Transformer fault diagnosis method based on CQFPA-WNN

Abstract

The invention discloses a transformer fault diagnosis method based on CQFPA-WNN, and the method specifically comprises the steps: 1, collecting oil fault feature gas concentration data of an oil-immersed transformer, enabling the fault feature gas concentration data to serve as a total sample set, and dividing the total sample set into a training sample and a test sample; 2, performing normalization processing on the collected total sample set; 3, initializing a wavelet neural network and a cloud quantum flower pollination algorithm, and preparing for inputting wavelet neural network optimization parameters into a training sample; 4, optimizing wavelet neural network parameters by using the training sample and applying a flower pollination algorithm, and training the optimized wavelet neural network to obtain a diagnosis model; and 5, applying the test samples to a wavelet neural network transformer fault diagnosis model optimized based on a cloud operator flower pollination algorithm,and classifying the test samples to complete fault diagnosis. According to the method, the fault diagnosis speed and accuracy can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of transformer fault online monitoring methods, and in particular relates to a transformer fault diagnosis method based on CQFPA-WNN. Background technique [0002] With the continuous improvement of the economic level, my country's power system has achieved unprecedented development, the scale of the power grid has continued to expand, and the number of substations has doubled, which poses greater challenges to the safe and reliable operation of the power system. If the power system fails or a large-scale blackout occurs, it will cause huge economic losses, and it will also endanger public safety and bring serious social impact. [0003] With the large-scale construction of UHV projects, the interaction between AC and DC systems has further intensified, and the problem of "strong direct and weak AC" has become prominent, and new challenges are faced in ensuring the safe and stable operation of large power gr...

AI Technical Summary

Problems solved by technology

The analysis of dissolved gas in transformer oil is a simple and effective fault diagnosis method, which has been actively applied by researchers and institutions. Based on this method, traditional diagnostic methods such as three-ratio method and David's triangle method are derived, and the above methods mainly It is a diagnostic rule established by operating experience and expert knowledge, so it is prone to problems such as low diagnostic accuracy due to lack of coding

Images