Converter station insulating sleeve defect identification method and system

Abstract

The invention discloses a converter station insulating sleeve defect identification method and system, and the method comprises the steps: carrying out the alignment processing of the obtained temperature data and field intensity data of a to-be-identified insulating sleeve, obtaining first temperature data and first field intensity data, and if the first temperature data and the first field intensity data meet a judgment condition, carrying out the identification of the defects of the to-be-identified insulating sleeve based on the first temperature data; calculating to obtain a radial gradient, an axial gradient and a temperature anomaly index based on the first field intensity data, calculating to obtain an electric field anomaly index based on the first field intensity data, and calculating to obtain an electric field temperature ratio according to the first temperature data and the first field intensity data; and according to the radial gradient, the axial gradient, the temperature anomaly index, the electric field anomaly index and the electric field temperature ratio, performing calculation by using a scoring model to obtain a score of each defect type, and selecting the defect type with the maximum score as a defect identification result of the to-be-identified insulating sleeve. According to the method, the defect detection precision of the converter station insulating sleeve is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of temperature monitoring technology for high-voltage direct current converter stations, and in particular to a method and system for identifying defects in the insulating bushings of converter stations. Background Technology

[0002] High-voltage direct current (HVDC) converter stations are widely used for long-distance, high-capacity power transmission, and their safe and stable operation depends on the insulation performance of the bushings. Oil-immersed bushings typically consist of a porcelain bushing, an insulating core, and an outer metal casing, filled with insulating oil to achieve uniform electric field distribution and heat conduction. With increased operating time and the influence of environmental factors, the following typical defects are prone to occur inside the bushing: 1) Moisture absorption: The insulating oil or paper insulation inside the bushing contains water due to environmental humidity or manufacturing processes, forming localized moisture accumulation, altering the dielectric constant, and causing electric field distortion. 2) Defects on the surface of the conductive rod: Scratches, metal particle adhesion, or corrosion on the surface of the conductive rod lead to partial discharge or abnormal electrothermal concentration. 3) Simulated creepage due to metal deposits or "metal lamination" marks on the inner wall of the porcelain bushing: The deposition of metal impurities or the formation of "metal lamination" marks on the inner wall of the porcelain bushing simulates creepage paths, enhancing the current path along the surface of the porcelain bushing and generating localized hot spots. 4) Grounding failure, also known as emulation of poor soldering and grounding in the bushing structure, occurs when the grounding shield or bushing connection is loose or the solder joint is poorly soldered, leading to grounding failure of the equipotential ring, resulting in localized sudden changes in electric field strength and accompanied by abnormal temperatures. Therefore, it is necessary to monitor the inside of the bushing to improve early warning capabilities.

[0003] However, in existing solutions, a small number of FBGs (Fiber Bragg Gratings) are usually arranged only on a single cross section at the top of the sleeve, and the calibrated curves do not take into account the complex internal structure of the sleeve. This leads to errors and low accuracy when identifying defects in oil-immersed sleeves. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method and system for identifying defects in the insulating bushings of converter stations, thereby resolving the issue of low accuracy in temperature monitoring of oil-immersed bushings in existing technologies.

[0005] A first aspect of this invention provides a method for identifying defects in the insulating bushings of a converter station, the method comprising: Acquire the first temperature data and the first electric field strength data of the insulating sleeve to be identified after alignment; The first temperature data is compared with the preset temperature threshold to obtain the first comparison result, and the first field strength data is compared with the preset electric field threshold to obtain the second comparison result. If either the first comparison result or the second comparison result meets the preset conditions, the defect identification step is initiated. The defect identification step includes: Based on the first temperature data, the radial gradient, axial gradient and temperature anomaly index are calculated. Based on the first field strength data, the electric field anomaly index is calculated. Based on the first temperature data and the first field strength data, the electric field temperature ratio is calculated. The feature vector is constructed based on the radial gradient, axial gradient, temperature anomaly index, electric field anomaly index, and electric field-temperature ratio. The feature vector is input into the scoring model corresponding to each defect type for calculation, and the score corresponding to each defect type is obtained. The defect type with the highest score is selected as the defect identification result of the insulating sleeve to be identified.

[0006] In one possible implementation of the first aspect, the first temperature data is obtained by collecting a set of temperature detection points set inside the insulating sleeve to be identified, and the set of temperature detection points are uniformly arranged on any cross section of the insulating sleeve to be identified along the radial direction of the insulating sleeve to be identified. The first field strength data was acquired by electric field sampling electrodes installed on the inner side of the casing of the insulating bushing to be identified, using multiple key annular grooves.

