@inproceedings{bc732bef1c0349d1b7e3f07e83d3f5a9,
title = "Online predictive maintenance approach for semiconductor equipment",
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.",
keywords = "fault prediction, kernel, predictive maintenance, recursive least square, semiconductor equipment",
author = "Ming Luo and Zhao Xu and Chan, {Hian Leng} and Marjan Alavi",
year = "2013",
doi = "10.1109/IECON.2013.6699718",
language = "英语",
isbn = "9781479902248",
series = "IECON Proceedings (Industrial Electronics Conference)",
pages = "3662--3667",
booktitle = "Proceedings, IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society",
note = "39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013 ; Conference date: 10-11-2013 Through 14-11-2013",
}