Transformer bushing state evaluation method, device, equipment, medium and product

Abstract

The invention relates to a transformer bushing state evaluation method, device and equipment, a medium and a product, and relates to the technical field of electric power. The method comprises the following steps: acquiring measurement data under at least one operation state characteristic corresponding to a to-be-evaluated transformer bushing; according to the measurement data of the at least one operation state characteristic, selecting a target attribute influencing the operation state of the transformer bushing from the at least one candidate attribute of the transformer bushing; determining at least one attribute category of the transformer bushing according to the at least one attribute value corresponding to each target attribute; for each attribute category, obtaining a state division threshold value of at least one running state feature under the attribute category; and determining a target operation state of the transformer bushing of the attribute category according to the measurement data of the at least one operation state feature and the corresponding state division threshold. By adopting the method, targeted evaluation can be performed on transformer bushings of different attribute categories, and objective and accurate transformer bushing state evaluation results can be obtained.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to methods, devices, equipment, media and products for evaluating the condition of transformer bushings. Background Art

[0002] Transformer bushings primarily support ground insulation of lead wires, provide current flow, and protect against contamination, rain, and moisture. They are an essential insulating structure in developing ultra-high voltage (UHV) power systems. The safety and stability of transformer bushings directly impact the operating status of the transformer, and thus the stability and reliability of the power system. Therefore, evaluating the operating status of transformer bushings is crucial.

[0003] In related technologies, the method for evaluating the operating status of a transformer bushing mainly determines the operating status of the transformer bushing based on whether relevant characteristic indicators exceed a threshold value. However, the above-mentioned method for evaluating the operating status of a transformer bushing cannot objectively reflect the actual operating status of the transformer bushing. Summary of the Invention

[0004] Based on this, it is necessary to provide a transformer bushing status assessment method, device, equipment, medium and product that can objectively reflect the actual operating status of the transformer bushing in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for assessing the condition of a transformer bushing, comprising:

[0006] Obtaining measurement data corresponding to at least one operating state characteristic of the transformer bushing to be evaluated;

[0007] selecting, based on the measurement data of at least one operating state characteristic, a target attribute affecting the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing;

[0008] determining at least one attribute category of the transformer bushing according to at least one attribute value corresponding to each target attribute;

[0009] For each attribute category, obtaining a state division threshold value of at least one operating state feature under the attribute category; the state division threshold value is used to determine a measurement data range corresponding to at least one preset operating state;

[0010] A target operating state of the transformer bushing of the attribute category is determined according to the measurement data of at least one operating state feature and the state classification threshold under the attribute category.

[0011] In one embodiment, based on measurement data of at least one operating status characteristic corresponding to the transformer bushing, a target attribute affecting the operating status is selected from at least one candidate attribute of the transformer bushing. The method includes: determining, for each candidate attribute of the transformer bushing, a state influence coefficient corresponding to the candidate attribute based on the measurement data of the at least one operating status characteristic corresponding to the transformer bushing; and selecting, based on the state influence coefficient, the target attribute affecting the operating status from the at least one candidate attribute of the transformer bushing.

[0012] In one embodiment, determining a state influence coefficient corresponding to a candidate attribute based on measurement data of at least one operating state characteristic corresponding to a transformer bushing includes: generating a first sample set based on measurement data of at least one operating state characteristic corresponding to the transformer bushing under the candidate attribute, and generating a second sample set based on measurement data of at least one operating state characteristic corresponding to each transformer bushing under other candidate attributes except the candidate attribute, and performing the following iterative steps until a preset number of iterations is reached: selecting a target sample from the first sample set and / or the second sample set; selecting a first sample from the first sample set whose distance to the target sample is less than a first preset distance, and selecting a second sample from the second sample set whose distance to the target sample is less than a second preset distance; and updating the state influence coefficient corresponding to the candidate attribute based on a first distance between the first sample and the target sample, and a second distance between the second sample and the target sample.

[0013] In one embodiment, obtaining a state classification threshold value for at least one operating state feature under an attribute category includes: obtaining measurement data of at least one operating state feature corresponding to a reference transformer bushing under the attribute category; for each operating state feature, accumulating the number of reference transformer bushings in ascending order of the measurement data corresponding to each reference transformer bushing, and using the measurement data corresponding to when a proportion of the accumulated number of reference transformer bushings reaches a preset proportion as the state classification threshold value.

[0014] In one embodiment, a target operating state of a transformer bushing of an attribute category is determined based on measurement data of at least one operating state feature and a corresponding state classification threshold, including: determining, for each operating state feature, a membership function corresponding to at least one preset operating state based on the measurement data of the operating state feature and the corresponding state classification threshold; determining, based on the measurement data of each operating state feature and the membership function corresponding to the at least one preset operating state, a membership degree of each operating state feature to the at least one preset operating state; and determining the target operating state of the transformer bushing of the attribute category based on the membership degree of each operating state feature to the at least one preset operating state.

[0015] In one embodiment, a target operating state of a transformer bushing of an attribute category is determined based on the degree of membership of each operating state feature to at least one preset operating state, including: for each operating state feature, according to the degree of membership of the operating state feature to at least one preset operating state, determining trust allocation information that the operating state feature belongs to the attribute category; and using evidence synthesis rules to fuse the trust allocation information of each operating state feature belonging to each attribute category to determine the target operating state of the transformer bushing of the attribute category.

[0016] In a second aspect, the present application further provides a transformer bushing condition assessment device, comprising:

[0017] A first acquisition module is configured to acquire measurement data corresponding to at least one operating state characteristic of the transformer bushing to be evaluated;

[0018] a selection module, configured to select a target attribute affecting the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing based on the measurement data of at least one operating state characteristic;

[0019] A first determining module is configured to determine at least one attribute category of the transformer bushing according to at least one attribute value included in each target attribute;

[0020] A second acquisition module is configured to acquire, for each attribute category, a state classification threshold value of at least one operating state feature under the attribute category; the state classification threshold value is used to determine a measurement data range corresponding to at least one preset operating state;

[0021] The second determining module is configured to determine a target operating state of the transformer bushing of an attribute category according to measurement data of at least one operating state feature and a corresponding state classification threshold.

