A Fault Diagnosis Method for Oil-immersed Transformer Based on Neural Network and Decision-making Fusion

Abstract

The invention proposes a fault diagnosis method for an oil-immersed transformer integrated with a neural network and decision-making. Among them, the method of neural network and decision fusion includes: fault coding, construction and training of neural network model, and calculation of decision fusion matrix. After encoding the faults of low-temperature overheating, medium-temperature overheating, high-temperature overheating, partial discharge, low-energy discharge, and high-energy discharge, use the dissolved gas content in 5 kinds of transformer oil as identification features, train multiple neural networks, and calculate according to the test accuracy of the neural network The decision fusion matrix realizes the decision fusion of multiple neural networks. This method can adjust its weight in the whole model identification according to the identification performance of a single neural network for a specific fault, so as to improve the accuracy of fault diagnosis, which is of great significance to the timely processing of transformer faults and the stable and reliable operation of power systems.

Description

technical field [0001] The invention belongs to the field of transformer fault diagnosis, and in particular relates to a fault diagnosis method for an oil-immersed transformer integrated with neural network and decision-making. Background technique [0002] As the key equipment of the power system, the transformer plays the role of voltage conversion, current conversion, power transmission and so on in the conversion of electric energy. With the gradual expansion of power grid capacity and the rapid development of EHV and UHV technologies, the power grid needs to have higher reliability and safety. Bring inconvenience, also can seriously affect the development progress of national economy. The operating status of the transformer will directly affect the stability, safety, integrity and economy of the power system, so it is of great significance to ensure the safety and stability of the transformer and timely troubleshooting. [0003] Dissolved gas analysis (DGA) in transfo...

AI Technical Summary

Problems solved by technology

[0004] Artificial neural network is a classification algorithm, which can effectively fit the nonlinear mapping relationship between input and output. It has very good classification performance and can be applied to fault detection, but it may fall into local problems when using neural network for training. Optimum, further may lead to unbalanced identification performance of different faults in fault identification, that is, it can identify certain types of faults well, but the identification effect on other faults is poor

Images