用于电弧定向能量沉积过程中热历史可扩展仿真的物理信息机器学习代理模型
Physics-informed machine learning surrogate for scalable simulation of thermal histories during wire-arc directed energy deposition
AI总结:
本研究提出将物理信息神经网络(PINNs)作为电弧定向能量沉积热历史仿真的代理模型,通过高效配置点采样解决了传统FEM计算成本高且数据驱动方法数据不足的问题,计算量减少达98.6%且保持高精度。
摘要:
电弧定向能量沉积(DED)已成为一种用于大型结构工程应用的有前景的增材制造(AM)技术。然而,该过程固有的复杂热动力学对确保所制造的厚壁和厚板的结构完整性和机械性能提出了挑战。虽然传统上采用有限元方法(FEM)仿真来预测沉积过程中的热历史,但对于实际的大型应用而言,其计算需求仍然高得令人望而却步。鉴于热管理和确定最佳打印策略需要进行多次重复仿真,FEM仿真很快变得完全不可行。相反,在使用训练好的神经网络作为快速预测的代理模型方面已经取得了进展。然而,传统的数据驱动方法在神经网络的训练和验证过程中需要大量相关且可验证的外部数据。对于大型电弧DED,这些数据源均无法以足以支持准确代理模型的数量 readily available。物理信息神经网络(PINNs)的引入通过将现有的物理现象知识与先进的机器学习方法相结合,开辟了一种替代的仿真策略。尽管具有理论优势,但PINNs在结构工程的大型电弧DED背景下的应用仍然有限。本研究调查了PINNs的可扩展性,重点关注高效的配置点采样,这是控制训练时间和模型性能的关键因素。结果表明,PINNs可以将计算时间和工作量减少高达98.6%,同时保持所需的精度并提供“超分辨率”。讨论了在金属AM中增强PINN性能的未来方向。
英文摘要:
Wire-arc directed energy deposition (DED) has emerged as a promising additive manufacturing (AM) technology for large-scale structural engineering applications. However, the complex thermal dynamics inherent to the process present challenges in ensuring structural integrity and mechanical properties of fabricated thick walls and plates. While finite element method (FEM) simulations have been conventionally employed to predict thermal history during deposition, their computational demand remains prohibitively high for actual large-scale applications. Given the necessity of multiple repetitive simulations for heat management and the determination of an optimal printing strategy, FEM simulation quickly becomes entirely infeasible. Instead, advancements have been made in using trained neural networks as surrogate models for rapid prediction. However, traditional data-driven approaches necessitate large amounts of relevant and verifiable external data, during the training and validation of the neural network. Regarding large-scale wire-arc DED, none of these data sources are readily available in quantities sufficient for an accurate surrogate. The introduction of physics-informed neural networks (PINNs) has opened up an alternative simulation strategy by leveraging the existing physical knowledge of the phenomena with advanced machine learning methods. Despite their theoretical advantages, PINNs have seen limited application in the context of large-scale wire-arc DED for structural engineering. This study investigates the scalability of PINNs, focusing on efficient collocation points sampling, a critical factor controlling both the training time and model performance. Results show PINNs can reduce computational time and effort by up to 98.6%, while maintaining the desired accuracy and offering "super-resolution". Future directions for enhancing PINN performance in metal AM are discussed.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。