Insulation Defect Identification Method, Device, Computer Equipment and Storage Medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for identifying insulation defects, and relates to the technical field of insulation detection. The method includes: obtaining a PRPD spectrum corresponding to the power equipment to be detected, and dividing the PRPD spectrum into a first sub-spectrum and a second sub-spectrum; obtaining a first signal cluster in the first sub-spectrum, determining a first time-domain waveform data set corresponding to the first signal cluster, and a first similarity within the first time-domain waveform data set; if the first similarity is greater than a first threshold, obtaining a second signal cluster in the second sub-spectrum, and determining a second time-domain waveform data set corresponding to the second signal cluster, and a second similarity between the first time-domain waveform data set and the second time-domain waveform data set; the second signal cluster is determined based on the phase angle of the first signal cluster; if the second similarity is greater than a second threshold, determining that there is an insulation defect signal in the power equipment to be detected. Using this method can improve the accuracy of insulation defect identification.

Description

Technical Field

[0001] The present application relates to the technical field of insulation detection, and particularly to a method, device, computer device, storage medium and computer program product for identifying insulation defects. Background Art

[0002] The atlas technology for judging partial discharge has developed rapidly, but the automatic judgment technology has been stagnant. The judgment of insulation defects is usually carried out by testers or experts. With the popularization of urban high-voltage technology and the advancement of urbanization, the workload of identifying insulation defects has doubled. Therefore, in related technologies, an artificial intelligence model can be used for automatic identification to improve the efficiency of insulation defect identification work.

[0003] In related technologies, usually, threshold judgment is performed on physical quantities based on multiple logic gates, and insulation defect identification is performed based on the relationship between the amplitude and phase of the PRPD (Phase Resolved Partial Discharge) atlas by a neural network. The recognition result is obtained by synthesizing the correlation relationship between the multiple logic gates and the neural network. However, by using the features provided by the PRPD atlas and the logical relationship of the feature quantities for insulation defect identification, it is essentially the recognition of the phase distribution characteristics of the PRPD atlas, resulting in a low data dimension of the features used for insulation defect identification and insufficient correlation between different features, leading to insufficient accuracy of insulation defect identification. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer device, computer-readable storage medium and computer program product for identifying insulation defects that can improve the recognition accuracy in view of the above technical problems.

[0005] In a first aspect, the present application provides a method for identifying insulation defects. The method includes:

[0006] Obtain a PRPD atlas corresponding to the power equipment to be detected, and divide the PRPD atlas into a first sub-atlas and a second sub-atlas;

[0007] Obtain a first signal group in the first sub-atlas, determine a first time-domain waveform data set corresponding to the first signal group, and a first similarity within the first time-domain waveform data set; the first similarity is determined based on the labeled data and comparison data in the first time-domain waveform data set; the labeled data is the data corresponding to the first preset number of samples configured in the first time-domain waveform set, and the comparison data is the data other than the labeled data in the first time-domain waveform data set, and the number of the labeled data and the comparison data is the same;

[0008] If the first similarity is greater than the first threshold, obtain the second signal cluster in the second sub-spectrum, and determine the second time-domain waveform data set corresponding to the second signal cluster, as well as the second similarity between the first time-domain waveform data set and the second time-domain waveform data set; the second signal cluster is determined based on the phase angle of the first signal cluster.

[0009] If the second similarity is greater than the second threshold, determine that there is an insulation defect signal in the power equipment to be detected.

[0010] In one embodiment, the obtaining the first signal cluster in the first sub-spectrum, determining the first time-domain waveform data set corresponding to the first signal cluster, and the first similarity within the first time-domain waveform data set includes:

[0011] Retrieve the signal clusters included in the first sub-spectrum. If the area of any retrieved signal cluster is greater than the preset area, determine the signal cluster as the first signal cluster and the phase angle corresponding to the first signal cluster.

[0012] Based on the phase angle of the first signal cluster, determine the first time-domain waveform data set corresponding to the first signal cluster, and determine the first similarity based on the marked data and comparison data in the first time-domain waveform data set.

[0013] In one embodiment, the determining the first similarity based on the marked data and comparison data in the first time-domain waveform data set includes:

[0014] Determine the calculation formula of the first similarity as follows:

[0015]

[0016] wherein, the first time-domain waveform data set is and the marked data is and the comparison data is , n represents the total number of elements in the first time-domain waveform data set, and C represents the first similarity.

[0017] In one embodiment, the obtaining the second signal cluster in the second sub-spectrum, determining the second time-domain waveform data set corresponding to the second signal cluster, and the second similarity between the first time-domain waveform data set and the second time-domain waveform data set includes:

[0018] Based on the phase angle corresponding to the first signal cluster, determine the retrieval range in the second sub-spectrum.

[0019] In the search range, determine a second signal group and a second time-domain waveform data set corresponding to the second signal group; the second time-domain waveform data set is determined by taking the opposite of the data of the time-domain waveform corresponding to the second signal group;

[0020] Based on the first time-domain waveform data set and the second time-domain waveform data set, determine a second similarity.

[0021] In one embodiment, the determining the second similarity based on the first time-domain waveform data set and the second time-domain waveform data set includes:

[0022] Determine the calculation formula of the second similarity as follows:

[0023]

[0024] wherein, the first time-domain waveform data set is , and the second time-domain waveform data set is , n represents the total number of elements in the first time-domain waveform data set, and E represents the second similarity.

[0025] In one embodiment, the dividing the PRPD map into a first sub-map and a second sub-map includes:

[0026] Determine a dividing line, and divide the PRPD map into a first sub-map and a second sub-map based on the dividing line; the dividing line is a vertical line, and the dividing point of the dividing line is located at the position corresponding to 180 degrees.

[0027] In one embodiment, the obtaining the PRPD map corresponding to the power equipment to be detected includes:

[0028] Obtain a partial discharge signal data stream corresponding to the power equipment to be detected; the partial discharge signal data stream includes the moments within a working cycle and the discharge signal amplitudes corresponding to each of the moments;

[0029] For each working cycle, based on the number of discharges in each phase segment included in the working cycle and the discharge signal amplitudes corresponding to the moments in the partial discharge signal data stream, determine the PRPD map corresponding to the power equipment to be detected.

[0030] In a second aspect, the present application also provides an insulation defect identification device. The device includes:

[0031] A map division module, configured to obtain a PRPD map corresponding to the power equipment to be detected and divide the PRPD map into a first sub-map and a second sub-map;

[0032] The first similarity determination module is configured to obtain the first signal group in the first sub-spectrum, determine the first time-domain waveform data set corresponding to the first signal group, and the first similarity within the first time-domain waveform data set; the first similarity is determined based on the labeled data and comparison data in the first time-domain waveform data set; the labeled data is the data corresponding to the first preset number of samples configured in the first time-domain waveform set, and the comparison data is the data other than the labeled data in the first time-domain waveform data set, and the number of the labeled data and the comparison data is the same;

[0033] The second similarity determination module is configured to, if the first similarity is greater than the first threshold, obtain the second signal group in the second sub-spectrum, and determine the second time-domain waveform data set corresponding to the second signal group, and the second similarity between the first time-domain waveform data set and the second time-domain waveform data set; the second signal group is determined based on the phase angle of the first signal group;

[0034] The insulation defect identification module is configured to, if the second similarity is greater than the second threshold, determine that there is an insulation defect signal in the power device to be detected.

[0035] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method as described in the first aspect are implemented.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method as described in the first aspect are implemented.

[0037] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method as described in the first aspect are implemented.

