Electric energy quality measurement missing restoration method of fuzzy self-organizing neural network

Abstract

The invention discloses an electric energy quality measurement data missing restoration method based on a fuzzy self-organizing neural network. The method is executed by a computer program and comprises the stages of 1) inputting an electric energy quality one-dimensional measurement data set containing missing; 2) carrying out segmented interception on the one-dimensional waveform data obtained by sampling according to N power quality sampling periods; 3) converting the matrix x into an image by adopting a graying method; 4) extracting a characteristic value of the two-dimensional harmonic grey-scale map, and carrying out normalization processing; 5) determining the optimal clustering number of the power grid harmonic data; 6) constructing a target function by taking the weighted quadratic sum of the distances from each sample to all clustering centers as a target; (7) completing restoration of the two-dimensional grey-scale map, and (8) fusing all layers of restored data. Through experimental data analysis, no matter under the condition of random missing or continuous missing, compared with an existing algorithm, the method provided by the invention has less restoration error anda higher signal-to-noise ratio under the conditions of low data loss rate and high data loss rate.

Description

technical field [0001] The present invention relates to a repair method for missing measurement data, and further relates to a repair method for missing data of power quality measurement, in particular to a method for repairing missing power quality measurement data of a fuzzy self-organizing neural network. Background technique [0002] The Ubiquitous Electric Internet of Things (UEIoT) realizes the comprehensive perception and intelligent measurement of the power system, and provides strong information support for the safe, stable and economical operation of the power grid. The ubiquitous sensing big data at the bottom of UEIoT is the basis for situational awareness and status identification of the entire system. Among them, the grid harmonic monitoring data is the key to grasp the harmonic law, realize harmonic control, and improve power quality. However, regardless of the classical Nyquist Nyquist sampling or compressed sensing sampling method, the problem of partial ac...

AI Technical Summary

Problems solved by technology

However, regardless of the classical Nyquist Nyquist sampling or compressed sensing sampling method, the problem of partial acquisition of harmonic signals is often lost due to faults in sensors, transmission equipment, conversion equipment, etc.; or in communication channels, such as Power line carrier, a phenomenon in which data is lost due to channel interference during propagation

Due to the non-repeatability of power grid data collection, in the case of insufficient redundancy, using missing harmonic data for analysis, there is no doubt that the conclusion drawn has a large deviation from the correct law; and when the signal is reconstructed by compressed sampling , since each sampling point contains a large amount of information, the loss of each sampling value will have a huge impact on signal reconstruction

Images