论文部分内容阅读
为了预测并控制激光拼焊板的力学性能,本文通过对0.8～1.5mm的St12板及其镀锌板进行差厚、等厚拼焊,在此基础上建立了以焊接工艺参数为输入变量的基于主成分分析的BP神经网络拼焊板力学性能预测模型。通过实例验证表明,本文所建预测模型对拼焊板抗拉强度及伸长率的预测精度均达91%以上。充分表明该模型与试验结果吻合良好,验证了该预测模型的合理性及适用性。
In order to predict and control the mechanical properties of the tailor-welded blanks, this paper, by making the thick-thickness and the isocenter welded sheets of the St12 plate and the galvanized sheet of 0.8-1.5mm, Prediction Model of Mechanical Properties of Tail Welded Plate Based on Principal Component Analysis and BP Neural Network. The experimental results show that the predictive model built in this paper can predict the tensile strength and elongation of the tailor welded plate by more than 91%. It shows that the model is in good agreement with the experimental results, which verifies the rationality and applicability of the model.