PulseAugur
实时 23:22:33
English(EN) Physics-Informed Machine Learning Regulated by Finite Element Analysis for Simulation Acceleration of Melt Pool Dynamics in Laser Powder Bed Fusion

FEA-PINN 以可比的精度加速熔池模拟

研究人员开发了一个名为 FEA-Regulated Physics-Informed Neural Network (FEA-PINN) 的新框架,用于加速激光粉末床熔融 (LPBF) 中熔池动力学的模拟。这种新方法在推理阶段整合了校正性有限元分析 (FEA) 模拟,以保持物理一致性并减少误差漂移,尤其是在捕捉陡峭梯度方面。FEA-PINN 框架能有效处理动态相变、温度依赖性材料特性和各种对流效应,实现了与传统 FEA 方法相当的精度,但计算成本显著降低。 AI

影响 加速复杂材料过程的模拟,可能降低增材制造的计算成本。

排序理由 该集群包含一篇详细介绍用于加速模拟的新计算方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · R. Sharma, Y. B. Guo ·

    Physics-Informed Machine Learning Regulated by Finite Element Analysis for Simulation Acceleration of Melt Pool Dynamics in Laser Powder Bed Fusion

    arXiv:2506.20537v3 Announce Type: replace Abstract: Efficient simulation of Laser Powder Bed Fusion (LPBF) is crucial for process prediction due to the lasting issue of high computational cost associated with traditional numerical methods such as finite element analysis (FEA). Wh…