Relating track geometry to vehicle performance using neural network approach

Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit

Volumn 220, Issue 3, 2006, Pages 273-281

  Li, D ^a   Meddah, A ^a   Hass, K ^a   Kalay, S ^a  

^a TRANSPORTATION TECHNOLOGY CENTER INC   (United States)

Author keywords

Neural network; Optimized track maintenance; Real time inspection; Track geometry; Vehicle performance

Indexed keywords

LUBRICATION; NEURAL NETWORKS; RAILROAD CARS; RAILROAD TRANSPORTATION; REAL TIME SYSTEMS; THREE DIMENSIONAL;

OPTIMIZED TRACK MAINTENANCE; PERFORMANCE-BASED TRACK GEOMETRY (PBTG); REAL TIME INSPECTION; VEHICLE PERFORMANCE;

RAILROAD TRACKS;

EID: 34247152911     PISSN: 09544097     EISSN: None     Source Type: Journal    
DOI: 10.1243/09544097JRRT39     Document Type: Article

References (16)

1. Li, D., Morgart, D., Harbuck, R., and Mischke, M. BNSF experience: track geometry inspection taking into account vehicle performance. Railw. Track Struct., 2005, 101 (9), 19-23.
2. Li, D., Meddah, A., Hass, K., and Kalay, S. Development and implementation of performance-based track geometry inspection. Proceedings of Railway Engineering Conference, London, UK, 28-29 June 2005 (ECS Publications, Edinburgh, UK).
3. Li, D., Stabler, L., Harbuck, R., Mischke, M., and Kalay, S. Implementation of performance-based track geometry inspection on North American railroads. Proceedings of 8th International Heavy Haul Conference, Rio de Janeiro, Brazil, 14-16 June 2005, pp. 553-560.
4. Li, D., Salahifar, T., Wu, H., and M alone, J. Performance-based track geometry study: vehicle/track interaction tests and modeling. R-955, Association of American Railroads, February 2002.
5. Salahifar, T., Li, D., and Shust, B. Neural network modeling: responses of a loaded, covered hopper car to track geometry. Technology Digest 99-022, Association of American Railroads, June 1999.
6. English, G. W. and Moynlhan, T. W. Realizing performance-based track geometry standards. Proceedings of 8th International Heavy Haul Conference, Rio de Janeiro, Brazil, 14-16 June 2005, pp. 539-546.
7. Gilbert, B. and Hope, K. Real time simulation of vehicle response to measured track geometry. Proceedings of World Congress on Railway Research, Edinburgh, UK, September 2003, pp. 1294-1302.
8. Bonaventura, C. S., Palese, J. W., and Zarembski, A. M. Real-time prediction of railway vehicle response to the interaction with track geometry. Proceedings of International Heavy Haul Association 2003 Specialist Technical Session, Dallas, Texas, 2003, pp. 5.1-5.9.
9. Martin, T. P., Carr, G. A., and El-Sibaie, M. Application of neural network technology for predicting wheel and rail interactive forces. Proceedings of ASME/IEEE Joint Rail Conference, Washington, DC, 2002, pp. 1-6.
10. Esveld, C. Modern railway track, MRT-Productions, West Germany, 1989.
11. Esveld, C. Assessment of track quality via vehicle reactions. Proceedings of International Heavy Haul Conference, Vancouver, Canada, June 1991, pp. 195-200.
12. Federal Railroad Administration. Track safety standards part 213, subparts A to F, class of track 1-5, 2001.
13. Haykin, S. Neural networks: a comprehensive foundation, 2nd edition, 1999 (Prentice Hall, New Jersey).
14. Ptlkington, J. P. Neural network modeling tools. Course notes, Neural Ware Technical Associates, 2000.
15. NUCARS™ User's manual, 2005 (Transportation Technology Center, Inc., Colorado).
16. AAR, Manual of Standards and Recommended Practices, Service-worthiness tests and analyses for new freight cars, Chapter XI, 1987 (Transportation Technology Center, Inc., Colorado).