Black-Box Modelling of a DC-DC Buck Converter Based on a Recurrent Neural Network

被引：22

作者：

Rojas-Duenas, Gabriel ^{[1
]}

Riba, Jordi-Roger ^{[1
]}

Kahalerras, Khaled ^{[2
]}

Moreno-Eguilaz, Manuel ^{[1
]}

Kadechkar, Akash ^{[1
]}

Gomez-Pau, Alvaro ^{[1
]}

机构：

[1] Univ Politecn Cataluna, Terrassa, Spain

[2] Airbus Operat SAS, Toulouse, France

来源：

2020 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT) | 2020年

关键词：

neural network; power converter; training; prediction; system identification; black-box model; POWER CONVERTERS; IDENTIFICATION;

D O I：

10.1109/ICIT45562.2020.9067098

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Artificial neural networks allow the identification of black-box models. This paper proposes a method aimed at replicating the static and dynamic behavior of a DC-DC power converter based on a recurrent nonlinear autoregressive exogenous neural network. The method proposed in this work applies an algorithm that trains a neural network based on the inputs and outputs (currents and voltages) of a Buck converter. The approach is validated by means of simulated data of a realistic nonsynchronous Buck converter model programmed in Simulink and by means of experimental results. The predictions made by the neural network are compared to the actual outputs of the system, to determine the accuracy of the method, thus validating the proposed approach. Both simulation and experimental results show the feasibility and accuracy of the proposed black-box approach.

引用

页码：456 / 461

页数：6

共 12 条

[1] Acuna G., 2012, The 2012 International Joint Conference on Neural Networks (IJCNN), P1, DOI DOI 10.1109/IJCNN.2012.6252476
[2] Balakrishnan H, 2018, IEEE INT POWER ELEC, P242, DOI 10.1109/EPEPEMC.2018.8521981
[3] A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation
Boussaada, Zina
Curea, Octavian
Remaci, Ahmed
Camblong, Haritza
Bellaaj, Najiba Mrabet
[J]. ENERGIES, 2018, 11 (03):
[4] Wind Speed Prediction Using a Univariate ARIMA Model and a Multivariate NARX Model
Cadenas, Erasmo
Rivera, Wilfrido
Campos-Amezcua, Rafael
Heard, Christopher
[J]. ENERGIES, 2016, 9 (02):
[5] Modeling Electronic Power Converters in Smart DC Microgrids An-Overview
Frances, Airan
Asensi, Rafael
Garcia, Oscar
Prieto, Roberto
Uceda, Javier
[J]. IEEE TRANSACTIONS ON SMART GRID, 2018, 9 (06) : 6274 - 6287
[6] Selection of Proper Neural Network Sizes and Architectures-A Comparative Study
Hunter, David
Yu, Hao
Pukish, Michael S., III
Kolbusz, Janusz
Wilamowski, Bogdan M.
[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2012, 8 (02) : 228 - 240
[7] Grey-box model for pipe temperature based on linear regression
Kicsiny, Richard
[J]. INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER, 2017, 107 : 13 - 20
[8] Identification and Prediction of Dynamic Systems Using an Interactively Recurrent Self-Evolving Fuzzy Neural Network
Lin, Yang-Yin
Chang, Jyh-Yeong
Lin, Chin-Teng
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2013, 24 (02) : 310 - 321
[9] Prakash A., 2017, BENEFITS LOW INDUCTI
[10] Identification of nonlinear systems using NARMAX model
Rahrooh, Alireza
Shepard, Scott
[J]. NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 2009, 71 (12) : E1198 - E1202

← 1 2 →