Title: An analysis of an optical coating process capability prediction model in a Six Sigma procedure by integrating APIBPN and K-means

Authors: Wen-Tsann Lin; Shen-Tsu Wang; Meng-Hua Li; Chiao-Tzu Huang; Han-Yi Huang

Addresses: Department of Industrial Engineering and Engineering Management, National Chin-Yi University of Technology, No. 57, Sec. 2, Zhongshan Rd., Taiping Dist., Taichung 41170, Taiwan. ' Department of Commerce Automation and Management, National Pingtung Institute of Commerce, No. 51, Min Sheng E. Road, Pingtung 900, Taiwan. ' Department and Institute of Industrial Management, Taiwan Shoufu University, No. 168, Nanshi Li, Madou Dist., Tainan City 72153, Taiwan. ' Department of Industrial Engineering and Engineering Management, National Chin-Yi University of Technology, No. 57, Sec. 2, Zhongshan Rd., Taiping Dist., Taichung 41170, Taiwan. ' Department of Industrial Engineering and Engineering Management, National Chin-Yi University of Technology, No. 57, Sec. 2, Zhongshan Rd., Taiping Dist., Taichung 41170, Taiwan

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.

Keywords: optical coating; six sigma; Taguchi methods; Pachycondyla apicalis; optimisation; back propagation neural networks; APIBPN; K-means; plastic panels; process capability prediction; modelling; optical film processing; product quality; orthogonal arrays; experimental design.

DOI: 10.1504/IJMPT.2012.048193

International Journal of Materials and Product Technology, 2012 Vol.44 No.1/2, pp.17 - 34

Published online: 17 Sep 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article