APPLICATION OF NEURAL NETWORKS AND THE TAGUCHI METHOD ON TOUCH COVER GLASS CUTTING QUALITY

勤益科大機構典藏 > 管理學院 > 工業工程與管理系(所) > 【工業工程與管理系所】期刊論文 > Item 987654321/6204

請使用永久網址來引用或連結此文件: http://ir.lib.ncut.edu.tw/handle/987654321/6204

題名:	APPLICATION OF NEURAL NETWORKS AND THE TAGUCHI METHOD ON TOUCH COVER GLASS CUTTING QUALITY
作者:	洪永祥
貢獻者:	工業工程與(工程)管理系
日期:	2013-08
上傳時間:	2017-09-30 13:22:00 (UTC+8)
摘要:	In recent years, a touch glass product is ideal for touch screens and many other applications. The traditional cutting mode of touch glass product causes severe cracks and defects. This study developed a new cutting method, the heterotypic full-cut mode, which uses a toothed penett to make vertical cracks that penetrates deeper than the traditional scribing break. The vertical cracks simplified the fracture-free system. However, the heterotypic full-cut mode adopts a toothed penett, which does not require a breaking procedure, as its scribed glass automatically cracks. This paper applied neural network prediction model based on Taguchi method to discuss the optimal design of touch cover glass (CG) process parameters to improve product quality, appearance strength, and process yield, while reducing costs. This study experimentally validated the optimal value intervals and predicted CG strengths. Through Taguchi method, the parameter settings influencing CG strength were determined with a processing time reduced by 668 sec/pcs, productive capacity was increased by 4.4 times, and glass strength reached 600 Mpa. These results are significantly better than the traditional cutting methods. © 2013 ISSN 2185-2766. (14 refs)
關聯:	ICIC Express Letters Part B: Applications
顯示於類別:	[工業工程與管理系(所)] 【工業工程與管理系所】期刊論文

文件中的檔案:

沒有與此文件相關的檔案.

檢視Licence

在NCUTIR中所有的資料項目都受到原著作權保護.

資料載入中.....