協同規劃、預測與補貨﹙Collaborative Planning, Forecasting and Replenishment; CPFR﹚是協同商務中的一個應用實務，主要強調供應鏈上買賣雙方協同合作流程的概念，以提升供應鏈上流程的處理效率。未來企業的競爭將是產品背後整體供應鏈的激烈競爭，能對於不斷變化的市場需求作出有效預測，進而快速反應的企業將脫穎而出。對於庫存與補貨的掌控能力更將是企業決勝的關鍵因素之一。 CPFR 中的補貨模型是根據銷售預測、訂單預測、存貨策略與供給面資訊來做實際訂單，以作為補貨之用。補貨模式的準確性可以使賣方針對不同的需求來有效分配未來訂單預測的需求量，並降低安全庫存；買方則可根據訂單預測來調整庫存策略與採購數量。 現今廣用的供應商管理存貨（Vendor Managed Inventory, VMI）並沒有像CPFR加入更多的協同項目與精神，因此比較VMI與CPFR的補貨流程的差異性與優劣性，進而提供企業導入CPFR的補貨流程是相當重要的。 本研究以補貨階段為主題，除了探討協同補貨模式所需具備的屬性與輸入變數外，更將建構一個整合供應鏈上、下游協同資訊與符合協同訂單預測特性之預測模型，以提升補貨準確度，進而堆砌出整個CPFR 協同補貨模式，並加以與現今企業廣為採用的供應商管理存貨（Vendor Managed Inventory, VMI）的補貨模式進行比較，證明CPFR優於VMI，進而可供欲導入CPFR 流程下協同補貨模式或一般補貨模式的相關人員之參考。 / CPFR (Collaborative Planning, Forecasting, and Replenishment) is one of the applications of collaborative business. The stressed concept is the cooperation process of sellers and buyers on the supply chain in order to increase the handling efficiency. In the future, the industries would compete on the whole supply chains behind products—only the industry that is capable of making accurate predictions according to the constantly changing market and reacts immediately has the chance of winning. Being able to control the inventory and supply effectively would be one of the key factors leading to an industry’s success. The replenishment model of CPFR is to fill out the order according to the sales prediction, order prediction, inventory strategy, and supply information. The precision of the replenishment model could affect both suppliers and customers. The former can distribute products properly and meet the different demands from the upcoming orders so as to reduce inventory; the latter are able to revise the inventory strategy and amount of order according to the order prediction. A few research papers aimed at the replenishment model, though, most still focus on the management issues like the process framework of CPFR and the implementation benefit. Hence, establishing both an information system that coordinates customer demand with suppliers and a collaborative replenishment model that increases the accuracy of predictions is fairly important. The phase of replenishment, as the subject of this study, will approach on parameters the collaborative replenishment model needs to input and combine evolution strategies with tabu search to establish a replenishment model under the process of CPFR.

本研究以單一汽車貨運業者的角度，評估當運輸需求大於自有車輛服務能力時，考量車種、時窗、貨物量等因素，以最小化成本為目標進行途程規劃，利用運輸水平整合、協同合作的概念，將未能滿足之需求任務委外給其他同業進行。 本研究主要分為兩階段，第一階段先確認是否需要委外，以禁忌搜尋法找出最節省成本之配送途程以及委外任務，解決業者選擇以自有車輛運送或委外給其他運輸業者服務的問題；而第二階段則是在確定委外的任務後，決定委外的對象，不僅考量對方出價，也評估對方的營運能力、商譽、風險管理、服務品質等因素，建構一多準則決策模式，透過網路程序分析法(ANP)決定評選準則權重，再利用VIKOR排序法決定各個方案之排序，希望能在不遺失客戶訂單及信任的期許下，決定最適合的委外對象。 / From the perspective of trucking carriers, concerning transport horizontal integration and collaboration, when the vehicles are insufficient to meet the demand of transport, carrier could seek for other carrier’s help. In this study, we consider vehicle types, capacity, time windows, and the objective of minimum cost, to do vehicle route planning, and also decide which tasks should be outsoursed. There are two phases in this study. First, after checking the insufficiency of own trucks, we use Tabu search to solve Vehicle Routing Problem with a Private fleet and a Common carrier (VRPPC) in order to find out the route of own vehicles and the tasks to be outsourced. In second phase, we will select the carrier to do those tasks. We not only consider the price of outsourcing, but also evaluate the capacity, service quality, risk management, and the goodwill of the company. We use Analytic Network Process (ANP) to decide the weight of each criterion, and VIKOR to rank each case and select the best one.

本論文針對多廠區訂單分配（Multi-plant order allocation）問題進行探討，此問題模式下企業擁有多間製造不同產品之工廠，且生產成本、產能、運送成本等也各自不同，因此這些因素都必須納入訂單分配時的考量。研究中同時考量三個目標：製造成本、配送前置時間和工廠平均產能利用率之均衡性，利用層級分析法（AHP）將三者進行結合，以達到多目標規劃。除了提出此模型架構外，並以基因演算法（Genetic Algorithm）結合層級分析法進行問題的求解，以達到最佳的分配方式，而為了加強求解的品質與效率，利用禁忌搜尋法（Tabu Search）來改善演化過程中，對於產生不可行解的處理方式。在研究最後，將計算結果與過去研究成果作比較，顯示採用基因演算法混合禁忌搜尋法，在求解多廠區訂單分配問題時，可以得到較佳的結果。

近年來，印刷電路板(printed circuit board, PCB)產業在台灣蓬勃發展，對台灣經濟表現有相當重要的影響；與此同時，產業內各廠商卻因內外環境變異等因素，而面臨日益激烈的競爭壓力。本研究針對產業前段的生產工廠(PCB manufacturing)從管理面探討問題來源，發現各廠商所導入的管理系統(MRP、ERP、SCM等)均缺乏現場排程(shop floor scheduling)功能，因此造成排程結果不具可行性，連帶導致管理系統的績效也未如預期理想。 　　為解決該產業所面臨的現場排程問題，本研究透過個案訪談方式，對產業特性深入了解，歸類此類問題為排程領域中的流程型工廠排程問題(flow shop scheduling)。 　　在求解過程中，本研究以總延遲時間(total tardiness)最小化為目標，並以禁忌搜尋法(tabu search)作為最佳化過程的演算法。於理論探討後，本研究亦實際建置一套排程系統，並以來自個案工廠的訂單資料實際求解，以評估此系統績效。