标题: 自我相关多变量制程的统计制程管制与工程制程管制流程
Statistical Process Control and Engineering Process Control Procedure for Autocorrelated Multivariate Process
作者: 蔡宏志
Hung-Chih Tsai
唐丽英
Lee-Ing Tong
工业工程与管理学系
关键字: 自我相关性;多变量制程;统计制程管制;工程制程管制;倒传递网路预测模式;倒传递网路控制器;Autocorrelation;Multivariate Process;SPC;EPC;Backprogagation Neural Network;Backpropagation Network Controller
公开日期: 2003
摘要: 管制图(control chart)是业界最常用来监控制程之统计制程管制工具(Statistical Process Control, SPC),可以有效地侦测出影响制程的非机遇原因(assignable cause)。但是当制程资料具有显着的自我相关(autocorrelated)时,使用传统的管制图将会产生错误的讯息,造成企业成本的损失。此外,随着科技的进步,产品的功能越来越多,一个产品往往需要同时监控数个品质特性才能确保其品质,而这些品质特性彼此间并不完全独立。因此,如果把这些品质特性视为独立变数而分别绘制管制图予以监控,则误判的机率会大为增加。在工程制程管制(Engineering Process Control, EPC)方面,当制程工程师发现制程输出观测值有显着偏离目标值的情形时,大多会使用工程制程管制来进行回馈控制,以使输出制程回归到目标值。而在实际的高科技产业中,制程的品质特性通常均多达数十种以上,所以传统的单变量工程制程管制方法将不再适用。因此,本研究之主要目的是针对具自我相关的多变量制程建构出一套完整的统计制程管制流程与工程制程管制流程。本研究利用倒传递神经网路(backpropagation neural network) 模式来处理两个部分: 1.利用此模式来求得输出变数的残差,接着利用残差来建立多变量管制图以消除自我相关性对输出制程的影响;2.当制程发生失控的情形,利用倒传递网路控制器(backpropagation network controller)进行多变量制程的回馈控制,使制程量测值接近目标值。应用本研究所建立之管制流程可以提供制程工程师一套有效且准确之自我相关多变量制程管制程序。
Control chart is a popular statistical process(SPC) control tool for monitoring process. It can detect the assignable cause effectively. However, if the process has significant autocorrelation, the traditional SPC procedure would cause suspious information Additonally, a process usually has multiple quality characteristics related to it. These quality characteristics are correlated among each other. If monitoring these quality characteristics using individual control charts, the chance of false alarms would increase. Moreover, EPC was developed for univariate process and cannot be employed for multivariate process. This study presents an integrated SPC and EPC procedure for autocorrelated multivariate process. Backprogagation neural network model was applied in this study to 1. calculate the residual of output-variation and Hotelling’s T2 control chart of residuals was established to eliminate the autocorrelation effect; 2. When the multivariate process is out-of-control, the backpropagation network controller is utilized to adjust the process mean to the target value. This study provides an effective SPC and EPC procedure for the autocorrelated multivariate process.
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT009133544
http://hdl.handle.net/11536/57645
显示于类别:Thesis


文件中的档案:

  1. 354401.pdf
  2. 354402.pdf
  3. 354403.pdf
  4. 354404.pdf
  5. 354405.pdf
  6. 354406.pdf
  7. 354407.pdf
  8. 354408.pdf
  9. 354409.pdf
  10. 354410.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.