Scholarlink

<p>Incorporating Renewable Energy Sources (RES), mainly solar energy into Brushless Direct Current (BLDC) motor fed Electric Vehicles (EVs) are becoming progressively popular as the world moves more quickly towards clean and sustainable transportation. However, EVs’ dynamic load demands and the erratic nature of solar radiation make it difficult to maintain control dependability, energy efficiency and peak performance. In order to address these issues, a refined photovoltaic (PV)-driven Trans Quasi Z-Source Modified SEPIC-Luo (TQZSMSL) converter and energy management system is presented in this study. A Lyrebird Optimisation Algorithm (LOA)-optimized Radial Basis Function Neural Network (RBFNN) is the main goal of proposed framework, guaranteeing real-time adaptation to varying solar input. A TQZSMSL converter is used in conjunction with this, offering reliable and adaptable voltage conversion capabilities to sustain a constant DC output. The BLDC motor speed is regulated with the aid of Proportional Integral (PI) controller. Also an Internet of Things (IoT)-enabled FPGA controller (NodeMCU Wi-Fi module) is included to continuously monitor important metrics like motor speed, battery State-of-Charge (SoC), and panel voltage and current. A cloud-based IoT monitoring system receives this data for remote diagnostics and analytics on energy management. The validation of proposed model is done via MATLAB/Simulink, an outcomes are made compared with other classical models in terms of voltage conversion efficiency (97.1%) as well as tracking efficiency of (99.97%).</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 of a smart solar-powered EV motor drive using TQZSMSL converter and LOA-optimized RBFNN MPPT

  • 期刊论文

  • 发表日期：

    2025年11月21日

查看全文
  • T. Muthamizhan,
  • J. Raji,
  • K. Sakthidhasan,
  • K. Aravinda

摘要

Incorporating Renewable Energy Sources (RES), mainly solar energy into Brushless Direct Current (BLDC) motor fed Electric Vehicles (EVs) are becoming progressively popular as the world moves more quickly towards clean and sustainable transportation. However, EVs’ dynamic load demands and the erratic nature of solar radiation make it difficult to maintain control dependability, energy efficiency and peak performance. In order to address these issues, a refined photovoltaic (PV)-driven Trans Quasi Z-Source Modified SEPIC-Luo (TQZSMSL) converter and energy management system is presented in this study. A Lyrebird Optimisation Algorithm (LOA)-optimized Radial Basis Function Neural Network (RBFNN) is the main goal of proposed framework, guaranteeing real-time adaptation to varying solar input. A TQZSMSL converter is used in conjunction with this, offering reliable and adaptable voltage conversion capabilities to sustain a constant DC output. The BLDC motor speed is regulated with the aid of Proportional Integral (PI) controller. Also an Internet of Things (IoT)-enabled FPGA controller (NodeMCU Wi-Fi module) is included to continuously monitor important metrics like motor speed, battery State-of-Charge (SoC), and panel voltage and current. A cloud-based IoT monitoring system receives this data for remote diagnostics and analytics on energy management. The validation of proposed model is done via MATLAB/Simulink, an outcomes are made compared with other classical models in terms of voltage conversion efficiency (97.1%) as well as tracking efficiency of (99.97%).