A Two-Step Framework for Predictive Maintenance of Cryogenic Pumps in Semiconductor Manufacturing

Research output: Contribution to conferencePaperpeer-review

37 Downloads (Pure)

Abstract

Semiconductor manufacturing involves many critical steps,
wherein maintaining an ultra-high vacuum is mandatory. To
this end, cryogenic pumps are used to create a controlled
ultra-low-pressure environment through the use of cryogenic
cooling. However, a sudden pump malfunction leads to
contamination in the processing chamber, disrupting
production. The primary focus of this study is preventing
unplanned shutdowns of cryogenic pumps. The data was
collected from various pump sensors also known as status
variable identification (SVID) that reveals current behavior
of the pump. A comprehensive framework is presented here
to develop a condition monitoring and fault detection. In the
proposed framework, a drift detection method is used for
condition monitoring of the pump to locate gradual and
abrupt drifts. Additionally, during regeneration (or
maintenance) phase, intrinsic features are extracted to
distinguish between normal and abnormal regeneration,
achieving an accuracy of 90.91% and a precision of 66.67%.
Utilizing the proposed system, cryo-pump operators can be
given maintenance guidelines and warnings about potential
health degradation of the pumps.
Original languageEnglish
Publication statusAccepted/In press - 22 Jul 2024
Event16th Annual Conference of the Prognostics and Health Management Society - Loews Vanderbilt Hotel, Nashville, United States
Duration: 9 Nov 202414 Nov 2024

Conference

Conference16th Annual Conference of the Prognostics and Health Management Society
Country/TerritoryUnited States
CityNashville
Period9/11/2414/11/24

Keywords

  • Predictive Maintenance
  • Cryogenic Pumps
  • Drift identification
  • Direct ratio estimation
  • novelty detection

Fingerprint

Dive into the research topics of 'A Two-Step Framework for Predictive Maintenance of Cryogenic Pumps in Semiconductor Manufacturing'. Together they form a unique fingerprint.

Cite this