在工業裝備製造領域，隨著產品規格的多樣化，大多數產品和製程都必須客製化，因而大大影響了產品生命週期的時間和成本。基於上述原因，良好的供應鏈管理將可以有效控制生產的製造時間和成本，從而增加企業利潤。良好的供應鏈管理最重要的任務是追蹤動態的、大量的客製產品訂單，即時選擇最合適的零組件供應商，以及管理向供應商所派出的訂單。本研究合作的產學方公司為一家客製化變壓器製造商。該公司目前主要通過主觀判斷（經驗法則）的方式來選擇其零組件供應商並進行派單。本研究將建立一個智能供應商選擇和派單系統，使用層次分析法（AHP）建立每個預定義標準的優先向量權重，然後將這些權重導入多目標整數規劃（MOIP）模型中以構建最合適的派單策略。每次派單完成後，由績效評估系統對所選擇之供應商的績效進行評估，將其表現量化並導入MOIP模型做為未來供應商選擇的其中一項依據。最後，本研究也將對此智能供應商選擇和派單系統中的參數進行敏感度分析，以了解這些參數值的改變對於模型結果的影響。本研究所開發之系統可以有效減少採購人員主觀因素對供應鏈管理和後續廠內生產效率的影響，為企業在選擇供應商時提供一個客觀準則。

In the field of industrial equipment manufacturing, with the diversification of product specifications, most products and productions must be customized, which affects the time and cost of the production lifecycle. For the above reason, having good supply chain management can effectively control the manufacturing time and cost of the production, thereby increasing profits. The most important task of a good supply chain management is to track dynamic and massive customized product orders, select the most suitable component suppliers in real time, and then manage the order dispatched to the suppliers. The collaborating research company in this research is a customized transformer manufacturer. Currently, the way they select component suppliers and dispatching orders is mainly through the subjective judgment (rule of thumb). This research will establish an intelligent supplier selection and order dispatching system, using the Analytic Hierarchy Process (AHP) to establish the priority vector weights of each pre-defined criterion, and these weights is then imported into a multi-objective integer programming (MOIP) model to construct the most suitable order dispatching strategy. After each order dispatch, the performance of the selected supplier is then evaluated by a performance evaluation system, which generates a score for the selected supplier and will be imported into the MOIP model for future supplier selection. Finally, this study will conduct two sensitivity analyses on the parameters in the proposed intelligent supplier selection and order dispatching system to find out the impact of changes in these parameters to the outcome of the proposed model. The proposed system can reduce the impact of the subjective factors of the purchasing personnel on the supply chain management and subsequent in-plant production efficiency, and offers an objective rule for selecting suppliers.

摘要 I
Abstract II
Table of Contents IV
List of Figures VI
List of Tables VII
1. Introduction 1
1.1 Research Background 1
1.2 Research Purpose 2
1.3 Research Framework 3
2. Literature Review 5
2.1 Ontology for Supplier Selection 6
2.2 Analytic Hierarchy Process (AHP) 7
2.3 Multi-Objective Optimization Models for Supplier Selection and Order Dispatching 9
2.4 Reinforcement Learning (RL) 11
3. Methodology 14
3.1 QCDS-Data Driven AHP Model 15
3.2 Multi-Objective Integer Programming (MOIP) Model Formulation 20
3.3 Performance Evaluation System 29
4. Case Study 31
4.1 Parameter Setting 31
4.2 System Output 36
4.3 Sensitivity Analysis 41
5. Conclusions 49
References 51

1. Abu Zwaida, T., Pham, C., & Beauregard, Y. (2021). Optimization of inventory management to prevent drug shortages in the hospital supply chain. Applied Sciences, 11(6), 2726.
2. Blank, J., & Deb, K. (2020). Pymoo: Multi-objective optimization in python. IEEE Access, 8, 89497-89509.
3. Bhutia, P. W., & Phipon, R. (2012). Application of AHP and TOPSIS method for supplier selection problem. IOSR Journal of Engineering, 2(10), 43-50.
