This report documents and presents the results of a study to determine the feasibility of applying Artificial Intelligence (AI) techniques to the diagnosis of transit railcars. The AI techniques investigated were expert systems, case-based reasoning, model-based reasoning, artificial neural networks, computer vision, fuzzy logic, and a procedural knowledge-based system. Site surveys were conducted at transit railcar maintenance facilities and at railcar subsystem suppliers. The site surveys gathered information about current and future diagnostic and maintenance practices, possible barriers to implementing advanced AI technology, and maintenance cost data. An economic analysis was performed to provide an estimate of cost savings expected by reducing the diagnostic effort.The values used in the matrix are based on a review of a number of vehicle technical specifications. ... The Time per 1, 000 Hours column is a product of failure rate and average repair time expressed as a function of 1, 000 hours of vehicleanbsp;...
|Title||:||Artificial Intelligence for Transit Railcar Diagnostics|
|Author||:||Ian P. Mulholland, Raymond A. Oren|
|Publisher||:||Transportation Research Board - 1994|