CAJ | 학술논문

利用 BP 神经网络-遗传算法对化学镀 Ni-Fe-Co-P 工艺进行寻优.首先利用正交试验表安排一定数量的实验,以构成人工神经网络的训练集.对训练集训练并利用实验数据检验,得到化学镀工艺的人工神经网络模型.最终再利用遗传算法对其进行寻优,以确定最佳的工艺参数.结果表明该方法结果可靠,可以用于实际各种工艺参数的寻优.
이용 BP 신경망락-유전산법대화학도 Ni-Fe-Co-P 공예진행심우.수선이용정교시험표안배일정수량적실험,이구성인공신경망락적훈련집.대훈련집훈련병이용실험수거검험,득도화학도공예적인공신경망락모형.최종재이용유전산법대기진행심우,이학정최가적공예삼수.결과표명해방법결과가고,가이용우실제각충공예삼수적심우.
BP neural network-genetic algorithm was used for optimization of Ni-Fe-Co-P electroless plating process. First a certain number of experiments were arranged by using orthogonal test table, in order to constitute a training set of artificial neural network. Through training set training and test of experimental data, artificial neural network model of the chemical plating process was obtained. Then its optimization was carried out by the genetic algorithm, in order to determine the optimal process parameters. The results show that the method is reliable, and can be used to optimize actual various process parameters.