A power distribution network fault classification method, system, device and medium

Abstract

The application discloses a power distribution network fault classification method, system, device and medium, and the method comprises the following steps: acquiring historical operation state data and corresponding fault category labels of a transformer oil chromatographic monitoring system, constructing a feature matrix according to the historical operation state data, preprocessing the feature matrix to obtain a reduced feature set; selecting different base learners, and preliminarily training the base learners according to the reduced feature set and the fault category labels; performing global optimization on the hyperparameters of each base learner according to the preliminary training result to obtain the optimal hyperparameter configuration of each base learner; constructing an integrated prediction model by weighting and integrating each base learner according to the optimal hyperparameter configuration to obtain a fault classification result; and deploying the integrated prediction model to the transformer oil chromatographic monitoring system, receiving monitoring data in real time and outputting a fault category prediction result, thereby realizing fault classification of the power distribution network and significantly improving the safety and reliability of the power distribution network operation.

Images