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

Search research articles

相关实验视频

Updated: Jun 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

基于条件批量规范化卷积神经网络的弧断检测研究,具有成本敏感的多功能提取.

Xin Ning^1,2, Tianli Ding³, Hongwei Zhu³

¹State Grid Sichuan Electric Power Research Institute, Chengdu 610041, China.

Sensors (Basel, Switzerland)

|December 17, 2024

概括

此摘要是机器生成的。

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

Nanoscale amorphization of poly(triarylamine) for efficient and stable inverted perovskite photovoltaics.

Nature nanotechnology·2026

Same author

Protonation-Gated Hydrogen Evolution Enabled by Pyridinic Nitrogen on Graphene Edges.

Nano letters·2026

Same author

Pain-free survival after endoscopic neurotomy versus radiofrequency ablation of the C2 dorsal root ganglion for cervicogenic headache: a real-world comparison study.

Frontiers in pain research (Lausanne, Switzerland)·2026

Same author

A universal scaling law for active diffusion in complex media.

Nature communications·2026

Same author

Development and efficacy evaluation of an inactivated Bordetella bronchiseptica vaccine in cats.

Vaccine·2026

Same author

CARES-Net: a channel-attention residual network for multi-disease classification in small-sample <sup>1</sup>H NMR metabolomics data.

Analytica chimica acta·2026

本研究介绍了一种先进的方法,通过整合多个数据特征来检测电力系统中危险的电弧故障. 新方法提高了安全性和系统稳定性,提高了准确性和降低了计算成本.

科学领域:

电气工程电气工程
电力系统安全电力系统安全
在工程领域的人工智能.

背景情况:

弧形断层在电力系统中构成重大火灾和安全风险.
现有的弧形故障检测方法往往在具有成本效益的特征选择方面扎.
准确及时检测对于预防事故和确保电网稳定性至关重要.

研究的目的:

开发一种优质的电弧故障检测方法,解决特征选择的局限性.
为了提高圆弧故障检测的准确性和减少误判率.
为电弧故障检测提供一个计算效率高的解决方案.

主要方法:

一种多特征的方法,结合了时间域,频率域,能量和空间特征.
将这些特征集成到一个有条件批量正常化 (CBN) 卷积神经网络中.
与传统的电弧故障检测模型进行比较分析.

主要成果:

拟议的多功能CBN方法证明了卓越的检测性能.
与传统模型相比,实现了更高的准确性和更低的误判率.
保持了较低的计算成本,表明了效率.

结论:

关键词:

在美国,CNN是CNN.电弧故障故障的时间有条件的批量正常化.具有成本敏感性的优化优化

更多相关视频

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

相关实验视频

Last Updated: Jun 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

开发的方法为电弧故障检测提供了有效的改进.
多功能集成和CBN网络提供了增强的安全性和运营稳定性.
这种方法为关键电力系统安全提供了可行的,具有成本效益的解决方案.