Soleymani Mehdi, Khoshnevisan Mohammad, Davoodi Behnam
School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, Iran.
Physics Department, College of Science, Northeastern University, Boston, MA 02115 USA.
Int J Adv Manuf Technol. 2022;123(9-10):3261-3274. doi: 10.1007/s00170-022-10355-4. Epub 2022 Nov 10.
This study introduces a non-destructive method by applying convolutional neural networks (CNN) to predict the micro-hardness of the thread-rolled steel. Material microstructure images were collected for our research, and micro-hardness tests were conducted to label the extracted microstructure images. In recent years, researchers have used machine learning (ML) and deep learning (DL) models to predict material properties for forming, machining, additive manufacturing, and other processes. However, they encountered industrial limitations primarily because of the absence of historical information on new and unknown materials, which are necessary to predict material properties by DL models. These problems can be solved by employing CNN models. In our work, we used a CNN model with two convolutional layers and visual geometry group (VGG19) as transfer learning (TL). We predicted four classes of micro-hardness of the St37 rolled threads. The prediction results of the micro-hardness test images by our proposed CNN model and pre-trained VGG19 model are comparable. Our proposed model has produced the same precision and recall scores as VGG19 for class B and class C hardness. VGG19 performed slightly better than our model for precision in class A and recall in class D. We observed that the training time of our proposed model using the CPU (central processing unit) was approximately nine times faster than the VGG19 model. Our proposed CNN and VGG19 have direct applications in advanced manufacturing (AM). They can automatically predict the micro-hardness in the thread rolling of St37. Our proposed model requires less memory and computational power and can be deployed more efficiently than the VGG19 model.
The online version contains supplementary material available at 10.1007/s00170-022-10355-4.
本研究介绍了一种通过应用卷积神经网络（CNN）来预测滚压螺纹钢显微硬度的无损方法。我们收集了材料微观结构图像用于研究，并进行了显微硬度测试以标记提取的微观结构图像。近年来，研究人员使用机器学习（ML）和深度学习（DL）模型来预测成型、加工、增材制造及其他工艺中的材料性能。然而，他们遇到了工业局限性，主要原因是缺乏新的和未知材料的历史信息，而这些信息是DL模型预测材料性能所必需的。这些问题可以通过采用CNN模型来解决。在我们的工作中，我们使用了一个具有两个卷积层的CNN模型，并将视觉几何组（VGG19）用作迁移学习（TL）。我们预测了St37滚压螺纹的四类显微硬度。我们提出的CNN模型和预训练的VGG19模型对显微硬度测试图像的预测结果具有可比性。对于B类和C类硬度，我们提出的模型产生了与VGG19相同的精度和召回率分数。在A类精度和D类召回率方面，VGG19的表现略优于我们的模型。我们观察到，使用中央处理器（CPU）时，我们提出的模型的训练时间比VGG19模型快约九倍。我们提出的CNN和VGG19在先进制造（AM）中有直接应用。它们可以自动预测St37滚压螺纹中的显微硬度。我们提出的模型所需的内存和计算能力更少，并且比VGG19模型更能高效部署。
在线版本包含可在10.1007/s00170-022-10355-4获取的补充材料。
