CN-121978471-A - Method, system, equipment and medium for predicting ablation of breaker contact

CN121978471ACN 121978471 ACN121978471 ACN 121978471ACN-121978471-A

Abstract

The invention provides a prediction method, a system, equipment and a medium for circuit breaker contact ablation, wherein the method comprises the steps of collecting spectrum data of arc among circuit breaker contacts, processing the spectrum data through a first non-orthogonal Gaussian processor to obtain a first processing result, extracting wavelength domain parameters, wherein the first non-orthogonal Gaussian processor is a wavelength domain processor, processing the wavelength domain parameters through a second non-orthogonal Gaussian processor to obtain a second processing result, extracting time domain parameters, wherein the second non-orthogonal Gaussian processor is a time domain processor, obtaining quality loss parameters corresponding to the circuit breaker contacts, selecting solving parameters, substituting the quality loss parameters and the solving parameters into a linear regression model, and realizing prediction of circuit breaker contact ablation. The method and the device can effectively mine the characteristic spectral line information of the material elements in the spectrum, deduce the material ablation degree through analysis of the spectral information, and effectively improve the accuracy of predicting the ablation of the breaker contact.

Inventors

XU XINXIN
LI ZHANG
YIN CHUANG
LIU SHENG
LIU PENGCHENG
KANG HAIDONG
WANG DONG
XIE TONG
WANG TAI
XU XIANGYU
WANG YUEBIN
HAO WEIHAN
WU XUELONG
Zhuang Qinghan
ZHANG FAN
WANG JIANWU
HUANG YANG
LI HAORAN

Assignees

三峡新能源阳江发电有限公司
广东阳江市创源海上风电综合投资有限公司
中国长江三峡集团有限公司
中国能源建设集团广东省电力设计研究院有限公司

Dates

Publication Date: 20260505
Application Date: 20251229

Claims (10)

1. A method of predicting circuit breaker contact erosion, comprising: Collecting spectrum data of an arc between contacts of a circuit breaker; Processing the spectrum data through a first non-orthogonal Gaussian processor to obtain a first processing result, and extracting wavelength domain parameters based on the first processing result, wherein the first non-orthogonal Gaussian processor is a wavelength domain processor; Processing the wavelength domain parameters through a second non-orthogonal Gaussian processor to obtain a second processing result, and extracting time domain parameters based on the second processing result, wherein the second non-orthogonal Gaussian processor is a time domain processor; and selecting solving parameters from the time domain parameters and the wavelength domain parameters, substituting the mass loss parameters and the solving parameters into a preset linear regression model to obtain the contact mass loss of the breaker contact, and realizing the prediction of the ablation of the breaker contact.
2. The method of predicting circuit breaker contact ablation of claim 1, wherein the predetermined linear regression model comprises: ; Wherein C is a constant, beta n is a regression coefficient, P n is a solution parameter, n is the number of solution parameters, Is a loss of contact mass.
3. A method of predicting circuit breaker contact erosion as set forth in claim 1 wherein, the extracting the wavelength domain parameter based on the first processing result includes: performing xyz conversion on the first processing result to obtain relative strength; And performing HLS transformation on the first processing result to obtain a parameter dominant wavelength, effective signal intensity and equivalent signal width.
4. The method for predicting circuit breaker contact ablation according to claim 1, wherein the processing the spectral data by a first non-orthogonal gaussian processor obtains a first processing result, specifically: acquiring first response curves of three first non-orthogonal Gaussian processors in a parameter domain where spectral data are located; Processing the spectrum data through the first response curve to obtain the output of three first non-orthogonal Gaussian processors; the outputs of the three first non-orthogonal gaussian processors are determined as the first processing results.
5. The method of claim 4, wherein the three first non-orthogonal gaussian processors differ in center wavelength and are uniformly distributed over a predetermined wavelength range.
6. The method for predicting circuit breaker contact ablation according to claim 1, wherein the processing the wavelength domain parameters by a second non-orthogonal gaussian processor obtains a second processing result, specifically: Acquiring second response curves of parameter domains of the three second non-orthogonal Gaussian processors, wherein the parameters of the three second non-orthogonal Gaussian processors are in the parameter domains, and the peak time of the three second non-orthogonal Gaussian processors is different; processing the wavelength domain parameters through the second response curve to obtain the output of three second non-orthogonal Gaussian processors; the outputs of the three second non-orthogonal gaussian processors are determined as the second processing results.
7. A method of predicting circuit breaker contact erosion as claimed in any one of claims 1 to 6 wherein the collecting spectral data of the arc between circuit breaker contacts comprises: Acquiring sensor data of an arc between contacts of a circuit breaker through an optical fiber sensor; And analyzing the sensor data through a spectrometer to obtain the spectrum data.
8. A predicting system for circuit breaker contact ablation is characterized by comprising a spectrum data acquisition module, a wavelength domain parameter extraction module, a time domain parameter extraction module and a predicting module, wherein, The spectrum data acquisition module is used for acquiring spectrum data of electric arcs among the breaker contacts; The wavelength domain parameter extraction module is used for processing the spectrum data through a first non-orthogonal Gaussian processor to obtain a first processing result, and extracting wavelength domain parameters based on the first processing result, wherein the first non-orthogonal Gaussian processor is a wavelength domain processor; The time domain parameter extraction module is used for processing the wavelength domain parameters through a second non-orthogonal Gaussian processor to obtain a second processing result, and extracting time domain parameters based on the second processing result, wherein the second non-orthogonal Gaussian processor is a time domain processor; The prediction module is used for acquiring mass loss parameters corresponding to the breaker contacts, selecting solving parameters from the time domain parameters and the wavelength domain parameters, substituting the mass loss parameters and the solving parameters into a preset linear regression model to acquire the contact mass loss of the breaker contacts, and realizing the prediction of the ablation of the breaker contacts.
9. A terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing a method of predicting circuit breaker contact ablation according to any one of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the method of predicting the erosion of a circuit breaker contact according to any one of claims 1 to 7.

