Hierarchical diagnosis and evaluation method for insulation resistance of mutual inductor
By combining multi-sensor data fusion and adaptive environmental compensation with LSTM and multinomial models, the compensation strategy is dynamically adjusted to solve the problems of accuracy and reliability in evaluating the insulation resistance of current transformers, achieving accurate evaluation and extended equipment life in complex environments.
Patent Information
- Application Number
- CN202511044284.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-28
- Publication Date
- 2025-12-12
AI Technical Summary
Existing technologies cannot accurately reflect the impact of complex field environments on the insulation resistance of instrument transformers, resulting in distorted measurement values. Furthermore, the nonlinear degradation of insulation materials in aging equipment leads to a high misjudgment rate. Traditional grading methods fail to effectively utilize machine learning to mine multidimensional features, resulting in the missed detection of early, subtle defects.
By acquiring real-time data from the current transformer, multi-sensor data fusion and adaptive environmental compensation are used to perform hierarchical compensation based on temperature and humidity weights. Combined with an LSTM compensator and a lightweight polynomial model, the compensation strategy is dynamically adjusted to accurately match the nonlinear degradation characteristics of the insulation material and perform graded diagnosis of insulation resistance.
It enables accurate assessment of the insulation resistance of instrument transformers in complex environments, reduces the impact of temperature and humidity, improves the accuracy and reliability of assessment, extends equipment life, reduces operation and maintenance costs, and promotes the transformation from periodic maintenance to intelligent predictive maintenance.
Smart Images
Figure CN121114900A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The embodiment of the present application relates to the technical field of mutual inductor, in particular to a grading diagnosis evaluation method of mutual inductor insulation resistance. BACKGROUND
[0002] In the power system, the insulation state of the current transformer (CT) and the voltage transformer (VT) directly affects the safe and stable operation of the power grid. The insulation resistance is one of the key indicators for evaluating the insulation performance of the mutual inductor, and its degradation can cause serious accidents such as partial discharge, dielectric breakdown and even device explosion. At present, the measurement and diagnosis of insulation resistance mainly rely on periodic preventive tests, but the resistance is significantly affected by temperature and humidity. The existing compensation model is based on linear or simple nonlinear formula (such as exponential temperature correction), which cannot accurately reflect the influence of complex field environment (such as condensation, pollution superposition and temperature variation), resulting in distortion of the measured value. In addition, for the aging equipment running for more than 10 years, the nonlinear degradation of insulation materials (such as oil-paper insulation cracking and cellulose degradation) makes the traditional threshold method invalid, resulting in a high false positive rate of up to 50% in the later stage of aging. Moreover, most grading methods rely on fixed thresholds or expert experience rules, and fail to use machine learning to mine the deep correlation between insulation resistance and multi-dimensional features, resulting in missed detection of early weak defects.
[0003] Therefore, it is urgent to propose a grading diagnosis method of insulation resistance to break through the dependence of traditional technology on idealized model and realize accurate evaluation under complex working conditions. SUMMARY
[0004] The purpose of the present application is to at least solve one of the above technical defects.
[0005] In one aspect, the embodiment of the present application provides a grading diagnosis evaluation method of mutual inductor insulation resistance, which comprises:
[0006] Obtaining real-time data of the mutual inductor, the real-time data including an insulation resistance original value, temperature data at a set position, humidity data at the set position, an electromagnetic interference value and a device aging factor value;
[0007] Determining a humidity gradient value according to the humidity data, and determining whether the humidity gradient is greater than a preset threshold value, if the humidity gradient is greater than the preset threshold value, the mutual inductor is divided into 5 layers along the set height direction, and the temperature weight of each layer and the humidity weight of each layer are determined;
[0008] Obtaining the temperature data and the humidity data corresponding to each layer, determining a temperature effective compensation parameter based on the temperature weight of each layer and the temperature data, and determining a humidity effective compensation parameter according to the humidity weight of each layer and the humidity data;
[0009] The target compensation method is determined based on the relationship between the equipment aging factor value and the set factor threshold. The original value of insulation resistance is then compensated based on the effective temperature compensation parameter, the effective humidity compensation parameter, and the target compensation method to obtain the compensated insulation resistance value.
[0010] Based on the humidity gradient and electromagnetic interference value, the data quality score of the current transformer is determined, and the compensated insulation resistance value and the data quality score of the current transformer are used as the results of the graded diagnostic assessment.
[0011] Optionally, the temperature data at the set location includes temperature data from the temperature sensor at the top of the transformer and temperature data from the temperature sensor at the bottom of the transformer; the humidity data at the set location includes humidity data from the humidity sensor at the top of the transformer and humidity data from the humidity sensor at the bottom of the transformer; the transformer is divided into 5 layers along the set height direction, including:
[0012] Set the position of the current transformer corresponding to the top sensor as the top, set the position of the current transformer corresponding to the bottom sensor as the bottom, and set the middle position between the top and bottom as the middle.
[0013] The position of the current transformer corresponding to the top and middle is set as the upper part, and the position of the current transformer corresponding to the middle and bottom is set as the lower part.
[0014] Optionally, based on the temperature weights and temperature data of each layer, effective temperature compensation parameters are determined, including:
[0015] Obtain the height coordinates of each layer of the current transformer, and perform differential processing on the temperature data at the set position based on the height coordinates of each layer to obtain the temperature data corresponding to the upper part, the middle part, and the lower part.
[0016] Based on the temperature weight of each layer, the temperature data at the set location, the temperature data corresponding to the upper part, the temperature data corresponding to the middle part, and the temperature data corresponding to the lower part, the effective temperature compensation parameters are determined.
