Affiliation:
1. Chung Yuan Christian University
Abstract
The Define, Measure, Analyze, Improve, Control (DMAIC) Six Sigma strategy was designed to improve product quality and to reduce product defects. Because of its classification and feature selection capabilities, the Mahalanobis-Taguchi System is integrated in the improvement stage of DMAIC to reduce redundant testing items in the testing procedure and to optimize the economic benefit of the test flow. The important variables screened by the Reduced Model in MTS are C2, C5 and the classification accuracy rate is 99.13%. Implementation results show that atomic force microscope (AFM) inspection process reduces inspection attributes and maintains high inspection accuracy. The average AFM thickness is decreased from to . The standard deviation is reduced from 45.76 to 8.73, PCI is raised from 0.73 to 3.81, process accuracy is improved from 0.07 to 0.012, and process performance is improved from 0.67 to 3.76. Finally, this study confirmed that the new process parameters can reduce variance in the alignment membrane thickness and enhance the overall LCD chromaticity yield.
Publisher
Trans Tech Publications, Ltd.
Reference5 articles.
1. Breyfogle, F. W. Implementing Six-Sigma: Smarter Solutions Using Statistical Methods, John Wiley & Sons, Inc., New York (1999).
2. Harry, M. and Schroeder, R. Six Sigma: The Breakthrough Management Strategy Revolutionising the World's Top Corporations, Doubleday, New York (2000).
3. Kane VE. Process capability indices. Journal of Quality Technology, Vol. 18(1) (1986), p.41–52.
4. Pearn WL, Kotz S, Johnson NL. Distributional and inferential properties of process capability indices. Journal of Quality Technology, Vol. 24(4) (1992), p.216–231.
5. Taguchi, G. and Jugulum, R. The Mahalanobis-Taguchi Strategy: A Pattern Technology System, John Wiley & Sons (2002).