Demonstration of Artificial Intelligence Technology for Transit Railcar211 Diagnostics

摘要

This report will be of interest to railcar maintenance professionals concerned211u001ewith improving railcar maintenance fault-diagnostic capabilities through the use 211u001eof artificial intelligence (AI) technologies. It documents the results of a 211u001edemonstration of an AI-based program that acts as a 'diagnostic assistant' from 211u001etransit railcar propulsion systems. The diagnostic program uses a hybrid AI 211u001eapproach with both model-based reasoning and expert system rules. The AI tool was 211u001etested at the Washington Metropolitan Area Transit Authority (WMATA) on direct 211u001ecurrent chopper propulsion systems of the 3000 series railcars. The system was 211u001edetermined to be easy to use and effective in diagnosing propulsion system 211u001efaults.