A transformer alarm method, device, equipment and storage medium

Abstract

The application belongs to the field of electric power, and discloses a transformer alarm method, device, equipment and storage medium, comprising: acquiring real-time voltage sequence, real-time current sequence, load fluctuation sequence and environment temperature sequence of the transformer, and generating abnormal frequency band signals and an abnormal signal feature set; calculating the difference value of adjacent load fluctuations and the difference value of adjacent environment temperatures in the load fluctuation sequence and the environment temperature sequence, obtaining fluctuation amplitude and temperature gradient, and generating a feature fusion matrix; extracting a principal component feature vector from the feature fusion matrix and determining a correction signal feature set corresponding to the abnormal signal feature set; inputting the abnormal frequency band signals into a prediction model to obtain a prediction signal sequence, performing curve fitting after signal smoothing on the prediction signal sequence to obtain a prediction waveform curve; calculating the difference value of the real-time voltage sequence and the prediction waveform curve to obtain a voltage deviation sequence, and performing alarm according to the comparison result of the voltage deviation sequence and a preset voltage deviation threshold.

Images