[0038] The above-mentioned insulation defect identification method, device, computer equipment, storage medium and computer program product obtain the PRPD map corresponding to the power equipment to be detected, and divide the PRPD map into a first sub-map and a second sub-map. Obtain the first signal cluster in the first sub-map, determine the first time-domain waveform data set corresponding to the first signal cluster, and based on the data corresponding to the first preset number of samples and the remaining data in the first time-domain waveform data set, the quantities of the two are equal, and determine the first similarity. When the first similarity is greater than the first threshold, obtain the second signal cluster in the second sub-map, and determine the second time-domain waveform data set corresponding to the second signal cluster, and determine the second similarity based on the first time-domain waveform data set and the second time-domain waveform data set. When the second similarity is greater than the second threshold, it is determined that there is an insulation defect signal in the power equipment to be detected, that is, it is recognized that there is an insulation defect in the power equipment to be detected. Due to the periodicity of the PRPD map and the symmetry of the PRPD map of insulation defects, dividing the PRPD map into a first sub-map and a second sub-map can filter out the PRPD map with noise interference. And by calculating the first similarity between the marked data and the comparison data in the first time-domain waveform data set corresponding to the first sub-map, it can be determined whether the first signal cluster is a defect pulse waveform of the same source. After that, after determining that the first signal cluster is a defect pulse waveform of the same source, the corresponding second signal cluster can be found in the second sub-map, and it is determined whether the second time-domain waveform data set corresponding to the second signal cluster is similar to the first time-domain waveform data set. If they are similar, it can be determined that the PRPD map has symmetry, and the second signal cluster is a defect pulse waveform of the same source, and it is determined that the power equipment to be detected contains an insulation defect signal. Therefore, by combining the PRPD map and the time-domain waveform data through the above process, it is judged whether there is an insulation defect in the power equipment, the data dimension for insulation defect identification is increased, and the accuracy of insulation defect identification is improved. Brief Description of the Drawings

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0040] Figure 1 It is an application environment diagram of the insulation defect identification method in an embodiment;

[0041] Figure 2 It is a flow schematic diagram of the insulation defect identification method in an embodiment;

[0042] Figure 3Schematic diagram of a typical insulation defect detection atlas in an embodiment;

[0043] Figure 4 Schematic diagram of a typical defect atlas in an embodiment;

[0044] Figure 5 Schematic diagram of a typical noise interference atlas in an embodiment;

[0045] Figure 6 Schematic flowchart of an insulation defect identification method in another embodiment;

[0046] Figure 7 Schematic diagram of a gridded PRPD atlas in an embodiment;

[0047] Figure 8 Schematic flowchart of insulation defect identification in yet another embodiment;

[0048] Figure 9 Schematic flowchart of insulation defect identification in yet another embodiment;

[0049] Figure 10 Structural block diagram of an insulation defect identification device in an embodiment;

[0050] Figure 11 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0051] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] The insulation defect identification method provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 can detect the power equipment to be detected, obtain the PRPD (Phase Resolved Partial Discharge) map corresponding to the power equipment to be detected, and the terminal 102 can record the voltage amplitude at each moment through the acquisition rate of the ADC (Analog-to-Digital Converter) chip, so as to obtain the time-domain waveform data corresponding to the power equipment to be detected. The terminal 102 can send the PRPD map and the time-domain waveform data corresponding to the power equipment to be detected to the server 104. The server 104 can divide the PRPD map into a first sub-map and a second sub-map. The server 104 obtains a first signal cluster in the first sub-map and determines a first set of time-domain waveform data corresponding to the first signal cluster. The server 104 calculates the similarity between the marked data and the comparison data inside the first set of time-domain waveform data. The marked data is the data corresponding to the first preset number of samples configured in the first time-domain waveform set, and the comparison data is the data other than the marked data in the first set of time-domain waveform data. The number of marked data and comparison data is the same, and the first similarity within the first set of time-domain waveform data is obtained. When the first similarity is greater than the first threshold, the server obtains a second signal cluster in the second sub-map and determines a second set of time-domain waveform data corresponding to the second signal cluster. The server 104 calculates the similarity between the first set of time-domain waveform data and the second set of time-domain waveform data to obtain the second similarity. When it is determined that the second similarity is greater than the second threshold, the server 104 can determine that there is an insulation defect signal in the power equipment to be detected, and the first signal cluster and the second signal cluster in the PRPD map, as well as the time-domain waveforms corresponding to the first signal cluster and the second signal cluster, are the parts corresponding to the insulation defect signal. The terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or other network servers.

