By Topic

Applying principal component analysis to isolating overall variability of on-line measurement process

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Ma Yizhong ; School of Economics and Management, Nanjing University of Science and Technology, 210094, China ; Chen Jie ; Liu Liping

Measurement plays a significant role in helping an organization improve quality. With the greater reliance on quantitative measurements in modern manufacturing industry, the requirements for measurement system have dramatically increased. In the analysis of measured data, the variation of measurement result is composed of not only product variation, but also measurement variation. In order to evaluate, optimize and monitor manufacturing process, it is necessary to discriminate product variation and measurement variation from the measured data. In this paper, the intraclass correlation criterion for evaluating measurement system is provided on the basis of the model of process. Then the principal component analysis is used to isolate product variation and measurement variation from the measured data. Finally, an example from a six sigma project is presented to exhibit the implementing program. The results show that the program provides a simple method for isolating product and measurement variation and finding the relative usefulness of the measurement system.

Published in:

2007 IEEE International Conference on Grey Systems and Intelligent Services

Date of Conference:

18-20 Nov. 2007