Pulse type insulator leakage fault diagnosis system and method

Abstract

The invention relates to the technical field of electric leakage detection, in particular to a pulse type insulator electric leakage fault diagnosis system and method, and the method specifically comprises the steps: collecting insulator electric leakage current data and humidity data of an environment where an insulator is located, and constructing an environment humidity influence coefficient according to the change characteristics of the insulator current data caused by humidity change and rainfall; constructing an electric leakage characteristic coefficient according to electric leakage current change characteristics generated when the insulator really has defects; based on the suspected defect insulator mark of the environment humidity influence coefficient and the electric leakage characteristic coefficient, the marked insulator is detected and maintained; the problem that the actual leakage situation of the insulator cannot be judged due to the fact that the environment influence is similar to the leakage current of the leakage fault caused by the defects of the insulator in the traditional insulator leakage fault diagnosis process is solved, and the fault diagnosis accuracy of the insulator is improved.

Description

Technical Field

[0001] This application relates to the field of leakage current detection technology, specifically to a pulse-type insulator leakage current fault diagnosis system and method. Background Technology

[0002] With the development of sensor and communication technologies, a large amount of theoretical research and monitoring equipment has emerged in the field of insulator condition monitoring. Since leakage current reflects the condition of an insulator, leakage current detection systems accurately extract useful characteristic signals by detecting leakage current sensors connected in series with the insulator string. These signals are then transmitted to the insulator monitoring and control center via IoT technology, using communication techniques employed within the IoT framework. Big data and anomaly detection technologies are used to process the data, thereby determining the actual condition of the insulator and enabling corresponding control and decision-making. In actual measurement, existing insulator leakage fault diagnosis methods primarily involve measuring the leakage current data of the insulator and using anomaly detection algorithms to analyze the current data. This determines whether the leakage current is caused by a defect in the insulator. If leakage is found to be caused by a defect in the insulator itself, relevant personnel need to quickly replace or repair the defective insulator.

[0003] However, when the humidity in the environment where the insulator is located is high, water vapor in the air condenses or adsorbs on the surface of the insulator, forming a continuous or discontinuous water film. If there is dirt (salt, dust, industrial pollutants) on the surface of the insulator, the water film will dissolve these electrolytes, forming a conductive electrolyte solution, ultimately creating a continuous conductive path, which can also cause leakage current on the surface of the insulator. This type of insulator leakage is highly affected by environmental changes. After leakage occurs, as the ambient humidity decreases and the insulator surface gradually dries, the leakage will stop. Therefore, compared to leakage caused by defects in the insulator itself, leakage caused by environmental factors has a less significant impact on power equipment. However, because leakage caused by environmental factors or defects in the insulator itself yields similar leakage current measurement results, traditional techniques are difficult to distinguish, ultimately leading to errors in judging the actual leakage situation of the insulator. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide a pulse-type insulator leakage fault diagnosis system and method, the specific technical solution of which is as follows: In a first aspect, embodiments of this application provide a method for diagnosing leakage faults in pulse-type insulators, the method comprising the following steps: Collect insulator current data and ambient humidity data at various times; Based on the degree of fluctuation of insulator current data, the trend of humidity change, and the maximum humidity value in each time period, an environmental humidity influence coefficient for insulators in each time period is constructed. Based on the current fluctuation rate, current distribution range and current fluctuation duration in each time period, leakage current characteristic coefficients of insulators in each time period are constructed. Based on the environmental humidity influence coefficient and the leakage characteristic coefficient, a defect-induced leakage coefficient for insulators in each time period is constructed; based on the defect-induced leakage coefficient, suspected defective insulators are marked, and the marked insulators are inspected and repaired.

[0005] In one embodiment, the process of obtaining the environmental humidity influence coefficient is as follows: The current data in each time period are fitted by a curve fitting algorithm to obtain the degree of disorder of the slope distribution at all sampling times in the fitted curve. The slope of the fitted straight line of the time series of all humidity data in each time period is calculated. Based on the degree of disorder, the slope of the fitted straight line and the maximum value of humidity data in each time period, the environmental humidity influence coefficient of each time period is determined.

[0006] In one embodiment, the disorder of the slope distribution is the standard deviation of the slope at all sampling times in the fitted curve.

[0007] In one embodiment, the environmental humidity influence coefficient is a positive fusion result of the disorder level, the slope of the fitted straight line, and the maximum value of humidity data for each time period.

[0008] In one embodiment, the process of obtaining the leakage current characteristic coefficient is as follows: Clustering algorithms are used to cluster all current data in each time period to obtain the total number of elements in the cluster with the highest mean of elements within the cluster. The maximum inflection point in the current data for each time period is obtained, and the current data in the cluster with the smallest mean of elements within the cluster are combined to calculate the rate of change for each time period. Based on the changing rate value, the difference between the maximum and minimum current values ​​and the total number of elements in the cluster in each time period, leakage current characteristic coefficients are constructed for each time period. The leakage current characteristic coefficients are positively correlated with the changing rate value, the difference between the maximum and minimum values ​​and the total number of elements in the cluster.

[0009] In one embodiment, the process of obtaining the changing speed value is as follows: In the cluster with the smallest mean of elements within the cluster, the current data point with the smallest time interval from the maximum inflection point is obtained, and the ratio of the current difference to the time difference between the maximum inflection point and the current data point is recorded as the rate of change value.

[0010] In one embodiment, the difference between the maximum and minimum values ​​of the current data is the ratio of the maximum value to the minimum value in the current data for each time period.

[0011] In one embodiment, the defect-induced leakage coefficient is a normalized value of the ratio of the leakage characteristic coefficient to the environmental humidity influence coefficient.

[0012] In one embodiment, the method for marking suspected defective insulators is as follows: If the leakage current coefficient caused by the defect of the insulator is greater than or equal to the preset segmentation threshold at any time, the insulator will be marked as a suspected defective insulator.

[0013] Secondly, embodiments of this application also provide a pulse-type insulator leakage fault diagnosis system, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0014] The embodiments of this application have at least the following beneficial effects: This application simultaneously collects insulator leakage current data and humidity data of the insulator's environment. Based on the characteristics of insulator current data changes caused by humidity variations and precipitation, an environmental humidity influence coefficient is constructed to analyze environmental interference caused by the external environment. Simultaneously, a leakage characteristic coefficient is constructed based on the leakage current changes caused by actual insulator defects. Combining these two factors, the application distinguishes whether the insulator's current data changes are due to environmental influences or its own defects, thus determining the cause of the current leakage current data. This solves the problem that in traditional methods of diagnosing insulator leakage faults, the leakage currents caused by environmental influences and insulator defects are often similar, making it impossible to determine the actual leakage situation. By accurately distinguishing the causes of insulator leakage faults, the application improves the efficiency of leakage fault detection and repair. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, 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.

[0016] Figure 1 A flowchart illustrating the steps of a pulse-type insulator leakage fault diagnosis method provided in one embodiment of this application; Figure 2 This is a schematic diagram illustrating the process of obtaining the leakage current characteristic coefficient. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the pulse-type insulator leakage fault diagnosis system and method proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0019] The following description, in conjunction with the accompanying drawings, details the specific scheme of the pulse-type insulator leakage fault diagnosis system and method provided in this application.

[0020] Please see Figure 1 The diagram illustrates a flowchart of a pulse-type insulator leakage fault diagnosis method according to an embodiment of this application. The method includes the following steps: Step S1: Collect insulator current data and ambient humidity data at various times.

[0021] An insulator current detection device is used to collect current data of the insulator under monitoring, acquiring the current data at intervals t. Simultaneously, a humidity sensor is used to acquire humidity data of the environment surrounding the insulator at intervals t. To avoid interference from different data units in subsequent calculations, this application uses a maximum-minimum normalization method to normalize the collected current and humidity data respectively. Furthermore, each interval T is considered a time period for subsequent processing; in this embodiment, t is set to 3 minutes and T to 1 hour. In other embodiments of this application, the implementer can set the values ​​of t and T according to actual conditions.

[0022] Step S2: Based on the degree of fluctuation of insulator current data, humidity change trend and maximum humidity value in each time period, construct the environmental humidity influence coefficient of insulator in each time period.

[0023] Under normal circumstances, when the insulator is functioning properly, the measured current data is extremely low. However, when the insulator suffers from defects such as aging of the insulation material, dampness, cracks, manufacturing defects (e.g., porosity in porcelain insulators), mechanical stress, external damage (e.g., compression, scratches), or poor wiring, its insulation performance deteriorates, leading to leakage faults. In these cases, the collected current data is significantly higher than normal. Furthermore, when the humidity in the insulator's environment increases, the measured current data also shows a significant increase. This can easily lead to misdiagnosis of an insulator fault, thus requiring prior analysis.

