Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Typical Model Studies

Typical Model Studies

Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Dual-band angular dispersion and polarization manipulation based on extrinsic chirality in a metasurface.

Optics letters·2026

Same author

Noninvasive Prediction of Decompensation in Compensated Advanced Chronic Liver Disease and a Liver Stiffness From 15 to 25 kPa.

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association·2026

Same author

Angle-Dependent Terahertz Circular Dichroism and Full-Space Polarization Manipulation via Extrinsic Chiral Metasurfaces.

Nanomaterials (Basel, Switzerland)·2026

Same author

Phenotypic discordance in monozygotic twins with a CDH2 variant.

European journal of medical genetics·2026

Same author

The diagnosis and management of portal hypertension in cirrhosis: The Gastroenterological Society of Australia consensus.

Hepatology communications·2026

Same author

Terahertz chiral biochemical metasensor based on analysis of linearly polarized waves.

Optics express·2026

Search research articles

相关实验视频

Updated: Jun 29, 2026

Ultrasonic Welding of Thermoplastic Composite Coupons for Mechanical Characterization of Welded Joints through Single Lap Shear Testing

Ultrasonic Welding of Thermoplastic Composite Coupons for Mechanical Characterization of Welded Joints through Single Lap Shear Testing

Published on: February 11, 2016

使用机器学习增强的计算流体动力学建模预测电子束接透深度.

Yi Yin^1,2, Yingtao Tian¹, Jialuo Ding²

¹Department of Engineering, Lancaster University, Bailrigg, Lancaster LA1 4YW, UK.

Sensors (Basel, Switzerland)

|November 14, 2023

概括

此摘要是机器生成的。

本研究提出了一种新的方法,通过结合计算流体动力学 (CFD) 和人工神经网络 (ANN) 来预测电子束 (EBW) 透深度. 这种高效的方法降低了成本,并改善了接质量控制.

关键词:

人工神经网络的人工神经网络波束的特征波束的特征计算流体动力学建模计算流体动力学建模电子束接使用电子束接.机器学习是机器学习.透深度预测的预测

更多相关视频

An Analog Macroscopic Technique for Studying Molecular Hydrodynamic Processes in Dense Gases and Liquids

An Analog Macroscopic Technique for Studying Molecular Hydrodynamic Processes in Dense Gases and Liquids

Published on: December 4, 2017

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

相关实验视频

Last Updated: Jun 29, 2026

Ultrasonic Welding of Thermoplastic Composite Coupons for Mechanical Characterization of Welded Joints through Single Lap Shear Testing

Ultrasonic Welding of Thermoplastic Composite Coupons for Mechanical Characterization of Welded Joints through Single Lap Shear Testing

Published on: February 11, 2016

An Analog Macroscopic Technique for Studying Molecular Hydrodynamic Processes in Dense Gases and Liquids

An Analog Macroscopic Technique for Studying Molecular Hydrodynamic Processes in Dense Gases and Liquids

Published on: December 4, 2017

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

科学领域:

材料科学与工程材料科学与工程
计算物理计算物理
制造业制造技术制造技术

背景情况:

精确预测电子束 (EBW) 透深度对于质量控制至关重要.
像回归分析和神经网络这样的传统方法可能耗时且昂贵.
现有的预测模型往往缺乏效率,需要进行广泛的初步测试.

研究的目的:

开发一种新,高效,准确的方法来预测EBW透深度.
将计算流体动力学 (CFD) 建模与人工神经网络 (ANN) 集成,以提高预测准确度.
为了减少EBW流程优化所需的时间和财务资源.

主要方法:

计算流体动力学 (CFD) 建模和人工神经网络 (ANN) 的协同组合.
应用CFD来模拟EBW所涉及的物理过程.
使用CFD生成的数据和实验参数进行ANN模型的培训和验证.
开发一个光束特征化方法,以实现更广泛的应用.

主要成果:

综合CFD-ANN方法在预测EBW透深度方面取得了很高的准确性,平均绝对百分比偏差约为8%.
准确的预测在 86 J/mm 到 324 J/mm 的线性电子束功率范围内是一致的.
该方法显著减少了昂贵和耗时的初步测试的需要.

结论:

合并的CFD-ANN模型为预测EBW透深度提供了高效和准确的解决方案.
这种方法可以通过微调关键过程变量来加强对EBW接质量的控制.
该方法可适应不同的电子束机器,在工业环境中提供多功能应用.