发表机构
Vanderbilt University（范德堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对熔融沉积建模零件的结合质量与孔隙率预测问题，提出三类物理信息混合机器学习策略并探索其八种组合，验证了多策略组合在有限实验数据下可构建准确的物理一致性预测模型。
AI 中文摘要
本文研究了多种将物理知识融入实验数据驱动的深度学习模型的物理信息混合机器学习策略，用于预测熔融沉积建模（FFF）零件的结合质量和孔隙率。探索了三类将物理约束和多物理场FFF模拟结果融入深度神经网络（DNN）以确保与物理定律一致的策略：（1）在DNN的损失函数中融入物理约束；（2）将物理模型输出作为DNN模型的额外输入；（3）用物理模型的输入输出对DNN进行预训练，再用实验数据对其进行更新。这些策略有助于确立结合质量与拉伸强度之间符合物理规律的关系，从而使孔隙率预测具有物理意义。本文研究了上述策略的八种不同组合，结果表明，多种策略的组合即便在实验数据有限的情况下，也能生成准确的机器学习模型。
英文摘要
This article investigates several physics-informed and hybrid machine learning strategies that incorporate physics knowledge in experimental data-driven deep-learning models for predicting the bond quality and porosity of fused filament fabrication (FFF) parts. Three types of strategies are explored to incorporate physics constraints and multi-physics FFF simulation results into a deep neural network (DNN), thus ensuring consistency with physical laws: (1) incorporate physics constraints within the loss function of the DNN, (2) use physics model outputs as additional inputs to the DNN model, and (3) pre-train a DNN model with physics model input-output and then update it with experimental data. These strategies help to enforce a physically consistent relationship between bond quality and tensile strength, thus making porosity predictions physically meaningful. Eight different combinations of the above strategies are investigated. The results show how the combination of multiple strategies produces accurate machine learning models even with limited experimental data.
Comments11 pages, JOM (Journal of The Minerals, Metals & Materials Society)
Journal refJOM 72, 4695--4705 (2020)
DOI：10.1007/s11837-020-04438-4
