English  |  正體中文  |  简体中文  |  Items with full text/Total items : 21921/27947 (78%)
Visitors : 4238026      Online Users : 432
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://140.128.103.80:8080/handle/310901/1711


    Title: 利用RFID與支持向量機的生產排程於SFIS系統
    Other Titles: A study on Scheduling of SFIS Systems by Using Support Vector Machine and RFID
    Authors: 莊明傑
    Chuang, Ming-Chieh
    Contributors: 陳隆彬
    Chen, Lung-Pin
    東海大學資訊工程學系碩士在職專班
    Keywords: 生產排程;屬性選擇;支持向量機;無線射頻辦識系統
    dynamic scheduling;attributes selection;support vector machine;radio frequency identification
    Date: 2009
    Issue Date: 2011-03-07T07:54:06Z (UTC)
    Abstract: 一個於製造業的即時資訊系統(Shop Flow Information System,簡稱SFIS)需設計一個強力的排程系統,動態的指定派工法則以達到最好的效能。一個即時資訊系統需掌握動有效的資源去面對各種不可預期的情況,如不同的產品型態、不同的產品比例、不同的工作到達和不同的工作時間。本研究將利用支持向量機(Support Vector Machines,簡稱SVM)產生動態的生產排程,以取得適合的派工法則進行生產,並且也萃取出最佳的屬性於不同的效能標準下,另外,也將以RFID的技術為基礎擷取生產的資訊,讓生產效能和屬性有效又即時的獲得與量測。本研究將針對電子製造業的主機板組裝作業為主,一般稱為表面黏著技術(Surface Mount Technology,簡稱SMT),目前由於SMT的製造是組裝作業最複雜也是最多零件的部分,所以是採用自動化的機器進行生產,但在極為快速的生產情況之下,一個生產排程的好壞將影響生產效能相當大。所以SMT組裝作業的生產排程,在利用SVM系統訓練學習的模型下,來預測下個新的生產排程採用何種派工法則能達到最佳的效能,以改善目前生產排程在人工或者簡單的系統安排下的使用,同時也會透過RFID進行生產的監督與量測了解生產的情形,以有效的控制與反應,讓整體的生產效能達到最佳的目標。而由於大部分製造業非常重視的生產量的效能,所以將會以此一效能進行實驗與評估。
    A shop flow control system (SFIS) needs to design powerful scheduling system, dynamically assigning dispatching rules for achieving best A shop flow control system (SFIS) needs to design powerful scheduling system, dynamically assigning dispatching rules for achieving best performance on manufacture industry. SFIS should possess available resource to face unpredictable situation in different part types, part mix rations, and job arrivals.This paper utilize support vector machine (SVM) to scheduling system dynamically for obtaining proper dispatching rule and optimal attributes by different performance criterion. In additional, based on RFID technology to obtain real-time information and measure for performance and attribute.This study will utilize scheduling of SFIS systems on surface mount technology (SMT) industry by using SVM and RFID technology. Let SVM learn and predict scheduling rules, then RFID monitor and measure performance for improving SFIS. Therefore, SFIS implements above two functions to achieve best goal of production.
    Appears in Collections:[資訊工程學系所] 碩士論文

    Files in This Item:

    File SizeFormat
    index.html0KbHTML196View/Open


    All items in THUIR are protected by copyright, with all rights reserved.


    本網站之東海大學機構典藏數位內容,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback