Insulator state evaluation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of power transmission lines, and provides an insulator state evaluation method and device, electronic equipment and a storage medium. Comprising the steps of obtaining insulator parameter data, leakage current data and environment data of an insulator string in a power transmission line; inputting the insulator parameter data, the leakage current data and the environment data into an evaluation model obtained by pre-training, and outputting an evaluation result; wherein the evaluation model is obtained by training based on a historical detection result, and the historical detection result is obtained by sequentially carrying out first zero value detection, second zero value detection and pollution detection on the insulator. Redundant operation of manual step-by-step diagnosis in a traditional method is eliminated, the automation degree of state evaluation is remarkably improved, real-time accurate monitoring of a large-scale power transmission line is achieved, and real-time decision support is provided for operation and maintenance of a power grid.

Description

Technical Field

[0001] This application relates to the field of power transmission line technology, specifically to an insulator condition assessment method, device, electronic equipment, and storage medium. Background Technology

[0002] Transmission line insulators are exposed to complex natural environments for extended periods, posing a significant challenge to their stability as a critical protective barrier for the power grid. In recent years, the problem of zero-value insulation performance caused by the coupling of surface contamination and humid environments has become increasingly prominent: contamination forms a conductive layer under humid conditions, leading to abnormally increased leakage current accompanied by partial discharge and temperature rise effects, accelerating the aging of silicone rubber materials and corrosion of the galvanized steel base, ultimately causing zero-value insulator failure. Statistics show that zero-value problems caused by contamination account for a high proportion of line tripping accidents caused by insulator faults in the power grid, becoming a major hidden danger threatening the safe operation of the power system.

[0003] To address the zero-value problem, insulator condition monitoring is necessary, but existing insulator condition monitoring technologies have significant limitations. Traditional manual inspection methods suffer from inherent drawbacks such as large blind spots (difficult to cover complex terrains like mountains and rivers) and poor timeliness (cycles can last for months). While conventional live-line testing technologies can achieve some close-range diagnosis, they are limited by high equipment costs (such as the need for dedicated testing vehicles) and the risks of working at heights (requiring personnel to climb towers), making it difficult to meet the real-time monitoring needs of large-scale transmission lines. Neither of these methods can effectively achieve early detection of insulator contamination and zero-value failure.

[0004] Therefore, how to achieve real-time and accurate monitoring of large-scale power transmission lines is a technical challenge that needs to be solved. Summary of the Invention

[0005] In view of this, embodiments of this application provide an insulator condition assessment method, apparatus, electronic device, and storage medium, which can realize real-time and accurate monitoring of large-scale transmission lines.

[0006] The first aspect of this application provides an insulator condition assessment method, including: Acquire insulator parameter data, leakage current data, and environmental data of insulator strings in transmission lines; The insulator parameter data, leakage current data, and environmental data are input into the pre-trained evaluation model, and the evaluation results are output. The evaluation model is trained based on historical detection results, which are obtained by performing a first zero-value detection, a second zero-value detection, and a pollution detection on the insulator in sequence.

[0007] In one embodiment, it also includes: The first zero-value test was performed on each insulator to preliminarily determine the normal insulators and the zero-value insulators; A second zero-value test is performed on the preliminarily determined zero-value insulators to identify the normal insulators and the zero-value insulators. The zero-value insulators determined by the second zero-value detection are subjected to pollution detection to identify insulators with zero value and pollution, as well as insulators with zero value and no pollution. The historical test results include normal, zero value and dirty, and zero value and no dirt. The normal insulators in the historical test results include the normal insulators determined by the first zero value test and the second zero value test.

[0008] In one embodiment, the insulator parameter data of the insulator string includes the insulator type and number of discs, and the leakage current data includes a three-dimensional feature vector of the leakage current. The environmental data includes ambient temperature and humidity; in, The value is the effective value of the leakage current, and THD is the total harmonic distortion. The pulse frequency is the number of pulses per unit time.

