CN-122017503-A - GIS defect detection method and system based on X-ray intensity self-adaptive regulation and control

CN122017503ACN 122017503 ACN122017503 ACN 122017503ACN-122017503-A

Abstract

The invention discloses a GIS defect detection method and a GIS defect detection system based on self-adaptive regulation and control of X-ray intensity. The process preferably ensures radiation safety, and intelligently switches to an enhanced excitation mode or an optimized adjustment mode according to the intensity of the partial discharge signal detected in real time so as to dynamically update the intensity of the X-rays, thereby effectively exciting latent defects or searching an optimal working point. And when the signal and the intensity change meet the convergence condition, the regulation and control are completed. And then based on the discharge signal excited by the optimal intensity, the defect type and the position are automatically judged. The invention overcomes the limitation of the traditional fixed dose method, obviously improves the sensitivity of early detection of defects, and realizes the optimal balance of radiation safety and detection efficiency.

Inventors

WU SHIYOU
XIAO LIRONG
DING DENGWEI
Qiu Riqiang
GONG ZHENZHOU
LIU XUANDONG
LIN ZHIYUAN
GE YINING
YAN WENQING
CHENG MENGYING
LONG GUOHUA

Assignees

国网江西省电力有限公司南昌供电分公司
国网江西省电力有限公司
西安交通大学
国网江西省电力有限公司电力科学研究院
清华四川能源互联网研究院

Dates

Publication Date: 20260512
Application Date: 20260413

Claims (10)