4. Cavalcante, I. M., Frazzon, E. M., Forcellini, F. A., & Ivanov, D. (2019). A supervised machine learning approach to data-driven simulation of resilient supplier selection in digital manufacturing. International Journal of Information Management, 49, 86-97.
5. Charnes, A., & Cooper, W. W. (1957). Management models and industrial applications of linear programming. Management science, 4(1), 38-91.
6. Che, Z., Chiang, T.-A., & Lin, T.-T. (2021). A multi-objective genetic algorithm for assembly planning and supplier selection with capacity constraints. Applied Soft Computing, 101, 107030.
7. de Almeida, E. M., & Asada, E. N. (2015). NSGA-II applied to the multi-objective Distribution System Expansion Planning problem. Paper presented at the 2015 18th International Conference on Intelligent System Application to Power Systems (ISAP).
8. Deb, K., & Jain, H. (2013). An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints. IEEE transactions on evolutionary computation, 18(4), 577-601.
9. Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation, 6(2), 182-197.
10. Deng, D. (2021). A Performance Evaluation Model Based on AHP and Its Application. Paper presented at the 2021 International Conference of Social Computing and Digital Economy (ICSCDE).
11. Dogan, I., & Güner, A. R. (2015). A reinforcement learning approach to competitive ordering and pricing problem. Expert Systems, 32(1), 39-48.
12. Dweiri, F., Kumar, S., Khan, S. A., & Jain, V. (2016). Designing an integrated AHP based decision support system for supplier selection in automotive industry. Expert Systems with Applications, 62, 273-283.
13. Eiben, A., & Smith, J. (2015). Introduction to Evolutionary Computing: Springer.
14. Erceg, Ž., & Mularifović, F. (2019). Integrated MCDM model for processes optimization in supply chain management in wood company. Operational research in engineering sciences: Theory and applications, 2(1), 37-50.
15. Fallahpour, A., Olugu, E. U., & Musa, S. N. (2017). A hybrid model for supplier selection: integration of AHP and multi expression programming (MEP). Neural Computing and Applications, 28(3), 499-504.
16. Fashoto, S. G., Akinnuwesi, B., Owolabi, O., & Adelekan, D. (2016). Decision support model for supplier selection in healthcare service delivery using analytical hierarchy process and artificial neural network. African journal of business Management, 10(9), 209-232.
17. Ghorabaee, M. K., Zavadskas, E. K., Olfat, L., & Turskis, Z. (2015). Multi-criteria inventory classification using a new method of evaluation based on distance from average solution (EDAS). Informatica, 26(3), 435-451.
18. Golmohammadi, D. (2011). Neural network application for fuzzy multi-criteria decision making problems. International Journal of Production Economics, 131(2), 490-504.
19. Govindan, K., & Sivakumar, R. (2016). Green supplier selection and order allocation in a low-carbon paper industry: integrated multi-criteria heterogeneous decision-making and multi-objective linear programming approaches. Annals of Operations Research, 238(1-2), 243-276.
20. Hamdan, S., & Jarndal, A. (2017). A two stage green supplier selection and order allocation using AHP and multi-objective genetic algorithm optimization. Paper presented at the 2017 7th International Conference on Modeling, Simulation, and Applied Optimization (ICMSAO).
21. He, Z., Tran, K.-P., Thomassey, S., Zeng, X., Xu, J., & Yi, C. (2021). A deep reinforcement learning based multi-criteria decision support system for optimizing textile chemical process. Computers in Industry, 125, 103373.
22. Hosseini, S., & Al Khaled, A. (2019). A hybrid ensemble and AHP approach for resilient supplier selection. Journal of Intelligent Manufacturing, 30(1), 207-228.
23. Kemmer, L., von Kleist, H., de Rochebouët, D., Tziortziotis, N., & Read, J. (2018). Reinforcement learning for supply chain optimization. Paper presented at the European Workshop on Reinforcement Learning.
24. Lo, H.-W., Liou, J. J., Wang, H.-S., & Tsai, Y.-S. (2018). An integrated model for solving problems in green supplier selection and order allocation. Journal of Cleaner Production, 190, 339-352.
