Change detection in precision manufacturing processes under transient conditions Academic Article

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. 2014 CIRP.

authors

• Bukkapatnam, Satish

published proceedings

• CIRP ANNALS-MANUFACTURING TECHNOLOGY

author list (cited authors)

• Wang, Z., Bukkapatnam, S., Kumara, S., Kong, Z., & Katz, Z.

citation count

• 29

complete list of authors

• Wang, Zimo||Bukkapatnam, Satish TS||Kumara, Soundar RT||Kong, Zhenyu||Katz, Zvi

publication date

• January 2014

publisher

• Elsevier  Publisher

published in

• CIRP annals  Journal

keywords

• Complex Systems
• Predictive Model
• Quality Assurance

Digital Object Identifier (DOI)

• 10.1016/j.cirp.2014.03.123

start page

• 449

end page

• 452

volume

• 63

issue

• 1

URL

• http%3A%2F%2Fdx.doi.org%2F10.1016%2Fj.cirp.2014.03.123