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

被引:0
|
作者
机构
[1] Park, Seung Hwan
[2] Park, Cheong-Sool
[3] Kim, Jun-Seok
[4] Baek, Jun-Geol
来源
Baek, Jun-Geol (jungeol@korea.ac.kr) | 1600年 / Springer London卷 / 90期
关键词
Fault detection - Production efficiency - Signal detection - Control charts - Chemical vapor deposition - Curve fitting - Semiconductor device manufacture;
D O I
暂无
中图分类号
学科分类号
摘要
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. © 2016, Springer-Verlag London.
引用
收藏
页码:9 / 12
相关论文
共 50 条
  • [1] 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
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2017, 90 (9-12): : 3523 - 3531
  • [2] 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
    The International Journal of Advanced Manufacturing Technology, 2017, 90 : 3523 - 3531
  • [3] Wavelets and non-linear principal components analysis for process monitoring
    Shao, R
    Jia, F
    Martin, EB
    Morris, AJ
    CONTROL ENGINEERING PRACTICE, 1999, 7 (07) : 865 - 879
  • [4] Non-linear principal components analysis for process fault detection
    Jia, F
    Martin, EB
    Morris, AJ
    COMPUTERS & CHEMICAL ENGINEERING, 1998, 22 : S851 - S854
  • [5] Non-linear principal components analysis with application to process fault detection
    Jia, F
    Martin, EB
    Morris, AJ
    INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2000, 31 (11) : 1473 - 1487
  • [6] Non-linear anomaly detection for hyperspectral image
    Han, Xiaoqing
    Yangon, Jinhua
    GLOBAL INTELLIGENT INDUSTRY CONFERENCE 2020, 2021, 11780
  • [7] LSTM-Based Anomaly Detection for Non-Linear Dynamical System
    Tan, Yue
    Hu, Chunjing
    Zhang, Kuan
    Zheng, Kan
    Davis, Ethan A.
    Park, Jae Sung
    IEEE ACCESS, 2020, 8 (08): : 103301 - 103308
  • [8] Non-linear multi-way principal components analysis for process performance monitoring
    Jia, F
    Martin, E
    Morris, J
    ADVANCES IN PROCESS CONTROL 5, 1998, : 141 - 150
  • [9] Non-linear process fault detection method based on RISOMAP
    Zhang, Ni
    Tian, Xuemin
    Cai, Lianfang
    Huagong Xuebao/CIESC Journal, 2013, 64 (06): : 2125 - 2130
  • [10] Non-linear error detection for elliptic curve cryptosystems
    Akdemir, K. D.
    Karakoyunlu, D.
    Sunar, B.
    IET INFORMATION SECURITY, 2012, 6 (01) : 28 - 40