[0017] Optionally, based on the humidity weight and humidity data of each layer, effective humidity compensation parameters are determined, including:
[0018] Obtain the height coordinates of each layer of the current transformer, and perform differential processing on the humidity data at the set position based on the height coordinates of each layer to obtain the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part.
[0019] The effective humidity compensation parameters are determined based on the temperature weight of each layer, the humidity data at the set location, the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part.
[0020] Optionally, after determining the effective humidity compensation parameters, the following may also be included:
[0021] If the humidity data of the humidity sensor at the bottom of the current transformer is greater than the preset humidity threshold, the condensation index is determined based on the humidity data of the humidity sensor at the bottom of the current transformer.
[0022] The humidity effective compensation parameters are corrected based on the condensation index to obtain the corrected humidity effective compensation parameters;
[0023] The original value of insulation resistance is compensated based on the effective temperature compensation parameters, effective humidity compensation parameters, and target compensation method, including:
[0024] The original value of insulation resistance is compensated based on the effective temperature compensation parameters, the corrected effective humidity compensation parameters, and the target compensation method.
[0025] Optionally, the target compensation method includes compensation methods for healthy equipment and compensation methods for aging equipment. The target compensation method is determined based on the relationship between the equipment aging factor value and a set factor threshold, including:
[0026] If the equipment aging factor value is less than the set factor threshold, the target compensation method is determined to be the compensation method for healthy equipment.
[0027] If the equipment aging factor value is not less than the set factor threshold, then the target compensation method is determined to be the compensation method for equipment in the aging period.
[0028] Optionally, the original value of insulation resistance is compensated based on effective temperature compensation parameters, effective humidity compensation parameters, and the target compensation method, including:
[0029] If the target compensation method is the compensation method for healthy equipment, then the original value of insulation resistance is compensated by a lightweight polynomial model based on the effective temperature compensation parameters and effective humidity compensation parameters.
[0030] If the target compensation method is the compensation method for equipment in the aging period, then the pollution level of the current transformer is obtained, and the original value of the insulation resistance is compensated by the LSTM compensator according to the pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter.
[0031] Optionally, the original value of insulation resistance can be compensated using an LSTM compensator based on the pollution level, equipment aging factor value, effective temperature compensation parameters, and effective humidity compensation parameters, including:
[0032] The pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter are input into the LSTM compensator to obtain the dynamic confidence level.
[0033] The original value of insulation resistance is compensated based on dynamic confidence level.
[0034] Optionally, the pollution level, equipment aging factor value, effective temperature compensation parameter, and effective humidity compensation parameter can be input into the LSTM compensator to obtain the dynamic confidence level, including:
[0035] The pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter are input into the LSTM compensator to obtain the initial dynamic confidence level.
[0036] Based on the pollution level and condensation index, the correction amount for the dynamic confidence level is determined, and the initial dynamic confidence level is corrected according to the correction amount to obtain the dynamic confidence level.
[0037] Optionally, a data quality score for the current transformer can be determined based on the humidity gradient and electromagnetic interference value, including:
[0038] The gradient score of the current transformer is determined based on the humidity gradient and the preset gradient threshold, and the electromagnetic interference score of the current transformer is determined based on the electromagnetic interference value.
[0039] Based on the respective weights of the gradient score and the electromagnetic interference score, the gradient score and the electromagnetic interference score are weighted together to obtain the data quality score of the transformer.
[0040] On the other hand, embodiments of this application provide a graded diagnostic evaluation device for the insulation resistance of a current transformer, the device comprising:
[0041] The data acquisition module is used to acquire real-time data from the current transformer. The real-time data includes the original value of insulation resistance, temperature data at the set location, humidity data at the set location, electromagnetic interference value, and equipment aging factor value.
[0042] The weight determination module is used to determine the humidity gradient value based on the humidity data and to determine whether the humidity gradient is greater than the preset threshold. If the humidity gradient is greater than the preset threshold, the current transformer is divided into 5 layers along the set height direction, and the temperature weight and humidity weight of each layer are determined.
[0043] The compensation parameter determination module is used to obtain the temperature and humidity data corresponding to each layer, determine the effective temperature compensation parameters based on the temperature weight and temperature data of each layer, and determine the effective humidity compensation parameters based on the humidity weight and humidity data of each layer.
[0044] The resistance compensation module is used to determine the target compensation method based on the relationship between the equipment aging factor value and the set factor threshold, and to compensate the original value of insulation resistance according to the effective temperature compensation parameter, the effective humidity compensation parameter and the target compensation method to obtain the compensated insulation resistance value.
[0045] The evaluation result determination module is used to determine the data quality score of the current transformer based on the humidity gradient and the electromagnetic interference value, and to use the compensated insulation resistance value and the data quality score of the current transformer as the graded diagnostic evaluation result.
[0046] In another aspect, embodiments of this application provide an electronic device, including a processor and a memory:
[0047] The memory is configured to store machine-readable instructions that, when executed by the processor, cause the processor to perform any one of the methods in a graded diagnostic evaluation method for the insulation resistance of a current transformer.
[0048] The beneficial effects of the technical solutions provided in this application include at least the following:
[0049] This application can obtain the original insulation resistance value of the instrument transformer, temperature data at the set location, humidity data at the set location, electromagnetic interference value, and equipment aging factor value. Then, through multi-sensor data fusion and adaptive environmental compensation, the insulation resistance is compensated, reducing the impact of temperature and humidity on the insulation resistance. Furthermore, the quality of the instrument transformer can be evaluated. It has significant advantages such as strong environmental adaptability, excellent anti-interference ability, and low operation and maintenance cost. It can effectively extend the equipment life and improve the reliability of power grid operation, promoting the transformation of insulation monitoring from periodic maintenance to intelligent predictive maintenance.
