Online predictive maintenance approach for semiconductor equipment

Ming Luo, Zhao Xu, Hian Leng Chan, Marjan Alavi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Scopus citations

Abstract

In this paper, an online predictive maintenance approach is proposed for monitoring health of semiconductor equipment. It includes two phases, the first is online prediction of the health indicator and the second phase is the classification of the indicator to one of the health states for making maintenance decisions. Kernel recursive least square (KRLS) algorithm is used for online prediction which is computational efficient. The health states of the equipment can be defined based on the requirement specification for the equipment maintenance. The classification is used in the second stage based on the prediction results come from the first stage. The approach is tested with a simulated dataset from a semiconductor tool and results show a relative high accuracy can be achieved with a satisfactory computational efficiency.

Original languageEnglish
Title of host publicationProceedings, IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society
Pages3662-3667
Number of pages6
DOIs
StatePublished - 2013
Externally publishedYes
Event39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013 - Vienna, Austria
Duration: 10 Nov 201314 Nov 2013

Publication series

NameIECON Proceedings (Industrial Electronics Conference)

Conference

Conference39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013
Country/TerritoryAustria
CityVienna
Period10/11/1314/11/13

Keywords

  • fault prediction
  • kernel
  • predictive maintenance
  • recursive least square
  • semiconductor equipment

Cite this