臺灣博碩士論文加值系統

隨著經濟環境的改變，品質已是消費者最基本的要求。為了維持一定的品質，檢驗就顯得很重要。產品品質源自於設計，而檢驗卻能呈現出已存在的品質狀況，經由檢驗我們可以了解品質狀況，降低顧客的不滿意度。一般產品在製程中大部分都有連續生產的特性，或者在製程中無法劃分批次的產品，都適用連續抽樣檢驗計畫。透過檢驗計畫可有效篩選出不良品，然而在檢驗的過程中，仍有可能因為機器或人為的誤判產生檢驗誤差。但一般連續抽樣檢驗計畫皆假設檢驗時沒有檢驗誤差的存在，事實上，檢驗時或多或少會存在誤判的情形，上述兩種情形都將造成生產者的損失。

CSP-2是一種連續型的抽樣檢驗計畫，其中有兩個特性是：(1)假設檢驗是完美的和(2)在平均出廠品質界限 (AOQL) 下，出貨批中允許一些不良品存在。然而，檢驗常會發生檢驗誤差（型Ⅰ和型Ⅱ），將會增加生產者的成本。另外，在現實中有許多狀況並不允許不良品的存在，此時不良品常會招致巨額的退貨成本，避免此一問題的方法之一，即是採用精密檢驗，以進行CSP-2程序後不良品的百分之百的篩選；惟精密檢驗需耗用較高的檢驗成本，所以如何取得成本和檢驗效果之間的平衡，也是個值得探討的問題。

本研究之目的即是要探討在CSP-2中引進較高成本之精密檢驗，以提升檢驗的精密度和降低出貨量中不良品的最佳混合檢驗策略。亦即，在考量檢驗誤差和退貨成本下，針對不可維修和可維修兩種產品，探討其最佳檢驗間隔數、抽樣比率及最佳精密檢驗比率，以決定CSP-2和精密檢驗之最佳混合檢驗策略。CSP-2 共有三種可能檢驗策略：(1) CSP-2無需檢驗；(2) CSP-2應執行百分之百的檢驗； (3) CSP-2可以設定任意數值的百分之百檢驗個數及任意的抽樣比率進行檢驗。另外，考慮是否採用精密檢驗部分結果有三：於CSP-2中未檢驗產品、檢驗全判定為良品和不良品之產品可能需要全部進行精密檢驗、無需精密檢驗或取任意比例進行精密檢驗。

With the change in the economic environment, quality is the most basic requirement of consumers. In order to maintain certain quality, the inspection is very important. The design determines product quality, while inspection can present the quality which has already existed. Through quality inspection, we can understand the quality situation thus reduce customers’ dissatisfaction. Continuous production is the characteristic of the most products, or products in the manufacturing process cannot be divided into batches of products, it applies to continuous sampling plan. Through the inspection plans, it can effectively filter out the defectives, but in the process of inspection, it is possible to make mistake judge. However, continuous sampling plan is assumed that the inspection is perfect. In fact, due to worn-down mechanical or human negligence, it will result in the loss of producers.

CSP-2 is a continuous sampling plan which has two characteristics: (1) Inspection is assumed to be perfect and (2) some defectives are permitted for the products shipped to the consumer under the average outgoing quality limits (AOQL). However, because the inspection testing fails to be perfect, two types (TypeⅠand TypeⅡ) of errors can occur. The two errors will increase the cost of producers. In addition, under some practical situations, defectives are not permitted and will incur huge return cost. Precise inspection is an effective method to screen out the defectives for CSP-2 to resolve this problem; while it is usually cost-consuming. Therefore, how to obtain a balance between the cost and result of inspection is also a problem which is worth discussing.
The purpose of this study is to determine a joint inspection policy between CSP-2 and precise inspection under inspection errors and return cost for non-repairable products and repairable products. By maximizing the unit net profit, we determine the following decision variables: (1) the optimal clearance number, (2) the optimal sampling frequency, and (3) the proportions which should be taken precise inspection for the non-inspected items in the procedure of CSP-2, defectives identified by CSP-2, and the non-defectives identified by CSP-2. There are three possible optimal inspection policies for CSP-2: CSP-2 does not need to inspection, CSP-2 should do 100% inspection, or any setting of (i,s) for CSP-2. For the defectives and the non-defectives identified and the non-inspected items for CSP-2, there are three possible proportions which should be performed a precise inspection: all, none, or any proportion.

