Machine condition monitoring in FDM based on electret microphone, SVM, and neural networks

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorUniversity of Naples Federico II-
Autor(es): dc.contributorUniversidade de São Paulo (USP)-
Autor(es): dc.contributorSão Paulo State Technological College-
Autor(es): dc.creatorLopes, Thiago Glissoi-
Autor(es): dc.creatorAguiar, Paulo Roberto-
Autor(es): dc.creatorMonson, Paulo Monteiro de Carvalho-
Autor(es): dc.creatorD’Addona, Doriana Marilena-
Autor(es): dc.creatorConceição Júnior, Pedro de Oliveira-
Autor(es): dc.creatorde Oliveira Junior, Reinaldo Götz-
Data de aceite: dc.date.accessioned2025-08-21T21:30:07Z-
Data de disponibilização: dc.date.available2025-08-21T21:30:07Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2023-10-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1007/s00170-023-12375-0-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/308332-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/308332-
Descrição: dc.descriptionThe fused deposition modeling (FDM) process, also known as 3D printing, deals with the manufacture of parts by adding layers of fused filament. Research on manufacturing process monitoring is on the rise, with an emphasis on investigating low-cost transducers as substitutes for the traditional, pricier options. The present study addresses a critical gap in the literature concerning the monitoring of the FDM process using acoustic signals from an electret microphone attached to the extruder. By employing an extensive signal processing and feature extraction analysis, including RMS values, ratio of power (ROP), and count statistics, this research uncovers distinguishable patterns in raw signals that relate to different machine conditions such as normal operation, extruder clogging, and filament shortages. Additionally, machine learning algorithms, specifically neural networks and support vector machine (SVM), are utilized to classify these machine conditions. Notably, signal filtering is found to significantly improve the classification models. The spectral analysis further contributes to characterizing the printing process, especially in identifying frequency values associated with defects. In conclusion, the methodology developed in this study holds promise for real-time monitoring systems, as it showcases high accuracy in classifying machine conditions and offers the potential to ensure quality and detect anomalies early in the printing process. Future research is encouraged to refine the methodology and explore its scalability across different FDM systems and materials.-
Descrição: dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionDepartment of Electrical Engineering Faculty of Engineering Sao Paulo State University-UNESP, Sao Paulo-
Descrição: dc.descriptionDepartment of Chemical Materials and Industrial Production Engineering University of Naples Federico II-
Descrição: dc.descriptionDepartment of Electrical and Computer Engineering São Carlos School of Engineering University of São Paulo (USP), São Paulo-
Descrição: dc.descriptionBiomedical Systems São Paulo State Technological College, São Paulo-
Descrição: dc.descriptionDepartment of Electrical Engineering Faculty of Engineering Sao Paulo State University-UNESP, Sao Paulo-
Descrição: dc.descriptionCNPq: 306774/2021-6-
Formato: dc.format1769-1786-
Idioma: dc.languageen-
Relação: dc.relationInternational Journal of Advanced Manufacturing Technology-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subject3D printing-
Palavras-chave: dc.subjectElectret microphone-
Palavras-chave: dc.subjectMonitoring-
Palavras-chave: dc.subjectNeural networks-
Palavras-chave: dc.subjectSignal processing-
Título: dc.titleMachine condition monitoring in FDM based on electret microphone, SVM, and neural networks-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.