[0007] In one possible implementation of the first aspect, the radial gradient and axial gradient are calculated based on the first temperature data, including: Extract the first temperature data to obtain the outer layer temperature data and inner layer temperature data for each layer; Based on the outer and inner temperature data of each layer, the radial gradient of each layer is obtained; The axial gradient of each layer is obtained based on the maximum and minimum temperature values ​​of each layer in the first temperature data.

[0008] In one possible implementation of the first aspect, a temperature anomaly index is calculated based on the first temperature data, including: Based on the initial temperature data and the number of temperature detection points, the average temperature is obtained; Based on the average temperature and the first temperature data corresponding to each temperature detection point, a set of temperature anomaly indices is obtained. The index with the largest value in the set of temperature anomaly indices is selected as the temperature anomaly index.

[0009] In one possible implementation of the first aspect, the scoring model is constructed using sample feature vectors, including: Obtain the sample feature vector of the insulating sleeve to be identified; The sample feature vectors are divided into corresponding defect types to obtain multiple feature sample libraries; Calculate the intraclass coefficient of variation of the feature vectors of each sample in each feature sample library; Based on the sample feature vectors, calculate the inter-class coefficient of variation between any feature sample library and the remaining feature sample libraries. Based on the intra-class coefficient of variation and the inter-class coefficient of variation, obtain the discrimination index. The discrimination index is normalized to obtain the scoring model corresponding to each defect type.

[0010] In one possible implementation of the first aspect, after obtaining the defect identification result, it further includes: Based on the first temperature data, the temperature information of each temperature detection point is obtained, and the temperature deviation of each temperature detection point is obtained based on the temperature information and the average temperature of each temperature detection point. Based on the temperature deviation, the weight of each temperature detection point is determined, and the weighted center is calculated based on the weight and position coordinates of each temperature detection point to obtain the defect location.

[0011] To address the same technical problem, a second aspect of this invention provides a converter station insulating bushing defect identification system, comprising: The acquisition module is used to acquire the first temperature data and the first electric field strength data of the insulating sleeve to be identified after alignment; The comparison module is used to compare the first temperature data with the preset temperature threshold to obtain the first comparison result, and to compare the first field strength data with the preset electric field threshold to obtain the second comparison result. The defect identification module is used to proceed to the defect identification step when either the first comparison result or the second comparison result meets a preset condition. The defect identification step includes: Based on the first temperature data, the radial gradient, axial gradient and temperature anomaly index are calculated. Based on the first field strength data, the electric field anomaly index is calculated. Based on the first temperature data and the first field strength data, the electric field temperature ratio is calculated. The feature vector is constructed based on the radial gradient, axial gradient, temperature anomaly index, electric field anomaly index, and electric field-temperature ratio. The feature vector is input into the scoring model corresponding to each defect type for calculation, and the score corresponding to each defect type is obtained. The defect type with the highest score is selected as the defect identification result of the insulating sleeve to be identified.

[0012] In one possible implementation of the second aspect, the first temperature data is obtained by collecting a set of temperature detection points set inside the insulating sleeve to be identified. The set of temperature detection points are uniformly arranged along the radial direction of the insulating sleeve to be identified on any cross section of the insulating sleeve to be identified. The first field strength data was acquired by an electric field sampling electrode installed in a key annular groove inside the casing of the insulating bushing to be identified.

[0013] A third aspect of the present invention provides a computer device, comprising: Memory, used to store computer programs; A processor is used to execute computer programs to implement steps such as the converter station insulating bushing defect identification method of the first aspect.

[0014] A fourth aspect of the present invention provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the converter station insulating bushing defect identification method of the first aspect.

[0015] The technical solution of this invention has the following advantages: The converter station insulating bushing defect identification method provided in this embodiment of the invention utilizes temperature and electric field detection points set on the insulating bushing to be identified to obtain temperature and electric field data. After aligning the temperature and electric field data, first temperature data and first electric field data are obtained. When either the first comparison result or the second comparison result meets a preset condition, defect identification is initiated. Based on the first temperature data, radial gradient, axial gradient, and temperature anomaly index are calculated. Based on the first electric field data, electric field anomaly index is calculated. The electric field-temperature ratio is calculated based on the first temperature and first electric field data. A feature vector is constructed based on the radial gradient, axial gradient, temperature anomaly index, electric field anomaly index, and electric field-temperature ratio. The feature vector is input into the scoring model corresponding to each defect type for calculation to obtain the score corresponding to each defect type. The defect type with the highest score is selected as the defect identification result of the insulating bushing to be identified. The above method improves the defect detection accuracy of the converter station insulating bushing by performing multi-point monitoring and analysis inside the insulating bushing. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the defect identification method for inverter station insulating bushings in this embodiment of the invention. Figure 2 This is a schematic diagram of the monitoring device layout structure for the converter station insulating bushing defect identification method in this embodiment of the invention; Figure 3 This is a flowchart illustrating the defect identification method for the insulating bushing defect identification in converter stations according to an embodiment of the present invention. Figure 4This is a structural block diagram of the converter station insulating bushing defect identification system in an embodiment of the present invention; Figure reference numerals: 400, Converter station insulating bushing defect identification system; 401, Acquisition module; 402, Comparison module; 403, Defect identification module. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] The converter station insulating bushing defect identification method provided in this embodiment of the invention, such as... Figure 1 As shown, Figure 1 The flowchart for the method of identifying defects in the insulating bushings of converter stations includes steps S101 to S103, and the specific steps are as follows: S101. Obtain the first temperature data and the first field strength data of the insulating bushing to be identified after alignment.

