A method, device, equipment, storage medium and product for monitoring the state of a capacitive voltage transformer

Abstract

The application discloses a capacitive voltage transformer state monitoring method, device, equipment, storage medium and product, relates to the technical field of fault diagnosis, and the method comprises the following steps: collecting operation state data of each capacitive voltage transformer in real time, wherein the operation state data comprises a plurality of sub-operation state data; comparing the sub-operation state data with corresponding sub-reference state data to obtain a first comparison result; if the value of the sub-operation state data is greater than a corresponding threshold value, it is determined that there is a fault risk; otherwise, a fault characteristic value is determined through the plurality of sub-operation state data, and it is judged whether the fault characteristic value is greater than a fault threshold value to determine whether there is a fault risk. Determining the fault characteristic value requires determining each sub-characteristic value and then synthesizing. After it is determined that there is a fault risk, a to-be-measured priority value is acquired, a surface image of the largest one is photographed, and an abnormal position is determined through analysis, wherein the analysis comprises the steps of segmenting the image, comparing the position image with a reference image and the like. The method can accurately diagnose the fault and locate the abnormal position.

Description

Technical Field

[0001] This application relates to the field of fault diagnosis technology, and in particular to a method, apparatus, equipment, storage medium, and product for monitoring the condition of a capacitive voltage transformer. Background Technology

[0002] With the continuous advancement of smart grid construction and the improvement of power system automation, the monitoring and fault diagnosis of the operating status of capacitive voltage transformers (CVTs), as key equipment in power systems, are particularly important. During long-term operation, CVTs are prone to defects such as degradation of dielectric losses in the capacitive voltage divider and overheating of the electromagnetic unit. If these defects are not detected and addressed in a timely manner, they will seriously affect the safe and stable operation of the power system.

[0003] Currently, traditional CVT fault diagnosis methods are easily affected by environmental interference, making it difficult to fully reflect the overall operating status of the CVT and resulting in poor accuracy in CVT fault diagnosis. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for monitoring the condition of a capacitive voltage transformer (CVT), which can improve the accuracy of CVT fault diagnosis.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, this application provides a method for monitoring the condition of a capacitive voltage transformer, including:

[0007] Real-time acquisition of operating status data for each capacitive voltage transformer, including multiple sub-operating status data;

[0008] The collected sub-operating state data of the capacitive voltage transformer are compared with their respective sub-reference state data to obtain the first comparison result;

[0009] If the first comparison result indicates that the value corresponding to the sub-operational status data is greater than the threshold corresponding to the sub-operational status data, then it is determined that the capacitive voltage transformer has a fault risk.

[0010] If the first comparison result indicates that the value corresponding to the sub-operational state data is less than or equal to the threshold corresponding to the sub-operational state data, then the fault characteristic value of the capacitive voltage transformer is determined by multiple sub-operational state data.

[0011] Determine whether the fault characteristic value is greater than the fault threshold to obtain the determination result. The fault threshold is dynamically adjusted based on the equipment health baseline value, the coefficient of variation of the dynamic reference value of the operating status data, the operating condition complexity coefficient, and the equipment health index.

[0012] If the judgment result indicates that the fault characteristic value is greater than the fault threshold, then it is determined that the capacitive voltage transformer has a fault risk.

[0013] If the judgment result indicates that the fault characteristic value is less than or equal to the fault threshold, then it is determined that the capacitive voltage transformer has no fault risk.

[0014] Optionally, the sub-operational status data includes: dielectric loss angle of the capacitor voltage divider, secondary side voltage, temperature of various parts of the capacitor voltage divider, temperature of various parts of the electromagnetic unit, and vibration frequency of various parts of the current transformer.

[0015] Optionally, determining the fault characteristic value of the capacitive voltage transformer through multiple sub-operational state data includes:

[0016] According to the Time to the The first sub-feature value is determined by comparing the value of the dielectric loss angle of the capacitor voltage divider at a given time with the threshold value of the dielectric loss angle of the capacitor voltage divider.

[0017] According to the Time to the The value of the secondary side voltage at time t and the threshold value of the secondary side voltage are used to determine the second sub-characteristic value;

[0018] According to the Time to the The third sub-feature value is determined by comparing the temperature values ​​of each part of the capacitor voltage divider at a given time with the temperature threshold values ​​of each part of the capacitor voltage divider.

[0019] According to the Time to the The fourth sub-feature value is determined by comparing the temperature values ​​of each part of the electromagnetic unit at a given time with the temperature threshold values ​​of each part of the electromagnetic unit.

[0020] According to the Time to the The fifth sub-characteristic value is determined by comparing the vibration frequency values ​​of various parts of the current transformer at different times with the threshold values ​​of the vibration frequency of various parts of the current transformer.

[0021] The fault characteristic value of the capacitive voltage transformer is determined based on the first sub-characteristic value, the second sub-characteristic value, the third sub-characteristic value, the fourth sub-characteristic value, and the fifth sub-characteristic value.

[0022] Optionally, after determining that the capacitive voltage transformer has a risk of failure, the method further includes:

[0023] Obtain the test priority value for each capacitive voltage transformer;

[0024] Take a picture of the capacitive voltage transformer with the highest priority value to be tested to obtain a surface image;

[0025] The abnormal location of the capacitive voltage transformer is obtained by analyzing the surface image.

[0026] Optionally, obtaining the test priority value of each capacitive voltage transformer includes:

[0027] Obtain the time interval from the moment when each capacitive voltage transformer was determined to have a fault risk to the current moment;

[0028] Based on the fault characteristic values ​​of each capacitive voltage transformer and the time interval from the moment when each capacitive voltage transformer was determined to have a fault risk to the current moment, the test priority value of each capacitive voltage transformer is determined.

[0029] Optionally, analyzing the surface image to determine the abnormal location of the capacitive voltage transformer includes:

[0030] The surface image is segmented to obtain partial images of each part of the capacitive voltage transformer;

[0031] The images of each part are compared with their respective reference images to obtain the second comparison result.

[0032] If the second comparison result indicates that the similarity between the image of the target location and the reference image is less than the similarity threshold, then the abnormal location of the capacitive voltage transformer is determined to be the target location.

[0033] Secondly, this application provides a condition monitoring device for a capacitive voltage transformer, comprising:

[0034] The acquisition module is used to acquire the operating status data of each capacitive voltage transformer in real time, and the operating status data includes multiple sub-operating status data.

[0035] The comparison module is used to compare the collected sub-operating state data of the capacitive voltage transformer with their respective sub-reference state data to obtain the first comparison result.

[0036] The determination module is configured to: if the first comparison result indicates that the value corresponding to the sub-operational status data is greater than the threshold corresponding to the sub-operational status data, then determine that the capacitive voltage transformer has a fault risk; if the first comparison result indicates that the value corresponding to the sub-operational status data is less than or equal to the threshold corresponding to the sub-operational status data, then determine the fault characteristic value of the capacitive voltage transformer through multiple sub-operational status data; determine whether the fault characteristic value is greater than the fault threshold to obtain a determination result, wherein the fault threshold is dynamically adjusted based on the equipment health baseline value, the coefficient of variation of the dynamic reference value of the operating status data, the operating condition complexity coefficient, and the equipment health index; if the determination result indicates that the fault characteristic value is greater than the fault threshold, then determine that the capacitive voltage transformer has a fault risk; if the determination result indicates that the fault characteristic value is less than or equal to the fault threshold, then determine that the capacitive voltage transformer does not have a fault risk.

[0037] Thirdly, this application provides a computing device, including a memory and a processor;

[0038] The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0039] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0040] Fifthly, this application provides a computer program product comprising one or more computer instructions, wherein when the computer instructions are executed by a computer, the computer performs the method as described in any one of the first aspects.

