| 研究生: |
陳心一 Chen, Hsin-I |
|---|---|
| 論文名稱: |
台鐵對號列車延誤預測之研究 Long Distance Train Delay Prediction: Evidence from Taiwan Railway System |
| 指導教授: |
鄭永祥
Cheng, Yung-Hsiang |
| 學位類別: |
碩士 Master |
| 系所名稱: |
管理學院 - 交通管理科學系 Department of Transportation and Communication Management Science |
| 論文出版年: | 2010 |
| 畢業學年度: | 98 |
| 語文別: | 中文 |
| 論文頁數: | 77 |
| 中文關鍵詞: | 鐵路延誤 、類神經網路 、統計預測 、線性迴歸 |
| 外文關鍵詞: | Train punctuality, Neural network, Statistical prediction, Linear regression |
| 相關次數: | 點閱:73 下載:9 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
鐵路系統的延誤高度影響系統可靠度及旅客滿意度,故營運者對於預先預測延誤甚感興趣。實務上常透過模擬的方式評估延誤狀態,隨著系統規模擴大,全尺度的模擬越來越困難,也造成人力需求及成本倍加。
本研究提出一列車延誤狀態的短期預測方法,利用三個月期的延誤歷史資料,透過類神經網路及線性模式,先針對列車是否會延誤進行預測,再進一步預測列車可能的延誤狀態,包含路程中延誤事件數及延誤時間佔行車時間比率。最後針對列車自身、路線、外在環境等各屬性的影響程度進行探討,提出改善建議。
研究發現,類神經網路與線性迴歸模式,用於預測延誤時間時效能接近;週末及國定假日的延誤狀況較嚴重、因路線擁擠產生延誤不顯著、特定車種延誤率偏高、一日中從早到晚延誤率依次增長、南北雙向自強號具有不同延誤型態。研究提出以下延誤改善建議:排點上針對不同時段及區間安排不同餘裕、針對旅次特性設計假日班表等。
Delay of railway trains is highly affecting reliability of the system, and has significant negative impact on customers' satisfaction. Simulation models often used in previous research and in practice to predict the train delay; due to the growth of the scale of system, it turned to be too costly to develop on such problem.
This research suggesting an approach on predicts train delay in the short term by linear model and neural network. With the train operation data of Taiwan Railway Administration for three month, we build several models on predicting weather the train will be delayed on the terminal station, the number of delay incidents on the train's journey and the length ratio of delay time, based on the predictive factors of train, route and environment.
We'd found that delay occurs much often on weekends and holidays; the congestion delay is not obvious in the research area; specific class of train had seriously high delay rates; delay increase from the morning to the evening in every single day; Tze-Chiang express have different delay condition on each directions of research section.
This research suggests that the system operator should build a special holiday timetable, according to the different passenger characteristic and destination between working days and non-working days, also we should increase the headway progressively to avoid the delay accumulate on the time period in a day.
1. Buscema, M., 2002. A brief overview and introduction to artificial neural networks. Substance use & misuse 37(8-10), 1093-1148.
2. Carey, M., Kwieciński, A., 1994. Stochastic approximation to the effects of headways on knock-on delays of trains. Transportation Research Part B 28(4), 251-267.
3. Carey, M., 1999. Ex ante heuristic measures of schedule reliability. Transportation Research Part B 33(7), 473-494.
4. Chang, L, 2005. Analysis of freeway accident frequencies: Negative binomial regression versus artificial neural network. Safety Science 43(8), 541-557.
5. Delen, D., Sharda, R., Bessonov, M., 2006. Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks. Accident Analysis & Prevention 38(3), 434-444.
6. Dessouky, M.M., Lu, Q., Leachman, R.C., 2002. Using simulation modeling to assess rail track infrastructure in densely trafficked metropolitan areas. Proceedings of Winter Simulation Conference. 1, 725-731.
7. Gibson, S., Cooper, G., Ball, B., 2002. Developments in Transport Policy: The Evolution of Capacity Charges on the UK Rail Network. Journal of Transport Economics and Policy 36(2), 341-354.
