摘要
为进一步提升绝缘子故障检测的准确率,在现有绝缘子故障检测方法上提出一种新的自动化检测方法.首先,借助热成像技术对绝缘子故障图像进行预处理;其次,借助卷积神经网络技术实现绝缘子故障特征识别;最后,借助Sobel算子实现绝缘子故障的检测及定位.从对比实验结果看,所提方法在绝缘子故障检测上具有较高准确率和精准度.
In order to further improve the accuracy of insulator fault detection,a new automated detection method is proposed based on existing insulator fault detection methods.Firstly,preprocess the insulator fault image using thermal imaging technology;Secondly,using convolutional neural network technology to achieve insulator fault feature recognition;Finally,the Sobel operator is used to detect and locate insulator faults.From the comparative experimental results,it can be seen that the proposed method has high accuracy and precision in insulator fault detection.
作者
车小春
刘慧凌
Che Xiaochun;Liu Huiling(State Grid Tibet Electric Power Co.,Ltd.,Lhasa Tibet 850000,China)
出处
《现代工业经济和信息化》
2024年第3期259-260,263,共3页
Modern Industrial Economy and Informationization
关键词
绝缘子
故障检测
对比试验
insulator
fault detection
contrast testtest
作者简介
车小春(1991-),男,甘肃岷县人,本科,毕业于电子科技大学,助理工程师,研究方向为电力系统及其自动化;刘慧凌(1993-),女,四川南充人,本科,毕业于电子科技大学,助理工程师,研究方向为电力系统及其自动化。
