The Artificial Neural Network Modeling of Dynamic Hysteresis Phase Diagram:Application on Mean-Field Ising Hysteresis

摘要：

　　This work used Artificial Neural Network (ANN) to investigate the hysteresis behavior of the Ising spins in structures ranging from one-to two-and three-dimensions.The equation of magnetization motion under the mean-field picture was solved using the Runge-Kutta method to extract the Ising hysteresis loops with varying the temperature, the external magnetic field parameters and the system structure (via the variation of number of nearest neighboring spins).The ANN was then used to establish relationship among parameters via Back Propagation technique in ANN training.With the trained networks, the ANN was used to predict hysteresis data, with an emphasis on the dynamic critical point, and compared with the actual target data.The predicted and the target data were found to agree well which indicates that the ANN functions well in modeling hysteresis behavior and its critical phase-diagram across systems with different structures.

关键词： Artificial Neural Network Ising Model Magnetic Hysteresis Mean-field Analysis

作者: Wimalin Laosiritaworn Kanokwan Kanchiang Yongyut Laosiritaworn

作者单位: Department of Industrial Engineering,Faculty of Engineering,Chiang Mai University,Chiang Mai 50200,T Department of Physics and Materials Science,Faculty of Science,Chiang Mai University,Chiang Mai 5020

会议类型: 国际会议

会议名称: the 2013 2nd International Conference on Metallurgy Technology and Materials(ICMTM2013)(第二届冶金技术与材料国际会议)

会议地点: 香港

会议语种:英文

页码: 16-19

在线出版日期: 2013-06-25（万方平台首次上网日期，不代表论文的发表时间）