Oil-immersed transformer fault diagnosis method and system and readable storage medium

Abstract

The invention provides an oil-immersed transformer fault diagnosis method and system and a readable storage medium. The oil-immersed transformer fault diagnosis method comprises the following steps: S1, acquiring corresponding gas contents in different fault states and normal states; s2, screening the gas in the S1, selecting the gas with centrality and integrity as a characteristic gas input model, and performing integer coding on the transformer state corresponding to the characteristic gas as an output result of model training; s3, preprocessing is carried out, and effective data is reserved as a first training set; s4, carrying out layered division, sample synthesis balance and standardization treatment; s5, training and testing are carried out; and S6, carrying out transformer fault diagnosis. According to the invention, the defects of the existing oil-immersed transformer fault diagnosis algorithm based on the traditional artificial intelligence algorithm can be made up, the fault diagnosis accuracy of the oil-immersed transformer is improved, and the power supply reliability is improved.

Description

【Technical field】 [0001] The invention relates to the technical field of transformer fault diagnosis, which is realized based on the SMOTE-XGBoost integrated learning algorithm, and specifically relates to an oil-immersed transformer fault diagnosis method, system and readable storage medium. 【Background technique】 [0002] Transformer fault diagnosis is an important part of the daily operation and maintenance of substations. It is related to the safety and reliability of power supply and is one of the key links to ensure the safe operation of the power grid. Transformer fault diagnosis is to monitor the state of substation equipment, analyze and mine some key state data of transformers in time, judge possible fault types of transformers through experience or big data analysis algorithms, and arrange maintenance in time. With the application of big data technology and advanced sensors, the operation and maintenance strategy of transformer fault diagnosis has gradually transi...

AI Technical Summary

Problems solved by technology

[0007] The factors that lead to transformer failures are complex, and various factors are coupled with each other. In addition, there are many transformers in the actual substation. The manual maintenance workload is huge and depends on the experience of the maintenance personnel, which is very subjective.

Although the traditional artificial intelligence fault diagnosis algorithm overcomes subjectivity and greatly reduces the workload of humans, it faces the challenge of lack of high-quality historical data sets and a serious imbalance in the distribution of data sets. Low accuracy, unreliable diagnostic results, etc.

Images