Design and analysis of aerospace DC arcing faults using fast fourier transformation and artificial neural network

This paper presents a novel scheme based on fast Fourier transformation and artificial neural network is utilized to design and analysis of the DC arcing faults in a spacecraft, for NASA experimental set up. It is important to keep the continuity of the power supply and at the same time increase the reliability of spacecraft energy power system (EPS). One of the most deadly faults is an arcing fault, which are accompanied by very erratic waveforms 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 transformation is applied to decompose the monitored voltage and current signals into a series of detailed spectral components. The artificial neural network is used to detect the arcing faults. The spectral energies are computed and then employed to train the neural network to identify the faults.