基于GA-BP神经网络的316L不锈钢成形尺寸精度预测

Prediction of Forming Dimensional Accuracy of 316L Stainless Steel Based on GA-BP Neural Network

建立选区激光熔化316L不锈钢成形质量预测模型,以响应面中心复合设计试验数据作为反向传播(Back Propagation,BP)神经网络模型的训练样本,采用遗传算法对BP神经网络的初始连接权值和阈值进行优化。结果表明,通过遗传算法优化的BP神经网络模型能够有效预测精度,使得成形件尺寸精度的平均相对预测误差为5.42%。

The prediction model of forming quality of 316L stainless steel melted by selective laser was established. The response surface center composite design test data is taken as the training sample of the Back Propagation(BP) neural network model, and the genetic algorithm is used to optimize the initial connection weight and threshold of the BP neural network. The results show that the BP neural network model optimized by genetic algorithm can achieve effective precision prediction, and the average relative prediction error of the formed part size accuracy is 5.42%.