[0020] In this embodiment, the internal temperature distribution is obtained by using FBG sensors arranged radially and axially to obtain the first temperature data. Miniature electric field sampling electrodes (E1-E4) are installed in the key annular groove inside the casing, one electrode per layer, with a reference electrode at the bottom, to monitor the local electric field strength in real time and obtain the first electric field strength data.

[0021] All sensor wiring is led out to the integrated data acquisition and processing unit via a multi-channel sealed connector at the bottom, and interfaced with the converter station control system using an industrial bus. Temperature and electric field signals are acquired synchronously according to spatial coordinates and timestamps, enabling multi-dimensional characterization of the electro-thermal coupling dynamic process. Through data fusion and model analysis, characteristic electro-thermal responses under different defect types, such as moisture and surface defects on the conductive rod, are identified.

[0022] In one embodiment, the first temperature data is collected by a set of temperature detection points set inside the insulating sleeve to be identified. The set of temperature detection points are uniformly arranged along the radial direction of the insulating sleeve to be identified on any cross section of the insulating sleeve to be identified. The first field strength data was acquired by an electric field sampling electrode installed in a key annular groove inside the casing of the insulating bushing to be identified.

[0023] In this embodiment, as Figure 2 As shown, Figure 2This invention relates to a multi-point electro-thermal joint monitoring device for the bushing of an oil-immersed transformer. Four FBG optical fibers are evenly arranged radially on each cross-section, with equal spacing around the perimeter. Three sets of FBG sensors, i.e., temperature detection points, are set at three cross-sections along the bushing length at 20%, 50%, and 80%, respectively, with four sensors per layer. Each FBG sensor serves as a temperature detection point. Each optical fiber passes radially through the core and has a grating polished at a designated axial cross-section to achieve point-level measurement. Miniature electric field sampling electrodes, namely sampling electrodes E1, E2, E3, and E4, are installed in key annular grooves inside the bushing shell, with one electrode per layer. A reference electrode is set at the bottom to monitor the local electric field strength in real time; the field strength data can also be used as electric field strength data.

[0024] like Figure 3 As shown, Figure 3 This is a flowchart illustrating the defect identification process for the insulating bushing defect identification method in converter stations. After reading 12 channels of temperature and 4 channels of electric field strength data, time / space alignment and noise reduction processing are performed first. Then, each data point is judged to exceed limits. If an exceedance is detected, defect identification and location are performed. Specifically, to ensure the consistency of data collected by the two modules in time, a GPS clock is used for synchronization. At system startup, both the FBG sensor and the electric field sampling module are connected to the GPS receiver to obtain accurate Global Positioning System time signals, which are used as the reference for their respective sampling timestamps. Simultaneously, to prevent time synchronization failure due to GPS signal loss, the system is also equipped with a local RTC (Real-Time Clock) chip as a backup time source. When the GPS signal is normal, the GPS clock is used first to update the local RTC time; when the GPS signal is interrupted, the system automatically switches to the local RTC to provide timestamps, ensuring the continuity of time synchronization. Due to the different sampling frequencies of the two modules, the obtained data time points are not completely consistent. To complete the temperature and electric field data into a common time grid, a linear interpolation method or a nearest neighbor matching method is used to complete the data. For example, suppose the FBG sensor collects temperature data T1, T2, T3... at times t1, t2, t3..., and the electric field sampling module collects electric field data C1, C2, C3... at times s1, s2, s3... First, a common time grid is determined, with the time interval set according to actual needs, such as 50ms. Then, for each time point t in the common time grid, two adjacent time points are found in the data time series of the FBG sensor. and , making The temperature value T at that moment is calculated using a linear interpolation formula. The electric field data is also processed using the same linear interpolation method, thus aligning both the temperature and electric field data onto a common time grid, achieving time alignment.

