Articles & Issues
- Language
- English
- Conflict of Interest
- In relation to this article, we declare that there is no conflict of interest.
- Publication history
-
Received June 22, 2025
Accepted July 25, 2025
Available online November 25, 2025
-
This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/bync/3.0) which permits
unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
All issues
Design and Implementation of a Neural Network‑Based Control Strategy for Temperature‑Regulated Direct Methanol Fuel Cell
https://doi.org/10.1007/s11814-025-00531-z
Abstract
Direct Methanol Fuel Cell (DMFC) stands out for its enhanced power, reduced weight, and extended operational life, making
it ideal, portable, off-grid applications. Its performance is highly sensitive to temperature variations, necessitating precise
monitoring and control to achieve optimal efficiency. In this study, the impact of temperature on DMFC performance was
examined through real-time experiments from 303 to 343 K. The behavior of the system under varying conditions, viz.,
temperature and operational stability at current levels from 1 to 11.8 A. The experimental findings affirm that the DMFC
exhibits stable and reliable performance. To enhance control, advanced dynamic models and intelligent controllers were
developed and compared, including the Radial Basis Function Neural Network–Proportional-Integral Controller (RBNNPIC),
a Fuzzy adaptive PI controller, and a Ziegler–Nichols-based PI controller. The RBNN-based controller demonstrates
fast convergence and strong capability to avoid local optima, highly effective for real-time DMFC temperature regulation.
Further, the experimental validation confirmed that the proposed RBNN-based control strategy was successfully implemented
in a temperature-regulated DMFC system. Controller performance was assessed based on CPM indices for servo response
and load rejection, which are lowest among other controllers. The results clearly establish the superiority of the RBNN-PIC
over the existing controllers.
