臺灣博碩士論文加值系統

由於近年來消費意識提升，消費者在選購產品時，除了考慮價格的因素外，會進一步了解、比較該產品的售後服務。所以各產業在設計與生產一產品時，更會考量到產品末端的售後服務機制，以提升市場的競爭力。
因此本研究提出了一個多目標數學模式，以達到最小總成本及維修設施之間之平均利用率差異為主要目標，希望能提供企業做參考。其中本研究在模式中加入後送機率，即一般維修站無法完成維修，必須送往專業維修站進行維修之機率。
在指派方面，本研究發現，當單獨考量總成本時，屬於集中式策略；當單獨考量平均利用率差異時，屬於分散式策略。
在求解方面，本研究提出一個改良式類免疫演算法，主要加入了漢明距離、刪除受支配解及菁英政策之機制。最後進行測試範例求解，並且與類免疫及基因演算法進行比較；結果發現求解品質都比基因及類免疫演算法佳，對基因演算法而言，當問題規模越大時，求解品質差異越小，但對類免疫演算法而言，當問題規模越大時，求解品質差異越大。
最後進行後送機率、初始母體數量及終止世代之敏感度分析。由分析結果發現，後送機率會對總成本造成影響，當後送機率較小時，所需的專業維修站數量較少；反之，當後送機率變大時，所需的專業維修站數量變多，且一般與專業維修站之間的距離會因為了減少運送成本而拉近。由結果分析發現，初始母體數量及終止世代會對求解的品質及速率造成影響。求解品質方面，在問題規模較小時，所造成的影響較小；反之，對問題規模較大時，具有較大的影響，當初始母體及終止世代越大，求解的品質就越好。在求解速率方面，不管在哪種問題規模，都具有很大的影響，當初始母體及終止世代越大，求解過程所需的時間就越長。
綜觀本研究成果，能在同時兼顧顧客服務品質與維修中心產能利用率的狀況下，設計一良好的逆物流網路，供業界在實務設計維修服務路網時參考使用，促使物流網路設計更加完善，冀望能創造零售商與顧客雙贏的局面，始為本研究之目的與貢獻所在。

In recent years, an increasing number of consumers are considering not only the price factor but also the after-care service when buying a product. Therefore, for enhancing the market competitiveness of a product, the producer would anticipate the after-care service mechanism before designing and manufacturing it.
The goal of this study is proposing a multi-objective mathematical model for getting the minimum total cost and the difference of average utilization rate between maintenance facilities, which can provide some references for the industry. In this study, the evacuation probability is added into the model, which is the possibility of the products that can not be fixed completely by general maintenance stations and needs to be sent to professional ones and repaired.
In the allocation of the model, when only consider about the total cost, it is the centralized strategy; when only consider about the the difference of average utilization rate between maintenance facilities, it is the decentralized strategy.
In the solution of the model, an improved immune algorithm is proposed in this study, which introduces the mechanism of Hamming distance, and deletes the dominanted solution and elite policy. Then, the solution of test samples is carried out, and it is compared with the immune and genetic algorithms. According to the results, it is found that the quality of solution in improved immune algorithm is better than that in immune and genetic algorithm. Moreover, for the genetic algorithm, the difference of solutions between two algorithms is reduced when the scale of the problem is smaller; but for the immune algorithm, the difference of solutions between two algorithms is increased when the scale of the problem is larger..
Finally, the analyses of sensitivities for evacuation probabilities, number of initial population and termination generations are executed. The results show that the evacuation probabilities influence the total cost, which means the number of professional maintenance stations becomes less when evacuation probabilities decrease. On the other hand, when the evacuation probabilities increase, the needed number of professional maintenance stations becomes more. Also, the distance between general and professional maintenance stations will decrease because of the reduction of transportation costs.
According to the results of analyses, it is found that the number of initial population and termination generations will influence the quality and speed of solution. With regard to the qualities of solution, the influence is less when the scale of the problem is smaller. On the contrary, the influence is greater when the scale of the problem increases, which illustrates that the qualities of solution is better when the number of initial population and termination generations are greater. No matter what the scale of the problem is, it has a great influence on the speed of solution. And, it spends more time for solving process when the initial population and termination generations are greater.
In terms of the results, the study proposes a good design of reverse logistics network, which gives consideration to both quality of customer service and capacity utilization of maintenance center. It can provide the industry with the reference for practical design of service network, which makes the design of logistics network more faultless. It is hoped to create a win-win situation for both retailers and customers, which is the goal and contribution of this study.

