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

Underground cable early fault detection and identification method based on DAE-CNN

A technology for underground cables and early faults, which is applied in the fault location, fault detection according to conductor type, and electrical measurement. High speed, wide use of space, high efficiency effect

Inactive Publication Date: 2021-08-03
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual power system, the circuit structure is complex, there is a strong correlation coupling relationship between components, and the operating conditions are uncertain. It is difficult to determine the appropriate threshold value according to the actual power system by using the threshold method; although the reasoning method does not need the threshold value, its Usually, wavelet transform and other signal processing methods are used to analyze the time-frequency domain characteristics of the fault signal, and based on this to infer the fault type, so it is highly targeted and difficult to generalize; using traditional classifiers to classify and identify disturbance signals shows performance is worse

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
  • Underground cable early fault detection and identification method based on DAE-CNN
  • Underground cable early fault detection and identification method based on DAE-CNN
  • Underground cable early fault detection and identification method based on DAE-CNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] This embodiment discloses a DAE-CNN-based underground cable early fault detection and identification method, such as figure 1 As shown, the steps are as follows:

[0078] S1. Simulate the early faults of underground cables to obtain current simulation data:

[0079] 1) According to the characteristics of several typical overcurrent disturbances of underground cables (cable half-cycle early faults, cable multi-cycle early faults, metallic short-circuit faults, transformer excitation inrush current, capacitor bank input, motor startup), in PSCAD / EMTDC and Laboratory Establish circuit models separately, and simulate current waveforms of different disturbance types to form a simulation data set;

[0080] 2) Normalize the simulation data:

[0081]

[0082] Among them, X i is the i-th data value in the simulation data set, X max is the maximum value of the data in the simulation data set, X min is the minimum value of the data in the simulation data set, X * is the n...

Embodiment 2

[0127] This embodiment discloses a DAE-CNN-based early fault detection and identification device for underground cables, which can realize the early fault detection and identification method for underground cables in Embodiment 1. The device includes a simulation module, a feature extraction module, a discriminator building module and a recognition module connected in sequence, and the feature extraction module is also connected to the recognition module;

[0128] Among them, the simulation module is used to simulate the early failure of the underground cable to obtain the simulation data of the current;

[0129] The feature extraction module is used to extract the features of the simulation data or the current data of the underground cable to be tested by using the noise reduction autoencoder to obtain the current data after dimension reduction;

[0130] The discriminator building block is used to train a convolutional neural network with dimensionality-reduced current data t...

Embodiment 3

[0134] This embodiment discloses a computer-readable storage medium, which stores a program. When the program is executed by a processor, the DAE-CNN-based underground cable early fault detection and identification method described in Embodiment 1 is implemented, specifically as follows:

[0135] Simulate the early faults of underground cables to obtain current simulation data;

[0136] Use the noise reduction autoencoder to extract the features of the simulation data, and obtain the current data after dimension reduction;

[0137] The convolutional neural network is trained using the dimensionally reduced current data to generate a discriminator that can be used to detect and identify early faults in underground cables;

[0138] A noise-reduction autoencoder is used to extract the features of the current data of the underground cable to be tested, and the dimension-reduced current data is obtained, which is used as the input of the discriminator, and the early fault identific...

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 an underground cable early fault detection and identification method based on a DAE-CNN. The method comprises the steps of carrying out the analog simulation of the early fault of an underground cable, so as to obtain the simulation data of a current, performing feature extraction on the simulation data by adopting a noise reduction automatic encoder to obtain dimension-reduced current data, training a convolutional neural network by using the current data after dimension reduction, and generating a discriminator which can be used for detecting and identifying an early fault of the underground cable, and performing feature extraction on the current data of the underground cable to be detected by adopting a noise reduction automatic encoder to obtain dimension-reduced current data, taking the dimension-reduced current data as the input of a discriminator, and outputting an early fault identification result of the underground cable by utilizing the discriminator. Accurate diagnosis of early faults of the power distribution network can be realized.

Description

technical field [0001] The invention relates to the technical field of early fault identification and signal processing of distribution networks, in particular to a DAE-CNN-based early fault detection and identification method for underground cables. Background technique [0002] At present, with the expansion of grid capacity and the increase of urban power consumption scale, underground power cables are widely used in power transmission and power distribution due to their advantages of small size, high safety and strong anti-interference. However, since the cable is laid underground for a long time, its insulating part (especially the position of the cable joint) is easily corroded by soil salt and moisture, resulting in local insulation defects. Early insulation defects will cause partial discharge of the cable, resulting in intermittent arc faults, and arc faults will further deteriorate the insulation of the cable, eventually leading to permanent failure of the cable. ...

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): G01R31/08
CPCG01R31/083G01R31/088G01R31/086
Inventor 季天瑶徐子弘李梦诗吴青华
Owner SOUTH CHINA UNIV OF TECH
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