Power distribution network fault identification method and system based on spectrum entropy and random forest

Abstract

The invention provides a power distribution network fault identification method and system based on spectrum entropy and random forest, and the method comprises the steps: taking the electrical quantity information, fault recording information and system network structure after a fault as the features of a sample, and taking the fault type as the label of each sample; generating an energy feature vector of each sample after the fault recording information is subjected to the spectrum entropy effect, and generating a plurality of decision trees by using a random forest algorithm after the energy feature vector is also used as a sample feature; different sample features are selected for each decision tree for training, and a strong classifier is generated based on a voting system; and taking the strong classifier as a trained fault identification network and carrying out fault identification on the to-be-identified power distribution network. According to the method, the fault recording information is processed through the frequency spectrum entropy, harmonic information in the fault recording information can be fully utilized, and recognition of weak data characteristics of the power distribution network is enhanced. And high-accuracy fault identification can be carried out on a sample with a plurality of features by using a random forest algorithm.

Description

technical field [0001] The invention belongs to the technical field of electric power systems and automation thereof, and in particular relates to a distribution network fault identification method and system based on spectrum entropy and random forest. Background technique [0002] The overhead lines of the distribution network are mainly distributed in cities and towns and span various terrains. Therefore, the fault types of the overhead lines of the distribution network are diverse, including: line insulator flashover, inrush current caused by transformer closing, single-phase grounding, phase-to-phase short circuit, Fault types such as abnormal lightning strikes. Different from the high-voltage transmission network, the distribution network has a low voltage level and a long line length, and the parameter magnitude of the line cannot be generalized with the high-voltage transmission network. Therefore, due to the different network line parameters, when a fault occurs in...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the present invention aims to solve the problem that the traditional fault identification method cannot accurately identify the weak data characteristics of the distribution network and the fault identification is difficult due to topology changes

Images