[0041] As can be seen from the above technical solution, this application has at least the following beneficial effects:

[0042] From the perspective of fault diagnosis accuracy, this method breaks through the limitations of traditional single-parameter monitoring. It incorporates sub-operational status data such as the dielectric loss angle of the capacitor divider, secondary side voltage, temperature of various parts of the capacitor divider, temperature of various parts of the electromagnetic unit, and vibration frequency of various parts of the transformer into the monitoring system. It can quickly identify obvious fault risks by comparing the sub-operational status data with the corresponding sub-reference thresholds. When all sub-operational status data are compliant, it calculates the first to fifth sub-feature values ​​based on the fluctuation characteristics of the sub-operational status data in the time period t1 to t2, and then merges them to obtain the fault feature value. By using the fault feature value and fault threshold for secondary judgment, it captures potential defects that are not excessive in a single parameter but are abnormal in the coordination of multiple parameters. It effectively avoids misjudgments caused by environmental interference, comprehensively reflects the overall operating status of the CVT, and greatly improves the accuracy of fault diagnosis.

[0043] From the perspective of targeted operation and maintenance response, after determining the fault risk, this method calculates the priority value of the test subject by using the fault characteristic value and the time interval from the risk determination time to the current time. Priority is given to taking pictures of CVTs with high risk level and long warning time to avoid disordered allocation of operation and maintenance resources. At the same time, the surface image is segmented and the similarity of the part image and the reference image is compared to accurately locate abnormal parts such as porcelain bushing cracks, joint heating traces, and oil leaks. There is no need for manual inspection one by one, which reduces the cost of manual intervention in the unmanned operation and maintenance scenario of smart substations and improves the efficiency of fault handling.

[0044] From the perspective of equipment safety and system stability, this method achieves rapid identification of explicit faults and early warning of implicit defects through hierarchical judgment logic. It can not only detect early defects that are easily missed by traditional methods, such as the degradation of dielectric loss of capacitor voltage dividers and overheating of electromagnetic units, but also clarify the root cause of the fault by locating the abnormal part, providing maintenance personnel with accurate maintenance basis, avoiding the expansion of defects that affect the safe and stable operation of the power system, and providing strong support for the automated operation of smart grids.

[0045] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0046] Figure 1 A flowchart illustrating a capacitive voltage transformer state monitoring method provided in this application embodiment;

[0047] Figure 2 A schematic diagram of a capacitive voltage transformer condition monitoring device provided in an embodiment of this application;

[0048] Figure 3 This is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0049] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0050] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0051] To ensure clarity and conciseness in the description of the following embodiments, a brief introduction to the related technologies is given first:

[0052] Capacitive voltage transformers (CVTs) are key devices used for voltage measurement and protection of high-voltage lines in power systems. The structure of a CVT consists of a capacitive voltage divider (used to proportionally convert high voltage to low voltage) and an electromagnetic unit (used for signal isolation and precise conversion). They are widely used in smart substations with voltage levels of 110kV and above and are fundamental components for ensuring the reliable operation of power grid metering, protection and monitoring systems.

[0053] Current CVT fault diagnosis technology is insufficient to meet the operation and maintenance needs of smart grids. The problem lies in the poor accuracy of fault diagnosis, which is manifested in the high rate of missed detection of latent defects, frequent misjudgments caused by environmental interference, and the lack of accurate guidance in operation and maintenance response.

[0054] On the one hand, traditional monitoring methods are often limited to a single parameter dimension, such as monitoring only the secondary voltage or local temperature, which makes it difficult to cover the fault characteristics of multiple coupled components in a CVT. Taking electromagnetic unit overheating as an example, this type of fault is often accompanied by a synergistic change in abnormal vibration frequency and increased dielectric loss angle. Single parameter monitoring can only capture local indicators, easily overlooking the hidden defects of normal local parameters but abnormal overall state, resulting in obvious blind spots in fault warning. At the same time, traditional technology uses static thresholds for judgment, without fully considering the dynamic effects of environmental factors (such as temperature and humidity) and power grid conditions (such as load fluctuations and voltage changes). For example, in the high temperature environment of summer, normal temperature fluctuations in the capacitor divider are easily misjudged as fault signals by static thresholds, further reducing the accuracy of overall diagnosis.

[0055] On the other hand, existing technologies lack both multi-parameter collaborative analysis mechanisms and a scientific operation and maintenance scheduling logic. These two shortcomings further exacerbate the limitations of diagnosis and operation and maintenance. Early defects in CVTs, such as slight insulation aging and slight component loosening, mostly manifest as small collaborative deviations of multiple parameters rather than significant exceedances of a single parameter. Traditional methods, lacking a multi-parameter fusion analysis model, cannot capture these early fault characteristics of quantitative accumulation leading to qualitative change. Warnings are often only issued after the defects have developed and worsened, missing the best opportunity for handling. Furthermore, after discovering fault risks, existing technologies often adopt a crude operation and maintenance model of evenly allocating resources, without prioritizing handling based on the severity of the fault and the duration of the warning. This results in delayed response to high-risk equipment, high time and labor costs for manual inspection, and a serious disconnect from the needs of unmanned operation and maintenance of smart substations.

[0056] In view of this, embodiments of this application provide a method for monitoring the state of a capacitive voltage transformer, which can be executed by a processing device. This processing device can be a terminal or a server. Terminals include, but are not limited to, smartphones, tablets, laptops, personal digital assistants, or smart wearable devices. The server can be a cloud server, such as a central server in a central cloud computing cluster or an edge server in an edge cloud computing cluster. Alternatively, the server can be a server in a local data center. A local data center refers to a data center directly controlled by the user.

[0057] To address the limitations of single-parameter monitoring, environmental interference-induced misjudgments, weak identification of latent defects, and inefficient allocation of maintenance resources in traditional CVT fault diagnosis, this application integrates key CVT sub-operational status data to construct a two-layer diagnostic logic. This logic enables rapid identification of explicit faults through initial threshold comparison and capture of latent defects through multi-parameter fusion calculation, overcoming the limitations of single-parameter monitoring. Simultaneously, a priority scheduling mechanism linking fault feature values ​​and early warning duration is introduced. Combined with image segmentation and similarity comparison, accurate location of abnormal parts is achieved. Ultimately, this realizes intelligent management of the entire process from fault diagnosis to maintenance, improving the accuracy of CVT fault diagnosis and the efficiency of maintenance response, thus meeting the high reliability requirements of smart grids for critical equipment status monitoring.

[0058] To make the technical solution of this application clearer and easier to understand, the following describes a method for monitoring the state of a capacitive voltage transformer provided by an embodiment of this application, in conjunction with the accompanying drawings. Figure 1 As shown, this figure is a flowchart of a capacitive voltage transformer state monitoring method provided in an embodiment of this application. The method includes:

[0059] S201. The processing equipment collects the operating status data of each capacitive voltage transformer in real time. The operating status data includes multiple sub-operating status data.

[0060] A capacitive voltage transformer (CVT) is a key device in a power system used for high-voltage voltage measurement and signal conversion. It converts high voltage to low voltage proportionally through a capacitive voltage divider and an electromagnetic unit, providing reliable signals for metering, protection, and monitoring systems.

[0061] Operational status data is a comprehensive data set that reflects the real-time working status of a CVT, covering multiple dimensions of information such as equipment electrical performance, temperature, and vibration. It serves as the basis for judging whether the equipment is operating normally.

[0062] Sub-operational status data consists of specific parameter items that constitute the operation status data. Sub-operational status data includes: dielectric loss angle of the capacitor voltage divider, secondary side voltage, temperature of various parts of the capacitor voltage divider, temperature of various parts of the electromagnetic unit, and vibration frequency of various parts of the current transformer.

[0063] The dielectric loss angle of a capacitive voltage divider refers to the phase difference angle caused by insulation material losses in a CVT under the influence of an AC electric field. It is an indicator of the insulation performance of the capacitive voltage divider. Under normal circumstances, insulation material losses are small, and the dielectric loss angle remains within a fixed range. When the insulation material ages, becomes damp, or has local defects, the losses increase, and the dielectric loss angle of the capacitive voltage divider deviates from the standard value. Therefore, this dielectric loss angle parameter directly reflects the insulation health status of the capacitive voltage divider and serves as a basis for early warning of insulation degradation faults.

