CN-122016266-A - Online monitoring method, system, equipment and medium for mechanical characteristics of circuit breaker

CN122016266ACN 122016266 ACN122016266 ACN 122016266ACN-122016266-A

Abstract

The invention relates to the technical field of circuit breaker state monitoring, in particular to a method, a system, equipment and a medium for monitoring the mechanical characteristics of a circuit breaker on line, which comprise the steps of responding to an operation trigger signal of the circuit breaker and synchronously collecting the mechanical characteristic parameters and the electrical characteristic parameters of the circuit breaker; the method comprises the steps of preprocessing mechanical characteristic parameters and electrical characteristic parameters through intelligent monitoring IED, extracting time sequence features and frequency domain features for representing dynamic changes of the operation process of the circuit breaker, carrying out multi-mode feature fusion on data after preprocessing and feature extraction through a cloud analysis platform, carrying out fault analysis through a three-level diagnosis model, and predicting the residual service life of the circuit breaker through a degradation model based on a random process based on output and historical operation data of the diagnosis model. The method has the beneficial effects that the limitation of the traditional monitoring means is broken through, and the online iterative optimization of the diagnosis model is realized through the edge-cloud cooperative architecture, so that the fault recognition rate is more than 95%.

Inventors

DING JIAN
WANG BO
XIE RONGBIN
LIN CHENG
FU YUAN
CHEN LIN
ZHANG YIMING
LI WEI
HAO YUEFENG
LU XINGFU
CAO JUN
WANG YINGSHU
WANG XUN
Qiu Zhiang
LI HONGCAI

Assignees

贵州电网有限责任公司

Dates

Publication Date: 20260512
Application Date: 20251205

Claims (10)

1. The on-line monitoring method for the mechanical characteristics of the circuit breaker is characterized by comprising the following steps of, In response to an operation trigger signal of the circuit breaker, synchronously acquiring mechanical characteristic parameters and electrical characteristic parameters of the circuit breaker; Preprocessing the mechanical characteristic parameters and the electrical characteristic parameters through intelligent monitoring IED, and extracting time sequence characteristics and frequency domain characteristics for representing dynamic changes in the operation process of the circuit breaker; The data after preprocessing and feature extraction are subjected to multi-mode feature fusion through a cloud analysis platform, and a three-level diagnosis model is adopted for fault analysis; The remaining useful life of the circuit breaker is predicted by a stochastic process based degradation model based on the output of the diagnostic model and historical operational data.
2. The method for on-line monitoring of mechanical properties of a circuit breaker according to claim 1, wherein said three-level diagnostic model comprises, Based on a preset threshold rule, carrying out quick screening and first-stage diagnosis of alarming on the characteristic parameters; Performing a second level diagnosis of pattern recognition of the timing characteristics based on a long-short term memory network model; and carrying out third-level diagnosis of reasoning analysis on the association faults among different components based on the graph neural network model.
3. The method for on-line monitoring of mechanical properties of a circuit breaker according to claim 2, wherein the degradation model based on a random process is a Wiener process model; the Wiener process model is constructed and updated, including, Based on historical monitoring data, adopting a maximum likelihood estimation algorithm to update drift coefficients and diffusion coefficients of the model in real time; Setting a failure threshold of mechanical characteristics according to contact material characteristics and factory parameters of the circuit breaker; And based on the updated model parameters and the failure threshold value, obtaining the probability distribution of the residual service life according to inverse Gaussian distribution analysis.
4. The method for on-line monitoring mechanical properties of a circuit breaker according to claim 3, wherein the mechanical property parameters comprise moving contact travel and vibration signals; the electrical characteristic parameters comprise opening coil current, closing coil current and energy storage motor current.
5. The method for on-line monitoring mechanical characteristics of a circuit breaker as set forth in claim 4, wherein the preprocessing comprises performing differential calculation on a moving contact travel-time curve to obtain an opening and closing speed characteristic; The pretreatment further comprises fast Fourier transform analysis of the opening coil current, the closing coil current and the energy storage motor current so as to extract harmonic components of the current signals.
6. The method for on-line monitoring mechanical characteristics of a circuit breaker according to any one of claims 1-5, wherein the time synchronization accuracy of the synchronization acquisition is in microsecond level; the multi-mode sensing unit comprises a high-precision angular displacement sensor, a closed-loop Hall current sensor group and a vibration sensor.
7. The method for on-line monitoring mechanical characteristics of a circuit breaker according to claim 6, wherein the high-precision angular displacement sensor adopts a magnetic grating ruler structure and measures the rotation angle of an output spindle of an operating mechanism of the circuit breaker in a non-contact mode.
8. An on-line monitoring system for mechanical characteristics of a circuit breaker, applying the method according to any one of claims 1-7, characterized in that it comprises: The acquisition module is used for responding to an operation trigger signal of the circuit breaker and synchronously acquiring mechanical characteristic parameters and electrical characteristic parameters of the circuit breaker; the extraction module is used for preprocessing the mechanical characteristic parameters and the electrical characteristic parameters through intelligent monitoring IED and extracting time sequence characteristics and frequency domain characteristics for representing dynamic changes in the operation process of the circuit breaker; The analysis module is used for carrying out multi-mode feature fusion on the data after pretreatment and feature extraction through the cloud analysis platform, and carrying out fault analysis by adopting a three-level diagnosis model; And the prediction module is used for predicting the residual service life of the circuit breaker through a degradation model based on a random process based on the output of the diagnosis model and the historical operation data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.

