A Data Optimization Strategy Applicable to Intelligent Diagnosis of the Health State of Gas Insulated Switchgears

As the main insulating substance of gas insulated switchgear (GIS), the parameters of sulfur hexafluoride (SF6) can effectively reflect the operating status of the equipment, and the monitoring of SF6 in GIS can effectively prevent unknown fault hazards. However, the data required in the constructed prediction model may be missing or redundant, which may lead to a large error in the results, and the selection of an appropriate sequence length is crucial to the accuracy and validity of the results. The time series range of SF6 gas involves gas pressure, temperature, humidity, leakage, and gas composition. In this paper, for the gas pressure parameters of SF6, the optimal length selection method based on phase space reconstruction is utilized to obtain the optimal data from the state quantity time series, and through this method, a section of the optimal time series that can reflect the overall change rule of the gas pressure of SF6 is obtained by taking the 72.5 kV GIS as an example.