TY - JOUR
T1 - AutoML-driven diagnostics of the feeder motor in fused filament fabrication machines from direct current signals
AU - Rooney, Sean
AU - Pitz, Emil
AU - Pochiraju, Kishore
N1 - Publisher Copyright:
© The Author(s) 2024.
PY - 2024
Y1 - 2024
N2 - Part defects in additive manufacturing are more frequent compared to machining or molding. Failures can go unnoticed for hours, wasting resources and extending process cycle times. This paper describes a Machine Learning based method for automated sensing of onset failure in additive manufacturing machinery. Investigations are conducted on a Fused Filament Fabrication (FFF) 3D printer, and the same methods are then applied to a digital light processing 3D printer. The investigation focuses on signal-based analysis, specifically passive sensing of stepper motors relating DC current measurements to the torque on a stepper, as opposed to any active acoustic interrogation of the part. Passive methods are used to characterize the loading on a feeder stepper in an FFF machine, forming a model that can identify early signs of filament-based failure with 85.65% 10-fold cross-validation accuracy. Efforts show filament breakage can be detected minutes before material runout would cause a defect, allowing ample time to pause, correct, or control the print. The machine learning pipeline was not naively conceived but optimized through automated machine learning.
AB - Part defects in additive manufacturing are more frequent compared to machining or molding. Failures can go unnoticed for hours, wasting resources and extending process cycle times. This paper describes a Machine Learning based method for automated sensing of onset failure in additive manufacturing machinery. Investigations are conducted on a Fused Filament Fabrication (FFF) 3D printer, and the same methods are then applied to a digital light processing 3D printer. The investigation focuses on signal-based analysis, specifically passive sensing of stepper motors relating DC current measurements to the torque on a stepper, as opposed to any active acoustic interrogation of the part. Passive methods are used to characterize the loading on a feeder stepper in an FFF machine, forming a model that can identify early signs of filament-based failure with 85.65% 10-fold cross-validation accuracy. Efforts show filament breakage can be detected minutes before material runout would cause a defect, allowing ample time to pause, correct, or control the print. The machine learning pipeline was not naively conceived but optimized through automated machine learning.
KW - Additive manufacturing
KW - Machine learning
KW - Non-destructive evaluation
UR - http://www.scopus.com/inward/record.url?scp=85188254269&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85188254269&partnerID=8YFLogxK
U2 - 10.1007/s10845-024-02332-3
DO - 10.1007/s10845-024-02332-3
M3 - Article
AN - SCOPUS:85188254269
SN - 0956-5515
JO - Journal of Intelligent Manufacturing
JF - Journal of Intelligent Manufacturing
ER -