Quantitative prediction of fracture toughness (<i>K</i><sub>I<i>c</i></sub>) of polymer by fractography using deep neural networks
Quantitative prediction of fracture toughness (<i>K</i><sub>I<i>c</i></sub>) of polymer by fractography using deep neural networks
复制标题
使用深度神经网络通过断口分析定量预测聚合物的断裂韧性 (<i>K</i><sub>I<i>c</i></sub>)
DOI：
10.1080/27660400.2022.2107883
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Demura M.
中科院分区：
文献类型：
--
作者：
Mototake Y.;Ito K.;Demura M.
断裂面提供关于断裂的各种类型的信息。断裂韧性表示抗断裂性，可以使用断裂表面的三维（3D）信息（即其粗糙度）来估计。然而，这是耗时和昂贵的获得的三维信息的断裂表面，因此，它是可取的估计从二维（2D）图像，这可以很容易地获得。近年来，使用深度学习从其2D图像估计3D结构的方法已经迅速发展。在这项研究中，我们提出了一个断裂学框架，该框架使用深度神经网络（DNN）直接从2D断裂表面图像进行估计。通常，使用DNN的图像识别需要大量的图像数据，由于实验成本高，很难获得用于断口分析的图像数据。为了弥补有限的数据量，在这项研究中，我们使用了迁移学习（TL）方法，通过迁移使用其他大数据集训练的机器学习模型，即使是小数据集也可以构建高性能的预测模型。我们发现，使用我们提出的框架获得的回归模型可以预测约1-5 [MPa\sqrtm]的范围，估计误差的标准差约为0.37 [MPa\sqrtm]。目前的研究结果表明，用TL训练的DNN为定量断口分析开辟了一条新的途径，即使用很小的数据集也可以从断裂表面估计断裂过程的参数。
Fracture surfaces provide various types of information about fracture. The fracture toughness, which represents the resistance to fracture, can be estimated using the three-dimensional (3D) information of a fracture surface, i.e. its roughness. However, this is time-consuming and expensive to obtain the 3D information of a fracture surface; thus, it is desirable to estimatefrom a two-dimensional (2D) image, which can be easily obtained. In recent years, methods of estimating a 3D structure from its 2D image using deep learning have been rapidly developed. In this study, we propose a framework for fractography that directly estimatesfrom a 2D fracture surface image using deep neural networks (DNNs). Typically, image recognition using a DNN requires a tremendous amount of image data, which is difficult to acquire for fractography owing to the high experimental cost. To compensate for the limited number of data, in this study, we used the transfer learning (TL) method and constructed high-performance prediction models even with a small dataset by transferring machine learning models trained using other large datasets. We found that the regression model obtained using our proposed framework can predictin the range of approximately 1–5 [MPa\sqrtm] with a standard deviation of the estimation error of approximately0.37 [MPa\sqrtm]. The present results demonstrate that the DNN trained with TL opens a new route for quantitative fractography by which parameters of fracture process can be estimated from a fracture surface even with a small dataset.