[0024] Specifically, under normal circumstances, a tiny, weak current exists on the surface of an insulator, fluctuating within a small range with changes in ambient humidity. When the humidity in the environment where the insulator is located increases, condensation forms on the insulator surface, creating a water film. This film dissolves dissolved salts, acids, and other contaminants on the insulator surface, generating a conductive solution and forming a conductive channel. The originally high surface resistance of the insulator drops sharply as the area of ​​the water film gradually expands. Furthermore, different insulators have different surface structures and states, macroscopically exhibiting a multi-layered, umbrella-shaped disc, and the distribution of contaminants on the insulator surface also varies. Therefore, the expansion of the water film involves multiple processes. Taking a post insulator as an example, it is usually placed vertically, and contaminants are mainly distributed on the upper surface of the umbrella-shaped disc, with relatively fewer contaminants on the lower surface. Therefore, when the water film expands, the upper surface of the disc expands faster, while the lower surface expands relatively slower. This difference in the rate of conductive channel formation leads to a stepwise increase in leakage current. Specifically, in current data, this manifests as a cycle of slow rise followed by a rapid rise, then a slow rise again. In humidity data, this manifests as a gradual increase in humidity, which is relatively high. In cases where the insulator itself has defects, the leakage current is more instantaneous, mainly manifested as a sudden surge in current data, a rapid increase in speed, and a high amplitude of the increased current.

[0025] To characterize the step-like increase in current data, current data collected in a single time period was used as input. A polynomial curve fitting algorithm was employed to fit the curve, calculating the slope of the fitted curve for each current data point. These slope fluctuation sequences were then constructed according to the sampling time order. In the case of a step-like increase in current data, the slope of the current data points changes from a small value (slow increase) to a large value (rapid increase) and then falls back to a small value. Compared to the case where the current changes slowly with humidity when humidity is not rising, resulting in a smaller slope and fluctuations between positive and negative values, the fluctuations are more dramatic.

[0026] The degree of disorder in the distribution of all elements in the slope fluctuation sequence is obtained, where the degree of disorder can be variance, standard deviation, information entropy, etc. In this embodiment, the degree of disorder is the standard deviation of all elements in the slope fluctuation sequence.

[0027] The slope of the fitted line is obtained by calculating the time series of all humidity data in each time period using the least squares method. The least squares linear fitting method is a well-known technique, and the specific process will not be described in detail here.

[0028] It should be noted that this application provides only one linear fitting algorithm for linear fitting of time series humidity data. There are many existing linear fitting algorithms, and implementers may also use other linear fitting algorithms to calculate the fitting line of time series humidity data. This application does not impose any specific restrictions.

[0029] The degree of disorder, the slope of the fitted straight line, and the maximum value of humidity data for each time period are used as the environmental humidity influence coefficient for the current data in each time period. The environmental humidity influence coefficient characterizes the influence of environmental humidity on the current data collected in each time period. The forward fusion refers to combining two or more indicators by addition or multiplication.

[0030] Preferably, in this embodiment, the expression for the environmental humidity influence coefficient is: In the formula, Let be the environmental humidity influence coefficient of the insulator to be monitored in the i-th time period. The degree of disorder in the slope fluctuation sequence of the insulator current data to be monitored during the i-th time period is described as follows: Let be the slope of the fitted straight line of the time series of all humidity data of the insulator to be monitored in the i-th time period. This represents the normalized maximum humidity value of the insulator to be monitored during the i-th time period. It is an exponential function with the natural constant e as the base. It is the hyperbolic tangent function.

[0031] In other embodiments of this application, the expression for the environmental humidity influence coefficient may also be: When the leakage current of the insulator under monitoring at different time periods is caused by changes in ambient humidity, the change in leakage current shows a step-like increase with the increase in humidity. As a result, the slope of the current data fluctuates more. At this time, the humidity data gradually increases, and the larger the humidity amplitude, the greater the influence coefficient of ambient humidity. This indicates that the insulator may be greatly affected by ambient humidity during this period, and therefore the leakage current of the insulator during this period is more likely to be caused by changes in ambient humidity.

[0032] Step S3: Based on the current fluctuation rate, current distribution range and current fluctuation duration in each time period, construct the leakage current characteristic coefficient of the insulator in each time period.

[0033] Insulators have a wide range of applications and face diverse environments, including complex weather conditions. Cold front precipitation is a common phenomenon, formed when a cold air mass actively pushes towards a warm air mass. The warm area ahead of the front is controlled by the warm air mass, resulting in higher temperature and humidity. When the cold front passes, the warm air mass rises, producing precipitation. After the cold front passes, both temperature and humidity drop sharply. When the area where the insulator is located experiences a cold front, the humidity in the environment will initially rise sharply and then drop rapidly. The measured current data will also show a rapid increase due to the humidity change. However, after the precipitation, the insulator surface remains moist due to the rainwater cover, while the ambient humidity has decreased. This results in a situation where the humidity data for the insulator's environment is low, but the current data is high, leading to a misjudgment that the insulator may be faulty and causing leakage. Therefore, further assessment of the actual situation is necessary.

[0034] Specifically, when the insulator is not affected by changes in the weather environment, the measured current data of the insulator will show extremely rapid changes and a high increase if the leakage current is caused by a defect in the insulator itself. Since the change is caused by the defect in the insulator itself, the irreversibility of the defect means that the current data will hardly decrease after the change, and thus the duration will be long. Therefore, if the insulator actually has a defect and causes a fault that leads to an increase in current, the current data will show an increase in the amplitude and a very rapid increase, which will last for a long time.

[0035] If the increase in insulator current is due to interference from cold front precipitation, the ambient humidity changes from relatively high to extremely high (precipitation occurs), and then drops rapidly. The insulator surface changes from being covered with a thin water film in a high humidity environment (current data increases slowly) to being gradually covered by rainwater (current data increases sharply multiple times). Even after the precipitation stops and the humidity drops, there is still a lot of rainwater covering the insulator surface (current data remains high). However, as time goes by, the rainwater evaporates, and the current data on the insulator surface gradually decreases and falls back to a minimum value. In other words, the overall manifestation is that the current data amplitude increases multiple times, and the overall increase rate is relatively slow and the duration is relatively short.

[0036] To characterize the rate at which current data changes from a small value to a maximum value, the current data for a single time period is first used as input, and clustering is performed using the DPC clustering algorithm. In this embodiment, the cutoff distance is set to 2% of the average distance of the data distribution, and the output consists of multiple clusters. Further, the mean value of the current data contained within a single cluster is calculated, and the cluster with the largest mean value is selected as the amplitude cluster. If the amplitude cluster contains a larger amount of data and the smaller the sampling time interval between each data point, it indicates that the duration of the current data amplitude is longer. The DPC clustering algorithm is a well-known technique, and its specific process will not be described in detail here.

[0037] It should be noted that this application provides only one clustering method for current data clustering. There are many existing clustering methods, and implementers may also use other clustering algorithms to cluster current data. This application does not impose any specific restrictions.

[0038] The process involves obtaining the difference between the maximum and minimum values ​​of the insulator current data under monitoring within a single time period. This difference can be a differential value, a ratio, etc. All inflection points in the insulator current data under monitoring within a single time period are then obtained, with the inflection point having the largest current value being designated as the maximum inflection point. Further, the current data point with the smallest sampling time interval from the maximum inflection point is identified within the cluster with the smallest mean current data. The absolute difference between the maximum inflection point and this current data point, along with the sampling time interval, is calculated. The ratio of this absolute difference to the sampling time interval is taken as the rate of change of the current data within that time period. The acquisition of inflection points is a well-known technique, and the specific process will not be detailed here. The minimum value of the sampling time interval between the maximum inflection point and this current data point is t, to avoid the maximum inflection point and this current data point having the same sampling time, which would result in a denominator of 0 in the ratio.

[0039] Based on the above analysis, leakage current characteristic coefficients are constructed for the measured current data of the insulator under monitoring in different time periods to characterize the probability that the current data in a single time period is caused by a leakage fault. Preferably, in this embodiment, the expression for the leakage current characteristic coefficient is: In the formula, Let be the leakage current characteristic coefficient of the insulator to be monitored in the i-th time period. This represents the rate of change of the measured current data of the insulator under monitoring during the i-th time period. , These represent the maximum and minimum values ​​of the current data measured by the insulator under monitoring during the i-th time period. Let be the total number of data points contained in the amplitude cluster of the insulator current data to be monitored during the i-th time period. It is an exponential function with the natural constant e as the base; The preset minimum positive number is used to prevent the denominator from being 0. In this embodiment, the minimum positive number is set as follows: Set to 0.01.