目錄…………………………………………….………………………………… i
表目錄………………………………………………………………………….... v
圖目錄……………………………………………………………………...……. x
一、緒論………………………………………………………………………… 1
1.1 研究背景與動機……………………………………………………. 1
1.2 研究目的……………………………………………………………….. 2
1.3 研究方法與流程……………………………………………………….. 3
二、文獻回顧……………………………………………….…………………... 5
2.1 區位問題……………………………………………………………….. 5
2.1.1 區位問題介紹…………………………..………………………… 5
2.1.2 小結………………………………..……………………………… 7
2.2 售後服務及逆物流…………………………….………………………. 7
2.2.1 售後服務……………………………….………………………….. 7
2.2.2 逆物流…………………………………….………………………. 9
2.2.3 逆物流相關文獻………………………….………………………. 10
2.3 多目標規劃………………………………….……………………. 14
2.3.1 柏拉圖最佳解(pareto Solution)………….………………………. 15
2.3.2 多目標求解法…………………………….………………………. 16
2.3.3 小結………………………………..……………………………… 17
2.4 類免疫演算法………………………………….……………………. 17
2.4.1 免疫系統…………………………………….……………………. 17
2.4.2 淋巴系統………………………………….………………………. 18
2.4.3 抗原與抗體……………………………….………………………. 20
2.4.4 株落選擇與記憶細胞…………………….………………………. 22
2.4.5 小結………………………………..……………………………… 23
2.5 基因演算法………………………………….……………………. 24
2.5.1 基因演算法步驟內容…………………….………………………. 27
2.5.2 相關文獻………………………………….………………………. 29
2.5.3 小結……………………………………….………………………. 30
2.6 田口實驗方法………………………………….……………………. 30
三、模式建立與演算求解法……………………………….…………………… 33
3.1問題描述……………………………….………………………………. 33
3.2模式建構……………………………….………………………………. 34
3.2.1 問題假設與限制……………………….…………………………. 34
3.2.2 符號定義……………………………….…………………………. 35
3.2.3 數學模式……………………………….…………………………. 36
3.3 模型驗證………………………………….…………………………. 38
3.2.1 範例一說明…………………………….…………………………. 38
3.2.2 範例一求解…………………………….…………………………. 40
3.2.3 範例二說明…………………………….…………………………. 41
3.2.4 範例二求解…………………………….…………………………. 41
3.2.5 小結…………………………………….…………………………. 45
3.3 改良式類免疫求解法…………………………….……………………. 45
3.4　基因演算求解法……………………………….……………………... 53
四、測試範例求解與敏感度分析………………………….……………………
58
4.1測試範例……………………………….………………………………. 58
4.1.1問題描述與環境設定……………………………………………… 58
4.1.2多目標式正規化……………………………….…………………. 63
4.1.3最小化總成本…….…………………………….…………………. 63
4.1.4最小化平均利用率差異……………………….…………………. 67
4.2參數設定………………………………………………………………… 73
4.2.1基因演算法實驗參數設定……………………………………… 73
4.2.2基因演算法實驗結果分析……………………………………… 74
4.2.3改良式演算法實驗參數設定…………………………………… 77
4.2.4改良式演算法實驗結果分析…………………………………… 77
4.2.5小結………………………………………………………………… 80
4.3測試範例求解及演算法績效分析…………………………………… 81
4.3.1　總節點數25之測試範例求解…...……………………….………….. 81
4.3.2　總節點數50之測試範例求解…...……………………….………….. 85
4.3.3　總節點數80之測試範例求解…...……………………….………….. 88
4.3.4　小結……………………...…………………………………………… 94
4.4改良式類免疫演算法績效分析……………………………………… 99
4.4.1　總節點數25之測試範例求解…...……………………….………….. 99
4.4.2　總節點數50之測試範例求解…...……………………….………….. 102
4.4.3　總節點數80之測試範例求解…...……………………….………….. 105
4.4.4　小結………………………………………………………….….. 108
4.5敏感度分析……………………………………………………………… 113
4.5.1　後送機率－敏感度分析…………………………….………….. 113
4.5.2　初始母體－敏感度分析…………………………….………….. 117
4.5.2.1總節點數25之求解分析……….…………………………... 117
4.5.2.2總節點數50之求解分析……….…………………………... 119
4.5.2.3總節點數80之求解分析……….…………………………... 121
4.5.3　終止世代－敏感度分析…………………………….………….. 124
4.5.3.1總節點數25之求解分析……….…………………………... 124
4.5.3.2總節點數50之求解分析……….…………………………... 126
4.5.3.3總節點數80之求解分析……….…………………………... 128