[0025] In terms of spatial alignment, the coordinates of the sensing positions of the three axial layers and the four radial temperature detection points are pre-calibrated. During the acquisition process, the position information of all points is attached to the data record to ensure that the subsequent feature calculations are based on the same spatial reference, thus aligning the first temperature data and the second electric field data.

[0026] S102. Compare the first temperature data with the preset temperature threshold to obtain the first comparison result, and compare the first field strength data with the preset electric field threshold to obtain the second comparison result.

[0027] In this embodiment, after alignment and noise reduction, a judgment is made to determine if a specified limit is exceeded. Specifically, all temperature data of the first temperature data are compared with a preset temperature threshold to obtain a first comparison result, and all field strength data of the first field strength data are compared with a preset electric field threshold to obtain a second comparison result. The first comparison results of all temperature detection points and the second comparison results of all electric field measurement points are comprehensively analyzed. If the first comparison result of any temperature detection point exceeds the specified limit, or the second comparison result of any electric field measurement point exceeds the specified limit, the system determines that the current time exceeds the specified limit. For example, a temperature threshold is set. and electric field threshold ,For example , If any temperature detection point or electric field measuring point If the value exceeds the specified limit, the process will proceed to the defect identification and location stage; otherwise, data collection will continue in a loop.

[0028] S103. When either the first comparison result or the second comparison result meets the preset conditions, the defect identification step is initiated. The defect identification step includes: Based on the first temperature data, the radial gradient, axial gradient and temperature anomaly index are calculated. Based on the first field strength data, the electric field anomaly index is calculated. Based on the first temperature data and the first field strength data, the electric field temperature ratio is calculated. The feature vector is constructed based on the radial gradient, axial gradient, temperature anomaly index, electric field anomaly index, and electric field-temperature ratio. The feature vector is input into the scoring model corresponding to each defect type for calculation, and the score corresponding to each defect type is obtained. The defect type with the highest score is selected as the defect identification result of the insulating sleeve to be identified.

[0029] In this embodiment, once an exceedance is detected, the defect identification and location phase begins immediately; otherwise, data acquisition continues cyclically. Under normal operating conditions, a significant temperature gradient and electric field gradient exist inside the bushing, meaning the electric field strength increases radially, reaching its maximum at the outermost shield electrode. Using 12 temperature detection points (3 axial layers × 4 radial points) and 4 electric field measurement points, the temperature / electric field distribution anomalies caused by different defects are analyzed based on the characteristic parameters of each typical defect. By setting 12 FBG points to cover multiple radial and axial cross-sections, a three-dimensional temperature cloud map is formed, allowing for precise determination of internal hotspot locations and reducing the risk of missed detections. Furthermore, acquiring field strength and temperature data reveals the electro-thermal interaction mechanism caused by defects, distinguishing between simple thermal anomalies and composite defects caused by electric field distortion.

[0030] Table 1. Comparison of Temperature and Electric Field Characteristics of Various Defects As shown in the table above, different types of defects exhibit unique characteristics in temperature distribution and electric field response, with significant differences between them. Specifically: 1) Moisture Intake Defects. When moisture slowly seeps into the bushing, it first settles near the outer layer of the capacitor core and the inner wall of the ceramic bushing. Therefore, when moisture accumulates, hot spots often appear on the outer or lower layer, resulting in a significantly increased radial temperature gradient, with the outer layer temperature being significantly higher than the inner layer; the temperature rise ratio, i.e., the temperature difference between the outer and inner layers, is significantly larger. Since humidity mainly increases dielectric loss, the electric field strength at the location of the electric field sensor may not change abruptly. Typical quantitative indicators can be expressed as an increased outer-inner layer temperature difference and a small change in the axial gradient.

[0031] 2) Surface defects on the conductive rod. Defects on the conductive rod surface can cause localized overheating at the contact point. Simulations and field studies show that localized hot spots form at the defect, typically at the conductive rod joint on the upper part of the sleeve. This leads to a sharp temperature increase on one side of that axial layer, abrupt changes in radial and axial temperature gradients, and a significant increase in the temperature rise ratio—the temperature difference between the hot spot and its surroundings. Because the defect alters the local conductive path, the electric field distribution may also change abruptly; for example, the electric field strength near the defect may be abnormally high or asymmetrical.

[0032] 3) Metal deposition on the inner wall of the ceramic sleeve. Metal particles or deposits adhering to the inner wall of the ceramic sleeve are equivalent to forming a localized conductive region on the insulating inner wall, which can lead to localized charge accumulation and partial discharge. Hot spots often appear near the deposition location, corresponding to abnormally high temperature sensor readings, resulting in an abnormally large radial temperature gradient at that location. Electric field sensors may measure abnormally high electric field strength near the deposition location, i.e., a sudden change in the electric field, thus causing a significant anomaly in the electric field / temperature ratio at that point. A typical characteristic of this defect is the simultaneous occurrence of localized temperature peaks and electric field peaks.

