Voltage transformer error prediction method based on transfer entropy and wavelet neural network

Abstract

The invention discloses a voltage transformer error prediction method based on transfer entropy and a wavelet neural network. The method comprises the following steps: acquiring environmental parameters, electrical parameters and error data of operation of an electronic voltage transformer; through a transfer entropy theory, calculating transfer entropy values of environmental parameters and electrical parameters on error data, selecting main influence quantities according to entropy values and positive and negative values, calculating transfer entropy values of contrast differences and angular differences of five influence factors in the environmental parameters and the electrical parameters respectively, and screening the influence factors with strong correlation; and normalizing the influence factors obtained by screening to enable the data to be in an order of magnitude, taking the processed data as an input quantity, and respectively establishing a ratio difference prediction model and an angular difference prediction model through a wavelet neural network; and calculating an error between the prediction curve and the expected curve, and representing the precision of the errorprediction method by an average absolute error. According to the invention, errors of the electronic voltage transformer under different voltage levels can be predicted, and the method has good adaptability.

Description

technical field [0001] The invention relates to the technical field of electronic voltage transformer calibration, in particular to a voltage transformer error prediction method based on transfer entropy and wavelet neural network. Background technique [0002] As an ideal substitute for traditional electromagnetic voltage transformers, electronic voltage transformers are currently widely used in smart substations to provide accurate voltage measurement data for metering and protection equipment. Due to immature technology development, its digital processing unit and sensing unit are susceptible to interference from the working environment, and there is a problem of accuracy degradation after long-term operation. This requires finding a way to obtain the error change of the electronic voltage transformer. In engineering, professionals regularly maintain and overhaul transformers. Due to the different equipment used, it can be divided into off-line overhaul and online calibra...

AI Technical Summary

Problems solved by technology

The internal components of electronic voltage transformers will be affected by factors such as electric field, magnetic field, temperature, vibration, etc., and long-term operation will cause accuracy degradation problems

Images