[0064] Secondary voltage refers to the low-voltage signal output by the CVT to the power grid metering, protection, and monitoring system after being stepped down by a capacitor divider and transformed by the electromagnetic unit. It is a parameter reflecting the accuracy of the CVT's voltage transformation. The secondary voltage needs to be stably maintained near its rated value. Abnormal fluctuations (such as being too low, too high, or experiencing periodic oscillations) may indicate an abnormal voltage division ratio in the capacitor divider, saturation of the electromagnetic unit core, or a winding fault, directly affecting the accuracy of power grid monitoring data and the reliable operation of the protection system.

[0065] The temperatures of various parts of the capacitor divider refer to the real-time temperatures of different key locations on the CVT capacitor divider body. These key locations include the top, middle, and bottom of the capacitor cells, as well as the connection points with the electromagnetic unit. Temperature data is collected by temperature sensors mounted at the corresponding locations. During normal operation, the capacitor divider exhibits a uniform temperature distribution and maintains a reasonable temperature difference with the ambient temperature. If the temperature of any part rises abnormally, such as localized overheating, it may be due to internal capacitor cell breakdown, aging and heating of the insulating dielectric, or excessive contact resistance. This temperature parameter can promptly detect the risk of thermal anomalies in the capacitor divider.

[0066] The temperature of various parts of the electromagnetic unit refers to the real-time temperature of different critical locations within the CVT electromagnetic unit. The electromagnetic unit includes components such as the iron core, windings, and oil tank. Critical locations include the iron core body, winding ends, and the surface of the oil tank. Temperature data is also collected using dedicated temperature sensors. The electromagnetic unit is the core of the CVT's signal conversion. During normal operation, it generates heat due to iron core losses and winding copper losses, but the temperature must be controlled within a safe range. If the temperature rises abnormally, such as due to a winding short circuit causing localized high temperatures or multiple grounding points in the iron core causing overheating, it will accelerate insulation aging and may even lead to serious faults such as oil tank leakage and winding burnout. This parameter is the basis for monitoring the health status of the electromagnetic unit.

[0067] The vibration frequency of various parts of the current transformer refers to the mechanical vibration frequency generated at different key locations of the CVT body during operation. These key locations include the base, the capacitor divider housing, and the electromagnetic unit oil tank. Vibration data is collected by vibration sensors installed at the corresponding locations. During normal operation, the vibration frequency of the CVT is stable, mostly a multiple of the grid frequency, such as 50Hz or 100Hz, and the amplitude is relatively small. If there is a deviation in vibration frequency, an increase in amplitude, or abnormal harmonic components, it may be due to loose mechanical components, such as loose base bolts, detachment of capacitor unit fixing structure, or loose electromagnetic unit core or winding deformation. This parameter can provide early warning of CVT mechanical structure faults and electromagnetic anomalies, avoiding equipment damage caused by increased vibration.

[0068] The processing equipment uses pre-deployed sensors, including temperature sensors mounted on the capacitive voltage divider and electromagnetic unit, vibration sensors installed on the transformer base, and a voltage signal acquisition module, to acquire real-time operating information for each CVT at a preset acquisition frequency of 1-5 minutes per acquisition. This acquisition frequency can be adjusted according to the power grid operation and maintenance needs. The "real-time" aspect emphasizes the synchronization between data acquisition and the actual operating status of the equipment, avoiding missed fault detections due to data delays. The "individual" aspect demonstrates the batch monitoring capability for multiple CVTs, adapting to scenarios where multiple devices in a substation are operated and maintained in parallel.

[0069] More importantly, the operational status data collected by the processing equipment is not a simple, single-dimensional dataset, but rather a collection of multiple sub-operational status data, including the dielectric loss angle of the capacitor divider, secondary voltage, temperatures of various components, and vibration frequency. This multi-parameter acquisition design is essentially to cover the characteristics of different CVT fault types. For example, capacitor divider insulation degradation is mainly reflected through the dielectric loss angle, electromagnetic unit overheating requires electromagnetic unit temperature monitoring, and loose mechanical components are detected by vibration frequency. By simultaneously acquiring multi-dimensional sub-data, the limitations of traditional single-parameter monitoring—which only sees a part and not the whole—can be avoided. For example, monitoring only temperature cannot detect insulation degradation risks, and monitoring only voltage is insufficient to detect mechanical loosening, thus providing comprehensive raw data support for subsequent multi-parameter fusion analysis to identify explicit faults and detect latent defects.

[0070] S202. The processing equipment compares the collected sub-operating state data of the capacitive voltage transformer with their respective sub-reference state data to obtain the first comparison result.

[0071] Sub-reference status data refers to the preset reference thresholds or reference ranges for each sub-operational status data that conform to the normal operation standards of CVT. These can be dynamically adjusted according to the CVT model, power grid conditions, and environmental conditions. For example, the normal reference value of the dielectric loss angle of the capacitor divider and the rated reference range of the secondary voltage are benchmarks for measuring whether the sub-operational status data is normal.

[0072] The first comparison result refers to the judgment result generated by the processing equipment after comparing each sub-operational status data with the corresponding sub-reference status data to determine whether it meets the standard. For example, a sub-operational status data is greater than the corresponding sub-reference status data, or a sub-operational status data is within the range of the corresponding sub-reference status data. This is the direct basis for subsequent judgment on whether there is a risk of failure in the CVT.

[0073] The processing device will match each CVT sub-operational status data collected previously with its corresponding sub-reference status data one by one. Then, according to the preset comparison rules, it will perform calculations and judgments on each set of sub-operational status data and sub-reference status data, and finally generate the first comparison result of whether each sub-operational status data meets the normal standard. For example, the comparison rules can be numerical comparison, judgment of whether the data is within the reference range, etc.

[0074] This step transforms the raw monitoring data into a preliminary judgment of whether it is abnormal, providing a basis for subsequent stratified diagnosis. If the first comparison result of a certain sub-operational status data shows that it exceeds the sub-reference status data, it can be quickly and preliminarily determined that there is a risk of failure in the CVT. If the first comparison results of all sub-operational status data show that they conform to the sub-reference status data, it is necessary to proceed to the subsequent multi-parameter fusion analysis stage to further investigate hidden defects.

[0075] S203. If the value corresponding to the sub-operational status data in the first comparison result is greater than the threshold corresponding to the sub-operational status data, then it is determined that the capacitive voltage transformer has a fault risk.

[0076] The values ​​corresponding to the sub-operational status data refer to the specific measured values ​​of each sub-operational status parameter of the CVT, which are collected in real time by sensors and received by processing equipment. For example, the measured value of the dielectric loss angle of the capacitor divider at a certain moment, the measured value of the secondary voltage, the measured value of the temperature of a certain part of the capacitor divider, etc.

[0077] The threshold values ​​corresponding to the sub-operation status data are preset critical values ​​for each sub-operation status data item, which are used to distinguish between normal and abnormal conditions. They serve as the benchmark for measuring whether the sub-operation status data exceeds the safe range. Examples include the maximum allowable value of the dielectric loss angle of the capacitor voltage divider, the highest safe value of the secondary voltage, and the upper limit of the temperature of various parts of the capacitor voltage divider.

[0078] The threshold corresponding to the sub-operational status data can be dynamically adjusted. The calculation expression for the threshold of the dielectric loss angle of the capacitor voltage divider is as follows:

[0079]

[0080] in, Indicates time The threshold value of the dielectric loss angle of the capacitor divider. Indicates the rated dielectric loss angle of the CVT. The first coefficient representing the dielectric loss angle, The second coefficient represents the dielectric loss angle. The third coefficient representing the dielectric loss angle. Indicates time Real-time altitude, A reference value representing altitude. This indicates the real-time load, reflecting the degree of equipment aging; an increased load indicates accelerated aging. The reference value representing the load. Indicates time Real-time grid voltage, This indicates the rated mains voltage.

[0081] The expression for calculating the threshold voltage of the secondary side is:

[0082]

[0083] in, Indicates time The threshold of the secondary side voltage, Indicates the rated secondary voltage of the CVT. The first coefficient represents the secondary voltage. The second coefficient represents the secondary voltage. Indicates time Real-time grid voltage, Indicates the rated mains voltage. Indicates time Real-time load current, This indicates the rated load current.

