Data-driven analysis of process, structure, and properties of additively manufactured Inconel 718 thin walls
Data-driven analysis of process, structure, and properties of additively manufactured Inconel 718 thin walls
复制标题
DOI：
10.1038/s41524-022-00808-5
复制
发表时间：
2022-06
影响因子：
9.7
通讯作者：
Lichao Fang;Lin Cheng;J. Glerum;Jennifer L. Bennett;Jian Cao;G. Wagner
中科院分区：
文献类型：
--
作者：
Lichao Fang;Lin Cheng;J. Glerum;Jennifer L. Bennett;Jian Cao;G. Wagner
在金属零件的加法制造中，能够准确、详细地预测极端多变的温度场，并将其与组织和性能定量地联系起来，是预测零件性能和优化工艺设计的关键步骤。本文采用定向能沉积(DED)过程的有限元模拟方法，对Inconel718多层墙体多层成型过程中的时间和空间温度场进行了数值模拟。热模型结果与DED建立过程中现场拍摄的动态红外图像具有很好的一致性。研究了预测冷却速度、显微组织特征和力学性能之间的关系，发现单独的冷却速度不足以给出定量的性能预测。由于机器学习提供了一种从序列数据中识别重要特征的有效方法，因此我们应用一维卷积神经网络数据驱动框架来自动从模拟的温度历史中提取主要的预测特征。使用模拟的热历史数据可以很好地预测材料的性能，特别是极限抗拉强度。为了进一步解释卷积神经网络预测，我们将在每一卷积层上产生的提取的特征可视化，并比较卷积神经网络在高极限抗拉强度和低极限抗拉强度情况下的热历史检测特征。一个关键的结果是确定了高温和中温条件下的热历史都会影响材料的性能。
In additive manufacturing of metal parts, the ability to accurately predict the extremely variable temperature field in detail, and relate it quantitatively to structure and properties, is a key step in predicting part performance and optimizing process design. In this work, a finite element simulation of the directed energy deposition (DED) process is used to predict the space- and time-dependent temperature field during the multi-layer build process for Inconel 718 walls. The thermal model results show good agreement with dynamic infrared images captured in situ during the DED builds. The relationship between predicted cooling rate, microstructural features, and mechanical properties is examined, and cooling rate alone is found to be insufficient in giving quantitative property predictions. Because machine learning offers an efficient way to identify important features from series data, we apply a 1D convolutional neural network data-driven framework to automatically extract the dominant predictive features from simulated temperature history. Very good predictions of material properties, especially ultimate tensile strength, are obtained using simulated thermal history data. To further interpret the convolutional neural network predictions, we visualize the extracted features produced on each convolutional layer and compare the convolutional neural network detected features of thermal histories for high and low ultimate tensile strength cases. A key result is the determination that thermal histories in both high and moderate temperature regimes affect material properties.