[0040] In other embodiments of this application, the expression for the leakage current characteristic coefficient may also be: When the current data of the insulator to be monitored collected in the i-th time period is the current change caused by the defect of the insulator to be monitored, the faster the rate of change of the current data, the larger the amplitude after the change and the longer the duration after the change, the more likely the data collected in the current time period is the leakage fault caused by the defect of the insulator to be monitored, rather than the environmental weather change of the insulator to be monitored.

[0041] Step S4: Construct the defect-induced leakage coefficient of the insulator for each time period based on the environmental humidity influence coefficient and the leakage characteristic coefficient; mark suspected defective insulators based on the defect-induced leakage coefficient, and inspect and repair the marked insulators.

[0042] Based on the environmental humidity influence coefficient and the leakage current characteristic coefficient, a defect-induced leakage current coefficient is constructed for the current data of the insulator to be monitored in each time period, characterizing the probability of leakage current fault in the current insulator to be monitored. Preferably, in this embodiment, the expression for the defect-induced leakage current coefficient is: In the formula, Let be the defect-induced leakage coefficient of the insulator current data to be monitored in the i-th time period. Let be the environmental humidity influence coefficient for the current data in the i-th time period. Let be the leakage current characteristic coefficient of the insulator to be monitored in the i-th time period. This is the normalization function; The preset minimum positive number is used to prevent the denominator from being 0. In this embodiment, the minimum positive number is set as follows: Set to 0.01. Wherein, This is denoted as the first ratio. The normalization function used in this application is the maximum-minimum normalization function, which takes the first ratio of all insulators in all time periods as the input of the maximum-minimum normalization function and outputs the normalized value of the first ratio of each insulator in each time period.

[0043] The less likely the measured current data of the insulator under monitoring in the i-th time period is affected by changes in ambient humidity, and the more current data changes include the current change data characteristics caused by leakage due to defects in the insulator itself, the greater the possibility that the insulator under monitoring has a leakage fault caused by its own defects.

[0044] The above method allows for the calculation of the defect-induced leakage coefficient of the measured current data for each time period. Current and humidity data for all insulators across all historical time periods are obtained, and the same method is used to calculate the defect-induced leakage coefficient for all insulators across all historical time periods. All defect-induced leakage coefficients are used as input to a threshold segmentation algorithm, and the output is the segmentation threshold for the defect-induced leakage coefficient. When the defect-induced leakage coefficient of the insulator under monitoring in a single time period is greater than or equal to this segmentation threshold, it indicates a high probability that the insulator under monitoring has a leakage fault caused by its own defects, and the corresponding insulator is marked as a suspected defective insulator. Otherwise, it indicates a low probability that the insulator under monitoring has a leakage fault caused by its own defects. In this embodiment, the Otsu method is used to obtain the segmentation threshold for the defect-induced leakage coefficient. Many existing threshold segmentation methods exist, and implementers can also use other threshold segmentation algorithms to obtain the segmentation threshold for the defect-induced leakage coefficient; this application does not impose specific limitations.

[0045] When a suspected defective insulator is detected, an alarm is immediately triggered, and fault information (such as leakage current value, location, and time) is uploaded to the remote management platform or the terminal equipment of maintenance personnel (such as an app, SMS, or telephone). Upon arrival at the site, maintenance personnel will wear insulated protective gear and use insulated tools to replace or repair the faulty insulator. They will then check whether the insulation resistance after repair meets the standards, and power supply can only be restored after confirming safety.

[0046] A schematic diagram of the process for obtaining the leakage current characteristic coefficient is shown below. Figure 2 As shown.

[0047] Based on the same inventive concept as the above methods, this application also provides a pulse insulator leakage fault diagnosis system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above pulse insulator leakage fault diagnosis methods.

