Autors: Hinov, N. L., Gilev, B. N., Popov, S. A.
Title: Modeling and Design of a Buck DC-DC Converter with Feed Forward Neural Networks
Keywords: Modeling, Design, Buck DC-DC Converter, Feed Forward Neural Networks

Abstract: This paper aims to present an approach which modeling and design a buck DC-DC converter through feedforward neural networks (NN-model). To solve this problem, in addition to the line NN called NN-model is created and the reverse-called NN-designer. The inverse network is used to determine the values of the converter elements. Thus, the paper presents an alternative way of designing power electronic devices, which is based on the use of artificial intelligence (AI) techniques, without applying computational procedures, according to a certain design methodology. In this aspect, this method of modeling and design is faster and more flexible than the standard approach, based on the analysis of the processes in the power scheme in an established mode of operation, after the completion of the transients. The proposed AI approach is confirmed by the parametric design of a synchronous Buck DC-DC converter, oriented to achieve maximum efficiency.

References

    Issue

    2021 International Conference on High Technology for Sustainable Development, HiTech 2021, 2021, Bulgaria,

    Copyright IEEE

    Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus