Metamodelagem para análise térmica no torneamento com ferramenta de aço rápido usando redes LSTM
Ano de defesa: | 2024 |
---|---|
Autor(a) principal: | |
Orientador(a): | |
Banca de defesa: | |
Tipo de documento: | Dissertação |
Tipo de acesso: | Acesso aberto |
Idioma: | por |
Instituição de defesa: |
Universidade Federal do Espírito Santo
BR Mestrado em Engenharia Mecânica Centro Tecnológico UFES Programa de Pós-Graduação em Engenharia Mecânica |
Programa de Pós-Graduação: |
Não Informado pela instituição
|
Departamento: |
Não Informado pela instituição
|
País: |
Não Informado pela instituição
|
Palavras-chave em Português: | |
Link de acesso: | http://repositorio.ufes.br/handle/10/18334 |
Resumo: | The prediction of temperature distribution during the turning process is essential for optimizing machining operations and extending tool life. This study investigates the application of LSTM neural networks to model the temperature field in turning operations using high-speed steel tools. The research compares numerical simulations conducted with ANSYS® software against simulated data generated by the software, enabling a comprehensive analysis of heat transfer mechanisms. The results reveal that the LSTM neural network is highly effective, achieving low root mean square error (RMSE) values and processing data more efficiently compared to traditional numerical methods. This dissertation proposes a metamodel that maintains prediction accuracy while significantly reducing computational costs compared to conventional simulations. This approach has the potential to enhance thermal monitoring in industrial processes, optimizing production and improving machining quality. Additionally, the study contributes to Sustainable Development Goal (SDG) No. 9 – Industry, Innovation, and Infrastructure – by promoting innovative technologies that strengthen industrial competitiveness and sustainability. |