A novel artificial neural network based selection harmonic reduction technique for single source fed high gain switched capacitor coupled multilevel inverter for renewable energy applications.

This research project focuses on the development and simulation-based evaluation of an artificial neural network (ANN) based selective harmonic reduction (SHR) technique applied to a single-source fed high-gain switched-capacitor coupled multilevel inverter (SC-MLI). Designed primarily for renewable energy integration, the proposed topology aims to achieve high voltage gain using a single DC source while minimizing the component count and eliminating the need for multiple isolated sources. To address the inherent challenge of total harmonic distortion (THD) in multilevel waveforms, an ANN-based optimization framework is formulated to determine the optimal switching angles. This machine learning approach replaces conventional transcendental equation-solving methods, offering real-time adaptation and computational efficiency. The project scope includes

modeling the switched-capacitor network, designing the ANN architecture for harmonic mitigation, and conducting comprehensive simulation studies under varying modulation indices. Performance evaluation is carried out by analyzing the output voltage quality, voltage gain, capacitor voltage balancing, and THD profiles, providing a robust methodology for high-efficiency power conversion in solar photovoltaic and other renewable energy systems.

Message: Hi FE, I need help with “A novel artificial neural network based selection harmonic reduction technique for single source fed high gain switched capacitor coupled multilevel inverter for renewable energy applications.” in “Electrical Engineering”