跳到主要內容

臺灣博碩士論文加值系統

(3.236.110.106) 您好!臺灣時間:2021/07/27 21:06
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:許鳴烝
研究生(外文):Ming-JengHsu
論文名稱:多樓層公路客運場站內部適應性號誌控制模式構建之研究─以臺北轉運站為例
論文名稱(外文):An Adaptive Signal Control Model for Inner Junction of the Taipei Bus Station
指導教授:魏健宏魏健宏引用關係
指導教授(外文):Chien-Hung Wei
學位類別:碩士
校院名稱:國立成功大學
系所名稱:交通管理學系碩博士班
學門:運輸服務學門
學類:運輸管理學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:英文
論文頁數:85
中文關鍵詞:適應性號誌控制模式類神經網路多樓層轉運站轉向比例
外文關鍵詞:adaptive signal control modelartificial neural networkmulti-platform terminalturning ratio
相關次數:
  • 被引用被引用:0
  • 點閱點閱:242
  • 評分評分:
  • 下載下載:60
  • 收藏至我的研究室書目清單書目收藏:0
臺北轉運站位居臺北市之交通樞紐點,高鐵、臺鐵、捷運與國道客運等乘客轉運於此,亦是臺灣西部地區與東部地區之交通轉運樞紐之一。為服務龐大客運班次,且受限於土地資源,臺北轉運站為臺灣第一座多樓層客運轉運站。由於立體站體設計,有別於單一月台層轉運站,服務績效不只在於人(乘客)之乘運效率,車輛於站內之營運績效對於整體系統服務效率影響更為顯著。

營運至今,尖峰時段常因車流交織問題出現壅塞,其中以位於3樓之承德出口較為嚴重,Wei et al. (2011) 對此提出號誌設計模式,根據車流特性(紓解車速、車間距、路口寬度等)以及不同時段之流量特性,進行號誌時制設計之初步探討。然,臺北轉運站之車輛到離站,並非完全依循既定時刻表,車輛到站時間具有不確定性,預設之號誌時制績效仍有改善空間。

因此,本研究嘗試利用站內現有之RFID車輛監測/監控系統與類神經網路之預測功能,預測承德出口於下一個時間區間之交通需求特性(包含到達車流量與轉向比例),並以轉向比例修正既有號誌設計模式之容量參數,構建臺北轉運站內部動態號誌控制模式。本研究亦考量未來路線班次調整或其他可能影響交通特性之外部因素,設計類神經網路持續自我訓練與學習機制,使具有調適場站運轉狀況之功能,根據本研究前測結果,服務績效良好。
Transit systems are solutions for the heavy travel demand problems of high-density areas, which play important roles in congestion mitigation, energy conservation and pollutant reduction. Improving bus arrival and departure on-time performance is a critical concern in reducing users’ wait and transfer time. Unlike a single-platform terminal, bus flow interruption in a multi-level-platform terminal could significantly reduce the service quality and deteriorate environmental condition.

Significant congestion has been experienced during peak periods at a T-junction in the multi-platform bus terminal, Taipei Bus Station, recently launched in the heart of Taipei metropolitan area. Based on the findings for this issue of an analytical signal control model developed by Wei et al. (2011), a traffic demand forecasting model is needed to upgrade the existing pre-timed control strategy to dynamic control level. The artificial neural network approach is employed for constructing the demand forecasting model taking into account the relevant traffic flow information provided by the RFID readers embedded in the terminal monitoring systems in this research.