Description

Method, system, equipment and medium for predicting ablation of breaker contact Technical Field The invention relates to the field of breaker contact ablation prediction, in particular to a breaker contact ablation prediction method, a breaker contact ablation prediction system, breaker contact ablation prediction equipment and a breaker contact ablation prediction medium. Background The high-voltage SF 6 circuit breaker is key protection equipment of an electric power system, an arc contact is acted by arc energy in the current breaking process, material vaporization and liquid drop splashing can occur, quality loss and surface morphology degradation are caused, and finally the breaking capacity of the equipment is reduced. The current contact ablation prediction research presents a development situation based on multi-source data acquisition and fusion and with an advanced algorithm model as a core. At present, the existing method mainly depends on electrical parameters or mechanical parameters, the ablation quantity is indirectly and reversely deduced, the method for predicting the contact ablation ignores the influence of material elements in an arc spectrum, the prediction error exceeds 30% under the working condition of high current, and the requirement of equipment state maintenance on precision cannot be met. The prediction of contact ablation is therefore problematic in that it is less accurate. Disclosure of Invention The invention provides a method, a system, equipment and a medium for predicting the ablation of a circuit breaker contact, which are used for solving the technical problem of how to improve the accuracy of the prediction of the ablation of the circuit breaker contact. In order to solve the technical problems, the application of the invention provides a method for predicting ablation of a breaker contact, which comprises the following steps: Collecting spectrum data of an arc between contacts of a circuit breaker; Processing the spectrum data through a first non-orthogonal Gaussian processor to obtain a first processing result, and extracting wavelength domain parameters based on the first processing result, wherein the first non-orthogonal Gaussian processor is a wavelength domain processor; Processing the wavelength domain parameters through a second non-orthogonal Gaussian processor to obtain a second processing result, and extracting time domain parameters based on the second processing result, wherein the second non-orthogonal Gaussian processor is a time domain processor; and selecting solving parameters from the time domain parameters and the wavelength domain parameters, substituting the mass loss parameters and the solving parameters into a preset linear regression model to obtain the contact mass loss of the breaker contact, and realizing the prediction of the ablation of the breaker contact. Preferably, the preset linear regression model includes: ; Wherein C is a constant, beta n is a regression coefficient, P n is a solution parameter, n is the number of solution parameters, Is a loss of contact mass. Preferably, the extracting the wavelength domain parameter based on the first processing result includes: performing xyz conversion on the first processing result to obtain relative strength; And performing HLS transformation on the first processing result to obtain a parameter dominant wavelength, effective signal intensity and equivalent signal width. Preferably, the processing, by the first non-orthogonal gaussian processor, the spectral data obtain a first processing result, specifically: acquiring first response curves of three first non-orthogonal Gaussian processors in a parameter domain where spectral data are located; Processing the spectrum data through the first response curve to obtain the output of three first non-orthogonal Gaussian processors; the outputs of the three first non-orthogonal gaussian processors are determined as the first processing results. Preferably, the center wavelengths of the three first non-orthogonal gaussian processors are different and are uniformly distributed in a preset wavelength range. Preferably, the processing, by the second non-orthogonal gaussian processor, the wavelength domain parameter to obtain a second processing result, specifically: Acquiring second response curves of parameter domains of the three second non-orthogonal Gaussian processors, wherein the parameters of the three second non-orthogonal Gaussian processors are in the parameter domains, and the peak time of the three second non-orthogonal Gaussian processors is different; processing the wavelength domain parameters through the second response curve to obtain the output of three second non-orthogonal Gaussian processors; the outputs of the three second non-orthogonal gaussian processors are determined as the second processing results. Preferably, the collecting spectral data of the arc between the contacts of the circuit breaker includes: Acquiring sensor data