Search research articles

相关概念视频

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

Revocable Signature Scheme with Implicit and Explicit Certificates.

Entropy (Basel, Switzerland)·2023

Same author

Comparison of Representative Microservices Technologies in Terms of Performance for Use for Projects Based on Sensor Networks.

Sensors (Basel, Switzerland)·2022

Same author

Comparison of Pedestrian Detectors for LiDAR Sensor Trained on Custom Synthetic, Real and Mixed Datasets.

Sensors (Basel, Switzerland)·2022

Same author

A Comparison of Java, Flutter and Kotlin/Native Technologies for Sensor Data-Driven Applications.

Sensors (Basel, Switzerland)·2021

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

Search research articles

相关实验视频

Updated: Jan 13, 2026

A Microfluidic Platform for Precision Small-volume Sample Processing and Its Use to Size Separate Biological Particles with an Acoustic Microdevice

A Microfluidic Platform for Precision Small-volume Sample Processing and Its Use to Size Separate Biological Particles with an Acoustic Microdevice

Published on: November 23, 2015

通过机器学习和数值建模,提高声流体芯片中的微粒分离效率.

Tamara Klymkovych^1,2, Nataliia Bokla^1,2, Wojciech Zabierowski³

¹Department of Semiconductor and Optoelectronic Devices, Lodz University of Technology, 116 Zeromskiego, 90-924 Łódź, Poland.

Sensors (Basel, Switzerland)

|October 29, 2025

概括

这项研究将COMSOL模拟与基于Python的强化学习相结合,以优化声流体实验室芯片设备中的微粒分离. 人工智能方法显著提高了排序效率,并减少了计算时间.

关键词:

科姆索尔多元物理多元物理这是一个 Livelink API.声流体学声流体学芯片上的实验室机器学习是机器学习.微流体仿真技术的应用微粒子分离的方法是微粒子分离.神经网络的神经网络的神经网络参数优化的参数优化强化学习是一种强化学习.

更多相关视频

Fabrication, Operation and Flow Visualization in Surface-acoustic-wave-driven Acoustic-counterflow Microfluidics

Fabrication, Operation and Flow Visualization in Surface-acoustic-wave-driven Acoustic-counterflow Microfluidics

Published on: August 27, 2013

Fabrication and Operation of Acoustofluidic Devices Supporting Bulk Acoustic Standing Waves for Sheathless Focusing of Particles

Fabrication and Operation of Acoustofluidic Devices Supporting Bulk Acoustic Standing Waves for Sheathless Focusing of Particles

Published on: March 6, 2016

相关实验视频

Last Updated: Jan 13, 2026

A Microfluidic Platform for Precision Small-volume Sample Processing and Its Use to Size Separate Biological Particles with an Acoustic Microdevice

A Microfluidic Platform for Precision Small-volume Sample Processing and Its Use to Size Separate Biological Particles with an Acoustic Microdevice

Published on: November 23, 2015

Fabrication, Operation and Flow Visualization in Surface-acoustic-wave-driven Acoustic-counterflow Microfluidics

Fabrication, Operation and Flow Visualization in Surface-acoustic-wave-driven Acoustic-counterflow Microfluidics

Published on: August 27, 2013

Fabrication and Operation of Acoustofluidic Devices Supporting Bulk Acoustic Standing Waves for Sheathless Focusing of Particles

Fabrication and Operation of Acoustofluidic Devices Supporting Bulk Acoustic Standing Waves for Sheathless Focusing of Particles

Published on: March 6, 2016

科学领域:

微流体学微流体学
计算科学计算科学
人工智能的人工智能

背景情况:

传统的对微粒子分离进行参数调整是耗时且计算密集的.
声流体实验室芯片系统需要高效的微粒分离,用于各种应用.
优化流速和声频等控制参数对于提高分离效率至关重要.

研究的目的:

开发一种综合方法,以提高声流体实验室在芯片系统中的微粒分离效率.
将数值建模与强化学习相结合,用于自动化优化.
为了解决传统参数调方法的局限性.

主要方法:

使用了COMSOL 6.2 Multiphysics®用于数值建模和LiveLinkTM用于COMSOL-Python集成.
在Python 3.10.14中实现了强化学习算法,以优化控制参数.
在100多个数值模拟中训练了一个神经网络,包括失败的实验,以预测和提高排序效率.

主要成果:

综合方法使得能够自动生成,执行和评估颗粒分离场景.
强化学习算法成功优化了控制参数,以提高排序效率.
将失败的实验结果纳入奖励结构显著提高了学习趋同和模型准确性.

结论:

开发的方法为微流体系统提供了一个智能和自主优化策略.
这种方法有助于推进微塑料的无标签分离,环境监测以及用于诊断的细胞/囊泡操纵.
这些发现为智能微流体系统铺平了道路,能够自主适应和优化.