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

Devakirubakaran S; Bharatiraja C; Narasimha Prasad T; Praveen Kumar B; Shitharth S

doi:10.1038/s41598-024-77696-w

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

Sci Rep. 2024 Nov 2;14(1):26455. doi: 10.1038/s41598-024-77696-w.

Authors

Devakirubakaran S¹, Bharatiraja C², Narasimha Prasad T³, Praveen Kumar B^{4

5}, Shitharth S⁶

Affiliations

¹ Center for Smart Energy Systems, Chennai Institute of Technology, Chennai, Tamilnadu, India.
² Center for Electric Mobility, Department of Electrical and Electronics Engineering, SRM Institute of Science and Technology, Chennai, India. bharatiraja@gmail.com.
³ Department of Electrical and Electronics Engineering, St. Ann's college of engineering and technology, Chirala, Andhra Pradesh, India.
⁴ Department of Electrical and Electronics Engineering, Vardhaman College of Engineering, Hyderabad, India.
⁵ Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Selangor, Malaysia.
⁶ Department of CSE, Kebri Dehar University, Somali, Ethiopia. shitharths@kdu.edu.et.

Abstract

Fuel cells are the most promising energy source for the future energy demand. The automobile industry is looking at the integration of fuel cells with electric vehicles (EV). This integration comes with many challenges like dynamic operational behaviors. For operating the fuel cell with maximum efficiency, this work proposes an Adaptive Neuro Fuzzy Inference System (ANFIS) based Maximum Power Point Tracking (MPPT) method. The hydrogen flow rate, pressure and stack temperature are the parameters considered to track the maximum power point of the fuel cell. The ANFIS-MPPT algorithm has been integrated with the 1.26 kW fuel cell in MATLAB/Simulink^® and validated in different scenarios like dynamic variation in hydrogen pressure, stack temperature, load variation. The performance has been observed and compared with the conventional MPPT algorithms of Perturb and Observe (P&O) algorithm and Incremental Conductance (InC) algorithm. The proposed ANFIS-MPPT algorithm improves the power stability by 10-15% than the P&O and InC methods. Also, the proposed ANFIS-MPPT has 30% faster response as compared to the P&O algorithm, and 23% than the InC algorithm. From the analysis, it is observed that the ANFIS, P&O and InC methods are having the response time of 2.5 s, 3.6 s and 4.5 s respectively. Also the ANFIS method delivers the maximum power output of 1.26 kW, whereas the P&O and InC deliver 1.13 kW, 1.19 kW respectively. The detailed simulation analysis and results are presented in this paper.

Keywords: Adaptive Neuro-Fuzzy Inference System; Fuel Cell; Maximum Power Point Tracking; Optimum operating point.