论文部分内容阅读
针对难以运用公式来表达强力旋压连杆衬套工艺参数与力学性能之间的复杂关系问题,建立了旋压工艺参数(减薄率、热处理温度、进给比)与力学性能(布氏硬度、伸长率、屈服强度、抗拉强度)之间的径向基函数(RBF)神经网络模型。用实验所得的数据对RBF神经网络进行训练,再用训练好的RBF神经网络对成形件的力学性能进行预测,通过与实测值对比分析,并与用BP神经网络所建模型的预测结果进行比较,发现RBF神经网络模型具有较BP神经网络更优的预测性能。RBF神经网络模型预测能力强、建模时间短、能有效提高连杆衬套工艺的设计效率和降低实际实验的所需成本。
Aiming at the problem that it is difficult to use the formula to express the complicated relationship between the process parameters and the mechanical properties of the spinning rod bushing, the spinning process parameters (thinning rate, heat treatment temperature, feed ratio) and mechanical properties (Brinell hardness , Elongation, yield strength, tensile strength) between the radial basis function (RBF) neural network model. The experimental data were used to train the RBF neural network, and then the trained RBF neural network was used to predict the mechanical properties of the formed parts. The results were compared with the measured values and compared with the prediction results of the BP neural network model It is found that RBF neural network model has better prediction performance than BP neural network. The RBF neural network model has strong prediction ability and short modeling time, which can effectively improve the design efficiency of the connecting rod bushing process and reduce the required cost of the actual experiment.