Change detection in precision manufacturing processes under transient conditions

Zimo Wang, Satish T.S. Bukkapatnam, Soundar Rajan Tirupatikumara, Zhenyu Kong, Zvi Katz

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

Early detection of changes in transient process behaviors from sensor signals is becoming essential for quality assurance in microelectronics and ultraprecision manufacturing processes. We present a Dirichlet process Gaussian State Machine (DPGSM) representation to capture complex dynamics as a random concatenation of nonlinear stationary segments, and develop a method to detect early-stage fault-inducing changes. Extensive experiments suggest that the present approach, compared to other methods tested, was able to detect slight changes that cause severe surface damage 48 ms earlier in an ultraprecision machining (UPM) process, and at least 2000 ms earlier in a chemical mechanical planarization (CMP) process.

Original languageEnglish (US)
Pages (from-to)449-452
Number of pages4
JournalCIRP Annals - Manufacturing Technology
Volume63
Issue number1
DOIs
StatePublished - Jan 1 2014

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering
  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Change detection in precision manufacturing processes under transient conditions'. Together they form a unique fingerprint.

Cite this