An analysis of an optical coating process capability prediction model in a Six Sigma procedure by integrating APIBPN and K-means
by Wen-Tsann Lin; Shen-Tsu Wang; Meng-Hua Li; Chiao-Tzu Huang; Han-Yi Huang
International Journal of Materials and Product Technology (IJMPT), Vol. 44, No. 1/2, 2012

Abstract: This study focused on plastic panel products, and treated product penetration rate as a quality characteristic to construct an optical coating process capability prediction model. This study applied Six Sigma to conduct an empirical study on an optical film processing plant. Combining the Taguchi's parameter design method and the back propagation neural network (BPNN) prediction method, this study used the orthogonal array in experimental design, and employed the Taguchi method to analyse the data obtained from the orthogonal array experiments to study the key factors and their levels, in order to determine the optimal process parameter combinations. The influential process parameters were input into the after 'apicalis' in Pachycondyla apicalis optimise back propagation network (APIBPN) and K-means, the outputs of which were the prediction results of the coating film process capability. The results can provide engineers a reference in quality improvement and decision-making planning. The experimental results suggested that the Cpk was improved from 0.89 to 1.63, indicating a significant improvement in process capability value. The prediction accuracy rate is over 97.6%, which is better than that of the trial and error method, and can improve coating film process capabilities and product quality.

Online publication date: Wed, 17-Sep-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Materials and Product Technology (IJMPT):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com