基于SVM的低压直流断路器故障诊断研究

Research on Fault Diagnosis of Low Voltage DC Circuit Breaker Based on SVM

摘要:

低压直流断路器作为电力系统控制和保护的最重要的开关设备之一，它的可靠运行关系着电力系统的安全稳定性。因此实现低压直流断路故障诊断对于提高电力系统可靠性和稳定性方面具有重要意义。首先搭建了低压直流断路器信号监测与采集平台，然后提取断路器在分合闸过程中的机械振动信号和线圈电流信号的特征量作为训练和识别故障的特征，最后研究了SVM对电流、振动特征向量的故障诊断效果。结果表明：SVM能够实现低压直流断路器故障诊断，并且在融合振动信号和电流信号时的诊断效果更好。

Abstract:

Low-voltage DC circuit breaker is one of the most important switch devices for controlling and protecting power system, which is reliable operation related to the safety and stability of the power system.Therefore, It is of great significance to diagnose the fault of Low-voltage DC circuit breaker for improving the reliability and stability of the power system. First, a low-voltage DC circuit breaker signal monitoring and acquisition platform is built. And then the characteristic quantities of mechanical vibration signals and coil current signals of circuit breakers during opening and closing are extracted as samples for training and fault identification. Finally, the fault diagnosis effect of SVM on current and vibration feature vector is studied. The results show that: SVM can realize the fault diagnosis of low-voltage DC circuit breaker, and the diagnosis effect is better when the vibration signal and current signal are combined.