Combined electrical appliance partial discharge defect diagnosis method and system

A combination of electrical appliances and partial discharge technology, applied in the direction of neural learning methods, instruments, measuring electricity, etc., can solve the problems of misjudgment and missed judgment by inspectors, many interference factors, and complicated live detection work, so as to improve maintenance efficiency and accuracy rate effect

Pending Publication Date: 2020-12-04
DONGYING POWER SUPPLY COMPANY STATE GRID SHANDONG ELECTRIC POWER +1
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1) The performance of testing instruments of different manufacturers and models varies greatly, and the types and formats of data storage are different. Different forms of unstructured data are exported, and deep neural networks are directly used for fitting training. The accuracy and adaptability of the algorithm are difficult to meet the actual situation. demand; traditional statistical analysis techniques cannot realize the management and application of such data
[0005] 2) The PD detection work is relatively complicated, and there are a large number of interference signals around the GIS, which leads to misjudgments and missed judgments by the detection personnel. The reliability of the detection results largely depends on the professional level of the detection personnel, which seriously restricts the partial discharge detection work of combined electrical

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
  • Combined electrical appliance partial discharge defect diagnosis method and system
  • Combined electrical appliance partial discharge defect diagnosis method and system
  • Combined electrical appliance partial discharge defect diagnosis method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] In one or more embodiments, a method for diagnosing partial discharge defects of a combination electrical appliance is disclosed, including feature map library modeling and CNN-based partial discharge pattern recognition.

[0038] Among them, the characteristic map library is modeled, and the data source is to collect the live detection data of 55 substations of a power supply company from 2015 to 2018, and obtain the detection map of substation combined electrical appliances in the actual operating environment, including tip discharge, internal air gap discharge of insulating parts, along the surface Defect types such as electrical discharges, levitating discharges, free metal particles, and disturbances.

[0039] During on-site detection, the pulse phase diagram (PRPD) and pulse sequence phase diagram (PRPS) of UHF partial discharge signals were collected in 55 substations by using partial discharge inspection instruments and oscilloscopes. The partial discharge defec...

Embodiment 2

[0069] In one or more embodiments, a device for diagnosing partial discharge defects of combined electrical appliances is disclosed, including:

[0070] The defect identification module is used to input the obtained ultra-high frequency partial discharge map of the substation combined electrical appliance to be tested into the trained convolutional neural network model, and output the defect identification result;

[0071] The defect cause matching module is used to match the defect identification result with the knowledge base to obtain the cause of the defect and the processing principle;

[0072] The neural network model training module is used to train the convolutional neural network model through a pre-built map library; the map library includes a number of substation combined electrical appliance detection map data sets with label information; the knowledge base includes different defect types corresponding to Causes of defects and handling principles.

[0073] The spe...

Embodiment 3

[0075] In one or more embodiments, a terminal device is disclosed, including a server, the server includes a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor executes the The program implements the method for diagnosing partial discharge defects of combined electrical appliances in Embodiment 1. For the sake of brevity, details are not repeated here.

[0076] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

[0077] The memory may include read-only ...

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 combined electrical appliance partial discharge defect diagnosis method and system. The combined electrical appliance partial discharge defect diagnosis method comprises thesteps of: inputting an obtained ultrahigh-frequency partial discharge map of a to-be-detected transformer substation combined electrical appliance into a trained convolutional neural network model, and outputting a defect recognition result; and matching the defect identification result with a knowledge base to obtain a reason and a processing principle for forming the defect, wherein the convolutional neural network model is trained through utilizing a pre-constructed atlas library, and the atlas library comprises a plurality of substation combined electrical appliance detection atlas data sets with annotation information, and the knowledge base comprises defect reasons and processing principles corresponding to different defect types. According to the combined electrical appliance partial discharge defect diagnosis method and the system, an improved VGG16 structure is adopted, a transfer learning mode is utilized, model parameters of a convolution layer, a pooling layer and a full connection layer are optimized through utilizing VGG16 network model parameters, identification of a partial discharge map type is achieved, and the accuracy rate of a partial discharge mode can be improved.

Description

technical field [0001] The invention relates to the technical field of partial discharge detection of gas-insulated combined electrical appliances, in particular to a method and system for diagnosing partial discharge defects of combined electrical appliances. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Gas Insulated Switchgear (GIS for short) is one of the key equipment of the power grid with SF6 gas as the insulating medium. With the increasing proportion of GIS in the power grid and the development of partial discharge detection of combined electrical appliances, the following problems exist in GIS UHF partial discharge detection: [0004] 1) The performance of testing instruments of different manufacturers and models varies greatly, and the types and formats of data storage are different. Different forms of unstructured data are e...

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
IPC IPC(8): G01R31/12G06N3/04G06N3/08
CPCG01R31/1254G06N3/08G06N3/045
Inventor 张聪聪高栋王刚陈晨路铭王佳辉王大鹏牛卫光李景生丁新勇
Owner DONGYING POWER SUPPLY COMPANY STATE GRID SHANDONG ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products