Machine learning can improve the use of process capability data to predict tolerances in blanking and piercing manufacturing processes

Kevin D. Delaney

doi:10.1016/j.rineng.2023.101523

Machine learning can improve the use of process capability data to predict tolerances in blanking and piercing manufacturing processes

Kevin D. Delaney

School of Mechanical Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

Machine Learning (ML) models can be used during the design process to simplify and improve the accuracy of the prediction of manufacturing variation using existing process measurement data stored in a Process Capability DataBase (PCDB). Process Capability Data (PCD) relating to the blanking and piercing of metals using progressive stamping dies is used to demonstrate the technique. Predicted variation values are compared with actual measured variation.

Original language	English
Article number	101523
Journal	Results in Engineering
Volume	20
DOIs	https://doi.org/10.1016/j.rineng.2023.101523
Publication status	Published - Dec 2023

Keywords

Machine learning
PCDB
Process capability data
Variation management

Access to Document

10.1016/j.rineng.2023.101523Licence: CC BY

Cite this

@article{a350eb7e4f01467aae905317125cb402,

title = "Machine learning can improve the use of process capability data to predict tolerances in blanking and piercing manufacturing processes",

abstract = "Machine Learning (ML) models can be used during the design process to simplify and improve the accuracy of the prediction of manufacturing variation using existing process measurement data stored in a Process Capability DataBase (PCDB). Process Capability Data (PCD) relating to the blanking and piercing of metals using progressive stamping dies is used to demonstrate the technique. Predicted variation values are compared with actual measured variation.",

keywords = "Machine learning, PCDB, Process capability data, Variation management",

author = "Delaney, \{Kevin D.\}",

note = "Publisher Copyright: {\textcopyright} 2023 The Author",

year = "2023",

month = dec,

doi = "10.1016/j.rineng.2023.101523",

language = "English",

volume = "20",

journal = "Results in Engineering",

issn = "2590-1230",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Machine learning can improve the use of process capability data to predict tolerances in blanking and piercing manufacturing processes

AU - Delaney, Kevin D.

PY - 2023/12

Y1 - 2023/12

N2 - Machine Learning (ML) models can be used during the design process to simplify and improve the accuracy of the prediction of manufacturing variation using existing process measurement data stored in a Process Capability DataBase (PCDB). Process Capability Data (PCD) relating to the blanking and piercing of metals using progressive stamping dies is used to demonstrate the technique. Predicted variation values are compared with actual measured variation.

AB - Machine Learning (ML) models can be used during the design process to simplify and improve the accuracy of the prediction of manufacturing variation using existing process measurement data stored in a Process Capability DataBase (PCDB). Process Capability Data (PCD) relating to the blanking and piercing of metals using progressive stamping dies is used to demonstrate the technique. Predicted variation values are compared with actual measured variation.

KW - Machine learning

KW - PCDB

KW - Process capability data

KW - Variation management

UR - https://www.scopus.com/pages/publications/85174597186

U2 - 10.1016/j.rineng.2023.101523

DO - 10.1016/j.rineng.2023.101523

M3 - Article

AN - SCOPUS:85174597186

SN - 2590-1230

VL - 20

JO - Results in Engineering

JF - Results in Engineering

M1 - 101523

ER -

Machine learning can improve the use of process capability data to predict tolerances in blanking and piercing manufacturing processes

Abstract

Keywords

Access to Document

Fingerprint

Cite this