Automatic train regulation for metro lines using dual heuristic dynamic programming

Abstract

Issues regarding capacity and service quality of metro lines have been receiving attention in worldwide transportation circles recently. Because investment in metro infrastructure is costly, increasing capacity utilization of existing systems while maintaining service quality, particularly in environments where disturbance occurs frequently, is a challenge. For highly homogeneous railway systems such as metro lines, the robustness of the train regulation system against disturbances is an important factor affecting capacity utilization and service quality. Train regulation in metro lines is essentially a highly non-linear, stochastic, and constrained optimization problem. This article proposes an automatic train regulation (ATR) design using dual heuristic dynamic programming (DHP). The ATR system makes easier the handling of the non-linear and stochastic characteristics of metro line with infrastructure constraint; and near-optimal regulation can be obtained more rapidly and accurately. The verification of the DHP-based ATR referring to practical operation data of Taipei metro is presented, and a comparison with a design using linear quadratic regulator is also provided, especially regarding robustness against disturbance.

Keywords

automatic train regulation dynamic programming adaptive critic design

Get full access to this article

View all access options for this article.

References

McClellan

Railroad capacity issues. In Conference Proceedings on the Web, Research to enhance rail network performance, 5-6 April 2008, vol. 3, pp. 31–37 (Transportation Research Board, Washington, DC, USA).

Parkinson

Fisher

‘Transportation research board, national research council’

In Rail transit capacity, transit cooperative research program (TCRP Report 13) (Washington, DC: National Academy Press) 1996

Capacity. UIC code 406 (Paris, France: International Union of Railways) 2004

Hansen

I A

Allan

Brebbia

C A

Hill

R J

Sciutto

Sone

Ed. ‘Increase of capacity through optimized timetabling’ In Computers in railways IX (Southampton, UK: WIT Press 2004): 529–538

Abril

Barber

Ingolotti

Salido

M A

Tormos

Lova

‘An assessment of railway capacity’

Transp. Res. E, Logist. Transp. Rev. 44 (2008): 774–806

Vromans

Reliability of railway systems PhD Dissertation, Erasmus Research Institute of Management, Erasmus University, Rotterdam, 2005.

Gill

D C

The impact of moving block train control on heavy metros. In Proceedings of the International Conference on Developments in Mass Transit Systems (Conf. Publ. No. 453), London, UK, 20-23 April 1998, pp. 235–242.

Van

B V

Campion

Bastin

‘Traffic modeling and state feedback control for metro lines’

IEEE Trans. Autom. Control 36 (1991): 770–784

Chang

C S

Thia

B S

‘Online rescheduling of mass rapid transit systems: Fuzzy expert system approach’

IEE Proc. Electr. Power Appl. 1434 (1996): 307–316

10.

Goodman

C J

Murata

‘Metro traffic regulation from the passenger perspective’

Proc. IMechE, Part F: J. Rail and Rapid Transit 215 F2 (2001): 137–147 DOI: 10.1243/0954409011531468.

11.

Ding

Chien

S I

‘Improving transit service quality and headway regularity with real-time control’

Transp. Res. Rec., J. Transp. Res. Board 1760/2001 (2001): 161–170

12.

Chang

S.-C.

Chung

Y.-C.

‘From timetabling to train regulation – a new train operation model’

Inf. Softw. Technol. 47 (2005): 575–585

13.

Wegele

Schnieder

Allan

Brebbia

C A

Hill

R J

Sciutto

Sone

Ed. ‘Automated dispatching of train operations using genetic algorithms’ In Computers in Railways IX (Southampton, UK: WIT Press) 2004

14.

Werbos

P J

Barto

Powell

Wunsch

Ed. ‘ADP: Goals, opportunities and principles’ In Handbook of learning and approximate dynamic programming (Hoboken, New Jersey, USA: IEEE Press, John Wiley 2004): 3–44

15.

Lendaris

G T S

Padgett

M L

Karayiannis

N B

Zadeh

L A

Ed. ‘Designing (approximate) optimal controllers via DHP adaptive critics & neural networks’ In The handbook of applied computational intelligence (Boca Raton, Florida, USA: CRC Press) 2000

16.

Prokhorov

Wunsch

‘Adaptive critic designs’

IEEE Trans. Neural Netw. 85 (1997): 997–1007

17.

Lendaris

G G

Neidhoefer

J C

Barto

Powell

Wunsch

Ed. ‘Guidance in the use of adaptive critics for control’ In Handbook of learning and approximate dynamic programming (Hoboken, New Jersey, USA: IEEE Press, John Wiley 2004): 97–124

18.

Paul

J W

White

D A

Sofge

D A

Ed. ‘Approximate dynamic programming for real-time control and neural modeling’ In Handbook of intelligent control: neural, fuzzy, and adaptive approaches (New York, USA: Van Nostrand Reinhold) 1992

19.

Prokhorov

D V

Santiago

R A

Wunch

D C

‘Adaptive critic designs: A case study for neurocontrol’

Neural Netw. 89 (1995): 1367–1372

20.

Goverde

R M P

Punctuality of railway operations and timetable stability analysis. PhD Dissertation, Transport and Planning Department, Delft University of Technology, The Netherlands, 2005.

21.

Lin

W S

Sheu

J W

Adaptive critic design of automatic train regulation of MRT system. In Proceedings of the IEEE International Conference on Industrial Technology, ICIT 2008, Chengdu, China, 21-24 April 2008.