Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fault section binary positioning method based on self-checking learning

A technology of fault section and location method, applied in the direction of neural learning method, fault location, short-circuit test, etc., can solve the problems of unknown operating status and low search efficiency, so as to improve robustness, obvious fault characteristics, and avoid misjudgment Effect

Pending Publication Date: 2022-07-08
CHONGQING UNIV OF POSTS & TELECOMM
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to propose a method based on current transformers in the case of complex networks, that is, there are a large number of nodes to be detected with unknown operating states in the distribution network, and there are blind spots for fault location caused by various factors. (CT) The twin neural network (SNN) of power frequency polarity verification realizes the identification of abnormal points or pseudo similar points, and at the same time combines the binary search method (BS) to overcome the search efficiency brought about by the sequential polling judgment of the centralized management of the main station low problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fault section binary positioning method based on self-checking learning
  • Fault section binary positioning method based on self-checking learning
  • Fault section binary positioning method based on self-checking learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to express the objectives, technical solutions and advantages of the present invention more clearly, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.

[0032] The similarity judgment of the present invention for the upstream and downstream transient zero-sequence currents of the fault point is based on figure 1 The schematic diagram of the structure of the Siamese neural network consists of two branch networks, the structure and weight parameters of the two sub-networks are shared, and the feature vector is finally output through a similarity measurement module:

[0033] X 1 and X 2 For the two time series to be compared, they are respectively input into two neural networks that share the weight W. original sequence X i and X j Obtain a new vector Net(w, X through the nonlinear mapping of Network i ) and Net(w,X j ), w is the network share parameter.

[0034] Suppose Net...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of automation of a power system, and particularly discloses a fault section binary positioning method based on self-checking learning, which comprises the following steps: after a fault occurs, an acquisition terminal uploads an actual measurement signal to a master station, firstly, wavelet transform is utilized to complete time sequence synchronization of a waveform and polarity checking of a detection device; and a twin neural network is introduced to complete similarity judgment of upstream and downstream transient zero-sequence currents of a fault point, fault section positioning is realized, and finally, on the basis of a system network topology, a binary search method is used to quickly determine a minimum fault section. The method can effectively eliminate interference caused by operation errors of transmission time delay of communication equipment and reverse connection of a current transformer, adaptive learning of the twin neural network can reveal potential relations of data, the fault detection capability under the conditions of different grounding positions, grounding moments, transition resistances and the like is improved, a fast search algorithm is combined, and the fault detection efficiency is improved. The generalization of the neural network can be fully reflected, the calculation amount of the master station can be reduced, and the positioning efficiency is improved.

Description

technical field [0001] The present application belongs to the technical field of power system automation, and relates to a method for segment location of single-phase grounding faults in medium-voltage distribution networks. And quickly locate the faulty section. Background technique [0002] Electricity has always been the energy that people rely on for survival. In order to ensure the normal life of people, it is necessary to strengthen the construction of power grid projects and provide more reliable power guarantees. Therefore, when a fault occurs in the distribution network, rapid and accurate troubleshooting is still an important task that needs to be completed. Among them, the medium-voltage distribution network is widely used in urban and rural power distribution in my country. It is a bridge connecting terminal power users and large power grids, and is directly related to the power quality and power supply reliability of users. Among all the faults, the single-pha...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01R31/08G01R31/52G06N3/04G06N3/08
CPCG01R31/086G01R31/52G06N3/086G06N3/045Y04S10/52
Inventor 王毅李曙
Owner CHONGQING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products