Klippel, EmersonOliveira, Ricardo Augusto RabeloMaslov, DmitryBianchi, Andrea Gomes CamposSilva, Saul Emanuel DelabridaGarrocho, Charles Tim Batista2023-07-212023-07-212022KLIPPEL, E. et al. Embedded edge artifcial intelligence for longitudinal rip detection in conveyor belt applied at the industrial mining environment. SN Computer Science, v. 3, n. 280, 2022. Disponível em: <https://link.springer.com/article/10.1007/s42979-022-01169-y>. Acesso em: 06 jul. 2023.2661-8907http://www.repositorio.ufop.br/jspui/handle/123456789/17028The use of deep learning on edge AI to detect failures in conveyor belts solves a complex problem of iron ore benefciation plants. Losses in the order of thousands of dollars are caused by failures in these assets. The existing fault detection systems currently do not have the necessary efciency and complete loss of belts is common. Correct fault detection is necessary to reduce fnancial losses and unnecessary risk exposure by maintenance personnel. This problem is addressed by the present work with the training of a deep learning model for detecting images of failures of the conveyor belt. The resulted model is converted and executed in an edge device located near the conveyor belt to stop it in case a failure is detected. A prototype built and tested in the feld obtained satisfactory results and is shown as the feasibility of using deep learning and edge arti- fcial intelligence in industrial mining environments.en-USrestritoDeep neural networkDevice edgeArtigo publicado em periodicohttps://link.springer.com/article/10.1007/s42979-022-01169-yhttps://doi.org/10.1007/s42979-022-01169-y