[0033] 4) Grounding failure, i.e., open circuit of the grounding electrode. Under normal circumstances, the outer electrode of the bushing is grounded, and the electric field distribution gradually decreases radially. If the grounding fails, the outer electrode will float, and the electric field distribution will be severely distorted. At this time, the electric field strength of the outer layer of the bushing may increase abnormally, leading to an overall increase in the temperature of the outer insulation, or even a high temperature throughout the entire outer layer. The radial distribution shows a uniform temperature rise, with temperatures at all radial points being similar. The axial gradient may also increase. This defect can be characterized by the overall temperature rise amplitude of the outer layer and the abnormal electric field distribution.

[0034] After time and space alignment, the first temperature data and the first electric field strength data are obtained. The first temperature data includes the temperature values ​​of four radial temperature detection points and three axial temperature detection points of the insulating sleeve at different times. Alternatively, the first temperature data can include the temperature values ​​of the four radial and three axial temperature detection points of the insulating sleeve at the same time. The first electric field strength data records the electric field strength values ​​of multiple electric field detection points around the insulating sleeve at the same time.

[0035] After obtaining the aligned first temperature and first electric field strength data, the radial gradient, axial gradient, temperature anomaly index, and electric field-temperature ratio in the insulating bushing to be identified are calculated. Based on these results, a feature vector is constructed. This feature vector is then input into the scoring model corresponding to each defect type for calculation, yielding a score for each defect type. The defect type with the highest score is selected as the defect identification result for the insulating bushing. The radial and axial gradients, i.e., the radial and axial temperature gradients, are used because the heat distribution of different defects is specific. For example, moisture is dominated by the radial gradient, while conductive rod defects show abrupt changes in both radial and axial gradients. Gradient calculation can effectively distinguish the spatial patterns of heat diffusion.

[0036] The field-temperature ratio, or electric field-temperature ratio, relates the coupling relationship between the electric field and temperature. Defects such as metal deposition can simultaneously cause electric field distortion and temperature rise. This ratio can amplify the characteristics of such defects, such as a sudden increase in the electric field-temperature ratio. The temperature anomaly index can quantify the degree of deviation from the normal state, avoiding the limitations of a single threshold judgment.

[0037] In one embodiment, the radial gradient and axial gradient are calculated based on the first temperature data, including: Extract the first temperature data to obtain the outer layer temperature data and inner layer temperature data for each layer; Based on the outer and inner temperature data of each layer, the radial gradient of each layer is obtained; The axial gradient of each layer is obtained based on the maximum and minimum temperature values ​​of each layer in the first temperature data.

[0038] In this embodiment, the heat distribution of different defects is specific. For example, moisture defects are dominated by radial gradients, while conductive rod defects exhibit abrupt changes in both radial and axial gradients. Gradient calculation can effectively distinguish the spatial patterns of heat diffusion. Specifically, the radial gradient can be calculated using the temperature difference between adjacent measuring points, and the specific calculation formula is as follows: In the formula, It is the first Radial temperature gradient of the layer, The outer layer temperature, This refers to the inner layer temperature.

[0039] When calculating the axial gradient, the temperature values ​​of all temperature detection points are determined from the first temperature data. The maximum and minimum temperature values ​​among these values ​​are found, and the difference between the maximum and minimum values ​​is calculated to obtain the axial gradient. The specific calculation formula is as follows: In the formula, This is the maximum temperature value. This is the minimum temperature value.

[0040] At the same time, for the first For each temperature detection point, calculate the ratio of its electric field to its temperature. The specific calculation formula is as follows: In the formula, For the first Temperature data from road temperature sensors. For the first Electric field intensity data at the road electric field sampling points.

[0041] In one embodiment, a temperature anomaly index is calculated based on first temperature data, including: Based on the initial temperature data and the number of temperature detection points, the average temperature is obtained; Based on the average temperature and the first temperature data corresponding to each temperature detection point, a set of temperature anomaly indices is obtained. The index with the largest value in the set of temperature anomaly indices is selected as the temperature anomaly index.

[0042] In this embodiment, based on the first temperature data and the number of temperature detection points, an average temperature is obtained. Then, the average temperature is used in conjunction with the first... The temperature anomaly index is obtained from the temperature data of each temperature monitoring point. The formula for calculating the temperature anomaly index is: In the formula, For the first Temperature data from road temperature sensors. This represents the average temperature.

