以數據關聯規則進行PCBA測試製程數據分析

Applying Data Association to Big Data Analysis of PCBA Functional Test

黃信和(Hsin-Ho Huang)

指導教授 ： 賀嘉生

中原大學/電機資訊學院/資訊工程研究所/碩士(2017年)

https://doi.org/10.6840/cycu201700834

摘要

EMS(Electronic Manufacturing Service)電子製造服務，是許多國際大廠的合作夥伴，現階段國際大廠聚焦於產品研發、產品行銷、通路開發業務，而製造部份多由代工廠提供專業服務，EMS廠可以提供有效率與高品質的生產環境，除了提供材料準備、試產與量產服務、還有管理庫存與出貨的服務，可協助客戶品質管控與降低成本。EMS廠的獲利越來越艱辛，生產品質異常或效率不佳將影響獲利，因此品質異常防止與效率提升是EMS廠重要的議題。
本論文針對生產過程的生產履歷紀錄Log File，運用Weka數據探勘之Apriori演算法，針對測試不良紀錄Log檔案做數據探勘，分析人員、機器、材料之間的關聯性。研究成果可以提供修護人員或工程人員在不良品問題分析時，能夠有效率分析與解決問題來達到品質改善，也可供設計者在零件上的選用參考，並做到生產上的不良預防。

關鍵字

EMS ； 生產履歷 ； 數據探勘 ； Apriori演算法

並列摘要

EMS (Electronic Manufacturing Service) is one of the important partners of many international manufacturers. Currently, many international manufacturers focus on product research, development, marketing and business development, especially for the manufacturing of OEMs (original equipment manufacturers). EMS can provide efficient and high quality production environment. In addition to material preparation, trial production and mass production services, inventory management and shipping are also provided by EMS whereby EMS helps customers for quality control and costs reduction. But the profit of EMS is getting harder and harder. Abnormal production quality and low efficiency will erode the profit of EMS, therefore the prevention of abnormal quality and efficiency improvement are important topics of EMS.

This paper is aimed at using the A priori algorithm of Weka data mining technology for data mining and analyzing the relevance between personnel, machines and materials by testing bad record log file. The research result can provide the repair staffs and engineering staffs to efficiently analyze and resolve the problems to improve the quality in analysis of bad production problems. Notwithstanding the foregoing, it can provide the selection of reference for the designers and the bad prevention of the production.

並列關鍵字

EMS ； Production traceability ； Data mining ； Apriori algorithm

參考文獻

2. Fayyad, U. M., “Data Mining and Knowledge Discovery: Marking Sense Out of Data,” IEEE Expert, Vol. 11, No. 10, pp.20-25,(1996).

4. Grupe, F.H. and Owrang, M.M.,〝Data Base Mining Discovering New Knowledge And Cooperative Advantage,〞Information Systems Management ,Vol.12,No. 4, pp.26-31, Fall (1995).

5. Kenneth R. Tillery, Arthur L. Rutledge, Quality-Strategy and Quality-Management Connections, International Journal of Quality & Reliability Management, Vol. 8 Iss: 1, pp. 71-77, MCB UP Ltd, (1991).

1. Agrawal, R., and Srikant, R., “Fast Algorithm for Mining association Rules,” In Proceedings of the 20th International conference on Very Large Databases (VLDB), pp. 487-499, (1994).

3. Usama M. Fayyad,(1996)Data mining and knowledge discovery in databases: applications in astronomy and planetary science, Proceedings of the thirteenth national conference on Artificial intelligence, PP.1590-1592, August 04-08 Portland, Oregon.Vapnik, V.N.(1999).Statistical Learning Theory. Wiley: New York.