Second International Diagnostic Competition – DXC’10

A framework to compare and evaluate diagnosis algorithms (DAs) has been created jointly by NASA Ames Research Center, Palo Alto Research Center, and Delft University of Technology. In this paper, we present the second implementation of this framework in a competition called DXC’10. The overall goal of this competition is to evaluate the performance of different diagnostic methods. In order to accurately mimic diagnostic technology use in a real-world context, we have defined diagnostic problems driven by use cases representing different roles of diagnosis results. In the end, the competition pitted seven DAs competing in two diagnostic problems. The paper presents the systems used in DXC’10, a description of faults and data sets used for each diagnostic problem, a listing of participating DAs, the performance metrics and results computed from running the DAs with the framework, and an analysis of the results.