Transformer fault diagnosis method for optimizing multi-granularity cascade forest model based on particle swarm algorithm

Abstract

The invention discloses a transformer fault diagnosis method for optimizing a multi-granularity cascade forest model based on a particle swarm algorithm, and the method comprises the steps: taking a non-coding ratio of characteristic gas dissolved in transformer oil as a characteristic parameter of the model, carrying out the normalization of the characteristic parameter, and dividing a training set and a test set; then constructing a multi-granularity cascade forest model, optimizing two key parameters of the multi-granularity cascade forest through a particle swarm algorithm, and obtaining two optimal parameters; and finally, establishing a multi-granularity cascade forest model based on particle swarm optimization for identifying the fault category of the transformer, so that the faultdiagnosis accuracy of the transformer is effectively improved, and a reliable basis is provided for operation and maintenance personnel to correctly judge the operation condition of the transformer.

Description

technical field [0001] The invention relates to the technical field of power equipment monitoring, in particular to a method for diagnosing a transformer fault based on a particle swarm algorithm to optimize a multi-granularity cascade forest model. Background technique [0002] A transformer failure will endanger the safe and stable operation of the entire power system. The transformer fault diagnosis method can analyze the equipment status information, which is the key to ensure the reliable and efficient operation of the equipment. Therefore, quickly and accurately identifying the fault type of the transformer and carrying out timely maintenance can provide an important guarantee for the normal operation of the power system. [0003] Dissolved Gas Analysis (DGA) is mainly used in the online monitoring of oil-immersed transformers. Based on the characteristic gas of DGA for data association analysis, domestic and foreign researchers have proposed IEC ratio method, Rogers ...

AI Technical Summary

Problems solved by technology

For example, the expert system cannot learn independently, the work efficiency is low, and it is difficult to obtain accurate diagnosis results; DBN has strong self-learning ability, but requires a large amount of sample data for training, hyperparameter adjustment is complicated, the learning cycle is long, and it is easy to overfit; SVM The accuracy of dealing with multi-classification problems of transformer fault diagnosis is low; the fuzzy processing process of fuzzy theory is relatively complicated, and the coding of fuzzy diagnosis corresponds to the fault type is mostly based on the traditional gas ratio or characteristic concentration diagnosis method

Images