Learning to predict train wheel failures

ABSTRACT

This paper describes a successful but challenging application of data mining in the railway industry. The objective is to optimize maintenance and operation of trains through prognostics of wheel failures. In addition to reducing maintenance costs, the proposed technology will help improve railway safety and augment throughput. Building on established techniques from data mining and machine learning, we present a methodology to learn models to predict train wheel failures from readily available operational and maintenance data. This methodology addresses various data mining tasks such as automatic labeling, feature extraction, model building, model fusion, and evaluation. After a detailed description of the methodology, we report results from large-scale experiments. These results clearly show the great potential of this innovative application of data mining in the railway industry.

REFERENCES

• 1: David W. Aha , Dennis Kibler , Marc K. Albert, Instance-Based Learning Algorithms, Machine Learning, v.6 n.1, p.37-66, Jan. 1991 [doi>10.1023/A:1022689900470]
• 2: Claudio Conversano , Roberta Siciliano , Francesco Mola, Supervised Classifier Combination through Generalized Additive Multi-model, Proceedings of the First International Workshop on Multiple Classifier Systems, p.167-176, June 21-23, 2000
• 3: Thomas G. Dietterich, An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization, Machine Learning, v.40 n.2, p.139-157, Aug. 2000 [doi>10.1023/A:1007607513941 ]
• 4: Chris Drummond , Robert C. Holte, Explicitly representing expected cost: an alternative to ROC representation, Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, p.198-207, August 20-23, 2000, Boston, Massachusetts, United States [doi>10.1145/347090.347126]
• 5: Robert P. W. Duin , David M. J. Tax, Experiments with Classifier Combining Rules, Proceedings of the First International Workshop on Multiple Classifier Systems, p.16-29, June 21-23, 2000
• 6: Saso Džeroski , Bernard Ženko, Is Combining Classifiers with Stacking Better than Selecting the Best One?, Machine Learning, v.54 n.3, p.255-273, March 2004 [doi>10.1023/B:MACH.0000015881.36452.6e]
• 7: Efron, B., Estimating the Error Rate of a Prediction Rules: Improvement on Cross Validation, J of American Statistical Association, Vol. 78, 1983, 316--331.
• 8: David A. Grossman , Ophir Frieder, Information Retrieval: Algorithms and Heuristics, Kluwer Academic Publishers, Norwell, MA, 1998
• 9: Mark A. Hall, Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning, Proceedings of the Seventeenth International Conference on Machine Learning, p.359-366, June 29-July 02, 2000
• 10: Jiawei Han , Micheline Kamber, Data mining: concepts and techniques, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2000
• 11: Michael Bonnell Harries , Claude Sammut , Kim Horn, Extracting Hidden Context, Machine Learning, v.32 n.2, p.101-126, Aug. 1998 [doi>10.1023/A:1007420529897 ]
• 12: Thorsten Joachims, Text Categorization with Suport Vector Machines: Learning with Many Relevant Features, Proceedings of the 10th European Conference on Machine Learning, p.137-142, April 21-23, 1998
• 13: Kenji Kira , Larry A. Rendell, A Practical Approach to Feature Selection, Proceedings of the Ninth International Workshop on Machine Learning, p.249-256, July 01-03, 1992
• 14: Miroslav Kubat , Robert C. Holte , Stan Matwin, Machine Learning for the Detection of Oil Spills in Satellite Radar Images, Machine Learning, v.30 n.2-3, p.195-215, Feb./ March, 1998
• 15: Louisa Lam, Classifier Combinations: Implementations and Theoretical Issues, Proceedings of the First International Workshop on Multiple Classifier Systems, p.77-86, June 21-23, 2000
• 16: Lechowicz, S. and Hunt, C., Monitoring and Managing Wheel Condition and Loading, http://www.ntsb.gov/events/symp_rec/proceedings/authors/lechowicz.pdf
• 17: Sylvain Létourneau , Fazel Famili , Stan Matwin, Data Mining to Predict Aircraft Component Replacement, IEEE Intelligent Systems, v.14 n.6, p.59-66, November 1999 [doi>10.1109/5254.809569 ]
• 18: Sylvain Létourneau, Data mining for maintenance of complex systems, Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence, p.1178, July 1998, Madison, Wisconsin, United States
• 19: Sylvain Letourneau , Stan Matwin , Fazel Famili, Identification of attribute interactions and generation of globally relevant continuous features in machine learning, 2003
• 20: Ling, C.X., Huang, J., Zhang, H. AUC: a Statistically Consistent and more Discriminating Measure than Accuracy, Proceedings of IJCAI 2003, 519--524.
• 21: Thomas M. Mitchell, Machine Learning, McGraw-Hill Higher Education, 1997
• 22: Opitz, D. and Maclin, R., Popular Ensemble Methods: An Empirical Study, Journal of Artificial Intelligence Research Vol. 11, 1999, 169--198.
• 23: Provost F.,Fawcett, T. Analysis and Visualization of Classifier Performance: Combination under Imprecise Class and Cost Distributions, Proceedings of International Conference on Knowledge Discovery and Data Mining (KDD97), 1997.
• 24: Salient Systems Inc., Preventing Train Derailment, http://www.salientsystems.com
• 25: Technical report, Advanced Technology Safety Initiative: Equipment Health Management System, Association of American Railroads, August 24, 2004
• 26: Tsoumakas, G., Katakis, I., and Blahavas I., Effective Voting of Heterogeneous Classifiers, Proceedings of the 15th European Conference on Machine Learning (MCML2004), Pisa, Italy, 465--476.
• 27: Ian H. Witten , Eibe Frank, Data mining: practical machine learning tools and techniques with Java implementations, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2000

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Data mining

Additional Classification:
  H. Information Systems
  H.4 INFORMATION SYSTEMS APPLICATIONS
      H.4.2 Types of Systems
          Subjects: Decision support (e.g., MIS)

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Concept learning
  I.5 PATTERN RECOGNITION
      I.5.2 Design Methodology
          Subjects: Classifier design and evaluation

General Terms:
Algorithms, Experimentation, Performance, Reliability

Keywords:
data mining, machine learning, methodology, model building, model evaluation, model fusion, wheel failure prediction