[0043] Similarly, the electric field anomaly index at each electric field sampling electrode is calculated based on the first field strength data. The formula for calculating the electric field anomaly index is as follows: In the formula, For the first Field strength data at road temperature sensing points This represents the average field strength.

[0044] Using the obtained radial gradient, axial gradient, temperature anomaly index, and electric field anomaly index, an eigenvector is constructed. .

[0045] In one embodiment, the scoring model is constructed using sample feature vectors, including: Obtain the sample feature vector of the insulating sleeve to be identified; The sample feature vectors are divided into corresponding defect types to obtain multiple feature sample libraries; Calculate the intraclass coefficient of variation of the feature vectors of each sample in each feature sample library; Based on the sample feature vectors, calculate the inter-class coefficient of variation between any feature sample library and the remaining feature sample libraries. Based on the intra-class coefficient of variation and the inter-class coefficient of variation, obtain the discrimination index. The discrimination index is normalized to obtain the scoring model corresponding to each defect type.

[0046] In this embodiment, three-dimensional models of four typical defects—moisture absorption, surface defects on the conductive rod, metal deposition on the inner wall of the porcelain bushing, and grounding failure—are established. The electrostatic field equation (for calculating electric field distribution) and the thermal diffusion equation (for calculating temperature distribution) are coupled to simulate characteristic parameter data under different defect levels. The model includes key structures such as the porcelain bushing, insulating core, and insulating oil, and its geometric parameters are consistent with those of the actual bushing.

[0047] For each set of simulation results, such as a scenario with a certain type of defect and a certain severity, the defined feature parameters are extracted: radial temperature gradient, axial temperature gradient, field-temperature ratio, temperature anomaly index, and electric field anomaly index. All simulation feature parameters are summarized to form a feature sample library for four types of defects, with at least 30 samples for each type, covering different severity levels. The discrimination index is calculated for the feature parameters of the four types of defects in the sample library, i.e., the sample feature vectors.

[0048] It should be noted that the discrimination index quantifies the uniqueness of a feature parameter to a specific defect. That is, it measures the difference between this feature and other defects within the target defect, specifically using the ratio of "intra-class coefficient of variation" to "between-class coefficient of variation." The intra-class coefficient of variation refers to the dispersion of a feature parameter within the same defect type, or within the same feature sample library, reflecting the stability of the feature among similar defects. Its calculation formula is: In the formula, For the first One defect type, For characteristic parameters, For the first Feature parameters for each defect type standard deviation The mean, No. The intra-class variation coefficient for each defect type.

[0049] The inter-class coefficient of variation refers to the degree of difference of a certain feature parameter between the target feature sample library and other feature sample libraries. It reflects the uniqueness of the feature to the target defect, and its calculation formula is as follows: In the formula, For feature parameters in other types of feature sample databases The mean, For the first The inter-class variation coefficient for each defect type.

[0050] It should be noted that each feature sample library corresponds to a type of defect, and each feature sample library includes multiple sample feature vectors, i.e., feature parameters.

[0051] The discrimination index refers to the combination of intra-class stability and inter-class uniqueness. The higher the value, the stronger the feature's ability to distinguish defects. Its calculation formula is as follows: In the formula, The discrimination index, For the first The inter-class variation coefficient for each defect type No. The intra-class variation coefficient for each defect type.

[0052] The discrimination index is normalized to a range, and the weighting formula is as follows: In the formula, For the feature vector dimension, For the first Characteristic parameters of each defect type The weight value.

[0053] The final scoring model is as follows: In the formula, For the first Feature parameters of each defect type The weight value, For the first Each feature parameter.

[0054] For all Calculate each type of defect separately Then select the largest scoring model value; for example, when the value corresponding to "conductive rod defect" is... If it is higher than the other three, then it is determined that the most likely cause is a surface defect in the conductive rod.

[0055] It should be noted that the weight values ​​of the feature parameters in each defect type are based on the electro-thermal characteristics of the casing defect. By quantitatively analyzing the ability of different features to distinguish specific defects, such as the more significant and definite change in radial temperature gradient when damp, the correlation between features and defects can be truly reflected.

[0056] In one embodiment, after obtaining the defect identification result, the method further includes: Based on the first temperature data, the temperature information of each temperature detection point is obtained, and the temperature deviation of each temperature detection point is obtained based on the temperature information and the average temperature of each temperature detection point. Based on the temperature deviation, the weight of each temperature detection point is determined, and the weighted center is calculated based on the weight and position coordinates of each temperature detection point to obtain the defect location.

