ICARUS: design and deployment of a case-based reasoning system for locomotive diagnostics

Abstract Locomotives, like many complex modern machines, are equipped with the capability to generate on-board fault messages indicating the presence of anomalous conditions. Such messages tend to be generated in large quantities, and are difficult and time consuming to interpret manually. This paper presents the design and development of a case-based reasoning system for diagnosing locomotive faults using such fault messages as input. The process of using historical repair data and expert input for case generation and validation is described. An algorithm for case matching is presented, along with some results on pilot data.

[1]  Ann Macintosh,et al.  Applications and Innovations in Expert Systems VI , 1999, Springer London.

[2]  Padraig Cunningham,et al.  Using Introspective Learning to Improve Retrieval in CBR: A Case Study in Air Traffic Control , 1997, ICCBR.

[3]  Eugene J. H. Kerckhoffs,et al.  Case-Based Reasoning in an Ultrasonic Rail-Inspection System , 1997, ICCBR.

[4]  K. Althoff.  Case-Based Reasoning for Decision Support and Diagnostic Problem Solving: The INRECA Approach , 1995 .

[5]  James R. McDonald,et al.  CBR Applied to Fault Diagnosis on Steam Turbines , 1995, UK Workshop on Case-Based Reasoning.

[6]  Claire Cardie,et al.  Examining Locally Varying Weights for Nearest Neighbor Algorithms , 1997, ICCBR.

[7]  David Hinkle,et al.  Applying case-based reasoning to autoclave loading , 1992, IEEE Expert.

[8]  Timothy L. Acorn,et al.  Smart: Support: Management Automated Reasoning Technology for Compaq Customer Service , 1992, IAAI.

[9]  Ralph Deters,et al.  Case-Based Diagnosis of Multiple Faults , 1995, ICCBR.

[10]  Boi Faltings.  Probabilistic Indexing for Case-Based Prediction , 1997, ICCBR.

[11]  Toby Walsh,et al.  Proceedings of AAAI-96 , 1996 .

[12]  Jutta Stehr,et al.  CBR and Machine Learning for Combustion System Design , 1995, ICCBR.

[13]  R. A. Vingerhoeds,et al.  Large-Scale Fault Diagnosis for On-Board Train Systems , 1995, ICCBR.

[14]  Francesco Ricci,et al.  Learning a Local Similarity Metric for Case-Based Reasoning , 1995, ICCBR.

[15]  Gholamreza Nakhaeizadeh,et al.  Learning Prediction of Time Series - A Theoretical and Empirical Comparison of CBR with some other Approaches , 1993, EWCBR.

[16]  Qiang Yang,et al.  Maintaining Unstructured Case Base , 1997, ICCBR.

[17]  Bing Leng,et al.  An Engineering Approach for Troubleshooting Case Bases , 1997, ICCBR.

[18]  Hiroaki Kitano,et al.  Case-Method: A Methodology for Building Large-Scale Case-Based Systems , 1993, AAAI.