1. A GIS defect detection method based on self-adaptive regulation and control of X-ray intensity is characterized by comprising the following steps: Step S1, setting initial X-ray intensity, inputting safety parameters of GIS equipment and a safety convergence threshold, wherein the safety parameters comprise a safety radiation dose threshold and a discharge quantity threshold, and the safety convergence threshold comprises an average discharge quantity convergence tolerance threshold and an X-ray intensity convergence tolerance threshold; step S2, setting an X-ray intensity updating principle, and executing the multi-mode self-adaptive regulation and control flow of the step S3-step S5 based on the X-ray intensity updating principle; step S3, performing radiation safety control, monitoring the current radiation dose in real time, if the current radiation dose is more than or equal to a safety radiation dose threshold value, immediately reducing the X-ray intensity to a minimum allowable value, and re-executing the step S3, otherwise, entering the step S4; s4, according to comparison of the average discharge capacity of the partial discharge signals detected in real time and a discharge capacity threshold value, different modulation strategies are executed to update the X-ray intensity; Step S5, checking whether the change of the average discharge amount before and after iteration and the change of the X-ray intensity are smaller than an average discharge amount convergence tolerance threshold value and an X-ray intensity convergence tolerance threshold value or not, if yes, judging that the X-ray intensity is converged to an optimal working point, completing self-adaptive regulation and control, and entering a step S6, otherwise, returning to the step S2 to continue iterative regulation and control; And S6, outputting the final X-ray intensity converged to the optimal working point after self-adaptive regulation, continuously exciting the GIS equipment by using the intensity, inducing a partial discharge signal, extracting characteristic parameters of the partial discharge signal, and realizing automatic judgment of the defect position by using a time difference method.
2. The GIS defect detection method based on the adaptive regulation and control of the X-ray intensity according to claim 1, wherein the step S4 comprises the following steps: Step S4.1, if the average discharge amount of the partial discharge signal is lower than a discharge amount threshold and the current radiation dose is lower than a safe radiation dose threshold, entering an enhanced excitation mode, calculating a preliminary intensity correction amount by a proportional-integral controller based on the error of the current discharge signal and a target value, and fusing a fourth-order Dragon-Kutta method and an Adam prediction-correction method to improve control precision and dynamically enhance X-ray intensity; And step S4.2, if the average discharge amount of the partial discharge signals is higher than or equal to a discharge amount threshold value, entering an optimization adjustment mode, wherein the optimization adjustment mode gradually adjusts the X-ray intensity to the minimum effective level of the identification defect by constructing a multi-objective optimization function for comprehensively balancing the signal quality, the radiation safety and the equipment energy consumption and performing iterative optimization by utilizing an intelligent optimization algorithm based on gradient descent.
3. The GIS defect detection method based on the adaptive regulation and control of the X-ray intensity according to claim 2, wherein the enhanced excitation mode specifically comprises the following steps: s4.11, calculating a discharge quantity error at the current moment based on the average discharge quantity and a discharge quantity threshold value of the partial discharge signals, and calculating a preliminary X-ray intensity correction quantity based on a proportional-integral controller; step S4.12, regarding the preliminary X-ray intensity correction output by the proportional-integral controller as a function of the X-ray intensity with respect to time; Step S4.13, applying a fourth-order Dragon-Kutta method, and sequentially calculating four intermediate slope values based on the current X-ray intensity, the time step and the function of the X-ray intensity on time; s4.14, carrying out weighted average on the slope to obtain a predicted value of the X-ray intensity; S4.15, calculating corrected control output by using an Adam prediction-correction method based on the predicted value of the X-ray intensity; S4.16, estimating the error of the slope of the last step under the current step length based on the corrected control output; Step S4.17, adaptively adjusting the time step according to the relation between the error of the slope of the last step under the current step and a preset tolerance threshold; and S4.18, updating the X-ray intensity by using the self-adaptive adjusted time step and the corrected control output to finish the iteration.
4. The GIS defect detection method based on the adaptive regulation and control of the X-ray intensity according to claim 3, wherein the optimization adjustment mode specifically comprises the following steps: Step S4.21, establishing a multi-objective function for balancing partial discharge signal quality, radiation safety and equipment energy consumption; S4.22, calculating a gradient of a multi-objective function, and calculating four intermediate gradient stepping values based on the current X-ray intensity, the learning rate and the time step by applying a fourth-order Dragon-Kutta method; step S4.23, carrying out weighted average on the four intermediate gradient stepping values to obtain a predicted value of the X-ray intensity; And S4.24, judging whether the multi-objective function value is smaller than that before iteration, if yes, adopting the predicted value of the X-ray intensity in the step S4.23, and if not, maintaining the original X-ray intensity.
5. The method for detecting GIS defects based on adaptive adjustment and control of X-ray intensity according to claim 4, wherein four intermediate slope values are calculated in sequence based on the current X-ray intensity, the time step and the function of the X-ray intensity with respect to time by using a fourth-order Longgar-Kutta method, and are expressed as: ; ; ; ; In the formula, Represents the 1 st intermediate slope value; represents the 2 nd intermediate slope value; Represents the 3 rd intermediate slope value; Represents the 4 th intermediate slope value; a time step representing a numerical integration; Represent the first Intensity of X-rays after a number of iterations With respect to time Is a function of (2); calculating a gradient of a multi-objective function, and calculating four intermediate gradient step values based on the current X-ray intensity, the learning rate and the time step by applying a fourth-order Dragon-Kutta method, wherein the four intermediate gradient step values are expressed as follows: ; ; ; ; In the formula, Representing the 1 st intermediate gradient step value; representing the 2 nd intermediate gradient step value; representing the 3 rd intermediate gradient step value; representing the 4 th intermediate gradient step value; Representing a learning rate; Representing a multi-objective function gradient.
6. The GIS defect detection method based on the adaptive regulation and control of the X-ray intensity according to claim 5, wherein the specific process of the step S6 is as follows: Step S6.1, under the continuous excitation of the final X-ray intensity, collecting partial discharge signals induced by GIS equipment, and extracting characteristic parameters for positioning, wherein the characteristic parameters comprise the space coordinates of a plurality of sensors arranged around the GIS equipment, the time when each sensor receives the partial discharge signals, and the propagation speed of the partial discharge signals in the GIS equipment; Step S6.2, performing defect space positioning on the extracted characteristic parameters by using a time difference method, firstly, selecting a1 st sensor as a reference sensor, acquiring the time when the reference sensor receives a partial discharge signal as a reference time, then, for each other sensor, calculating the time difference of the time when the partial discharge signal is received relative to the reference time, according to the characteristic that the partial discharge signal uniformly propagates in GIS equipment, establishing a hyperbola equation set according to the condition that the distance difference between the discharge source position and the space coordinates of each sensor is equal to the product of the propagation speed and the time difference, and finally, solving the hyperbola equation set by using a least square method to obtain the space coordinates of the final discharge position, thereby realizing automatic judgment of the defect position.
7. The method for detecting the GIS defects based on the adaptive adjustment and control of the X-ray intensity according to claim 6, wherein the X-ray intensity updating principle is that the next X-ray intensity is equal to the current X-ray intensity plus a correction amount.
8. A GIS defect detection system based on adaptive regulation of X-ray intensity, for executing the GIS defect detection method based on adaptive regulation of X-ray intensity according to any one of claims 1 to 7, comprising: The GIS parameter input module is used for executing: Setting an initial X-ray intensity based on the input electrical parameters and the measured structural parameters; Inputting safety parameters and safety convergence threshold values of GIS equipment; An adaptive control module for performing: setting an X-ray intensity updating principle, and executing a multi-mode self-adaptive regulation and control flow based on the X-ray intensity updating principle; Performing radiation safety control, monitoring the current radiation dose in real time, if the current radiation dose is more than or equal to a safety radiation dose threshold value, immediately reducing the X-ray intensity to an allowable minimum value, and re-performing the radiation safety control, otherwise, performing different modulation strategies to update the X-ray intensity according to the comparison of the average discharge amount of the partial discharge signals detected in real time and the discharge amount threshold value; Checking whether the change of the average discharge amount before and after iteration and the change of the X-ray intensity are smaller than the convergence tolerance threshold of the average discharge amount and the convergence tolerance threshold of the X-ray intensity or not, if so, judging that the X-ray intensity is converged to an optimal working point, and completing self-adaptive regulation, otherwise, continuing the iterative regulation; A partial discharge detection module for performing: outputting the final X-ray intensity converged to the optimal working point after self-adaptive regulation, continuously exciting the GIS equipment by using the intensity, inducing a partial discharge signal, extracting characteristic parameters of the partial discharge signal, and realizing automatic judgment of the defect position by using a time difference method.
9. An electronic device, comprising a processor, a memory and a bus, wherein the processor and the memory are connected through the bus, the memory is used for storing a set of program codes, and the processor is used for calling the program codes stored in the memory to execute the GIS defect detection method based on the adaptive regulation and control of the X-ray intensity according to any one of claims 1-7.
10. A non-volatile computer storage medium storing computer executable instructions for performing a GIS defect detection method based on adaptive regulation of X-ray intensity according to any one of claims 1 to 7.

