Harmonics Real Time Identification Based on ANN, GPS and Distributed Ethernet

A novel harmonic real time identification method by artificial neural network based on GPS technology and distributed Ethernet was proposed in this paper. The method uses an artificial neural network to estimate the amplitudes and phase angles of the distorted current/voltage in power system. In this method, only half cycle harmonic current signal was used as the input of the neural network. In order to improve the accuracy of harmonic source identification, Global Positioning System (GPS) is used as the synchronized signal for an embedded harmonics measurement system based on digital signal processor (DSP). The samples selecting and training methods of artificial neural network are explained and the hardware structure of the embedded harmonic identification system is given. Real-Time Digital Simulator (RTDS) simulation results prove the effectiveness of the proposed method.