论文部分内容阅读
以摩擦系数、坯料预热温度、挤压速度、模具预热温度为输入参数,通过DEFORM-3D获取试验数据,应用MATLAB工具箱中径向基函数(RBF),建立了对零件成形质量预测的神经网络模型。结果表明,RBF神经网络模型具有较高的精度,能够很好地反映工艺参数与温挤成形质量之间的复杂关系,有效的提高连杆衬套工艺的设计效率和降低实际实验所需成本。
Taking the friction coefficient, the preheating temperature of the blank, the extrusion speed and the preheating temperature as the input parameters, the test data were acquired by DEFORM-3D and the radial basis function (RBF) of the MATLAB toolbox was used to predict the forming quality of the part Neural Network Model. The results show that the RBF neural network model has high precision and can well reflect the complex relationship between the process parameters and the quality of the warm extrusion, effectively improve the design efficiency of the connecting rod liner process and reduce the cost of the actual experiment.