No abstract

GIS’s reducing unit is a new and environment-friendly structural unit, which can greatly reduce the consumption of aluminum alloy material and insulating gas. The structural size of this unit is much smaller than the conventional one. In this paper, an acoustic-structure coupling interaction model of partial discharge in reducing unit of gas insulated switchgear (GIS) is presented. The interaction between the internal acoustic source of partial discharge and structure of GIS is simulated with the finite element analysis, and the acoustic pressure levels distribution of GIS is obtained. The results show that the sound pressure distribution of the reducing unit is basically the same as that of the conventional one, but the amplitude is larger. At the same time, the high-frequency part of the acoustic signal attenuates more quickly in the reducing unit. This paper provides a theoretical guidance basis for the ultrasonic partial discharge detection of the GIS reducing unit.

The BP neural network is used to calculate the basic fault probability distribution of the dissolved gas in the transformer oil and the core grounding online monitoring data, and the Dempster-Shafer evidence theory is used to fuse the multi-source information of the basic probability of various types of faults to obtain a transformer fault diagnosis model. Transformer samples are used to verify the model, and the support vector machine and convolutional neural network fault diagnosis models are compared, and it is concluded that the proposed method is better in terms of fault diagnosis accuracy and stability.

No abstract

No abstract