Failure Behavior Identification for a Space Antenna via Neural Networks

Using neural networks, a method for the failure behavior identification of a space antenna model is investigated. The proposed method employs three stages. If a fault is suspected by the first stage of fault detection, a diagnostic test is performed on the antenna. The diagnostic test´s results are used by the second and third stages to identify which fault occurred and to diagnose the extent of the fault, respectively. The first stage uses a multi-layer perceptron, the second uses a multi-layer perceptron and neural networks trained with the quadratic optimization algorithm, a novel training procedure, and the third stage uses back-propagation trained neural networks.