Preliminary study of advanced fault detection scheme

Yu Hsuan Shih, Yi Ting Huang, Fan-Tien Cheng

研究成果: Conference contribution

摘要

In high-tech plants, the manufacturing stability and product quality are monitored through periodic sampling. As for those non-sampled workpieces, their quality is commonly monitored by a fault detection and classification (FDC) method. Nevertheless, it may fail to detect out-of-control (OOC) products if their corresponding manufacturing process parameters are all in-spec. In other words, unless those certain defected workpieces are selected for sampling measurements, they may not be detected through simply monitoring all the individual manufacturing process parameters. We have proposed a product quality fault detection scheme (FDS), which utilizes the classification and regression tree (CART) to build a single failure model (FML) for identifying the relationship between process parameters and OOC products. However, all the failure modes (FMs) are contained in the single FML, which makes it difficult to understand the causes of defected products. To remedy this problem, this paper develops an advanced fault detection scheme (AFDS). The AFDS builds the corresponding FM by CART for each individual failure cause and generates a FM manager via support vector machine (SVM) to manage all the FMs. Finally, the dual-phase concept is adopted to run the AFDS for achieving on-line real-time fault detection.

原文English
主出版物標題2013 IEEE International Conference on Robotics and Automation, ICRA 2013
頁面3561-3566
頁數6
DOIs
出版狀態Published - 2013 十一月 14
事件2013 IEEE International Conference on Robotics and Automation, ICRA 2013 - Karlsruhe, Germany
持續時間: 2013 五月 62013 五月 10

出版系列

名字Proceedings - IEEE International Conference on Robotics and Automation
ISSN(列印)1050-4729

Other

Other2013 IEEE International Conference on Robotics and Automation, ICRA 2013
國家Germany
城市Karlsruhe
期間13-05-0613-05-10

指紋

Fault detection
Failure modes
Sampling
Support vector machines
Managers
Monitoring

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

引用此文

Shih, Y. H., Huang, Y. T., & Cheng, F-T. (2013). Preliminary study of advanced fault detection scheme. 於 2013 IEEE International Conference on Robotics and Automation, ICRA 2013 (頁 3561-3566). [6631076] (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2013.6631076
Shih, Yu Hsuan ; Huang, Yi Ting ; Cheng, Fan-Tien. / Preliminary study of advanced fault detection scheme. 2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. 頁 3561-3566 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{398442b69aaf401b987d7f5510509c1e,
title = "Preliminary study of advanced fault detection scheme",
abstract = "In high-tech plants, the manufacturing stability and product quality are monitored through periodic sampling. As for those non-sampled workpieces, their quality is commonly monitored by a fault detection and classification (FDC) method. Nevertheless, it may fail to detect out-of-control (OOC) products if their corresponding manufacturing process parameters are all in-spec. In other words, unless those certain defected workpieces are selected for sampling measurements, they may not be detected through simply monitoring all the individual manufacturing process parameters. We have proposed a product quality fault detection scheme (FDS), which utilizes the classification and regression tree (CART) to build a single failure model (FML) for identifying the relationship between process parameters and OOC products. However, all the failure modes (FMs) are contained in the single FML, which makes it difficult to understand the causes of defected products. To remedy this problem, this paper develops an advanced fault detection scheme (AFDS). The AFDS builds the corresponding FM by CART for each individual failure cause and generates a FM manager via support vector machine (SVM) to manage all the FMs. Finally, the dual-phase concept is adopted to run the AFDS for achieving on-line real-time fault detection.",
author = "Shih, {Yu Hsuan} and Huang, {Yi Ting} and Fan-Tien Cheng",
year = "2013",
month = "11",
day = "14",
doi = "10.1109/ICRA.2013.6631076",
language = "English",
isbn = "9781467356411",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
pages = "3561--3566",
booktitle = "2013 IEEE International Conference on Robotics and Automation, ICRA 2013",

}

Shih, YH, Huang, YT & Cheng, F-T 2013, Preliminary study of advanced fault detection scheme. 於 2013 IEEE International Conference on Robotics and Automation, ICRA 2013., 6631076, Proceedings - IEEE International Conference on Robotics and Automation, 頁 3561-3566, 2013 IEEE International Conference on Robotics and Automation, ICRA 2013, Karlsruhe, Germany, 13-05-06. https://doi.org/10.1109/ICRA.2013.6631076

Preliminary study of advanced fault detection scheme. / Shih, Yu Hsuan; Huang, Yi Ting; Cheng, Fan-Tien.

2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. p. 3561-3566 6631076 (Proceedings - IEEE International Conference on Robotics and Automation).

研究成果: Conference contribution

TY - GEN

T1 - Preliminary study of advanced fault detection scheme

AU - Shih, Yu Hsuan

AU - Huang, Yi Ting

AU - Cheng, Fan-Tien

PY - 2013/11/14

Y1 - 2013/11/14

N2 - In high-tech plants, the manufacturing stability and product quality are monitored through periodic sampling. As for those non-sampled workpieces, their quality is commonly monitored by a fault detection and classification (FDC) method. Nevertheless, it may fail to detect out-of-control (OOC) products if their corresponding manufacturing process parameters are all in-spec. In other words, unless those certain defected workpieces are selected for sampling measurements, they may not be detected through simply monitoring all the individual manufacturing process parameters. We have proposed a product quality fault detection scheme (FDS), which utilizes the classification and regression tree (CART) to build a single failure model (FML) for identifying the relationship between process parameters and OOC products. However, all the failure modes (FMs) are contained in the single FML, which makes it difficult to understand the causes of defected products. To remedy this problem, this paper develops an advanced fault detection scheme (AFDS). The AFDS builds the corresponding FM by CART for each individual failure cause and generates a FM manager via support vector machine (SVM) to manage all the FMs. Finally, the dual-phase concept is adopted to run the AFDS for achieving on-line real-time fault detection.

AB - In high-tech plants, the manufacturing stability and product quality are monitored through periodic sampling. As for those non-sampled workpieces, their quality is commonly monitored by a fault detection and classification (FDC) method. Nevertheless, it may fail to detect out-of-control (OOC) products if their corresponding manufacturing process parameters are all in-spec. In other words, unless those certain defected workpieces are selected for sampling measurements, they may not be detected through simply monitoring all the individual manufacturing process parameters. We have proposed a product quality fault detection scheme (FDS), which utilizes the classification and regression tree (CART) to build a single failure model (FML) for identifying the relationship between process parameters and OOC products. However, all the failure modes (FMs) are contained in the single FML, which makes it difficult to understand the causes of defected products. To remedy this problem, this paper develops an advanced fault detection scheme (AFDS). The AFDS builds the corresponding FM by CART for each individual failure cause and generates a FM manager via support vector machine (SVM) to manage all the FMs. Finally, the dual-phase concept is adopted to run the AFDS for achieving on-line real-time fault detection.

UR - http://www.scopus.com/inward/record.url?scp=84887290468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887290468&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2013.6631076

DO - 10.1109/ICRA.2013.6631076

M3 - Conference contribution

AN - SCOPUS:84887290468

SN - 9781467356411

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 3561

EP - 3566

BT - 2013 IEEE International Conference on Robotics and Automation, ICRA 2013

ER -

Shih YH, Huang YT, Cheng F-T. Preliminary study of advanced fault detection scheme. 於 2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. p. 3561-3566. 6631076. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2013.6631076