Zero crossing point detection in a distorted sinusoidal signal using random forest classifier

Abstract

The identification of zero-crossing points in a sinusoidal signal is critical in a variety of electrical applications, including protection of power system components and designing of controllers. In this article, 96 datasets are generated from a deformed sinusoidal waveforms using MATLAB. MATLAB generates deformed sinusoidal waves with varying amounts of noise and harmonics. In this study, a random forest model is utilized to estimate the zero crossing point in a deformed waveform using input characteristics such as the slope, intercept, correlation, and RMSE. The random forest model was developed and evaluated in the Google Colab platform. According to simulation data, the model based on random forest predicts the zero-crossing point more accurately than other models such as logistic regression and decision tree classifier.