A Novel Monitoring Strategy Combining the Advantages of NPE and GMM
Semiconductor manufacturing process data usually have multimodel and multiphase characteristics which do not meet the application assumptions in neighborhood preserving embedding (NPE). Aiming at the above limitations of NPE, a novel monitoring strategy combining the advantages of the neighborhood p...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9078081/ |
id |
doaj-82af5647837d43c59f045d72e720f401 |
---|---|
record_format |
Article |
spelling |
doaj-82af5647837d43c59f045d72e720f4012021-03-30T01:43:00ZengIEEEIEEE Access2169-35362020-01-018829898299710.1109/ACCESS.2020.29893409078081A Novel Monitoring Strategy Combining the Advantages of NPE and GMMCheng Zhang0Xunian Dai1https://orcid.org/0000-0001-5351-2972Xiaofang Zheng2Yuan Li3Research Center for Technical Process Fault Diagnosis and Safety, Shenyang University of Chemical Technology, Shenyang, ChinaResearch Center for Technical Process Fault Diagnosis and Safety, Shenyang University of Chemical Technology, Shenyang, ChinaResearch Center for Technical Process Fault Diagnosis and Safety, Shenyang University of Chemical Technology, Shenyang, ChinaResearch Center for Technical Process Fault Diagnosis and Safety, Shenyang University of Chemical Technology, Shenyang, ChinaSemiconductor manufacturing process data usually have multimodel and multiphase characteristics which do not meet the application assumptions in neighborhood preserving embedding (NPE). Aiming at the above limitations of NPE, a novel monitoring strategy combining the advantages of the neighborhood preserving embedding and Gaussian mixture model(NPE-GMM) is proposed. Firstly, the window data are obtained by the default window width. Next, the score of the current window data set are calculated by NPE. After that, some Gaussian components of the score are determined by GMM. Finally, a quantification index is proposed to monitor process status. NPE-GMM can not only maintain more local structure information of the current window data set in the feature subspace, but also reduce the computational complexity of GMM in fault detection processes. By introducing the new statistic, NPE-GMM can effectively improve the fault detection rate of some multimodel batch processes. The effectiveness of the proposed method is verified in a numerical case and the semiconductor etching process. The simulation results indicated that the proposed method has a higher fault detection rate than traditional methods.https://ieeexplore.ieee.org/document/9078081/Batch production systemsfault detectionGaussian mixture modelmultimodelmoving windowneighborhood preserving embedding |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Cheng Zhang Xunian Dai Xiaofang Zheng Yuan Li |
spellingShingle |
Cheng Zhang Xunian Dai Xiaofang Zheng Yuan Li A Novel Monitoring Strategy Combining the Advantages of NPE and GMM IEEE Access Batch production systems fault detection Gaussian mixture model multimodel moving window neighborhood preserving embedding |
author_facet |
Cheng Zhang Xunian Dai Xiaofang Zheng Yuan Li |
author_sort |
Cheng Zhang |
title |
A Novel Monitoring Strategy Combining the Advantages of NPE and GMM |
title_short |
A Novel Monitoring Strategy Combining the Advantages of NPE and GMM |
title_full |
A Novel Monitoring Strategy Combining the Advantages of NPE and GMM |
title_fullStr |
A Novel Monitoring Strategy Combining the Advantages of NPE and GMM |
title_full_unstemmed |
A Novel Monitoring Strategy Combining the Advantages of NPE and GMM |
title_sort |
novel monitoring strategy combining the advantages of npe and gmm |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Semiconductor manufacturing process data usually have multimodel and multiphase characteristics which do not meet the application assumptions in neighborhood preserving embedding (NPE). Aiming at the above limitations of NPE, a novel monitoring strategy combining the advantages of the neighborhood preserving embedding and Gaussian mixture model(NPE-GMM) is proposed. Firstly, the window data are obtained by the default window width. Next, the score of the current window data set are calculated by NPE. After that, some Gaussian components of the score are determined by GMM. Finally, a quantification index is proposed to monitor process status. NPE-GMM can not only maintain more local structure information of the current window data set in the feature subspace, but also reduce the computational complexity of GMM in fault detection processes. By introducing the new statistic, NPE-GMM can effectively improve the fault detection rate of some multimodel batch processes. The effectiveness of the proposed method is verified in a numerical case and the semiconductor etching process. The simulation results indicated that the proposed method has a higher fault detection rate than traditional methods. |
topic |
Batch production systems fault detection Gaussian mixture model multimodel moving window neighborhood preserving embedding |
url |
https://ieeexplore.ieee.org/document/9078081/ |
work_keys_str_mv |
AT chengzhang anovelmonitoringstrategycombiningtheadvantagesofnpeandgmm AT xuniandai anovelmonitoringstrategycombiningtheadvantagesofnpeandgmm AT xiaofangzheng anovelmonitoringstrategycombiningtheadvantagesofnpeandgmm AT yuanli anovelmonitoringstrategycombiningtheadvantagesofnpeandgmm AT chengzhang novelmonitoringstrategycombiningtheadvantagesofnpeandgmm AT xuniandai novelmonitoringstrategycombiningtheadvantagesofnpeandgmm AT xiaofangzheng novelmonitoringstrategycombiningtheadvantagesofnpeandgmm AT yuanli novelmonitoringstrategycombiningtheadvantagesofnpeandgmm |
_version_ |
1724186559766331392 |