[0009] In one embodiment, it also includes: If the total harmonic distortion (THD) exceeds the a× reference value multiple times consecutively, and the pulse frequency per unit time exceeds the 3σ range of historical data, and the phase offset angle of the effective value of leakage current is abnormal, then it is preliminarily determined to be a zero-value insulator. Otherwise, it is preliminarily determined to be a normal insulator; Where a is a preset value greater than 1, and σ is the standard deviation of historical pulse frequency data.

[0010] In one embodiment, it also includes: The first zero-value detection is performed using leakage current monitoring, the second zero-value detection is performed using electric field detection, and the pollution detection is performed using microwave detection.

[0011] In one embodiment, it also includes: Historical sample data of insulator strings in transmission lines are obtained; wherein the historical sample data includes historical insulator parameter data, leakage current data, environmental data and corresponding historical test results; The historical detection results are used as classification labels, and the constructed model is trained using the historical insulator parameter data, leakage current data, and environmental data to obtain the evaluation model. The evaluation results output by the evaluation model include normal, zero value with dirt, and zero value with no dirt.

[0012] A second aspect of this application provides an insulator condition assessment device, comprising: The data acquisition module is used to acquire insulator parameter data, leakage current data, and environmental data of insulator strings in transmission lines; The model analysis module is used to input the insulator parameter data, leakage current data and environmental data into the pre-trained evaluation model and output the evaluation results. The evaluation model is trained based on historical detection results, which are obtained by performing a first zero-value detection, a second zero-value detection, and a pollution detection on the insulator in sequence.

[0013] In one embodiment, a historical detection result acquisition module is further included, for: The first zero-value test was performed on each insulator to preliminarily determine the normal insulators and the zero-value insulators; A second zero-value test is performed on the preliminarily determined zero-value insulators to identify the normal insulators and the zero-value insulators. The zero-value insulators determined by the second zero-value detection are subjected to pollution detection to identify insulators with zero value and pollution, as well as insulators with zero value and no pollution. The historical test results include normal, zero value and dirty, and zero value and no dirt. The normal insulators in the historical test results include the normal insulators determined by the first zero value test and the second zero value test.

[0014] In one embodiment, a first zero-value detection module is further included, for: If the total harmonic distortion (THD) exceeds the a× reference value multiple times consecutively, and the pulse frequency per unit time exceeds the 3σ range of historical data, and the phase offset angle of the effective value of leakage current is abnormal, then it is preliminarily determined to be a zero-value insulator. Otherwise, it is preliminarily determined to be a normal insulator; Where a is a preset value greater than 1, and σ is the standard deviation of historical pulse frequency data.

[0015] In one embodiment, a model training module is also included, for: Historical sample data of insulator strings in transmission lines are obtained; wherein the historical sample data includes historical insulator parameter data, leakage current data, environmental data and corresponding historical test results; The historical detection results are used as classification labels, and the constructed model is trained using the historical insulator parameter data, leakage current data, and environmental data to obtain the evaluation model. The evaluation model outputs evaluation results including normal, zero value with pollution, and zero value with no pollution; the insulator parameter data includes insulator type and number of discs; and the leakage current data includes a three-dimensional feature vector of the leakage current. The environmental data includes ambient temperature and humidity; The value is the effective value of the leakage current, and THD is the total harmonic distortion. The pulse frequency is the number of pulses per unit time.

[0016] A third aspect of this application provides an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the insulator state assessment method provided in the first aspect of this application.

[0017] A fourth aspect of this application provides a computer program product including a computer program that, when run, causes the method described in the first aspect of this application to be performed.

[0018] The insulator condition assessment method provided in the first aspect of this application includes acquiring insulator parameter data, leakage current data, and environmental data of insulator strings in a transmission line; inputting the insulator parameter data, leakage current data, and environmental data into a pre-trained assessment model, and outputting assessment results; wherein the assessment model is trained based on historical detection results, and the historical detection results are obtained by sequentially performing a first zero-value detection, a second zero-value detection, and a pollution detection on the insulator. By sequentially performing the first zero-value detection, the second zero-value detection, and the pollution detection on the insulator, cross-validation of the detection results is achieved, thereby obtaining reliable historical detection results. A reliable assessment model is trained based on these historical detection results, realizing multi-source data fusion analysis. Thus, by uniformly inputting insulator parameters, leakage current, and environmental data into the assessment model, assessment results can be directly output, eliminating redundant operations of manual step-by-step diagnosis in traditional methods, significantly improving the automation level of condition assessment, realizing real-time and accurate monitoring of large-scale transmission lines, and providing real-time decision support for power grid operation and maintenance.

