鐵路運輸於台灣扮演重要旅客疏運角色，增加鐵路運量為近年來重要課題。以台灣東部臺東線鐵路為例，目前共計有19處單線區間，成為鐵路路線容量之瓶頸，然而將單線區間雙線化有助於增加路線容量，提升可排入的班次數。
增加鐵道運輸的運輸量，可以藉著排入更多班次，然而班次數受限於路線容量，其中路線容量牽涉的因素眾多，如列車異質性、列車速度以及班表的影響。本研究中以班次數衡量路線容量，探討軌道設計對班次數(路線容量)與旅行時間的影響，並找出瓶頸路段。為了求得最佳解，我們使用基因演算法並結合Lee and Chen (2009)所提出來的求解班表演算法，由於求解效率不佳，亦加入迴歸分析提高求解效率，求得最佳的軌道設計。實測的地點在臺東線，結果顯示單線與雙線有明顯的差異。此研究結果可以在資源有限的情況下選擇最佳的雙線站間，提供台鐵在興建或改善鐵路上的參考數據。

Since the railway system plays an important role in transporting passengers around Taiwan, increasing the line capacity is a major issue. For instance, there are many bottlenecks on the Taitung Line, because of 19 single-track sections. The railway line capacity can be increased by upgrading the single-track sections to double-track lines.
Increasing transport volumes means that the rail operators should schedule more services. However, services are limited by the railway line capacity and such line capacity is affected by several factors, including train-type heterogeneity, speed and schedule effects. This study has evaluated services for railway line capacity, and has investigated the influence of track design (single-track or double-track) on the number of services and travel times, and has identified the bottlenecks. To solve the problem and find the optimal solution, we have designed Genetic Algorithm by combining the heuristic proposed by Lee and Chen (2009) with regression analysis. When tested with real-world examples from the Taitung Line, the results showed that there are significant differences between single-track and double-track lines. To ensure the quality of the problem solving, we have also used Lee and Chen’s (2009) scheduling timetable algorithm to enumerate the solution. The results prove that our algorithms are able to provide an optimal solution that is both accurate and rapid computationally. This research can provide the Taiwan Railways Administration (TRA) with suggestions for the best locations to upgrade their lines from single-track to double-track under conditions of limited resources.

1. 邱子瑜(2014)，台鐵司機員輪班問題之研究，國立成功大學交通管理科學系碩士論文。

2. 黃冠捷(2013)，鐵路車輛編組運用之最佳化，國立成功大學土木工程學系碩士論文。

3. 謝欣宏(2002)，台鐵司機員排班與輪班問題之研究-以基因演算法求解，國立成功大學土木工程學系碩士論文。

4. 蔡欣恬(2014)，以班表試排法評估鐵路路線容量:以臺鐵臺東線為例，國立成功大學土木工程學系碩士論文。

5. 蘇昭旭(1999)，臺灣鐵路火車百科，台北:人人出版社。

6. Abril, M., Barber, F., Ingolotti, L., Salido, M. A., Tormos, P., & Lova, A. (2008). An assessment of railway capacity. Transportation Research Part E-Logistics and Transportation Review, 44(5), 774-806.

7. Bandyopadhyay, S., Murthy, C. A., & Pal, S. K. (2000). VGA-Classifier: Design and applications. Ieee Transactions on Systems Man and Cybernetics Part B-Cybernetics, 30(6), 890-895.

8. Barnhart, C., Jin, H., & Vance, P. H. (2000). Railroad blocking: A network design application. Operations Research, 48(4), 603-614.

9. Barrena, E., Canca, D., Coelho, L. C., & Laporte, G. (2014). Single-line rail rapid transit timetabling under dynamic passenger demand. Transportation Research Part B-Methodological, 70(1), 134-150.

10. Carey, M., & Crawford, I. (2007). Scheduling trains on a network of busy complex stations. Transportation Research Part B-Methodological, 41(2), 159-178.

11. Castillo, E., Gallego, I., Urena, J. M., & Coronado, J. M. (2011). Timetabling optimization of a mixed double- and single-tracked railway network. Applied Mathematical Modelling, 35(2), 859-878.

12. Chen, I. C., Hsu, S. K., Hsu, H. H., Chen, C. Y., Lin, D. Y., Lee, W. H., & Lee, Y. (2011). TrainWorld: A Powerful Tool for Railway Timetabling. Paper presented at the Joint Rail Conference, USA.

13. Cook, D. F., Ragsdale, C. T., & Major, R. L. (2000). Combining a neural network with a genetic algorithm for process parameter optimization. Engineering Applications of Artificial Intelligence, 13(4), 391-396.

14. Dingler, M. H., Lai, Y. C., & Barkan, C. P. (2014). Effect of train-type heterogeneity on single-track heavy haul railway line capacity. Proceedings of the Institution of Mechanical Engineers Part F-Journal of Rail and Rapid Transit, 228(8), 845-856.

15. Grefenstette, J. J. (1986). Optimization of Control Parameters for Genetic Algorithms. Ieee Transactions on Systems Man and Cybernetics, 16(1), 122-128.

16. Harrod, S. (2009). Capacity factors of a mixed speed railway network. Transportation Research Part E-Logistics and Transportation Review, 45(5), 830-841.

17. He, B. S., Song, R., He, S. W., & Xu, Y. (2014). High-Speed Rail Train Timetabling Problem: A Time-Space Network Based Method with an Improved Branch-and-Price Algorithm. Mathematical Problems in Engineering, 2014, 15 pages.