[0084] The formulas for calculating the temperature thresholds of various parts of the capacitor voltage divider are as follows:

[0085]

[0086] in, Indicates time The capacitor divider The temperature threshold of the part, This indicates the rated operating temperature of the capacitor divider. Indicates the capacitor divider's first... The location coefficient of a component, for example, is 0.9 for the top and 1.1 for the bottom near the heat source, reflecting the difference in heat dissipation at different installation locations. The first coefficient representing the temperature of the capacitor voltage divider section. The second coefficient representing the temperature of the capacitor voltage divider section. Indicates time Real-time ambient temperature, A reference value representing ambient temperature. Indicates time Real-time grid load, This indicates the rated grid load.

[0087] The formula for calculating the temperature threshold of each part of the electromagnetic unit is as follows:

[0088]

[0089] in, Indicates time The electromagnetic unit The temperature threshold of the part, Indicates the rated operating temperature of the electromagnetic unit. Indicates the electromagnetic unit number The location coefficient of a component, for example, is 1 for the surface of the fuel tank and 1.2 for the area near the iron core, reflecting the differences in heat dissipation / heat generation at different installation locations. The first coefficient representing the temperature of the electromagnetic unit. The second coefficient representing the temperature of the electromagnetic unit. The third coefficient representing the temperature of the electromagnetic unit. Indicates time Real-time ambient temperature, A reference value representing ambient temperature. Indicates time Real-time grid load, Indicates the rated grid load. Indicates time Real-time load current, This indicates the rated load current.

[0090] The calculation formula for the threshold vibration frequency of each part of the current transformer is as follows:

[0091]

[0092] in, Indicates time The mutual inductor The threshold of the vibration frequency of a part. Indicates the rated vibration frequency. Indicates the mutual inductor number 1 The position coefficient of a component, for example, 1.2 for the base and 0.9 for the top, reflects the differences in vibration characteristics at different installation locations. The first coefficient representing the vibration frequency of the current transformer component. The second coefficient representing the vibration frequency of the current transformer section. The third coefficient represents the vibration frequency of the current transformer section. Indicates time Real-time grid load, Indicates the rated grid load. Indicates real-time load. The reference value representing the load. Indicates time Real-time wind speed, A baseline value representing wind speed.

[0093] After the processing equipment completes the comparison between the sub-operational status data and the corresponding threshold, it will analyze the first comparison result of each sub-operational status data. If the first comparison result of a certain sub-operational status data shows that the measured value of the sub-operational status data exceeds its corresponding threshold, such as the measured value of the dielectric loss angle of the capacitor voltage divider being greater than the maximum allowable value, or the measured value of the secondary voltage being higher than the maximum safe value, then it will be directly determined that the CVT has a fault risk.

[0094] S204. If the value corresponding to the sub-operational status data in the first comparison result is less than or equal to the threshold corresponding to the sub-operational status data, then the fault characteristic value of the capacitive voltage transformer is determined by multiple sub-operational status data.

[0095] Fault characteristic values ​​are comprehensive indicators generated based on multiple compliant sub-operational status data through preset algorithms (such as weighted fusion, deviation accumulation calculation, etc.). They are used to quantify the overall fault risk of CVT and can integrate the small fluctuation characteristics of multiple parameters to capture hidden defects where a single sub-data is compliant but multiple parameters are abnormally coordinated.

[0096] If the first comparison result of all sub-operational status data shows that the measured value is less than or equal to the corresponding threshold, it indicates that no single sub-data item has obviously exceeded the standard, but there may be a hidden defect of a single parameter being normal and multiple parameters being offset collaboratively.

[0097] To capture these hidden risks, the processing equipment will further invoke a preset fusion algorithm, taking all compliant sub-operational status data as input, and integrating multi-dimensional information through weighted calculation, deviation accumulation, and other methods to finally generate a fault characteristic value that can reflect the overall failure risk of the CVT.

[0098] The specific method for determining the fault characteristic values ​​of a capacitive voltage transformer is as follows:

[0099] Processing equipment according to the first Time to the The first sub-characteristic value is determined by comparing the value of the dielectric loss angle of the capacitor voltage divider at a given time with the threshold value of the dielectric loss angle. The expression for calculating the first sub-characteristic value is:

[0100]

[0101] in, Represents the first sub-eigenvalue. Indicates time The value of the dielectric loss angle of the capacitor voltage divider. Indicates time The threshold value of the dielectric loss angle of the capacitor divider. Indicates the first time, Indicates the first time.

[0102] Processing equipment according to the first Time to the The value of the secondary side voltage at time t and the threshold value of the secondary side voltage are used to determine the second sub-eigenvalue. The expression for calculating the second sub-eigenvalue is:

[0103]

[0104] in, Indicates the second sub-eigenvalue. Indicates time The value of the secondary voltage. Indicates time The threshold of the secondary side voltage.

[0105] Processing equipment according to the first Time to the The third sub-characteristic value is determined by comparing the temperature values ​​of various parts of the capacitor voltage divider at different times with the temperature threshold values ​​of those parts. The expression for calculating the third sub-characteristic value is:

[0106]

[0107] in, Represents the third sub-eigenvalue. Indicates time The capacitor divider The temperature value of the part. Indicates time The capacitor divider The temperature threshold of the part, This indicates the number of components included in a capacitor voltage divider.

[0108] Processing equipment according to the first Time to the The fourth sub-eigenvalue is determined by comparing the temperature values ​​of various parts of the electromagnetic unit at different times with the temperature thresholds for each part. The expression for calculating the fourth sub-eigenvalue is as follows:

[0109]

[0110] in, Represents the fourth sub-eigenvalue. Indicates time The electromagnetic unit The temperature value of the part. Indicates time The electromagnetic unit The temperature threshold of the part, This indicates the number of parts contained in an electromagnetic unit.

[0111] Processing equipment according to the first Time to the The fifth sub-characteristic value is determined by comparing the vibration frequency values ​​of various parts of the current transformer at a given time with the threshold values ​​of those frequencies. The expression for calculating the fifth sub-characteristic value is as follows:

[0112]

[0113] in, Represents the fifth sub-eigenvalue. Indicates time The mutual inductor The numerical value of the vibration frequency of the part. Indicates time The mutual inductor The threshold of the vibration frequency of a part. This indicates the number of components contained in the current transformer.

[0114] The processing equipment determines the fault characteristic values ​​of the capacitive voltage transformer based on the first, second, third, fourth, and fifth sub-characteristic values. The calculation expression for the fault characteristic values ​​is:

[0115]

[0116] in, Indicates fault characteristic values, This is represented as the first weighting coefficient. This is represented as the second weighting coefficient. Represented as the third weighting coefficient, This is represented as the fourth weighting coefficient. It is represented as the fifth weighting coefficient.

[0117] S205. The processing equipment determines whether the fault characteristic value is greater than the fault threshold and obtains the judgment result.

[0118] The fault threshold is a preset critical value based on fault characteristic values, used to distinguish between a healthy CVT and one with a risk of failure. It serves as a benchmark for measuring whether the overall operating status of the CVT exceeds the safe range. For example, the fault threshold for a certain CVT model might be set to 8. The fault threshold is dynamically adjusted based on the equipment health baseline value, the coefficient of variation of dynamic reference values ​​for operating status data, the operating condition complexity coefficient, and equipment health indicators.

[0119] The judgment result refers to the clear conclusion generated by the processing equipment after comparing the fault characteristic value with the fault threshold, which is whether the fault characteristic value is greater than the fault threshold. It is usually divided into two categories: the fault characteristic value is greater than the fault threshold or the fault characteristic value is less than or equal to the fault threshold. It is the direct basis for finally determining whether there is a fault risk in the CVT.

