Distribution network fault classification method based on convolution depth confidence network

Abstract

The invention relates to a distribution network fault classification method based on a convolution depth confidence network. The method comprises the steps of firstly collecting the three-phase voltage, zero-sequence voltage and three-phase current of a low-voltage bus of a main transformer and a low-voltage side of the main transformer, and respectively interceptting the signal waveform data of one cycle wave before and after each fault condition as training samples; secondly, carrying out the time-frequency decomposition on the training sample data of step S1 by using the discrete wavelet packet transform, and obtaining the time-frequency matrix, then constructing the pixel matrix of the time-frequency spectrum map, and constructing the time-frequency spectrum map as the input of the subsequent CDBN model; then constructing the CDBN model to train two convolution-constrained Boltzmann machines in unsupervised learning mode, and adding the softmax classifier after the second CRBM to train the network model to effectively extract and automatically classify the fault features, and finally, using the trained model to realize the fault classification of distribution network. The method of the invention can realize accurate fault location.

Description

technical field [0001] The invention relates to the field of battery testing, in particular to a distribution network fault classification method using a convolutional deep belief network. Background technique [0002] The distribution network structure is becoming more and more complex, and faults are inevitable, among which short-circuit and ground faults are the most common. After a fault occurs, whether it is network reconstruction, fault location, or accident analysis, troubleshooting, and maintenance all depend on the accurate classification of fault types. However, the existence of many interference factors has created difficulties for the distribution network to accurately identify the fault type: the distribution network is susceptible to interference from user site noise and harmonics, making the fault characteristics blurred; in addition, due to the complex composition and many branches, the distribution network The electrical characteristics of the grid fault ar...

AI Technical Summary

Problems solved by technology

However, based on the method of this step, the involved signal decomposition, feature extraction, pattern recognition methods, and fault feature quantities all need manual extraction, which is easily disturbed by human factors and takes a lot of time, increasing the uncertainty of the results.

Images