STFT Cluster Analysis for DC Pulsed Load Monitoring and Fault Detection on Naval Shipboard Power Systems

Abstract

Current trends in Naval shipboard power system architecture indicate that the electrification of future warships is inevitable, and it will be equipped with loads that draw periodic pulsed currents from the dc microgrid or have large transients while switching state. In order to monitor the operation of those loads, solely time-based features are not enough as they do not provide sufficiently unique information to differentiate various transient stages of the load profile. The focus of more recent research has been on extracting time–frequency features. However, no comprehensive solution exists that could work for any general load profile. The proposed load monitoring and fault detection method presented in this article outlines a data clustering-based approach to extract unique feature vectors from short-time Fourier transform analysis for any pulsed load. These features can then be used to identify various events in the load transient as well as shunt faults and series arcing faults. Implementation and performance of the scheme for several load profiles and fault scenarios are included.