ZCP Dataset - Distorted Sinusoidal Signal

Zero-crossing point detection is necessary to establish a consistent performance in various power system applications. Machine learning models can be used to detect zero-crossing points. A dataset is required to train and test machine learning models in order to detect the zero crossing point. These datasets can be helpful to the researchers who are working on zero-crossing point detection problem using machine learning models. All these datasets are created based on MATLAB simulations. Total 28 datasets developed based on various window size like 5,10,15,20 and noise levels like 10%,20%,30%,40%,50% and 60%. Similarly, total 28 datasets developed based on various window size like 5,10,15,20 and THD levels like 10%,20%,30%,40%,50% and 60%. Also, total 36 datasets prepared based on window size like 5,10,15,20 and combination of noise (10%,30%,60%) and THD (20%,40%,60%). Each dataset consists 4 input features called slope, intercept, correlation and RMSE, and one output label with the values either 0 or 1. 0 represents non zero-crossing point class, whereas 1 represents zero-crossing point class. Datasets Information like number of samples and combinations (Window size, Noise and THD) is available in Data Details excel sheet. These datasets will be useful for faculty, students and researchers who are working on ZCP problem.