摘要
当前变电站高压电气设备自动检测节点的部署一般采用定点形式,覆盖区域较小,导致错误检测次数增加,为此提出基于自组织映射(Self-Organizing Maps,SOM)神经网络的变电站高压电气设备自动检测方法。采用多点位的方式扩大自动检测的覆盖区域,实现对多点位自动检测节点的部署,构建SOM神经网络高压电气设备自动检测模型,将数据输入该模型从而得到相关的检测结果。测试结果表明,设计方法的错误检测次数较少,这表明该方法的稳定性与针对性更强,具有较高的实际的应用价值。
The current deployment of automatic detection nodes for high-voltage electrical equipment in substations generally adopts a fixed-point form,with a small coverage area,resulting in an increase in the number of erroneous detections.Therefore,a method for automatic detection of high-voltage electrical equipment in substations based on Self-Organizing Maps(SOM)neural network is proposed.Adopting a multi-point approach to expand the coverage area of automatic detection,deploying multi-point automatic detection nodes,constructing an SOM neural network high-voltage electrical equipment automatic detection model,and inputting data into the model to obtain relevant detection results.The test results show that the error detection frequency of the design method is relatively low,indicating that the method has stronger stability and specificity,and has high practical application value.
作者
冯永康
王梦欣
FENG Yongkang;WANG Mengxin(School of Information and Electronic Engineering,Shangqiu Institute of Technology,Shangqiu 476000,China)
出处
《通信电源技术》
2025年第3期82-84,共3页
Telecom Power Technology
关键词
自组织映射(SOM)神经网络
变电站
高压电气设备
自动检测
检测节点部署
Self-Organizing Maps(SOM)neural network
substation
high voltage electrical equipment
automatic detection
deployment of detection nodes
