Preface

The increasing complexity of space vehicles such as satellites, and the cost reduction measures that have affected satellite operators are increasingly driving the need for more autonomy in satellite diagnostics and control systems. Current methods for detecting and correcting anomalies onboard the spacecraft as well as on the ground are primarily manual and labor intensive, and therefore, tend to be slow. Operators inspect telemetry data to determine the current satellite health. They use various statistical techniques and models, but the analysis and evaluation of the large volume of data still require extensive human intervention and expertise that is prone to error. Furthermore, for spacecraft and most of these satellites, there can be potentially unduly long delays in round-trip communications between the ground station and the satellite. In this context, it is desirable to have onboard fault-diagnosis system that is capable of detecting, isolating, identifying or classifying faults in the system without the involvement and intervention of operators. Toward this end, the principle goal here is to improve the efficiency, accuracy, and reliability of the trend analysis and diagnostics techniques through utilization of intelligent-based and hybrid-based methodologies. It is a well-recognized fact that an automated satellite health monitoring and fault diagnosis system using advanced decision-support systems is the need of today’s satellite ground support system. A system that can generate an early-warning to the operator is well suited to satellite ground operations where the operators are already overloaded with satellite command and control tasks. Due to recent advances in computing technologies, health monitoring and fault diagnosis schemes for satellites can be automated using advanced decision-support systems such as rule-based expert systems and artificial intelligence (AI)-based methodologies. Soft computing based on artificial neural-networks is witnessing an increasing use in such activities. Toward this end, in this work we have developed, analyzed, and implemented novel techniques to accurately monitor the telemetry data of the satellite’s ACS system to pinpoint potential causes of actuator anomalies and failures and to facilitate and optimize the operator resources to critical events for troubleshooting problems. Different approaches have been investigated and developed for accurately predicting actuator failures based on detection of abnormal and/or subtle deviations of the actuators from their normal range in key variables/feature points. We believe this additional diagnostic capability combined with autonomous fault detection, diagnosis,