半導體封裝廠之顆粒成型製程生產績效改善研究 –以A公司為例

NCU Institutional Repository > 管理學院 > 工業管理研究所碩士在職專班 > 博碩士論文 > Item 987654321/85650

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/85650

题名:	半導體封裝廠之顆粒成型製程生產績效改善研究 –以A公司為例
作者:	湯易齊;Tang, Yi-Ci
贡献者:	工業管理研究所在職專班
关键词:	IC封裝;產能提升;資料探勘;決策樹;IC packaging;Capacity increase;Data mining;Decision tree
日期:	2021-07-07
上传时间:	2021-12-07 11:11:34 (UTC+8)
出版者:	國立中央大學
摘要:	在半導體市場蒸蒸日上的發展下，封裝測試的需求也日與俱增，封裝廠主要以接單代工為主的生產模式，為了滿足顧客的需求還有交期，生產線排程上的單一站點生產流速容易造成整理Cycle time生產瓶頸，為了能夠順利調整生產狀況並提升產出是非常重要的。封裝廠的後段的生產模式與封裝前段廠不相似，但由於產品與技術的複雜度較前段生產為低，生產排程仰賴大量人工去做調整，使得生產效率與穩定性會因為人為因素決策，造成整體生產相對不佳。封裝廠後段廠生產管?改善，已有許多的研究探討；關於顆粒成型站點上尺寸改機來說其特性並無法直接套用相關之研究成果。本研究之目標為發展出針對公司MES上的大數據歷史資料進行分析，並做出生產上的排程調整，而本研究的重點是將顆粒成型站點資料進行探勘，找出決策的關鍵因子，並改善後續生產排程方向。透過資訊收集，運用決策樹，讓顆粒成型站點達到該廠站點最大生產量為目標，發展出針對一個區間的內WIP走勢與PC投料相應對關係改善，進而改善生產管?模式提高設備稼動率及滿足降低WIP為主要目標。 ;The semiconductor industry market is developing rapidly in recent years, and the demand for packaging and testing is also increasing day by day. The packaging factory is mainly based on the production mode of build-to-order. In order to meet the needs of customers and customer delivery time, it is easily to cause production cycle time bottleneck at a production flow rate of single site on the production line schedule. It is very important to be able to smoothly adjust the production status and increase the output. The production mode of the back end of the packaging plant is not similar to front end of the packaging plant. However, because the complexity of products and technology is lower than that of the previous production, the production schedule mostly relies on manual adjustments, so that the production efficiency and stability will be decided by human factors which lead to relatively poor productivity. There have been many researches and discussions on the improvement of production management in the back-end of the packaging plant; the characteristics of Saw-singulation machine’s modification adjustment cannot be directly applied to the related research results. The goal of this research is to develop an analysis of the big data historical data on the company′s MES and make production scheduling adjustments. The focus of this research is to explore the Saw-singulation step data and find the key factors for decision-making. , And improve the direction of subsequent production scheduling. Through information collection, using decision trees, which reach the goal of the Saw-singulation step can reach the maximum production capacity of the plant site. And develop an improvement of production management mode of the relationship between WIP trends and PC ordering for an interval. Improving equipment utilization and meeting WIP reduction are the main goals.
显示于类别:	[工業管理研究所碩士在職專班 ] 博碩士論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	94	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....