Learning magnetization dynamics

JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS

卷:491

Article

Kovacs, Alexander¹  Fischbacher, Johann¹  Oezelt, Harald¹  Gusenbauer, Markus¹  Exl, Lukas²  Bruckner, Florian³  Suess, Dieter³  Schrefl, Thomas¹ 

[1] Danube Univ Krems, Dept Integrated Sensor Syst, Viktor Kaplan Str 2, A-2700 Wiener Neustadt, Austria

[2] Wolfgang Pauli Inst, Fac Math, Oskar Morgenstern Pl 1, A-1090 Vienna, Austria

[3] Univ Vienna, Christian Doppler Lab Adv Magnet Sensing & Mat, Fac Phys, Wahringer Str 17, A-1090 Vienna, Austria

关键词: Micromagnetics;    Magnetic sensors;    Machine learning;    Model order reduction;   

DOI  :  10.1016/j.jmmm.2019.165548

来源: Elsevier

【 摘 要 】

Deep neural networks are used to model the magnetization dynamics in magnetic thin film elements. The magnetic states of a thin film element can be represented in a low dimensional space. With convolutional autoencoders a compression ratio of 1024:1 was achieved. Time integration can be performed in the latent space with a second network which was trained by solutions of the Landau-Lifshitz-Gilbert equation. Thus the magnetic response to an external field can be computed quickly.

【 授权许可】

Free