粒子群神经网络用于电磁兼容预测  

PSO-based Neural Network Used for Prediction of EMC

作　　者：陈书文[1] 张煜东[2] 张斌[3] 王水花[2] 

机构地区：[1]江苏省辐射环境保护咨询中心,江苏南京210096 [2]东南大学信息科学与工程学院,江苏南京210096 [3]江苏省辐射监测管理站,江苏南京210096

出　　处：《无线电工程》2010年第3期39-41,共3页Radio Engineering

基　　金：东南大学优秀博士学位论文基金(YBJJ0908);河海大学青年科技基金(08D002-04)

摘　　要：为了更好地对电磁兼容进行预测,提出采用人工神经网络的方法。传统的BP神经网络易于陷入局部最优,因此采用粒子群算法对网络权值进行优化。以平行线间电磁耦合干扰为具体算例,证明本算法的预测结果的均方误差仅有10-4数量级。因此,使用PSO优化网络权值的方法有效,且神经网络模型能准确预测电磁兼容。In order to predict the electromagnetic compatibility more effectively, an improved method based on artificial neural network was proposed. Due to the fact that BP neural network was inclined to be trapped in local extrama, a novel network--particle swarm optimization based neural network--was proposed in this paper to solve the above shortcoming. The specific example on electromagnetie coupling interference between two parallel wires demonstrates the median square error of the prediction is more or less only 10^-4 order of magnitude. Thus, this PSO-based neural network is effective, and our model can predict electromagnetic compatibility accurately.

关 键 词：电磁兼容 预测 神经网络 

分 类 号：TN911.73[电子电信—通信与信息系统]