Convolutional neural networks for expediting the determination of minimum volume requirements for studies of microstructurally small cracks, part II: Model interpretation
Convolutional neural networks for expediting the determination of minimum volume requirements for studies of microstructurally small cracks, part II: Model interpretation
复制标题
DOI：
10.1016/j.commatsci.2023.112261
复制
发表时间：
2023-06-03
影响因子：
3.3
通讯作者：
Spear，Ashley D.
中科院分区：
文献类型：
--
作者：
DeMille，Karen J.;Spear，Ashley D.
微结构小裂纹（MSC）研究中的一个重要问题是：在涉及MSC的研究中应包括的最小微结构体积是多少？为了回答这个问题，代表性的体积元素的微观结构小裂纹（RVEMSC），或最小体积的微结构所需的MSC周围，以实现收敛的裂纹前参数相对于体积大小，先前确定使用有限元（FE）模拟。通过FE模拟确定RVEMSC的大量计算费用促使卷积神经网络（CNN）的实现，以加快RVEMSC的确定（第一部分）。除了加快RVEMSC的确定，经过训练的CNN还提供了通过各种解释方法获得RVEMSC预测的机会，我们在当前的工作中对此进行了研究。首先，对CNN预测的检查揭示了CNN学习的趋势。第二，输入采样网格研究提供了对MSC周围微观结构体积的见解，这对RVEMSC的预测影响最大。第三，输入特征灵敏度分析比较微观结构和几何特征对RVEMSC预测的影响。第四，显着图的视觉检查揭示了在预测RVEMSC时对CNN最重要的局部微观结构。CNN解释结果表明，微观结构特征比几何特征对CNN预测更为关键。尽管在解释显着性图方面存在固有的局限性，但结果表明CNN可以学习识别各个裂纹前沿点的各种微观结构排列。总体而言，这项研究强调了在确定RVEMSC时考虑各种微观结构实例的重要性，因为RVEMSC应该是一个保守的最小体积要求，适用于广泛的微观结构实例。
A significant question in the study of microstructurally small cracks (MSCs) is:What is the minimum microstructural volume that should be included in studies involving MSCs?To answer this, representative volume elements for microstructurally small cracks (RVEMSC), or the minimum volume of microstructure required around an MSC to achieve convergence of crack-front parameters with respect to volume size, were previously determined using finite element (FE) simulations. The large computational expense of determining RVEMSCvia FE simulations motivated the implementation of convolutional neural networks (CNNs) to expedite the determination of RVEMSC(Part I). In addition to expediting the determination of RVEMSC, trained CNNs provide the opportunity to gain insights about RVEMSCpredictions through various interpretation methods, which we investigate in the current work. First, an inspection of CNN predictions reveals trends learned by the CNN. Second, an input sampling grid study offers insights into the volume of microstructure around an MSC that most influences predictions of RVEMSC. Third, an input feature sensitivity analysis compares the influence of microstructural and geometrical features on RVEMSCpredictions. Fourth, visual inspections of saliency maps reveal the local microstructure that is most important to the CNN when predicting RVEMSC. The CNN interpretation results show that microstructural features are more critical than geometrical features to the CNN predictions. Despite inherent limitations in interpreting saliency maps, the results demonstrate that the CNN can learn to identify various microstructural arrangements at individual crack-front points. Overall, this study highlights the importance of considering a variety of microstructural instantiations when determining RVEMSC, as RVEMSCshould be a conservative minimum volume requirement that applies across a wide range of microstructural instantiations.