Scholarlink

<p>The increasing integration of electric vehicles (EVs) into the transportation sector necessitates the development of reliable and power quality compliant charging systems. One of the challenges in EV charging infrastructure is the harmonic distortion introduced by power electronic converters, which affects grid stability and performance. This paper presents a power quality oriented EV charging solution that incorporates a canonical switching converter and a flyback converter, regulated through an Artificial Neural Network (ANN) based control technique. The ANN controller dynamically adjusts switching patterns based on the voltage error and its rate of change, aiming to reduce total harmonic distortion (THD) and improve power factor correction (PFC). The effectiveness of the proposed control strategy is validated through both simulation and a 350&#xa0;W experimental prototype operating at 230&#xa0;V and 50&#xa0;Hz. Experimental results confirm that the input current THD is consistently maintained below 2%, complying with the IEEE 519–2014 standards, while also achieving a power factor (PF) above 0.98. These results demonstrate that the proposed ANN-controlled charger significantly enhances power quality and offers a promising solution for next-generation EV charging systems.</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

Artificial neural network controlled canonical switching converter for electric vehicle charging applications

  • 期刊论文

  • 发表日期：

    2026年4月21日

查看全文
  • M. Muhammed Alaudeen Ashiq,
  • L. Jessi Sahaya Shanthi,
  • G. Sivasankar,
  • C. Balasundar

摘要

The increasing integration of electric vehicles (EVs) into the transportation sector necessitates the development of reliable and power quality compliant charging systems. One of the challenges in EV charging infrastructure is the harmonic distortion introduced by power electronic converters, which affects grid stability and performance. This paper presents a power quality oriented EV charging solution that incorporates a canonical switching converter and a flyback converter, regulated through an Artificial Neural Network (ANN) based control technique. The ANN controller dynamically adjusts switching patterns based on the voltage error and its rate of change, aiming to reduce total harmonic distortion (THD) and improve power factor correction (PFC). The effectiveness of the proposed control strategy is validated through both simulation and a 350 W experimental prototype operating at 230 V and 50 Hz. Experimental results confirm that the input current THD is consistently maintained below 2%, complying with the IEEE 519–2014 standards, while also achieving a power factor (PF) above 0.98. These results demonstrate that the proposed ANN-controlled charger significantly enhances power quality and offers a promising solution for next-generation EV charging systems.