[0050] In this application, the compensation strategy can be dynamically adjusted according to the equipment aging factor, which can accurately match the nonlinear degradation characteristics of the insulation material, significantly reduce the insulation resistance assessment error of the aging equipment, avoid premature retirement caused by conservative thresholds, extend the service life of the equipment, and significantly improve the economy and reliability of condition-based maintenance. Attached Figure Description
[0051] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0052] Figure 1 A flowchart illustrating a graded diagnostic evaluation method for the insulation resistance of a current transformer, provided in an embodiment of this application;
[0053] Figure 2 A schematic diagram of the structure of a graded diagnostic and evaluation device for the insulation resistance of a current transformer provided in an embodiment of this application;
[0054] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0055] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting the invention.
[0056] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.
[0057] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0058] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0059] Specifically, such as Figure 1 As shown, the method may include:
[0060] Step S101: Obtain real-time data from the current transformer. The real-time data includes the original value of insulation resistance, temperature data at the set location, humidity data at the set location, electromagnetic interference value, and equipment aging factor value.
[0061] Optionally, the raw insulation resistance value in the real-time data can be obtained through the anti-interference resistance measurement module inside the high-voltage shielding box. The temperature data at the set location refers to the temperature data obtained by the temperature sensor at the top (i.e., the uppermost) of the transformer and the temperature data obtained by the temperature sensor at the bottom (i.e., the lowermost) of the transformer. The humidity data at the set location refers to the humidity data obtained by the humidity sensor at the top (i.e., the uppermost) of the transformer and the humidity data obtained by the humidity sensor at the bottom (i.e., the lowermost) of the transformer. The electromagnetic interference value can be obtained based on the electromagnetic interference monitor, while the equipment aging factor value can be calculated and determined based on the equipment's operating years and historical degradation curves, represented by 0-1. The longer the usage time, the larger the aging factor value, and vice versa. New equipment is 0.
[0062] Step S102: Determine the humidity gradient value based on the humidity data, and determine whether the humidity gradient is greater than the preset threshold. If the humidity gradient is greater than the preset threshold, divide the current transformer into 5 layers along the set height direction, and determine the temperature weight and humidity weight of each layer.
[0063] Optionally, after acquiring humidity data, the difference between the humidity data obtained by the humidity sensor at the top (i.e., the uppermost) of the current transformer and the humidity data obtained by the humidity sensor at the bottom (i.e., the lowermost) of the current transformer can be used as the humidity gradient value. This humidity gradient value reflects the humidity difference between the upper and lower parts of the current transformer. Then, the obtained humidity gradient value is compared with a preset threshold. If it is determined that the humidity gradient is greater than the preset threshold, the current transformer is divided into 5 layers along a set height direction (e.g., the longitudinal direction from top to bottom), and the temperature weight and humidity weight of each layer are determined.
[0064] In an optional embodiment of this application, the temperature data at the set location includes temperature data from the temperature sensor at the top of the transformer and temperature data from the temperature sensor at the bottom of the transformer; the humidity data at the set location includes humidity data from the humidity sensor at the top of the transformer and humidity data from the humidity sensor at the bottom of the transformer; and the transformer is divided into 5 layers along the set height direction, including:
[0065] Set the position of the current transformer corresponding to the top sensor as the top, set the position of the current transformer corresponding to the bottom sensor as the bottom, and set the middle position between the top and bottom as the middle.
[0066] The current transformer is designated as the upper part corresponding to the position between the top and the middle, and the current transformer is designated as the lower part corresponding to the position between the middle and the bottom.
[0067] Optionally, current transformers typically have sensors arranged at the top and bottom. In this case, the position corresponding to the topmost sensor can be designated as the top, the position corresponding to the bottommost sensor as the bottom, and the position between the top and bottom as the middle. Correspondingly, the position between the top and middle of the current transformer is designated as the upper part, and the position between the middle and bottom is designated as the lower part. In this case, the current transformer can be divided into 5 layers along the vertical direction from top to bottom: top, upper, middle, lower, and bottom.
[0068] Step S103: Obtain the temperature and humidity data corresponding to each layer. Based on the temperature weight and temperature data of each layer, determine the effective temperature compensation parameters. Also, based on the humidity weight and humidity data of each layer, determine the effective humidity compensation parameters.
[0069] Optionally, after dividing the current transformer into 5 layers, the temperature and humidity data corresponding to each layer can be determined. Then, based on the temperature weight and temperature data corresponding to each layer of the current transformer, the effective temperature compensation parameters are obtained. At the same time, based on the humidity weight and humidity data of each layer, the effective humidity compensation parameters are determined.
[0070] In this embodiment of the application, effective temperature compensation parameters are determined based on the temperature weight and temperature data of each layer, including:
[0071] Obtain the height coordinates of each layer of the current transformer, and perform differential processing on the temperature data at the set position based on the height coordinates of each layer to obtain the temperature data corresponding to the upper part, the middle part, and the lower part.
[0072] Based on the temperature weight of each layer, the temperature data at the set location, the temperature data corresponding to the upper part, the temperature data corresponding to the middle part, and the temperature data corresponding to the lower part, the effective temperature compensation parameters are determined.
[0073] In practical applications, since the temperature may vary at different locations on the current transformer structure, the temperature data from only the top and bottom points are insufficient to reflect the overall situation. Therefore, spatial interpolation algorithms (such as Kriging interpolation) are needed to estimate the temperature distribution across the entire current transformer surface.