[0022] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0023] Obtain measurement data of at least one operating state characteristic corresponding to a transformer bushing to be evaluated; select a target attribute that affects the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing based on the measurement data of the at least one operating state characteristic; determine at least one attribute category of the transformer bushing based on at least one attribute value corresponding to each target attribute; obtain, for each attribute category, a state classification threshold for at least one operating state characteristic under the attribute category; the state classification threshold is used to determine a range of measurement data corresponding to at least one preset operating state; and determine a target operating state of the transformer bushing of the attribute category based on the measurement data of the at least one operating state characteristic and the corresponding state classification threshold.

[0024] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0025] Obtain measurement data of at least one operating state characteristic corresponding to a transformer bushing to be evaluated; select a target attribute that affects the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing based on the measurement data of the at least one operating state characteristic; determine at least one attribute category of the transformer bushing based on at least one attribute value corresponding to each target attribute; obtain, for each attribute category, a state classification threshold for at least one operating state characteristic under the attribute category; the state classification threshold is used to determine a range of measurement data corresponding to at least one preset operating state; and determine a target operating state of the transformer bushing of the attribute category based on the measurement data of the at least one operating state characteristic and the corresponding state classification threshold.

[0026] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0027] Obtain measurement data of at least one operating state characteristic corresponding to a transformer bushing to be evaluated; select a target attribute that affects the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing based on the measurement data of the at least one operating state characteristic; determine at least one attribute category of the transformer bushing based on at least one attribute value corresponding to each target attribute; obtain, for each attribute category, a state classification threshold for at least one operating state characteristic under the attribute category; the state classification threshold is used to determine a range of measurement data corresponding to at least one preset operating state; and determine a target operating state of the transformer bushing of the attribute category based on the measurement data of the at least one operating state characteristic and the corresponding state classification threshold.

[0028] The above-mentioned transformer bushing condition assessment method, device, equipment, medium and product select a target attribute that affects the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing based on measurement data of at least one operating state characteristic, thereby accurately assessing the operating state of the transformer bushing under the influence of the target attribute. Moreover, based on at least one attribute value corresponding to each target attribute corresponding to the transformer bushing, the transformer bushing can be divided into at least one attribute category, which is equivalent to grading the transformer bushings. The attribute categories of the transformer bushings can objectively reflect the individual differences of the transformer bushings, thereby enabling targeted assessment of transformer bushings of different attribute categories, thereby obtaining more objective and accurate transformer bushing condition assessment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 2. FIG. 1 is an application environment diagram of a transformer bushing condition assessment method according to an embodiment;

[0031] Figure 2 1 is a flow chart of a transformer bushing condition assessment method according to an embodiment;

[0032] Figure 3 Schematic diagram of a process for selecting target attributes in one embodiment;

[0033] Figure 4 A schematic diagram of a flow chart of steps for obtaining a state classification threshold in one embodiment;

[0034] Figure 5 1 is a flow chart of steps for determining a target operating state in one embodiment;

[0035] Figure 6 is a flow chart of a transformer bushing condition assessment method according to another embodiment;

[0036] Figure 7 is a schematic diagram of a Weibull distribution curve corresponding to pressure in one embodiment;

[0037] Figure 8 Schematic diagram of membership function curves corresponding to various preset operating states in one embodiment;

[0038] Figure 9 A schematic diagram of fusion membership corresponding to various preset operating states in one embodiment;

[0039] Figure 10 is a structural block diagram of a transformer bushing condition assessment device according to one embodiment;

[0040] Figure 11 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0042] The transformer bushing condition assessment method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104 or placed in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc. Server 104 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0043] In an exemplary embodiment, Figure 2 As shown in the figure, a transformer bushing condition assessment method is provided, which is applied to Figure 1 The server in the example is used to illustrate, including the following S210~S250. Among them:

[0044] S210: Obtain measurement data of at least one operating state characteristic corresponding to the transformer bushing to be evaluated.

[0045] The operating status characteristics can be understood as characteristics that reflect the operating status of the transformer bushing. Optionally, the operating status characteristics may include at least one of pressure, temperature, moisture, hydrogen, acetylene, leakage current, dielectric loss factor, and capacitance. Pressure can be understood as the pressure of the insulating medium (such as oil or sulfur hexafluoride) inside the transformer bushing. Temperature can be understood as the temperature of the insulating medium during operation. Moisture can be understood as the concentration of water molecules in the insulating oil or insulating paper inside the transformer bushing. Hydrogen can be understood as the volume concentration of hydrogen dissolved in the insulating oil inside the transformer bushing. Acetylene can be understood as the volume concentration of acetylene generated by high-temperature arc discharge inside the transformer bushing. Leakage current can be understood as stray current on the insulation surface or inside the transformer bushing. Dielectric loss factor can be understood as the ratio of energy loss to reactive power of the insulating material inside the transformer bushing. Capacitance can be understood as the equivalent capacitance between the conductor and the end screen inside the transformer bushing.

[0046] In an optional embodiment, measurement data under the corresponding operating state feature may be acquired according to the sensor corresponding to each operating state feature.

[0047] S220 : Selecting a target attribute that affects the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing according to the measurement data of at least one operating state feature.

[0048] The candidate attributes can be understood as attribute characteristics of the transformer bushing that may affect its operating status. Optionally, the candidate attributes may include at least one of voltage level, operating life, oil grade, manufacturer, operating environment temperature, operating environment humidity, and operating environment altitude. Voltage level can be understood as the maximum system voltage the transformer bushing is designed to withstand, such as 10kV, 110kV, or 500kV. Operating life can be understood as the expected service life of the transformer bushing under normal operating conditions, such as typically 20 to 30 years. Oil grade can be understood as the type of insulating oil used in the transformer bushing. Manufacturer can be understood as the manufacturer of the transformer bushing. Operating environment temperature can be understood as the temperature range of the transformer bushing's operating environment. Operating environment humidity can be understood as the relative humidity of the air in the transformer bushing's operating environment. Operating environment altitude can be understood as the altitude of the transformer bushing's installation location.

[0049] In an optional embodiment, a target attribute whose influence on the operating state of the transformer bushing exceeds a set threshold may be selected from at least one candidate attribute of the transformer bushing.

[0050] In an optional embodiment, a target attribute that affects the operating state of the transformer bushing can be selected from at least one candidate attribute of the transformer bushing based on measurement data of at least one operating state characteristic corresponding to the transformer bushing, based on a pre-trained attribute selection model. The attribute selection model can be implemented based on a traditional machine learning model or a deep learning model, and this application does not impose any restrictions on the specific network structure of the attribute selection model.

[0051] In an optional embodiment, the attribute selection model can be trained in the following manner: obtaining measurement data corresponding to at least one operating state characteristic of a reference transformer bushing; obtaining candidate attribute samples of the reference transformer bushing, and target attribute samples selected from the candidate attribute samples; using the measurement data corresponding to at least one operating state characteristic of the reference transformer bushing and the candidate attribute samples of the reference transformer bushing as training input samples, and using the target attribute samples selected from the candidate attribute samples as training output samples, adjusting the network parameters of the pre-constructed attribute selection model until a training cutoff condition is satisfied. The training cutoff condition can include at least one of the following: the number of training samples reaches a preset number threshold, the number of model training iterations reaches a preset number threshold, the model accuracy reaches a preset accuracy threshold, and the model converges. The preset number threshold, the preset number threshold, and the preset accuracy threshold can be set or adjusted by a technician based on needs or experience, or determined through repeated experiments, and this application does not impose any limitations on this.

[0052] S230: Determine at least one attribute category of the transformer bushing according to at least one attribute value corresponding to each target attribute.

[0053] In an optional embodiment, at least one attribute value corresponding to each target attribute may be arranged and combined to obtain at least one attribute value combination, and each attribute value combination may be understood as an attribute category.

[0054] Exemplarily, the target attributes may include the following three attributes: voltage level, service life, and oil number. The voltage level may include three voltage values: A, B, and C; the service life may include two service life values: XX and YY. The oil number may include two oil numbers: A and B. By permuting and combining the attribute values ​​of the above three attributes, 12 combinations, i.e., 12 attribute value combinations, or 12 attribute categories, may be obtained. For example, a transformer bushing with a voltage level of A, a service life of YY, and an oil number of A; another example is a transformer bushing with a voltage level of B, a service life of XX, and an oil number of A; and so on.

[0055] S240 , for each attribute category, obtaining a state classification threshold of at least one operating state feature under the attribute category; the state classification threshold is used to determine a measurement data range corresponding to at least one preset operating state.

[0056] The at least one preset operating state can be understood as at least one operating state obtained by artificially classifying the operating state of the transformer bushing. Optionally, the preset operating state can include at least one of a normal state, a caution state, an abnormal state, and a critical state. A normal state can be understood as meaning that all operating state characteristics are stable, the measured data of each operating state characteristic is within the normal range, and the transformer bushing can operate stably and long-term. A transformer bushing in a normal state can undergo routine inspection, maintenance, and testing according to the normal cycle or an extended period of one year. A caution state can be understood as meaning that the measured data of one or more operating state characteristics of the transformer bushing are trending towards a caution threshold, and the transformer bushing can continue to operate. A transformer bushing in a caution state can undergo routine inspection, maintenance, and testing at a cycle less than or equal to the normal cycle, but requires enhanced monitoring. An abnormal state can be understood as meaning that the measured data of the operating state characteristics of the transformer bushing have significantly changed, exceeding the caution threshold. A transformer bushing in an abnormal state can be inspected at an appropriate time, and the type of maintenance and power outage can be determined based on the inspection results. Enhanced monitoring should be implemented before maintenance. A serious condition can be understood as the measurement data of a single operating status characteristic of the transformer bushing seriously exceeding the standard; transformer bushings in a serious condition should be inspected as soon as possible, and the type of maintenance and power outage should be determined based on the inspection results. Monitoring should be strengthened before maintenance.

[0057] For each attribute category, each operating state feature corresponds to a state classification threshold under the attribute category.

[0058] In an optional embodiment, each operating state feature corresponds to a state classification threshold under a corresponding attribute category, which may be preset or obtained based on an empirical value.

[0059] In another optional embodiment, the state classification threshold corresponding to each operating state feature under the corresponding attribute category may be obtained by statistically analyzing measurement data of at least one operating state feature corresponding to a reference transformer bushing under the corresponding attribute category.

[0060] S250: Determine a target operating state of the transformer bushing of the attribute category according to measurement data of at least one operating state feature and a state classification threshold under the attribute category.

[0061] In an optional embodiment, for each attribute category, the target measurement data range to which the measurement data of at least one operating state characteristic belongs can be determined based on the measurement data of at least one operating state characteristic and the corresponding state division threshold; the target operating state can be determined based on the measurement data range corresponding to at least one preset operating state and the target measurement data range to which the measurement data of at least one operating state characteristic belongs.

[0062] In the above-mentioned transformer bushing condition assessment method, a target attribute that affects the operating state of the transformer bushing is selected from at least one candidate attribute of the transformer bushing based on measurement data of at least one operating state characteristic, thereby accurately assessing the operating state of the transformer bushing under the influence of the target attribute. Furthermore, based on at least one attribute value corresponding to each target attribute corresponding to the transformer bushing, the transformer bushing can be divided into at least one attribute category, which is equivalent to grading the transformer bushings. The attribute categories of the transformer bushings can objectively reflect the individual differences of the transformer bushings, thereby enabling targeted assessment of transformer bushings of different attribute categories, thereby obtaining a more objective and accurate transformer bushing condition assessment result.

[0063] Based on the technical solutions of the above embodiments, the present application also provides another optional embodiment. In this optional embodiment, the step of selecting target attributes in S220 is refined.

[0064] like Figure 3 As shown, the step of selecting target attributes in S220 may include:

[0065] S310 , for each candidate attribute of the transformer bushing, determine a state influence coefficient corresponding to the candidate attribute based on measurement data of at least one operating state feature corresponding to the transformer bushing.

[0066] The state influence coefficient can be understood as the influence degree of each candidate attribute on the operating state of the transformer bushing. Optionally, the larger the state influence coefficient corresponding to the candidate attribute, the higher the influence degree of the candidate attribute on the operating state of the transformer bushing.

[0067] S320 : Selecting a target attribute that affects the operating state from at least one candidate attribute of the transformer bushing according to the state influence coefficient.

[0068] In an optional embodiment, a target attribute with the largest state influence coefficient may be selected from at least one candidate attribute according to the state influence coefficient.

[0069] In yet another optional embodiment, a target attribute having a state influence coefficient exceeding a set threshold may be selected from at least one candidate attribute based on the state influence coefficient.

[0070] In another optional embodiment, at least one candidate attribute may be sorted in descending order of state influence coefficient, and a preset number of target attributes may be selected from the at least one candidate attribute.

[0071] In this embodiment, by selecting a target attribute that affects the operating state from at least one candidate attribute of the transformer bushing based on the state influence coefficient, the target attribute that affects the operating state can be accurately determined. For example, the target attribute that has a greater impact on the operating state can be screened out, thereby accurately evaluating the operating state of the transformer bushing under the influence of the target attribute.

[0072] Based on the technical solutions of the above embodiments, the present application also provides another optional embodiment, in which the step of determining the state influence coefficient in S310 is refined. According to the measurement data of at least one operating state feature corresponding to the transformer bushing, the state influence coefficient corresponding to the candidate attribute is determined, including: generating a first sample set according to the measurement data of at least one operating state feature corresponding to the transformer bushing under the candidate attribute, and generating a second sample set according to the measurement data of at least one operating state feature corresponding to each transformer bushing under other candidate attributes except the candidate attribute, and performing the following iterative steps until a preset number of iterations is reached: selecting a target sample from the first sample set and / or the second sample set; selecting a first sample from the first sample set whose distance to the target sample is less than a first preset distance, and selecting a second sample from the second sample set whose distance to the target sample is less than a second preset distance; updating the state influence coefficient corresponding to the candidate attribute according to the first distance between the first sample and the target sample, and the second distance between the second sample and the target sample.

[0073] Among them, each sample in the first sample set can be understood as a sample of the same type, each sample in the second sample set can be understood as a sample of the same type, and any sample in the first sample set and any sample in the second sample set are heterogeneous samples.

[0074] In an optional embodiment, at least one target sample may be selected. In an optional embodiment, the target sample may be randomly selected from the first sample set and / or the second sample set.

[0075] In an optional embodiment, a first preset number of first samples whose distance from the target sample is less than a first preset distance may be selected from the first sample set; and a second preset number of second samples whose distance from the target sample is less than a second preset distance may be selected from the second sample set. Optionally, the first preset distance is optional, and the first preset number and the second preset number may be the same.

[0076] In an optional embodiment, the state influence coefficient corresponding to the candidate attribute can be obtained according to the following formula:

[0077]

[0078] In the above formula, W i W represents the size of the state influence coefficient of the i-th target sample x; i-1 represents the size of the state influence coefficient when iterating to the i-1th target sample; k represents the number of the first sample or the second sample selected. It should be understood here that the number of the first sample is the same as the number of the second sample; diff(x,H j (x)) represents the distance between the i-th target sample x and its j-th similar sample H (the first sample or the second sample); diff(x,M j (x)) represents the distance between the i-th sample x and its j-th heterogeneous sample M (the second sample or the first sample); m is the number of iterations; class(x) represents the category of the target sample x, p(C) represents the proportion of the number of samples in category C (that is, the category of the target sample x) to the total number of samples, and p(class(x)) represents the proportion of the number of samples in the category of the target sample x to the total number of samples.

[0079] In this embodiment, through the above iterative process, different weights, i.e., state influence coefficients, are assigned to each candidate attribute based on the correlation between each candidate attribute and the candidate attribute category. The above algorithm is simple and has high computational efficiency, and can quickly determine the state influence coefficient corresponding to each candidate attribute.

[0080] On the basis of the technical solutions of the above embodiments, the present application also provides another optional embodiment. In this optional embodiment, the step of obtaining the state division threshold in S230 is refined.

[0081] See also Figure 4 The step of obtaining the state classification threshold in S230 may include:

[0082] S410: For each attribute category, obtain measurement data of at least one operating status feature corresponding to a reference transformer bushing in the attribute category.

[0083] In an optional embodiment, for each attribute category, historical measurement data of at least one operating status feature corresponding to a reference transformer bushing of the same attribute category may be obtained.

[0084] The historical measurement data may be understood as measurement data generated in a historical time period.

[0085] S420: For each operating state feature, the number of reference transformer bushings is accumulated in ascending order of the measurement data corresponding to each reference transformer bushing, and the measurement data corresponding to when the proportion of the accumulated number of reference transformer bushings reaches a preset proportion is used as the state classification threshold.

[0086] The state classification threshold may be determined based on the number of preset operating states. Optionally, when there are four preset operating states, the number of state classification thresholds may be three. For example, the preset operating states may include a normal operating state, a caution operating state, an abnormal operating state, and a severe operating state, and the state classification thresholds may include a caution threshold, an abnormal threshold, and a severe threshold.

[0087] The preset number ratio may be determined based on the number of reference transformer bushings under various preset operating states and the total number of reference transformer bushings.

[0088] In an optional embodiment, for the threshold for dividing the state between the normal operating state and the caution operating state, the preset number ratio may be determined based on the number of reference transformer bushings in the normal operating state among all reference transformer bushings and the total number of reference transformer bushings. For the threshold for dividing the state between the caution operating state and the abnormal operating state, the preset number ratio may be determined based on the sum of the number of reference transformer bushings in the normal operating state and the caution operating state among all reference transformer bushings and the total number of reference transformer bushings. For the threshold for dividing the state between the abnormal operating state and the critical operating state, the preset number ratio may be determined based on the sum of the number of reference transformer bushings in the normal operating state, the caution operating state, and the abnormal operating state among all reference transformer bushings and the total number of reference transformer bushings.

[0089] For example, in historical data of reference transformer bushings with a voltage level of 110 kV, the proportions of reference transformer bushings in normal operation, reference transformer bushings in caution operation and above, and reference transformer bushings in abnormal operation and above are 90%, 92%, and 95%, respectively. By accumulating the number of reference transformer bushings in ascending order of the measurement data corresponding to each reference transformer bushing, it can be found that when the number of reference transformer bushings in normal operation reaches 90%, the corresponding measurement data is 0.0635 MPa, when the number of reference transformer bushings in normal operation and caution operation reaches 92%, the corresponding measurement data is 0.0652 MPa, and when the number of reference transformer bushings in normal operation, caution operation, and abnormal operation reaches 95%, the corresponding measurement data is 0.0683 MPa.

[0090] In an optional embodiment, for each operating state characteristic, a Weibull distribution curve can be generated based on the measurement data of each reference transformer bushing under that operating state characteristic and the Weibull distribution probability density function. Based on the Weibull distribution curve, the cumulative number of reference transformer bushings in at least one operating state is determined, and the corresponding measurement data when the cumulative number of reference transformer bushings reaches a preset number is used as a state classification threshold.

[0091] Among them, the probability density function of Weibull distribution is:

[0092]

[0093] In the above formula, is the shape parameter; is the scale parameter; For measurement data.

[0094] In this embodiment, the number of reference transformer bushings is accumulated in ascending order of the measurement data corresponding to each reference transformer bushing, and the measurement data corresponding to when the proportion of the accumulated number of reference transformer bushings reaches a preset proportion is used as the state division threshold. In this way, the state division threshold for dividing various preset operating states can be quickly obtained. The method is relatively simple and can improve the efficiency of obtaining the state division threshold.

[0095] Based on the technical solutions of the above embodiments, the present application also provides another optional embodiment. In this optional embodiment, the step of determining the target operating state in S250 is refined.

[0096] See also Figure 5 The step of determining the target operating state in S250 may include:

[0097] S510 , for each operating state feature, determining a membership function corresponding to at least one preset operating state according to measurement data of the operating state feature and a corresponding state classification threshold.

[0098] The membership function can be understood as the degree to which the transformer bushing belongs to a preset operating state. It should be noted that the set of measurement data corresponding to the preset operating state in this application is a fuzzy set. In an optional embodiment, after obtaining the state classification threshold, the values ​​around the state classification threshold can be fuzzified, that is, discrete values ​​can be converted to continuous values.

[0099] In an optional embodiment, the mean and variance of the membership functions corresponding to various preset operating states can be obtained based on the state division threshold. For each preset operating state, the corresponding membership function can be obtained based on the mean, variance and state division threshold corresponding to the preset operating state.

[0100] In an optional embodiment, the attention threshold, abnormality threshold, and severity threshold may be defined as follows: , and .according to , and , it can be determined that the means of the membership functions corresponding to the four preset operating states are , , and , and their variances are , , and .

[0101] The relationships between the mean, variance, and state division threshold corresponding to the four preset operating states are:

[0102]

[0103]

[0104]

[0105]

[0106] From this we can get the membership function corresponding to the normal operating state:

[0107]

[0108] Note that the membership function corresponding to the running state is:

[0109]

[0110] The membership function corresponding to the abnormal operating state is:

[0111]

[0112] The membership function corresponding to the severe operating state is:

[0113]

[0114] S520 : Determine the membership degree of each operating state feature to at least one preset operating state based on the measurement data of each operating state feature and the membership function corresponding to at least one preset operating state.

[0115] In an optional embodiment, for each operating state feature, the measurement data corresponding to the operating state feature may be substituted into a membership function corresponding to at least one preset operating state to determine the membership degree of the operating state feature to at least one preset operating state.

[0116] S530 : For each attribute category, determine a target operating state of the transformer bushing of the attribute category according to the membership degree of each operating state feature to at least one preset operating state.

[0117] In an optional embodiment, for each preset operating state, the fusion membership corresponding to the preset operating state is determined according to the membership of each operating state feature to the preset operating state, and then the preset operating state with the highest corresponding membership can be used as the target operating state of the transformer bushing.

[0118] In an optional embodiment, a pre-trained operating state determination model can be used to determine the target operating state of the transformer bushing for a given attribute category based on the degree of membership of each operating state feature to at least one preset operating state. The operating state determination model can be implemented based on a traditional machine learning model or a deep learning model. This application does not impose any restrictions on the specific network structure of the operating state determination model.

[0119] In an optional embodiment, the operating state determination model can be trained in the following manner: obtaining membership samples of each operating state feature belonging to at least one preset operating state; and target operating state samples of the transformer bushing of the attribute category; using the membership samples of each operating state feature belonging to at least one preset operating state as training input samples, and using the target operating state samples of the transformer bushing of the attribute category as training output samples, and adjusting the network parameters of the pre-constructed operating state determination model until a training cutoff condition is met. The training cutoff condition may include at least one of the number of training samples reaching a preset number threshold, the number of model training iterations reaching a preset number threshold, the accuracy of the model reaching a preset accuracy threshold, and the model tending to converge. The preset number threshold, the preset number threshold, and the preset accuracy threshold can be set or adjusted by technicians based on needs or experience, or determined repeatedly through a large number of experiments, and this application does not impose any restrictions on this.

[0120] In the embodiment of the present application, the target operating state of the transformer bushing of the attribute category can be determined more accurately by determining the degree of membership of each operating state feature to at least one preset operating state.

[0121] Based on the technical solutions of the above embodiments, the present application also provides another optional embodiment, in which the step of determining the target operating state in S530 is refined. The target operating state of the transformer bushing of the attribute category is determined based on the membership degree of each operating state feature to at least one preset operating state, including: determining a fusion weight corresponding to each operating state feature based on the preset relative importance between each operating state feature; and fusing the membership degree of each operating state feature to at least one preset operating state based on the fusion weight to obtain the target operating state of the transformer bushing of the attribute category.

[0122] The preset relative importance can be understood as a relative importance determined based on the importance of any fault of the transformer bushing according to different operating state characteristics. Optionally, the preset relative importance can be manually preset.

[0123] For example, the relative importance of any two operating status features may be manually evaluated according to Table 1, where i and j represent any two different operating status features.

[0124] Table 1

[0125]

[0126] In an optional embodiment, the judgment matrix A may be obtained according to the following formula based on the preset relative importance between the operating state features:

[0127]

[0128] In the above formula, n represents the number of operating state features; Indicates the preset relative importance between operating status feature i and operating status feature j.

[0129] Next, we can get the antisymmetric matrix B based on the judgment matrix A:

[0130]

[0131] In the above formula, i=1,2,…,n; j=1,2,…,n.

[0132] Next, we can get the optimal transfer matrix C based on the antisymmetric matrix B:

[0133]

[0134] Next, we can obtain the quasi-optimal consistent matrix D based on the optimal transfer matrix C:

[0135]

[0136] Finally, the fusion weights corresponding to each operating state feature can be obtained:

[0137]

[0138] In a feasible embodiment, the membership of each operating state feature to at least one preset operating state may be weighted and summed according to the fusion weight corresponding to each operating state feature to obtain the target operating state of the transformer bushing of the attribute category.

[0139] In a feasible embodiment, the Dempster-Shafer (DS) evidence fusion theory may be used to fuse the membership degree of each operating state feature to at least one preset operating state.

[0140] Each operating state feature can be defined as a piece of evidence. For each operating state feature, the trust allocation information of the operating state feature belonging to the attribute category is calculated based on the degree of membership of each operating state feature to at least one preset operating state:

[0141]

[0142] in,

[0143]

[0144] In the above formula, The measurement data representing the characteristics of the i-th operating state; 、 Represents the operating status characteristics The degree of membership and trust belonging to the k-th state; Indicates operating status characteristics uncertainty; Indicates the credibility of the running status feature, which is determined by the fusion weight Calculated, where λ represents the priority credibility coefficient, usually taken as 0.9; is the maximum value of the variable weight in the fusion running state feature.

[0145] The trust distribution information of each operating state feature belonging to each attribute category is fused using evidence synthesis rules to obtain the target operating state of the transformer bushing with a certain attribute category:

[0146]

[0147] In the above formula, A is the recognition framework, A={normal, caution, abnormal, severe}; , Represent the recognition framework of two operating state features, where ∈{normal, caution, abnormal, severe, uncertainty}, ∈{normal, caution, abnormal, severe, uncertainty}; is an empty set, indicating and The uncertainty is taken as the value of the total trust distribution. m(A) is the total trust distribution output after the fusion of the two operating state features. Based on the total trust distribution result, the target operating state of the transformer bushing is obtained.

[0148] In the embodiment of the present application, the mutually related operating state features can be fused through the fusion weights corresponding to the various operating state features, thereby obtaining a more realistic target operating state.

[0149] Based on the technical solutions of the above embodiments, the present application also provides another optional embodiment, in which a method for evaluating the status of a transformer bushing is described in detail.

[0150] See also Figure 6 The flowchart of the transformer bushing condition assessment method shown in FIG. 1 includes:

[0151] S610: Obtain measurement data of at least one operating state characteristic corresponding to a transformer bushing to be evaluated.

[0152] S620. For each candidate attribute of the transformer bushing, generate a first sample set based on the measurement data of at least one operating state characteristic corresponding to the transformer bushing under the candidate attribute, and generate a second sample set based on the measurement data of at least one operating state characteristic corresponding to each transformer bushing under other candidate attributes, and perform the following iterative steps until a preset number of iterations is reached: select a target sample from the first sample set and / or the second sample set; select a first sample from the first sample set whose distance from the target sample is less than a first preset distance, and select a second sample from the second sample set whose distance from the target sample is less than a second preset distance; and update the state influence coefficient corresponding to the candidate attribute based on the first distance between the first sample and the target sample and the second distance between the second sample and the target sample.

[0153] S630: Select a target attribute that affects the operating state from at least one candidate attribute of the transformer bushing according to the state influence coefficient.

[0154] S640: For each attribute category, obtain measurement data of at least one operating status feature corresponding to a reference transformer bushing in the attribute category.

[0155] S650: For each operating state feature, the number of reference transformer bushings is accumulated in ascending order of the measurement data corresponding to the reference transformer bushings, and the measurement data corresponding to when the proportion of the accumulated number of reference transformer bushings reaches a preset proportion is used as the state classification threshold.

[0156] S660 : For each operating state feature, determine a membership function corresponding to at least one preset operating state according to the measurement data of the operating state feature and the corresponding state classification threshold.

[0157] S670 : Determine the membership degree of each operating state feature to at least one preset operating state based on the measurement data of each operating state feature and the membership function corresponding to at least one preset operating state.

[0158] S680: Determine a fusion weight corresponding to each operating state feature according to a preset relative importance of each operating state feature.

[0159] S690 , for each attribute category, fusing the membership degree of each operating state feature to at least one preset operating state according to the fusion weight, to obtain a target operating state of the transformer bushing of the attribute category.

[0160] Based on the technical solutions of the above embodiments, the present application also provides another optional embodiment, in which a method for evaluating the status of a transformer bushing is described in detail.

[0161] In this optional embodiment, eight operating status characteristics that affect the operating status of the transformer bushing are selected, namely, pressure, temperature, moisture, hydrogen, acetylene, leakage current, dielectric loss factor, and capacitance value. The operating status of the transformer bushing having four candidate attributes, namely, voltage level, operating years, manufacturer, and oil grade, is evaluated.

[0162] First, for each candidate attribute, the corresponding state influence coefficient is calculated based on the measured data under various operating state characteristics corresponding to the transformer bushing. For example, the state influence coefficient for voltage level is 0.298777, the state influence coefficient for service life is 0.233666, the state influence coefficient for manufacturer is 0.233871, and the state influence coefficient for oil grade is 0.233686. Based on the state influence coefficients corresponding to these four candidate attributes, the candidate attribute with the largest state influence coefficient can be selected as the target attribute, that is, voltage level.

[0163] According to the three preset voltage values ​​corresponding to the voltage levels: 110 kV, 220 kV and 500 kV, transformer bushings can be divided into three categories: transformer bushings with a voltage level of 110 kV, transformer bushings with a voltage level of 220 kV, and transformer bushings with a voltage level of 550 kV.

[0164] The following describes the process of evaluating the operating status of a 110 kV transformer bushing, taking the 110 kV transformer bushing as an example.

[0165] According to the preset relative importance between any operating state characteristics, a judgment matrix is ​​obtained. According to the judgment matrix, an antisymmetric matrix is ​​obtained. According to the antisymmetric matrix, an optimal transfer matrix is ​​obtained. According to the optimal transfer matrix, a pseudo-optimal consistent matrix is ​​obtained. According to the pseudo-optimal consistent matrix, the fusion weights corresponding to each operating state characteristic are obtained. For example, the fusion weight corresponding to pressure is 0.15796001, the fusion weight corresponding to temperature is 0.14484997, the fusion weight corresponding to moisture is 0.15796001, the fusion weight corresponding to hydrogen is 0.12180382, the fusion weight corresponding to acetylene is 0.13282801, the fusion weight corresponding to leakage current is 0.07898001, the fusion weight corresponding to dielectric loss factor is 0.11169459, and the fusion weight corresponding to capacitance value is 0.09392358.

[0166] Taking pressure as an example, according to the measured value of pressure, the Weibull distribution curve corresponding to the pressure can be obtained, such as Figure 7 As shown, the horizontal axis of the Weibull distribution curve represents the measured value of pressure, and the vertical axis represents the probability density value.

[0167] In the historical data corresponding to a reference transformer bushing with a voltage level of 110 kV, the proportions of transformer bushings in normal operating conditions, cautionary operating conditions, and abnormal operating conditions were 90%, 92%, and 95%, respectively. Based on the three cumulative probability density values ​​of 0.9, 0.92, and 0.95 and the Weibull distribution curve, the caution threshold for classifying the four preset operating states (normal operating conditions, cautionary operating conditions, abnormal operating conditions, and critical operating conditions) is 0.0635 MPa, the abnormal threshold is 0.0652 MPa, and the critical threshold is 0.0683 MPa.

[0168] Next, based on the attention threshold of 0.0635MPa, the abnormal threshold of 0.0652MPa, and the severe threshold of 0.0683MPa, the membership functions corresponding to the four preset operating states can be calculated. And the membership function curve is obtained according to the membership function, as shown in the following example: Figure 8 shown. Figure 8 In the figure, f1(x) represents the membership function curve corresponding to the normal operation state; f2(x) represents the membership function curve corresponding to the caution operation state; f3(x) represents the membership function curve corresponding to the abnormal operation state; and f4(x) represents the membership function curve corresponding to the severe operation state.

[0169] Next, the pressure measurements are substituted into the membership functions corresponding to the four preset operating states to obtain the pressure memberships for each of the preset operating states. For example, the pressure membership for the normal operating state is 0.0002, the pressure membership for the caution operating state is 0.5180, the pressure membership for the abnormal operating state is 0.2383, and the pressure membership for the critical operating state is 0.0000.

[0170] Then, according to the above process, the membership degrees of the other 7 operating state characteristics under various preset operating states can be obtained, as shown in Table 2:

[0171] Table 2

[0172]

[0173] Finally, for each preset operating state, the membership of the 8 operating state features under the preset operating state can be fused, that is, weighted summation can be performed to obtain the fused membership under the preset operating state. The fused membership corresponding to each preset operating state can be found in Figure 9 Then, the preset operating state with the highest fusion membership can be used as the target operating state corresponding to the transformer bushing with a voltage level of 110 kV.

[0174] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0175] Based on the same inventive concept, embodiments of the present application also provide a transformer bushing condition assessment device for implementing the aforementioned transformer bushing condition assessment method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the transformer bushing condition assessment device provided below can be found in the above-described limitations of the transformer bushing condition assessment method and are not further elaborated here.

[0176] In an exemplary embodiment, Figure 10As shown, a transformer bushing status assessment device is provided, comprising: a first acquisition module 1010, a selection module 1020, a first determination module 1030, a second acquisition module 1040 and a second determination module 1050, wherein:

[0177] A first acquisition module 1010 is configured to acquire measurement data corresponding to at least one operating state characteristic of a transformer bushing to be evaluated;

[0178] A selection module 1020 is configured to select a target attribute that affects the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing based on the measurement data of at least one operating state characteristic;

[0179] A first determining module 1030 is configured to determine at least one attribute category of the transformer bushing according to at least one attribute value included in each target attribute;

[0180] The second acquisition module 1040 is configured to acquire, for each attribute category, a state classification threshold value of at least one operating state feature under the attribute category; the state classification threshold value is used to determine a measurement data range corresponding to at least one preset operating state;

[0181] The second determining module 1050 is configured to determine a target operating state of the transformer bushing of the attribute category according to the measurement data of at least one operating state feature and the state classification threshold under the attribute category.

[0182] In one embodiment, the selection module 1020 is specifically configured to: determine, for each candidate attribute of the transformer bushing, a state influence coefficient corresponding to the candidate attribute based on measurement data of at least one operating state characteristic corresponding to the transformer bushing; and select, based on the state influence coefficient, a target attribute that affects the operating state from the at least one candidate attribute of the transformer bushing.

[0183] In one embodiment, the selection module 1020 is specifically used to: generate a first sample set based on the measurement data of at least one operating status feature corresponding to the transformer bushing under the candidate attribute, and generate a second sample set based on the measurement data of at least one operating status feature corresponding to each transformer bushing under other candidate attributes except the candidate attribute, and perform the following iterative steps until a preset number of iterations is reached: select a target sample from the first sample set and / or the second sample set; select a first sample from the first sample set whose distance to the target sample is less than a first preset distance, and select a second sample from the second sample set whose distance to the target sample is less than a second preset distance; update the state influence coefficient corresponding to the candidate attribute according to the first distance between the first sample and the target sample, and the second distance between the second sample and the target sample.

