Date of Award

1993

Document Type

Thesis

Publisher

Edith Cowan University

Degree Name

Bachelor of Applied Sciences Honours

Faculty

Faculty of Science and Technology

First Supervisor

Dr David McDougall

Abstract

As part of my undergraduate degree I studied various areas in quality control. Included in these areas of study was the concept of control charts, which are becoming increasingly more important in industry for effective manufacturing processes. The general form for constructing a control chart assumes that the outcomes of the process conform to a normal distribution. Data gathered at an industrial site in Western Australia illustrates that this is not always the case. The distribution of the data collected for a specific manufacturing process was found to be significantly different from the normal distribution, in that it was right tail skewed. This report investigates one method of constructing control charts for asymmetrically distributed process data. The method involves transforming the data to fit a normal distribution, calculating the control limits, converting them back to the original data scale and then constructing the control chart. A simulated Poisson distribution is used throughout this report in various examples. However, in Chapter 6 real data from an industrial manufacturing process is used to provide a complete case study. This example illustrates the significance of the study and highlights the possibilities for further research in this area.

Share

 
COinS