SymbolicPhasor: Power System Phasor Estimation via Deep Symbolic Regression

Abstract

Accurate phasor estimation during power system faults is challenging because fault currents contain decaying DC offsets, harmonics, noise, and possible frequency deviations. These distortions can significantly degrade conventional discrete Fourier transform-based estimators, especially during the first cycle after fault inception. This paper presents SymbolicPhasor, a dynamic deep symbolic regression framework for estimating the fundamental component of distorted fault current signals. The method processes the signal through overlapping moving windows, learns interpretable analytical expressions for the full waveform within each window, and then projects the reconstructed signal onto nominal sine and cosine bases to recover the instantaneous fundamental magnitude and phase. By embedding symbolic tokens corresponding to the nominal, third-, and fifth-order harmonic frequencies, the proposed approach is guided toward physically meaningful expressions while preserving data-driven flexibility. The method is evaluated under single decaying-DC, multiple decaying-DC, and off-nominal frequency conditions. Results show consistently high reconstruction accuracy, with coefficient of determination values reaching 0.985, demonstrating that the proposed framework can recover the fundamental component within one cycle for practical protective relaying and measurement applications.