Description

GIS defect detection method and system based on X-ray intensity self-adaptive regulation and control Technical Field The invention relates to the technical field of GIS detection, in particular to a GIS defect detection method and system based on self-adaptive regulation and control of X-ray intensity. Background Gas insulated metal-enclosed switchgear (GIS) is one of the key and core devices of the electrical grid. The existing partial discharge detection technology has low detection sensitivity to latent defects such as tiny bubbles in the GIS equipment insulator and high omission rate. Under the current background of the accelerated development of the global power system to ultra-high voltage and large capacity, the long-term latent insulation defect in the GIS is gradually evolved into a systematic risk threatening the safe and stable operation of the whole power grid. With the continuous increase of the operating voltage level and the increasing complexity of the equipment structure, the electro-thermal-mechanical multi-physical field stress born by the GIS internal insulation system is obviously enhanced, so that the dangers of early micro defects which are difficult to detect, such as micro bubbles remained in the manufacturing process, interface weak points of solid insulation parts, particulate pollutants introduced in the assembling process and the like, are greatly amplified. Such defects are in a latent state under a long-term operating voltage, but partial discharge activity caused by the defects gradually deteriorates insulation performance with time, and finally, insulation breakdown can be caused, and even cascading failures are caused. The micro-defect-induced discharge is one of the main factors of GIS insulation failure, so that the evolution mechanism, early diagnosis and effective intervention of the GIS latent insulation defect become important leading problems and urgent technical requirements in the field of ultra-high voltage network insulation reliability research. The X-ray excitation technology injects enough high-energy electrons into the insulation defect area through external irradiation, so that the statistical time delay of discharge formation is effectively shortened, and the partial discharge starting voltage is obviously reduced on a macroscopic level. The technology is used as a non-invasive external excitation means, and can effectively excite the insulation defect which is in a latent state originally on the premise of maintaining the existing operating voltage of the GIS, and induce to generate an artificial partial discharge signal with detectability. The process not only improves the identification probability of early insulation defects, but also provides important basis for state evaluation, overhaul and maintenance of equipment. However, the traditional X-ray excitation method mostly adopts fixed dose output, and cannot be automatically adjusted according to different voltage levels, shell thicknesses and detection targets of the GIS equipment, so that the dose is insufficient or excessive under partial conditions, the detection sensitivity is affected, and the radiation risk is increased. Patent publication CN120539190a discloses a method for detecting internal defects of GIS using X-rays as an excitation source, but the method does not propose a method for adjusting the intensity of the X-rays. In conclusion, the existing GIS internal defect detection method is insufficient in sensitivity, passive in defect identification and weak in active regulation and control capability on defect characteristics, and cannot meet the requirement of intelligent operation and maintenance on accurate prediction of equipment states. Disclosure of Invention Aiming at the defects of the prior art, the invention provides a GIS defect detection method and system based on self-adaptive regulation and control of X-ray intensity, and aims to solve the problems in the background art. In order to achieve the purpose, the invention provides the technical scheme that the GIS defect detection method based on the self-adaptive regulation and control of the X-ray intensity comprises the following steps: Step S1, setting initial X-ray intensity, inputting safety parameters of GIS equipment and a safety convergence threshold, wherein the safety parameters comprise a safety radiation dose threshold and a discharge quantity threshold, and the safety convergence threshold comprises an average discharge quantity convergence tolerance threshold and an X-ray intensity convergence tolerance threshold; step S2, setting an X-ray intensity updating principle, and executing the multi-mode self-adaptive regulation and control flow of the step S3-step S5 based on the X-ray intensity updating principle; step S3, performing radiation safety control, monitoring the current radiation dose in real time, if the current radiation dose is more than or equal to a safety radiation dose threshold value, immediately re