[0120] The processing equipment adjusts the fault threshold based on the equipment health baseline value, the coefficient of variation of dynamic reference values ​​of operating status data, the operating condition complexity coefficient, and equipment health indicators. The formula for calculating the fault threshold is:

[0121]

[0122] in, Indicates time The fault threshold, This represents the baseline health value of the equipment, calculated from the fault-free historical data of the CVT during its initial 1-2 years of operation. The first coefficient represents the fault threshold. The second coefficient represents the fault threshold. The third coefficient represents the fault threshold. express The average value comprehensively reflects the overall stability of all operational status data reference values. Indicates the first The coefficient of variation of dynamic reference values ​​for each running status data point Indicates time The operating condition complexity coefficient is adjusted accordingly; the more complex the operating condition, the larger the correction. Indicates time The equipment health index; the higher the health level, the smaller the correction for this item. This represents the maximum value of the device's health status.

[0123] The calculation expression is:

[0124]

[0125] in, Indicates the first The coefficient of variation of dynamic reference values ​​for each running status data point Indicates the number of times within the last hour The standard deviation of the dynamic reference values ​​of the operating status data Indicates the number of times within the last hour The mean of the dynamic reference values ​​for each running status data.

[0126] The calculation expression is:

[0127]

[0128] in, Indicates time The working condition complexity coefficient, The first coefficient representing the complexity of the operating condition. The second coefficient representing the complexity of the operating conditions. The third coefficient represents the complexity of the operating conditions.

[0129] After generating fault feature values ​​from multi-sub-operational status data, the processing device will call the preset judgment logic to compare the calculated fault feature values ​​(e.g., the quantization result is 10) with the preset fault threshold (e.g., set to 8).

[0130] Through this comparison, the processing equipment will generate a clear judgment result. If the fault characteristic value is greater than the fault threshold, it means that the overall operating status of the CVT has exceeded the safe range and there is a hidden or potential fault risk. If the fault characteristic value is less than or equal to the fault threshold, it means that the overall health status of the CVT meets the preset standard.

[0131] The purpose of this step is to transform the quantified fault characteristic values ​​into clear risk assessment conclusions, providing the final decision-making basis for whether to initiate subsequent maintenance responses (such as photo location and alarm notifications), and ensuring an accurate assessment of the overall CVT fault risk.

[0132] S206. If the judgment result indicates that the fault characteristic value is greater than the fault threshold, then it is determined that the capacitive voltage transformer has a fault risk.

[0133] If the judgment result clearly shows that the fault characteristic value is greater than the fault threshold, it means that although the multi-dimensional sub-operational status data of the CVT has not exceeded the standard in any single case, the coordinated anomaly formed by these sub-data during operation has caused the overall risk of the equipment to exceed the preset safety range, and thus it can be determined that the CVT has hidden or potential fault risks.

[0134] From the perspective of data characteristics, in this type of situation, whether it is the dielectric loss angle of the capacitor divider, the secondary side voltage, or the sub-operational status data such as temperature and vibration frequency of various parts, when compared with their respective sub-reference thresholds, they are all within the compliance range, and there is no obvious single parameter anomaly.

[0135] However, from the perspective of overall correlation, there is a subtle synergy among these sub-data. For example, although the dielectric loss angle of the capacitor divider is within the normal range, it shows a slow upward trend. At the same time, the temperature of a certain part of the electromagnetic unit is slightly higher than the historical average for the same period, and the vibration frequency of the transformer base shows a slight shift. These subtle changes that are difficult to detect in a single dimension, after being integrated and calculated to form fault characteristic values, will exceed the safety limit of the fault threshold.

[0136] Such coordinated anomalies are often early signals of latent defects within the CVT. They may originate from slight aging of insulation materials, minor loosening of component connections, or potential losses within the electromagnetic unit. If not addressed in time, these latent defects may gradually develop into overt faults as operating time progresses. For example, increased insulation degradation may lead to a significant exceedance of the dielectric loss angle, or loose components may cause abnormally increased vibration, ultimately affecting the normal operation of the CVT and even impacting the stability of the power system.

[0137] Therefore, capturing such hidden risks by judging whether the fault characteristic value is greater than the fault threshold is a key link in ensuring the safe operation of CVT throughout its entire life cycle.

[0138] S207. If the judgment result indicates that the fault characteristic value is less than or equal to the fault threshold, then it is determined that the capacitive voltage transformer has no fault risk.

[0139] When the judgment result shows that the fault characteristic value is less than or equal to the fault threshold, it means that two aspects of information are verified: First, all the sub-operational status data collected previously, such as the dielectric loss angle of the capacitor divider, the secondary side voltage, the temperature of each part, and the vibration frequency, are within the compliance range when compared with their respective sub-reference thresholds, and there is no single parameter abnormality.

[0140] On the other hand, the overall risk index formed by the fusion and calculation of these sub-data, namely the fault characteristic value, has not exceeded the safety threshold and there is no hidden defect of a single parameter being normal but multiple parameters being abnormal in coordination.

[0141] From a practical operational perspective, this assessment indicates that the CVT's current insulation performance, voltage conversion accuracy, thermal stability, and mechanical structure stability all meet design requirements. There are no potential internal faults, and it can meet the power system's operational needs without requiring subsequent maintenance response actions (such as photo location, alarm prompts, etc.).

[0142] This rule avoids excessive maintenance of normally operating equipment and ensures the reliability of risk-free determination through multi-parameter fusion verification, providing an accurate basis for efficient power grid operation and maintenance.

[0143] After determining that the capacitive voltage transformer has a fault risk, the method also includes in-depth analysis of the abnormal parts of the capacitive voltage transformer. The specific implementation steps are as follows:

[0144] First, the processing equipment obtains the test priority values ​​for each capacitive voltage transformer.

[0145] The test priority value is used to measure the urgency and handling priority of different CVT failure risks. A higher value indicates that maintenance and testing should be scheduled more quickly. The test priority value is obtained as follows:

[0146] Specifically, the processing equipment acquires the time interval from the moment when each capacitive voltage transformer was determined to be at risk of failure to the current moment.

[0147] The moment when a fault risk is identified refers to the specific time point at which the processing equipment, after completing data comparison and judgment, clearly determines that a certain CVT has a fault risk. The time is accurate to the second or minute, such as 2024-05-20-14:30:00. This time point will be automatically recorded and stored by the processing equipment as the reference time for subsequent calculations.

[0148] The current moment refers to the real-time point when the processing equipment starts calculating the time interval. It uses the same time standard as the moment when a fault risk is determined, and it is the end time of the calculated time interval.

[0149] The time interval refers to the difference in duration between the moment when a fault risk is identified and the current moment. It is used to measure the duration of a CVT's fault risk and is one of the parameters for calculating the priority value to be tested.

[0150] Once multiple CVTs have been identified as having a fault risk, the processing device first retrieves the moment when the fault risk was identified for each CVT from its own database. This moment is the time automatically recorded when the device completed the fault judgment (such as exceeding the sub-data limit or the fault characteristic value limit). Then, the processing device obtains the real-time time at the time of the current calculation, i.e., the current moment. Finally, using a preset time difference algorithm, the device subtracts the moment when the fault risk was identified from the current moment to obtain the specific time interval from when the fault risk was discovered for each CVT.

[0151] The processing equipment determines the test priority value for each capacitive voltage transformer based on its fault characteristic values ​​and the time interval from the moment each transformer was determined to have a fault risk to the current moment. The expression for calculating the test priority value is as follows:

[0152]

[0153] in, Indicates the priority value to be tested. These are fault characteristic values. The first preset coefficient, The second coefficient is preset. This is the time interval from the moment when the capacitive voltage transformer was determined to be at risk of failure to the present moment.

[0154] Then, the processing equipment takes a picture of the capacitive voltage transformer with the highest priority value to be tested, and obtains a surface image.

[0155] The capacitive voltage transformer (CVT) with the highest test priority value refers to the CVT with the highest test priority value calculated by the processing equipment among all CVTs identified as having a risk of failure. This equipment usually indicates a higher severity of failure risk and a longer duration of risk, and is the one that currently requires the highest priority for operation and maintenance testing.

[0156] Taking pictures refers to the process of sending a shooting command to cameras (such as high-definition industrial cameras or cameras carried by inspection robots) pre-deployed around the CVT, so that the cameras can capture images of the visible areas of the target CVT, such as its appearance, shell, and connection parts, in order to obtain visual information about the surface of the equipment.

