Publicação

A Plataform for Sharing Knowledge in Projects With Superconductors

Ver documento

Detalhes bibliográficos
Resumo:The dependency on electrical energy is increasing every year, without any sign of slowing down, worsening the changes in the climate. A more efficient way to combat energy losses and increase energy efficiency comes through the introduction of High Temperatures Superconductors (HTS) in the construction of electrical transformers. Unfortunately, there is still no platform that can process data from experiments with the material used in transformers. No previous work has been done to create a platform that integrates the ability to collect data and process it. The existing platforms operate separately and do not address HTS in transformers. In this thesis, a web application was developed to collect, share and process data from HTS materials used in electrical transformer experiments. To develop such a web application, it was necessary to create the front and back end of the application with intuitive user interfaces, as it was necessary to integrate Data Science methods, mainly Machine Learning to obtain patterns from the collected data. This work is expected to improve HTS technology in electrical transformers and the ability to share these same improvements with the community.
Autores principais:Vieira, Miguel Rebelo
Assunto:Data Science Machine Learning Web Application High Temperature Superconductors
Ano:2022
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
Descrição
Resumo:The dependency on electrical energy is increasing every year, without any sign of slowing down, worsening the changes in the climate. A more efficient way to combat energy losses and increase energy efficiency comes through the introduction of High Temperatures Superconductors (HTS) in the construction of electrical transformers. Unfortunately, there is still no platform that can process data from experiments with the material used in transformers. No previous work has been done to create a platform that integrates the ability to collect data and process it. The existing platforms operate separately and do not address HTS in transformers. In this thesis, a web application was developed to collect, share and process data from HTS materials used in electrical transformer experiments. To develop such a web application, it was necessary to create the front and back end of the application with intuitive user interfaces, as it was necessary to integrate Data Science methods, mainly Machine Learning to obtain patterns from the collected data. This work is expected to improve HTS technology in electrical transformers and the ability to share these same improvements with the community.