基于振动特征估计的气体绝缘开关设备故障检测与定位

为了有效检测气体绝缘金属全封闭开关设备(Gas Insulated Switchgear, GIS)故障,提出一种基于振动特征分析的GIS设备故障检测与定位方法。首先,选取GIS金属外壳多测点振动信号作为设备的状态变量。然后,构建多输出支持向量回归(Multi-Output Support Vector Regression, MOSVR)模型对GIS设备多测点振动特征进行回归估计,并利用多测点振动特征残差相对值计算故障预警指标。之后,利用指数移动加权平均方法计算自适应阈值来衡量故障预警指标的变化趋势以实现设备的故障检测。检测出故障后,利用箱形图分析多测点振动特征残差来定位设备故障。最后,利用现场实测信号验证了提出方法的有效性。

Fault Detection and Location of Gas Insulated Switchgear Based on Vibration Feature Estimation

In order to effectively detect the fault of Gas Insulated Switchgear (GIS), a method for fault detection and location of GIS based on vibration characteristics analysis is proposed. Firstly, the frequency domain feature of the vibration sig-nals of multiple measuring points on the metal enclosure is extracted as the state variable of the GIS. Then, the Mul-ti-Output Support Vector Regression (MOSVR) model is used to estimate the multi-point vibration characteristics of GIS, and the fault early warning indicator is calculated by using the relative residual value of multi-measurement vibra-tion characteristics. After that, the Exponential Moving Weighted Average (EMWA) method is used to calculate the adaptive threshold to measure the change trend of the fault early warning indicator, which can realize the fault detec-tion of the equipment. After detecting a fault, the box plot is hired to analyze the residual value of multi-point vibration characteristics to locate the fault. Finally, the effectiveness of the proposed fault detection method is verified by the field measured signals.