首页|Study Findings from Florida International University Update Knowledgein Machine Learning (Precision Calibration in Wire-Arc-Directed Energy Deposition Simulati ons Using a Machine-Learning-Based Multi-Fidelity Model)
Study Findings from Florida International University Update Knowledgein Machine Learning (Precision Calibration in Wire-Arc-Directed Energy Deposition Simulati ons Using a Machine-Learning-Based Multi-Fidelity Model)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators discuss new findings in artificial intelligence. According to news reportingoriginating from Miami, Flo rida, by NewsRx correspondents, research stated, “Thermal simulation isessentia l in wire-arc-directed energy deposition (W-DED) to accurately estimate temperat ure distributions,impacting residual stress and distortion in components.”Funders for this research include Devcom-army Research Laboratory.Our news journalists obtained a quote from the research from Florida Internation al University: “Propercalibration of simulation models minimizes inaccuracies c aused by varying material properties, machinesettings, and environmental condit ions. The lack of standardized calibration methods further complicatesthermal p redictions. This paper introduces a novel calibration method integrating both ma chine learning,as the high-fidelity (HF) model, and response surface modeling, as the low-fidelity (LF) model, withina multi-fidelity (MF) framework. The appr oach utilizes Bayesian optimization to effectively explore thesearch space for optimal solutions. A two-tiered model employs the LF model to identify feasible regions,followed by the HF model to refine calibration parameters, such as ther mal efficiency (e), convectioncoefficient (h), and emissivity (e), which are di fficult to determine experimentally. A three-factor Box-Behnken design (BBD) is applied to explore the design space, requiring only thirteen parameter configurations, conserving resources and enabling robust model training.”
Florida International UniversityMiamiFloridaUnited StatesNorth and Central AmericaCyborgsEmerging Technologi esMachine Learning
NETL
NSTL
