English  |  正體中文  |  简体中文  |  Items with full text/Total items : 889/889 (100%)
Visitors : 14653069      Online Users : 12
RC Version 7.0 © 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://ccur.lib.ccu.edu.tw/handle/A095B0000Q/275

    Title: 影像處理與機器學習於鏟花加工面之研究;A Research of Scraping Surface Inspection with Image Processing and Machine Learning
    Authors: 吳翊菱;WU, YI-LING
    Contributors: 機械工程系研究所
    Keywords: 鏟花;影像處理;機器學習;Scraping;Image processing;Machine learning
    Date: 2017
    Issue Date: 2019-07-17
    Publisher: 機械工程系研究所
    Abstract:   台灣工具機產業出口面臨複雜的國際競爭,唯有提升產業技能才能確保台灣的競爭力。鏟花針對工具機而言非常重要,目前文獻都針對鏟花做影像處理,目標都是評定鏟花的承斑點數及面積比,或研發自動鏟花機構來取代人工鏟花,達到自動化工廠之目的。本研究利用影像處理與機器學習之方法來研究鏟花加工面,經由影像處理可以去除不必要的雜訊並擷取所需要的特徵,再利用機器學習方式運算擷取後之特徵,而機器學習的部分以「倒傳遞類神經網路」的方法進行研究,以大數據分析其工件樣本再加以訓練,經由良好網路輸出可信賴的鏟花數據,本研究影像處理經由機器學習後的正確率無論是分類或PPI的預測皆可達90%。
      Scraping technique is one of the key point techniques in machine tool industry. The quality of scraping are mostly inspected manually or judged automatically using image processing methods. Since the scraping sizes, shapes and patterns of work pieces are different from another, manual judgement can be subjective. In addition, different image processing methods can lead to different inspect results. Thus, in addition to image processing methods, machine learning is applied in this study to make the inspection results more reliable. The experimental results show that with proposed method, both of the correct scraping classification rate and correct PPI prediction rate by image processing followed by the machine learning method can reach up to 90 %.
    Appears in Collections:[機械工程學系] 學位論文

    Files in This Item:

    File Description SizeFormat

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

    版權聲明 © 國立中正大學圖書館網頁內容著作權屬國立中正大學圖書館


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