RT Journal Article
T1 Towards Zero-Defect Manufacturing Based on Artificial Intelligence through the Correlation of Forces in 5-Axis Milling Process
A1 Cascón-Morán, Itxaso
A1 Gómez, Meritxell
A1 Fernández, David
A1 Gil Del Val, Alain
A1 Alberdi, Nerea
A1 González, Haizea
AB Zero-Defect Manufacturing (ZDM) is a promising strategy for reducing errors in industrial processes, aligned with Industry 4.0 and digitalization, aiming to carry out processes correctly the first time. ZDM relies on digital tools, notably Artificial Intelligence (AI), to predict and prevent issues at both product and process levels. This study’s goal is to significantly reduce errors in machining large parts. It utilizes data from process models and in situ monitoring for AI-driven predictions. AI algorithms anticipate part deformation based on manufacturing data. Mechanistic models simulate milling processes, calculating tool deflection from cutting forces and assessing geometric and dimensional errors. Process monitoring provides real-time data to the models during execution. The research focuses on a high-value component from the oil and gas industry, serving as a test piece to predict geometric errors in machining based on the deviation of cutting forces using AI techniques. Specifically, an AISI 1095 steel forged flange, intentionally misaligned to introduce error, undergoes multiple milling operations, including 3-axis roughing and 5-axis finishing, with 3D scans after each stage to monitor progress and deviations. The work concludes that Support Vector Machine algorithms provide accurate results for the estimation of geometric errors from the machining forces.
SN 2075-1702
YR 2024
FD 2024-04
LK https://hdl.handle.net/11556/4624
UL https://hdl.handle.net/11556/4624
LA eng
NO Cascón-Morán , I , Gómez , M , Fernández , D , Gil Del Val , A , Alberdi , N & González , H 2024 , ' Towards Zero-Defect Manufacturing Based on Artificial Intelligence through the Correlation of Forces in 5-Axis Milling Process ' , Machines , vol. 12 , no. 4 , 226 . https://doi.org/10.3390/machines12040226
NO Publisher Copyright: © 2024 by the authors.
DS TECNALIA Publications
RD 29 jul 2024