4.5.4　小結………………………………………………………….….. 132
五、結論及建議…………………………………………….……………………
133
5.1結論…………………………………….………………………………. 133
5.2建議……………………………………………………………………… 134
參考文獻……………………………………………………………….……………. 135
附錄一：LINGO 範例一求解…….…………………………………..…………… 139
附錄二：LINGO 範例二求解（目標式一）……………………………………… 141
附錄三：LINGO 範例二求解（目標式二）……………………………………… 143
附錄四：LINGO 範例二求解（合併目標式）…………………………………… 145
附錄五：測試範例一資料－總節點數25………………….……………………… 147
附錄六：測試範例二資料－總節點數25………………….……………………… 148
附錄七：測試範例三資料－總節點數25………………….……………………… 149
附錄八：測試範例一資料－總節點數50………………….……………………… 150
附錄九：測試範例二資料－總節點數50………………….……………………… 151
附錄十：測試範例三資料－總節點數50………………….……………………… 152
附錄十一：測試範例一資料－總節點數80……………….……………………… 153
附錄十二：測試範例二資料－總節點數80……………….……………………… 155
附錄十三：測試範例三資料－總節點數80……………….……………………… 157
附錄十四：標準L9直交表…………. …………………………………….……… 159
附錄十五：標準L18直交表………….…………………………………………… 160

1.PC Shopper電腦買物王，2006年8月15日，http://www.ettoday.com/2006/08/15/339-1978147.htm。
2.林耕全，2005，裝修工程廢棄物回收站與再利用廠設置最佳化區位評選之研究，國立中央大學，營建管理研究所碩士論文。
3.林萍珍，1998，遺傳演算法在使用者導向的投資組合選擇之應用，國立中央大學，資訊管理學系研究所碩士論文。
4.美國逆向物流協會網站，http://www.rlec.org。
5.馬誠韋，2001，解答多目標規劃的新方法-免疫系統法，元智大學，工業工程與管理研究所碩士論文。
6.許志義，1994，多目標決策，五南出版社，台北。
7.許鈞婷，2006，售後服務滿意對忠誠意願影響之研究--以信任及承諾為中介變數，國立高雄第一科技大學，行銷與流通管理所碩士論文。
8.張庭嘉，2004，應用基因演算法於全球退貨維修系統之規劃--以主機板產業為例，中原大學，工業工程研究所碩士論文。
9.張慶彬，2004，應用分散式類免疫演算法於散熱片之最佳化設計，大同大學，機械工程研究所碩士論文。
10.廖子銘，2000，類免疫演算法於多目標最佳化問題之研究與應用，大同大學，機械工程研究所碩士論文。
11.鄧宏安，2003，整合CFDRC及類免疫演算法於散熱片之最佳化設計，大同大學，機械工程研究所碩士論文。
12.蔡麗敏，2000，廢輪胎處理廠區位指派與運送路線選擇之研究，國立交通大學，交通運輸研究所碩士論文。
13.蘇朝墩，2006，品質工程，三民書局，台北。
14.Altiparmak, F., Gen, M., Lin, L. and Paksoy, T., 2006, “A genetic algorithm approach for multi-objective optimization of supply chain networks”, Computers & Industrial Engineering 51, pp.197-216
15.Amini, M.M., Retzlaff-Roberts D. and Bienstock, C.C., 2005, “Designing a reverse logistics operation for short cycle time repair services”, Int. J. Production Economics, 96, pp.367–380
16.Anell, Barbro I. and Timothy L. Wilson, 2001, ” Channel Structures of International After-Sales Service Networks”, Journal of Marketing Channels, 9 (1/2), pp.93–124
17.Asugman, G., Johnson, J.L. and McCullough, J., 1997, “The Role of After-sales Service in International Marketing”, Journal of International Marketing, vol.5, no.4, pp.11–28
18.Blumberg, D.F., 1999. “Strategic examination of reverse logistics & repair service requirements, needs, market size, and opportunities”, Journal of Business Logistics, 20 (2), pp.141–159.
19.Busacca, P.G., Marseguerra, M., and Zio, E., 2001, “Multiobjective optimization by genetic algorithms: application to safety systems”, Reliability Engineering and System Safety, 72, pp.59–74
20.Carter, C. R. and Ellram, L. M., 1998, “Reverse logistics: A Review of the Literature and Framework for Future Investigation,” Journal of Business Logistics, Vol. 19, No. 1, pp.85–102
21.Chankong, V., Haimes, Y.Y., 1983. “Multiobjective Decision Making: Theory and Methodology”, North-Holland, NewYork.
