Insulator surface equivalent salt deposit density prediction system and method

Abstract

The invention discloses an insulator surface equivalent salt deposit density prediction system and method; the system comprises an original data acquisition unit, an adaptive variation particle swarm unit, a generalized regression nerve network prediction unit, an ESDD prediction output unit and an ESDD early warning unit; the collected insulator surface equivalent salt deposit density data and local meteorology data are inputted into the adaptive variation particle swarm unit; the adaptive variation particle swarm searches the generalized regression nerve network optimal smooth factor value in a global solution space, and outputs the factor value to the generalized regression nerve network prediction unit; the generalized regression nerve network prediction unit builds a prediction model according to the inputted optimal smooth factor value, the insulator surface equivalent salt deposit density data and local meteorology data, thus predicting the insulator surface equivalent salt deposit density; the ESDD prediction output unit outputs an ESDD value predicted by the model, thus providing references for power transmission line operation personnel; the ESDD early warning unit determines whether a preset graded early warning threshold is reached or not, and sends an early warning signal if needed.

Description

technical field [0001] The invention belongs to the technical field of external insulation of power systems, and more specifically relates to a prediction system and method for the equivalent salt density on the surface of an insulator. Background technique [0002] Due to the accumulation of dirt on the surface of insulators under normal working voltage, pollution flashover accidents are prone to occur in rainy, foggy and other bad weather, which poses a serious threat to the safe and stable operation of the power system. It is very necessary to predict the pollution degree of insulators on transmission lines in order to prevent pollution flashover accidents in time. The Equivalent Salt Deposit Density (ESDD) is usually used to evaluate the pollution degree of the insulator surface. [0003] The generalized regression neural network (GRNN) model is widely used because of its strong nonlinear mapping ability and flexible network structure, strong learning ability and approx...

AI Technical Summary

Problems solved by technology

[0003] The generalized regression neural network (GRNN) model is widely used because of its strong nonlinear mapping ability and flexible network structure, strong learning ability and approximation ability, and good robustness and fault tolerance. The value of the smoothing factor (SPREAD) in the GRNN model will have a great impact on the approximation accuracy and prediction accuracy of the network

Images