[0184] In one embodiment, the second acquisition module 1040 is specifically configured to: obtain measurement data of at least one operating status characteristic corresponding to the reference transformer bushings under the attribute category; for each operating status characteristic, accumulate the number of reference transformer bushings in ascending order of the measurement data corresponding to each reference transformer bushing; and use the measurement data corresponding to when the proportion of the accumulated number of reference transformer bushings reaches a preset proportion as the state classification threshold.

[0185] In one embodiment, the second determination module 1050 is specifically configured to: determine, for each operating state feature, a membership function corresponding to at least one preset operating state based on the measurement data of the operating state feature and a corresponding state classification threshold; determine, based on the measurement data of each operating state feature and the membership function corresponding to the at least one preset operating state, the membership degree of each operating state feature to the at least one preset operating state; and determine, based on the membership degree of each operating state feature to the at least one preset operating state, a target operating state of the transformer bushing of the attribute category.

[0186] In one embodiment, the second determination module 1050 is specifically configured to: for each operating state feature, determine, based on the degree of membership of the operating state feature to at least one preset operating state, trust allocation information of the operating state feature belonging to an attribute category; and fuse the trust allocation information of each operating state feature belonging to each attribute category using an evidence synthesis rule to obtain a target operating state of the transformer bushing of the determined attribute category.

[0187] Each module in the aforementioned transformer bushing condition assessment device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0188] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 11As shown. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, memory and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store measurement data corresponding to at least one operating state characteristic of the transformer bushing to be evaluated. The I / O interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for evaluating the condition of a transformer bushing is implemented.

[0189] Those skilled in the art will understand that Figure 11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0190] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0191] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0192] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0193] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0194] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, 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 application.

[0195] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for evaluating the condition of a transformer bushing, characterized in that: The method comprises: Obtaining measurement data corresponding to at least one operating state characteristic of the transformer bushing to be evaluated; selecting, based on the measurement data of the at least one operating state characteristic, a target attribute that affects the operating state of the transformer bushing from at least one candidate attribute of the transformer bushing; determining at least one attribute category of the transformer bushing according to at least one attribute value corresponding to each target attribute; For each attribute category, obtaining a state classification threshold value of the at least one operating state feature under the attribute category; the state classification threshold value is used to determine a measurement data range corresponding to at least one preset operating state; The target operating state of the transformer bushing of the attribute category is determined according to the measurement data of the at least one operating state feature and the state classification threshold under the attribute category.

2. The method according to claim 1, characterized in that The step of selecting a target attribute that affects the operating state from at least one candidate attribute of the transformer bushing based on the measurement data of at least one operating state feature corresponding to the transformer bushing includes: For each candidate attribute of the transformer bushing, determining a state influence coefficient corresponding to the candidate attribute based on measurement data of at least one operating state feature corresponding to the transformer bushing; A target attribute affecting the operating state is selected from at least one candidate attribute of the transformer bushing according to the state influence coefficient.

3. The method according to claim 2, characterized in that The determining, based on the measurement data of at least one operating state feature corresponding to the transformer bushing, a state influence coefficient corresponding to the candidate attribute includes: Generating a first sample set based on the measurement data of at least one operating status feature corresponding to the transformer bushing under the candidate attribute, and generating a second sample set based on the measurement data of at least one operating status feature corresponding to each of the transformer bushings under other candidate attributes except the candidate attribute, and performing the following iterative steps until a preset number of iterations is reached: Selecting a target sample from the first sample set and / or the second sample set; Selecting a first sample from the first sample set whose distance to the target sample is less than a first preset distance, and selecting a second sample from the second sample set whose distance to the target sample is less than a second preset distance; The state influence coefficient corresponding to the candidate attribute is updated according to a first distance between the first sample and the target sample, and a second distance between the second sample and the target sample.

4. The method according to claim 1, wherein The obtaining of the state classification threshold of the at least one operating state feature under the attribute category includes: Obtaining measurement data of at least one operating status characteristic corresponding to a reference transformer bushing under the attribute category; For each operating state feature, the number of reference transformer bushings is accumulated in ascending order of the measurement data corresponding to each reference transformer bushing, and the measurement data corresponding to the time when the proportion of the accumulated number of reference transformer bushings reaches a preset proportion is used as the state division threshold.

5. The method according to any one of claims 1 to 4, characterized in that The determining, based on the measurement data of the at least one operating state feature and the corresponding state classification threshold, the target operating state of the transformer bushing of the attribute category includes: For each operating state feature, determining a membership function corresponding to at least one preset operating state based on the measurement data of the operating state feature and the corresponding state classification threshold; Determining, based on the measurement data of each operating state feature and the membership function corresponding to the at least one preset operating state, the membership degree of each operating state feature to the at least one preset operating state; The target operating state of the transformer bushing of the attribute category is determined according to the membership degree of each operating state feature to at least one preset operating state.

6. The method according to claim 5, characterized in that The determining of the target operating state of the transformer bushing of the attribute category according to the degree of membership of each operating state feature to at least one preset operating state includes: For each operating state feature, determining, according to the degree of membership of the operating state feature to at least one preset operating state, trust allocation information that the operating state feature belongs to the attribute category; The trust allocation information of each operating state feature belonging to each attribute category is fused using evidence synthesis rules to obtain the target operating state of the transformer bushing that determines the attribute category.

7. A transformer bushing condition assessment device, characterized in that: The device comprises: A first acquisition module is configured to acquire measurement data corresponding to at least one operating state characteristic of the transformer bushing to be evaluated; a selection module, configured to select, based on the measurement data of the at least one operating state characteristic, a target attribute affecting the operating state of the transformer bushing from the at least one candidate attribute of the transformer bushing; A first determining module is configured to determine at least one attribute category of the transformer bushing according to at least one attribute value included in each target attribute; A second acquisition module is configured to acquire, for each attribute category, a state classification threshold value of the at least one operating state feature under the attribute category; the state classification threshold value is used to determine a measurement data range corresponding to at least one preset operating state; The second determining module is configured to determine a target operating state of the transformer bushing of the attribute category according to the measurement data of the at least one operating state feature and a corresponding state classification threshold.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images