论文部分内容阅读
基于BP神经网络算法和理论,研究了Tb0.5Dy0.7Fe1.95合金的磁致伸缩性能,建立了影响磁致伸缩性能参数与伸缩性的预测神经网络模型。结果表明,随着添加元素量的增加,磁致伸缩性在降低;随着磁场强度的增强,磁致伸缩性也随着增强;建立的神经网络模型的预测结果能与实验结果很好对应,误差很小。
Based on the BP neural network algorithm and theory, the magnetostrictive performance of Tb0.5Dy0.7Fe1.95 alloy was studied and a predictive neural network model was established to influence the magnetostrictive performance parameters and scalability. The results show that the magnetostriction decreases with the increase of the amount of added elements, and the magnetostriction increases with the increase of the magnetic field strength. The prediction results of the neural network model established can well correspond with the experimental results, The error is small.