Combined use of sensor data and structural knowledge processed by Bayesian network: Application to a railway diagnosis aid scheme

Transportation Research Part C: Emerging Technologies

Volumn 16, Issue 6, 2008, Pages 755-767

  Oukhellou, L ^a,b   Come E ^a   Bouillaut, L ^a   Aknin, P ^a  

^a Institute of Research on Transportation and Safety   (France)

^b UNIVERSITÉ PARIS EST CRÉTEIL   (France)

Author keywords

Bayesian network; Broken rail; Classification; Diagnosis; Structural data

Indexed keywords

BAYESIAN NETWORKS; CLASSIFICATION (OF INFORMATION); COMPUTER AIDED DIAGNOSIS; DEFECTS; DIAGNOSIS; RAILROAD TRANSPORTATION; RAILROADS;

ADDITIONAL KNOWLEDGE; APPLICATION CONTEXTS; BROKEN RAIL; DEFECT CLASSIFICATION; RAILWAY INFRASTRUCTURE; STRUCTURAL DATA; STRUCTURAL KNOWLEDGE; TECHNOLOGICAL SOLUTION;

RAILS;

BAYESIAN ANALYSIS; DATABASE; RAILWAY TRANSPORT; SENSOR; TRANSPORTATION INFRASTRUCTURE;

EID: 52049083428     PISSN: 0968090X     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.trc.2008.04.001     Document Type: Article

References (51)

