摘要
由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-人工智能的新数据在一份新的报告中呈现。根据来自新泽西州立大学罗格斯大学的新闻，NewsRx记者的研究表明，"金属添加剂制造中的熔池动力学(AM)对印刷材料的工艺稳定性、微观结构形成和最终性能至关重要。"这项研究的资助者包括土木、机械和制造业创新司。我们的新闻记者从新泽西州州立大学罗格斯大学的研究中获得了一句话：“基于物理的模拟，包括循环流体动力学(CFD)，是预测熔体池动态的主要方法。然而，基于物理的模拟方法存在计算量大的问题，本文提出了一种基于物理信息的机器学习方法，该方法将传统的神经网络与控制物理规律相结合，不需要任何速度和压力的训练数据来预测熔池的温度、速度和压力，避免了非线性Navier-Stokes方程的数值求解。这大大降低了计算成本（如果包括VE本地数据生成的成本）。Go Verning方程难以确定的参数值也可以通过数据驱动的发现推断出来。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on artificial intelligence are presented in a new report. According to news originating from Rutgers Univer sity - The State University of New Jersey by NewsRx correspondents, research sta ted, “Melt pool dynamics in metal additive manufacturing (AM) is critical to pro cess stability, microstructure formation, and final properties of the printed ma terials.” Funders for this research include Division of Civil, Mechanical And Manufacturin g Innovation. Our news journalists obtained a quote from the research from Rutgers University - The State University of New Jersey: “Physics-based simulation, including compu tational fluid dynamics (CFD), is the dominant approach to predict melt pool dyn amics. However, the physics-based simulation approaches suffer from the inherent issue of very high computational cost. This paper provides a physics-informed m achine learning method by integrating the conventional neural networks with the governing physical laws to predict the melt pool dynamics, such as temperature, velocity, and pressure, without using any training data on velocity and pressure . This approach avoids solving the nonlinear Navier-Stokes equation numerically, which significantly reduces the computational cost (if including the cost of ve locity data generation). The difficult-to-determine parameters’ values of the go verning equations can also be inferred through data-driven discovery.”
NETL
NSTL