摘要
首先概述了基于“Q-N”诊断规则的变压器故障诊断方法,随后设计了适用于变压器的在线监测与故障诊断系统,该系统硬件部分主要有ARM主机、DSP从机、局部放电传感器等组成;软件部分由VC++与MATALB混合编程开发,利用BP人工神经网络对前端传感器反馈的数据进行分析,并基于深度学习生成的“诊断规则”进行故障诊断。从应用效果来看,该系统可以准确鉴别变压器故障,为变电站电气设备维护工作开展提供了有益帮助。
First summarizes the transformer fault diagnosis method based on "Q-N" diagnosis rule,and then designs the online monitoring and fault diagnosis system suitable for transformer.The hardware part of the system is mainly composed of ARM host,DSP slave,partial discharge sensor,etc.The software part is developed by VC++ and MATALB hybrid programming.BP artificial neural network is used to analyze the feedback data of front-end sensors,and fault diagnosis is carried out based on the "diagnosis rules" generated by deep learning.From the application effect,the system can accurately identify transformer faults and provide beneficial help for substation electrical equipment maintenance work.
作者
张宇
Zhang Yu(State Grid Heilongjiang Power Transmation and Transformation Engeering Co.,Ltd.,Harbin 150000,China)
出处
《科学技术创新》
2022年第33期88-91,共4页
Scientific and Technological Innovation