Considering time-varying demand, this study developed an adaptive signal control model for managing bus traffic in Taipei Bus Station. An off-line operational performance is examined with historical data, followed by on-line preliminary testing by new data. In the case study, the proposed model has demonstrated itself very efficient in reducing congestion within the terminal.
CHAPTER 1 INTRODUCTION 1
1.1 Background 1
1.2 Brief Introduction of TBS 3
1.3 Problem Statement and Research Objectives 5
1.4 Research Procedures 7
CHAPTER 2 LITERATURE REVIEW 10
2.1 Recent Studies on Taipei Bus Station (TBS) 10
2.1.1 Capacity and Level of Service (LOS) 10
2.1.2 Signal Control for Inner Junction in TBS – Time-Dependent Fix Control Plan 11
2.2 Adaptive Signal Control Methods 12
2.2.1 SCATS 13
2.2.2 SCOOT 14
2.2.3 RHODES 14
2.2.4 OPAC 16
2.2.5 ARTC 18
2.3 Artificial Neural Networks Applications in Transportation 20
2.3.1 Artificial Neural Networks 20
2.3.2 Brief Introduction of Relevant Applications 22
2.4 Comments 27
CHAPTER 3 MODEL CONSTRUCTION & EVALUATION CRITERIA 30
3.1 Signal Control Model – Analytical Modeling Approach 31
3.1.1 Discharge Time Functions 32
3.1.2 Delay Functions 36
3.2 Traffic Forecasting Model – Artificial Neural Network (ANN) Approach 37
3.2.1 Forecasting Model Construction 38
3.2.2 Back Propagation Network (BPN) Algorithm of ANNs 39
3.3 Model Evaluation 44
CHAPTER 4 DATA COLLECTION & ANALYSIS 46
4.1 Flow Rate 46
4.2 Turning Factor 51
CHAPTER 5 MODLE CALIBRATION & OFF-LINE EVALUATION 54
5.1 Pre-set Timing Plans 54
5.2 Input Variable Selection for ANN Model 58
5.3 ANN Model Structure 58
5.3.1 Basic Model Calibration 60
5.3.2 Advanced Model Calibration 65
5.4 ANN Model Assessments 71
CHAPTER 6 PRELIMILARY TESTING FOR ON-LINE APPLICATION 72
6.1 Procedure of ON-LINE Evaluation 72
6.2 The Programs of Preliminary Testing 75
6.2.1 Testing Period 75
6.2.2 Sample Size 75
6.2.3 Program and Software 75
6.2.4 Retraining tolerance setting 75
6.3 Results of Preliminary Testing 76
6.4 Sensitivity Analysis 80
6.4.1 Relaxing Retraining Tolerance during Non-Peak Hours 80
6.4.2 Extreme Volume Testing 81
CHAPTER 7 CONCLUSIONS & RECOMMENDATIONS 82
7.1 Conclusions 82
7.2 Recommendations 84

