基于神经网络结合遗传算法的Jiles-Atherton磁滞模型参数计算

Parameters Calculation of Jiles-Atherton Hysteresis Model Based on Combination of Genetic Algorithms and Neural Networks

根据改进的Jiles-Atherton磁滞数学模型,提出了一种实用的磁滞模型参数的提取方法,即基于神经网络结合遗传算法的方法,通过神经网络训练拟合寻优函数,以及遗传算法极值寻优,而得到Jiles-Atherton磁滞模型的5个常规参数。计算证明,应用本文方法的计算参数得到的磁滞回线与实验磁滞回线相吻合。

Based on the improved Jiles-Atherton hysteresis model, this paper presents a modified method, combining genetic algorithm and neural network method to calculate the parameters of the Jiles-Atherton hysteresis model. In the proposed method, five regular parameters of the Jiles-Atherton hysteresis model are obtained through the neural network training to find the optimization function and through the genetic algorithm to find the function extreme. The Jiles Atherton hysteresis model parameters and hysteresis curve are obtained by the genetic algorithm combined with the neural network. The numerical results obtained by this method are found to be in good agreement with the measurement data.