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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

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

Shape-Adaptive Robotics: Programmable Morphing through SMA and SMP Integration.

Soft robotics·2026

Same author

Lateral Duodenal Diverticulitis Mimicking a Right Retroperitoneal Collection: A Case Report.

Cureus·2026

Same author

Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural Network.

Sensors (Basel, Switzerland)·2025

Same author

Fault Diagnosis Method for Shearer Arm Gear Based on Improved S-Transform and Depthwise Separable Convolution.

Sensors (Basel, Switzerland)·2025

Same author

Hybrid mechanical metamaterials: Advances of multi-functional mechanical metamaterials with simultaneous static and dynamic properties.

Heliyon·2025

Same author

Passive highly dispersive matching network enabling broadband electromagnetic absorption.

Nature communications·2025

Search research articles

相关实验视频

Updated: Jun 8, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

通过转移学习进行基于AI的自适应替代模型,用于DEM模拟多组件分离的模拟.

Ahmed Hadi¹, Morteza Moradi², Yusong Pang³

¹Department of Maritime and Transport Technology, Faculty of Mechanical Engineering, Delft University of Technology, Delft, 2628CD, The Netherlands. A.H.Hadi-1@tudelft.nl.

Scientific reports

|November 6, 2024

概括

机器学习替代模型 (SMs) 加快颗粒材料离散元件方法 (DEM) 校准. 一种新的转移学习方法显著减少了对新情景的数据需求,提高了使用最小样本的模型准确性.

关键词:

在 DEM 校准中使用 DEM 校准离散元件方法的离散元素方法.颗粒状材料是一种颗粒状材料.机器学习是机器学习.分离隔离的隔离转移学习转移学习

更多相关视频

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: Jun 8, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

科学领域:

计算物理和工程计算物理和工程
材料科学和颗粒力学颗粒力学
机器学习在科学建模中的应用.

背景情况:

颗粒状材料的分离是一个重要的工业挑战.
离散元件方法 (DEM) 模拟提供了洞察力,但需要广泛的校准.
机器学习 (ML) 替代模型 (SMs) 为DEM校准提供了一个有前途的解决方案.

研究的目的:

开发有效的SM,将DEM相互作用参数与颗粒分离联系起来.
为了评估各种ML模型并使用贝叶斯优化优化超参数.
为适应性中小企业在新情景中引入转移学习 (TL) 方法.

主要方法:

在经济高效的DEM模拟数据上训练了多个ML模型 (ANN,合体学习).
采用贝叶斯优化与超参数调整的交叉验证.
开发了一种基于TL的新方法,使用高斯过程回归 (GPR) 来处理未见的场景.

主要成果:

高斯过程回归 (GPR) 在非常小的数据集中显示出高精度.
通过TL方法,在很少样本的情况下,可以为未见的初始配置提供准确的SM.
在未见的场景中,对TL-GPR观察到17% (1个样本) 和47% (5个样本) 的性能改善.

结论:

拟议的基于TL的SM显著降低了DEM校准的数据负担.
这种方法加速了对颗粒材料的可靠DEM模型的开发.
这些发现有助于有效校准和预测颗粒分离现象.