[0157] Surface images refer to images obtained by taking pictures that reflect the external shape and surface condition of the CVT. They can clearly show whether there is damage, oil leakage, or rust on the equipment shell, whether there are loose marks on the connection parts, and whether there are abnormal heat discoloration on the surface. They serve as a visual basis for locating abnormal parts.

[0158] After the processing equipment completes the calculation and sorting of the test priority values ​​of all risky CVTs, it will automatically identify the CVT with the highest test priority value. This CVT is the one with the most urgent fault risk and needs to be dealt with first. Then, the processing equipment will send a photo-taking command to the preset camera matched with the CVT. After receiving the command, the camera will take pictures of the visible areas of the CVT, such as the body, shell, and key connection points. Finally, the captured surface image will be sent back to the processing equipment, which will then receive and store the image.

[0159] The purpose of this step is to transform abstract fault risks into concrete surface information: through surface images, it is possible to intuitively observe whether there are externally visible anomalies in the CVT (such as shell cracks, oil leaks, component deformation, etc.), providing visual support for subsequent comparison with normal images and accurate location of internal abnormal parts (such as shell discoloration corresponding to overheated areas), avoiding blind troubleshooting by maintenance personnel and improving fault location efficiency.

[0160] Finally, the processing equipment analyzes the surface image to identify the abnormal locations of the capacitive voltage transformer.

[0161] Specifically, firstly, the processing equipment segments the surface image to obtain partial images of each part of the capacitive voltage transformer.

[0162] Segmentation refers to the process of dividing a surface image into regions according to the physical structural features of a CVT (such as the contours and positions of different functional components) using image recognition algorithms, such as deep learning semantic segmentation models and edge detection algorithms. Essentially, it is about separating independent visual regions from different parts of the overall image.

[0163] The part images refer to the local images of different functional components of the CVT obtained by segmentation, such as the top image of the capacitor divider, the surface image of the electromagnetic unit oil tank, and the image of the base connection part. Each part image contains only visual information of a single functional component and serves as the basic unit for subsequent targeted analysis.

[0164] After acquiring the surface image of the CVT with the highest priority value, the processing equipment calls the preset image segmentation algorithm. First, it identifies the contour boundaries of each functional component of the CVT in the image through feature extraction, such as the connection gap between the capacitor divider and the electromagnetic unit, and the structural boundary between the oil tank and the base. Then, based on these boundaries, the overall surface image is divided into multiple independent regions, each corresponding to a specific part of the CVT, such as the top of the capacitor divider, the outer shell of the winding end, the bolt connection area of ​​the base, etc. Finally, it outputs an independent image of each part, i.e., the part image.

[0165] The purpose of this step is to achieve accurate decomposition from the whole to the part: the original surface image contains the whole picture of the CVT, making it difficult to directly locate specific abnormal parts; while the part images obtained by segmentation can focus on a single functional component, which is convenient for subsequent targeted analysis of the characteristics of different parts, laying the foundation for accurate matching of abnormal types.

[0166] Then, the processing device compares the image of each part with the corresponding reference image of each part to obtain the second comparison result.

[0167] The reference images corresponding to each part refer to the standard images of each part of the CVT under normal operating conditions, which are pre-stored in the processing equipment. These images need to be collected when the CVT is in a healthy state after leaving the factory or after maintenance, and include the normal appearance characteristics of each part (such as color, texture, and structural integrity), which serve as the benchmark for measuring whether there are any abnormalities in the part images.

[0168] Comparison refers to the process by which processing equipment uses image feature comparison algorithms, such as pixel difference analysis and feature point matching, to extract visual features of the part image and the corresponding reference image one by one, such as color distribution, contour shape, and texture details, and to perform difference detection on the features of the two. Essentially, it is to determine whether there is a deviation between the part image and the standard state.

[0169] The second comparison result refers to the conclusion generated by the processing equipment after comparing the images of each part with the reference image. It usually includes specific judgments such as no obvious difference, abnormal color, structural deformation, and foreign matter (such as oil stains), which directly reflect whether the appearance of each part of the CVT deviates from the normal state.

[0170] After obtaining images of each part of the CVT, the processing device retrieves the corresponding reference image for each part image according to the part matching principle. Then, the processing device starts the preset image comparison algorithm to extract the key visual features of the two sets of images respectively. For example, it compares whether there is abnormal color change (such as yellowing of the shell due to overheating), whether there is structural deformation of the contour (such as shell dent), and whether there are extra foreign objects on the surface (such as oil leakage marks). Finally, based on the presence and type of feature differences, an independent second comparison result is generated for each part.

[0171] The purpose of this step is to transform the local image into a location anomaly determination: by accurately comparing it with the standard reference image, subtle appearance anomalies in a single location can be quickly identified, avoiding oversights in manual observation; at the same time, the second comparison result can be directly associated with the specific location, providing a clear basis for subsequently pinpointing the source of the fault (such as fuel tank seal failure) and developing targeted operation and maintenance plans.

[0172] If the second comparison result indicates that the similarity between the image of the target part and the reference image is less than the similarity threshold, then the abnormal part of the capacitive voltage transformer is determined to be the target part.

[0173] Similarity refers to the degree of similarity between a part image and a reference image, obtained through image comparison algorithms. It is represented by a value of 0-100% or 0-1. The higher the value, the closer the appearance features (color, structure, texture) of the two are, and the closer the part is to normal.

[0174] The similarity threshold is a pre-set critical value that divides a part of the image into similar and dissimilar images with a reference image. For example, 80% can be dynamically adjusted according to the image clarity and the characteristics of the part. It is a benchmark for measuring whether the appearance of a part deviates from the normal standard. If it is lower than the threshold, it is considered that there is a significant difference in appearance.

[0175] Abnormal areas refer to specific parts of the CVT whose appearance deviates from the normal state. The similarity between the image of this part and the reference image is lower than the threshold, which may indicate problems such as damage, oil leakage, discoloration, or deformation. These areas are the targets for subsequent maintenance and troubleshooting to identify the source of the fault.

[0176] After generating the second comparison results for each part, the processing device will extract the similarity value between the part image and the reference image for each target part, and compare it with the preset similarity threshold.

[0177] If the second comparison result shows that the similarity value of the target part is less than the similarity threshold, it means that the appearance characteristics (such as surface color and structural integrity) of the part are significantly different from the normal state. For example, there are oil stains on the surface of the fuel tank that are not in the reference image, or there are discolored areas on the casing of the capacitor voltage divider that are not in the reference image. At this time, the processing equipment can directly determine that the target part is the current abnormal part of the CVT.

[0178] This step transforms abstract similarity values ​​into specific anomaly locations, avoiding the predicament of knowing there's a risk of equipment failure but being unable to pinpoint the problem area. By clearly identifying the anomaly, maintenance personnel can be guided to conduct in-depth testing directly on that area, such as disassembling and inspecting the internal structure and measuring local temperatures, significantly shortening troubleshooting time and improving maintenance efficiency.

[0179] Based on the above description, this application has the following beneficial effects:

[0180] From the perspective of fault diagnosis accuracy, this method breaks through the limitations of traditional single-parameter monitoring. It incorporates sub-operational status data such as the dielectric loss angle of the capacitor divider, secondary side voltage, temperature of various parts of the capacitor divider, temperature of various parts of the electromagnetic unit, and vibration frequency of various parts of the transformer into the monitoring system. It can quickly identify obvious fault risks by comparing the sub-operational status data with the corresponding sub-reference thresholds. When all sub-operational status data are compliant, it calculates the first to fifth sub-feature values ​​based on the fluctuation characteristics of the sub-data in the time period t1 to t2, and then merges them to obtain the fault feature value. By using the fault feature value and fault threshold for secondary judgment, it captures potential defects where a single parameter does not exceed the standard but multiple parameters are abnormally coordinated. It effectively avoids misjudgments caused by environmental interference, comprehensively reflects the overall operating status of the CVT, and significantly improves the accuracy of fault diagnosis.

