Research On The Forecasting Method For The Pollution Severity Of Suspension-type Porcelain Insulators

The character of leakage current on the surface of the suspension-type porcelaininsulator was analyzed firstly. Based these, two kinds of leakage current sensors weredeveloped. A series of research work had been carried out in the fog chamber. Therelations among leakage current, ESDD (Equivalent Salt Deposit Density) and relativehumidity (RH) under operating voltage had been analysed. The correctness of therelation had been proved by the grey relational analysis in the data of the temperature,humidity and leakage current from on-line monitoring system of 220kV insulators. Theoverall aim of this project was using the artificial neural network (ANN) to predict thepollution severity of insulators. The results of simulation by the experiment data provedthat the method could predict the pollution severity of insulators more accurately.Thismethod is able to guid the work of cleaning insulators and optimize the cleaning cyclesof insulators effectively.