A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes

Yu Chuan Su, Fan Tien Cheng, Guo Wei Huang, Min Hsiung Hung, Taho Yang

研究成果: Paper

4 引文 (Scopus)

摘要

A quality prognostics scheme for predicting the product quality during the semiconductor or TFT-LCD manufacturing processes is proposed in this work. This scheme considers the current production equipment parameters sensed during the manufacturing process and several previous quality data collected from the measurement equipment to predict the quality of the product in the future. This quality prognostics scheme is composed of a conjecture model and a prediction model. The conjecture model itself can also be applied for the purpose of virtual metrology. With this two-tier arrangement, the quality prognostics scheme becomes more applicable. The algorithms adopted by the conjecture model can be various and exchangeable. Basically, numerous algorithms of artificial intelligence and statistics may be applied. The selection criteria are based on the physics of the equipment and the property of the measured parameters. The prediction algorithms used in the prediction model are weighted moving average, neural network, or any algorithm with prediction capability. Besides, the quality prognostics scheme possesses a self-searching mechanism and a self-adjusting mechanism. Upon the new conjecture or prediction algorithm being selected, the self-searching mechanism will be activated. The self-searching mechanism will not stop until the best combination of various parameters/functions used by the conjecture algorithm or prediction algorithm is found. Then, the conjecture or prediction model enters the normal running mode. After a period of time, if the prediction accuracy exceeds an acceptable bound or the equipment properties are altered due to scheduled maintenance or part change, the self-adjusting mechanism is launched to tune the system parameters to bring the prediction accuracy within the acceptable bounds.

原文English
頁面1972-1977
頁數6
出版狀態Published - 2004 十二月 1
事件IECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society - Busan, Korea, Republic of
持續時間: 2004 十一月 22004 十一月 6

Other

OtherIECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society
國家Korea, Republic of
城市Busan
期間04-11-0204-11-06

指紋

Liquid crystal displays
Semiconductor materials
Artificial intelligence
Physics
Statistics
Neural networks

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

引用此文

Su, Y. C., Cheng, F. T., Huang, G. W., Hung, M. H., & Yang, T. (2004). A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes. 1972-1977. 論文發表於 IECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society, Busan, Korea, Republic of.
Su, Yu Chuan ; Cheng, Fan Tien ; Huang, Guo Wei ; Hung, Min Hsiung ; Yang, Taho. / A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes. 論文發表於 IECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society, Busan, Korea, Republic of.6 p.
@conference{ebcec7766ab6476ab27bf9645d39d8b7,
title = "A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes",
abstract = "A quality prognostics scheme for predicting the product quality during the semiconductor or TFT-LCD manufacturing processes is proposed in this work. This scheme considers the current production equipment parameters sensed during the manufacturing process and several previous quality data collected from the measurement equipment to predict the quality of the product in the future. This quality prognostics scheme is composed of a conjecture model and a prediction model. The conjecture model itself can also be applied for the purpose of virtual metrology. With this two-tier arrangement, the quality prognostics scheme becomes more applicable. The algorithms adopted by the conjecture model can be various and exchangeable. Basically, numerous algorithms of artificial intelligence and statistics may be applied. The selection criteria are based on the physics of the equipment and the property of the measured parameters. The prediction algorithms used in the prediction model are weighted moving average, neural network, or any algorithm with prediction capability. Besides, the quality prognostics scheme possesses a self-searching mechanism and a self-adjusting mechanism. Upon the new conjecture or prediction algorithm being selected, the self-searching mechanism will be activated. The self-searching mechanism will not stop until the best combination of various parameters/functions used by the conjecture algorithm or prediction algorithm is found. Then, the conjecture or prediction model enters the normal running mode. After a period of time, if the prediction accuracy exceeds an acceptable bound or the equipment properties are altered due to scheduled maintenance or part change, the self-adjusting mechanism is launched to tune the system parameters to bring the prediction accuracy within the acceptable bounds.",
author = "Su, {Yu Chuan} and Cheng, {Fan Tien} and Huang, {Guo Wei} and Hung, {Min Hsiung} and Taho Yang",
year = "2004",
month = "12",
day = "1",
language = "English",
pages = "1972--1977",
note = "IECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society ; Conference date: 02-11-2004 Through 06-11-2004",

}

Su, YC, Cheng, FT, Huang, GW, Hung, MH & Yang, T 2004, 'A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes' 論文發表於 IECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society, Busan, Korea, Republic of, 04-11-02 - 04-11-06, 頁 1972-1977.

