Complex electric energy quality perturbation analysis method based on both-way long short-term memory

Abstract

The present invention discloses a complex electric energy quality perturbation analysis method based on both-way long short-term memory. The method concretely comprises the steps of: collecting a plurality of voltage or current signals in an electric power system to be detected, or employing a mathematic model to obtain 7 classes of basic PQDs and total samples of the complex PQDs formed by different combinations thereof; performing sampling marking to convert to a sequence form, dividing the samples into a training set and a test set; constructing a both-way long short-term memory neural network model and perform training of the both-way long short-term memory neural network model; performing overfitting determination, if there is an overfitting phenomenon, regulating hyper-parameters, and then performing retraining, repeating in this way until there is no overfitting; and employing the trained neural network model to perform PQD determination, wherein the input data is signal sequence data, and the output data is the electric energy type corresponding to each data in the sequence. The defect problems are solved that the identification accuracy is low, the implementation process is complex, the timeliness is poor, and the disturbance start-stop moments cannot be accurately located in the prior art.

Description

technical field [0001] The invention belongs to the technical field of power quality analysis and detection methods, and relates to a complex power quality disturbance analysis method based on bidirectional long-short-term memory. Background technique [0002] Accurate identification of disturbance types is the premise and foundation of complex power quality disturbance (Power Quality Disturbance, PQD) analysis. Power Quality Disturbance (PQD) can be divided into basic PQD and complex PQD. According to the time characteristics of the disturbance, the basic PQD is divided into steady state disturbance (mainly including harmonic / interharmonic, fluctuation, etc.) and transient disturbance (mainly including sag, swell, interruption, oscillation transient, pulse transient, etc. ). Complex PQD is composed of basic PQD with different disturbance types, different disturbance intensities, and different start and end times, especially the disturbance with superimposed transient comp...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a complex power quality disturbance analysis method based on two-way long-term and short-term memory, which solves the problems of low recognition accuracy, complex implementation process, and poor real-time performance in the prior art, and it is impossible to accurately determine the start and end moments of the disturbance. Shortcomings

Images