Additive Manufacturing (AM), a cornerstone of Industry 4.0, is expected to revolutionise production in practically all industries. However, multiple production challenges still exist, preventing its diffusion. In recent years, Machine Learning algorithms have been employed to overcome these hurdles. Nonetheless, the usage of these algorithms is constrained by the scarcity of data together with the challenges associated with accessing and integrating the information generated during the AM pipeline. In this work, we present a vendor-agnostic platform for AM that enables collecting, storing, analysing and linking the heterogeneous data of the complete AM process. We conducted an extensive analysis of the different AM datatypes and identified the most suitable technologies for storing them. Furthermore, we performed an in-depth study of the requirements of different AM stakeholders to develop a rich and intuitive Graphical User Interface. We showcased the specific usage of the platform for Powder Bed Fusion, one of the most popular AM processes, in a real industrial scenario, integrating specific existing modules for in-situ monitoring and real-time defect detection.
A Distributed Software Platform for Additive Manufacturing / FONTANA CRESPO, RAFAEL NATALIO; Cannizzaro, Davide; Bottaccioli, Lorenzo; Macii, Enrico; Patti, Edoardo; DI CATALDO, Santa. - (2023). (Intervento presentato al convegno IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2023) tenutosi a Sinaia, Romania nel 12-15 September 2023) [10.1109/ETFA54631.2023.10275694].
A Distributed Software Platform for Additive Manufacturing
Rafael Natalio Fontana Crespo;Davide Cannizzaro;Lorenzo Bottaccioli;Enrico Macii;Edoardo Patti;Santa Di Cataldo
2023
Abstract
Additive Manufacturing (AM), a cornerstone of Industry 4.0, is expected to revolutionise production in practically all industries. However, multiple production challenges still exist, preventing its diffusion. In recent years, Machine Learning algorithms have been employed to overcome these hurdles. Nonetheless, the usage of these algorithms is constrained by the scarcity of data together with the challenges associated with accessing and integrating the information generated during the AM pipeline. In this work, we present a vendor-agnostic platform for AM that enables collecting, storing, analysing and linking the heterogeneous data of the complete AM process. We conducted an extensive analysis of the different AM datatypes and identified the most suitable technologies for storing them. Furthermore, we performed an in-depth study of the requirements of different AM stakeholders to develop a rich and intuitive Graphical User Interface. We showcased the specific usage of the platform for Powder Bed Fusion, one of the most popular AM processes, in a real industrial scenario, integrating specific existing modules for in-situ monitoring and real-time defect detection.File | Dimensione | Formato | |
---|---|---|---|
Paper_AM_Rafael.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
439.21 kB
Formato
Adobe PDF
|
439.21 kB | Adobe PDF | Visualizza/Apri |
A_Distributed_Software_Platform_for_Additive_Manufacturing.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
1.13 MB
Formato
Adobe PDF
|
1.13 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2982338