【摘要】 以实验为基础,利用神经网络和遗传算法优化Al-5%Cu合金的电脉冲孕育处理工艺参数。神经网络的输入参数为脉冲电压、脉冲时间和电脉冲孕育处理时熔体温度,输出参数是合金凝固组织的晶粒度。在神经网络训练的基础上,采用遗传算法优化神经网络的输入参数。结果表明,神经网络和遗传算法的组合建模获得了较好的优化结果。更多还原

【Abstract】 Based on the experiments an optimal pattern of the electric pulse modification for Al-5%Cu was investigated using neural networks and genetic algorithms.The input parameters of the artificial neural network(ANN) are the voltage of electric pulse,electric pulse time and temperature of molten alloy.The outputs of the ANN model are the grain size of Al-5%Cu alloy.Based the successfully trained ANN model,genetic algorithms(GA) are used to optimize the input parameters of the model.The good optimization can be obtained through the integrated mode of neural networks and genetic algorithms.更多还原