Demonstration of artificial intelligence technology for transit railcar diagnostics.

Author(s)
Mulholland, I. & Kahric, Z.
Year
Abstract

TCRP Report 44, "Demonstration of Artificial Intelligence Technology for Transit Railcar Diagnostics," will be of interest to railcar maintenance professionals concerned with improving railcar maintenance fault-diagnostic capabilities through the use of artificial intelligence (AI) technologies. The report documents the results of a demonstration of an AI-based program that acts as a "diagnostic assistant" for transit railcar propulsion systems. The diagnostic program uses a hybrid AI approach with both model-based reasoning and expert system rules. The AI tool was tested at the Washington Metropolitan Area Transit Authority (WMATA) on direct current chopper propulsion systems of the 3000 series railcars. The system was determined to be easy to use and effective in diagnosing propulsion system faults. The results of TCRP Project E-2, "Artificial Intelligence for Transit Railcar Diagnostics," were published as TCRP Report 1 in 1994. The objectives of this project were to assess the potential application of artificial intelligence (AI) techniques in diagnostic practices in the railcar maintenance environment and, where appropriate, to recommend steps to introduce such practices. The researchers (1) identified AI techniques that are applicable to the diagnosis or prediction of railcar failures; (2) identified the AI techniques with high probabilities of success; (3) estimated the magnitude of potential benefits from using these techniques; (4) identified, in order of priority, the railcar subsystems (e.g., propulsion, brakes, doors) that benefit most from application of each of these techniques; and (5) developed a research program for systematically evaluating and implementing these techniques. The final report for this project recommends that a follow-up demonstration of AI technology be considered. The report recommends that a demonstration of the technology focusing on the railcar propulsion system be performed to evaluate its benefit to the diagnostic process. The report concludes that the use of AI technology in diagnosing railcar propulsion system problems could pay for itself in 1 year if it could provide a 7.2 percent reduction in the propulsion system mean time to repair. Under TCRP Project E-2A, research was undertaken by ANSTEC, Inc. to develop and demonstrate a "diagnostic assistant" computer program using AI technology to provide efficient and effective support for diagnosing transit railcar propulsion system problems. To achieve the project objectives, the researchers (1) selected a demonstration site based on established criteria; (2) specified and procured an AI software shell and workstation hardware; (3) developed functional and causal models of the propulsion system and generated diagnostic rules for input into the AI software; (4) pre-tested the AI system, with debugging as necessary; (5) tested the AI system in actual field operation at three WMATA facilities; and (6) evaluated the AI system diagnostic capability. (A)

Publication

Library number
990515 ST S
Source

Washington, D.C., National Research Council NRC, Transportation Research Board TRB / National Academy Press, 1999, 66 p.; Transit Cooperative Research Program TCRP Report ; 44 / Project E-02A FY'96 - ISSN 1073-4872 / ISBN 0-309-06318-3

Our collection

This publication is one of our other publications, and part of our extensive collection of road safety literature, that also includes the SWOV publications.