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

High-voltage AC line intelligent fault diagnosis method and system based on VGG16 algorithm

A high-voltage communication and fault diagnosis technology, applied in fault locations, neural learning methods, biological neural network models, etc., can solve the problems of lack of samples, long time-consuming diagnosis, relying on manual diagnosis, etc., to achieve accurate and reliable results, easy to implement, rich effect of experience

Pending Publication Date: 2022-07-29
ELECTRIC POWER RES INST OF STATE GRID ANHUI ELECTRIC POWER +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The technical problem to be solved by the present invention is how to solve the technical problems of lack of samples, long time-consuming diagnosis and relying on manual diagnosis

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
  • High-voltage AC line intelligent fault diagnosis method and system based on VGG16 algorithm
  • High-voltage AC line intelligent fault diagnosis method and system based on VGG16 algorithm
  • High-voltage AC line intelligent fault diagnosis method and system based on VGG16 algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] like figure 1 As shown, the idea of ​​this method is to analyze the current waveform when the AC line is faulty, and use the VGG16 algorithm to simulate the method of analyzing the waveform of the human eye for diagnosis, which is in line with the process and idea of ​​artificial fault diagnosis. A large number of AC faults are analyzed and learned, and the diagnosis results are obtained by analyzing the changing trend of the waveform. The trend analysis steps of the waveform include:

[0075] S1. Input the current waveforms at the beginning and end of the line into the trained VGG16 network;

[0076] S2. Use the VGG16 algorithm to analyze the double-terminal current waveform, and obtain the diagnosis result according to the change trend in the double-terminal current waveform:

[0077] S3. Get the fault in the area;

[0078] S4. Get the fault outside the area;

[0079] S5. Acquire the fault or normal operation of the transmission line when the capacitor current is to...

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 provides a VGG16 algorithm-based high-voltage AC line intelligent fault diagnosis method and system, and the method comprises the steps: building a fault model according to a double-end power supply system schematic diagram shown in a figure 3, where Zm and Zn are power supply equivalent impedance, f is system frequency, l1 is the length of a line in a fault region, and l2 is the length of a line outside the fault region; building a high-voltage alternating-current line simulation model in power system simulation software MATLAB (Matrix Laboratory); setting and operating different working conditions in the established simulation model, and acquiring double-end current data of the power transmission line under the corresponding working conditions; and inputting the current data at the head end and the tail end generated in the step 3 into an MATLAB program to draw a picture, and drawing the current at the two ends on the same picture. The sample can be used as a VGG16 network training and testing sample; and each output type generates enough samples, and then the samples are input into the VGG16 network for training and testing. The technical problems of lack of samples, long diagnosis time and dependence on manual diagnosis are solved.

Description

technical field [0001] The invention relates to an intelligent fault diagnosis method for high-voltage AC lines, in particular to a high-voltage AC line intelligent fault diagnosis method and system based on VGG16 algorithm. Background technique [0002] High-voltage AC transmission lines are an important link in the transmission of electric energy in the power system. The transmission distance is long and the transmission environment is complex, and various faults are inevitably prone to occur. The failure of transmission lines will have a great impact on the security and stability of the power system, and bring serious consequences to all sectors of the national economy and people's daily life. Therefore, it is necessary to strengthen the analysis and research on the fault diagnosis of high-voltage AC lines, so that when the AC line fails, it can be solved in the shortest time and the loss can be minimized. [0003] When the power grid is in a fault state, especially when...

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): G01R31/08G06F30/27G06N3/08
CPCG01R31/085G01R31/088G06F30/27G06N3/08Y04S10/52
Inventor 汪勋婷丁津津孙辉张峰龚庆武彭勃石孝承乔卉张豪杰刘栋
Owner ELECTRIC POWER RES INST OF STATE GRID ANHUI ELECTRIC POWER
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