Zero-Crossing Point Detection of Sinusoidal Signal in Presence of Noise and Harmonics Using Deep Neural Networks

Zero-crossing point detection is necessary to establish a consistent performance in various power system applications, such as grid synchronization, conversion and switch-gear protection. In this paper, zero-crossing points of sinusoidal signal are detected using deep neural networks. order train evaluate the network model, new datasets for signals having noise levels from 5% 50% harmonic distortion 10% developed. This complete study implemented Google Colab learning framework Keras. Results shows that proposed model able detect distorted with good accuracy.