[0057] In this embodiment, utilizing the principle of heat diffusion, it is assumed that after the additional heat released at the defect diffuses steadily in the insulating medium, the temperature rise is more significant at measuring points closer to the defect. The temperature deviation at each temperature detection point is calculated using the following formula: In the formula, For the first Temperature data from road temperature sensors. This represents the average temperature.

[0058] Then, in the sleeve's own coordinate system, the three-dimensional coordinates of each temperature detection point are pre-calibrated as follows: ,in,( Corresponding radial position, Corresponding to axial dimensions, such as 0.2L, 0.5L, and 0.8L.

[0059] Using temperature deviation as a weight, only positive deviations are weighted. Based on the obtained weights, the weighted center of gravity of all temperature detection points is calculated, which is the most likely approximate location of the defect, thus obtaining the defect location. The specific calculation formula is as follows: In the formula, As weight, The three-dimensional coordinates of each temperature detection point. The approximate positions are calculated for each coordinate.

[0060] It should be noted that defect location is based on the weighted centroid of temperature deviation. The logic behind this is the physical law of heat diffusion: as a heat source, the closer the measurement point is to the defect, the more significant the temperature rise (the greater the temperature deviation). Therefore, using the temperature deviation as the weight to calculate the spatial centroid can approximate the actual location of the defect.

[0061] After obtaining the defect identification results through the above methods, this application can clearly identify the location, type, and cause of the defect, avoiding blind repairs. For example, if the defect is identified as dampness in the insulation of the oil-paper bushing, targeted oil quality testing, vacuum oil injection, or replacement of the insulating oil can be carried out during repairs, rather than disassembling the entire bushing. If the defect is identified as an internal metal foreign object, its location can be located using an endoscope, and it can be removed using specialized tools, minimizing damage to the bushing body. If the defect is identified as a grounding shield loss, it will cause severe distortion of the electric field distribution inside the bushing, and a sudden increase in local field strength may instantly break down the insulation. Therefore, the corresponding equipment must be shut down immediately to prevent the defect from expanding.

[0062] The converter station insulating bushing defect identification system provided in this embodiment of the invention, such as... Figure 4 As shown, Figure 4 This is a system block diagram of the converter station insulating bushing defect identification system 400 in an embodiment of the present invention, including: The acquisition module 401 is used to acquire the first temperature data and the first field strength data of the insulating sleeve to be identified after alignment; The comparison module 402 is used to compare the first temperature data with the preset temperature threshold to obtain a first comparison result, and to compare the first field strength data with the preset electric field threshold to obtain a second comparison result. The defect identification module 403 is used to proceed to the defect identification step when either the first comparison result or the second comparison result meets a preset condition. The defect identification step includes: Based on the first temperature data, the radial gradient, axial gradient and temperature anomaly index are calculated. Based on the first field strength data, the electric field anomaly index is calculated. Based on the first temperature data and the first field strength data, the electric field temperature ratio is calculated. The feature vector is constructed based on the radial gradient, axial gradient, temperature anomaly index, electric field anomaly index, and electric field-temperature ratio. The feature vector is input into the scoring model corresponding to each defect type for calculation, and the score corresponding to each defect type is obtained. The defect type with the highest score is selected as the defect identification result of the insulating sleeve to be identified.

[0063] In one embodiment, the first temperature data is collected by a set of temperature detection points set inside the insulating sleeve to be identified. The set of temperature detection points are uniformly arranged along the radial direction of the insulating sleeve to be identified on any cross section of the insulating sleeve to be identified. The first field strength data was acquired by an electric field sampling electrode installed in a key annular groove inside the casing of the insulating bushing to be identified.

[0064] The specific implementation of the converter station insulating bushing defect identification system is basically the same as the specific implementation of the converter station insulating bushing defect identification method described above, and will not be repeated here.

[0065] In one embodiment of this application, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above steps. The implementation principle and technical effects of the computer device provided in this embodiment are similar to those of the above method embodiments, and will not be repeated here.

[0066] In one embodiment of this application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, it performs the above steps; the implementation principle and technical effects of the computer-readable storage medium provided in this embodiment are similar to those of the above method embodiments, and will not be repeated here.

[0067] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0068] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for identifying defects in the insulating bushings of a converter station, characterized in that, include: Acquire the first temperature data and the first electric field strength data of the insulating sleeve to be identified after alignment; The first temperature data is compared with the preset temperature threshold to obtain the first comparison result, and the first field strength data is compared with the preset electric field threshold to obtain the second comparison result. If either the first comparison result or the second comparison result meets a preset condition, the defect identification step is initiated, wherein the defect identification step includes: Based on the first temperature data, the radial gradient, axial gradient and temperature anomaly index are calculated. Based on the first field strength data, the electric field anomaly index is calculated. Based on the first temperature data and the first field strength data, the electric field temperature ratio is calculated. Based on the radial gradient, axial gradient, temperature anomaly index, electric field anomaly index, and electric field-temperature ratio, a feature vector is constructed. The feature vector is input into the scoring model corresponding to each defect type for calculation to obtain the score corresponding to each defect type. The defect type with the largest score is selected as the defect identification result of the insulating sleeve to be identified.

