Method for predicting concentration of dissolved gas in transformer oil based on EMD-RF

Abstract

The invention discloses a method for predicting the concentration of dissolved gas in transformer oil based on EMD-RF. The method comprises the following steps: firstly, carrying out empirical mode decomposition on original concentration sequences of seven characteristic gases dissolved in the transformer oil to obtain sub-sequences IMF1 to IMFn and a residual component RES; constructing random forest prediction models RF1 to RFn+1, respectively normalizing the decomposed sub-sequences to serve as input vectors of a random forest model, training the constructed random forest models RF1 to RFn+1 to obtain a predicted value of each sub-sequence component, carrying out reverse normalization processing, and superposing all the data subjected to reverse normalization processing to obtain a final prediction result; and comparing the actual values of the characteristic gas concentrations, and evaluating the prediction performance of the model through error analysis of the prediction result and an actual value. The method solves the problems of mutual influence among seven characteristic gas concentrations and low prediction precision, the change trend of the concentration of the dissolvedgas in the oil can be accurately predicted, and an important basis is provided for subsequent preventive maintenance of the transformer.

Description

technical field [0001] The invention relates to the technical field of power equipment monitoring, in particular to a method for predicting the concentration of dissolved gas in oil-immersed transformer oil. Background technique [0002] With the development of energy interconnection, power transformers are the basic equipment for the safe operation of the power grid. Once a failure occurs, it will endanger the safe and stable operation of the entire power system. Therefore, to quickly and accurately understand the latent faults of transformers, so as to carry out maintenance work, can provide an important guarantee for the normal operation of the power system. [0003] Dissolved gas analysis in oil (dissolved gas analysis, DGA) can timely determine the latent faults in the transformer, extract the content of dissolved characteristic gas in the oil through the transformer online detection device, and form a sequence of historical characteristic gas content. Predicting the d...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a method for predicting the concentration of dissolved gases in transformer oil based on empirical mode decomposition and random forest model, which solves the problem of low prediction accuracy caused by the mutual influence of seven characteristic gases dissolved in transformer oil , it is simple to adjust the parameters of the model using this method, and the training efficiency is fast. It can accurately predict the development trend of the dissolved gas concentration in the transformer oil, and can provide an important basis for the preventive maintenance of the transformer.

Images