A ConvNeXt and attention mechanism-based method for detecting spontaneous explosive faults in insulators

ZHA Shikang; HUANG Chenrong

doi:10.3969/j.issn.1672-3643.2023.03.007

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

A ConvNeXt and attention mechanism-based method for detecting spontaneous explosive faults in insulators

更新时间：2026-09-14

- A ConvNeXt and attention mechanism-based method for detecting spontaneous explosive faults in insulators
- Ningxia Electric Power Issue 3, (2023)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1672-3643.2023.03.007
  CLC：
- Online First：06 September 2023，
  
  Published：2023
- 稿件说明：
移动端阅览
ZHA Shikang, HUANG Chenrong. A ConvNeXt and attention mechanism-based method for detecting spontaneous explosive faults in insulators[J]. Ningxia Electric Power, 2023, (3).
DOI：

ZHA Shikang, HUANG Chenrong. A ConvNeXt and attention mechanism-based method for detecting spontaneous explosive faults in insulators[J]. Ningxia Electric Power, 2023, (3). DOI： 10.3969/j.issn.1672-3643.2023.03.007.

摘要

为了更加准确地识别和定位架空线路绝缘子的自爆故障，保障电力系统安全稳定运行，提出一种基于ConvNeXt和注意力机制的目标检测算法，可用于无人机、巡检机器人等设备拍摄的可见光图像中绝缘子自爆故障检测。首先，使用一种新型卷积神经网络ConvNeXt作为主干网络，使用1∶1∶1∶3的阶段模块数量比例，增强网络对抽象语义特征的提取能力；其次，使用跨阶段局部连接结构，减少网络参数量和计算复杂度，丰富网络梯度连接；最后，引入卷积注意力机制，增强网络对复杂背景中目标区域的感知能力。实验结果表明，改进后的绝缘子自爆故障检测模型的平均精度均值达到97.4%，相比基线YOLOv7提升了1.4%，能够有效实现绝缘子自爆缺陷的检测。

Abstract

To ensure the safe and stable operation of the power system by accurately identifying and locating spontaneous explosive faults of overhead power line insulators

an object detection algorithm is proposed.Based on ConvNeXt and attention mechanism

this algorithm can effectively detect insulator spontaneous explosive faults from visible light images captured by equipment such as unmanned aerial vehicles and inspection robots.Firstly

ConvNeXt

a novel convolutional neural network

is used as the backbone network with 1∶1∶1∶3 stage module ratio to enhance the network′s ability to extract abstract semantic features.Secondly

a cross-stage local connection structure is used to reduce network parameters and computational complexity

thereby enriching network gradient connections.Finally

a convolutional attention mechanism CBAM is introduced to enhance the network′s ability to perceive target areas within complex backgrounds.Experimental results show that the improved insulator spontaneous explosive fault detection model achieves an average precision of 97.4%

an improvement of 1.4% over the baseline YOLOv7

effectively enabling the detection of spontaneous explosive faults in insulators.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Wind power forecasting based on modal decomposition and TCN – transformer

Fault identification of high-voltage circuit breaker energy storage mechanism based on EEMD and GA-BP neural network

Study on key parameters of soil corrosion in substation grounding grids in the Ningxia region

Optimization and simulation on the covering air-supported membrane structure for a substation project

Single-phase inverter power supply control for chemical instrumentation based on a second-order generalized integrator

Related Author

No data

Related Institution

No data

AI问答

⁰