REFERENCES R-1
Appendix 1 Flow Rates in a Typical Day A-1
Appendix 2 Pre-set Timing Plans A-7
Adya, M. and Collopy, F., “How Effective are Neural Networks at Forecasting and Prediction? A Review and Evaluation, Journal of Forecasting, Vol. 17, pp. 481-495, 1998.
Amin, I. J., Taylor, A. J., Junejo, F., Al-Habaibeh, A., Parkin, R. M., “Automated people-counting by using low-resolution infrared and visual cameras, Measurement, Vol. 41, pp. 589-599, 2008.
Australia. RTA Annual Report 2007. New South Wales Government, 2007.
Ballman, K. V., “Cost-Effectiveness of Smart Traffic Signals, Dissertation Presented to Sloan School of Management, 1991.
Chen, M. S., “Level of Service and Capacity of Taipei Bus Station, Master Thesis Presented to Department of Civil Engineering College of Engineering National Taiwan University, 2010. (in Chinese)
Efendigil, T., Önüt, S. and Kahraman, C., “A Decision Support System for Demand Forecasting with Artificial Neural Networks and Neuro-Fuzzy Model: A Comparative Analysis, Expert System with Applications, Vol. 36, pp. 6697-6707, 2009.
FHWA, “Traffic Control Systems Handbook, Federal Highway Administration Office of Transportation Management, 2005.
Freeman, J. A. and Skapura, D. M., “Neural Networks: Algorithms, Applications, and Programming Techniques, Addison-Wesley Publishing Company, 1991.
He, W. Z., “Data Fusion with Artificial Neural Network in Accident Duration Time Forecast on Freeway, Master Thesis Presented to Department of Transportation & Communication Management Science of National Cheng Kung University, 2010. (in Chinese)
Hsu, K. C., “Adaptive Traffic Signal Control Model with Self-Learning Capability, Dissertation Presented to Department of Transportation and Communication Management Science of National Cheng Kung University, 2003. (in Chinese)
Huang, Y.P., Chen, C.H., Chang, Y. T., and Sandnes, F. E., “An intelligent strategy for checking the annual inspection status of motorcycles based on license plate recognition, Expert Systems with Applications, Vol. 36, pp. 9260-9267, 2009.
Hwang ,T. L., “A Study on Establishment of Intelligent Traffic-Adaptive Network Signal Control Model, Dissertation Presented to Department of Transportation and Communication Management Science of National Cheng Kung University, 1994. (in Chinese)
IOT, “2001 Highway Capacity Manual in Taiwan, Institute of Transportation, Ministry of Transportation and Communications, 2001. (in Chinese)
Ivan, J. N., “Neural Network Representations Arterial Street Incident Detection Data Fusion, Transportation Research Part C, Vol. 5, No. 3/4, pp, 245-254, 1997.
Ki, Y. K. and Baik, D. K., “Vehicle Classification Algorithm for Single-Loop Detector Using Neural Networks, IEEE Transactions on Vehicular Technology, Vol. 55, No. 6, pp. 1704-1711, November 2006.
Kim, J. L., Liu, J. C. S. and Swarnam, P. I., “The Areawide Real-Time Traffic Control CARTC) System: A New Traffic Control Concept, Vehicular Technology, IEEE Transactions, 1993.
Kumar, U. A., “Comparison of Neural Networks and Regression Analysis: A New Insight, Expert System with Applications, Vol. 29, pp. 424-430, 2005.
Lee, Y., “Development of Freeway Bus Travel Time Forecasting Model Using Artificial Neural Networks, Master Thesis Presented to Department of Transportation & Communication Management Science of National Cheng Kung University, 2002. (in Chinese)
Litman, T.. “Valuing Transit Service Quality Improvements, Journal of Public Transportation, Vol. 11, No. 2, pp. 43-63, 2008.
Lin, F. B., and Vijayakumar, S., “Adaptive Signal Control at Isolated Intersections, Journal of Transportation Engineering, Vol. 114, No.5, pp. 555-573, 1988.
Moore, R. S., Beauchamp, M. B., Barnes, C. Z. and Stammerjohan, C. A., “Artificial Neural Networks: An Introduction and Application in a Consumer Behavior Setting, The Marketing Management Journal, Vol. 17, Issue 1, pp. 27-38, 2007.
Nelson, M. M. and Illingworth, W. T., “A Practical Guide to Neural Nets, Addison-Wesley Publishing Company, Inc, 1991.
Qi, M. and Zhang, G. P., “Trend Time-Series Modeling and Forecasting with Neural Networks, IEEE Transactions on Neural Networks, Vol. 19, No. 5, pp. 808-816, 2008.
SCATS Website, http://www.scats.com.au/.
Shao, C., “Adaptive Control Strategy for Isolated Intersection and Traffic Network, Dissertation Presented to The Graduate Faculty of The University of Akron, 2009.
Spall, J.C. and Chin, D. C., “Traffic-Responsive Signal Timing for System- wide Traffic Control, Transportation Research Part C, Vol. 5, No. 3, pp. 153-163, 1997.
Staats, R. C., “Integration of Predictive Routing Information with Dynamic Traffic Signal Control, Dissertation Presented to Department of Electrical Engineering and Computer Science of Massachusetts Institute of Technology, 1994.
TRB, “Highway Capacity Manual, Transportation Research Board, National Research Council, 2000.
Tsai, H. S., “Traffic Control Theory and Practice, Sheng He Cheng Publishing Company, 1990. (in Chinese)
Tsai, T. H., “Applying Artificial Neural Network Models to Short-Term Railway Passenger Demand Forecasting, Dissertation Presented to Department of Transportation and Communication Management Science of National Cheng Kung University, 2001.
Wan Da Tong Enterprise Co., Ltd., Introduction of Taipei Bus Station, 2010. (in Chinese)
Wan Da Tong Enterprise Co., Ltd., Taipei Bus Station Operation Database, 2011. (in Chinese)
Wang, G., “The Area Wide Real-Time Traffic Control (ARTC) System: The Logical Structure and Computational Algorithms, Comme Exigence Partielle de la Maîtrise en Informatique Extensionnée de L'Université du Québec à Montréal, 2006.
Wang, H. P., “Research on Evaluation Indexes of Service Level for Public Bus Transfer Center, Master Thesis Presented to Department of Civil Engineering College of Engineering National Taiwan University, 2006. (in Chinese)
Wang, Q., Sun, X. Y., Golden, B. L., Silets, L. D., Wasil, E. A., Luco, S., and Peck, A., “A Neural Network Model for the Wire Bonding Process, Computers and Operations Research, Vol. 20, NO. 8, pp. 879-888, 1993.
Wei, C. H., Chien, I. J., Wang, D. J. and Hsu, M. J., “Reducing Internal Delay for the Taipei Bus Station with Signal Control Considering Bus Operation and Geographic Constraints–An Analytical Approach, The 11th Asia-Pacific ITS Forum and Exhibition, 2011.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top