18. Higgins, A., Kozan, E., & Ferreira, L. (1996). Optimal scheduling of trains on a single line track. Transportation Research Part B-Methodological, 30(2), 147-161.

19. Holland, J. H.(1975)，Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence:U Michigan Press。

20. Homaifar, A., & Mccormick, E. (1995). Simultaneous Design of Membership Functions and Rule Sets for Fuzzy Controllers Using Genetic Algorithms. Ieee Transactions on Fuzzy Systems, 3(2), 129-139.

21. Juang, C. F., Lin, J. Y., & Lin, C. T. (2000). Genetic reinforcement learning through symbiotic evolution for fuzzy controller design. Ieee Transactions on Systems Man and Cybernetics Part B-Cybernetics, 30(2), 290-302.

22. Ke, B. R., Lin, C. L., Chien, H. H., Chiu, H. W., & Chen, N. (2015). A new approach for improving the performance of freight train timetabling of a single-track railway system. Transportation Planning and Technology, 38(2), 238-264.

23. Kraay, D. R., & Harker, P. T. (1995). Real-Time Scheduling of Freight Railroads. Transportation Research Part B-Methodological, 29(3), 213-229.

24. Lai, Y. C., Dingler, M., Lin, S. Y., & Liu, K. C. (2013). Optimal track class assignment for a railroad network. Journal of the Operational Research Society, 64(12), 1800-1809.

25. Landex, A. (2009). Evaluation of Railway Networks with Single Track Operation Using the UIC 406 Capacity Method. Networks & Spatial Economics, 9(1), 7-23.

26. Landex, A., Schittenhelm, B., Kaas, A., & Schneider-Tilli, J. (2008). Capacity measurement with the UIC 406 capacity method. Paper presented at the Eleventh International Conference on Computer System Design and Operation in the Railway and Other Transit Systems (COMPRAIL08).

27. Lee, Y., & Chen, C. Y. (2009). A heuristic for the train pathing and timetabling problem. Transportation Research Part B-Methodological, 43(8-9), 837-851.

28. Lin, C. J., & Hsu, Y. C. (2007). Reinforcement hybrid evolutionary learning for recurrent wavelet-based neurofuzzy systems. Ieee Transactions on Fuzzy Systems, 15(4), 729-745.

29. Lin, C. J., & Xu, Y. J. (2005). Efficient reinforcement learning through dynamic symbiotic evolution for TSK-type fuzzy controller design. International Journal of General Systems, 34(5), 559-578.

30. Lindfeldt, O. (2011). An analysis of double-track railway line capacity. Transportation Planning and Technology, 34(4), 301-322.

31. Liu, Y. M., & Wang, C. J. (1999). A modified genetic algorithm based optimisation of milling parameters. International Journal of Advanced Manufacturing Technology, 15(11), 796-799.

32. Lulli, G., Pietropaoli, U., & Ricciardi, N. (2011). Service network design for freight railway transportation: the Italian case. Journal of the Operational Research Society, 62(12), 2107-2119.

33. Moriarty, D. E., & Miikkulainen, R. (1996). Efficient reinforcement learning through symbiotic evolution. Machine Learning, 22(1-3), 11-32.

34. Niu, H. M., & Zhang, M. H. (2012). An Optimization to Schedule Train Operations with Phase-Regular Framework for Intercity Rail Lines. Discrete Dynamics in Nature and Society, 2012, 13 pages.

35. Pazour, J. A., Meller, R. D., & Pohl, L. M. (2010). A model to design a national high-speed rail network for freight distribution. Transportation Research Part a-Policy and Practice, 44(3), 119-135.

36. Sogin, S. L., Lai, Y. C., Dick, C. T., & Barkan, C. P. L. (2013). Comparison of Capacity of Single- and Double-Track Rail Lines. Transportation Research Record: Journal of the Transportation Research Board(2374), 111-118.

37. Su, R. D., Gu, Q. R., & Wen, T. (2014). Optimization of High-Speed Train Control Strategy for Traction Energy Saving Using an Improved Genetic Algorithm. Journal of Applied Mathematics, 2014, 7 pages.

38. Vansteenwegen, P., & van Oudheusden, D. (2006). Developing railway timetables which guarantee a better service. European Journal of Operational Research, 173(1), 337-350.

39. Wong, K. K., & Ho, T. K. (2004). Dynamic coast control of train movement with genetic algorithm. International Journal of Systems Science, 35(13-14), 835-846.

40. Yaghini, M., Nikoo, N., & Ahadi, H. R. (2014). An Integer Programming Model for Analysing Impacts of Different Train Types on Railway Line Capacity. Transport, 29(1), 28-35.

41. Yang, T., Kuo, Y., & Cho, C. (2007). A genetic algorithms simulation approach for the multi-attribute combinatorial dispatching decision problem. European Journal of Operational Research, 176(3), 1859-1873.

42. Zhou, X. S., & Zhong, M. (2007). Single-track train timetabling with guaranteed optimality: Branch-and-bound algorithms with enhanced lower bounds. Transportation Research Part B-Methodological, 41(3), 320-341.

43. Zhu, E. D., Crainic, T. G., & Gendreau, M. (2014). Scheduled Service Network Design for Freight Rail Transportation. Operations Research, 62(2), 383-400.

44. Zwaneveld, P. J., Kroon, L. G., & van Hoesel, S. P. M. (2001). Routing trains through a railway station based on a node packing model. European Journal of Operational Research, 128(1), 14-33.