论文部分内容阅读
材料工艺与性能的关系具有复杂、非线性交互等特点。本文根据TC11钛合金力学性能与其影响因素之间的映射关系,以大量的试验数据为基础,建立了BP神经网络模型。模型的输入包括锻造温度、锻后冷却方式等热加工工艺参数;输出为常用的力学性能指标,即抗拉强度、屈服强度、延伸率和断面收缩率。运用该模型对TC11钛合金力学性能进行了预测,并通过试验数据对模型的预测精度进行了可靠性验证。同时,运用已建立的神经网络模型对TC11钛合金工艺参数与力学性能的关系进行了分析。结果表明,所建立的力学性能预测模型具有良好的外推能力,并且可以很好地反映出该合金的工艺-性能之间的复杂关系。
The relationship between material technology and performance has the characteristics of complex and nonlinear interaction. In this paper, based on the mapping relationship between the mechanical properties of TC11 titanium alloy and its influencing factors, a BP neural network model is established based on a large amount of experimental data. The input of the model includes forging temperature, cooling method after forging and other thermal processing parameters; the output is commonly used mechanical properties, namely, tensile strength, yield strength, elongation and reduction of area. The model was used to predict the mechanical properties of TC11 titanium alloy. The reliability of the model was verified by the experimental data. At the same time, the relationship between process parameters and mechanical properties of TC11 titanium alloy has been analyzed by using the established neural network model. The results show that the established mechanical properties prediction model has a good extrapolation ability, and can well reflect the complex relationship between the process - performance of the alloy.