Scholarlink

Multilevel inverters have gained prominence in modern power systems due to their ability to generate high-quality output with reduced harmonics. In this article, the author proposed a reduced switch five level multilevel inverter which can be used for various applications. The proposed topology is designed using four unidirectional and one bidirectional switch along with three isolated DC sources to generate five levels of output voltage. However, achieving optimal performance requires intricate parameter tuning, which can be a complex and time-consuming task. To address this challenge, an approach that leverages artificial neural network (ANN) to automate the selection of optimal values for the multilevel inverter control scheme is used. The input parameters for ANN are taken as modulation index and switching frequency. The simulation results using ANN based approach is thus verified by real time results using OPAL-RT controller.

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

A Novel Reduced Switch Multilevel Inverter with Optimal Control Values Selection Using Artificial Neural Network

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Aditya Sirsa,
  • Arvind Mittal,
  • Amit Ojha,
  • Malle Lingamaiah

摘要

Multilevel inverters have gained prominence in modern power systems due to their ability to generate high-quality output with reduced harmonics. In this article, the author proposed a reduced switch five level multilevel inverter which can be used for various applications. The proposed topology is designed using four unidirectional and one bidirectional switch along with three isolated DC sources to generate five levels of output voltage. However, achieving optimal performance requires intricate parameter tuning, which can be a complex and time-consuming task. To address this challenge, an approach that leverages artificial neural network (ANN) to automate the selection of optimal values for the multilevel inverter control scheme is used. The input parameters for ANN are taken as modulation index and switching frequency. The simulation results using ANN based approach is thus verified by real time results using OPAL-RT controller.