[0074] Optionally, temperature and humidity weights can be assigned to each layer, with the sum of the weights for the five layers being 100%. Since condensation occurs at the bottom of the transformer, a higher weight is assigned to the bottom area. For example, the temperature weight is allocated as follows: top 25%, upper 15%, middle 20%, lower 15%, and bottom 25%; the humidity weight is allocated as follows: top 20%, upper 15%, middle 20%, lower 15%, and bottom 30%.
[0075] Furthermore, the temperature data at a set location (temperature data at the top and temperature data at the bottom) can be interpolated using the following formula based on the corresponding height coordinates of each layer to obtain the temperature data for the upper, middle, and lower parts:
[0076] T layer =T bottom +(T top -T bottom )*(Z layer -Z bottom ) / (Z top -Z bottom )
[0077] Among them, T layer For the temperature data corresponding to the desired layer, T bottom For the temperature data corresponding to the bottom, T top For the temperature data corresponding to the top, Z laye Z represents the height coordinates of the desired layer. bottom Z represents the height coordinate of the bottom. top The coordinates are the height of the top.
[0078] Furthermore, based on the temperature weights of each layer, the temperature data at the set location, the temperature data corresponding to the upper part, the temperature data corresponding to the middle part, and the temperature data corresponding to the lower part, a weighted average is performed to obtain the effective temperature compensation parameters, which can be determined by the following formula:
[0079] T eff =0.25*T top +0.15*T upper +0.20*T middle +0.15*T lower +0.25*T bottom
[0080] Among them, T eff For effective temperature compensation parameters, T bottom For the temperature data corresponding to the bottom, T top For the temperature data corresponding to the top, T middle For the temperature data corresponding to the central region, T lower The temperature data is shown below.
[0081] In optional embodiments of this application, effective humidity compensation parameters are determined based on the humidity weight and humidity data of each layer, including:
[0082] Obtain the height coordinates of each layer of the current transformer, and perform differential processing on the humidity data at the set position based on the height coordinates of each layer to obtain the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part.
[0083] The effective humidity compensation parameters are determined based on the temperature weight of each layer, the humidity data at the set location, the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part.
[0084] In practical applications, since the humidity may vary at different locations on the current transformer structure, the humidity data from only the top and bottom points are insufficient to reflect the overall situation. Therefore, spatial interpolation algorithms (such as Kriging interpolation) are needed to estimate the humidity distribution across the entire current transformer surface.
[0085] Optionally, for the humidity data of each layer, linear interpolation is also used to calculate the humidity data of the intermediate layers. Specifically, based on the height coordinates of each layer, the humidity data at a set location (humidity data at the top and bottom) can be interpolated using the following formula to obtain the humidity data for the upper, middle, and lower parts:
[0086] H layer =H bottom +(H top -H bottom )*(H layer -H bottom ) / (H top -H bottom )
[0087] Among them, H layer H represents the humidity data corresponding to the desired layer. bottom H represents the humidity data corresponding to the bottom. top H represents the humidity data corresponding to the top. laye H represents the height coordinates of the desired layer. bottom H represents the height coordinates of the bottom. top The coordinates are the height of the top.
[0088] Furthermore, based on the temperature weight of each layer, the humidity data at the set location, the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part, a weighted average is performed to obtain the effective humidity compensation parameter, which can be determined by the following formula:
[0089] H eff =0.20*H top +0.15*H upper +0.20*H middle +0.15*H lower +0.30*H bottom
[0090] Among them, H eff H is the effective humidity compensation parameter.bottom H represents the humidity data corresponding to the bottom. top H represents the humidity data corresponding to the top. middle For the humidity data corresponding to the central region, H lower The humidity data is shown below.
[0091] Step S104: Determine the target compensation method based on the relationship between the equipment aging factor value and the set factor threshold, and compensate the original value of insulation resistance according to the effective temperature compensation parameter, the effective humidity compensation parameter and the target compensation method to obtain the compensated insulation resistance value.
[0092] Optionally, the obtained equipment aging factor can be compared with the set factor threshold, and the target compensation method can be determined based on the relationship between the two. Then, based on the effective temperature compensation parameter and the effective humidity compensation parameter, the original value of insulation resistance can be compensated using the determined target compensation method to obtain the compensated insulation resistance value.
[0093] In an optional embodiment of this application, after determining the effective humidity compensation parameters, the method further includes:
[0094] If the humidity data of the humidity sensor at the bottom of the current transformer is greater than the preset humidity threshold, the condensation index is determined based on the humidity data of the humidity sensor at the bottom of the current transformer.
[0095] The humidity effective compensation parameters are corrected based on the condensation index to obtain the corrected humidity effective compensation parameters;
[0096] The original value of insulation resistance is compensated based on the effective temperature compensation parameters, effective humidity compensation parameters, and target compensation method, including:
[0097] The original value of insulation resistance is compensated based on the effective temperature compensation parameters, the corrected effective humidity compensation parameters, and the target compensation method.
[0098] Optionally, excessive condensation at the bottom can cause errors in the accuracy of humidity data. Therefore, in this embodiment, the humidity data from the humidity sensor at the bottom of the transformer can be compared with a preset humidity threshold. When the humidity data from the humidity sensor at the bottom of the transformer is greater than the preset humidity threshold, it indicates that condensation has occurred at the bottom of the transformer. At this time, a condensation index can be generated based on the humidity data from the humidity sensor at the bottom of the transformer according to the following formula:
[0099] CI = (H) bottom -75) / 20
[0100] Where CI is the condensation index, and H is the condensation index. bottom This is the humidity data corresponding to the bottom.
[0101] Furthermore, based on the generated condensation index, the determined effective humidity compensation parameters are corrected using the following formula to obtain the corrected effective humidity compensation parameters:
[0102] H eff '=H eff ×(1+0.2×CI)
[0103] Among them, H eff ' represents the corrected effective humidity compensation parameter, CI is the condensation index, and H...' eff This is the effective humidity compensation parameter.
