Deep multistage multi-task learning for quality prediction of multistage manufacturing systems

Hao Yan, Nurettin Dorukhan Sergin, William A. Brenneman, Stephen Joseph Lange, Shan Ba

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

In multistage manufacturing systems, modeling multiple quality indices based on the process sensing variables is important. However, the classic modeling technique predicts each quality variable one at a time, which fails to consider the correlation within or between stages. We propose a deep multistage multi-task learning framework to jointly predict all output sensing variables in a unified end-to-end learning framework according to the sequential system architecture in the MMS. Our numerical studies and real case study have shown that the new model has a superior performance compared to many benchmark methods as well as great interpretability through developed variable selection techniques.

Original languageEnglish (US)
Pages (from-to)526-544
Number of pages19
JournalJournal of Quality Technology
Volume53
Issue number5
DOIs
StatePublished - 2021

Keywords

  • deep neural network
  • multi-task learning
  • multistage manufacturing process
  • quality prediction

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Deep multistage multi-task learning for quality prediction of multistage manufacturing systems'. Together they form a unique fingerprint.

Cite this