Aerospace DC Arcing Fault Detection Using Neural Network Techniques

In spacecraft energy power system (EPS), the objective of fault protection is to detect and respond to spacecraft faults. Its purpose is to eliminate single point failures or their effects and to ensure the spacecraft system integrity under anomalous conditions. Also, it is important to keep the continuity of the power supply and at the same time increase the reliability of spacecraft Energy power system. One of most deadly faults is arcing faults, which are accompanied by very erratic waveform variations. The sustainable current level in the arc is not sufficient to be reliably detected by conventional means. Feeder current signal analysis provides a solution to this detection problem. A Fast Fourier Transform method is applied to decompose the monitored voltage and current signals into a series of detailed spectral components. The spectral energies are calculated and then employed to train a neural network to identify arcing faults accurately.