22.Cheng, F. Y., Li, D., 1998, “Genetic algorithm development for multiobjective optimization of structures”, American Institute of Aeronautics and Astronautics Journal, 36 (6), 1105.
23.Dennis, M.J. and Kambil, A., 2003, “Service management: Building profits after the sale”, Supply Chain Management Review (January/February), pp.42–48.
24.Dowlatshahi, S., 2000, “Developing a Theory of Reverse Logistics,” Interfaces, Vol. 30,No.3, pp.143–155
25.Du, F and Evans, G.W., 2008, “A bi-objective reverse logistics network analysis for post-sale service”, Computers & Operations Research, 35, pp.2617–2634
26.Fleischmann, M., Bloemhof-Ruwaard, J.M., Dekker, R., Laan, E.V.D., Nunen, J.A.E.E.V., and Wassenhove, L.N.V., 1997, “Quantitative models for reverse logistics: A review”, European Journal of Operation Research, 103, pp.1-17
27.Fleischmann, M., Krikke, H.R., Dekker R., and Flapper S.D.P., 2000, “A characterization of logistics networks for product recovery”, Omega , 28, pp.653–666.
28.Hajela, P., Yoo, J., and Lee, J., 1997, “GA based simulation of immune networks applications in structural optimization”, Engineering Optimization, 22, pp.131–149.
29.Hakimi, S.L., 1964, “Optimal Location of Switching Centers and the Absolute Centers and Medians of a Graph”, Operations Research, Vol.12.
30.Houck, C.R., Joines, J.A. and Kay, M.G., 1996, “Comparison of genetic algorithms, random restart and two-opt switching for solving large location-allocation problems”, Computers and Operations Research, Vol.23, No.6, pp.587-596.
31.Jayaraman, V., Patterson, R.A. and Rolland E., 2003, “The design of reverse distribution networks:Models and solution procedures”, European Journal of Operational Research, 150, pp.128–149
32.Ko, H.J. and Evans G.W., 2007, “A genetic algorithm-based heuristic for the dynamic integrated forward/reverse logistics network for 3PLs”, Computers & Operations Research, 34, pp.346–366
33.Kursawe, F., 1991. A variant of evolution strategies for vector quantization. In: Schwefel, H.P., Manner, R. (Eds.), Parallel Problem Solving from Nature. Springer, Berlin, pp. 193–197.
34.Lu, Z. and Bostel, N., 2007, “A facility location model for logistics systems including reverse flows: The case of remanufacturing activities” Computers & Operations Research, 34, pp.299–323
35.Marin, A. and Pelegrin, B., 1998, “The return plant location: Modelling and Resolution” European Journal of Operational Research, 104, pp.375–392
36.Min, H.and Ko, H.J., 2007, “The dynamic design of a reverse logistics network from the perspective of third-party logistics service providers”, Int. J. Production Economics
37.Min, H., Ko, H.J. and Ko, C.S., 2006, “Agenetic algorithm approach to developing the multi-echelon reverse logistics network for product returns”, Omega, 34, pp.56–69
38.Murata, T., Ishibuchi, H., & Tanaka, H., 1996, “Multi-objective genetic algorithm and its applications to flowshop scheduling”, Computers and Industrial Engineering, vol. 30(4), pp. 957– 968.
39.Owen, S.H. and Daskin, M.S., 1998, “Strategic facility location: A Review,” European Journal of Operational Research, No.111, pp.423–447.
40.Ommeren, J.C.W.V., Bumb, A.F. and Sleptchenko, A.V., 2006, “Locating repair shops in a stochastic environment”, Computers & Operations Research, 33, pp.1575–1594
41.Poulos, P.N., Rigatos, G.G., Tzafestas, S.G. and Koukos, A.K., 2001, “A Pareto-optimal genetic algorithm for warehouse multi-objective optimization”, Engineering Applications of Artificial Intelligence, 14, pp.737-749
42.Salema, M.I.G., Barbosa-Povoa, A.P. and Novais, A.Q., 2007, “An optimization model for the design of a capacitated multi-product reverse logistics network with uncertainty”, European Journal of Operational Research, 179, pp.1063–1077
43.Silva C.M., Biscaia E.C., and Jr, 2003, “Genetic algorithm development for multi-objective optimization of batch free-radical polymerization reactors”, Computers and Chemical Engineering, 27, pp.1329–1344
44.Stock, J. R., White Paper: Reverse Logistics, USA: Council of Logistics Management, 1998
45.Tazawa, I., Koakutsu, S., and Hirata, H., 1996, “An immunity based genetic algorithm and its application to the VLSI floorplan design problem”, IEEE, pp.417–421.