Power distribution network fault data identification method based on convolutional neural network

Abstract

The invention relates to a power distribution network fault data identification method based on a convolutional neural network, and belongs to the technical field of electric power. The method comprises the following steps: S1, acquiring transient fault data of the power distribution network, and preprocessing the transient fault data; S2, building a fault feature extraction network by using multiple layers of 1DCAE, and inputting the preprocessed transient fault data to train and optimize the fault feature extraction network to obtain low-dimensional fault features; and S3, building a fault feature classification model by using the multi-layer 1DCNN, and inputting low-dimensional fault features to train and optimize the fault feature classification model to complete different types of identification of transient fault data. The method has an automatic feature extraction capability and a relatively good fault-tolerant capability, and is more suitable for identifying mass fault data in the power distribution network.

Description

technical field [0001] The invention belongs to the technical field of electric power, and relates to a method for identifying fault data of a power distribution network based on a convolutional neural network. Background technique [0002] As the power system is moving towards intelligence and transparency, the structure of the distribution network is becoming more and more complex, the detection equipment is more numerous, and the probability of various failures during operation increases sharply. After a fault occurs, in order to avoid further deterioration and spread of the fault, it is necessary to quickly and accurately perform fault location, network reconfiguration, fault fusion, fault event analysis and troubleshooting, and fault diagnosis and identification are the prerequisites for the above work. [0003] At present, the fault diagnosis and classification methods for distribution network can be classified into three categories: [0004] The first category is the...

AI Technical Summary

Problems solved by technology

This type of method improves the classification performance to a certain extent, but it takes a lot of time to manually analyze and extract features, the model is easily affected by human factors, and it is more difficult to extract artificial features for fault samples with small differences in multiple types

[0006] The third type is data feature processing and feature classifiers, both of which use deep learning frameworks to identify fault types. This type of full deep learning model is more suitable for identifying massive fault data in distribution networks. However, the research on this model is not perfect, and the adaptability weaker

[0007] Therefore, there is an urgent need for a distribution network fault data identification method that can solve the problems of low fault tolerance, low identification efficiency, and low identification accuracy of SVM, ANN, and CNN in traditional manual feature extraction methods

Images