English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 93861/124308 (76%)
Visitors : 28917381      Online Users : 296
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://nccur.lib.nccu.edu.tw/handle/140.119/53415

    Title: 整合允差設計及管制圖設計之研究
    Other Titles: Integrate Tolerance Design and Control Charts Design
    Authors: 楊素芬
    Contributors: 國立政治大學統計學系
    Keywords: 統計;整合允差設計;管制圖設計
    Date: 2012
    Issue Date: 2012-08-30 09:59:38 (UTC+8)
    Abstract: 在製程管制上設計符合各種生產製程型態的管制圖以維持及改善品質是重要 的。對製造者而言,規劃適當的檢驗策略以篩選合格品,達到客戶滿意,辦演重要的 角色。 過去20 年,以經濟觀點設計規格界限以檢驗產品或零件的論文很多。然而只限 於探討單一製程及未考慮製程管制成本。對單一品質特性及多元品質特性同步設計 規格界限及管制圖之研究尚未有文獻探討。這樣的研究主題似乎是有趣且具挑戰的。 我們提出3 年期計畫,探討以下的主題。 (1) 在單一製程及無檢驗誤差下,研究如何以更新理論建立經濟模式,再以最小化單 位時間之平均總成本以決定規格界限和管制圖之設計參數值。品質特性分別考慮是 望大、望小及望目,服從常態分配、枷瑪分配及折疊常態分配。此外,考慮非對稱 二次及線性損失函數。 (2) 推廣(1)的研究為管制圖具適應性的情形。 (3) 對(1)(2)考慮檢驗誤差的情形。 (4) 推廣(1)-(3)的研究為相依製程的情形。 (5) 推廣(1)-(4)為多元品質特性的情形。 (6) 所有以上的研究主題之績效將被衡量及比較; 在有檢驗誤差及無檢驗誤差下,規格 界限和管制圖之設計參數對損益平衡點的影響將被探討, 且敏感度分析將被執行。 期望這些結果可以對品質管制提出新的觀點,這在學術研究上及產業實務應用上會 是有用及有價值的。
    In SPC, design appropriate control charts to maintain/improve the quality of a quality characteristic is important. For manufacturers, planning an inspection strategy to satisfy their customers by screening non-conforming products plans an important role. In the past twenty years, economic development of specifications for inspection has been discussed. However, under a single process or dependent process steps, the related study of simultaneously design specifications and control charts for a single quality characteristic or multiple quality characteristics with variable data has not been addressed. Therefore, the study of the topics would be interesting and challenge. In the three-year project, we will propose the following study topics. (1) Under a single process and perfect inspection, study how to formulate economic models to determine the specifications and design parameters (sample size, sampling interval and factors of control limits) of control charts by minimizing the derived expected total cost per unit time for the smaller the better, larger the better and target the best quality characteristics. We respectively consider that the quality characteristic follows a normal distribution, gamma distribution and folded normal distribution. Moreover, we formulate the economic models with asymmetric quality loss functions, in both quadratic and piecewise linear cases. (2) Under a single process and perfect inspection, extend the study in (1) to the control charts with adaptive control scheme (such as, variable sampling intervals, variable sample sizes and sampling intervals). (3) Under a single process, consider the inspection is imperfect for the study in (1) and (2). (4) Extend the study in (1)-(3) to multiple dependent process steps. (5) Extend the study in (1)-(4) to multivariate quality characteristics. (6) All the performance of the studied topics will be measured and compared; the effects of parameters on the break-even points for either perfect or imperfect inspection will be studied, and the effects of parameters on the optimal design parameters and specifications will be implemented. We expect the study results will provide some new version of quality control. They would be useful and valuable in academic research and reality.
    Relation: 應用研究
    研究期間:10108~ 10207
    Data Type: report
    Appears in Collections:[統計學系] 國科會研究計畫

    Files in This Item:

    File Description SizeFormat
    100-2118-M-004-003-MY2.pdf759KbAdobe PDF363View/Open

    All items in 政大典藏 are protected by copyright, with all rights reserved.

    社群 sharing

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