Electric energy quality disturbance recognition method based on improved PSO (Particle Swarm Optimization) and SVM (Support Vector Machine)

Abstract

The invention discloses an electric energy quality disturbance recognition method based on improved PSO (Particle Swarm Optimization) and an SVM (Support Vector Machine). The method comprises the following steps that: 1) constructing a weighted morphological filter to carry out filtering processing on a collected voltage and current signal, reducing the interference of noise for the signal, and extracting a corresponding characteristic value; 2) improving the traditional PSO, utilizing the improved PSO to optimize SVM parameters, and constructing a classifier model; and 3) taking an extractedelectric energy quality disturbance signal characteristic signal as the input of a classifier, and through the identification of the classifier, outputting a corresponding disturbance signal category.By use of the method, firstly, noise in the signal is quickly filtered, and the historical data of the electric energy quality signal is trained to quickly and accurately realize electric energy quality disturbance recognition classification.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis and classification identification, in particular to a power quality disturbance identification method based on improved PSO and SVM. Background technique [0002] With the widespread application of electronic equipment and the increasing number of nonlinear loads in power systems, the disturbance of power quality has become a very important problem in power systems. Any event that causes a voltage or current deviation can be seen as a disturbance in power quality, which greatly reduces the stability of the power system. Therefore, it is necessary to detect the power quality, which can detect whether there is a disturbance in the power system and then classify various power faults. How to extract features and then identify them becomes the most important issue in power quality monitoring and analysis. [0003] According to the relevant standards of IEEE 1159-2009, power quality disturbanc...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the disadvantages of optimizing existing methods, and propose a power quality disturbance identification method based on improved PSO and SVM, which breaks through the problems of low recognition accuracy and slow recognition speed in traditional power quality disturbance recognition methods. Data training on disturbance faults can effectively improve the accuracy of identification and realize fast and accurate identification of power quality disturbances

Images