Autors: Hinov, N. L., Gilev, B. N.
Title: Intelligent Design of ZVS Single-Ended DC/AC Converter Based on Neural Network
Keywords: intelligent modeling and design; neural networks; resonant c

Abstract: This paper presents a model-based and neural network-based innovative design of single-ended transistor resonant DC/AC converters with zero voltage switching (ZVS). A characteristic of the proposed design method is that the determination of the circuit elements of the converter is performed with an automated procedure, as their values are determined by the output of a previously trained neural network. The use of the proposed method is justified in cases where there is no methodology for the design of the specific power electronic device, or such a methodology exists, but it is either too complex or based on a large number of assumptions. This is usually due to the increasing complexity of power circuits, their possible modes of operation, and the inevitable assumptions and limitations in the analyses and methodologies based on them. In this way, a natural combination of classic design methods and innovative processes is developed based on applied techniques for AI.

References

    Issue

    Inventions, vol. 8(1), 2023, Switzerland, MDPI, Basel, Switzerland, DOI 10.3390/inventions8010041

    Copyright MDPI AG

    Цитирания (Citation/s):
    1. Hou, Langbo; Chen, Heng; Wang, Jinjun; Qiao, Shichao; Xu, Gang; Chen, Honggang; Liu, Tao, Optimal Dispatch Strategy for a Distribution Network Containing High-Density Photovoltaic Power Generation and Energy Storage under Multiple Scenarios, DOI 10.3390/inventions8050130 - 2023 - в издания, индексирани в Scopus или Web of Science

    Вид: статия в списание, публикация в издание с импакт фактор, публикация в реферирано издание, индексирана в Scopus и Web of Science