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

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

The efficacy, safety, and rationale of orelabrutinib combined with obinutuzumab (O2) as a first-line systemic treatment for marginal zone lymphoma.

Blood cancer journal·2026

Same author

Robust Quantum Cutting via Halide-Bearing Ligand Passivation and Gradient Halide Reconstruction for Ultrabroadband Ultraviolet-to-Near-Infrared Photodetection and Imaging.

ACS nano·2026

Same author

A high-dexterity soft neuroprosthetic hand for daily activities.

Nature communications·2026

Same author

Robust retrieval of biophysical traits under shade gradients in young <i>Hopea hainanensis</i> using visible and near-infrared hyperspectral hybrid modeling.

Frontiers in plant science·2026

Same author

Effects of 12-weeks of Brisk Walking on Health-related Physical Fitness, Balance, and Life Satisfaction in Overweight Older Chinese Women: A Cluster Randomized Control Trial.

PloS one·2026

Same author

[Whole-cell catalytic synthesis of 2,5-furandicarboxylic acid].

Sheng wu gong cheng xue bao = Chinese journal of biotechnology·2026

Search research articles

相关实验视频

Updated: Jun 14, 2025

Fabrication Process of Silicone-based Dielectric Elastomer Actuators

Fabrication Process of Silicone-based Dielectric Elastomer Actuators

Published on: February 1, 2016

介电弹性体执行器的自动设计框架:基于神经网络的实时模拟,基于遗传算法的电极优化和实验验证.

Zijian Qin^1,2, Jieji Ren^1,2, Feifei Chen^1,2

¹State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai, China.

|November 29, 2024

概括

本研究引入了用于设计介电弹性体执行器 (DEA) 的深度学习框架. 该方法快速优化电极图案,显著提高DEA性能,并使更广泛的应用成为可能.

关键词:

持续的变形持续的变形介电弹性体驱动器 (DEA) 是一种分布式电场是分布式的电场.基于遗传算法的优化设计.神经网络嵌入的物理信息.

更多相关视频

Fabrication of Carbon-Based Ionic Electromechanically Active Soft Actuators

Fabrication of Carbon-Based Ionic Electromechanically Active Soft Actuators

Published on: April 25, 2020

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Published on: March 1, 2019

相关实验视频

Last Updated: Jun 14, 2025

Fabrication Process of Silicone-based Dielectric Elastomer Actuators

Fabrication Process of Silicone-based Dielectric Elastomer Actuators

Published on: February 1, 2016

Fabrication of Carbon-Based Ionic Electromechanically Active Soft Actuators

Fabrication of Carbon-Based Ionic Electromechanically Active Soft Actuators

Published on: April 25, 2020

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Published on: March 1, 2019

科学领域:

材料科学材料科学材料科学
机器人技术机器人技术机器人技术
人工智能的人工智能

背景情况:

介电弹性体执行器 (DEA) 为软机器人提供快速响应和高能量密度.
优化DEA设计是具有挑战性的,因为复杂的机电行为和高维的设计空间.
目前的优化方法依赖于耗时的有限元分析.

研究的目的:

开发基于深度学习的框架,用于DEA的自动和快速设计.
在高维空间设计中克服传统优化方法的局限性.
为了加速为DEAs生成优化的电极模式.

主要方法:

一个数据集构建策略与有限元建模相结合,以优化数据分布.
一个包含物理信息的神经网络,用于准确预测连续变形.
一个与神经网络集成的遗传算法,用于快速优化电极模式.

主要成果:

该框架成功地为DEA生成了高维分布式电极模式.
连续变形的准确预测在0.011秒内实现.
电极图案的自动设计过程在不到2分钟内完成.
在各种案例研究中,在DEA表现上表现出显著的改善.

结论:

提出的深度学习框架使DEA的自动和快速设计成为可能.
这种方法加快了优化过程,克服了以前的效率限制.
该框架为在软机器人领域更广泛地采用和应用DEA铺平了道路.