庫存等候系統中需求回應時間機率分配之研究

The Approximated Distributions of Demands Response Time in a Serial Inventory-Queue System

石燕真(Yen-Chen Shin)

指導教授 ： 張國華

中原大學/工學院/工業工程研究所/碩士(2007年)

https://doi.org/10.6840/cycu200700429

摘要

摘要
在全球消費性產品供應鏈中，組裝生產業扮演著重要的角色，例如筆記型電腦。生產者除了利用存貨式生產(Make to Stock;簡稱MTS )滿足一般需求之外，他們通常也必須因應產品多樣化的趨勢去接受客製化產品的客製化訂單，並採用接單式生產(Make to Order ;簡稱MTO)來生產以快速回應客製化需求，在此我們將需求到達至需求滿足的時間稱之為需求回應時間(response time)。在普通情況下，一般需求到來是在生產計畫當中的，所以一般需求到達時必須立刻滿足他，然而對客製化需求而言他是快速且不定時間的，對生產者來說，替客製化需求特別開設一條MTO生產線來生產是不賺錢的，因為客製化需求的產品通常只有些許的差異，所以生產者通常考慮將MTO嵌入MTS，這變為一個混線生產系統，故混線生產系統的設置是管理者的重要課題。
本論文將要利用設置基本庫存量的控制方式去探討混線庫存等候系統中的需求回應時間，並以Lindley-type的遞迴式作為分析的方式。如果該需求到達前所有的基本量都為已知，此遞迴式可明確的計算出某一需求的回應時間，並可表示出回應時間在站與站以及與需求間的關係，且找出回應時間的分配再進一步建立成本結構，在系統績效指標決定之下中找出最小總成本之最佳基本庫存量的設置。

關鍵字

庫存等候線系統 ； Lindley遞迴式 ； 需求之回應時間 ； 基本庫存量 ； 機率分配

並列摘要

Abstract
Assembly manufacturing plays a very important role in the global supply chain of consumer products, such as laptop computers. Assemblers, in addition to fulfill the ordinary demands for the regular products by adopting make-to-stock (MTS) production, they are often asked to take care of the special demands for the customized products and to adopt make-to-order(MTO) production. The time elapsing between the demand arriving at the system and obtaining the end-production is called the response time of the demand. In usual cases, ordinary demands are the planned orders and should be satisfied immediately, however, there is a time window for the special demand. To the assembler, it is not profitable to maintain a solo MTO production line exclusively for the special demands. Since these customized products are only slightly different from the regular ones, the assembler will usually consider embedding the MTO lines into the main stream MTS lines, which become a hybrid production system. The corresponding design and the control issues for the hybrid lines are crucial to the management.
In this research, we analyze the response time of the demand in a hybrid production system .We consider the base stock policy for accelerating the response to the demand and we study the Lindley-type recursive equations for the response time of the demand and the waiting time in queue by decomposition the system to the system. From Lindley-type recursive equations for the waiting time in queue, we can express the information from those preceding customers are available with the response time of the demand if based on these equations, we can also study the probability distribution of the response time of the demand. We are setting up cost structure and finding out the minimum total cost determining system performance measures such as optimal probability of no delay and the expect delay of the response time of demand on the basic stocks.

並列關鍵字

Lindley-type Recursive Equations. ； Base Stock Policy ； Queueing System ； Response Time of Demands ； Probability Distribution ； Production and Inventory system

參考文獻

[1] Bai, L., Fralix, B., Liu, L. and Shang, W., “Inter-Departure Times in Base-Stock Inventory-Queues,” Queueing Systems, No.47, pp.345-361, 2004.

[2] Buzacott, J. A., Price, S. M., Shanthikumar, J. G., “Service Level in Multistage MRP and Base Stock Controlled Production Systems,” New Directions for Operations Research in a Manufacturing System, pp.445-463, 1992.

[4] Carr, S. and Duenyas, I., “Optimal Admission Control and Sequencing in a Make to Stock/Make to Order Production System,” Operational Research, No.48, pp.709-720, 2000.

[7] Duri, C., Frein, Y., Mascolo, M. D., “Performance Evaluation and Design of Base Stock Systems,” European Journal of Operational Research, No.127, pp.172-188, 2000.

[8] Ettl, M., G. E. Feigin, G. Y. Lin, D. D., “A supply network model with base-stock control and service requirements,” Operational Research, 48 pp.216–232, 2000.