Login | Register

Defects control charts for high-quality processes

Title:

Defects control charts for high-quality processes

Aebtarm, Surath (2008) Defects control charts for high-quality processes. Masters thesis, Concordia University.

[img]
Preview
Text (application/pdf)
MR63320.pdf - Accepted Version
3MB

Abstract

The traditional C-chart by Shewhart has been widely applied for monitoring count data in industrial and nonindustrial processes. However, using C-chart always experiences an excessive amount of false alarms, since control limits of traditional C-chart are defined by impractical normal assumption. Specially, when we monitor two or more correlated characteristics of defects, C-chart becomes unsuitable. Thus, monitoring a process by traditional C-chart leads to the increase of unnecessary costs of inspection. There are many works that have attempted to improve C-charts. In this thesis, 11 selected improved versions of C-chart are presented. The performances of improved C-charts are evaluated in term of numerical results to demonstrate the sensitivity of the charts and costs of inspections. We also propose an optimal bivariate Poisson field chart to monitor two correlated characteristics of defects. Our chart is based on the optimization of bivariate Poisson confidence interval and projection of bivariate Poisson data in Poisson field. The detailed description of our proposed algorithm is presented by numerical data. The experimental results demonstrate improved performances regarding user-friendly visualization and false alarm rate Furthermore, we propose an optimal diagonal inflated bivariate Poisson field chart to monitor two over/under dispersed correlated count data. The detailed description of our chart will be presented. The experimental results demonstrate improved performances according to loss function and false alarm rate compared to other methods.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Concordia Institute for Information Systems Engineering
Item Type:Thesis (Masters)
Authors:Aebtarm, Surath
Pagination:x, 67 leaves : ill. ; 29 cm.
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Institute for Information Systems Engineering
Date:2008
Thesis Supervisor(s):Bouguila, N
ID Code:976259
Deposited By: Concordia University Library
Deposited On:22 Jan 2013 16:22
Last Modified:18 Jan 2018 17:42
Related URLs:
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Back to top Back to top