An intelligent maintenance system for earth-based failure analysis and self-repairing of microsatellites

This paper describes a recently developed maintenance system for a microsatellite, which is being constructed and it is expected to be launched shortly. The autonomous maintenance system is going to be installed on a personal computer located in an earth-based control room. As this place will most likely be staffed 24 h a day, 7 days a week, there is a good deal of interest in the use of increased automation in maintenance tasks in order to improve the efficiency with which personnel are used and as a way to reduce costs. The system described here is a good example of emerging automation technology that is intended to replace human operators responsible for system maintenance. The structure of the automation system is based upon an architecture of collaborative intelligent agents designed to detect failure in any of the microsatellite's components. The multiagent system consists of a set of different agents devoted to failure detection, prevention and correction. Regarding correction, specific agents for each constitutive part of the microsatellite have been developed that take over the necessary actions to solve any given problem in its operation. The detection agent decides which correction agent control should be transferred, based upon inference obtained from its knowledge base made up of rules for testing and diagnosis. Actions for correction may imply the use of redundant systems, which can reconfigure themselves to avoid defective circuits, among other repairing strategies. The prevention agent uses predictive models that have been developed for each significant failure mode. Statistical models are also used by this agent to determine the shape of the distribution of times to failure. The prevention agent selects the corresponding correction agent to which control is going to be transferred and this agent carries out the necessary actions to prevent the system failure. The overall intelligent system employs a blackboard architecture for communication and collaboration among agents. Several simulations with specially designed test cases used to evaluate the system performance suggest that in order for maintenance automation to be effective, it must be designed in close relationship with human operators who will occasionally troubleshoot, maintain and repair the microsatellite from earth. This human-centered approach of the design implies assigning particular importance to the effectiveness achieved in the process of knowledge acquisition when the intelligent agents are being designed.