IoT-Driven Deep Learning for Enhanced Industrial Production Forecasting

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade de São Paulo (USP)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorPolitecnico Di Torino-
Autor(es): dc.creatorAugusto David, Gabriel-
Autor(es): dc.creatorMonteiro De Carvalho Monson, Paulo-
Autor(es): dc.creatorSoares Junior, Cristiano-
Autor(es): dc.creatorDe Oliveira Conceicao Junior, Pedro-
Autor(es): dc.creatorRoberto De Aguiar, Paulo-
Autor(es): dc.creatorSimeone, Alessandro-
Data de aceite: dc.date.accessioned2025-08-21T18:18:57Z-
Data de disponibilização: dc.date.available2025-08-21T18:18:57Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2023-12-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/JIOT.2024.3447579-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/306673-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/306673-
Descrição: dc.descriptionIndustrial demand forecasting is crucial for managing stock levels, financial revenue projections, logistics, and efficient production operations. However, there are notable gaps in the literature, particularly in the research that explores the potential of intelligent monitoring systems using Internet of Things (IoT) devices in combination with industrial production forecasting algorithms. This gap is particularly evident in scenarios characterized by seasonal data and limited historical samples. This research work presents an affordable method for monitoring and forecasting industrial production demand, which involves developing an IoT device and applying deep learning algorithms to an industrial production line. In the proposed methodology, an edge device, known as a datalogger, collects and transmits production data to a cloud server obtained through photoelectric laser beam sensors and the programmable logic computer of a filling machine. The data is subsequently retrieved from the cloud database for analysis and production demand forecasting. This work compares the performance of three distinct neural networks - long short-term memory, gated recurrent unit, and sample convolution and interaction network (SCINet) - in the context of time series forecasting. The evaluation employs metrics, such as root mean-squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Through this framework, it was possible to achieve to forecast production demand with error rates of 9.08 (RMSE), 7.67 (MAE), and 1.86 (MAPE), due to the SCINet neural network, even in scenarios with seasonal samples and limited historical data from an industrial filling line.-
Descrição: dc.descriptionUniversity Of São Paulo (EESC-USP) Department Of Electrical And Computer Engineering-
Descrição: dc.descriptionSão Paulo State University Department Of Electrical Engineering-
Descrição: dc.descriptionPolitecnico Di Torino Department Of Management And Production Engineering-
Descrição: dc.descriptionSão Paulo State University Department Of Electrical Engineering-
Formato: dc.format38486-38495-
Idioma: dc.languageen-
Relação: dc.relationIEEE Internet of Things Journal-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectDeep learning (DL)-
Palavras-chave: dc.subjectforecasting-
Palavras-chave: dc.subjectIndustrial Internet of Things (IIoT)-
Palavras-chave: dc.subjectsample convolution and interaction network (SCINet)-
Palavras-chave: dc.subjecttime-series-
Título: dc.titleIoT-Driven Deep Learning for Enhanced Industrial Production Forecasting-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.