[0048] In summary, this application provides a pulse-type insulator leakage fault diagnosis method. It simultaneously collects insulator leakage current data and humidity data of the insulator's environment. An environmental humidity influence coefficient is constructed based on the characteristics of insulator current data changes caused by humidity variations and precipitation, analyzing the environmental interference caused by the external environment. Simultaneously, a leakage characteristic coefficient is constructed based on the leakage current changes caused by actual insulator defects. Combining these two methods distinguishes whether the insulator current data changes are due to environmental influences or inherent defects, thus determining the cause of the current leakage current data. This solves the problem that in traditional insulator leakage fault diagnosis methods, the leakage currents caused by environmental influences and insulator defects are often similar, making it impossible to determine the actual leakage situation. By accurately distinguishing the causes of insulator leakage faults, the efficiency of leakage fault detection and repair is improved.

[0049] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0050] The various embodiments in this application are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0051] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for diagnosing leakage faults in pulse-type insulators, characterized in that, The method includes the following steps: Collect insulator current data and ambient humidity data at various times; Based on the degree of fluctuation of insulator current data, the trend of humidity change, and the maximum humidity value in each time period, an environmental humidity influence coefficient for insulators in each time period is constructed. Based on the current fluctuation rate, current distribution range and current fluctuation duration in each time period, leakage current characteristic coefficients of insulators in each time period are constructed. Based on the environmental humidity influence coefficient and the leakage characteristic coefficient, a defect-induced leakage coefficient for insulators in each time period is constructed; based on the defect-induced leakage coefficient, suspected defective insulators are marked, and the marked insulators are inspected and repaired.

2. The pulse-type insulator leakage fault diagnosis method as described in claim 1, characterized in that, The process for obtaining the environmental humidity influence coefficient is as follows: The current data in each time period are fitted by a curve fitting algorithm to obtain the degree of disorder of the slope distribution at all sampling times in the fitted curve. The slope of the fitted straight line of the time series of all humidity data in each time period is calculated. Based on the degree of disorder, the slope of the fitted straight line and the maximum value of humidity data in each time period, the environmental humidity influence coefficient of each time period is determined.

3. The pulse-type insulator leakage fault diagnosis method as described in claim 2, characterized in that, The degree of disorder in the distribution of the slope is the standard deviation of the slope at all sampling times in the fitted curve.

4. The pulse-type insulator leakage fault diagnosis method as described in claim 2, characterized in that, The environmental humidity influence coefficient is a positive fusion result of the disorder level, the slope of the fitted straight line, and the maximum value of humidity data for each time period.

5. The pulse-type insulator leakage fault diagnosis method as described in claim 1, characterized in that, The process for obtaining the leakage current characteristic coefficient is as follows: Clustering algorithms are used to cluster all current data in each time period to obtain the total number of elements in the cluster with the highest mean of elements within the cluster. The maximum inflection point in the current data for each time period is obtained, and the current data in the cluster with the smallest mean of elements within the cluster are combined to calculate the rate of change for each time period. Based on the changing rate value, the difference between the maximum and minimum current values ​​and the total number of elements in the cluster in each time period, leakage current characteristic coefficients are constructed for each time period. The leakage current characteristic coefficients are positively correlated with the changing rate value, the difference between the maximum and minimum values ​​and the total number of elements in the cluster.

6. The pulse-type insulator leakage fault diagnosis method as described in claim 5, characterized in that, The process for obtaining the changing speed value is as follows: In the cluster with the smallest mean of elements within the cluster, the current data point with the smallest time interval from the maximum inflection point is obtained, and the ratio of the current difference to the time difference between the maximum inflection point and the current data point is recorded as the rate of change value.

7. The pulse-type insulator leakage fault diagnosis method as described in claim 5, characterized in that, The difference between the maximum and minimum values ​​of the current data is the ratio of the maximum value to the minimum value in the current data for each time period.

8. The pulse-type insulator leakage fault diagnosis method as described in claim 1, characterized in that, The defect-induced leakage coefficient is the normalized value of the ratio of the leakage characteristic coefficient to the environmental humidity influence coefficient.

9. The pulse-type insulator leakage fault diagnosis method as described in claim 1, characterized in that, The method for marking suspected defective insulators is as follows: If the leakage current coefficient caused by the defect of the insulator is greater than or equal to the preset segmentation threshold at any time, the insulator will be marked as a suspected defective insulator.

10. A pulse-type insulator leakage fault diagnosis system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-9.

Images