基于人工神经网络的点焊熔核直径预测

Nugget size forecasting based on artificial neural network

从电极位移曲线上提取出的两个特征值及焊接能量值作为输入值,熔核直径为输出值,建立了基于BP算法的铝合金直流点焊熔核直径预测模型。该模型为隐层结点数为5的三层结构,隐层转移函数为Sigmoid函数,输出层的转移函数为线性函数。对实测结果与仿真结果进行了对比分析,结果表明,45.2%的预测值与实测值相差不超过0.5mm,77.4%的预测误差不超过1mm,94.3%的预测误差没有超过2mm。回归分析结果为A=0.878T+0.982。

The nugget size forecasting model was built based on Bp algorithm of artificial neural network.The input parameters of the model are two characteristic number extracted from electrode displacement curve and welding energy value.The output parameter of the model is nugget size.The model has three layers and the hidden layer have five nodes.The transfer function of hidden layer is Sigmoid function and the transfer function of output layer is linear function.Measured value and forecasting value were analyzed and the difference between measured value and forecasting value was calculated.The results showed that 45.2% of the difference is less than 0.5 mm,77.4% of the difference value is less than 1 mm and 94.3% of the difference value is less than 2 mm.The simulation result was also analyzed by regression analysis method and the result was A =0.878T + 0.982.