论文部分内容阅读
以静置温度、静置时间、熔化时和浇注时的机械振动辅助搅拌的振动频率为输入层参数,以抗拉强度为输出层参数,构建4×16×8×1四层结构的高强镁合金铸造工艺优化神经网络模型,并对神经网络模型进行了预测验证。此外对优化铸造工艺制备的高强镁合金Mg-10Gd-2.3Y-1.2Zn-0.3Zr-0.2Co进行了显微组织、物相组成和力学性能测试与分析。结果表明,该神经网络模型的平均相对预测误差为1.9%,具有较高的预测能力和预测精度;用优化铸造工艺制备的该高强镁合金抗拉强度达548 MPa、屈服强度达412 MPa、伸长率达14.7%。
Taking the static temperature, standing time, the vibration frequency of auxiliary vibration during melting and pouring as the input layer parameters and the tensile strength as the output layer parameters, a 4 × 16 × 8 × 1 four-layer high-strength magnesium Alloy casting process optimization neural network model, and the neural network model was verified. In addition, the microstructure, phase composition and mechanical properties of Mg-10Gd-2.3Y-1.2Zn-0.3Zr-0.2Co prepared by optimized casting process were tested and analyzed. The results show that the average relative prediction error of the neural network model is 1.9%, which has high predictive ability and prediction accuracy. The tensile strength of the high strength magnesium alloy prepared by optimized casting process reaches 548 MPa, yield strength reaches 412 MPa, The growth rate of 14.7%.