A Novel Electromagnetic Interference Source Reconstruction Method based on Artificial Neural Network

摘要：

　　This paper discusses an equivalent magnetic dipoles hybrid with artificial neural network method to reconstruct the noise source.The original near-field of the real source is obtained through the near-field scanning,and then the equivalent magnetic dipoles source is constructed to predict the radiation from the real source.The information of fields amplitude and phase is used to find the magnetic moment and locations of the equivalent dipoles.An iterative method combined with the artificial neural network is proposed for this purpose,where the origin field is continuously subtracted from the new field generated by equivalent magnetic dipoles.Through numerical and experimental results,the accuracy and efficiency of the proposed method are verified.

关键词： Source reconstruction artificial neural network magnetic dipoles

作者: Ze-Kai Hu Yu-Han Zhong Xing-Chang Wei Yi-Wen Wang Yu-Fei Shu

作者单位: College of Information Science and Electronic Engineering Zhejiang University Hangzhou,China

会议类型: 国际会议

会议名称: The 12th International Symposium Antennas, Propagation, and EM Theory(ISAPE 2018)?(第十二届天线、传播与电磁理论国际学术会议)

会议地点: 杭州

会议语种:英文

页码: 1-4

在线出版日期: 2018-12-03（万方平台首次上网日期，不代表论文的发表时间）