes.cnpq.br/9745845064013172 Rufato Júnior, Eloi Andrade, Humberto Dionísio de http://lattes.cnpq.br/1253785596446469 Artificial intelligence Operation and maintenance Systematic literature review ANN LSTM Global warming has alerted the international community to the need to of renewable and clean energy sources in the generation of electricity. In this scenario, wind energy is expanding. As this source depends on a central equipment, the wind turbine, its operation and maintenance are fundamental for the viability of the business and, therefore, the application of technologies, such as Artificial Intelligence, can improve the competitiveness of the sector. The objective of this study is to present a framework for the application of Artificial Intelligence in the operation and maintenance of wind farms. For this, theoretical and field research were carried out. The theoretical research complemented a traditional literature review and a systematic literature review. State-of-the-art was identified through the analysis of 51 articles obtained from the Periodicos Capes Platform. The research identified the equipment studied, data, methods and metrics adopted in the application of AI. The field research was carried out by applying the framework to a wind farm, simulating an application of condition monitoring for bearings through the modelling of its temperature using SCADA data. Three neural networks models were tested: Feedforward Neural Network, Autoregressive Neural Network and Long ShortTerm Memory (LSTM). The LSTM model presented the best performance among the tested algorithms, even when compared to other studies, which shows that it can be used for this type of application. The proposed framework is composed by four macro-steps: Selecting application, data preparation, model development and evaluation of results. Conselho Nacional de Desenvolvimento Científico e Tecnológico - CNPq O aquecimento global alertou à comunidade internacional da necessidade de uso de fontes renováveis e limpas na geração de energia elétrica. Nesse cenário, a energia eólica se encontra em expansão. Como essa fonte de geração depende de um equipamento central, o aerogerador, a sua operação e manutenção é fundamental para a viabilidade do negócio, e por isso, a aplicação de novas tecnologias, como a Inteligência Artificial, pode trazer maior competitividade do setor. O objetivo do estudo é apresentar um framework para a aplicação de Inteligência Artificial na operação e manutenção de parques eólicos. Para tanto, foi realizada uma pesquisa teórica e de campo. A pesquisa teórica considerou uma revisão tradicional da literatura e uma revisão bibliográfica sistemática. O estado da arte foi identificado pela análise detalhada de 51 artigos obtidos na Plataforma Periódicos da Capes. Foram identificados os equipamentos estudados, métodos e métricas adotadas e etapas da aplicação da IA. A pesquisa de campo foi realizada pela aplicação do framework em um parque eólico, mediante a simulação de uma aplicação de monitoramento da condição de rolamentos através da modelagem da temperatura, mediante dados SCADA. Três modelos de redes neurais foram testados: Rede Neural Feedforward, Rede Neural Autorregressiva e Long Short-Term Memory O modelo de Long Short-Term Memory apresentou a melhor performance dentre os algoritmos testados, mesmo quando comparado com outros estudos, o que mostra que ele pode ser usado para esse tipo de aplicação. O framework proposto é dividido em quatro macro-etapas: Seleção da aplicação, preparação de dados, desenvolvimento do modelo e avaliação de resultados. 2022-04-05T22:54:29Z 2022-04-05T22:54:29Z 2020-12-17 masterThesis SOUZA, Mateus Guilherme Melo de. Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework. 2020. 94f. Dissertação (Mestrado em Engenharia de Produção) - Centro de Tecnologia, Universidade Federal do Rio Grande do Norte, Natal, 2020. https://repositorio.ufrn.br/handle/123456789/46814 pt_BR Acesso Aberto application/pdf Universidade Federal do Rio Grande do Norte Brasil UFRN PROGRAMA DE PÓS-GRADUAÇÃO EM ENGENHARIA DE PRODUÇÃO

Aplication of artificial intelligence for wind turbine operation and maintenance: proposal of framework

Registros relacionados