Monitoring and Fault Detection of Manufacturing Control System

碩士 === 龍華科技大學 === 資訊管理系碩士班 === 99 === In recent years, run-to-run control technology has been widely used in the semiconductor industry. Based on the latest information observed from a process to predict and change control variables in a regression model is the main purpose; it can make reaction val...

Full description

Bibliographic Details
Main Authors: Jia-ming Wang, 王家銘
Other Authors: Chih-hung Jen
Format: Others
Language:zh-TW
Published: 2012
Online Access:http://ndltd.ncl.edu.tw/handle/85393199584742646946
id ndltd-TW-099LHU05396009
record_format oai_dc
spelling ndltd-TW-099LHU053960092015-10-13T21:50:44Z http://ndltd.ncl.edu.tw/handle/85393199584742646946 Monitoring and Fault Detection of Manufacturing Control System 製造控制系統之監控與錯誤偵測 Jia-ming Wang 王家銘 碩士 龍華科技大學 資訊管理系碩士班 99 In recent years, run-to-run control technology has been widely used in the semiconductor industry. Based on the latest information observed from a process to predict and change control variables in a regression model is the main purpose; it can make reaction value close to the target in the process. This study focused on single input single output and double exponentially weighted moving average of multi input multi output used in batch control. Weighted sum squared residual is our fault detection mechanism. Simulate the dynamic process changes caused by the self-correlation coefficients and the trends by a process of aging and phenomenon of migration under one to three times standard deviation and range of different sizes within the window. The system detects faults successful or not when controllers lost some control and out of the scope of the process, then get the standard deviation value of best performance. Finally, we practice using the semiconductor case through the process control simulation to verify our research. In this study, WSSR fault detection mechanism has applied to a run-to-run control system, and results are significant in standard deviation and different window size settings. Chih-hung Jen 任志宏 2012 學位論文 ; thesis 59 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 龍華科技大學 === 資訊管理系碩士班 === 99 === In recent years, run-to-run control technology has been widely used in the semiconductor industry. Based on the latest information observed from a process to predict and change control variables in a regression model is the main purpose; it can make reaction value close to the target in the process. This study focused on single input single output and double exponentially weighted moving average of multi input multi output used in batch control. Weighted sum squared residual is our fault detection mechanism. Simulate the dynamic process changes caused by the self-correlation coefficients and the trends by a process of aging and phenomenon of migration under one to three times standard deviation and range of different sizes within the window. The system detects faults successful or not when controllers lost some control and out of the scope of the process, then get the standard deviation value of best performance. Finally, we practice using the semiconductor case through the process control simulation to verify our research. In this study, WSSR fault detection mechanism has applied to a run-to-run control system, and results are significant in standard deviation and different window size settings.
author2 Chih-hung Jen
author_facet Chih-hung Jen
Jia-ming Wang
王家銘
author Jia-ming Wang
王家銘
spellingShingle Jia-ming Wang
王家銘
Monitoring and Fault Detection of Manufacturing Control System
author_sort Jia-ming Wang
title Monitoring and Fault Detection of Manufacturing Control System
title_short Monitoring and Fault Detection of Manufacturing Control System
title_full Monitoring and Fault Detection of Manufacturing Control System
title_fullStr Monitoring and Fault Detection of Manufacturing Control System
title_full_unstemmed Monitoring and Fault Detection of Manufacturing Control System
title_sort monitoring and fault detection of manufacturing control system
publishDate 2012
url http://ndltd.ncl.edu.tw/handle/85393199584742646946
work_keys_str_mv AT jiamingwang monitoringandfaultdetectionofmanufacturingcontrolsystem
AT wángjiāmíng monitoringandfaultdetectionofmanufacturingcontrolsystem
AT jiamingwang zhìzàokòngzhìxìtǒngzhījiānkòngyǔcuòwùzhēncè
AT wángjiāmíng zhìzàokòngzhìxìtǒngzhījiānkòngyǔcuòwùzhēncè
_version_ 1718069170609848320