论文部分内容阅读
利用人工神经网络(ANN)方法建立了超级马氏体不锈钢(SMSS)淬火工艺参数与力学性能的预测模型。模型输入单元为淬火温度、保温时间和冷却方式,输出单元为抗拉强度、屈服强度和伸长率;网络为3-9-3结构,动量因子为0.2,采用提前终止法与Levenberg-Marquardt算法相结合训练网络,以实验结果验证网络的可靠性。预测结果表明,抗拉强度、屈服强度和伸长率相对误差绝对值的最大值分别为2.2050%、1.4393%和8.4211%。该模型可为SMSS热处理工艺制定提供参考依据。
The artificial neural network (ANN) method was used to establish the prediction model of the quenching parameters and mechanical properties of the super martensitic stainless steel (SMSS). The input unit of the model is quenching temperature, holding time and cooling mode, the output unit is tensile strength, yield strength and elongation; the network is 3-9-3 structure, the momentum factor is 0.2, using early termination method and Levenberg-Marquardt algorithm Combined with training network, the experimental results verify the reliability of the network. The prediction results show that the absolute values of the relative errors of tensile strength, yield strength and elongation are respectively 2.2050%, 1.4393% and 8.4211%. The model can provide a reference for the development of SMSS heat treatment process.