Integrating ANFIS for Improved MPPT in A 24V PEMFC System with Switched Inductor Boost Converter

This study presents a comprehensive analysis of a 1.26 kW, 24V Proton Exchange Membrane Fuel Cell (PEMFC) system integrated with an Adaptive Neuro-Fuzzy Inference System (ANFIS) based Maximum Power Point Tracking (MPPT) control and a switched inductor DC-to-DC boost converter. The converter is designed to achieve an output voltage of 220V. The primary objectives of this research are to model the PEMFC system, design the switched inductor DC-to-DC boost converter and develop an ANFIS model for MPPT control. Simulations are conducted to observe the fuel cell voltage and current under varying air and water pressure conditions and the dynamics in the fuel cell parameters are analyzed. Additionally, the study investigates the impact of temperature variations on the fuel cell's performance. The converter output voltage and power are observed under Standard Test Conditions (STC) to evaluate the overall system efficiency. A key focus of the research is the comparison between the ANFIS-based MPPT control and Artificial Neural Network (ANN) based MPPT control for the Switched Inductor DC-to-DC Boost Converter (SIDC) output. The comparative analysis considers variations in air and water pressure as well as temperature changes. The results reveal insights into the dynamic behavior of the PEMFC system under different operating conditions. Furthermore, the comparative study between ANFIS and ANN highlights the efficacy of ANFIS in optimizing the converter output. The proposed model and control strategies contribute to the advancement of PEMFC technology, which offers a valuable foundation for the design and optimization of fuel cell systems in various environmental conditions. This research aligns with the growing interest in renewable energy sources and underscores the importance of advanced control strategies for enhancing the performance of fuel cell systems.