[0181] From the perspective of targeted operation and maintenance response, after determining the fault risk, this method calculates the priority value of the test subject by using the fault characteristic value and the time interval from the risk determination time to the current time. Priority is given to taking pictures of CVTs with high risk level and long warning time to avoid disordered allocation of operation and maintenance resources. At the same time, the surface image is segmented and the similarity of the part image and the reference image is compared to accurately locate abnormal parts such as porcelain bushing cracks, joint heating traces, and oil leaks. There is no need for manual inspection one by one, which reduces the cost of manual intervention in the unmanned operation and maintenance scenario of smart substations and improves the efficiency of fault handling.

[0182] From the perspective of equipment safety and system stability, this method achieves rapid identification of explicit faults and early warning of implicit defects through hierarchical judgment logic. It can not only detect early defects that are easily missed by traditional methods, such as the degradation of dielectric loss of capacitor voltage dividers and overheating of electromagnetic units, but also clarify the root cause of the fault by locating the abnormal part, providing maintenance personnel with accurate maintenance basis, avoiding the expansion of defects that affect the safe and stable operation of the power system, and providing strong support for the automated operation of smart grids.

[0183] The above text combined Figure 1 The capacitive voltage transformer state monitoring method provided in the embodiments of this application has been described in detail. The apparatus and equipment provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0184] like Figure 2 As shown in the figure, this is a schematic diagram of a capacitive voltage transformer condition monitoring device provided in an embodiment of this application. The device includes:

[0185] The acquisition module 301 is used to acquire the operating status data of each capacitive voltage transformer in real time, and the operating status data includes multiple sub-operating status data.

[0186] The comparison module 302 is used to compare the collected sub-operating state data of the capacitive voltage transformer with their respective sub-reference state data to obtain the first comparison result.

[0187] The determination module 303 is configured to: determine if the value corresponding to the sub-operational status data is greater than the threshold value corresponding to the sub-operational status data in the first comparison result, then determine that the capacitive voltage transformer has a fault risk; determine if the value corresponding to the sub-operational status data is less than or equal to the threshold value corresponding to the sub-operational status data in the first comparison result, then determine the fault characteristic value of the capacitive voltage transformer through multiple sub-operational status data; determine whether the fault characteristic value is greater than the fault threshold value to obtain a determination result, wherein the fault threshold value is dynamically adjusted based on the equipment health baseline value, the coefficient of variation of the dynamic reference value of the operating status data, the operating condition complexity coefficient, and the equipment health index; determine if the determination result indicates that the fault characteristic value is greater than the fault threshold value, then determine that the capacitive voltage transformer has a fault risk; determine if the determination result indicates that the fault characteristic value is less than or equal to the fault threshold value, then determine that the capacitive voltage transformer does not have a fault risk.

[0188] Optionally, module 303 is determined, specifically for use according to the first... Time to the The first sub-feature value is determined by comparing the value of the dielectric loss angle of the capacitor voltage divider at a given time with the threshold value of the dielectric loss angle of the capacitor voltage divider.

[0189] According to the Time to the The value of the secondary side voltage at time t and the threshold value of the secondary side voltage are used to determine the second sub-characteristic value;

[0190] According to the Time to the The third sub-feature value is determined by comparing the temperature values ​​of each part of the capacitor voltage divider at a given time with the temperature threshold values ​​of each part of the capacitor voltage divider.

[0191] According to the Time to the The fourth sub-feature value is determined by comparing the temperature values ​​of each part of the electromagnetic unit at a given time with the temperature threshold values ​​of each part of the electromagnetic unit.

[0192] According to the Time to the The fifth sub-characteristic value is determined by comparing the vibration frequency values ​​of various parts of the current transformer at different times with the threshold values ​​of the vibration frequency of various parts of the current transformer.

[0193] The fault characteristic value of the capacitive voltage transformer is determined based on the first sub-characteristic value, the second sub-characteristic value, the third sub-characteristic value, the fourth sub-characteristic value, and the fifth sub-characteristic value.

[0194] Optionally, the acquisition module 301 is also used to acquire the test priority value of each capacitive voltage transformer; and to take a picture of the capacitive voltage transformer with the largest test priority value to obtain a surface image.

[0195] The determination module 303 is also used to analyze the surface image to obtain the abnormal location of the capacitive voltage transformer.

[0196] Optionally, the acquisition module 301 is specifically used to acquire the time interval from the moment when each capacitive voltage transformer is determined to have a fault risk to the current moment.

[0197] The determination module 303 is specifically used to determine the test priority value of each capacitive voltage transformer based on the fault characteristic value of each capacitive voltage transformer and the time interval from the moment when each capacitive voltage transformer is determined to have a fault risk to the current moment.

[0198] Optionally, the comparison module 302 is specifically used to segment the surface image to obtain partial images of each part of the capacitive voltage transformer;

[0199] The images of each part are compared with their respective reference images to obtain the second comparison result.

[0200] The determination module 303 is specifically used to determine the abnormal part of the capacitive voltage transformer as the target part if the similarity between the part image representing the target part and the reference image is less than the similarity threshold.

[0201] The capacitive voltage transformer condition monitoring device according to the embodiments of this application can correspond to the execution of the method described in the embodiments of this application, and the other operations and / or functions of each module / unit of the capacitive voltage transformer condition monitoring device are respectively for realizing Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0202] This application also provides a computing device. For example... Figure 3 As shown in the figure, this is a schematic diagram of a computing device provided in an embodiment of this application. The computing device 700 includes a bus 701, a processor 702, a communication interface 703, and a memory 704. The processor 702, the memory 704, and the communication interface 703 communicate with each other via the bus 701.

[0203] The 701 bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0204] The processor 702 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0205] The communication interface 703 is used for communication with external devices.

[0206] Memory 704 may include volatile memory, such as random access memory (RAM). Memory 704 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0207] The memory 704 stores executable code, and the processor 702 executes the executable code to perform the aforementioned capacitive voltage transformer state monitoring method.

[0208] Specifically, in achieving Figure 2 In the case of the illustrated embodiment, and Figure 2 When the modules or units of the capacitive voltage transformer state monitoring device described in the embodiment are implemented by software, the following steps are performed: Figure 2 The software or program code required for the functions of each module / unit can be partially or wholly stored in the memory 704. The processor 702 executes the program code corresponding to each unit stored in the memory 704 to execute the aforementioned capacitive voltage transformer state monitoring method.

[0209] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-described capacitive voltage transformer state monitoring method.

[0210] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0211] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0212] When the computer program product is executed by a computer, the computer performs any of the aforementioned capacitive voltage transformer state monitoring methods. The computer program product can be a software installation package; when any of the aforementioned capacitive voltage transformer state monitoring methods is required, the computer program product can be downloaded and executed on the computer.

