Scholarlink

<p>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&#xa0;K. The behavior of the system under varying conditions, viz., temperature and operational stability at current levels from 1 to 11.8&#xa0;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 (RBNN-PIC), 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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design and Implementation of a Neural Network-Based Control Strategy for Temperature-Regulated Direct Methanol Fuel Cell

  • 期刊论文

  • 发表日期：

    2025年8月2日

查看全文
  • Ramasamy Govindarasu,
  • Divya Baskaran,
  • M. Vijayakarthick,
  • Hun-Soo Byun

摘要

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 (RBNN-PIC), 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.