论文部分内容阅读
利用人工神经网络的自学习以及非线性逼近能力对材料元素与硬度的相关性进行拟合和预测；并用遗传算法的强寻优能力对喷涂材料成分进行优化．优化结果与非学习Ｎｉ基喷涂材料配方相比较表明，神经网络能对Ｎｉ基喷涂材料的性能进行较好地拟合和预测，而遗传算法则能在不同的样本区间对材料进行优化，二者的有机结合可进一步提高材料优化与设计的有效性．
The correlation between material elements and hardness was fitted and predicted by the self-learning and non-linear approximation ability of artificial neural network, and the spray material composition was optimized by using the strong optimization ability of genetic algorithm. The results of the optimization compared with the non-learning Ni-based coating materials show that the neural network can better fit and predict the performance of the Ni-based coating material, while the genetic algorithm can optimize the material in different sample intervals. Organic combination can further improve the material optimization and design effectiveness.