Description

Online monitoring method, system, equipment and medium for mechanical characteristics of circuit breaker Technical Field The invention relates to the technical field of breaker state monitoring, in particular to a method, a system, equipment and a medium for on-line monitoring of mechanical characteristics of a breaker. Background High-voltage circuit breakers are critical protection and control devices in power systems, the reliability of their mechanical characteristics being directly related to the safe and stable operation of the power grid. For this reason, monitoring and diagnosing the mechanical state of a circuit breaker has been the focus of industry research. The traditional monitoring mode relies on a periodic off-line test, and cannot reflect the state of equipment under actual operation conditions. In recent years, with the development of sensing and communication technologies, online monitoring technologies have been gradually applied. However, the existing online monitoring technology has the problems that on one hand, the monitoring dimension is single, mechanical and electrical multidimensional characteristics in the operation process of the circuit breaker are difficult to comprehensively capture through a single sensor, so that state perception is incomplete, on the other hand, the degradation trend of the mechanical characteristics cannot be effectively evaluated, early fault early warning cannot be realized due to the lack of prospective life prediction capability, and the problems limit further improvement of the technical effect of online monitoring of the mechanical characteristics of the circuit breaker. Disclosure of Invention In order to solve the technical problems, the invention provides the following technical scheme: In a first aspect, the invention provides an on-line monitoring method for mechanical characteristics of a circuit breaker, which comprises the steps of responding to an operation trigger signal of the circuit breaker and synchronously collecting mechanical characteristic parameters and electrical characteristic parameters of the circuit breaker; Preprocessing mechanical characteristic parameters and electrical characteristic parameters through intelligent monitoring IED, and extracting time sequence characteristics and frequency domain characteristics for representing dynamic changes in the operation process of the circuit breaker; The data after preprocessing and feature extraction are subjected to multi-mode feature fusion through a cloud analysis platform, and a three-level diagnosis model is adopted for fault analysis; The remaining useful life of the circuit breaker is predicted by a stochastic process based degradation model based on the output of the diagnostic model and historical operational data. As a preferable scheme of the on-line monitoring method of the mechanical characteristics of the circuit breaker, the method comprises the following steps of three-level diagnosis models, including, Based on a preset threshold rule, carrying out quick screening and first-stage diagnosis of alarming on the characteristic parameters; Performing a second level diagnosis of pattern recognition of the timing sequence features based on the long-short term memory network model; and carrying out third-level diagnosis of reasoning analysis on the association faults among different components based on the graph neural network model. As a preferable scheme of the on-line monitoring method of the mechanical characteristics of the circuit breaker, the degradation model based on a random process is a Wiener process model; The Wiener process model is constructed and updated, including, Based on historical monitoring data, adopting a maximum likelihood estimation algorithm to update drift coefficients and diffusion coefficients of the model in real time; Setting a failure threshold of mechanical characteristics according to contact material characteristics and factory parameters of the circuit breaker; and obtaining the probability distribution of the residual service life according to the inverse Gaussian distribution analysis based on the updated model parameters and the failure threshold. As a preferable scheme of the on-line monitoring method for the mechanical characteristics of the circuit breaker, the invention comprises the following steps of mechanically-characterizing parameters including a moving contact stroke and a vibration signal; the electrical characteristic parameters comprise a brake opening coil current, a brake closing coil current and an energy storage motor current. The invention relates to a circuit breaker mechanical characteristic on-line monitoring method, which comprises the following steps of preprocessing, namely differential calculation of a travel-time curve of a moving contact to obtain a switching-on and switching-off speed characteristic; the pretreatment further comprises performing fast Fourier transform analysis on the opening coil current