LCD零組件出貨品質管制流程之構建-以背光光學特性之管制為例

Abstract

管制圖目前已廣為工業界所採用來監控製程，以有效減少非機遇原因(Assignable cause)所造成的產品品質不良問題。傳統 -R或 -S管制圖是針對管制單一變異來源所設計，然而，有些產品之實際製程中的變異來源，除了有產品本身各量測點間的變異外，還有各產品間的變異及不同批量間的變異等。隨著量測設備的進步，量測設備可以快速且自動地針對產品之多個量測點進行量測，另外，隨著客戶對產品品質的要求愈來愈高，產品的複雜度也逐漸增加，許多的產品或製程都需同時管制兩個以上的品質特性，而傳統的統計製程管制方法，僅能針對每一個品質特性分別繪製管制圖，造成管制圖太多，導致實務上管制工作不易施行。本研究主要之目的是針對LCD零組件出貨品質，建構一套可監控各種變異來源的線上管制流程，此管制流程除了可有效監控零組件品質之外，並可辦別出各種品質變異來源。本研究針對具多個品質特性的產品，利用主成份分析法先合併相關性高的品質特性，再應用本研究方法，以簡化管制作業量。本研究最後以台灣某背光模組廠的實際案例，驗證了本研究方法確實可有效管理零組件的出貨品質。

In order to reduce the quality loss caused by assignable causes, manufacturers usually implement control chart to monitor the product’s manufacturing process. Because the conventional -R or -S charts are designed for detecting the single source of variation in a manufacturing process, they are incapable of detecting assignable causes for a process with several sources of variation, such as within-product variation, product-to-product variation and run-to-run variation in a manufacturing process. Due to the advanced measuring equipment has been developed, it can measure multiple reading at high speed automatically. Moreover, the increasing demands of product quality from customers make the manufacturing process complex and multiple quality characteristics need to be monitored simultaneously. It will take too much time or cost to implement a control charts for each quality characteristic in practice. This study presents a quality control procedure which is capable of detecting assignable causes concealed behind multiple characteristics and multiple readings in a manufacturing process with several sources of variation. The proposed method utilizes the Principal Component Analysis (PCA) to reduce the number of related quality characteristics to decrease the number of control charts. Finally, a case from a Taiwanese manufacturer of backlight unit is utilized to demonstrate the effectiveness of the proposed method. The results of this study can provide a valuable reference for manufacturers of LCD in assessing the quality of their output process.