Metamodelagem para análise térmica no torneamento com ferramenta de aço rápido usando redes LSTM
Nenhuma Miniatura disponível
Data
2024-12-13
Autores
Santos, Hugo dos Anjos
Título da Revista
ISSN da Revista
Título de Volume
Editor
Universidade Federal do Espírito Santo
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.
Descrição
Palavras-chave
Metamodelagem , Processo de torneamento , Previsão de temperatura