An artificial intelligence identification method for the external fault of the commutation bus of the hvdc system

A technology for commutating busbars and external faults, applied in measurement devices, instruments, biological neural network models, etc., can solve the problems of stable operation of AC and DC systems, system operation collapse, hazards, etc., achieves good model classification capabilities, and is easy to implement , the effect of high reliability

Active Publication Date: 2016-11-30
STATE GRID CORP OF CHINA +2
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In some cases, commutation failure may recover by itself, but continuous commutation failure may cause the DC transmission system to block, and even endanger the stability of the entire system, causing greater harm
In the AC-DC hybrid operation system, the voltage collapse and the voltage oscillation caused by the control will cause the permanent commutation failure of the inverter
[0004] The multi-infeed DC transmission system has a larger transmission capacity and a more flexible operation mode, so the interaction between converter stations is more sensitive to commutation failure. The commutation failure of a converter station will not only cause its own DC The voltage fluctuation of the system may also cause commutation failure in multiple nearby converter stations, which will directly affect the stable operation of the AC and DC system, and even cause the entire system to collapse.

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
  • An artificial intelligence identification method for the external fault of the commutation bus of the hvdc system
  • An artificial intelligence identification method for the external fault of the commutation bus of the hvdc system
  • An artificial intelligence identification method for the external fault of the commutation bus of the hvdc system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] combine figure 1 , which illustrates the flow chart of the artificial intelligence identification method for the external faults of the HVDC system converter bus. identify.

[0036] 1. The structure of BP neural network

[0037] 1. Select the fault signal

[0038] When the HVDC AC system fails, electrical quantities such as commutation voltage, DC voltage, DC current and firing angle will all change suddenly. In this embodiment, the DC voltage U on the inverter side is selected d as a fault signal. Select respectively the DC voltage signal U d , as training samples for the neural network. Among them, the different operating modes of the system mainly include: A, the bipolar wiring operation mode of the system; B, the single pole ground circuit operation mode of the system; C, the full voltage operation mode; D, the step-down operation mode (20%, 30% step-down) ; E, bipolar unbalanced operation mode. N1, F1~F4 faults mainly refer to: N1-normal state; F1-single-ph...

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 an artificial intelligence identification method for an external fault of a commutation bus in an HVDC system. Its characteristic is that the method uses wavelet transform multi-scale decomposition algorithm to decompose system fault signals into different frequency bands, uses wavelet energy skewness of signals in different frequency bands as fault diagnosis feature vectors, and combines BP neural network to realize accurate identification of AC system fault types. Compared with the previous AC system fault type identification method, this method only needs to extract the feature of one fault signal from the perspective of energy distribution, and is not affected by the system operation mode. It is simple to operate, has good accuracy and high reliability.

Description

technical field [0001] The invention relates to an artificial intelligence identification method for external faults of a commutation bus in an HVDC system, and belongs to the field of high-voltage direct current transmission. Background technique [0002] The operation of the HVDC (high voltage direct current) transmission system is affected by the failure of the DC line, converter or AC system. In order to ensure the safe and reliable operation of the entire AC and DC system, it is necessary to detect the existence, type and occurrence of the fault at the initial stage of the fault. s position. [0003] The influence of the AC system fault on the DC system is effected by the change of the commutation voltage applied to the converter. When the AC system fails, the rate, amplitude and phase of the AC voltage drop will affect the operation of the DC system. When the AC system on the inverter side fails, the AC bus voltage of the inverter station decreases, which reduces the...

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 Patents(China)
IPC IPC(8): G01R31/00G06N3/02
Inventor 王渝红朱艳贺兴容徐卫张彪宋梁张旭波范强丁志林邱大强高锦锋
Owner STATE GRID CORP OF CHINA
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