电力系统保护与控制
電力繫統保護與控製
전력계통보호여공제
POWER SYSTM PROTECTION AND CONTROL
2015年
10期
62-67
,共6页
高压断路器%机械故障%概率神经网络%特征信号提取%故障诊断
高壓斷路器%機械故障%概率神經網絡%特徵信號提取%故障診斷
고압단로기%궤계고장%개솔신경망락%특정신호제취%고장진단
high voltage circuit breakers%mechanical failure%probability neural network%characteristic signal extraction%fault diagnosis
高压断路器是最重要的电力设备之一，在电力系统中起控制和保护作用。为了提高高压断路器故障诊断的准确率，提出了一种基于概率神经网络(PNN)的高压断路器故障诊断方法。该方法在分析高压断路器的故障特性来确定特征信号的基础上建立了PNN故障诊断模型，该模型将采集的特征数据作为网络的输入，通过Parzen窗估计法得到类条件概率密度，进而按Bayes决策规则对特征数据进行分类。经仿真表明，概率神经网络故障诊断模型具有收敛速度快、故障诊断准确率高、容易训练等特点。因此，该方法是一种有效的故障诊断方法，具有良好的应用前景。
高壓斷路器是最重要的電力設備之一，在電力繫統中起控製和保護作用。為瞭提高高壓斷路器故障診斷的準確率，提齣瞭一種基于概率神經網絡(PNN)的高壓斷路器故障診斷方法。該方法在分析高壓斷路器的故障特性來確定特徵信號的基礎上建立瞭PNN故障診斷模型，該模型將採集的特徵數據作為網絡的輸入，通過Parzen窗估計法得到類條件概率密度，進而按Bayes決策規則對特徵數據進行分類。經倣真錶明，概率神經網絡故障診斷模型具有收斂速度快、故障診斷準確率高、容易訓練等特點。因此，該方法是一種有效的故障診斷方法，具有良好的應用前景。
고압단로기시최중요적전력설비지일，재전력계통중기공제화보호작용。위료제고고압단로기고장진단적준학솔，제출료일충기우개솔신경망락(PNN)적고압단로기고장진단방법。해방법재분석고압단로기적고장특성래학정특정신호적기출상건립료PNN고장진단모형，해모형장채집적특정수거작위망락적수입，통과Parzen창고계법득도류조건개솔밀도，진이안Bayes결책규칙대특정수거진행분류。경방진표명，개솔신경망락고장진단모형구유수렴속도쾌、고장진단준학솔고、용역훈련등특점。인차，해방법시일충유효적고장진단방법，구유량호적응용전경。
The high voltage circuit breaker is one of the most important electrical equipments, which controls and protects the power system. In order to improve the accuracy of fault diagnosis of high voltage circuit breakers, a fault diagnosis method of high voltage circuit breakers is proposed based on probabilistic neural network (PNN). This paper establishes PNN fault diagnosis model on the basis of analyzing the failure characteristics of high voltage circuit breaker to determine the characteristics of the signal. The model takes the collected feature data as the input of the network to get the class conditional probabilistic density function by Parzen window estimation method, then classifies characteristic data according to the Bayes decision rules. The simulation verifies that the probabilistic neural network fault diagnosis model has fast convergence, high fault diagnosis accuracy, easy to train and so on. Therefore, this method is an effective method of fault diagnosing and has good prospects.
