摘要
采用人工神经网络方法对5A06铝合金电子束焊接的熔深进行了预测研究。使用正交试验方法采集训练样本,并对样本进行标准化,通过确定合适的网络模型、网络结构及算法、网络训练次数,建立了从加速电压、束流、焊接速度到熔深的BP网络映射模型。网络训练后的检验精度较高,通过编制的用户界面实现了一定工艺参数范围内的熔深预测。
Fusion penetration for 5A06 Electronic Beam Welding（EBW） is predicted based on Articial Neural Network（ANN）.Based on adaptive network model and network structure,and selected trainning algorithm and times,a BP neural network mapping model from accelerating voltage,beam current and welding speed to fusion penetration is established.Training samples are obtained by using orthogonal experiment and normalized for reducing prediction e^mor.The trained network can predict fusion penetration in a definite range through GUI, which has good verifying precision.
出处
《电焊机》
2007年第3期14-16,共3页
Electric Welding Machine
