標題: 應用資料探勘技術於智慧型電腦整合製造系統建構之研究-以IC封裝測試業為例
Using Data Mining Technology to Build an Intelligent CIM System- A Case Study of IC Testing House
作者: 黃振聲
Huang Chen-Sheng
陳瑞順
Dr. Ruey-Shun Chen
管理學院資訊管理學程
關鍵字: 資料探勘;資料倉儲;決策樹;電腦整合製造;Data Mining;Data Warehouse;Decision Tree;Computer Integrated Manufacturing
公開日期: 2004
摘要: 本研究是應用資料探勘技術來將企業推向商業智慧化系統架構,建構一個有特定功能導向的電腦整合製造系統(Computer Integrated Manufacturing, CIM)。在本研究中詳細介紹一個智慧型電腦整合製造系統,這個系統中所整合了五個主要的技術分別是: 電腦整合製造、資料倉儲、線上分析、資料探勘和人工智慧。 本系統架構是以ERP系統所積蓄的既有龐大資料為基礎,經由整合CIM系統與資料倉儲、整合資料倉儲與決策分析、整合決策分析與資料探勘系統等三階段的過程,實際建置涵蓋操作資料、倉儲資料、智慧應用等三個層級的系統架構。資料探勘系統則是應用決策樹演算法與分類預測的模型,以探勘CIM系統中隱含的、有意義的決策資訊。探勘到的知識規則,則以專家系統的法則式知識表現,搭配WEB化方式來展示。 本系統所提出的系統架構也可應用於傳統製造業,藉由行銷管理、目標市場分析、顧客關係管理等方面,協助企業提昇競爭力。
This paper is applied data mining technology to use a systematic framework of business intelligence to bring a specific CIM system. This paper explains an intelligent CIM system by integrating the following five major subject areas: computer integrated manufacturing, data warehouse, online analytical processing, data mining, and artificial intelligence. The framework of this system is provided by the massive amounts of data gathered by a ERP system. Through a three-step process of integrating CIM systems, data warehouses and decision analysis with data mining technology, a three-tiered systematic framework has been established. The three tiers of this practical framework consist of operational data, warehouse data, and intelligent application. The data mining system makes use of the decision tree algorithm and classification model in exploring the meaningful information, which is useful in the process of decision-making. Subsequently, the rules discovered by the data mining system are expressed through the rule based knowledge presentation method of the expert system. These rules are exhibited by web-based framework. The contribution can be help increase the business competitiveness, the analysis of customer characteristics, target market analysis, the analysis of customer loyalty, predicting the loss of customers and the segmentation of customers.
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT008964520
http://hdl.handle.net/11536/79658
Appears in Collections:Thesis


Files in This Item:

  1. 452001.pdf
  2. 452002.pdf