电子元件与材料2009，Vol.28Issue(8)：75-77,85,4.DOI:10.3969/j.issn.1001-2028.2009.08.021
用Bayesian正则化BP神经网络预测稀土永磁体性能
Property prediction of the (Nd2Fe14B/α-Fe) permanent magnet based on the Bayesian-regularization BP neural network
摘要
Abstract
The (Nd2Fe14B/α-Fe) permanent magnetic property prediction model was bulit by taking magnetic particle preparation processes(spinning speed and annealing temperature) and alloy components as network input, the magnetic properties as output. For enhancing the model's ability of generalization it was trained by the way of weighted detecting method and clustering multiple based on the Bayesian-regularization BP neural network. The input data was analyzed the principal components for reducing its dimension.The results show that this model's generalization is better. The relative error between the measured value and predicted value of Br is confined to about 2% and that of Hcj、(BH)max to 5%. And the average of the relative error fluctuates within 1% in every prediction.关键词
纳米晶复相(Nd2Fe14B/α-Fe)永磁体/主成分分析/Bayesian正则化/BP神经网络/泛化Key words
nanocrystalline multiphase (Nd2Fe14B/α-Fe) permanent magnet/principal component analysis/Bayesian-regularization BP neural network/generalization分类
信息技术与安全科学引用本文复制引用
王向中,查五生,刘锦云,储林华..用Bayesian正则化BP神经网络预测稀土永磁体性能[J].电子元件与材料,2009,28(8):75-77,85,4.基金项目
四川省教育厅重点资助项目(No. 2004A110) （No. 2004A110）
