当前位置: X-MOL 学术Comput. Mech. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine learning for metal additive manufacturing: predicting temperature and melt pool fluid dynamics using physics-informed neural networks
Computational Mechanics ( IF 4.1 ) Pub Date : 2021-01-06 , DOI: 10.1007/s00466-020-01952-9
Qiming Zhu , Zeliang Liu , Jinhui Yan

The recent explosion of machine learning (ML) and artificial intelligence (AI) shows great potential in the breakthrough of metal additive manufacturing (AM) process modeling, which is an indispensable step to derive the process-structure-property relationship. However, the success of conventional machine learning tools in data science is primarily attributed to the unprecedented large amount of labeled data-sets (big data), which can be either obtained by experiments or first-principle simulations. Unfortunately, these labeled data-sets are expensive to obtain in AM due to the high expense of the AM experiments and prohibitive computational cost of high-fidelity simulations, hindering the direct applications of big-data based ML tools to metal AM problems. To fully exploit the power of machine learning for metal AM while alleviating the dependence on “big data”, we put forth a physics-informed neural network (PINN) framework that fuses both data and first physical principles, including conservation laws of momentum, mass, and energy, into the neural network to inform the learning processes. To the best knowledge of the authors, this is the first application of physics-informed deep learning to three dimensional AM processes modeling. Besides, we propose a hard-type approach for Dirichlet boundary conditions (BCs) based on a Heaviside function, which can not only exactly enforce the BCs but also accelerate the learning process. The PINN framework is applied to two representative metal manufacturing problems, including the 2018 NIST AM-Benchmark test series. We carefully assess the performance of the PINN model by comparing the predictions with available experimental data and high-fidelity simulation results, using finite element based variational multi-scale formulation method. The investigations show that the PINN, owed to the additional physical knowledge, can accurately predict the temperature and melt pool dynamics during metal AM processes with only a moderate amount of labeled data-sets. The foray of PINN to metal AM shows the great potential of physics-informed deep learning for broader applications to advanced manufacturing. All the data-sets and the PINN code will be made open-sourced in https://yan.cee.illinois.edu/ once the paper is published.

中文翻译:

金属增材制造的机器学习:使用物理神经网络预测温度和熔池流体动力学

最近机器学习 (ML) 和人工智能 (AI) 的爆炸式增长在金属增材制造 (AM) 工艺建模的突破中显示出巨大潜力,这是推导出工艺-结构-性能关系不可或缺的一步。然而,传统机器学习工具在数据科学中的成功主要归功于前所未有的大量标记数据集(大数据),这些数据集可以通过实验或第一性原理模拟获得。不幸的是,由于 AM 实验的高昂费用和高保真模拟的计算成本过高,在 AM 中获得这些标记数据集的成本很高,这阻碍了基于大数据的 ML 工具直接应用于金属 AM 问题。为了充分利用机器学习对金属增材制造的力量,同时减轻对“大数据”的依赖,我们提出了一个物理信息神经网络 (PINN) 框架,该框架融合了数据和第一物理原理,包括动量守恒定律、质量和能量,进入神经网络以告知学习过程。据作者所知,这是物理信息深度学习首次应用于三维 AM 过程建模。此外,我们提出了一种基于 Heaviside 函数的狄利克雷边界条件 (BC) 的硬类型方法,它不仅可以准确地强制执行 BC,还可以加速学习过程。PINN 框架应用于两个具有代表性的金属制造问题,包括 2018 NIST AM-Benchmark 测试系列。我们使用基于有限元的变分多尺度公式化方法,通过将预测与可用的实验数据和高保真模拟结果进行比较,仔细评估 PINN 模型的性能。研究表明,PINN 由于额外的物理知识,可以准确地预测金属 AM 工艺过程中的温度和熔池动态,仅需要适量的标记数据集。PINN 对金属 AM 的尝试显示了基于物理的深度学习在更广泛地应用于先进制造的巨大潜力。论文发表后,所有数据集和 PINN 代码都将在 https://yan.cee.illinois.edu/ 中开源。使用基于有限元的变分多尺度公式化方法。研究表明,PINN 由于额外的物理知识,可以准确地预测金属 AM 工艺过程中的温度和熔池动态,仅需要适量的标记数据集。PINN 对金属 AM 的尝试显示了基于物理的深度学习在更广泛地应用于先进制造的巨大潜力。论文发表后,所有数据集和 PINN 代码都将在 https://yan.cee.illinois.edu/ 中开源。使用基于有限元的变分多尺度公式化方法。研究表明,PINN 由于额外的物理知识,可以准确地预测金属 AM 工艺过程中的温度和熔池动态,仅需要适量的标记数据集。PINN 对金属 AM 的尝试显示了基于物理的深度学习在更广泛地应用于先进制造的巨大潜力。论文发表后,所有数据集和 PINN 代码都将在 https://yan.cee.illinois.edu/ 中开源。PINN 对金属 AM 的尝试显示了基于物理的深度学习在更广泛地应用于先进制造的巨大潜力。论文发表后,所有数据集和 PINN 代码都将在 https://yan.cee.illinois.edu/ 中开源。PINN 对金属 AM 的尝试显示了基于物理的深度学习在更广泛地应用于先进制造的巨大潜力。论文发表后,所有数据集和 PINN 代码都将在 https://yan.cee.illinois.edu/ 中开源。
更新日期:2021-01-06
down
wechat
bug