2. The method for identifying defects in the insulating bushings of converter stations as described in claim 1, characterized in that, The first temperature data is collected by a set of temperature detection points set inside the insulating sleeve to be identified. The set of temperature detection points are uniformly arranged along the radial direction of the insulating sleeve to be identified on any cross section of the insulating sleeve to be identified. The first field strength data is obtained by electric field sampling electrodes installed on the inner side of the outer shell of the insulating sleeve to be identified through multiple key annular grooves.

3. The method for identifying defects in the insulating bushings of converter stations as described in claim 1, characterized in that, The calculation of the radial gradient and axial gradient based on the first temperature data includes: The first temperature data is extracted to obtain the outer layer temperature data and inner layer temperature data of each layer; Based on the outer layer temperature data and the inner layer temperature data of each layer, the radial gradient of each layer is obtained; The axial gradient of each layer is obtained based on the maximum and minimum temperature values ​​of each layer in the first temperature data.

4. The method for identifying defects in the insulating bushing of a converter station as described in claim 2, characterized in that, The calculation of the temperature anomaly index based on the first temperature data includes: Based on the first temperature data and the number of temperature detection points, the average temperature is obtained; Based on the average temperature and the first temperature data corresponding to each of the temperature detection points, a temperature anomaly index set is obtained; The index with the largest value in the set of temperature anomaly indices is selected as the temperature anomaly index.

5. The method for identifying defects in the insulating bushings of a converter station as described in claim 1, characterized in that, The scoring model is constructed using sample feature vectors, including: Obtain the sample feature vector of the insulating sleeve to be identified; The sample feature vectors are divided into corresponding defect types to obtain multiple feature sample libraries; Calculate the intraclass coefficient of variation of the feature vectors of each sample in each of the feature sample libraries; Based on the sample feature vector, calculate the inter-class coefficient of variation between any one of the feature sample libraries and the remaining feature sample libraries, and obtain the discrimination index based on the intra-class coefficient of variation and the inter-class coefficient of variation. The discrimination index is normalized to obtain the scoring model corresponding to each defect type.

6. The method for identifying defects in the insulating bushing of a converter station as described in claim 1 or 4, characterized in that, After obtaining the defect identification result, the following is also included: Based on the first temperature data, the temperature information of each temperature detection point is obtained, and the temperature deviation of each temperature detection point is obtained according to the temperature information of each temperature detection point and the average temperature. Based on the temperature deviation, the weight of each temperature detection point is determined, and the weighted center is calculated based on the weight and position coordinates of each temperature detection point to obtain the defect location.

7. A converter station insulating bushing defect identification system, characterized in that, include: The acquisition module is used to acquire the first temperature data and the first electric field strength data of the insulating sleeve to be identified after alignment; The comparison module is used to compare the first temperature data with a preset temperature threshold to obtain a first comparison result, and to compare the first field strength data with a preset electric field threshold to obtain a second comparison result. A defect identification module is configured to proceed to a defect identification step when either the first comparison result or the second comparison result meets a preset condition. The defect identification step includes: Based on the first temperature data, the radial gradient, axial gradient, and temperature anomaly index are calculated. Based on the first field strength data, the electric field anomaly index is calculated. The electric field-temperature ratio is calculated based on the first temperature data and the first field strength data. A feature vector is constructed based on the radial gradient, axial gradient, temperature anomaly index, electric field anomaly index, and electric field-temperature ratio. The feature vector is input into the scoring model corresponding to each defect type for calculation to obtain the score corresponding to each defect type. The defect type with the largest score is selected as the defect identification result of the insulating sleeve to be identified.

8. The converter station insulating bushing defect identification system as described in claim 7, characterized in that, The first temperature data is collected by a set of temperature detection points set inside the insulating sleeve to be identified. The set of temperature detection points are uniformly arranged along the radial direction of the insulating sleeve to be identified on any cross section of the insulating sleeve to be identified. The first field strength data is acquired by an electric field sampling electrode installed in a key annular groove inside the casing of the insulating sleeve to be identified.

9. A computer device, characterized in that, include: Memory, used to store computer programs; A processor is configured to implement the converter station insulating bushing defect identification method as described in any one of claims 1 to 6 when executing the computer program.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the converter station insulation bushing defect identification method as described in any one of claims 1 to 6.

Images