The increasing popularity of additive manufacturing (AM) is pushing the industry to provide new solutions to improve the process stability. In the past, process monitoring and control has proved to be a fundamental tool to enhance the repeatability of many manufacturing processes, however the typical AM fast dynamics require a high spatiotemporal resolution data flow to accurately describe the process and these new types of data are presenting new challenges for standard statistical process monitoring (SPM) techniques. In this work, the capabilities of a new machine learning (ML) based framework for the detection of cooling rate-related defects in metal additive manufacturing processes via in-situ high-speed cameras are presented and discussed.
A new method for in-situ process monitoring of AM cooling rate-related defects
Bugatti M.;Colosimo B. M.
2021-01-01
Abstract
The increasing popularity of additive manufacturing (AM) is pushing the industry to provide new solutions to improve the process stability. In the past, process monitoring and control has proved to be a fundamental tool to enhance the repeatability of many manufacturing processes, however the typical AM fast dynamics require a high spatiotemporal resolution data flow to accurately describe the process and these new types of data are presenting new challenges for standard statistical process monitoring (SPM) techniques. In this work, the capabilities of a new machine learning (ML) based framework for the detection of cooling rate-related defects in metal additive manufacturing processes via in-situ high-speed cameras are presented and discussed.File | Dimensione | Formato | |
---|---|---|---|
A new method for in-situ process monitoring of AM cooling rate-related defects.pdf
accesso aperto
:
Publisher’s version
Dimensione
1.02 MB
Formato
Adobe PDF
|
1.02 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.