Optimal power generation of proton exchange membrane fuel cell using ANFIS based MPPT algorithm.

Area of Science:

• Renewable Energy Systems
• Automotive Engineering
• Control Systems

Background:

• Fuel cells are crucial for future energy demands, particularly in electric vehicles (EVs).
• Integrating fuel cells into EVs presents challenges in managing dynamic operational behaviors.
• Maximizing fuel cell efficiency requires advanced tracking methods for optimal power output.

Purpose of the Study:

• To propose and evaluate an Adaptive Neuro Fuzzy Inference System (ANFIS) based Maximum Power Point Tracking (MPPT) method for fuel cells.
• To enhance the efficiency and dynamic performance of fuel cell systems in automotive applications.
• To compare the proposed ANFIS-MPPT method against conventional MPPT algorithms.

Main Methods:

• Developed an ANFIS-MPPT algorithm considering hydrogen flow rate, pressure, and stack temperature.
• Integrated the ANFIS-MPPT algorithm with a 1.26 kW fuel cell model in MATLAB/Simulink.
• Validated the system under dynamic variations in hydrogen pressure, stack temperature, and load.

Main Results:

• The ANFIS-MPPT algorithm demonstrated a 10-15% improvement in power stability over Perturb and Observe (P&O) and Incremental Conductance (InC) methods.
• ANFIS-MPPT exhibited a 30% faster response than P&O and 23% faster than InC.
• ANFIS achieved a response time of 2.5s, delivering 1.26 kW, outperforming P&O (3.6s, 1.13 kW) and InC (4.5s, 1.19 kW).

Conclusions:

• The ANFIS-based MPPT method offers superior performance in terms of power stability and response time for fuel cell systems.
• This advanced MPPT technique is highly effective for optimizing fuel cell electric vehicle (FCEV) operation.
• The proposed method provides a robust solution for managing dynamic behaviors and maximizing power output in fuel cell applications.