THD Reduction in Cascaded H-Bridge Multilevel Inverter using Adaptive Neuro-Fuzzy Controller

Multilevel inverters (MLIs) have gained significant attention in modern power electronics due to their ability to generate high-quality output waveforms with reduced Total Harmonic Distortion (THD). Among various MLI topologies, the Cascaded H-Bridge Multilevel Inverter (CHB-MLI) offers notable advantages such as modularity, scalability, and lower switching losses. However, maintaining a low THD in CHB-MLI output under varying operating conditions remains a critical challenge. This research proposes an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based controller to optimize the performance of CHB-MLIs by reducing THD effectively. The ANFIS controller combines the advantages of neural networks and fuzzy logic to dynamically adjust control parameters in response to real-time changes in load and operating conditions. Simulation studies and experimental validation reveal that the proposed system achieves superior THD reduction compared to conventional Proportional-Integral (PI) and pure fuzzy logic controllers. The findings suggest that the ANFIS-based approach provides a robust and efficient solution for enhancing the power quality in renewable energy systems and industrial drives.