成本導向抽樣檢驗決策模式之多階段生產系統

A Cost-based Sampling Inspection Decision Model for Multistage Production Systems

閻永峰(Yung-Fong Yen)

指導教授 ： 饒忻

中原大學/工學院/工業工程研究所/碩士(2003年)

https://doi.org/10.6840/cycu200300623

摘要

摘要

檢驗作業是生產系統中不可或缺的一環。隨著科技的進步，自動化生產的普及，100%地實施全面檢驗已成為一項趨勢。然而檢驗作業並不能為產品帶來任何附加價值，因此多年以來許多學者以統計的角度尋求以最低的檢驗次數來保障產品的品質。隨著產品功能日趨複雜，檢驗系統所需檢驗的項目也日趨增加，若是 100%地對所有產品實施檢驗，將使得檢驗系統承受相當大的負擔。因此如何有效運用生產系統的檢驗資源，減少不必要的檢驗，並且能保障產品品質及降低生產成本是生產管理上相當重要的議題。因此規畫需要多少檢驗站並決定在哪些生產階段從事何種形式的檢驗策略，是一項重要的決策。
本研究並把允收抽樣檢驗之檢驗站設置議題考量至多階生產系統中。經由貝式定理分析，本研究所建構之數學模式，以最小成本為決策考量，找出生產系統中需在那個工作站後設置檢驗站，並且決定以何種策略實施檢驗。本研究提供了一種新的邏輯思維，面對多階生產系統中是否要檢驗的決策，除了零(不設置檢驗站)與壹(設置檢驗站)之外，尚可考量介於零與壹之間的檢驗策略(跳批檢驗)。另外，本研究提出較Hsu[1984]合理之模式。同時，本研究亦提出一啟發式演算法，可以解較大之系統且大幅度地降低求解所需要的時間。

關鍵詞：檢驗站設置，單次允收抽樣檢驗，多階生產系統

關鍵字

多階生產系統 ； 單次允收抽樣檢驗 ； 檢驗站設置

並列摘要

ABSTRACT
Inspection is a necessary task in production systems. With advanced technology and highly automated production, complete inspection for high-value products has become a trend. However, inspection does not add any value on products, so people work very hard, on one hand to minimize the times of inspection using statistic methods, but on the other hand to maintain the quality of product. When functions of a product are getting more complicated, more inspections are needed. If complete inspection is required, then there would be tremendous amount of burden on the inspection system. Therefore, efficient handling inspection, reduction of unnecessary inspection, and guarantee of product quality have been important issues. The goal is to minimize cost and maximize profit with a good strategy of inspection.
This research considers sampling on the inspection allocation problem for multistage production systems. Using a Bayesian theorem analysis, a mathematical model is developed for minimizing total cost in order to setup the optimal inspection strategy, which is a skip-lot inspection plan between zero (not allocating inspection station) and one (allocating inspection station and inspecting lot by lot). In addition, comparing with the literature, this study finds a more rational model than Hsu’s model (1984). Moreover, this study develops a heuristic method, which can solve much larger sizes of system with much less CPU time.
Keywords: Inspection allocation, sampling plan, multistage production systems.

並列關鍵字

sampling plan ； Inspection allocation ； multistage production systems.

參考文獻

朱育宏，「生產系統檢驗站設置問題之研究」，中原大學工業工程所碩士論文，2001

Bai, D. S. and Yun, H. J., “Optimal Allocation of Inspection Effort in A Serial Multi-Stage Production System” Computers and Industrial Engineering, Vol.30, No. 3, 1996, pp. 387-396

Ballou, D. P. and Pazer, H. L., “The Impact of Inspector Fallibility on the Inspection Policy in Serial Production Systems” Management Science, Vol. 28, No. 4, April 1982

Barad, M., “A Break-Even Quality Level Approach to Location of Inspection Station in a Multi-Stage Production Process” International Journal of Production Research, Vol. 28, No. 1, 1990, pp. 29-45.

Chakravarty, A. K., “Strategic Allocation of Inspection Effort In a Serial, Multi-Product Production System” IIE Transactions, March 1987, pp.13-22