A Physics-Informed Convolutional Neural Network with Custom Loss Functions for Porosity Prediction in Laser Metal Deposition.
A Physics-Informed Convolutional Neural Network with Custom Loss Functions for Porosity Prediction in Laser Metal Deposition.
复制标题
DOI：
10.3390/s22020494
复制
发表时间：
2022-01-10
期刊：
影响因子：
--
通讯作者：
Guo WG
中科院分区：
文献类型：
--
作者：
McGowan E;Gawade V;Guo WG
基于物理的机器学习正在通过大量的方法和各种应用出现。本文发现了基于物理的自定义损失函数作为增材制造（AM）的可实现解决方案。具体而言，激光金属沉积（LMD）是一种AM工艺，其中激光束熔化沉积的粉末，并且溶解的颗粒熔合以产生金属部件。在这种印刷结构中形成的孔隙或小空腔通常被认为是金属AM中最具破坏性的缺陷之一。传统上，计算机断层扫描测量孔隙度。虽然这对于理解孔隙形成的性质及其特征是有用的，但纯物理驱动的模型缺乏实时预测能力。与此同时，一种纯粹的深度学习方法来预测孔隙度，留下了宝贵的物理知识。本文创建了一个使用经验和模拟LMD数据的混合模型，以显示各种物理信息损失函数如何影响孔隙度预测基线深度学习模型的准确性，精度和召回率。特别是，某些版本的物理模型可以提高基线深度学习模型的精度（尽管以牺牲整体精度为代价）。
Physics-informed machine learning is emerging through vast methodologies and in various applications. This paper discovers physics-based custom loss functions as an implementable solution to additive manufacturing (AM). Specifically, laser metal deposition (LMD) is an AM process where a laser beam melts deposited powder, and the dissolved particles fuse to produce metal components. Porosity, or small cavities that form in this printed structure, is generally considered one of the most destructive defects in metal AM. Traditionally, computer tomography scans measure porosity. While this is useful for understanding the nature of pore formation and its characteristics, purely physics-driven models lack real-time prediction ability. Meanwhile, a purely deep learning approach to porosity prediction leaves valuable physics knowledge behind. In this paper, a hybrid model that uses both empirical and simulated LMD data is created to show how various physics-informed loss functions impact the accuracy, precision, and recall of a baseline deep learning model for porosity prediction. In particular, some versions of the physics-informed model can improve the precision of the baseline deep learning-only model (albeit at the expense of overall accuracy).
登录
查看更多内容
DOI：
10.3390/s21072561
发表时间：
2021-04-06
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Oskolkov A;Bezukladnikov I;Trushnikov D
通讯作者：
Trushnikov D
影响因子：
11
作者：
Hirsch, Matthias;Patel, Rikesh;Clare, Adam T.
通讯作者：
Clare, Adam T.
影响因子：
2.6
作者：
Khanzadeh, Mojtaba;Chowdhury, Sudipta;Bian, Linkan
通讯作者：
Bian, Linkan
影响因子：
8.4
作者：
Mahamood, R. M.;Akinlabi, E. T.
通讯作者：
Akinlabi, E. T.
DOI：
10.1016/b978-0-08-100433-3.00013-0
发表时间：
2017-01-01
期刊：
LASER ADDITIVE MANUFACTURING: MATERIALS, DESIGN, TECHNOLOGIES, AND APPLICATIONS
影响因子：
--
作者：
Liu, R.;Wang, Z.;Newkirk, J.
通讯作者：
Newkirk, J.