8. Ginkel, A., Schöbel, A., 2007. To Wait or Not to Wait? The Bicriteria Delay Management Problem in Public Transportation. Transportation Science 41(4), 527-538.
9. Gorman, M.F., 2009. Statistical estimation of railroad congestion delay. Transportation Research Part E 45(3), 446-456.
10. Hall, R., 1987. Passenger Delay in a Rapid Transit Station. Transportation Science 21(4), 279-292.
11. Higgins, A., Ferreira, L., Kozan, E., 1995a. Modelling single line train operations. Transportation Research Record(1489), 9-16.
12. Higgins, A., Ferreira, L., Kozan, E., 1995b. Modelling delay risks associated with train schedules. Transportation Planning and Technology 19(2), 89-108.
13. Higgins, A., Ferreira, L., Kozan, E., 1996. Optimisation of train schedules to achieve minimum transit times and maximum reliability. Proceedings of 13th International Symposium on Transportation and Traffic Theory, 589-614.
14. Higgins, A., Kozan, E., 1998. Modeling Train Delays in Urban Networks. Transportation Science 32(4), 346-357.
15. Kroes, E., Kouwenhoven, M., Duchateau, H., Debrincat, L., Goldberg, J., 2007. Value of Punctuality on Suburban Trains to and from Paris. Transportation Research Record(2006), 67-75.
16. Lu, Q., Dessouky, M.M., Leachman, R.C., 2004. Modeling train movements through complex rail networks. ACM Transactions on Modeling and Computer Simulation 14(1), 48-75.
17. Murali, P., Dessouky, M.M., Ordóñez, F., Palmer, K., 2010. A delay estimation technique for single and double-track railroads. Transportation Research Part E 46(4), 483-495.
18. Nefti, S., Oussalah, M., 2004. A neural network approach for railway safety prediction. Proceedings of 2004 IEEE International Conference on Systems, Man and Cybernetics, 3915-3920.
19. Olsson, N.O.E., Haugland, H., 2004. Influencing factors on train punctuality - results from some Norwegian studies. Transport Policy 11(4), 387-397.
20. Petersen, E., Taylor, A., 1982. A Structured Model for Rail Line Simulation and Optimization. Transportation Science 16(2), 192-206.
21. Tsai, T.H., 2006. Applying artificial neural network models to short-term railway passenger demand forecasting, Ph. D. Thesis, National Cheng Kung University.
22. Tsai, T.H., Lee, C.K., Wei, C.H., 2005a. Short-term railway passenger demand forecasting via a parsimonious multi-layer feed-forward neural network. Proceedings of 25th International Symposium on Forecasting.
23. Tsai, T.H., Lee, C.K., Wei, C.H., 2005b. Design of dynamic Neural Networks to forecast short-term railway passenger demand. Journal of the Eastern Asia Society for Transportation Studies 6, 1651-1666.
24. van Lint, J.W.C., Hoogendoorn, S.P., van Zuylen, H.J., 2005. Accurate freeway travel time prediction with state-space neural networks under missing data. Transportation Research Part C 13(5-6), 347-369.
25. Vromans, M.J.C.M., Dekker, R., Kroon, L.G., 2006. Reliability and heterogeneity of railway services. European Journal of Operational Research 172(2), 647-665.
26. Yuan, J., Hansen, I.A., 2007. Optimizing capacity utilization of stations by estimating knock-on train delays. Transportation Research Part B 41(2), 202-217.
27. 張恩輔 (民91),捷運系統運轉整理之模擬分析,成功大學交通管理科學研究所碩士論文。
28. 黃範哲 (民90),高速鐵路系統運轉整理之研究,成功大學交通管理科學研究所碩士論文。
29. 蔡宗憲、李治綱、魏健宏 (民95),「短期列車旅運需求之類神經網路預測模式建構與評估」,運輸計劃季刊,第三十五卷第四期,頁475-505。
30. 謝興盛 (民92),捷運列車延誤時班距調整模式之模擬分析—以台北捷運中、高運量系統為例,成功大學交通管理科學研究所博士論文。
31. 謝言訢 (民95),台灣高速鐵路延滯應變班表之研究,成功大學交通管理科學研究所碩士論文。