[0104] Accordingly, the original value of insulation resistance is compensated based on the effective temperature compensation parameters, the corrected effective humidity compensation parameters, and the target compensation method to obtain the compensated original value of insulation resistance.
[0105] In optional embodiments of this application, the target compensation method includes a compensation method for healthy-period equipment and a compensation method for aging-period equipment. The target compensation method is determined based on the relationship between the equipment aging factor value and a set factor threshold, including:
[0106] If the equipment aging factor value is less than the set factor threshold, the target compensation method is determined to be the compensation method for healthy equipment.
[0107] If the equipment aging factor value is not less than the set factor threshold, then the target compensation method is determined to be the compensation method for equipment in the aging period.
[0108] Optionally, the target compensation method in this application embodiment includes a compensation method for healthy equipment and a compensation method for aging equipment. Specifically, when the equipment aging factor value is less than a set factor threshold, the target compensation method is the compensation method for healthy equipment; if the equipment aging factor value is not less than the set factor threshold, the target compensation method is determined to be the compensation method for aging equipment.
[0109] In optional embodiments of this application, compensation for the original value of insulation resistance is performed based on effective temperature compensation parameters, effective humidity compensation parameters, and a target compensation method, including:
[0110] If the target compensation method is the compensation method for healthy equipment, then the original value of insulation resistance is compensated by a lightweight polynomial model based on the effective temperature compensation parameters and effective humidity compensation parameters.
[0111] If the target compensation method is the compensation method for aging equipment, then the pollution level of the current transformer is obtained, and the original value of insulation resistance is compensated by an LSTM (Long Short-Term Memory) compensator based on the pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter.
[0112] Optionally, the compensation methods used for healthy equipment and aging equipment are different. When using the compensation method for healthy equipment, the effective temperature and humidity compensation parameters are input into the lightweight polynomial model to compensate for the original insulation resistance value. This lightweight polynomial model is expressed by the following formula:
[0113] R comp =R raw *{[α(T eff -25)+β(H eff -60)+γ(T eff -25)(H eff -60)]}
[0114] Among them, R comp R is the compensated insulation resistance value. raw T represents the original value of the insulation resistance. eff H is the effective temperature compensation parameter. eff The parameters for effective humidity compensation are: α is the temperature compensation coefficient, β is the humidity compensation coefficient, and γ is the temperature-humidity coupling coefficient. The specific values of α, β, and γ are determined through laboratory accelerated aging tests and field data regression analysis. Different equipment types (oil-immersed / dry) require different parameters.
[0115] Optionally, when using compensation methods for equipment in its aging stage, due to the long operating years and severe aging of the equipment, there will be contamination generated during use. In this case, it is necessary to obtain the contamination level of the current transformer, and then compensate the original value of the insulation resistance through an LSTM compensator based on the contamination level, equipment aging factor value, effective temperature compensation parameters, and effective humidity compensation parameters, thereby ensuring a more accurate compensation result.
[0116] In optional embodiments of this application, the original value of insulation resistance is compensated using an LSTM compensator based on the pollution level, equipment aging factor value, effective temperature compensation parameter, and effective humidity compensation parameter, including:
[0117] The pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter are input into the LSTM compensator to obtain the dynamic confidence level.
[0118] The original value of insulation resistance is compensated based on dynamic confidence level.
[0119] Optionally, the pollution level can be one-hot encoded, and the effective temperature compensation parameter can be normalized to a reference of 25℃ and the effective humidity compensation parameter can be normalized to a reference of 60%RH. Then, the encoded pollution level, equipment aging factor value, normalized effective temperature compensation parameter and effective humidity compensation parameter are input into the LSTM compensator for adaptive edge calculation, obtain dynamic confidence and output it, and multiply the output dynamic confidence with the original value of insulation resistance to obtain the compensated insulation resistance.
[0120] The LSTM compensator includes an input layer, an embedding layer, LSTM layer 1 (64 units), Dropout (0.2), LSTM layer 2 (32 units), a fully connected layer, and an output layer.
[0121] In an optional embodiment of this application, the pollution level, equipment aging factor value, effective temperature compensation parameter, and effective humidity compensation parameter are input into the LSTM compensator to obtain dynamic confidence, including:
[0122] The pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter are input into the LSTM compensator to obtain the initial dynamic confidence level.
[0123] Based on the pollution level and condensation index, the correction amount for the dynamic confidence level is determined, and the initial dynamic confidence level is corrected according to the correction amount to obtain the dynamic confidence level.
[0124] Optionally, to ensure a more accurate insulation resistance value after compensation correction, the correction amount for the dynamic confidence level can be determined based on the pollution level and condensation index. Then, the initial dynamic confidence level is corrected based on this correction amount to obtain the final dynamic confidence level. For example, when the pollution level is ≥3 and the initial dynamic confidence level is <1.1, the corrected dynamic confidence level is:
[0125] K final =K×(1+0.1*(Pollution-2))
[0126] Among them, K final The corrected dynamic confidence level is given by K, where K is the initial dynamic confidence level and Pollution is the level of contamination.
[0127] When the condensation index > 0.7, the corrected dynamic confidence level is:
[0128] K final =K×min(1.3,1+0.2*CI)
[0129] Among them, K finalThe corrected dynamic confidence level is K, where K is the initial dynamic confidence level and CI is the condensation index.
[0130] In this application, the compensation strategy can be dynamically adjusted according to the equipment aging factor, which can accurately match the nonlinear degradation characteristics of the insulation material, significantly reduce the insulation resistance assessment error of the aging equipment, avoid premature retirement caused by conservative thresholds, extend the service life of the equipment, and significantly improve the economy and reliability of condition-based maintenance.