[0019] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic flowchart of an insulator condition assessment method provided in an embodiment of this application; Figure 2 This is a schematic flowchart of an insulator condition assessment method provided in another embodiment of this application; Figure 3 This is a schematic flowchart of an insulator condition assessment method provided in another embodiment of this application; Figure 4 This is a schematic flowchart of an insulator condition assessment method provided in another embodiment of this application; Figure 5 This is a schematic diagram of the insulator condition assessment device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0023] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0024] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0025] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0026] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0027] like Figure 1 As shown, the insulator condition assessment method provided in this application includes the following steps S101 to S102: Step S101: Obtain insulator parameter data, leakage current data, and environmental data of the insulator strings in the transmission line; Step S102: Input the insulator parameter data, leakage current data, and environmental data into the pre-trained evaluation model and output the evaluation results; The evaluation model is trained based on historical test results, which are obtained by performing a first zero-value test, a second zero-value test, and a pollution test on the insulator in sequence.

[0028] In application, the evaluation results output by the evaluation model include normal, zero value with dirt, and zero value with no dirt.

[0029] In the application, after obtaining insulator parameter data, leakage current data, and environmental data in step S101, these data are preprocessed, for example, missing and outlier values ​​are removed. The data are then normalized to obtain the input data for the evaluation model.

[0030] This application's embodiments achieve multi-source data fusion analysis through a pre-trained model. Its technical advantage lies in uniformly inputting insulator parameters, leakage current, and environmental data into the evaluation model, directly outputting classification results, eliminating redundant manual step-by-step diagnostic operations in traditional methods. The model is trained based on historical detection results, which are derived from the cross-validation process of two zero-value detections and pollution detections, ensuring the reliability of the training data. This method significantly improves the automation level of condition assessment, realizing end-to-end processing from data acquisition to result output, providing real-time decision support for power grid operation and maintenance.

[0031] In one embodiment, such as Figure 2 As shown, it also includes: Step S201: Perform the first zero-value test on each insulator to preliminarily determine the normal insulators and the zero-value insulators; Step S202: Perform a second zero-value test on the preliminarily determined zero-value insulators to identify the normal insulators and the zero-value insulators. Step S203: Perform a pollution test on the zero-value insulators determined by the second zero-value test to determine the insulators with zero value and pollution, and the insulators with zero value and no pollution. Among them, the historical test results include normal, zero value and dirty, and zero value and no dirt. The normal insulators in the historical test results include the normal insulators determined by the first zero value test and the second zero value test.

[0032] In application, the first zero-value test is used to initially identify normal insulators and zero-value insulators. However, a single zero-value test may result in false positives. To improve accuracy, the zero-value insulators identified in the first test are retested, thus eliminating some normal insulators that were falsely identified as zero-value insulators. Finally, a pollution test is performed on the zero-value insulators identified after the retest to identify whether the zero-value insulator is contaminated. Integrating the three tests yields historical test results for three scenarios: normal, zero-value with contamination, and zero-value without contamination. By combining these historical test results with corresponding insulator parameter data, leakage current data, and environmental data, the correspondence between the collected data and the test results can be established, thereby enabling the training of the evaluation model.

[0033] This application establishes a tiered detection mechanism. The initial zero-value detection performs preliminary screening, a second zero-value detection verifies the initial screening results, and pollution detection further subdivides the attributes of confirmed zero-value insulators. Historical detection results integrate normal insulator data from the two tests with pollution verification conclusions, forming a ternary labeling system: normal, zero-value with pollution, and zero-value without pollution. Multi-level verification eliminates the risk of misjudgment from a single detection, ensuring that the model training data simultaneously includes both real normal samples and accurately classified abnormal samples, guaranteeing the generalization ability and reliability of the evaluation model from the data source.