A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes. / Su, Yu Chuan; Cheng, Fan Tien; Huang, Guo Wei; Hung, Min Hsiung; Yang, Taho.

2004. 1972-1977 論文發表於 IECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society, Busan, Korea, Republic of.

研究成果: Paper

TY - CONF

T1 - A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes

AU - Su, Yu Chuan

AU - Cheng, Fan Tien

AU - Huang, Guo Wei

AU - Hung, Min Hsiung

AU - Yang, Taho

PY - 2004/12/1

Y1 - 2004/12/1

N2 - A quality prognostics scheme for predicting the product quality during the semiconductor or TFT-LCD manufacturing processes is proposed in this work. This scheme considers the current production equipment parameters sensed during the manufacturing process and several previous quality data collected from the measurement equipment to predict the quality of the product in the future. This quality prognostics scheme is composed of a conjecture model and a prediction model. The conjecture model itself can also be applied for the purpose of virtual metrology. With this two-tier arrangement, the quality prognostics scheme becomes more applicable. The algorithms adopted by the conjecture model can be various and exchangeable. Basically, numerous algorithms of artificial intelligence and statistics may be applied. The selection criteria are based on the physics of the equipment and the property of the measured parameters. The prediction algorithms used in the prediction model are weighted moving average, neural network, or any algorithm with prediction capability. Besides, the quality prognostics scheme possesses a self-searching mechanism and a self-adjusting mechanism. Upon the new conjecture or prediction algorithm being selected, the self-searching mechanism will be activated. The self-searching mechanism will not stop until the best combination of various parameters/functions used by the conjecture algorithm or prediction algorithm is found. Then, the conjecture or prediction model enters the normal running mode. After a period of time, if the prediction accuracy exceeds an acceptable bound or the equipment properties are altered due to scheduled maintenance or part change, the self-adjusting mechanism is launched to tune the system parameters to bring the prediction accuracy within the acceptable bounds.

AB - A quality prognostics scheme for predicting the product quality during the semiconductor or TFT-LCD manufacturing processes is proposed in this work. This scheme considers the current production equipment parameters sensed during the manufacturing process and several previous quality data collected from the measurement equipment to predict the quality of the product in the future. This quality prognostics scheme is composed of a conjecture model and a prediction model. The conjecture model itself can also be applied for the purpose of virtual metrology. With this two-tier arrangement, the quality prognostics scheme becomes more applicable. The algorithms adopted by the conjecture model can be various and exchangeable. Basically, numerous algorithms of artificial intelligence and statistics may be applied. The selection criteria are based on the physics of the equipment and the property of the measured parameters. The prediction algorithms used in the prediction model are weighted moving average, neural network, or any algorithm with prediction capability. Besides, the quality prognostics scheme possesses a self-searching mechanism and a self-adjusting mechanism. Upon the new conjecture or prediction algorithm being selected, the self-searching mechanism will be activated. The self-searching mechanism will not stop until the best combination of various parameters/functions used by the conjecture algorithm or prediction algorithm is found. Then, the conjecture or prediction model enters the normal running mode. After a period of time, if the prediction accuracy exceeds an acceptable bound or the equipment properties are altered due to scheduled maintenance or part change, the self-adjusting mechanism is launched to tune the system parameters to bring the prediction accuracy within the acceptable bounds.

UR - http://www.scopus.com/inward/record.url?scp=20544473801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20544473801&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:20544473801

SP - 1972

EP - 1977

ER -

Su YC, Cheng FT, Huang GW, Hung MH, Yang T. A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes. 2004. 論文發表於 IECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society, Busan, Korea, Republic of.