A. G. Quan, U. M. Schwuttke, J. S. Herstein, J. S. Spagnuolo, and S. Burleigh, Jet Propulsion Laboratory, California Institute of Technology
SHARP is a knowledge-based system for the diagnosis of problems in NASA’s Deep Space Network (DSN) telecommunications system. The telecommunications system provides the means of communication between a spacecraft and operations personnel at Jet Propulsion Laboratory. SHARP analyzes problems that occur in both the on-board spacecraft telecom subsystem and in the DSN. It employs a rule-based expert system to detect and diagnose anomalies and to recommend corrective action. This diagnostic logic is represented in the form of a binary decision tree which is encoded in Prolog. The knowledge base is designed to be easy to maintain and expand, with a one-to-one correspondence between decision tree nodes and rules. The knowledge base is embedded within a C program which contains a telemetry interface and a graphical user- interface. Data is obtained both from on-line sources. such as telemeby and Sequence of Events files, and from the user when the required data is not available from any on-line source. The majority of rules are generic in nature, allowing SHARP to be applied to multi- ple missions.