Toward a better monitoring statistic for profile monitoring via variational autoencoders

Nurettin Dorukhan Sergin, Hao Yan

Research output: Contribution to journalArticlepeer-review

Abstract

Variational autoencoders have been recently proposed for the problem of process monitoring. While these works show impressive results over classical methods, the proposed monitoring statistics often ignore the inconsistencies in learned lower-dimensional representations and computational limitations in high-dimensional approximations. In this work, we first manifest these issues and then overcome them with a novel statistic formulation that increases out-of-control detection accuracy without compromising computational efficiency. We demonstrate our results on a simulation study with explicit control over latent variations, and a real-life example of image profiles obtained from a hot steel rolling process.

Original languageEnglish (US)
JournalJournal of Quality Technology
DOIs
StateAccepted/In press - 2021

Keywords

  • Deep learning
  • high-dimensional nonlinear profile
  • latent variable model
  • profile monitoring
  • variational autoencoder

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 'Toward a better monitoring statistic for profile monitoring via variational autoencoders'. Together they form a unique fingerprint.

Cite this