2024PHM 半导体制造中低温泵预测性维护的两步框架

ID:72701

阅读量:1

大小:0.60 MB

页数:5页

时间:2025-01-03

金币:1

上传者:神经蛙1号
1
A Two-Step Framework for Predictive Maintenance of Cryogenic
Pumps in Semiconductor Manufacturing
Sanjoy Kumar Saha
1
, M.M. Manjurul Islam
1
, Shaun McFadden
1
, Saugat Bhattacharyya
1
, Mark Gorman
2
and Girijesh Prasad
1
1
Intelligent Systems Research Centre, Ulster University, Londonderry, BT48 7JL, UK
saha-sk@ulster.ac.uk
g.prasad@ulster.ac.uk
2
Seagate Technology, Londonderry, Northern Ireland, BT48 0BF, UK
mark.gorman@seagate.com
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.
1. INTRODUCTION
Continuous operation of pumps ensures precise and high-
quality production of semiconductors. A typical fabrication
facility employs hundreds of pumps, from cryogenic to water
pumps, within the clean room. Cryogenic pumps operate at
fast pumping rates and very low pressure (10
-10
torr). These
pumps use helium as a coolant gas in two refrigeration stages.
The first stage usually operates at 100 K(-173
o
C) followed by
a second stage, operating roughly at 10 K (-263
0
C) to 12 K
(265
0
C). In the first stage, water vapor is trapped, while in the
second stage, gases such as nitrogen (N
2
) and hydrogen (H
2
)
are cryogenically condensed from the process chamber
(Collart et al., 2022a).
Within a process tool a group of four to six on-board
cryopumps for each chamber are connected to a common
compressor that services the connected cryopumps. Two
types of operationsetching and depositionare commonly
performed within these chambers. The cryogenic pump
requires a maintenance procedure known as regeneration that
routinely removes the solid deposits from the cryogenically
cooled stages and allows the pump to operate optimally.
Additionally, a regeneration process typically consists of
three stages: i) the warm-up stage, where the temperature is
raised to approximately 320K, ii) the steady stage, during
which gases are extracted using a roughing pump, and iii) the
cooldown stage, where a cooling medium, such as liquid
helium, is used to bring the system down to operational
temperatures. Moreover, a regeneration can be classified into
short or long regeneration based on time.
2. PROBLEM STATEMENT
In semiconductor manufacturing facilities, process tools are
kept isolated from the surrounding environment. In such
facilities, smart manufacturing can reduce risk and
uncertainty by setting priorities and coordinating
maintenance (Abdallah et al., 2023). Consider a typical
scenario within a cryo-pump, where from captured gases
escape, due to an unforeseen malfunction, leading to
contamination in the process chamber. Additionally, wafer
scrap could happen when implant dose mistakes and ion
beam neutralization are brought on by elevated chamber
pressure. This elevated pressure is a consequence of a
malfunctioning cryo-pump. This situation leads to an
unscheduled downtime that causes financial loss. The
utilization of health monitoring and the conversion of
Sanjoy Kumar Saha et al. This is an open-access article distributed under
the terms of the Creative Commons Attribution 3.0 United States License,
which permits unrestricted use, distribution, and reproduction in any
medium, provided the original author and source are credited.
资源描述:

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。
关闭