Monitoring for changes in parameters of Weibull processes /

We developed several new statistical process control charts

Bibliographic Details
Main Author: Kang, Hunku, 1959-
Format: Thesis Book
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1997.
Subjects:
Online Access:http://proxy.library.tamu.edu/login?url=http://proquest.umi.com/pqdweb?did=739891111&sid=1&Fmt=2&clientId=2945&RQT=309&VName=PQD
Description
Summary:We developed several new statistical process control charts
for monitoring for changes in the scale and shape parameter
of Weibull processess. Shewhaxt-type control charts on the
MLEs of the process parameters were developed. The bootstrap
percentile method was used to set up the control limits on
each parameter. Using likelihood ratio tests (LRTS) for the
change point hypotheses on the Weibull process parameters, we
developed change point (CP) control charts for monitoring for
changes in the scale and shape parameters of a given
magnitude. We considered combinations of these CP charts as
possible strategies for monitoring a Weibull process. We
also utilize maximum likelihood estimates (MLES) of the
process parameters to construct general changes in the
parameters. Also, using LRTs for change point hypotheses on
the Weibull process parameters, we constructed omnibus
control charts. Average run lengths (ARLS) were computed for
each control chart. The ARL performances of the control
charts were compared over a variety of conditions.
Combinations of control charts were considered as different
strategies for monitoring Weibull processes. Recommendations
based on ARL considerations were made for choosing a strategy
for monitoring a Weibilll process.
Item Description:Vita.
"Major Subject: Industrial Engineering".
Physical Description:xii, 106 leaves : illustrations ; 28 cm.
Issued also on microfiche from University Microfilms Inc.
Bibliography:Includes bibliographical references: pages 94-96.