System Health Monitoring for Space Mission Operations

Many spacecraft provide an abundance of system status telemetry that is monitored in real time by ground personnel and archived to allow for further analysis. In the flight control room, controllers typically monitor these values using text or graphical displays that incorporate individual parameter limit checking or simple trend analysis. Recent developments in data mining techniques for anomaly detection make it possible to use the wealth of archived system data to produce more sophisticated system health monitoring applications. These "data driven" applications are capable of characterizing and monitoring interactions between multiple parameters and can complement existing practice to provide valuable decision support for mission controllers. Data driven software tools have been successfully applied to mission operations for both the Space Shuttle and the International Space Station. These tools have been applied to engineering analysis of spacecraft data to detect unusual events in the data, and to real-time system health monitoring in the flight control room. Augmenting traditional mission control software with advanced monitoring tools can provide controllers with greater insight into the health and performance of the space systems under their watch. Adding heuristic rule based methods that encode system knowledge obtained from seasoned mission controllers can also be helpful to less experienced personnel. We will describe how such techniques have been applied to NASA mission control operations and discuss plans for future mission control system health monitoring software systems.