UVESH SIPAI

The PQD ML Classifier App is a robust tool designed to facilitate the classification of power quality disturbances (PQDs) using machine learning algorithms. Users can import datasets and labels generated by the previous apps, then select from various classifiers, including k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Gaussian Naive Bayes (GNB). The app allows customization of the train-test split ratio, k-fold cross-validation, and hyperparameter optimization through Grid Search or Random Search.

The DWT MRA Feature Extraction App is a specialized tool designed for extracting statistical features from power quality disturbance (PQD) signals using Discrete Wavelet Transform (DWT) and Multi-Resolution Analysis (MRA). Researchers can import PQD data and select the desired mother wavelet and level of decomposition to perform wavelet-based analysis. The app allows users to extract a comprehensive set of statistical features, such as mean, standard deviation, skewness, kurtosis, and energy, from the wavelet coefficients.

The PQD Data Generation App is a user-friendly tool designed to create synthetic power quality disturbance (PQD) signals tailored to specific research needs. Users can customize various parameters, including the number of signals per class, cycles per signal, fundamental frequency, sampling frequency, amplitude, and noise levels, such as white Gaussian noise. The app supports the generation of signals that adhere to IEEE 1159-2019 standards.