25. Mahdi, P. M., & Mohammad, S.-M. (2017). A hybrid genetic algorithm for dynamic virtual cellular manufacturing with supplier selection. The International Journal of Advanced Manufacturing Technology, 92(5-8), 3001-3017.
26. Majumder, M. (2015). Multi criteria decision making. In Impact of urbanization on water shortage in face of climatic aberrations (pp. 35-47): Springer.
27. Mondragon, A. E. C., Mastrocinque, E., Tsai, J.-F., & Hogg, P. J. (2019). An AHP and fuzzy AHP multifactor decision making approach for technology and supplier selection in the high-functionality textile industry. IEEE Transactions on Engineering Management.
28. Nazari-Shirkouhi, S., Shakouri, H., Javadi, B., & Keramati, A. (2013). Supplier selection and order allocation problem using a two-phase fuzzy multi-objective linear programming. Applied Mathematical Modelling, 37(22), 9308-9323.
29. Nazeri, A., & Bafruei, M. K. (2015). Implementation of meta-heuristic algorithms for supplier selection and evaluation and multi product order allocation. J. UMP Soc. Sci. Technol. Manag, 3(3).
30. Noy, N. F., & McGuinness, D. L. (2001). Ontology development 101: A guide to creating your first ontology. In: Stanford knowledge systems laboratory technical report KSL-01-05 and ….
31. Park, K., Kremer, G. E. O., & Ma, J. (2018). A regional information-based multi-attribute and multi-objective decision-making approach for sustainable supplier selection and order allocation. Journal of Cleaner Production, 187, 590-604.
32. Puška, L. A., Kozarević, S., Stević, Ž., & Stovrag, J. (2018). A new way of applying interval fuzzy logic in group decision making for supplier selection. Economic Computation & Economic Cybernetics Studies & Research, 52(2).
33. Ray, A. K., Jenamani, M., & Mohapatra, P. K. (2011). Supplier behavior modeling and winner determination using parallel MDP. Expert Systems with Applications, 38(5), 4689-4697.
34. Saaty, T. L. (1990). How to make a decision: the analytic hierarchy process. European Journal of operational research, 48(1), 9-26.
35. Siksnelyte-Butkiene, I., Zavadskas, E. K., & Streimikiene, D. (2020). Multi-criteria decision-making (MCDM) for the assessment of renewable energy technologies in a household: A review. Energies, 13(5), 1164.
36. Sureeyatanapas, P., Sriwattananusart, K., Niyamosoth, T., Sessomboon, W., & Arunyanart, S. (2018). Supplier selection towards uncertain and unavailable information: An extension of TOPSIS method. Operations Research Perspectives, 5, 69-79.
37. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction: MIT press.
38. Tirkolaee, E. B., Mardani, A., Dashtian, Z., Soltani, M., & Weber, G.-W. (2020). A novel hybrid method using fuzzy decision making and multi-objective programming for sustainable-reliable supplier selection in two-echelon supply chain design. Journal of Cleaner Production, 250, 119517.
39. Tusnial, A., Sharma, S. K., Dhingra, P., & Routroy, S. (2020). Supplier selection using hybrid multicriteria decision-making methods. International Journal of Productivity and Performance Management.
40. Vahidi, F., Torabi, S. A., & Ramezankhani, M. (2018). Sustainable supplier selection and order allocation under operational and disruption risks. Journal of Cleaner Production, 174, 1351-1365.
41. Yan, L. C., Yoshua, B., & Geoffrey, H. (2015). Deep learning. nature, 521(7553), 436-444.
42. Yannibelli, V., Pacini, E., Monge, D., Mateos, C., & Rodriguez, G. (2020). A Comparative Analysis of NSGA-II and NSGA-III for Autoscaling Parameter Sweep Experiments in the Cloud. Scientific Programming, 2020.
43. You, L., Yao, D.-Q., Sikora, R. T., & Nag, B. (2017). An Adaptive Supplier Selection Mechanism in E-Procurement Marketplace. Journal of International Technology and Information Management, 26(2), 94-116.
44. Zhang, Q., Guo, Z., Man, F., & Ma, J. (2020). Evaluation and selection of manufacturing suppliers in B2B E-commerce environment. Complexity, 2020.