應用機器視覺及管制圖於模具磨損監控

Applying Machine Vision and Control Chart in Monitoring Mold Wearing

柯佳伶(Chia-Ling Ke)

指導教授 ： 田方治

國立臺北科技大學/管理學院/工業工程與管理研究所/碩士(2011年)

摘要

品質管制於各種產業製程已是一個非常重要的工具。本研究提出機器視覺檢測結合品質管制圖線上及時偵測模具是否磨損該更換，以減少廢料的產生，不僅能提升產能，時間成本也大大地降低。本論文提出一個修正後品質管制圖更能及時檢測小變動及大變動，並利用其他管制圖偵測小變動及大變動來加以比較，能達到線上及時反映模具受損，隨即發出警訊來告知該停止產線，檢查模具是否該更換。
本論文研究對象以沖壓導線架（Lead Frame）之模具為研究對象，在生產導線架快速製程中，模具隨時會產生損傷，造成導線架規格不合，另外，沖壓後所產生的碎屑，也會造成品質損耗，然而，發現模具損傷的時間，早已造成許多廢料及成本損耗。目前工廠檢查是否模具損傷，需等一批製程結束後，再進行管制量測，因此造成許多廢料。

關鍵字

品質管制圖 ； 機器視覺 ； 導線架

並列摘要

The research purpose of utilizing the statistical process control (SPC) and machine vision is to improve the quality and productivity of the manufacture process. It has been applied for on-line detecting the process shifts which resulted from assignable causes for decades. However, research which has empirically documented the link between the statistical process control and machine vision is scant. Therefore, the aim of this article attempts to combine with each other for diagnosing if the mold has worn. This study proposes the new modified control chart (SFCUSUM-XS control chart) that rapidly detects the small/large shifted mean and variance. Although the detection ability is more sensitive, the false alarm occurs easier.

並列關鍵字

Quality Control Chart ； Machine Vision ； Lead Frame

參考文獻

[1] Shewhart and Walter A., Economic Control of Quality of Manufactured Product, New York: Van Nostrand, 1931.

[2] S. W. Roberts, "Control chart tests based on geometric moving average," Technomertics, vol. 42, no. 1, 1959, pp. 239-250.

[3] E. S. Page, "Continuous inspection schemes," Biometrics, vol. 41, no. 1/2, 1954, pp. 100-115.

[4] J. S. Hunter, "The exponentially weighted moving average," Journal of Quality Technology, vol. 18, no. 4, 1986, pp. 203-210.

[5] C. Sanby, L. Norton-Wayne, R. Harwood, "The automated inspection of lace using machine vision," Mechatronic, vol. 5, no. 2-3, 1995, pp. 215-231.