<title>NASA integrated vehicle health management technology experiment for X-37</title>

Abstract

The NASA Intem'ated Vehicle Health Management (IVHM) Technology Experiment for X-37 was intended to run IVHM software on-board the X-37 spacecraft. The X-37 is intended to be an unpiloted vehicle that would orbit the Earth for up to 21 days before landing on a runway. The scope of the experiment was to perform real-time fauIt detection and isolation for X-37's electrical power system and electro-mechanical actuators.The experiment used Livingstone, a software system that performs diagnosis using a qualitative, model-based reasoning approach that searches system-wide interactions to detect and isolate failures. Two of the challenges we faced were to make this research software more efficient so that it would fit within the Iimited computational resources that were available to us on the X-37 spacecraft, and to modify it so that it satisfied the X-37's software safety requirements.Although the experiment is currently unfunded, the development effort had value in that it resulted in major improvements in Livingstone's efficiency and safety. This paper reviews some of the details of the modeling and inte_ation efforts, and some of the lessons that were learned.

Review on integrated health management for aerospace plane

“…The IVHM software will never directly command any vehicle subsystems and under no circumstances would its recommendations be acted upon automatically by the vehicle. The VMS then telemeters this information to the ground, where ground software processes and displays the information [15][16][17].…”

Unifying System Health Management and Automated Decision Making

“…The mode identification and reconfiguration module was based on Livingstone (Williams & Pandurang, 1996), a reactive configuration management engine that reasons over declarative models. Livingstone later evolved into Livingstone 2 (Kurien & Nayak, 2000), which served as the diagnostic component of several other ISHM prototypes (Meyer et al, 2003;Nicewarner & Dorais, 2006;Schwabacher, Samuels, & Brownston, 2002). In Livingstone 2 problems were represented as partially observable Markov decision processes (Kaelbling, Littman, & Cassandra, 1998), although that representation was only used for tracking the state of a system, rather than for generating action recommendations.…”

The Livingstone Model of a Spacecraft Power System

“…• Earth Observing One -L2 will automatically identify and diagnose a number of simulated failures scheduled to occur by software controlling the instruments of Earth observing satellite [3]. • X-37 -The experiment used L2 to perform diagnosis of electro-mechanical actuators for control surfaces and electrical power system, using a qualitative, model-based reasoning approach that searches system-wide interactions to detect and isolate failures [4]. • International Space Station -NASA's Ames Research Center (ARC) is researching issues in modeling hardware and software elements for some ISS subsystems, such as Command and Data Handling, and in using the model to assist ground operators with fault analysis.…”