Principal curve-based monitoring chart for anomaly detection of non-linear process signals

Seung Hwan Park, Cheong Sool Park, Jun Seok Kim, Jun-Geol Baek

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This study proposes a monitoring chart for anomaly detection of non-linear process signals generated by semiconductor manufacturing processes. In these manufacturing processes, fault detection and classification (FDC) and statistical process control (SPC) have been established as fundamental techniques to improve production efficiency and yield. Non-linear process signals are collected through automatic sensing during each operation cycle of a manufacturing process. As these cyclic signals non-linearly vary on the process state, the usage of the prevalent SPC chart is limited. Therefore, we propose a more efficient monitoring chart considering non-linear and time-variant characteristics. Using the principal curve, a non-linear smoothing algorithm, we construct a time-variant centerline that represents the standard pattern of the process. Then, control limits are calculated with time-variant variances over the course of the process. To evaluate performance, the proposed method was applied to industrial data for chemical vapor deposition (CVD), a semiconductor manufacturing process. We employed the misdetection ratio of signals to evaluate the performance. The proposed method demonstrated superior performance compared to other existing methods.

Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalInternational Journal of Advanced Manufacturing Technology
DOIs
Publication statusAccepted/In press - 2016 Nov 9

Fingerprint

Statistical process control
Monitoring
Semiconductor materials
Fault detection
Chemical vapor deposition
Control charts

Keywords

  • Anomaly detection
  • Nonlinear process signal
  • Principal curve-based monitoring chart
  • Semiconductor manufacturing process
  • Statistical process control

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Mechanical Engineering
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

Principal curve-based monitoring chart for anomaly detection of non-linear process signals. / Park, Seung Hwan; Park, Cheong Sool; Kim, Jun Seok; Baek, Jun-Geol.

In: International Journal of Advanced Manufacturing Technology, 09.11.2016, p. 1-9.

Research output: Contribution to journalArticle

@article{ec5ced51867645ca903a6086b66d191a,
title = "Principal curve-based monitoring chart for anomaly detection of non-linear process signals",
abstract = "This study proposes a monitoring chart for anomaly detection of non-linear process signals generated by semiconductor manufacturing processes. In these manufacturing processes, fault detection and classification (FDC) and statistical process control (SPC) have been established as fundamental techniques to improve production efficiency and yield. Non-linear process signals are collected through automatic sensing during each operation cycle of a manufacturing process. As these cyclic signals non-linearly vary on the process state, the usage of the prevalent SPC chart is limited. Therefore, we propose a more efficient monitoring chart considering non-linear and time-variant characteristics. Using the principal curve, a non-linear smoothing algorithm, we construct a time-variant centerline that represents the standard pattern of the process. Then, control limits are calculated with time-variant variances over the course of the process. To evaluate performance, the proposed method was applied to industrial data for chemical vapor deposition (CVD), a semiconductor manufacturing process. We employed the misdetection ratio of signals to evaluate the performance. The proposed method demonstrated superior performance compared to other existing methods.",
keywords = "Anomaly detection, Nonlinear process signal, Principal curve-based monitoring chart, Semiconductor manufacturing process, Statistical process control",
author = "Park, {Seung Hwan} and Park, {Cheong Sool} and Kim, {Jun Seok} and Jun-Geol Baek",
year = "2016",
month = "11",
day = "9",
doi = "10.1007/s00170-016-9624-y",
language = "English",
pages = "1--9",
journal = "International Journal of Advanced Manufacturing Technology",
issn = "0268-3768",
publisher = "Springer London",

}

TY - JOUR

T1 - Principal curve-based monitoring chart for anomaly detection of non-linear process signals

AU - Park, Seung Hwan

AU - Park, Cheong Sool

AU - Kim, Jun Seok

AU - Baek, Jun-Geol

PY - 2016/11/9

Y1 - 2016/11/9

N2 - This study proposes a monitoring chart for anomaly detection of non-linear process signals generated by semiconductor manufacturing processes. In these manufacturing processes, fault detection and classification (FDC) and statistical process control (SPC) have been established as fundamental techniques to improve production efficiency and yield. Non-linear process signals are collected through automatic sensing during each operation cycle of a manufacturing process. As these cyclic signals non-linearly vary on the process state, the usage of the prevalent SPC chart is limited. Therefore, we propose a more efficient monitoring chart considering non-linear and time-variant characteristics. Using the principal curve, a non-linear smoothing algorithm, we construct a time-variant centerline that represents the standard pattern of the process. Then, control limits are calculated with time-variant variances over the course of the process. To evaluate performance, the proposed method was applied to industrial data for chemical vapor deposition (CVD), a semiconductor manufacturing process. We employed the misdetection ratio of signals to evaluate the performance. The proposed method demonstrated superior performance compared to other existing methods.

AB - This study proposes a monitoring chart for anomaly detection of non-linear process signals generated by semiconductor manufacturing processes. In these manufacturing processes, fault detection and classification (FDC) and statistical process control (SPC) have been established as fundamental techniques to improve production efficiency and yield. Non-linear process signals are collected through automatic sensing during each operation cycle of a manufacturing process. As these cyclic signals non-linearly vary on the process state, the usage of the prevalent SPC chart is limited. Therefore, we propose a more efficient monitoring chart considering non-linear and time-variant characteristics. Using the principal curve, a non-linear smoothing algorithm, we construct a time-variant centerline that represents the standard pattern of the process. Then, control limits are calculated with time-variant variances over the course of the process. To evaluate performance, the proposed method was applied to industrial data for chemical vapor deposition (CVD), a semiconductor manufacturing process. We employed the misdetection ratio of signals to evaluate the performance. The proposed method demonstrated superior performance compared to other existing methods.

KW - Anomaly detection

KW - Nonlinear process signal

KW - Principal curve-based monitoring chart

KW - Semiconductor manufacturing process

KW - Statistical process control

UR - http://www.scopus.com/inward/record.url?scp=84994527434&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994527434&partnerID=8YFLogxK

U2 - 10.1007/s00170-016-9624-y

DO - 10.1007/s00170-016-9624-y

M3 - Article

SP - 1

EP - 9

JO - International Journal of Advanced Manufacturing Technology

JF - International Journal of Advanced Manufacturing Technology

SN - 0268-3768

ER -