Demonstration of Artificial Intelligence Technology for Transit Railcar Diagnostics

Document Type


Publication Date


Subject Area

mode - rail, mode - subway/metro, mode - car


Artificial intelligence, Demonstration projects, Diagnostic tests, Propulsion systems, Rapid transit cars, Washington Metropolitan Area Transit Authority


This report 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.


Permission to link to report given by TRB.