[0131] Step S105: Based on the humidity gradient and electromagnetic interference value, determine the data quality score of the current transformer, and use the compensated insulation resistance value and the data quality score of the current transformer as the results of the graded diagnostic evaluation.
[0132] This application can obtain the original insulation resistance value of the instrument transformer, temperature data at the set location, humidity data at the set location, electromagnetic interference value, and equipment aging factor value. Then, through multi-sensor data fusion and adaptive environmental compensation, the insulation resistance is compensated, reducing the impact of temperature and humidity on the insulation resistance. Furthermore, the quality of the instrument transformer can be evaluated. It has significant advantages such as strong environmental adaptability, excellent anti-interference ability, and low operation and maintenance cost. It can effectively extend the equipment life and improve the reliability of power grid operation, promoting the transformation of insulation monitoring from periodic maintenance to intelligent predictive maintenance.
[0133] In an optional embodiment of this application, the data quality score of the current transformer is determined based on the humidity gradient and electromagnetic interference value, including:
[0134] The gradient score of the current transformer is determined based on the humidity gradient and the preset gradient threshold, and the electromagnetic interference score of the current transformer is determined based on the electromagnetic interference value.
[0135] Based on the respective weights of the gradient score and the electromagnetic interference score, the gradient score and the electromagnetic interference score are weighted together to obtain the data quality score of the transformer.
[0136] Optionally, a preset gradient threshold can be obtained, and then the gradient score of the current transformer can be determined as 1 - 0.01 × (preset gradient threshold humidity gradient) based on the humidity gradient and the preset gradient threshold. Alternatively, an electromagnetic interference threshold can be obtained, and then the electromagnetic interference score of the current transformer can be determined based on the following formula:
[0137] EMI score = 1 - Electromagnetic interference value / 1.0
[0138] Among them, the EMI score is the electromagnetic interference score.
[0139] Furthermore, the obtained gradient score and electromagnetic interference score can be weighted based on their respective weights to obtain the data quality score of the transformer.
[0140] In this application, the data quality score of the current transformer is determined by humidity gradient and electromagnetic interference value, that is, the reliability of the measurement data is evaluated by quantification. This can significantly improve the accuracy and reliability of insulation resistance diagnosis, while supporting standardized data interaction and reducing false alarm rate and invalid maintenance.
[0141] This application provides a graded diagnostic and evaluation device for the insulation resistance of a current transformer, such as... Figure 2 As shown, the device may include: a data acquisition module 201, a weight determination module 202, a compensation parameter determination module 203, a resistance compensation module 204, and an evaluation result determination module 205, wherein,
[0142] The data acquisition module is used to acquire real-time data from the current transformer. The real-time data includes the original value of insulation resistance, temperature data at the set location, humidity data at the set location, electromagnetic interference value, and equipment aging factor value.
[0143] The weight determination module is used to determine the humidity gradient value based on the humidity data and to determine whether the humidity gradient is greater than the preset threshold. If the humidity gradient is greater than the preset threshold, the current transformer is divided into 5 layers along the set height direction, and the temperature weight and humidity weight of each layer are determined.
[0144] The compensation parameter determination module is used to obtain the temperature and humidity data corresponding to each layer, determine the effective temperature compensation parameters based on the temperature weight and temperature data of each layer, and determine the effective humidity compensation parameters based on the humidity weight and humidity data of each layer.
[0145] The resistance compensation module is used to determine the target compensation method based on the relationship between the equipment aging factor value and the set factor threshold, and to compensate the original value of insulation resistance according to the effective temperature compensation parameter, the effective humidity compensation parameter and the target compensation method to obtain the compensated insulation resistance value.
[0146] The evaluation result determination module is used to determine the data quality score of the current transformer based on the humidity gradient and the electromagnetic interference value, and to use the compensated insulation resistance value and the data quality score of the current transformer as the graded diagnostic evaluation result.
[0147] Optionally, the temperature data at the set location includes the temperature data from the temperature sensor at the top of the transformer and the temperature data from the temperature sensor at the bottom of the transformer; the humidity data at the set location includes the humidity data from the humidity sensor at the top of the transformer and the humidity data from the humidity sensor at the bottom of the transformer. When the transformer is divided into 5 layers along the set height, the weight determination module is specifically used for:
[0148] Set the position of the current transformer corresponding to the top sensor as the top, set the position of the current transformer corresponding to the bottom sensor as the bottom, and set the middle position between the top and bottom as the middle.
[0149] The position of the current transformer corresponding to the top and middle is set as the upper part, and the position of the current transformer corresponding to the middle and bottom is set as the lower part.
[0150] Optionally, the compensation parameter determination module, when determining the effective temperature compensation parameters based on the temperature weights and temperature data of each layer, is specifically used for:
[0151] Obtain the height coordinates of each layer of the current transformer, and perform differential processing on the temperature data at the set position based on the height coordinates of each layer to obtain the temperature data corresponding to the upper part, the middle part, and the lower part.
[0152] Based on the temperature weight of each layer, the temperature data at the set location, the temperature data corresponding to the upper part, the temperature data corresponding to the middle part, and the temperature data corresponding to the lower part, the effective temperature compensation parameters are determined.
[0153] Optionally, when determining the effective humidity compensation parameters based on the humidity weight and humidity data of each layer, the compensation parameter determination module is specifically used for:
[0154] Obtain the height coordinates of each layer of the current transformer, and perform differential processing on the humidity data at the set position based on the height coordinates of each layer to obtain the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part.
