The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Un circuit intégré de commande de grille actif génère une forme d'onde de commutation arbitraire pour réduire la perte de commutation, le dépassement de tension et les interférences électromagnétiques (EMI) en optimisant le modèle de commutation. Cependant, il est difficile de trouver un modèle de commutation optimal car celui-ci offre d’énormes combinaisons possibles. Dans cet article, la méthode permettant d'estimer la perte de commutation et le dépassement de tension à partir du modèle de commutation avec un réseau neuronal (NN) est proposée. Le modèle NN implémenté obtient des résultats d'apprentissage raisonnables pour les ensembles de données.
Satomu YASUDA
Tokyo Metropolitan University
Yukihisa SUZUKI
Tokyo Metropolitan University
Keiji WADA
Tokyo Metropolitan University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Satomu YASUDA, Yukihisa SUZUKI, Keiji WADA, "Estimation of Switching Loss and Voltage Overshoot of Active Gate Driver by Neural Network" in IEICE TRANSACTIONS on Electronics,
vol. E103-C, no. 11, pp. 609-612, November 2020, doi: 10.1587/transele.2019ESS0004.
Abstract: An active gate driver IC generates arbitrary switching waveform is proposed to reduce the switching loss, the voltage overshoot, and the electromagnetic interference (EMI) by optimizing the switching pattern. However, it is hard to find optimal switching pattern because the switching pattern has huge possible combinations. In this paper, the method to estimate the switching loss and the voltage overshoot from the switching pattern with neural network (NN) is proposed. The implemented NN model obtains reasonable learning results for data-sets.
URL: https://global.ieice.org/en_transactions/electronics/10.1587/transele.2019ESS0004/_p
Copier
@ARTICLE{e103-c_11_609,
author={Satomu YASUDA, Yukihisa SUZUKI, Keiji WADA, },
journal={IEICE TRANSACTIONS on Electronics},
title={Estimation of Switching Loss and Voltage Overshoot of Active Gate Driver by Neural Network},
year={2020},
volume={E103-C},
number={11},
pages={609-612},
abstract={An active gate driver IC generates arbitrary switching waveform is proposed to reduce the switching loss, the voltage overshoot, and the electromagnetic interference (EMI) by optimizing the switching pattern. However, it is hard to find optimal switching pattern because the switching pattern has huge possible combinations. In this paper, the method to estimate the switching loss and the voltage overshoot from the switching pattern with neural network (NN) is proposed. The implemented NN model obtains reasonable learning results for data-sets.},
keywords={},
doi={10.1587/transele.2019ESS0004},
ISSN={1745-1353},
month={November},}
Copier
TY - JOUR
TI - Estimation of Switching Loss and Voltage Overshoot of Active Gate Driver by Neural Network
T2 - IEICE TRANSACTIONS on Electronics
SP - 609
EP - 612
AU - Satomu YASUDA
AU - Yukihisa SUZUKI
AU - Keiji WADA
PY - 2020
DO - 10.1587/transele.2019ESS0004
JO - IEICE TRANSACTIONS on Electronics
SN - 1745-1353
VL - E103-C
IS - 11
JA - IEICE TRANSACTIONS on Electronics
Y1 - November 2020
AB - An active gate driver IC generates arbitrary switching waveform is proposed to reduce the switching loss, the voltage overshoot, and the electromagnetic interference (EMI) by optimizing the switching pattern. However, it is hard to find optimal switching pattern because the switching pattern has huge possible combinations. In this paper, the method to estimate the switching loss and the voltage overshoot from the switching pattern with neural network (NN) is proposed. The implemented NN model obtains reasonable learning results for data-sets.
ER -