[0034] In one embodiment, the insulator parameter data of the insulator string includes the insulator type and number of discs, and the leakage current data includes a three-dimensional feature vector of the leakage current. Environmental data includes ambient temperature and humidity; in, The value is the effective value of the leakage current, and THD is the total harmonic distortion. The pulse frequency is the number of pulses per unit time.

[0035] In applications, the collected leakage current data is analyzed using an adaptive wavelet packet decomposition algorithm to separate the power frequency component, harmonic component, and random pulse component of the leakage current, thereby constructing a three-dimensional feature vector. ; in, The term THD is used to represent power frequency components, while THD is used to represent harmonic components. Used to represent random pulse components.

[0036] In the model input data of this application embodiment, the insulator type and number of discs characterize structural properties, ambient temperature and humidity reflect external operating conditions, and the three-dimensional feature vector of leakage current includes dynamic electrical characteristics such as effective value harmonic distortion rate and pulse frequency. This multi-dimensional data combination simultaneously covers static attributes, dynamic behavior, and environmental interference factors, enabling the model to capture composite characteristic patterns in the insulator degradation process. The construction of the index system takes into account both steady-state parameters and transient characteristics, providing a complete data foundation for the model to identify gradual failure caused by pollution and abrupt failure caused by cracks.

[0037] In one embodiment, it also includes: If the total harmonic distortion (THD) exceeds the a× reference value multiple times consecutively, and the pulse frequency per unit time exceeds the 3σ range of historical data, and the phase offset angle of the effective value of leakage current is abnormal, then it is preliminarily determined to be a zero-value insulator. Otherwise, it is preliminarily determined to be a normal insulator; Where a is a preset value greater than 1, and σ is the standard deviation of historical pulse frequency data.

[0038] In application, if the total harmonic distortion (THD) exceeds 150% of the reference value for three consecutive times, the pulse frequency per unit time exceeds the 3σ range of historical data, and the phase offset angle of the effective value of leakage current is abnormal, it is preliminarily determined to be a zero-value insulator.

[0039] This application's embodiments establish a multi-condition joint criterion for zero-value insulators. Continuously exceeding the harmonic distortion rate limit reflects nonlinear distortion of the insulating medium; pulse frequency exceeding the historical statistical range indicates abnormally active discharge activity; and phase shift characterizes the transition from capacitive to resistive properties. The simultaneous fulfillment of these three conditions significantly improves the specificity of the judgment and avoids false triggering caused by fluctuations in a single indicator. The pulse frequency employs an adaptive threshold based on the standard deviation of historical data, allowing the judgment criterion to be dynamically adjusted according to the equipment's operating status. This composite criterion mechanism effectively suppresses environmental noise interference while ensuring detection sensitivity.

[0040] In one embodiment, it also includes: The first zero-value detection is performed using leakage current monitoring, the second zero-value detection is performed using electric field detection, and the pollution detection is performed using microwave detection.

[0041] In applications, leakage current monitoring is used to monitor insulator strings in transmission lines online, acquiring weak leakage current signals from the surface or interior of the insulators in real time. Specifically, high-precision Rogowski coil sensors can be used, installed at key nodes of the insulator strings, to acquire leakage current signals in the 0.1Hz~10MHz frequency band in real time, while simultaneously recording ambient temperature and humidity data, salt density, and ash density data.

[0042] In application, the electric field distribution method uses an electric field sensor mounted on a drone to detect the insulator string under test. The electric field distribution curve of the insulator string is viewed on a display terminal. If the electric field distribution curve of the insulator string is undistorted, there are no zero-value insulators in the string; if the curve is distorted, zero-value insulators are present, and the location of the distortion point is the location of the zero-value insulator. The gimbal under the drone features a convenient assembly and disassembly design. After the drone performs a preliminary detection of the insulator string using the electric field distribution method, the zero-value insulators are marked, and the drone returns to the takeoff point to replace the battery. The electric field distribution method can be used to re-test zero-value insulators found by the leakage current monitoring method, improving the accuracy of zero-value insulator detection.

[0043] The electric field detection method is used to re-test zero-value insulators detected by the leakage current monitoring method. This method is advantageous because the electric field distribution method directly reflects the insulator's state and is less susceptible to environmental influences. Since the electric field strength curve along the insulator's axis is smooth for a normal insulator, when the insulator approaches zero, it affects the electric field distribution around the insulator, altering its electric field strength and making the curve no longer smooth. The location of the zero-value insulator can be determined by identifying the areas of electric field distortion. A drone equipped with an electric field sensor is used to perform live zero-value detection on the insulator string. The drone flies around the insulator string and, once at the test distance, performs zero-value detection along the high-voltage side to the low-voltage side. After detection, the electric field distribution curve displayed on the terminal shows the presence of zero-value insulators in the string. This method avoids the problems of time-consuming, inefficient, and high-risk manual tower climbing inspections, achieving accurate and efficient insulator detection.

[0044] In applications, microwave detection methods analyze the interaction between electromagnetic waves and contamination layers to detect changes in the dielectric properties of insulator surfaces. The microwave detection method utilizes a UAV platform equipped with a dual-band millimeter-wave radar, integrating a time-domain reflectometry (TDR) module and a high-sensitivity signal acquisition unit. The UAV platform is equipped with a motorized gimbal for 360° rotation scanning to ensure the microwave beam covers the insulator surface. The microwave detection model features an adaptive signal processing system, including a noise suppression module, a timing feature extraction algorithm, and a nodal characteristic inversion model. The microwave detection method measures the propagation delay of microwaves through the contamination layer using the time-domain reflectometry (TDR) principle to invert dielectric property parameters. ; Where σ is the pollution conductivity, d is the insulator diameter, and c is the speed of light in vacuum. The microwave propagation time delay difference is ω, where ω is the angular frequency. is the vacuum permittivity.

[0045] Microwave detection, combined with a pre-calibrated database of pollution dielectric properties, rapidly assesses the salt density (ESDD) and ash density (NSDD) levels, completing non-contact pollution screening to determine whether the insulator is contaminated. When pollution is present, the insulator has a zero value and is in a contaminated state; when pollution is absent, the insulator has a zero value and is not in a contaminated state.

[0046] Microwave detection is used to capture and identify the pollution level in areas where zero-value insulators are located. Microwave technology can detect changes in the dielectric properties of the insulator surface by analyzing the interaction between electromagnetic waves and the pollution layer. When microwaves irradiate the insulator surface, the dielectric constant of the pollution layer will be significantly higher than that of the clean surface, causing shifts in the amplitude, phase, or resonant frequency of reflected and transmitted waves. By analyzing these parameter changes, the conductive and non-conductive components of the pollution can be deduced, enabling non-contact and rapid assessment of the pollution status of the insulator surface. A drone equipped with a microwave transmitter and receiver hovers or slowly approaches the insulator along a preset flight path, adjusting the antenna angle to cover the surface with a microwave beam (usually in the 10-30 GHz band). Continuous wave or pulsed microwave signals are emitted, and reflected or transmitted waves are received simultaneously. The amplitude, phase, or resonant frequency shift of the reflected signal is analyzed in real time by airborne or ground-based equipment. Combined with a pre-calibrated pollution dielectric property database, the salt density (ESDD) and ash density (NSDD) levels can be quickly assessed, completing non-contact pollution screening.

[0047] This application's embodiments utilize leakage current monitoring as a primary screening method, offering advantages in low-cost continuous monitoring. Electric field detection precisely locates zero-value insulators through electric field distortion, while microwave detection achieves non-contact pollution quantification based on dielectric property inversion. These three methods complement each other across different detection dimensions: leakage current provides temporal trends, electric field method enables spatial positioning, and microwave method completes attribute identification. This tiered combination of technologies fully leverages the advantages of each method, minimizing overall implementation costs while ensuring detection accuracy.

