PDF(Pubmed)
Abstract：
Regulating the microstructure of powder metallurgy (P/M) nickel-based superalloys to achieve superior mechanical properties through heat treatment is a prevalent method in turbine disk design. However, in the case of dual-performance turbine disks, the complexity and non-uniformity of the heat treatment process present substantial challenges. The prediction of yield strength is typically derived from the analysis of microstructures under various heat treatment regimes. This method is time-consuming, expensive, and the accuracy often depends on the precision of microstructural characterization. This study successfully employed a coupled method of Artificial Neural Network (ANN) and finite element analysis (FEA) to reveal the relationship between the heat treatment process and yield strength. The coupled method accurately predicted the location specified and temperature-dependent yield strength based on the heat treatment parameters such as holding temperatures and cooling rates. The root mean square error (RMSE) and mean absolute percentage deviation (MAPD) for the training set are 50.37 and 3.77, respectively, while, for the testing set, they are 50.13 and 3.71, respectively. Furthermore, an integrated model of FEA and ANN is established using a Abaqus user subroutine. The integrated model can predict the yield strength based on temperature calculation results and automatically update material properties of the FEA model during the loading process simulation. This allows for an accurate calculation of the stress-strain state of the turbine disk during actual working conditions, aiding in locating areas of stress concentration, plastic deformation, and other critical regions, and provides a novel reliable reference for the rapid design of the turbine disk.
摘要：
通过热处理调节粉末冶金（P/M）镍基高温合金的微观结构以获得优异的机械性能是涡轮盘设计中的一种普遍方法。然而,在双性能涡轮盘的情况下，热处理过程的复杂性和不均匀性提出了重大挑战。屈服强度的预测通常来自各种热处理方式下的微观结构分析。这种方法很耗时,贵,而精度往往取决于微结构表征的精度。本研究成功地采用了人工神经网络（ANN）和有限元分析（FEA）的耦合方法来揭示热处理工艺与屈服强度之间的关系。耦合方法基于热处理参数(诸如保持温度和冷却速率)准确地预测指定的位置和温度相关的屈服强度。训练集的均方根误差（RMSE）和平均绝对百分比偏差（MAPD）分别为50.37和3.77，while,对于测试集，分别为50.13和3.71。此外，使用Abaqus用户子程序建立了FEA和ANN的集成模型。集成模型可以根据温度计算结果预测屈服强度，并在加载过程模拟中自动更新FEA模型的材料性能。这允许在实际工作条件下准确计算涡轮盘的应力-应变状态，帮助定位应力集中区域，塑性变形,和其他关键区域，为涡轮盘的快速设计提供了新颖可靠的参考。
