Transformer bushing state evaluation method and device and electronic equipment

Abstract

The invention discloses a transformer bushing state evaluation method, a transformer bushing state evaluation device and electronic equipment. The method comprises the steps that target working condition data and target state data corresponding to a target casing are obtained, the target working condition data comprise current working condition data, and the target state data comprise current state data; determining a first correlation parameter between the target working condition data and the target state data; calling a reference casing data set; according to the reference casing data set, determining second correlation parameters between the current state data and the multiple pieces of reference state data; and according to the current working condition data, the current state data, the first correlation parameter and the second correlation parameter, performing state evaluation on the target casing to obtain a target evaluation result corresponding to the target casing. According to the invention, the technical problem that the state evaluation of the transformer bushing is inaccurate when the state evaluation is carried out on the transformer bushing in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of fault detection, and more specifically, to a method, apparatus, and electronic device for assessing the condition of transformer bushings. Background Technology

[0002] In related technologies, because transformer high-voltage bushings operate under high voltage, high current, and harsh environments for extended periods, their performance can be affected, leading to transformer failures and even power grid failures. Therefore, it is necessary to assess the condition of transformer bushings. However, current technologies suffer from inaccurate assessments of transformer bushing conditions.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, and electronic device for assessing the condition of transformer bushings, in order to at least solve the technical problem of inaccurate condition assessment of transformer bushings in related technologies.

[0005] According to one aspect of the present invention, a method for assessing the condition of a transformer bushing is provided, comprising: acquiring target operating condition data and target state data corresponding to a target bushing, wherein the target operating condition data includes current operating condition data and the target state data includes current state data; determining a first correlation parameter between the target operating condition data and the target state data; retrieving a set of reference bushing data, wherein the set of reference bushing data includes reference state data corresponding to multiple reference bushings, wherein the similarity index between the attribute parameters of the multiple reference bushings and the attribute parameters of the target bushing is greater than a similarity threshold, and the attribute parameters include bushing type; determining a second correlation parameter between the current state data and the multiple reference state data based on the set of reference bushing data; and assessing the condition of the target bushing based on the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter to obtain a target assessment result corresponding to the target bushing.

[0006] Optionally, the step of evaluating the state of the target bushing based on the current operating condition data, the current state data, the first association parameter, and the second association parameter to obtain a target evaluation result corresponding to the target bushing includes: determining multiple state attribute items corresponding to the target bushing; determining current attribute values ​​corresponding to the multiple state attribute items based on the current state data; determining reference attribute values ​​corresponding to the multiple state attribute items based on the current operating condition data and the first association parameter; and evaluating the state of the target bushing based on the current attribute values ​​and reference attribute values ​​corresponding to the multiple state attribute items, and the second association parameter to obtain a target evaluation result corresponding to the target bushing.

[0007] Optionally, determining the second correlation parameter between the current state data and multiple reference state data based on the reference sheath data set includes: when the second correlation parameter includes a difference correlation parameter, determining the difference index between the current state data and the multiple reference state data based on the reference sheath data set; determining the difference state data from the multiple reference state data based on the multiple difference indices, wherein the difference state data is the state data with the largest difference index among the multiple reference state data; and determining the difference correlation parameter between the current state data and the difference state data.

[0008] Optionally, determining the difference association parameter between the current state data and the difference state data includes: determining multiple difference attribute items based on the current state data and the difference state data; determining first difference attribute values ​​corresponding to the multiple difference attribute items based on the current state data; determining second difference attribute values ​​corresponding to the multiple difference attribute items based on the difference state data; and determining the difference association parameter based on the first and second difference attribute values ​​corresponding to the multiple difference attribute items.

[0009] Optionally, before acquiring the target operating condition data and target state data corresponding to the target sleeve, the method further includes: if the current state data includes current temperature data, determining the current sleeve image and current infrared image corresponding to the target sleeve, wherein the time difference between the acquisition time of the current sleeve image and the acquisition time of the current infrared image is less than a time threshold; determining the current fused image corresponding to the target sleeve based on the current sleeve image and the current infrared image; and determining the current temperature data corresponding to the target sleeve based on the current fused image.

[0010] Optionally, the step of evaluating the state of the target sleeve based on the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter to obtain a target evaluation result corresponding to the target sleeve includes: determining the state change trend corresponding to the target sleeve based on the second correlation parameter; and evaluating the state of the target sleeve based on the current operating condition data, the current state data, the first correlation parameter, and the state change trend to obtain a target evaluation result corresponding to the target sleeve.

[0011] Optionally, before acquiring the target operating condition data and target status data corresponding to the target bushing, the process includes: determining the environmental operating condition data and power grid operating condition data corresponding to the target bushing; and determining the target operating condition data corresponding to the target bushing based on the environmental operating condition data and the power grid operating condition data.

[0012] According to one aspect of the present invention, a transformer bushing condition assessment device is provided, comprising: an acquisition module, configured to acquire target operating condition data and target state data corresponding to a target bushing, wherein the target operating condition data includes current operating condition data and the target state data includes current state data; a first determination module, configured to determine a first correlation parameter between the target operating condition data and the target state data; a retrieval module, configured to retrieve a set of reference bushing data, wherein the set of reference bushing data includes reference state data corresponding to multiple reference bushings respectively, wherein the similarity index between the attribute parameters of the multiple reference bushings and the attribute parameters of the target bushing is greater than a similarity threshold, and the attribute parameters include bushing type; a second determination module, configured to determine a second correlation parameter between the current state data and the multiple reference state data respectively based on the set of reference bushing data; and a third determination module, configured to perform a condition assessment on the target bushing based on the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter, to obtain a target assessment result corresponding to the target bushing.

[0013] According to one aspect of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the transformer bushing condition assessment method described in any of the preceding claims.

[0014] According to one aspect of the present invention, a computer-readable storage medium is provided, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the transformer bushing condition assessment method described in any of the preceding claims.

[0015] In this embodiment of the invention, target operating condition data and target state data corresponding to the target sleeve are acquired, wherein the target operating condition data includes current operating condition data and the target state data includes current state data; a first correlation parameter between the target operating condition data and the target state data is determined; a reference sleeve data set is retrieved, wherein the reference sleeve data set includes reference state data corresponding to multiple reference sleeves, wherein the similarity index between the attribute parameters of the multiple reference sleeves and the attribute parameters of the target sleeve is greater than a similarity threshold, and the attribute parameters include the sleeve model; based on the reference sleeve data set, a second correlation parameter between the current state data and the multiple reference state data is determined; based on the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter, the state of the target sleeve is evaluated to obtain a target evaluation result corresponding to the target sleeve. By determining the first correlation parameter between the target operating condition data and the target state data of the target bushing, the trend of the target bushing state changing with the operating condition can be reflected. By retrieving the reference bushing data set, the second correlation parameter between the current state data and multiple reference state data can be determined. This allows for a clearer definition of whether the state of the target bushing deviates from the acceptable range compared to bushings with similar attribute parameters. By combining the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter, the state of the target bushing can be accurately assessed. This solves the technical problem of inaccurate state assessment of transformer bushings in related technologies. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a transformer bushing condition assessment method according to an embodiment of the present invention;

[0018] Figure 2 This is a flowchart of the casing condition evaluation method in an optional embodiment of the present invention;

[0019] Figure 3 This is an online casing inspection system in an optional embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of the deployment method of the casing online monitoring system in an optional embodiment of the present invention;

[0021] Figure 5 This is a structural block diagram of a transformer bushing condition assessment device according to an embodiment of the present invention;

[0022] Figure 6This is a structural block diagram of a transformer bushing condition assessment device according to an embodiment of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] According to an embodiment of the present invention, an embodiment of a transformer bushing condition assessment method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a flowchart of a transformer bushing condition assessment method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0028] S102, acquire the target operating condition data and target status data corresponding to the target bushing, wherein the target operating condition data includes the current operating condition data and the target status data includes the current status data;

[0029] In step S102 of this application, target operating condition data and target status data corresponding to the target sleeve are obtained.

[0030] This involves target bushings, which are transformer bushings that require condition assessment.

[0031] This includes target operating condition data, which is data associated with the target bushing and reflects its operating environment and working conditions, including current operating condition data and historical operating condition data, used to comprehensively understand the external operating conditions of the bushing.

[0032] This involves target status data, which refers to data reflecting the performance, health status, and other characteristics of the target casing itself, including current status data and possible historical status data, used to assess the internal state of the casing.

[0033] This includes current operating condition data, which is part of the target operating condition data. This data reflects the operating conditions of the target casing at the current moment or within the current time period, and is used to reflect the external conditions of the casing operation in real time.

[0034] This includes current status data, which is the target status data within the target bushing itself at the current moment or time period. This data includes current insulation status parameters (leakage current signal, high-frequency partial discharge signal, dielectric loss signal, and equivalent capacitance signal of the bushing end screen, etc.), oil sample status parameters (data on dissolved hydrogen in the insulating oil inside the bushing, water content, oil pressure, and oil temperature, etc.), and external status parameters (visible light images and infrared thermal imaging spectra of the bushing exterior, etc.). These data are used to reflect the real-time health status of the bushing itself.

[0035] Target operating condition data and target status data can provide insights into the operating environment, working conditions, performance, and health status of the target bushing, thus providing a data foundation for subsequent assessment of the target bushing's condition.

[0036] S104, determine the first correlation parameter between the target working condition data and the target state data;

[0037] In step S104 of this application, a first correlation parameter between the target operating condition data and the target state data is determined.

[0038] This involves a first correlation parameter, which is a parameter used to reflect the relationship between target operating condition data and target state data, and is used to describe the changing trend or characteristics of the casing state under the corresponding operating conditions.

[0039] Determining the first correlation parameter between the target operating condition data and the target state data can quantify and describe the relationship between the two, and help to reveal the specific impact of operating conditions on the casing state.

[0040] S106, retrieve the reference casing data set, wherein the reference casing data set includes reference status data corresponding to multiple reference casings respectively, and the similarity index between the attribute parameters of the multiple reference casings and the attribute parameters of the target casing is greater than the similarity threshold, and the attribute parameters include casing model;

[0041] In step S106 of this application, a reference sleeve data set is retrieved.

[0042] This involves multiple reference bushings, which are a set of transformer bushings used for comparative analysis with the target bushing. These bushings have a high degree of similarity to the target bushing in terms of attribute parameters.

[0043] This involves reference state data, which refers to the state data of each of these reference bushings, including their insulation state parameters, oil sample state parameters, external state parameters, etc., used for comparison and analysis with the state data of the target bushing.

[0044] This involves attribute parameters, which are used to describe the characteristics of the casing and determine the similarity between the reference casing and the target casing. Attribute parameters include, but are not limited to, casing type and casing service life.

[0045] This includes a similarity index, which measures the degree of similarity between the target casing and the reference casing in terms of attribute parameters.

[0046] This involves a similarity threshold, which is a preset threshold used to determine whether the reference sheath and the target sheath are sufficiently similar. Only when the similarity index is greater than this threshold will the reference sheath be included in the reference sheath dataset.

[0047] This includes the casing model number, which is a specific model identifier for the casing used to distinguish different types of casing.

[0048] The similarity index between the attribute parameters of the reference casing and the target casing is greater than the preset similarity threshold, which ensures that the reference casing and the target casing are sufficiently similar in characteristics, so that the reference state data can provide a reference for evaluating the state of the target casing.

[0049] S108, Based on the reference bushing data set, determine the second correlation parameters between the current status data and multiple reference status data respectively;

[0050] In step S108 provided in this application, a second correlation parameter is determined between the current state data and multiple reference state data based on the reference sleeve data set.

[0051] This involves a second correlation parameter, which is used to quantify the correlation between the current state data and various reference state data, such as difference correlation, to help evaluate the correlation between the target casing's state data and the reference casing's state data, such as the degree of difference.

[0052] By determining a second correlation parameter between the current state data and multiple reference state data based on the reference casing data set, the degree of correlation between the current state of the target casing and the state of the reference casing can be quantitatively evaluated, which helps to identify abnormal changes in the state of the target casing.

[0053] S110, based on the current working condition data, current status data, first correlation parameter, and second correlation parameter, perform a status assessment on the target casing to obtain the target assessment result corresponding to the target casing.

[0054] In step S110 provided in this application, the target sleeve is evaluated based on the current working condition data, the current status data, the first correlation parameter, and the second correlation parameter to obtain the target evaluation result corresponding to the target sleeve.

[0055] This includes the target assessment result, which is the final evaluation of the target bushing's condition after comprehensively considering current operating data, current status data, the first correlation parameter, and the second correlation parameter. This target assessment result reflects the target bushing's health status, performance level, and the presence of potential fault risks under current operating conditions. For example, the target assessment result includes the health status level (e.g., good, average, poor), the determination of whether a specific fault exists (e.g., partial discharge, insulation aging), and the prediction of the bushing's remaining service life.

[0056] By integrating information from multiple dimensions, including current operating condition data, current status data, first correlation parameter, and second correlation parameter, the target bushing is evaluated to accurately determine its health status and performance level under current operating conditions.

[0057] Through the above steps S102-S110, target operating condition data and target status data corresponding to the target bushing are obtained, wherein the target operating condition data includes current operating condition data, and the target status data includes current status data; a first correlation parameter between the target operating condition data and the target status data is determined; a reference bushing data set is retrieved, wherein the reference bushing data set includes reference status data corresponding to multiple reference bushings, and the similarity index between the attribute parameters of the multiple reference bushings and the attribute parameters of the target bushing is greater than a similarity threshold, and the attribute parameters include the bushing model; based on the reference bushing data set, a second correlation parameter between the current status data and the multiple reference status data is determined; based on the current operating condition data, the current status data, the first correlation parameter, and the second correlation parameter, the status of the target bushing is evaluated to obtain the target evaluation result corresponding to the target bushing. By determining the first correlation parameter between the target operating condition data and the target state data of the target bushing, the trend of the target bushing state changing with the operating condition can be reflected. By retrieving the reference bushing data set, the second correlation parameter between the current state data and multiple reference state data can be determined. This allows for a clearer definition of whether the state of the target bushing deviates from the acceptable range compared to bushings with similar attribute parameters. By combining the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter, the state of the target bushing can be accurately assessed. This solves the technical problem of inaccurate state assessment of transformer bushings in related technologies.

[0058] As an optional embodiment, based on current operating condition data, current state data, a first correlation parameter, and a second correlation parameter, a state assessment of the target bushing is performed to obtain a target assessment result corresponding to the target bushing. This includes: determining multiple state attribute items corresponding to the target bushing; determining current attribute values ​​corresponding to each of the multiple state attribute items based on the current state data; determining reference attribute values ​​corresponding to each of the multiple state attribute items based on the current operating condition data and the first correlation parameter; and performing a state assessment of the target bushing based on the current attribute values ​​and reference attribute values ​​corresponding to each of the multiple state attribute items, as well as the second correlation parameter, to obtain a target assessment result corresponding to the target bushing.

[0059] This embodiment describes the specific steps for performing a status assessment on the target sleeve based on current operating condition data, current status data, a first correlation parameter, and a second correlation parameter, to obtain a target assessment result corresponding to the target sleeve.

[0060] This involves multiple state attribute items, which are used to describe the state of the target bushing. These state attribute items are used to comprehensively describe the state of the bushing. For example, state attribute items may include insulation state parameters (such as leakage current, dielectric loss, etc.), oil sample state parameters (such as oil temperature, oil pressure, etc.), and external state parameters (such as bushing surface temperature, visible light image features, etc.).

[0061] This includes the current attribute value, which is the real-time measurement or observation value corresponding to multiple status attribute items of the target casing at the current time or within the current time period.

[0062] This involves reference attribute values, which are reference values ​​derived from the current operating condition data and the first associated parameter, corresponding to various state attribute items. For example, the reference attribute value could be an attribute threshold.

[0063] By identifying multiple status attribute items corresponding to the target casing, the status of the target casing can be decomposed into multiple dimensions to achieve quantitative evaluation under different dimensions. Furthermore, based on the current operating data and the first correlation parameter, the corresponding reference attribute value can be determined, which can provide a more accurate comparison benchmark for status evaluation. Thus, by comparing the current attribute value and the reference attribute value of each status attribute item, and in conjunction with the second correlation parameter, the accuracy of the target casing evaluation can be further improved.

[0064] As an optional embodiment, based on a set of reference sheath data, determining a second correlation parameter between the current state data and multiple reference state data includes: if the second correlation parameter includes a difference correlation parameter, determining a difference index between the current state data and multiple reference state data based on the set of reference sheath data; determining a difference state data from the multiple reference state data based on the multiple difference indices, wherein the difference state data is the state data with the largest difference index among the multiple reference state data; and determining a difference correlation parameter between the current state data and the difference state data.

[0065] This embodiment describes the specific steps for determining the second correlation parameter between the current state data and multiple reference state data based on the reference sleeve data set.

[0066] This involves a difference correlation parameter, which is used to quantify the correlation between the difference values ​​between the current state data and the differing state data. This difference correlation parameter specifically reflects the correlation between the differences in state attributes between the two.

[0067] This includes a difference index, which is a quantitative indicator used to measure the magnitude of the difference between the current state data and various reference state data, and is used to compare the degree of difference between the current state data and different reference state data.

[0068] This includes difference status data, which is the reference status data with the largest difference index among multiple reference status data.

[0069] By determining the difference index between the current state data and multiple reference state data, the degree of difference between the target casing state and each reference casing state can be quantitatively assessed. Selecting the difference state data with the largest difference index can pinpoint the reference state with the most significant difference from the target casing state, which usually means that the reference state deviates significantly from the target casing in some key attributes. Further determining the difference correlation parameters between the current state data and the difference state data can specifically reveal how the differences in these key attributes are related, thereby accurately locating potential problems with the target casing.

[0070] As an optional embodiment, determining the difference association parameter between the current state data and the difference state data includes: determining multiple difference attribute items based on the current state data and the difference state data; determining a first difference attribute value corresponding to each of the multiple difference attribute items based on the current state data; determining a second difference attribute value corresponding to each of the multiple difference attribute items based on the difference state data; and determining the difference association parameter based on the first difference attribute value and the second difference attribute value corresponding to each of the multiple difference attribute items.

[0071] This embodiment describes the specific steps for determining the difference correlation parameters between the current state data and the difference state data.

[0072] This involves multiple difference attribute items, which are state attribute items used to compare and analyze the specific differences between the current state data and the difference state data.

[0073] This involves a first difference attribute value, which is the value corresponding to multiple difference attribute items in the current state data.

[0074] This involves a second difference attribute value, which is the value corresponding to multiple difference attribute items in the difference state data.

[0075] By identifying multiple difference attribute items between the current state data and the difference state data, along with their corresponding first and second difference attribute values, the differences between the target sleeve and the difference state data in specific state attributes can be accurately identified. This makes the determination of difference correlation parameters more targeted and accurate, and enables the difference correlation parameters to specifically reflect the correlation between these difference attributes.

[0076] As an optional embodiment, before acquiring the target operating condition data and target state data corresponding to the target sleeve, the method further includes: if the current state data includes the current temperature data, determining the current sleeve image and the current infrared image corresponding to the target sleeve, wherein the time difference between the acquisition time of the current sleeve image and the acquisition time of the current infrared image is less than a time threshold; determining the current fused image corresponding to the target sleeve based on the current sleeve image and the current infrared image; and determining the current temperature data corresponding to the target sleeve based on the current fused image.

[0077] This embodiment describes the specific steps before obtaining the target operating condition data and target status data corresponding to the target casing.

[0078] This includes current temperature data, which is a temperature value related to the target sleeve measured in some way at the current moment or within the current time period, used to reflect the current temperature status of the sleeve.

[0079] This includes the current sleeve image, which is an image of the sleeve's appearance captured by a visible light imaging device at the current moment or within the current time period, used to visually demonstrate the sleeve's external structure and appearance.

[0080] This includes the current infrared image, which is a thermal distribution image of the sleeve captured by an infrared thermal imaging device at the current moment or within the current time period, used to reflect the temperature distribution on the surface and inside of the sleeve.

[0081] This involves the acquisition time, which is the specific time when the current sleeve image and the current infrared image were captured or recorded.

[0082] This involves a time difference, which is the difference between the acquisition time of the current sleeve image and the acquisition time of the current infrared image, used to measure how close the acquisition times of the two are.

[0083] This involves a time threshold, a preset value used to limit the maximum allowable time difference between the acquisition time of the current sleeve image and the current infrared image. Only when the time difference between the two images is less than this time threshold are they considered to be sufficiently close in time and suitable for subsequent fusion processing.

[0084] This involves the current fused image, which is obtained by fusing the current sheath image and the current infrared image together using certain image processing techniques. This fused image includes both the appearance information and temperature distribution information of the sheath, and can more comprehensively reflect the condition of the sheath.

[0085] With current status data including current temperature data, by determining the current sheath image and current infrared image corresponding to the target sheath, and ensuring that the acquisition time difference between the two is less than a time threshold, sufficiently close information about the sheath's appearance and temperature distribution can be obtained. The fused image obtained by combining these two images contains both the sheath's appearance and temperature distribution information, providing a more comprehensive reflection of the sheath's condition. The current temperature data determined based on the fused image improves the accuracy of the temperature data, contributing to a more accurate subsequent assessment of the target sheath's health status.

[0086] As an optional embodiment, the target bushing is evaluated based on the current operating condition data, current state data, a first correlation parameter, and a second correlation parameter to obtain a target evaluation result corresponding to the target bushing. This includes: determining the state change trend corresponding to the target bushing based on the second correlation parameter; and evaluating the state of the target bushing based on the current operating condition data, current state data, the first correlation parameter, and the state change trend to obtain a target evaluation result corresponding to the target bushing.

[0087] This embodiment describes the specific steps for performing a status assessment on the target sleeve based on current operating condition data, current status data, a first correlation parameter, and a second correlation parameter, to obtain a target assessment result corresponding to the target sleeve.

[0088] This includes the trend of state change, which is the pattern or direction of the target casing state changing over time, reflecting whether the casing state tends to stabilize, improve, or deteriorate.

[0089] By following the steps above, the trend of the target casing's state change can be determined based on the second correlation parameter, which can help us understand the direction of the casing's state development. Furthermore, by combining the current operating data, current state data, and the first correlation parameter for comprehensive evaluation, we can more accurately judge the current condition of the casing.

[0090] As an optional embodiment, before acquiring the target operating condition data and target status data corresponding to the target bushing, the process includes: determining the environmental operating condition data and power grid operating condition data corresponding to the target bushing; and determining the target operating condition data corresponding to the target bushing based on the environmental operating condition data and the power grid operating condition data.

[0091] This embodiment describes the specific steps before obtaining the target operating condition data and target status data corresponding to the target casing.

[0092] This includes environmental operating condition data, which is operating condition data related to the external environment of the target casing, including but not limited to ambient temperature, humidity, atmospheric pressure, and pollutant concentration. These data reflect the natural environmental conditions in which the casing operates.

[0093] This includes power grid operating condition data, which is operating condition data related to the power grid operating status of the target bushing, including but not limited to power grid voltage, current, load ratio, power factor, etc. These data reflect the electrical conditions of the power grid in which the bushing operates.

[0094] Determining the environmental and power grid operating conditions corresponding to the target bushing, and then using this data to determine the target operating conditions, allows for a comprehensive understanding of the external natural environment and power grid electrical conditions in which the bushing operates. This data comprehensively reflects the actual operating conditions of the bushing, providing crucial information for subsequent condition assessments.

[0095] Based on the above embodiments and optional embodiments, an optional implementation method is provided, which is described in detail below.

[0096] In related technologies, the long-term operation of transformer high-voltage bushings in high-voltage, high-current, and harsh environments can affect their performance, leading to transformer failures and even power grid failures. Therefore, it is necessary to assess the condition of transformer bushings. However, in related technologies, there are technical problems with the inaccuracy of transformer bushing condition assessment.

[0097] There is currently no effective solution to the above problems.

[0098] In view of this, the optional embodiments of the present invention provide a method and system for assessing the condition of transformer bushings, which can also be called a bushing condition evaluation method and system. It can effectively solve the technical problem of inaccurate assessment of the condition of transformer bushings in related technologies.

[0099] (I) Methods for evaluating the condition of casing:

[0100] Figure 2 This is a flowchart of the casing condition evaluation method in an optional embodiment of the present invention, as shown below. Figure 2 As shown below, a detailed description will be provided.

[0101] S1. Obtain the operating condition data (same as the target operating condition data) and state data (same as the target state data) of the bushing (same as the target bushing mentioned above), and fit them to obtain the full data of the bushing. The operating condition data of the bushing is used to represent the external conditions of the bushing, and the state data of the bushing is used to represent the characteristics of the bushing itself. The operating condition data includes real-time operating condition data (same as the current operating condition data mentioned above) and historical operating condition data. The state data includes real-time state data (same as the current state data mentioned above) and historical state data. The state data contains multiple state parameters of the bushing. The multiple state parameters (same as the multiple state attribute items mentioned above) include insulation state parameters, oil sample state parameters, and external state parameters. The external state parameters include visible light images and infrared thermal imaging spectra of the outside of the bushing.

[0102] The operating condition data includes meteorological environmental operating condition data and power grid operating condition data of the bushing location. Specifically, it includes obtaining meteorological environmental operating condition data and power grid operating condition data of the bushing location from the meteorological information system and the power grid information system, respectively. Among them, the meteorological environmental operating condition data includes weather and environmental data; the power grid operating condition data includes voltage, current, load ratio and magnetic field data of the power grid.

[0103] For insulation condition parameters, these include leakage current signal, high-frequency partial discharge signal, dielectric loss signal, and equivalent capacitance signal at the bushing end screen; for oil sample condition parameters, these include dissolved hydrogen data, water content data, oil pressure data, and oil temperature data inside the bushing.

[0104] For each unstructured state parameter in the state data, a structured processing is performed to obtain the structured expression data corresponding to the state parameter. The structured expression data includes the component information, parameter description information, and time information of the bushing.

[0105] The external state parameters are unstructured state parameters. For each unstructured state parameter in the state data, structuring processing is performed, including: extracting the component regions corresponding to each component of the sheath from the visible light image (same as the current sheath image mentioned above); fusing the visible light image with the infrared thermal imaging spectrum (same as the current infrared image mentioned above) to obtain a fused image (same as the current fused image mentioned above); determining the temperature of each component region of the sheath based on the fused image to obtain the temperature of each component of the sheath; and generating structured representation data corresponding to the external state parameters (same as the current temperature data mentioned above) based on the temperature of each component of the sheath and the acquisition time of the external state parameters.

[0106] Furthermore, a casing data model can be constructed using the correlation matrix, based on the structured representation data corresponding to each state parameter in the state data, and the operating condition data corresponding to each state parameter. Based on the casing data model, multiple data samples characterizing the casing state under different operating conditions are obtained. These multiple data samples include multiple positive samples and multiple negative samples. The defect causes of each negative sample are determined. The defect causes of each negative sample are sorted according to time series and defect severity to generate a dynamic evaluation model for casing performance, so as to dynamically evaluate the state of the casing using the dynamic evaluation model for casing performance.

[0107] S2. For each real-time status parameter, adjust the alarm threshold of the real-time status parameter based on the real-time operating condition data corresponding to the real-time status parameter to obtain the latest alarm threshold of the real-time status parameter.

[0108] Specifically, S2 also includes adjusting the alarm threshold of the real-time state parameter based on the real-time operating condition data corresponding to the real-time state parameter to obtain the latest alarm threshold of the real-time state parameter, including: constructing a dynamic model of full information association expression based on the correlation between operating condition data and state data (same as the first correlation parameter mentioned above); adjusting the alarm threshold of the real-time state parameter based on the real-time operating condition data corresponding to the real-time state parameter through the dynamic model of full information association expression to obtain the latest alarm threshold of the real-time state parameter.

[0109] S3. Retrieve the reference casing data set, which includes reference status data corresponding to multiple reference casings. The similarity index between the attribute parameters of the multiple reference casings and the attribute parameters of the target casing is greater than the similarity threshold. The attribute parameters include the casing model.

[0110] For example, the state data of multiple families of casings (similar to the aforementioned reference casings) with the same attribute parameters, including the same model, the same operating conditions, and the service life within a predetermined range, are fitted in advance to construct a family data model; family difference samples with significant differences are selected from the family data model, and the reliability of the family data model is evaluated based on the family difference samples; the state data of the casing is associated with the family data model after the reliability evaluation, and family-based state evaluation and individual difference comparison are performed to determine the mutation parameters of the casing (similar to the aforementioned difference attribute items) and mutation parameter correlation parameters (similar to the aforementioned difference correlation parameters); based on the mutation parameters and mutation parameter correlation parameters, the state evolution and deterioration trend of the casing (similar to the aforementioned state change trend) are predicted.

[0111] S4. Compare the real-time status parameters with the latest alarm threshold to determine whether the real-time status parameters are abnormal. If the real-time status parameters are abnormal, then issue an alarm for the status of the bushing.

[0112] (II) Casing Condition Evaluation System:

[0113] A casing condition evaluation system can also be called a casing online monitoring system.

[0114] Figure 3 This is an optional embodiment of the online casing inspection system of the present invention, such as... Figure 3 As shown, the casing online monitoring system includes an online monitoring host, a non-invasive acoustic-electric sensor, an invasive electrochemical sensor (i.e., an oil sample state sensor), and a dual-spectral optical sensor. The invasive electrochemical sensor, also known as the oil sample state sensor, is used to measure the state of the oil sample inside the casing. The online monitoring host is wirelessly connected to the non-invasive acoustic-electric sensor, the invasive electrochemical sensor, and the dual-spectral optical sensor, respectively.

[0115] Figure 4 This is a schematic diagram illustrating the deployment method of the casing online monitoring system in an optional embodiment of the present invention, as shown below. Figure 4 As shown, the bushing being monitored can specifically be a transformer oil-paper insulated capacitive high-voltage bushing (hereinafter referred to as "bushing"). The bushing is deployed on the transformer body, and the bottom of the bushing has a riser seat, through which it is installed on the top of the transformer body. The riser seat is equipped with a end screen and an oil outlet (specifically, a lower flange oil outlet). From bottom to top, the bushing includes components such as the end screen, lower flange oil outlet, outer sheath, cap, oil level window, and terminal fittings.

[0116] The non-invasive acoustic-electric sensor is wirelessly connected to the online monitoring host. It can be mounted on the end screen of the bushing to collect insulation status parameters. The sensor includes a leakage current measurement unit, a high-frequency partial discharge measurement unit, a dielectric loss measurement unit, and an equivalent capacitance measurement unit. These units respectively collect the leakage current signal, high-frequency partial discharge signal, dielectric loss signal, and equivalent capacitance signal from the end screen of the bushing. Insulation status parameters can be obtained based on these signals. Furthermore, the non-invasive acoustic-electric sensor can transmit the collected insulation status parameters to the online monitoring host for processing, enabling the determination of the bushing's insulation status.

[0117] It should be noted that the non-invasive acoustic-electric sensor can be an integrated structure. In other words, the leakage current measurement unit, the high-frequency partial discharge measurement unit, the dielectric loss measurement unit, and the equivalent capacitance measurement unit can be integrated into one unit to form a non-invasive acoustic-electric sensor.

[0118] An interferometric electrochemical sensor (i.e., an oil sample state sensor) is wirelessly connected to the online monitoring host. The sensor can be installed at the oil sampling port (lower flange oil sampling port) on the bushing riser to collect oil sample state parameters inside the bushing. The interferometric electrochemical sensor includes a dissolved hydrogen measurement unit, a water content measurement unit, an oil pressure measurement unit, and an oil temperature measurement unit. These units collect data on dissolved hydrogen, water content, oil pressure, and oil temperature inside the bushing, respectively. Based on these data, the oil sample state parameters can be obtained. Furthermore, the interferometric electrochemical sensor can transmit the collected oil sample state parameters to the online monitoring host for processing, thereby determining the oil sample state inside the bushing.

[0119] It should be noted that the interventional electrochemical sensor can be an integrated structure. In other words, the insulating oil dissolved hydrogen measurement unit, water content measurement unit, oil pressure measurement unit, and oil temperature measurement unit can be integrated into one unit to form an interventional electrochemical sensor.

[0120] The dual-spectrum optical sensor is wirelessly connected to the online monitoring host. The dual-spectrum optical sensor is positioned outside the casing to collect external state parameters of the casing. It includes a visible light measurement unit and an infrared thermal imaging measurement unit. The visible light measurement unit and the infrared thermal imaging measurement unit respectively acquire visible light images and infrared thermal images of the casing's exterior. Based on these images, external state parameters containing both the casing's optical appearance features and its thermal distribution characteristics can be obtained. Furthermore, the dual-spectrum optical sensor can transmit the acquired external state parameters of the casing to the online monitoring host for processing, enabling the determination of external defects and thermal faults in the casing based on these parameters.

[0121] It should be noted that the dual-spectrum optical sensor can be a single integrated structure. In other words, the visible light measurement unit and the infrared thermal imaging measurement unit can be integrated into one unit to form a dual-spectrum optical sensor.

[0122] As can be seen, the online casing monitoring system provided in this embodiment of the invention acquires multiple parameters of the casing from different dimensions through multiple acquisition devices (non-invasive acoustic-electric sensors, invasive electrochemical sensors, and dual-spectral optical sensors), and can achieve coordinated acquisition of all parameters of the casing.

[0123] Non-invasive acoustic-electric sensors and invasive electrochemical sensors can communicate wirelessly with the online monitoring host via LoRa (LoRa) technology for power transmission and transformation IoT. It should be noted that LoRa is a low-power local area network wireless standard. Its biggest advantage is that it can travel farther than other wireless methods under the same power consumption, achieving a balance between low power consumption and long distance. It extends the distance by 3-5 times compared to traditional wireless radio frequency communication under the same power consumption. The physical layer uses linear frequency modulation spread spectrum, operating in the 470-510MHz and 2400-2483.5MHz frequency bands.

[0124] Dual-spectrum optical sensors can wirelessly communicate with the online monitoring host via the Wireless API (WAPI) protocol. Simultaneously receiving control signals from the online monitoring host, the dual-spectrum optical sensor can transmit its acquired visible light images and infrared thermal images back to the host. It should be noted that the WAPI is the foundational architecture for authentication and security in wireless local area networks (WLANs); it is a security protocol, a wireless transmission protocol, and specifically a transmission protocol within WLANs.

[0125] The online monitoring host can be wall-mounted and installed on the transformer firewall or transformer room wall. The wireless antenna of the online monitoring host can be externally mounted. The antenna of the online monitoring host can transmit or receive electromagnetic waves of WAPI-2.4GHz, WAPI-5.8GHz, and LoRa-470M to enable wireless communication with various sensors.

[0126] The online monitoring host can also communicate wirelessly with handheld live-line detectors (including UHF partial discharge detectors, ultrasonic partial discharge detectors, transient ground voltage partial discharge detectors, infrared thermal imagers, acoustic imagers, etc.) specifically used in the power industry via Bluetooth or wireless network (WIFI) to enable the fusion analysis of status information collected by the handheld live-line detectors and online monitoring data.

[0127] The non-invasive acoustic-electric sensor can be implemented as an integrated intelligent end-screen adapter. This adapter integrates a leakage current measurement unit, a high-frequency partial discharge measurement unit, a dielectric loss measurement unit, and an equivalent capacitance measurement unit. The integrated intelligent end-screen adapter can be mounted on the end screen of the bushing. Based on high-efficiency magnetically shielded sensor embedded micro-integration technology, its advantage over traditional bushing online monitoring devices is that it eliminates the need for a grounding wire to the end screen, does not change the grounding point or grounding method of the bushing end screen, and solves the compatibility problem of accurate measurement of high-frequency and power frequency defect characteristic signals and reliable grounding of the end screen under strong electromagnetic interference conditions in ultra-high voltage substations. This enables accurate dynamic sensing and dynamic acquisition of bushing insulation state characteristic parameters.

[0128] It should be noted that the end screen of the capacitor layer is a crucial part of the transformer's high-voltage bushing. It employs a direct grounding method using a metal cover plate without extending the bushing body, ensuring proper grounding of the bushing's capacitor core. This method can also be used for dielectric loss and insulation testing. However, the metal cover plate must be removed during a power outage and restored after the test. If the end screen cover plate is not properly restored or is not properly grounded during operation, a capacitance will form between the end screen and ground. According to the principle of capacitor series connection, a high floating voltage will form between the end screen and the ground, causing the end screen to discharge to ground. This leads to a decrease in the bushing's insulation and may even cause the bushing to explode. To address this, this invention proposes a sensor-embedded micro-integration technology based on high-efficiency magnetic shielding to develop an integrated bushing end-screen adapter. This adapter integrates leakage current measurement, high-frequency partial discharge measurement, dielectric loss measurement, and equivalent capacitance measurement units. Without altering the original grounding method of the end-screen, the adapter allows the bushing end-screen core lead-out rod to pass through a shielded monitoring sensor and directly ground through the outer shell. The grounding method remains consistent with the high-voltage bushing's factory specifications, enabling accurate sensing of the end-screen current signal and reliable grounding compatibility under strong electromagnetic interference. Furthermore, the integrated end-screen adapter employs a spring-loaded crimping structure, with the spring end welded to the adapter shell. This ensures a reliable connection between the bushing end-screen lead-out rod and the grounding point after passing through the spring, effectively mitigating the risk of poor grounding caused by improper tightening during installation and preventing connection detachment during prolonged operation.

[0129] The non-invasive acoustic-electric sensor has a leakage current measurement accuracy of no less than 0.1mA, a minimum partial discharge monitoring accuracy of no less than 5pC, a dielectric loss measurement accuracy of no less than 0.001, and a capacitance measurement accuracy of no less than 1pF; the overall protection level of the sensor is designed to meet the protection level standard and the requirements for use in complex weather conditions.

[0130] The hydrogen dissolution measurement unit of the interferometric electrochemical sensor can be implemented as a palladium alloy thin-film sensor. It utilizes a palladium catalyst to catalytically decompose hydrogen molecules into hydrogen atoms. These hydrogen atoms can rapidly diffuse into the palladium alloy lattice, causing lattice expansion and phase transition, driving a change in the conductivity of the alloy thin film. Based on this characteristic, the hydrogen content (hydrogen concentration) can be measured. This measurement method is suitable for detecting the state of oil samples in low-oil conditions in bushings, overcoming the limitations of chromatographic methods for analyzing low-oil equipment samples.

[0131] It should be noted that transformer high-voltage bushings employ capacitive insulation technology, filling the space between the capacitor core and the outer sheath of the bushing with oil-paper insulation, serving functions such as insulation, oxidation prevention, and heat dissipation. The insulating oil inside the high-voltage bushing decomposes into hydrogen (H2) and hydrocarbon gases due to temperature changes and high-energy electric discharge. It also dissolves oxygen (O2), nitrogen (N2), and trace amounts of water due to the sealing effect. Monitoring these gaseous decomposition products in the oil provides a direct indication of the bushing's internal insulation condition. Due to limitations in the bushing's internal structure and the relatively small amount of insulating oil, traditional oil-circulation chromatographic monitoring techniques are not suitable for high-voltage bushings. Internal monitoring of high-voltage bushings should be a relatively static method, requiring no strong internal oil circulation, while simultaneously possessing the ability to detect oil temperature, oil pressure, and moisture content, without affecting the original insulation structure of the transformer's high-voltage bushing. To address this, in some embodiments of the present invention, a palladium alloy thin-film sensor (as a hydrogen dissolved in insulating oil measuring unit) is encapsulated within an interventional electrochemical sensor to measure hydrogen dissolved in insulating oil. This enables the detection of oil sample status under low-oil conditions in bushings, overcoming the limitations of chromatographic analysis for low-oil equipment samples. Simultaneously, a platinum-rhodium thermocouple and a piezoelectric ceramic can be integrated at the top of the interventional electrochemical sensor, serving as the oil pressure measuring unit and oil temperature measuring unit respectively, enabling simultaneous measurement of oil temperature and oil pressure inside the bushing.

[0132] The water content measurement unit of the interventional electrochemical sensor can adopt a bimetallic electrode structure, which is filled with a solid insulating medium. By changing the medium constant through water content, the equivalent capacitance of the detection unit is changed to achieve quantitative analysis of water content.

[0133] The oil pressure measurement unit of the interventional electrochemical sensor can be implemented as a diffused silicon pressure sensor. By detecting changes in oil pressure using the diffused silicon pressure sensor, early warning of oil leakage defects can be achieved. Furthermore, it can be combined with an oil temperature measurement unit to identify early indicators of casing overheating leading to deflagration.

[0134] The interferometric electrochemical sensor has an accuracy of no less than ±25ppm for hydrogen monitoring, no less than ±5ppm for trace water monitoring, no less than ±1℃ for oil temperature monitoring, and no less than 0.001MPa for oil pressure monitoring. The overall protection level of the interferometric electrochemical sensor is designed to meet or exceed the required protection level standards, and it can be installed in the oil circuit of the bushing riser to meet the needs of use in complex weather conditions.

[0135] Based on external state parameters (visible light images and infrared thermal imaging spectra) obtained from dual-spectrum optical sensors, the online monitoring host can acquire the region of interest from the visible light image using an adaptive sliding window, and obtain the boundary information within the region of interest by combining edge detection methods. Based on the boundary information, the profile of the casing components (such as the profile of the outer sheath, equalizing ring, etc.) is constructed to obtain the target of interest. Furthermore, the target of interest can be classified and identified, and the influence of illumination can be identified, so as to identify the external defects of each component of the casing (outer sheath, equalizing ring, etc.).

[0136] The online monitoring host can also extract target hot spots, hot surfaces, and heat distribution line features from infrared thermal imaging spectra. Furthermore, it can use scale-invariant feature transformation algorithms to perform precise matching between visible light images and infrared thermal imaging spectra to obtain affine transformation matrices of the visible light images and infrared thermal imaging spectra. Based on the affine transformation matrix, a fused image of the visible light images and infrared thermal imaging spectra can be further obtained. Based on the fused image, the structural features of the heating origin of the bushing can be identified, and the heating type and heating cause can be deduced to determine the thermal faults of various components of the bushing (equalizing ring, riser seat, bushing body, and drain line, etc.).

[0137] It is understandable that external defects of the casing that can be determined based on the external state parameters of the casing include external defects of components such as the outer sheath, equalizing ring, and bushing. Thermal faults of the casing that can be determined based on the external state parameters of the casing include thermal faults of components such as the equalizing ring, riser, casing body, and drain line.

[0138] The online monitoring host can utilize feature matching and image fusion technology to fuse visible light images and infrared thermal imaging spectra to generate a fused image. Based on the fused image, it is possible not only to identify external defects and thermal faults in the casing, but also to locate the fault.

[0139] The visible light measurement unit has autofocus and optical zoom capability of over 30x, and the visible light images acquired by the visible light measurement unit have a resolution of no less than 4 million pixels. The infrared thermal imaging measurement unit has a resolution of no less than 640×512 pixels for infrared thermal imaging, a temperature measurement accuracy of no less than ±1℃, and an overall protection level no less than the protection level standard, meeting the needs of use in complex weather conditions.

[0140] The online monitoring host can use clock synchronization technology (specifically, high-precision clock synchronization technology at the microsecond or nanosecond level) to acquire time-synchronized insulation state parameters, oil sample state parameters, and external state parameters collected by non-invasive acoustic-electric sensors, invasive electrochemical sensors, and dual-spectral optical sensors.

[0141] The non-invasive acoustic-electric sensor, the invasive electrochemical sensor, and the dual-spectral optical sensor all possess clock synchronization capabilities within 20μs. Upon receiving control signals from the online monitoring host, they can simultaneously transmit their currently acquired insulation state parameters, oil sample state parameters, and external state parameters to the online monitoring host. Based on this, high-precision time synchronization of insulation state parameters, oil sample state parameters, and external state parameters can be achieved, and multiple parameter data from the same tested bushing can be uniformly transmitted back to the online monitoring host.

[0142] The online monitoring host can provide a unified high-precision clock for non-invasive acoustic-electric sensors, invasive electrochemical sensors, and dual-spectral optical sensors via wireless means, so as to realize the accurate and coordinated acquisition of electrical, non-electrical, structured, and unstructured parameters by each sensor.

[0143] Non-invasive acoustic-electric sensors, invasive electrochemical sensors, and dual-spectral optical sensors can calibrate their respective clock times based on a unified clock source (provided reference time), achieving microsecond-level clock synchronization among the sensors. Furthermore, these sensors can continuously collect time-synchronized insulation state parameters, oil sample state parameters, and external state parameters based on the unified clock time and simultaneously transmit them to the online monitoring host. Based on this, time synchronization facilitates the establishment of correlations between multiple parameters and the analysis of casing status at various time points, improving the accuracy and real-time performance of multi-parameter data fusion for more accurate multi-parameter data analysis.

[0144] For example, in the casing online monitoring system of the present invention, the online monitoring host can wake up each connected sensor through wireless communication discontinuous reception scheduling technology, and send broadcast channel (BCH) frame synchronization signals to each woken-up sensor (non-invasive acoustic-electric sensor, invasive electrochemical sensor, and dual-spectral optical sensor) to provide a reference time for the non-invasive acoustic-electric sensor, invasive electrochemical sensor, and dual-spectral optical sensor. Each sensor can calibrate its own clock time based on the reference time to achieve clock synchronization of each sensor.

[0145] Furthermore, the online monitoring host can perform time correction on insulation state parameters, oil sample state parameters, and external state parameters collected by non-invasive acoustic-electric sensors, invasive electrochemical sensors, and dual-spectral optical sensors based on a unified time series. Through time correction, high-precision time synchronization of insulation state parameters, oil sample state parameters, and external state parameters can be achieved.

[0146] Specifically, the online monitoring host can determine the sampling frequencies of the non-invasive acoustic-electric sensor, the invasive electrochemical sensor, and the dual-spectral optical sensor, and then determine the minimum sampling frequency among the insulation state parameters, oil sample state parameters, and external state parameters. Using the minimum sampling frequency as a reference, the sampling times of the insulation state parameters, oil sample state parameters, and external state parameters collected by the non-invasive acoustic-electric sensor, the invasive electrochemical sensor, and the dual-spectral optical sensor are recorded on a unified time series. This allows the determination of the correspondence between the insulation state parameters, oil sample state parameters, and external state parameters and time. Based on the correspondence between parameters and time, time correction is performed on the insulation state parameters, oil sample state parameters, and external state parameters. This eliminates time deviations between different sensors and aligns the data of multiple parameters.

[0147] It should be noted that in practical applications, the clock synchronization scheme and time correction scheme in the above embodiments can be used in combination to achieve high-precision time synchronization of multiple parameter data. Based on this, the bushing status at each time point can be accurately analyzed. Furthermore, it can improve the accuracy and real-time performance of multi-parameter data fusion, enabling more accurate multi-parameter data analysis.

[0148] Edge computing containers (containers based on an edge computing framework) can be deployed in the online monitoring host to achieve containerized edge computing within the host. This can be understood as the online monitoring host acting as an edge computing node, used to monitor the status of bushings at corresponding node locations in real time at the edge. Based on the edge computing container, the online monitoring host can control non-invasive acoustic-electric sensors, invasive electrochemical sensors, and dual-spectral optical sensors to collect real-time insulation state parameters, oil sample state parameters, and external state parameters of the bushing, thus enabling real-time monitoring of the bushing's status. Furthermore, by analyzing the insulation state parameters, oil sample state parameters, and external state parameters, potential faults and problems with the bushing can be detected promptly, and corresponding measures can be taken in a timely manner to ensure the stable and reliable operation of the transformer's high-voltage bushings.

[0149] Furthermore, the online monitoring host, based on an edge computing container, can extract features (extracting characteristic data representing different states of the bushing) from time-synchronized insulation state parameters, oil sample state parameters, and external state parameters, process, and analyze them to determine the insulation state, oil sample state, external defects, and thermal faults of the bushing at various time points. This allows for analysis of the bushing's health status at the edge based on the time domain dimension, facilitating the timely detection of potential bushing faults and problems, and enabling timely implementation of corresponding measures to ensure the stable and reliable operation of the transformer's high-voltage bushings.

[0150] The online monitoring host, based on an edge computing container, can also fit insulation state parameters, oil sample state parameters, and external state parameters with the on-site environmental indicators of the bushing to generate predetermined structured data. Based on unified structured data, it can achieve normalized uploading and storage of collected data.

[0151] Collaborative sensing applications can be deployed within edge computing containers. These applications can establish and store the relationships between insulation state parameters, oil sample state parameters, and external state parameters for subsequent data retrieval and analysis. Specifically, relationships can be established and stored for time-synchronized insulation state parameters, oil sample state parameters, and external state parameters.

[0152] The casing online monitoring system may also include a client application, which can communicate with the online monitoring host, for example, via a wired or wireless network connection. The online monitoring host can generate corresponding waveforms and / or spectrum graphs based on insulation condition parameters, oil sample condition parameters, and external condition parameters, and send them to the client for display. This provides a clear visual representation of the trends of multiple parameters, allowing users to analyze the casing health status.

[0153] The bushing online monitoring system integrates acoustic, optical, electrical, and electrochemical sensors. Specifically, it integrates an online monitoring host, a non-invasive acoustic-electric sensor, an invasive electrochemical sensor, and a dual-spectral optical sensor. It can perform full-parameter collaborative online monitoring of transformer high-voltage bushings. Specifically, it can continuously collect insulation status parameters such as leakage current, high-frequency partial discharge, dielectric loss, and equivalent capacitance of the bushing end screen, oil sample status parameters such as dissolved hydrogen, water content, oil pressure, and oil temperature of the insulating oil, and external status parameters such as visible light images and infrared thermal imaging spectra without power interruption. This enables the system to provide high-frequency, highly effective, and highly correlated data support for bushing condition assessment.

[0154] By employing clock synchronization and time correction schemes, high-precision time synchronization of various parameter data collected by multiple sensors can be achieved. With time synchronization, it is easier to establish correlations among various parameters and to analyze the bushing status at different time points. This improves the accuracy and real-time performance of multi-parameter data fusion, enabling more accurate multi-parameter data analysis.

[0155] Furthermore, the online monitoring host, based on an edge computing container, processes and analyzes time-synchronized insulation status parameters, oil sample status parameters, and external status parameters to determine the insulation status, oil sample status, external defects, and thermal faults of the bushing at various time points. This enables time-domain analysis of the bushing's health status at the edge, facilitating the timely detection of potential bushing faults and problems, and allowing for prompt implementation of appropriate measures to ensure the stable and reliable operation of the transformer's high-voltage bushings.

[0156] The above optional implementation methods can achieve at least the following beneficial effects:

[0157] (1) Compared with related technologies, the present invention can reflect the trend of the target bushing state as the operating conditions change by determining the first correlation parameter between the target operating condition data and the target state data of the target bushing, and retrieve the reference bushing data set to determine the second correlation parameter between the current state data and multiple reference state data respectively. This can more clearly define whether the state of the target bushing deviates from the acceptable range compared with bushings with similar attribute parameters. Thus, by combining the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter, the state of the target bushing can be accurately evaluated, thereby solving the technical problem of inaccurate state evaluation of transformer bushings in related technologies.

[0158] (2) Compared with related technologies, the present invention can decompose the state of the target casing in multiple dimensions by determining multiple state attribute items corresponding to the target casing, so as to achieve quantitative evaluation in different dimensions. Furthermore, based on the current working condition data and the first correlation parameter, the corresponding reference attribute value is determined, which can provide a more accurate comparison benchmark for state evaluation. Thus, based on the comparison between the current attribute value and the reference attribute value of each state attribute item, and combined with the second correlation parameter, the accuracy of the target casing evaluation can be further improved.

[0159] (3) By determining the difference index between the current state data and multiple reference state data, the degree of difference between the target casing state and each reference casing state can be quantitatively assessed. Selecting the difference state data with the largest difference index can pinpoint the reference state that differs most significantly from the target casing state, which usually means that the reference state deviates significantly from the target casing in some key attributes. Further determining the difference correlation parameters between the current state data and the difference state data can specifically reveal how the differences in these key attributes are related, thereby accurately locating potential problems with the target casing.

[0160] (4) Compared with related technologies, the present invention obtains the working condition data and status data of the bushing, adjusts the alarm threshold of the real-time status parameter based on the real-time working condition data corresponding to the real-time status parameter, and judges whether the real-time status parameter is abnormal based on the latest alarm threshold of the real-time status parameter. It can fully consider and correct the influence of external conditions (working conditions) on the bushing status, and the evaluation of the bushing status is more accurate and reliable. Moreover, the alarm information can accurately characterize the current health status of the bushing, ensure the effectiveness of the alarm, and avoid the situation where invalid alarms are triggered due to the influence of external conditions on the bushing status.

[0161] (5) Compared with related technologies, the present invention can integrate and analyze the status data and operating condition data that reflect the casing status and operating conditions, and comprehensively evaluate the casing status, thereby improving the accuracy and reliability of the casing status evaluation.

[0162] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0163] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0164] Example 2

[0165] According to an embodiment of the present invention, an apparatus for implementing the above-described transformer bushing condition assessment method is also provided. Figure 6 This is a structural block diagram of a transformer bushing condition assessment device according to an embodiment of the present invention, as shown below. Figure 6 As shown, the device includes: an acquisition module 602, a first determination module 604, a retrieval module 606, a second determination module 608, and a third determination module 610. The device will be described in detail below.

[0166] The module 602 is used to acquire target operating condition data and target status data corresponding to the target sleeve, wherein the target operating condition data includes current operating condition data and the target status data includes current status data; the first determining module 604, connected to the acquisition module 602, is used to determine a first correlation parameter between the target operating condition data and the target status data; the retrieving module 606, connected to the first determining module 604, is used to retrieve a set of reference sleeve data, wherein the set of reference sleeve data includes reference status data corresponding to multiple reference sleeves, and the similarity index between the attribute parameters of the multiple reference sleeves and the attribute parameters of the target sleeve is greater than a similarity threshold, and the attribute parameters include the sleeve model; the second determining module 608, connected to the retrieving module 606, is used to determine a second correlation parameter between the current status data and the multiple reference status data based on the set of reference sleeve data; the third determining module 610, connected to the second determining module 608, is used to perform a status evaluation on the target sleeve based on the current operating condition data, the current status data, the first correlation parameter, and the second correlation parameter, and obtain a target evaluation result corresponding to the target sleeve.

[0167] It should be noted here that the above-mentioned acquisition module 602, first determination module 604, retrieval module 606, second determination module 608 and third determination module 610 correspond to steps S102 to S110 in the transformer bushing condition assessment method. The multiple modules and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiment 1.

[0168] Example 3

[0169] According to another aspect of the present invention, an electronic device is also provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute instructions to implement the transformer bushing condition assessment method of any of the above embodiments.

[0170] Figure 5 This is a schematic diagram of a computing device in an optional embodiment of the present invention, such as... Figure 5 As shown, in the basic configuration, the computing device includes at least one processing unit (same as the processor described above) and system memory (same as the memory described above).

[0171] Optionally, depending on the configuration and type of the computing device, the system memory includes, but is not limited to, volatile memory (e.g., random access memory), non-volatile memory (e.g., read-only memory), flash memory, or any combination of such memory.

[0172] Optionally, the system memory includes the operating system.

[0173] Optionally, the operating system is adapted to control the operation of the computing device. Furthermore, it is practiced in conjunction with graphics libraries, other operating systems, or any other applications, and is not limited to any particular application or system. Figure 5 The basic configuration is shown in the diagram by the components within the dashed lines.

[0174] Optionally, the computing device has additional features or functions. For example, the computing device includes additional data storage devices (removable and / or non-removable), such as disks, optical discs, or magnetic tapes. This additional storage... Figure 5 The image shows removable storage devices and non-removable storage devices.

[0175] Optionally, program modules are stored in system memory.

[0176] Optionally, the program module may include one or more applications, without limiting the type of application. For example, applications may include: graph analysis applications, graph 3D rendering applications, word processing applications, spreadsheet applications, database applications, web browser applications, etc.

[0177] Optionally, examples can be implemented in circuits including discrete electronic components, in packages or integrated electronic chips containing logic gates, in circuits utilizing microprocessors, or on a single chip containing electronic components or a microprocessor. For example, this can be achieved via... Figure 5 Each or many of the components shown can be implemented as an example by integrating a System-on-a-Chip (SOC) on a single integrated circuit. According to one aspect, such an SOC device may include one or more processing units, graphics units, communication units, system virtualization units, and various application functions, all integrated as a single integrated circuit onto a chip substrate. When operated via the SOC, the functions described herein can be operated via dedicated logic integrated on a single integrated circuit (chip) with other components of the computing device. Embodiments of the invention can also be practiced using other techniques capable of performing logical operations (e.g., AND, OR, and NOT), including but not limited to mechanical, optical, fluid, and quantum technologies. Furthermore, embodiments of the invention can be practiced within a general-purpose computer or in any other circuit or system.

[0178] Optionally, the computing device may also have one or more input devices, such as a keyboard, mouse, pen, voice input device, touch input device, etc. It may also include output devices, such as a monitor, speakers, printer, etc. The foregoing devices are examples and other devices may also be used. The computing device may include one or more communication connections that allow communication with other computing devices. Examples of suitable communication connections include, but are not limited to: radio frequency (RF) transmitters, receivers, and / or transceiver circuitry; universal serial bus (USB); parallel and / or serial ports.

[0179] Example 4

[0180] According to another aspect of the present invention, a computer-readable storage medium is also provided, which, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the transformer bushing condition assessment method described above.

[0181] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0182] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0183] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0184] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0185] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0186] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0187] The above description is only a preferred 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 assessing the condition of transformer bushings, characterized in that, include: Obtain target operating condition data and target status data corresponding to the target sleeve, wherein the target operating condition data includes current operating condition data and the target status data includes current status data; Determine a first correlation parameter between the target operating condition data and the target state data; Retrieve a reference sheath data set, wherein the reference sheath data set includes reference status data corresponding to multiple reference sheaths, and the similarity index between the attribute parameters of the multiple reference sheaths and the attribute parameters of the target sheath is greater than a similarity threshold, wherein the attribute parameters include the sheath model; Based on the reference sleeve data set, determine the second correlation parameters between the current state data and multiple reference state data respectively; Based on the current operating condition data, the current status data, the first correlation parameter, and the second correlation parameter, the status of the target sleeve is evaluated to obtain the target evaluation result corresponding to the target sleeve.

2. The method according to claim 1, characterized in that, The step of evaluating the state of the target sleeve based on the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter to obtain a target evaluation result corresponding to the target sleeve includes: Determine multiple status attribute items corresponding to the target sleeve; Based on the current state data, determine the current attribute value corresponding to each of the plurality of state attribute items; Based on the current operating condition data, the first associated parameter determines the reference attribute value corresponding to each of the multiple state attribute items; Based on the current attribute value and reference attribute value corresponding to the plurality of status attribute items, and the second association parameter, the status of the target sleeve is evaluated to obtain the target evaluation result corresponding to the target sleeve.

3. The method according to claim 1, characterized in that, The step of determining the second correlation parameter between the current state data and multiple reference state data based on the reference sleeve data set includes: When the second correlation parameter includes a difference correlation parameter, the difference index between the current state data and the plurality of reference state data is determined based on the reference sleeve data set. Based on multiple difference indices, difference state data is determined from the multiple reference state data, wherein the difference state data is the state data with the largest difference index among the multiple reference state data; Determine the difference correlation parameters between the current state data and the difference state data.

4. The method according to claim 3, characterized in that, The step of determining the difference correlation parameter between the current state data and the difference state data includes: Based on the current state data and the difference state data, multiple difference attribute items are determined; Based on the current state data, determine the first difference attribute value corresponding to each of the plurality of difference attribute items; Based on the difference status data, determine the second difference attribute value corresponding to each of the plurality of difference attribute items; The difference association parameters are determined based on the first difference attribute value and the second difference attribute value corresponding to the plurality of difference attribute items, respectively.

5. The method according to claim 1, characterized in that, Before acquiring the target operating condition data and target status data corresponding to the target casing, the process also includes: When the current status data includes the current temperature data, the current sleeve image and the current infrared image corresponding to the target sleeve are determined, wherein the time difference between the acquisition time of the current sleeve image and the acquisition time of the current infrared image is less than a time threshold. Based on the current cannula image and the current infrared image, determine the current fused image corresponding to the target cannula; Based on the current fused image, determine the current temperature data corresponding to the target sleeve.

6. The method according to claim 1, characterized in that, The step of evaluating the state of the target sleeve based on the current operating condition data, the current state data, the first correlation parameter, and the second correlation parameter to obtain a target evaluation result corresponding to the target sleeve includes: Based on the second correlation parameter, determine the state change trend corresponding to the target sleeve; Based on the current operating condition data, the current state data, the first associated parameter, and the state change trend, the state of the target sleeve is evaluated to obtain the target evaluation result corresponding to the target sleeve.

7. The method according to any one of claims 1 to 6, characterized in that, Before acquiring the target operating condition data and target status data corresponding to the target sleeve, the following steps are included: Determine the environmental operating conditions and power grid operating conditions corresponding to the target bushing; Based on the environmental operating condition data and the power grid operating condition data, the target operating condition data corresponding to the target bushing is determined.

8. A transformer bushing condition assessment device, characterized in that, include: The acquisition module is used to acquire target operating condition data and target status data corresponding to the target sleeve, wherein the target operating condition data includes current operating condition data and the target status data includes current status data; The first determining module is used to determine a first correlation parameter between the target operating condition data and the target state data; The retrieval module is used to retrieve a reference sleeve data set, wherein the reference sleeve data set includes reference status data corresponding to multiple reference sleeves, and the similarity index between the attribute parameters of the multiple reference sleeves and the attribute parameters of the target sleeve is greater than a similarity threshold, wherein the attribute parameters include the sleeve model. The second determining module is used to determine, based on the reference sleeve data set, a second association parameter between the current state data and multiple reference state data respectively; The third determining module is used to perform a status assessment on the target sleeve based on the current working condition data, the current state data, the first correlation parameter, and the second correlation parameter, and obtain a target assessment result corresponding to the target sleeve.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the transformer bushing condition assessment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the transformer bushing condition assessment method as described in any one of claims 1 to 7.

Images