[0048] In one embodiment, such as Figure 3 As shown, it also includes: Step S301: Obtain historical sample data of insulator strings in the transmission line; wherein the historical sample data includes historical insulator parameter data, leakage current data, environmental data and corresponding historical test results.

[0049] In application, historical sample data includes historical test results and corresponding relevant parameters. Historical test results are categorized into three types: normal, zero value with contamination, and zero value without contamination. Relevant parameters include insulator parameter data, leakage current data, and environmental data for the corresponding insulator.

[0050] Step S302: Use historical test results as classification labels, and train the constructed model using historical insulator parameter data, leakage current data, and environmental data to obtain the evaluation model; The evaluation results output by the evaluation model include normal, zero value with dirt, and zero value with no dirt.

[0051] In the application, historical sample data is normalized and used as the original sample set for the random forest model. The random forest model randomly selects multiple training samples with replacement from the original sample set, with each selection representing 100% of the original samples, but allowing approximately 36.8% of the samples to remain unselected for subsequent generalization error estimation. A classification decision tree is constructed for each training sample in the random forest model, using Gini impurity as the splitting criterion, while limiting the maximum tree depth to prevent overfitting. Historical detection results—normal, zero value with contamination, and zero value without contamination—are used as the model's classification labels. To prevent false alarms, a classification probability threshold (zero value class probability > 0.9) is set to filter low-confidence predictions and prevent false alarms from the monitoring system. For example, when the classification probability is 0.7, which is less than the classification probability threshold of 0.9, the data is labeled and output for manual negative testing.

[0052] In addition, incremental feature extraction and model lightweighting are used when evaluating model deployment to ensure millisecond-level response.

[0053] like Figure 4As shown, historical sample data were obtained after a first zero-value detection using leakage current monitoring, a second zero-value detection using electric field detection, and pollution detection using microwave detection. Specifically, leakage current monitoring acquires leakage current data, which is then converted into a three-dimensional feature vector. The system assesses the total harmonic distortion rate, pulse frequency per unit time, and phase offset angle of the effective value of leakage current to initially identify zero-value insulators and normal insulators in the first zero-value detection. In the second zero-value detection stage, the initially identified zero-value insulators are retested using an electric field detection method. Data is transmitted to a display terminal via a drone equipped with power plant sensors. Distortion of the electric field distribution curve on the display terminal is used to determine if an insulator is zero-value. If distortion is present, it is identified as a zero-value insulator; otherwise, it is identified as a normal insulator. The normal insulators identified in both the first and second zero-value detections are considered together as normal insulators in the overall detection results. Microwave detection is then applied to the zero-value insulators identified in the second zero-value detection to determine if each insulator is contaminated. The final historical detection results—normal, zero-value with contamination, and zero-value without contamination—are used as classification labels for training a machine learning model.

[0054] This application constructs a data-driven model training paradigm. Historical sample data includes multi-dimensional feature parameters of insulators and their corresponding verification labels, which are derived from the hierarchical detection conclusions of the claims. The training process transforms physical detection results into machine learning-recognizable classification labels, enabling the model to learn the mapping relationship from raw data to state classification. This training mechanism based on field verification data allows the model to inherently inherit the technical advantages of multi-level detection, ultimately forming a lightweight evaluation model that can replace complex detection processes. This method achieves an order-of-magnitude improvement in evaluation efficiency while preserving detection accuracy.

[0055] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0056] This application also provides an insulator condition assessment device for performing the steps described in the above-described insulator condition assessment method embodiments. The insulator condition assessment device can be a virtual device within an electronic device, run by the electronic device's processor, or it can be the electronic device itself.

[0057] like Figure 5 As shown, the insulator condition assessment device 100 provided in this application embodiment includes: The data acquisition module 101 is used to acquire insulator parameter data, leakage current data and environmental data of insulator strings in transmission lines; Model analysis module 102 is used to input insulator parameter data, leakage current data and environmental data into the pre-trained evaluation model and output the evaluation results; The evaluation model is trained based on historical test results, which are obtained by performing a first zero-value test, a second zero-value test, and a pollution test on the insulator in sequence.