中文摘要-----------------------------------------------i
英文摘要-----------------------------------------------iii
誌謝---------------------------------------------------v
表目錄-------------------------------------------------vii
圖目錄-------------------------------------------------viii
第一章
緒論---------------------------------------------------1
1.1 研究背景與動機-----------------------------------1
1.2 研究目的-----------------------------------------3
1.3 論文架構-----------------------------------------3
第二章
完美檢驗之最佳化問題-----------------------------------4
第三章
不完美檢驗下的最佳化策略-------------------------------14
第四章
最佳檢驗策略-------------------------------------------21
4.1 類型Ⅰ(不可維修的產品)---------------------------22
4.2 類型Ⅱ(可維修的產品)-----------------------------30
第五章
範例說明-----------------------------------------------37
5.1 類型Ⅰ(不可維修的產品)---------------------------37
5.2 類型Ⅱ(可維修的產品)-----------------------------40
第六章
結論與未來研究方向-------------------------------------42
6.1 結論---------------------------------------------42
6.2 未來研究方向-------------------------------------43
參考文獻-----------------------------------------------44

1.巫文萍 (2007)，考量檢驗誤差與退貨成本下之CSP-1的最佳抽樣策略，國立虎尾科技大學，碩士論文。
2.Case, K. E., Bennett, G. K. and Schmidt, J. W. (1973). “The Dodge CSP-1 continuous sampling plan under inspection error”, AIIE Transactions, vol. 5, pp.193-202.
3.Chen, C. H. and Chou, C. Y. (2002). “Economic design of continuous sampling plan under linear inspection cost”, Journal of Applied Statistics, vol. 29, pp.1003-1009.
4.Chen, C. H. and Chou, C. Y. (2004). “Minimum average fraction inspected for modified CSP-1 plan”, Pan-Pacific Management Review, vol. 7, pp.35-43.
5.Dodge, H. F. (1943). “A sampling inspection plan for continuous production”, Annals of Mathematical Statistics, vol.14, pp.264-279.
6.Dodge, H. F. and Torrey, M. N. (1951). “Additional continuous sampling inspection plans”, Industrial Quality Control, vol. 7, pp.7-12.
7.Ghosh, D. T. (1996). “An optimum continuous sampling plan CSP-2 with to minimize the amount of inspection when incoming quality follow a distribution”, The Indian Journal of Statistics, vol. 58, Series B, pp.105-117.
8.Govindaraju, K. and Kandasamy, C. (2000). “Design of generalized CSP-C continuous sampling plan”, Journal of Applied Statistics, vol. 27, pp.829-841.
9.Haji, A. and Haji, R. (2004). “The optimal policy for a sampling plan in continuous in terms of the clearance number”, Computers & Industrial Engineering, vol. 47, pp.141-147.
10.Mohamed, B. D. (2002). “The economic production lot-sizing problem with imperfect production processes and imperfect maintenance”, International Journal of Production Economics, vol. 76, pp.257-264.
11.Porteus, E. L. (1986). “Optimal lot sizing, process quality improvement and setup cost reduction”, Operations Research , vol. 34, pp.137-144.
12.Rahim, M. A. (1994). “Joint determination of production quantity, inspection schedule, and control chart design”, IIE Transactions, vol. 26, no. 6, pp.2-11.
13.Resnikoff, G. J. (1960). “Minimum average fraction inspected for a continuous sampling plan”, Journal of Industrial Engineering, vol. 11, pp.208-209.
14.Wang, C. H. and Sheu, S. H. (2003). “Optimal lot sizing for products sold under free-repair warranty”, European Journal of Operational Research, vol.149, pp.131-141.
15.Wang, R. C. and Chen, C. H. (1994). “Minimum AFI for CSP-2 under inspection error”, Computer ind. Engng, vol. 26, no. 4 , pp.755-785.
16.Wang, R. C. and Chen, C. H. (1997). “Minimum average fraction inspected for continuous sampling plan CSP-1 under inspection error”, Journal of Applied Statistics, vol. 24, pp.539-548.