GA-BP神经网络预测钛合金表面粗糙度

BP Neural Network Optimized by Genetic Algorithm Predict the Surface Roughness of Titanium Alloy

为了有效预测铣削加工中钛合金工件的表面粗糙度,建立了以切削速度、进给量、径向切深、轴向切深为输入参数,表面粗糙度为输出参数的预测模型。该预测模型将遗传算法与BP神经网络结合起来,使用遗传算法优化BP神经网络的初始权值和阈值,进行铣削实验获得实验数据,并对神经网络进行训练,最终获得预测模型。通过对比分析GA-BP预测模型、BP预测模型、线性回归预测模型的预测精度,得出GA-BP预测模型具有相对较好的预测精度,证明该预测模型是有效的。

In order to effectively predict the surface roughness of titanium alloy in milling process,the cutting speed,feed rate,radial depth of cut,axial depth of cut are set as input parameters,and surface roughness as the output parameter. The prediction model combines genetic algorithm with BP neural network,and the weights and t hresholds of the BP neural network are optimized by genetic algorithm(GA). Milling experiments were carried out to obtain experimental datas,and train the neural network to obtain the prediction model. By comparing the GA-BP prediction model,BP prediction model,linear regression prediction model prediction accuracy,the GA-BP prediction model’s relatively higher,that proves the accuracy of GA-BP model is effective.