Transformer real-time hot spot temperature prediction method

Abstract

The invention relates to the field of transformer real-time hot spot temperature prediction, in particular to a transformer real-time hot spot temperature prediction method, which comprises the stepsof firstly obtaining historical data of load current, environment temperature, top oil temperature and real-time hot spot temperature of a transformer, and preprocessing the historical data to generate a training sample set and a test sample set; then selecting a training sample set to establish an SVR prediction model; training the SVR by adopting a training sample, optimizing the parameters of the SVR by adopting an improved gravitation search algorithm in the training process, and improving the prediction capability of the prediction model; and finally, inputting the test sample into the trained SVR for prediction to obtain a real-time hot spot temperature prediction value of the transformer. According to the method, the problem of localized optimization of a gravitation search algorithm is effectively solved, the problem that parameters of the support vector machine are difficult to select is effectively solved, the prediction performance of the support vector machine is enhanced,and the real-time hot spot temperature prediction precision of the transformer is improved.

Description

technical field [0001] The invention relates to the field of transformer real-time hot spot temperature prediction, in particular to a transformer real-time hot spot temperature prediction method. Background technique [0002] The hot spot temperature of a power transformer is an important data that reflects the health of the transformer. If the transformer is operated at an excessively high hot spot temperature, it will seriously affect the life and safety of the transformer. The existing transformer hot spot temperature research methods mainly include real-time monitoring of hot spot temperature based on transformer temperature measurement system, hot spot temperature calculation based on empirical formula method, thermal circuit model method and numerical simulation method, and transformer hot spot temperature prediction based on intelligent learning algorithm. kind. At present, the commonly used transformer hot spot temperature prediction methods mainly include neural n...

AI Technical Summary

Problems solved by technology

[0003] The invention provides a real-time hotspot temperature prediction method of a transformer, which effectively solves the localized optimal problem of the gravity search algorithm, effectively solves the problem of difficult selection of support vector machine parameters, enhances the prediction performance of the support vector machine, and can be applied to Scientific research and engineering applications in transformer-related fields can improve the accuracy of transformer real-time hot spot temperature prediction

Images