[0213] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0214] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method for monitoring the condition of a capacitive voltage transformer, characterized in that, The method includes: Real-time acquisition of operating status data for each capacitive voltage transformer, including multiple sub-operating status data; The collected sub-operating state data of the capacitive voltage transformer are compared with their respective sub-reference state data to obtain the first comparison result; If the first comparison result indicates that the value corresponding to the sub-operational status data is greater than the threshold corresponding to the sub-operational status data, then it is determined that the capacitive voltage transformer has a fault risk. If the first comparison result indicates that the value corresponding to the sub-operational state data is less than or equal to the threshold corresponding to the sub-operational state data, then the fault characteristic value of the capacitive voltage transformer is determined through multiple sub-operational state data; wherein, the fault characteristic value is calculated in the following manner: The expression for calculating the first sub-eigenvalue is: in, Represents the first sub-eigenvalue. Indicates time The value of the dielectric loss angle of the capacitor voltage divider. Indicates time The threshold value of the dielectric loss angle of the capacitor voltage divider. Indicates the first time, Indicates the first time; The expression for calculating the second sub-eigenvalue is: in, Indicates the second sub-eigenvalue. Indicates time The value of the secondary voltage. Indicates time The threshold of the secondary side voltage; in, Represents the third sub-eigenvalue. Indicates time The capacitor divider The temperature value of the part. Indicates time The capacitor divider The temperature threshold of the part, Indicates the number of components included in a capacitor voltage divider; The expression for calculating the fourth sub-eigenvalue is: in, Represents the fourth sub-eigenvalue. Indicates time The electromagnetic unit The temperature value of the part. Indicates time The electromagnetic unit The temperature threshold of the part, Indicates the number of parts contained in an electromagnetic unit; The expression for calculating the fifth sub-eigenvalue is: in, Represents the fifth sub-eigenvalue. Indicates time The mutual inductor The numerical value of the vibration frequency of the part. Indicates time The mutual inductor The threshold of the vibration frequency of a part. Indicates the number of components contained in the current transformer; The expression for calculating the fault characteristic value is: in, Indicates fault characteristic values, This is represented as the first weighting coefficient. This is represented as the second weighting coefficient. Represented as the third weighting coefficient, This is represented as the fourth weighting coefficient. This is represented as the fifth weighting coefficient; The system determines whether the fault characteristic value is greater than a fault threshold, and obtains a judgment result. The fault threshold is dynamically adjusted based on the equipment health baseline value, the coefficient of variation of the dynamic reference value of the operating status data, the operating condition complexity coefficient, and the equipment health index. The calculation expression for the fault threshold is: in, Indicates time The fault threshold, Indicates the baseline health value of the equipment. The first coefficient represents the fault threshold. The second coefficient represents the fault threshold. The third coefficient represents the fault threshold. express The average value, Indicates the first The coefficient of variation of dynamic reference values ​​for each running status data point Indicates time The working condition complexity coefficient, Indicates time The equipment health index This represents the maximum value indicating the device's health status. The calculation expression is: in, Indicates the first The coefficient of variation of dynamic reference values ​​for each running status data point Indicates the number of times in the past hour The standard deviation of the dynamic reference values ​​of the operating status data Indicates the number of times in the past hour The mean of dynamic reference values ​​for each running status data; The calculation expression is: in, Indicates time The working condition complexity coefficient, The first coefficient representing the complexity of the operating condition. The second coefficient representing the complexity of the operating conditions. The third coefficient representing the complexity of the operating conditions. Indicates time Real-time grid load, Indicates the rated grid load. Indicates time Real-time grid voltage, Indicates the rated mains voltage. Indicates time Real-time altitude, A reference value representing altitude; If the judgment result indicates that the fault characteristic value is greater than the fault threshold, then it is determined that the capacitive voltage transformer has a fault risk. If the judgment result indicates that the fault characteristic value is less than or equal to the fault threshold, then it is determined that the capacitive voltage transformer has no fault risk.

2. The method for monitoring the condition of a capacitive voltage transformer according to claim 1, characterized in that, The sub-operational status data includes: dielectric loss angle of the capacitor voltage divider, secondary side voltage, temperature of various parts of the capacitor voltage divider, temperature of various parts of the electromagnetic unit, and vibration frequency of various parts of the current transformer.

3. The method for monitoring the condition of a capacitive voltage transformer according to claim 1, characterized in that, After determining that the capacitive voltage transformer has a risk of failure, the method further includes: Obtain the test priority value for each capacitive voltage transformer; Take a picture of the capacitive voltage transformer with the highest priority value to be tested to obtain a surface image; The abnormal location of the capacitive voltage transformer is obtained by analyzing the surface image.

4. The method for monitoring the condition of a capacitive voltage transformer according to claim 3, characterized in that, The process of obtaining the test priority value for each capacitive voltage transformer includes: Obtain the time interval from the moment when each capacitive voltage transformer was determined to have a fault risk to the current moment; Based on the fault characteristic values ​​of each capacitive voltage transformer and the time interval from the moment when each capacitive voltage transformer was determined to have a fault risk to the current moment, the test priority value of each capacitive voltage transformer is determined.

5. The method for monitoring the condition of a capacitive voltage transformer according to claim 3, characterized in that, The analysis of the surface image to identify abnormal locations in the capacitive voltage transformer includes: The surface image is segmented to obtain partial images of each part of the capacitive voltage transformer; The images of each part are compared with their respective reference images to obtain the second comparison result. If the second comparison result indicates that the similarity between the image of the target location and the reference image is less than the similarity threshold, then the abnormal location of the capacitive voltage transformer is determined to be the target location.

6. A condition monitoring device for a capacitive voltage transformer, characterized in that, The device includes: The acquisition module is used to acquire the operating status data of each capacitive voltage transformer in real time, and the operating status data includes multiple sub-operating status data. The comparison module is used to compare the collected sub-operating state data of the capacitive voltage transformer with their respective sub-reference state data to obtain the first comparison result. The determination module is configured to: if the first comparison result indicates that the value corresponding to the sub-operational status data is greater than the threshold corresponding to the sub-operational status data, then determine that the capacitive voltage transformer has a fault risk; if the first comparison result indicates that the value corresponding to the sub-operational status data is less than or equal to the threshold corresponding to the sub-operational status data, then determine the fault characteristic value of the capacitive voltage transformer through multiple sub-operational status data; determine whether the fault characteristic value is greater than the fault threshold to obtain a determination result, wherein the fault threshold is dynamically adjusted based on the equipment health baseline value, the coefficient of variation of the dynamic reference value of the operating status data, the operating condition complexity coefficient, and the equipment health index; if the determination result indicates that the fault characteristic value is greater than the fault threshold, then determine that the capacitive voltage transformer has a fault risk; if the determination result indicates that the fault characteristic value is less than or equal to the fault threshold, then determine that the capacitive voltage transformer does not have a fault risk. The fault characteristic values ​​are calculated in the following way: The expression for calculating the first sub-eigenvalue is: in, Represents the first sub-eigenvalue. Indicates time The value of the dielectric loss angle of the capacitor voltage divider. Indicates time The threshold value of the dielectric loss angle of the capacitor voltage divider. Indicates the first time, Indicates the first time; The expression for calculating the second sub-eigenvalue is: in, Indicates the second sub-eigenvalue. Indicates time The value of the secondary voltage. Indicates time The threshold of the secondary side voltage; in, Represents the third sub-eigenvalue. Indicates time The capacitor divider The temperature value of the part. Indicates time The capacitor divider The temperature threshold of the part, Indicates the number of components included in a capacitor voltage divider; The expression for calculating the fourth sub-eigenvalue is: in, Represents the fourth sub-eigenvalue. Indicates time The electromagnetic unit The temperature value of the part. Indicates time The electromagnetic unit The temperature threshold of the part, Indicates the number of parts contained in an electromagnetic unit; The expression for calculating the fifth sub-eigenvalue is: in, Represents the fifth sub-eigenvalue. Indicates time The mutual inductor The numerical value of the vibration frequency of the part. Indicates time The mutual inductor The threshold of the vibration frequency of a part. Indicates the number of components contained in the current transformer; The expression for calculating the fault characteristic value is: in, Indicates fault characteristic values, This is represented as the first weighting coefficient. This is represented as the second weighting coefficient. Represented as the third weighting coefficient, This is represented as the fourth weighting coefficient. This is represented as the fifth weighting coefficient; The formula for calculating the fault threshold is as follows: in, Indicates time The fault threshold, Indicates the baseline health value of the equipment. The first coefficient represents the fault threshold. The second coefficient represents the fault threshold. The third coefficient represents the fault threshold. express The average value, Indicates the first The coefficient of variation of dynamic reference values ​​for each running status data point Indicates time The working condition complexity coefficient, Indicates time The equipment health index This represents the maximum value indicating the device's health status. The calculation expression is: in, Indicates the first The coefficient of variation of dynamic reference values ​​for each running status data point Indicates the number of times in the past hour The standard deviation of the dynamic reference values ​​of the operating status data Indicates the number of times in the past hour The mean of dynamic reference values ​​for each running status data; The calculation expression is: in, Indicates time The working condition complexity coefficient, The first coefficient representing the complexity of the operating condition. The second coefficient representing the complexity of the operating conditions. The third coefficient representing the complexity of the operating conditions. Indicates time Real-time grid load, Indicates the rated grid load. Indicates time Real-time grid voltage, Indicates the rated mains voltage. Indicates time Real-time altitude, A baseline value representing altitude.

7. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, The computer program product includes one or more computer instructions, which, when executed by a computer, perform the method as described in any one of claims 1 to 5.

Images