Comparison of machine learning methods for automatic classification of porosities in powder-based additive manufactured metal parts
Comparison of machine learning methods for automatic classification of porosities in powder-based additive manufactured metal parts
复制标题
DOI：
10.1007/s00170-022-09141-z
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Nicholas Satterlee;E. Torresani;E. Olevsky;John S. Kang
中科院分区：
文献类型：
--
作者：
Nicholas Satterlee;E. Torresani;E. Olevsky;John S. Kang
增材制造的一个突出问题是由工艺引起的缺陷（例如孔隙率）引起的部件质量的可变性。基于图像的孔隙度检测代表了可以以低成本容易地实施到现有系统中的解决方案。然而，当前的工业孔隙度检测软件利用基于阈值的方法，其需要用户校准和理想的照明条件，并且因此不能完全自动化。本文研究了机器学习方法的应用，并比较了它们对3D打印金属零件横截面图像中孔隙率进行分类的能力。人工定义和自动从图像中提取51个特征，并使用特征约简方法选择其中最相关的特征。通常用于分类问题的六种机器学习算法使用这些特征进行训练，并用于孔隙度分类。决策树是六种机器学习算法之一，在0.5秒的处理时间内对691张图像中的孔隙进行分类，准确率为85%。然而，手动特征可能无法充分表征孔隙度，因为它们取决于用户的经验和判断。或者，不需要用户定义特征的深度卷积神经网络（DCNN）用于分类问题。比较结果表明，DCNN在1.8 s的处理时间内对来自相同691张图像的孔隙度进行分类，获得了95%的最高准确度。
An outstanding problem of additive manufacturing is the variability in part quality caused by process-induced defects such as porosity. Image-based porosity detection represents a solution that can be easily implemented into existing systems at a low cost. However, current industry porosity detection software utilizes threshold-based methods which require user calibration and ideal lighting conditions, and thus cannot be fully automated. This paper investigates the application of machine learning methods and compares their ability to classify porosities from cross-section images of 3D printed metal parts. Fifty-one features are manually defined and automatically extracted from the images and the most relevant features among them are selected using feature reduction methods. Six machine learning algorithms that are commonly used for classification problems are trained with those features and used for the porosity classification. The decision tree, one of the six machine learning algorithms, yields 85% accuracy with a processing time of 0.5 s to classify porosities from 691 images. However, manual features may not adequately characterize porosity because they are dependent on user’s experience and judgment. Alternatively, deep convolutional neural network (DCNN) that does not require user-defined features is used for the classification problem. The comparison results showed that a DCNN yields the highest accuracy of 95% with a processing time of 1.8 s to classify porosities from the same 691 images.