Individual information
Ruohan GONG | ![]() | |
Titre | Post-Doctorant | |
Equipe | Outils et Méthodes Numériques | |
Adresse | Université de LILLE Avenue Paul langevin 59655 VILLENEUVE-D'ASCQ | |
Téléphone | +33 (0)7-86-23-05-76 | |
Ruohan.Gong@univ-lille.fr | ||
Observation / Thématique de recherche | Multi-physics field analysis and computing | |
Publications |
International Journals |
---|
[1] Investigation of Convolutional Neural Network U-net under Small Datasets in Transformer Magneto-Thermal Coupled Analysis The International Journal for Computation and Mathematics in Electrical and Electronic Engineering (COMPEL), Vol. 39, N°. 4, pages. 959-970, 08/2020, URL, Abstract GONG Ruohan, TANG Zuqi |
This paper aims to investigate the approach combine the deep learning (DL) and finite element method for the magneto-thermal coupled problem. |
International Conferences and Symposiums |
[1] Small Data Sets Deep Learning based on DCGAN for Magnetic Field CEFC 2020, Nov 16-18, 2020 – Pisa, Italy, 11/2020 GONG Ruohan, ZHOU Xiangchun, LI Yue, CUI Tao, TANG Zuqi |
[2] Training Sample Selection Strategy Applied To Convolutional Neural Network In Magneto-Thermal Coupled Analysis CEFC 2020, Nov 16-18, 2020 – Pisa, Italy, 11/2020 GONG Ruohan, TANG Zuqi |
[3] Convolutional Neural Network U-net applied in Transformer Multi-physics Analysis COMPUMAG 2019, Paris, France, 07/2019 GONG Ruohan, TANG Zuqi |
[4] 3D coupled electromagnetic-fluid-thermal analysis and experiment of 10kV oil-immersed triangular wound core transformer 2019 Joint MMM-Intermag, January 14-18, 2019 Washington, DC, 01/2019 GONG Ruohan, TANG Zuqi, WANG Shuhong, HENNERON Thomas, RUAN Jiangjun |
National Conferences and Symposiums |
[1] Computer-Aided Measurement method of Hysteresis Loop based on Convolution Neural Network SGE 2020, Nantes, France, 11/2020, Abstract GONG Ruohan, BENABOU Abdelkader, TANG Zuqi |
In this paper, a surrogate model base on deep learning (DL) is proposed to predict the hysteresis loops of ferro-magnetic materials. The databases of hysteresis loops were measured on the MPG200D Brockhaus equipment with an Epsteinframe. In order to reduce the experimental cost and accelerate measurements, a surrogate model based on the convolutional neural network (CNN) is proposed. First, presenting the measurement results in the form of 256× 256 × 1 images and extract the 6 most characteristic parameters, namely peak magnetic flux density, frequency, maximum magnetic field strength, remanence, coercivity, and the area of the hysteresis loop. All these physical parameters are taken as the label in the supervised DL process. These labe linformation are normalized to form a Gaussian distribution image of 256× 256 × 3 as the input, and the corresponding B-H curve is the output. Using image-to-image CNN U-net, once the network is effectively trained, the hysteresis loops under other excitation parameters can be predicted without further measurement. Our numerical examples show that the prediction results agree well with the measurement results. The sensitivity of CNN for hysteresis loops prediction with respect to the hyperparameters are investagted. A set of empirical hyperparameter configurations isput forward to guarantee an efficient convergence. This research shows that the proposed approach can be an efficient tool to predict the hysteresis loop of ferromagnetic materials under different circumstances, which can potentially contribute to nonlinear hysteresis FEM computation. |
Dernières actualités
- Séminaire doctorants, 28 Janv. 2021
- Journée des doctorants de 3ème année, 12 Fév. 2021
- Assemblée générale du laboratoire, 22 Janv. 2021
- Soutenance de thèse, Raphaël PILE, 20 Janv. 2021
- Soutenance de thèse, Jérome MARAULT, 20 Janv. 2021
- Soutenance de thèse, Racha AYDOUN, 17 Déc. 2020
- Soutenance de thèse, Abdelhak MEKAHLIA, 17 Déc. 2020
- lauréat du Force Award, Emile Devillers
- Soutenance de Thèse, Xin WEN, 7 Déc. 2020
- Soutenance de thèse, Adham KALOUN, 4 Déc. 2020