1. Allotta B., Colla V., and Malvezzi M. Train position and speed estimation using wheel velocity measurements. Journal of Rail and Rapid Transit 216 3 (2002) 207-225
2. ASNT, 1986. Nondestructive Testing Handbook, vol. 4. Electromagnetic Testing. ASNT.
3. Bakhtazad A., Palazoglu A., and Romagnoli J. Detection and classification of abnormal process situations using multidimensional wavelet domain hidden Markov trees. Computers and Chemical Engineering 24 5 (2000) 769-777
4. Bentoumi, M., Aknin, P., Bloch, G., Talbi, S., 2001. Improving the detection capacity of differential probes by means of inverse filters delivering estimated absolute signals. In: Fourth International Workshop on Advances in Signal Processing for Non Destructive Evaluation of Materials, vol. 6, pp. 125-130.
5. Bentoumi M., Aknin P., and Bloch G. On-line defect diagnosis with differential eddy current probes and specific detection processings. European Journal of Applied Physics 23 3 (2003) 227-233
6. Camci, F., Chinnam, R., 2005. Dynamic Bayesian networks for machine diagnostics: hierarchical hidden Markov models vs. competitive learning. In: IEEE International Joint Conference on Neural Networks, pp. 1752-1757.
7. Cerniglia, D., Garcia, G., Kalay, S., 2006. Application of laser induced ultrasound for rail inspection. In: World Congress on Railway Research.
8. Come, E., Bouillaut, L., Aknin, P., Oukhellou, L., 2007. Hidden Markov random field, an application to railway infrastructure diagnosis. In: First IFAC Symposium on Dependable Control of Discrete systems, Cachan, France, pp. 155-160.
9. Cygan, H., Aknin, P., Simard, P., Girardi, L., 2003. B-scan ultrasonic image analysis for internal rail defect detection. In: World Congress on Railway Research.
10. Das, G., Lin, K.-I., Mannila, H., Renganathan, G., Smyth, P., 1998. Rule discovery from time series. In: Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining (KDD'98), New York, NY, USA, pp. 16-22.
11. Dean T., and Kanazawa K. A model for reasoning about persistence and causation. Computational Intelligence 5 3 (1989) 142-150
12. Deutschl, E., Gasser, C., Niel, A., Werschonig, J., 2004. Defect detection on rail surfaces by a vision based system. In: Intelligent Vehicles Symposium IEEE, vol. 14-17, pp. 507-511.
13. Dojer N., Gambin A., Mizera A., Wilczyski B., and Tiuryn J. Applying dynamic Bayesian networks to perturbed gene expression data. BMC Bioinformatics 7 (2006) 249
14. Durbin R., Eddy S., Krogh A., and Mitchison G. Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids (1998), Cambridge University Press, Cambridge, UK
15. Fabbro, H., Meneroud, P.F., Claeyssen, Chiron, P., Thomas, R., 1999. Magnetic resonant sensors for remote measurement of the position of objects. In: Ninth International Trade Fair and Conference for Sensors, Transducers and Systems, pp. 95-98.
16. Fan Y., Dixon S., Edwards R., and Jian X. Ultrasonic surface wave propagation and interaction with surface defects on rail track head. Independent Non Destructive Testing and Evaluation 40 6 (2007) 471-477
17. Friedman N. Inferring cellular networks using probabilistic graphical models. Science 303 (2004) 799-805
18. Garcia G. Nondestructive testing technologies applications for in-track rail inspections. Railway Track and Structures August (2002)
19. Ge M., Du R., and Xu Y. Hidden Markov model based fault diagnosis for stamping processes. Mechanical Systems and Signal Processing 18 2 (2004) 391-408
20. Geistler, A., Bohringer, F., 2004. Robust velocity measurement for railway applications by fusing eddy current sensor signals. In: IEEE Intelligent Vehicles Symposium, pp. 664-669.
21. Jablonski D., and Pelloux P. Effect of train load spectra on crack growth in rail steel. Residual Stresses in Rails 1 (1992) 81-98
22. Jensen F. An Introduction to Bayesian Networks (1996), UCL Press
23. Josse, F., Hager, J., 1999. Automatic measuring of rail gaps. In: World Congress on Railway Research.
24. Kalay S., Morgan R., Reiff R., and Peters J. Broken rail detection. Transit Cooperative Research Program, report 71 1 (2001) 71
25. Kim S., Imoto S., and Miyano S. Inferring gene networks from time series micro-array data using dynamics Bayesian networks. Brief Bioinformatics 4 (2003) 228-235
26. Labropoulos, K., Moundoulas, P., Moropoulo, A., 2006. Methodology for the monitoring, control and warning of defects for preventive maintenance of rails. In: Tenth International Conference on Computer System Design and Operation in the Railway and Other Transit Systems, pp. 935-944.
27. Landwehr N., Mielikainen T., Eronen L., Toivonen H., and Mannila H. Constrained hidden Markov models for population based haplotyping. BMC Informatics (2007) 8
28. Likforman-Sulem, L., Sigelle, M., 2007. Recognition of broken characters from historical printed books using dynamic Bayesian networks. In: AAAI, pp. 173-177.
29. Mannila H., Toivonen H., and Verkamo A.I. Discovery of frequent episodes in event sequences. Data Mining and Knowledge Discovery 1 3 (1997) 259-289
30. Mesch, F., Leon, F.P., Engelberg, T., July 2000. Train-based location by detecting rail switches. In: Fifth International Conference on Computers in Railways, pp. 1251-1260.
31. Murphy, K., 2002a. Dynamic Bayesian networks: representation, inference and learning. Ph.D. Thesis, University of California, Berkley.
32. Murphy, K., 2002b. Dynamic Bayesian networks: representation, inference and learning. Ph.D. Thesis, University of California, Berkeley.
33. Oates, T., Cohen, P.R., 1996. Searching for structure in multiple streams of data. In: Proceedings of the Thirteenth International Conference on Machine Learning (ICML'96), San Francisco, NY, USA, pp. 346-354.
34. Oukhellou L., Aknin P., and Perrin J. Dedicated sensor and classifier of rail head defects for railway systems. Control Engineering Practice 7 (1999) 57-61
35. Pearl, J., 1982. Reverend bayes on inference engines: A distributed hierarchical approach. In: AAAI, pp. 133-136.
36. Pohl R., Erhard A.H.J., Montag H.M., and Thomas H.W. NDT techniques for railroad wheel and gauge corner inspection. Independent Non Destructive Testing and Evaluation 34 2 (2004) 89-94
37. Rabiner L. A tutorial in hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE 77 2 (1989) 257-286
38. Rose, J., Avioli, M., 2002. Elastic wave analysis for broken rail detection. In: Topics on Nondestructive Evaluation: Nondestructive Testing and Evaluation for the Railroad Industry, pp. 33-47.
39. Rose J., Avioli M., Mudgeand P., and Sanderson R. Guided wave inspection potential of defects in rail. Non Destructive Testing & Evaluation International 37 2 (2004) 153-161
40. Scalea F., Rizzo P., Coccia S., Bartoli I., Fateh M., Viola E., and Pascale G. Non contact ultrasonic inspection of rails and signal processing for automatic defect detection and classification. Insight-NDT and condition Monitoring, Special Issue on NDT of Rails 6 45 (2005) 346-353
41. Scutti J., Pelloux P., and Fuquen-Moleno R. Fatigue behaviour of rail steel. Fatigue and Fracture of Engineering Materials and Structures 7 (1984) 121-135
42. Shooman, S., 1997. Broken rail detection without track circuits, MTAS-New York city transit, a proposal. In: Workshop on rail defect detection and removal policies and broken rail technologies.
43. Sih G., and Jeong D. Effect of load sequence on fatigue life of rail steel. Residual Stresses in Rails 2 (1992) 63-85
44. Singh, M., Singh, S., Jaiswal, J., Hempshall, J., 2006. Autonomous rail track inspection using vision based system. In: IEEE International Conference on Computational Intelligence for Homeland Security and Personal Safety, vol. 16-17, pp. 56-59.
45. UIC, 2001. A Joint Strategy for European Rail Research 2020: Towards a Single European Railway System. UIC publication.
46. Vlontzos J., and Kung S. Hidden Markov models for character recognition. IEEE Transactions on Image Processing 1 4 (1992) 539-543
47. Weise, V., Waite, G., July 2004. Developments of rail flaw inspection techniques within the UK rail industry. In: International Conference on Railway Engineering.
48. Ying J., Kirubarajan T., Pattipati K.R., and Patterson-Hine A. A hidden Markov model-based algorithm for fault diagnosis with partial and imperfect tests. Transaction SMC, Part C 30 4 (2000) 463-473
49. Zerbst U., Madler K., and Hintze H. Fracture mechanics in railway applications: an overview. Engineering Fracture Mechanics 72 (2005) 163-194
50. Zimmermann M., Chappelier J., and Bunke H. Offline grammar-based recognition of handwritten sentences. IEEE Transactions on Pattern Analysis and Machine Intelligence 28 5 (2006) 818-821
51. Zweig, G., Russell, S., 1998. Speech recognition with dynamic Bayesian networks. In: AAAI, pp. 173-180.