Microgrid Fault Diagnosis Method Based on Whale Algorithm Optimizing Extreme Learning Machine

Abstract

The present invention relates to a microgrid fault diagnosis method based on the whale algorithm to optimize the extreme learning machine, including S1, first building a microgrid grid-connected operation simulation model including wind generators, photovoltaic cells and storage batteries, and collecting three-phase faults at both ends of the line Voltage signal; S2. Select db6 wavelet as the wavelet base, decompose and reconstruct the simulated three-phase fault voltage signal including phase A, phase B and phase C respectively according to the relevant formula of wavelet packet analysis, and calculate its energy entropy to obtain a total Contains the eigenvector X of energy entropy of 24 wavelet packets=[x 1 ,x 2 ,...x 24 ] T As a data sample; S3, using the whale algorithm WOA to optimize the input weights and hidden layer thresholds of the extreme learning machine ELM to establish a WOA-ELM fault diagnosis model, and bring the data samples obtained in S2 into the WOA-ELM model for training and verification. The diagnostic model established by BP neural network, RBF neural network and ELM was compared with the WOA-ELM model to verify the validity and reliability of the WOA-ELM model.

Description

technical field [0001] The invention relates to a fault diagnosis method for a wind-solar-storage micro-grid, which belongs to the field of fault detection and protection of a micro-grid, and specifically relates to a fault diagnosis method for a micro-grid based on a whale algorithm to optimize an extreme learning machine. Background technique [0002] Distributed power generation is the main direction of new energy development. Microgrid is one of the effective means of integrating distributed energy and an important part of the power system. Microgrid uses renewable energy such as wind turbines, solar power generation equipment, and fuel cells to generate electricity. It has the advantages of green environmental protection, safety and reliability, simple energy conversion, and low operation and maintenance costs. It can effectively solve the shortage of traditional energy sources and the increasingly serious environmental problems. pollution problem. During the operation...

AI Technical Summary

Problems solved by technology

By using the Whale Algorithm to optimize the input weights and hidden layer thresholds of the extreme learning machine to establish a fault diagnosis model, it solves the problem that the network performance is difficult to achieve optimal due to the artificial setting of the initial weights and hidden layer thresholds of the extreme learning machine, which is conducive to further development. Improve recognition accuracy

Images