[0155] The effective humidity compensation parameters are determined based on the temperature weight of each layer, the humidity data at the set location, the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part.
[0156] Optionally, after determining the effective humidity compensation parameters, the compensation parameter determination module is also used for:
[0157] If the humidity data of the humidity sensor at the bottom of the current transformer is greater than the preset humidity threshold, the condensation index is determined based on the humidity data of the humidity sensor at the bottom of the current transformer.
[0158] The humidity effective compensation parameters are corrected based on the condensation index to obtain the corrected humidity effective compensation parameters;
[0159] When compensating for the original value of insulation resistance based on effective temperature compensation parameters, effective humidity compensation parameters, and the target compensation method, the resistance compensation module is specifically used for:
[0160] The original value of insulation resistance is compensated based on the effective temperature compensation parameters, the corrected effective humidity compensation parameters, and the target compensation method.
[0161] Optionally, the target compensation method includes compensation methods for healthy equipment and compensation methods for aging equipment. The target compensation method is determined based on the relationship between the equipment aging factor value and a set factor threshold, including:
[0162] If the equipment aging factor value is less than the set factor threshold, the target compensation method is determined to be the compensation method for healthy equipment.
[0163] If the equipment aging factor value is not less than the set factor threshold, then the target compensation method is determined to be the compensation method for equipment in the aging period.
[0164] Optionally, when the resistance compensation module compensates the original value of the insulation resistance based on the effective temperature compensation parameters, effective humidity compensation parameters, and the target compensation method, it is specifically used for:
[0165] If the target compensation method is the compensation method for healthy equipment, then the original value of insulation resistance is compensated by a lightweight polynomial model based on the effective temperature compensation parameters and effective humidity compensation parameters.
[0166] If the target compensation method is the compensation method for equipment in the aging period, then the pollution level of the current transformer is obtained, and the original value of the insulation resistance is compensated by the LSTM compensator according to the pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter.
[0167] Optionally, when the resistance compensation module compensates for the original value of insulation resistance using an LSTM compensator based on the pollution level, equipment aging factor value, effective temperature compensation parameters, and effective humidity compensation parameters, it is specifically used for:
[0168] The pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter are input into the LSTM compensator to obtain the dynamic confidence level.
[0169] The original value of insulation resistance is compensated based on dynamic confidence level.
[0170] Optionally, when the resistance compensation module inputs the pollution level, equipment aging factor value, effective temperature compensation parameter, and effective humidity compensation parameter into the LSTM compensator to obtain the dynamic confidence level, it is specifically used for:
[0171] The pollution level, equipment aging factor value, effective temperature compensation parameter and effective humidity compensation parameter are input into the LSTM compensator to obtain the initial dynamic confidence level.
[0172] Based on the pollution level and condensation index, the correction amount for the dynamic confidence level is determined, and the initial dynamic confidence level is corrected according to the correction amount to obtain the dynamic confidence level.
[0173] Optionally, the evaluation result determination module, when determining the data quality score of the current transformer based on the humidity gradient and electromagnetic interference value, is specifically used for:
[0174] The gradient score of the current transformer is determined based on the humidity gradient and the preset gradient threshold, and the electromagnetic interference score of the current transformer is determined based on the electromagnetic interference value.
[0175] Based on the respective weights of the gradient score and the electromagnetic interference score, the gradient score and the electromagnetic interference score are weighted together to obtain the data quality score of the transformer.
[0176] The instrument for classifying and evaluating the insulation resistance of a current transformer in this embodiment can execute the method for classifying and evaluating the insulation resistance of a current transformer shown in the embodiment of this application. The implementation principle is similar and will not be described again here.
[0177] This application provides an electronic device, which includes a processor and a memory configured to store machine-readable instructions that, when executed by the processor, cause the processor to perform a graded diagnostic evaluation method for the insulation resistance of a current transformer.
[0178] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 The illustrated electronic device includes a processor 2001 and a memory 2003. The processor 2001 and the memory 2003 are connected, for example, via a bus 2002. Optionally, the electronic device 2000 may further include a transceiver 2004. It should be noted that in practical applications, the transceiver 2004 is not limited to one type, and the structure of this electronic device 2000 does not constitute a limitation on the embodiments of this application.
[0179] Processor 2001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 2001 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
[0180] Bus 2002 may include a pathway for transmitting information between the aforementioned components. Bus 2002 may be a PCI bus or an EISA bus, etc. Bus 2002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0181] The memory 2003 may be ROM or other type of static storage device capable of storing static information and instructions, RAM or other type of dynamic storage device capable of storing information and instructions, or EEPROM, CD-ROM or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.
[0182] The memory 2003 stores the application code that executes the scheme of this application, and its execution is controlled by the processor 2001. The processor 2001 executes the application code stored in the memory 2003 to implement... Figure 2 The illustrated embodiment provides the operation of a graded diagnostic evaluation device for the insulation resistance of a current transformer.
[0183] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.
[0184] The above description is only a partial embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. A method for graded diagnosis and evaluation of the insulation resistance of a current transformer, characterized in that, include: Acquire real-time data from the current transformer, including the original insulation resistance value, temperature data at the set location, humidity data at the set location, electromagnetic interference value, and equipment aging factor value. The humidity gradient value is determined based on the humidity data, and it is determined whether the humidity gradient is greater than a preset threshold. If the humidity gradient is greater than the preset threshold, the current transformer is divided into 5 layers along the set height direction, and the temperature weight and humidity weight of each layer are determined. Obtain the temperature and humidity data corresponding to each layer. Based on the temperature weight and temperature data of each layer, determine the effective temperature compensation parameters. Also, based on the humidity weight and humidity data of each layer, determine the effective humidity compensation parameters. The target compensation method is determined based on the relationship between the equipment aging factor value and the set factor threshold. The original value of the insulation resistance is then compensated based on the effective temperature compensation parameter, the effective humidity compensation parameter, and the target compensation method to obtain the compensated insulation resistance value. Based on the humidity gradient and the electromagnetic interference value, the data quality score of the current transformer is determined, and the compensated insulation resistance value and the data quality score of the current transformer are used as the results of the graded diagnostic evaluation.