[0058] In one embodiment, a historical detection result acquisition module is further included, for: The first zero-value test was performed on each insulator to preliminarily determine the normal insulators and the zero-value insulators; A second zero-value test was conducted on the preliminarily identified zero-value insulators to determine which insulators were normal and which were zero-value insulators. The zero-value insulators determined by the second zero-value test are subjected to pollution test to identify insulators with zero value and pollution, as well as insulators with zero value and no pollution. Among them, the historical test results include normal, zero value and dirty, and zero value and no dirt. The normal insulators in the historical test results include the normal insulators determined by the first zero value test and the second zero value test.

[0059] In one embodiment, a first zero-value detection module is further included, for: If the total harmonic distortion (THD) exceeds the a× reference value multiple times consecutively, and the pulse frequency per unit time exceeds the 3σ range of historical data, and the phase offset angle of the effective value of leakage current is abnormal, then it is preliminarily determined to be a zero-value insulator. Otherwise, it is preliminarily determined to be a normal insulator; Where a is a preset value greater than 1, and σ is the standard deviation of historical pulse frequency data.

[0060] In one embodiment, a model training module is also included, for: Obtain historical sample data of insulator strings in transmission lines; the historical sample data includes historical insulator parameter data, leakage current data, environmental data, and corresponding historical test results; Historical test results are used as classification labels. The model is trained using historical insulator parameter data, leakage current data, and environmental data to obtain the evaluation model. The evaluation model outputs evaluation results including normal, zero value with pollution, and zero value with no pollution; insulator parameter data includes insulator type and number of discs; leakage current data includes a three-dimensional feature vector of the leakage current. Environmental data includes ambient temperature and humidity; The value is the effective value of the leakage current, and THD is the total harmonic distortion. The pulse frequency is the number of pulses per unit time.

[0061] In applications, the modules in the insulator condition assessment device can be software program modules, or they can be implemented through different logic circuits integrated in a processor, or they can be implemented through multiple distributed processors.

[0062] like Figure 6 As shown, this application embodiment also provides an electronic device 200, including: at least one processor 201 ( Figure 6 The diagram shows only one processor, memory 202, and computer program 203 stored in memory 202 and executable on at least one processor 201. When processor 201 executes computer program 203, it implements the steps in the various method embodiments described above.

[0063] In applications, electronic devices may include, but are not limited to, processors and memory. Those skilled in the art will understand that... Figure 6 This is merely an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than shown, or a combination of certain components, or different components.

[0064] In applications, the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0065] In applications, memory can be an internal storage unit of an electronic device in some embodiments, such as a hard drive or RAM. In other embodiments, memory can be an external storage device of the electronic device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, memory can include both internal and external storage units of the electronic device. Memory is used to store operating systems, applications, bootloaders, data, and other programs, such as program code for computer programs. Memory can also be used to temporarily store data that has been output or will be output.

[0066] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0067] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0068] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps described in the various method embodiments above.

[0069] This application provides a computer program product, including a computer program, which, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0070] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0071] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0072] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0073] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0074] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0075] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method of insulator condition assessment, characterized by, The method comprises the following steps: obtaining insulator parameter data, leakage current data and environmental data of an insulator string in a power transmission line; inputting the insulator parameter data, leakage current data and environmental data into a pre-trained evaluation model to output an evaluation result; wherein the evaluation model is trained based on historical detection results, and the historical detection results are obtained by sequentially performing first zero value detection, second zero value detection and contamination detection on the insulator.

2. The insulator condition assessment method according to claim 1, wherein The method further comprises the following steps: performing first zero value detection on each insulator to preliminarily determine normal insulators and zero value insulators; performing second zero value detection on the preliminarily determined zero value insulators to determine normal insulators and zero value insulators among them; performing contamination detection on the zero value insulators determined by the second zero value detection to determine insulators with zero value and contamination, and insulators with zero value and no contamination; wherein the historical detection results include normal, zero value and contamination, and zero value and no contamination, and the normal insulators in the historical detection results include normal insulators determined by the first zero value detection and the second zero value detection.

