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

Fault positioning method for mining traveling wave time-frequency domain characteristics by using deep learning

A technology of deep learning and fault location, which is applied in the field of power system, can solve the problems of large positioning error, positioning failure, and low reliability of traveling wave positioning, and achieve the effect of avoiding calculation errors and improving reliability and accuracy

Inactive Publication Date: 2021-06-11
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, fault traveling wave location methods are mainly divided into the following two types: time-domain information-based and frequency-domain information-based; the time-domain information-based traveling wave location method uses the arrival time of the initial traveling wave head and the second reflected wave head to calculate the fault location. Accurately detect the amplitude, polarity and arrival time of the initial traveling wave head, and correctly identify the nature of the subsequent refraction and reflection waveforms, which requires a high sampling rate, especially in high-impedance ground faults or voltage zero-crossing faults, it is difficult to detect weak wave head signal; the traveling wave location method based on frequency domain information, the fault location is performed according to the functional relationship between the main component of the natural frequency of the fault traveling wave and the fault location, the key of this method is to accurately extract the natural frequency component, but when the topology , the natural frequency is aliased, resulting in the inability to accurately extract the natural frequency
[0004] Existing traveling wave positioning methods are only based on time domain information or single frequency band information in frequency domain, resulting in low reliability of traveling wave positioning. In the case of high-resistance grounding faults, voltage zero-crossing faults, and faults at the exit of detection points, the actual positioning error is relatively large. large, or even location failure

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 positioning method for mining traveling wave time-frequency domain characteristics by using deep learning
  • Fault positioning method for mining traveling wave time-frequency domain characteristics by using deep learning
  • Fault positioning method for mining traveling wave time-frequency domain characteristics by using deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0035] The embodiment of the present invention discloses a fault location method using deep learning to mine time-frequency domain features of traveling waves, such as figure 1 Shown is the flow chart of the inventive method, comprises the following steps:

[0036] Step 1: Obtain the fault traveling wave line mode components under various fault conditions.

[0037] Specifically, the three-phase voltage traveling wave data detected at various positions on the ...

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 discloses a fault positioning method for mining traveling wave time-frequency domain characteristics by using deep learning, and relates to the technical field of power systems. The method specifically comprises the following steps: obtaining fault traveling wave line mode components under various fault conditions; performing continuous wavelet transform on the fault traveling wave line mode components to obtain fault traveling wave time-frequency domain distribution as a training set and a test set of deep learning; constructing a convolutional neural network, and training the convolutional neural network to obtain a mapping relation between the fault traveling wave time-frequency domain distribution and a fault position; performing continuous wavelet transform on voltage traveling wave data recorded when the power grid has an actual fault to obtain actual fault traveling wave time-frequency domain distribution; and inputting the actual fault traveling wave time-frequency domain distribution into the convolutional neural network to obtain an accurate fault point position. The method has the advantages of high positioning precision, no dependence on wave head accurate calibration, no need of selecting a wave velocity and the like.

Description

technical field [0001] The invention relates to the field of electric power systems, and more specifically relates to a fault location method for mining time-frequency domain characteristics of traveling waves by using deep learning. Background technique [0002] In the operation of the power system, the transmission line is responsible for the important task of power transmission and distribution. When the transmission line fails, the fault point should be quickly found to speed up the repair of the fault and reduce the loss of power failure. However, the distance of high-voltage transmission lines is long, and the method of manual line inspection to find fault points is inefficient and unreliable. Therefore, it is of great significance to develop an accurate and reliable transmission line fault location method to ensure the safe operation of the power system. [0003] Fault traveling wave has a fast response speed and is not affected by factors such as distributed capacit...

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): G01R31/08G06F17/14G06N3/04G06N3/08
CPCG01R31/085G01R31/088G06F17/148G06N3/08G06N3/045Y04S10/52
Inventor 邓丰曾哲张振黄懿菲冯思旭
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
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