ANN Identification technique and fuzzy PI Control of a Hybrid Indirect Matrix Converter with a Flying Capacitor three level Inverter in Power Active Filtering Application

Abstract

In this paper, we study the performance of a power active filtering of the current perturbation using a hybrid indirect matrix with a three cell flying capacitance; this hybrid structure is controlled by a fuzzy PI controller in which it gains are tuned with the PSO algorithm and genetic algorithm (GA). In the first part, we present the full grid model with the perturbation source, as well as a detail of the hybrid structure. In the second part, we explain the current perturbation identification technique, and then we passed to gains tuning used algorithms.
 The simulation results by MATLAB, Simscap/sim power system code shows a good performance of the fuzzy PI gains tuning by obtaining a low THD value in the filtration process.

Modeling Longitudinal Evolution of Decommissioned Geostationary Satellites using Neural Networks

“…In the realm of artificial intelligence (AI) and machine learning (ML), a plethora of methodologies and applications have emerged, showcasing the immense potential and versatility of these technologies. Methodologically, AI and ML encompass a wide spectrum of techniques, including feature selection and stability analysis [7], hybrid control systems involving artificial neural networks (ANNs) and fuzzy PI control [8], and comparative assessments of predictive algorithms, such as ordinary ANNs and convolutional neural networks (CNNs) for customer churn prediction [9]. These methods collectively form the foundation for addressing complex challenges across diverse domains.…”