3. The insulator condition assessment method according to claim 2, wherein The insulator parameter data of the insulator string includes insulator type and piece number, and the leakage current data includes three-dimensional feature vector of leakage current , and the environment data includes environment temperature and humidity wherein, Ileak is the leakage current effective value, THD is the total harmonic distortion, f is the pulse frequency per unit time.

4. The insulator condition assessment method according to claim 3, wherein The method further comprises the following steps: if the total harmonic distortion rate THD exceeds a×reference value continuously for multiple times, the unit time pulse frequency exceeds the 3σ range of historical data, and the phase shift angle of the leakage current effective value is abnormal, then the insulator is preliminarily determined as a zero value insulator; otherwise, the insulator is preliminarily determined as a normal insulator; wherein a is a preset value greater than 1, and σ is the standard deviation of historical pulse frequency data.

5. The insulator condition assessment method of claim 1, wherein, The method further comprises the following steps: performing the first zero value detection by a leakage current monitoring method, performing the second zero value detection by an electric field detection method, and performing the contamination detection by a microwave detection method.

6. The insulator condition assessment method of claim 1, wherein, The method further comprises the following steps: obtaining historical sample data of an insulator string in a power transmission line; wherein the historical sample data includes historical insulator parameter data, leakage current data, environmental data and corresponding historical detection results; using the historical insulator parameter data, leakage current data and environmental data to train a constructed model to obtain the evaluation model, with the historical detection results as classification labels; wherein the evaluation result output by the evaluation model includes normal, zero value and contamination, and zero value and no contamination.

7. An insulator condition evaluation device characterized by comprising: The method comprises the following steps: a data acquisition module for obtaining insulator parameter data, leakage current data and environmental data of an insulator string in a power transmission line; a model analysis module for inputting the insulator parameter data, leakage current data and environmental data into a pre-trained evaluation model to output an evaluation result; wherein the evaluation model is trained based on historical detection results, and the historical detection results are obtained by sequentially performing first zero value detection, second zero value detection and contamination detection on the insulator.

8. The insulator condition assessment device of claim 7, wherein, The method further comprises a historical detection result acquisition module for: performing first zero value detection on each insulator to preliminarily determine normal insulators and zero value insulators; performing second zero value detection on the preliminarily determined zero value insulators to determine normal insulators and zero value insulators among them; performing contamination detection on the zero value insulators determined by the second zero value detection to determine insulators with zero value and contamination, and insulators with zero value and no contamination; The historical detection result includes normal, zero value and presence of contamination, and zero value and absence of contamination, and the normal insulator in the historical detection result includes normal insulators determined by the first zero value detection and the second zero value detection.

9. The insulator condition assessment device of claim 7, wherein, The first zero value detection module is further included and configured to: If the total harmonic distortion rate THD exceeds a×reference value for a plurality of times in succession, the pulse frequency per unit time exceeds a 3σ range of historical data, and the phase shift angle of the leakage current effective value is abnormal, the insulator is preliminarily determined as a zero value insulator; Otherwise, the insulator is preliminarily determined as a normal insulator; Wherein, a is a preset value greater than 1, and σ is a standard deviation of historical pulse frequency data.

10. The insulator condition assessment device of claim 7, wherein, The model training module is further included and configured to: Obtain historical sample data of insulator strings in a power transmission line; wherein the historical sample data includes historical insulator parameter data, leakage current data, environmental data and corresponding historical detection results; Use the historical insulator parameter data, leakage current data and environmental data as classification labels to train a constructed model to obtain the evaluation model; The evaluation result output by the evaluation model includes normal, zero value and existence of contamination, and zero value and non-existence of contamination; the insulator parameter data includes an insulator model and a piece number; and the leakage current data includes a three-dimensional feature vector of the leakage current The environmental data includes an environmental temperature and humidity. is a leakage current effective value, THD is a total harmonic distortion rate, is a pulse frequency per unit time.

11. An electronic device, comprising: The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

12. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images