2. The method according to claim 1, characterized in that, The temperature data at the set location includes the temperature data from the temperature sensor at the top of the current transformer and the temperature data from the temperature sensor at the bottom of the current transformer. The humidity data at the set location includes the humidity data from the humidity sensor at the top of the current transformer and the humidity data from the humidity sensor at the bottom of the current transformer. The current transformer is divided into 5 layers along the set height direction, including: The position of the current transformer corresponding to the uppermost sensor is set as the top, the position of the current transformer corresponding to the lowermost sensor is set as the bottom, and the middle position between the top and the bottom is set as the middle. The position of the current transformer corresponding to the location between the top and the middle is designated as the upper part, and the position of the current transformer corresponding to the location between the middle and the bottom is designated as the lower part.
3. The method according to claim 2, characterized in that, The determination of effective temperature compensation parameters based on the temperature weight of each layer and the temperature data includes: Obtain the height coordinates corresponding to each layer of the current transformer, and perform differential processing on the temperature data at the set position based on the height coordinates corresponding to each layer to obtain the temperature data corresponding to the upper part, the temperature data corresponding to the middle part, and the temperature data corresponding to the lower part. The effective temperature compensation parameters are determined based on the temperature weight of each layer, the temperature data at the set position, the temperature data corresponding to the upper part, the temperature data corresponding to the middle part, and the temperature data corresponding to the lower part.
4. The method according to claim 2, characterized in that, The step of determining effective humidity compensation parameters based on the humidity weight of each layer and the humidity data includes: Obtain the height coordinates corresponding to each layer of the current transformer, and perform differential processing on the humidity data at the set position based on the height coordinates corresponding to each layer to obtain the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part. The effective humidity compensation parameter is determined based on the temperature weight of each layer, the humidity data at the set location, the humidity data corresponding to the upper part, the humidity data corresponding to the middle part, and the humidity data corresponding to the lower part.
5. The method according to claim 2, characterized in that, After determining the effective humidity compensation parameters, the method further includes: If the humidity data of the humidity sensor at the bottom of the current transformer is greater than the preset humidity threshold, the condensation index is determined based on the humidity data of the humidity sensor at the bottom of the current transformer. The humidity effective compensation parameter is corrected based on the condensation index to obtain the corrected humidity effective compensation parameter; The compensation of the original value of the insulation resistance based on the effective temperature compensation parameter, the effective humidity compensation parameter, and the target compensation method includes: The original value of the insulation resistance is compensated based on the effective temperature compensation parameter, the corrected effective humidity compensation parameter, and the target compensation method.
6. The method according to claim 5, characterized in that, The target compensation method includes compensation methods for healthy equipment and compensation methods for aging equipment. Determining the target compensation method based on the relationship between the equipment aging factor value and a set factor threshold includes: If the equipment aging factor value is less than the set factor threshold, then the target compensation method is determined to be the compensation method for the healthy equipment. If the equipment aging factor value is not less than the set factor threshold, then the target compensation method is determined to be the compensation method for the aging equipment.
7. The method according to claim 6, characterized in that, The compensation of the original value of the insulation resistance based on the effective temperature compensation parameter, the effective humidity compensation parameter, and the target compensation method includes: If the target compensation method is the compensation method for the healthy period equipment, then the original value of the insulation resistance is compensated by a lightweight polynomial model based on the effective temperature compensation parameters and the effective humidity compensation parameters; If the target compensation method is the compensation method for the aging equipment, then the pollution level of the current transformer is obtained, and the original value of the insulation resistance is compensated by an LSTM compensator based on the pollution level, the equipment aging factor value, the effective temperature compensation parameter, and the effective humidity compensation parameter.
8. The method according to claim 7, characterized in that, The compensation of the original insulation resistance value using an LSTM compensator based on the pollution level, the equipment aging factor value, the effective temperature compensation parameter, and the effective humidity compensation parameter includes: The pollution level, the equipment aging factor value, the effective temperature compensation parameter, and the effective humidity compensation parameter are input into the LSTM compensator to obtain the dynamic confidence level. The original value of the insulation resistance is compensated based on the dynamic confidence level.
9. The method according to claim 8, characterized in that, The process of inputting the pollution level, the equipment aging factor value, the effective temperature compensation parameter, and the effective humidity compensation parameter into the LSTM compensator to obtain dynamic confidence levels includes: The pollution level, the equipment aging factor value, the effective temperature compensation parameter, and the effective humidity compensation parameter are input into the LSTM compensator to obtain the initial dynamic confidence level. Based on the pollution level and the condensation index, the correction amount of the dynamic confidence level is determined, and the initial dynamic confidence level is corrected based on the correction amount of the dynamic confidence level to obtain the dynamic confidence level.
10. The method according to claim 8, characterized in that, The step of determining the data quality score of the current transformer based on the humidity gradient and the electromagnetic interference value includes: The gradient score of the current transformer is determined based on the humidity gradient and the preset gradient threshold, and the electromagnetic interference score of the current transformer is determined based on the electromagnetic interference value. Based on the respective weights of the gradient score and the electromagnetic interference score, a weighted average is applied to the gradient score and the electromagnetic interference score to obtain the data quality score of the current transformer.