[0053] Among them, the terminal 102 can be, but is not limited to, various computers and partial discharge detection devices. The partial discharge detection device can be a high-frequency current sensor, an ultrasonic sensor, a UHF sensor, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0054] In an exemplary embodiment, as Figure 2 shown, a method for identifying insulation defects is provided. Taking the method applied to the Figure 1 server 104 in it as an example, it includes the following steps S202 to step S208. Among them:

[0055] Step S202: Obtain the PRPD map corresponding to the power equipment to be detected, and divide the PRPD map into a first sub-map and a second sub-map.

[0056] Among them, the power equipment to be detected may include equipment such as transformers, switchgear, gas-insulated switchgears, high-voltage cables, ring main units, and reactors. The PRPD map corresponds the amplitude of the partial discharge signal with the phase angle of the power frequency voltage, and shows the discharge activity graph within a complete voltage cycle from 0 degrees to 360 degrees. The horizontal axis of the PRPD map represents the phase angle of the power frequency voltage, and the range can be from 0 to 360 degrees. The vertical axis represents the amplitude of the partial discharge signal, and the color or brightness represents the occurrence frequency of the discharge time.

[0057] Specifically, the server can obtain the PRPD map of the power equipment to be detected through the terminal, and split the PRPD map at a preset phase angle within a complete voltage cycle to obtain two sub-maps, namely the first sub-map and the second sub-map. In one example, the server can determine the sub-map with a relatively smaller phase angle as the first sub-map, and determine the sub-map with a relatively larger phase angle as the second sub-map.

[0058] Step S204: Obtain the first signal cluster in the first sub-map, determine the first time-domain waveform data set corresponding to the first signal cluster, and the first similarity within the first time-domain waveform data set.

[0059] Among them, the first similarity is determined based on the labeled data and the comparison data in the first time-domain waveform data set. The labeled data is the data corresponding to the first preset number of samples configured in the first time-domain waveform data set as the labeled data, and the comparison data can be unlabeled data, that is, the data in the first time-domain waveform data set that is not labeled. The number of labeled data and comparison data is the same.

[0060] Specifically, the server can search in the first sub-map to determine whether there is a first signal cluster. In the case of determining the first signal cluster, the server can determine the time-domain waveform data corresponding to each phase angle according to the phase angle, voltage amplitude, and color of the first signal cluster in the PRPD map, so as to obtain the first time-domain waveform data set. For example, the server can determine that the phase angle is 90 degrees, and includes all the scattered points of all colors and all voltage amplitudes, and determine the time-domain waveform data corresponding to the above scattered points to obtain the time-domain waveform data corresponding to this phase angle. After determining all the scattered points within the phase angle range corresponding to the first signal cluster, the first time-domain waveform data set corresponding to the first signal cluster can be obtained.

[0061] The server can mark the first preset number of samples in the first time-domain waveform data set based on a preset marking strategy to obtain marked data, and determine the other samples in the first time-domain waveform data set as comparison data. The server can compare the marked data and the comparison data at the corresponding positions based on their positions in the first time-domain waveform data set, so as to obtain the first similarity between each marked data and each comparison data.

[0062] Step S206, if the first similarity is greater than the first threshold, obtain the second signal cluster in the second sub-spectrum, determine the second time-domain waveform data set corresponding to the second signal cluster, and the second similarity between the first time-domain waveform data set and the second time-domain waveform data set.

[0063] Among them, the second signal cluster is determined based on the phase angle of the first signal cluster. Since the PRPD spectrum corresponding to the power equipment with insulation defects has a certain symmetry, the server can determine the phase angle at the symmetric position based on the phase angle (i.e., the phase angle value) of the first signal cluster, and determine the second signal cluster at the phase angle at the symmetric position.

[0064] Specifically, the server can determine whether the first similarity is greater than the first threshold. If the first similarity is not greater than the first threshold, it is determined that there is no insulation defect in the first signal cluster. The server can obtain a new PRPD spectrum, and return to the step of dividing the PRPD spectrum into the first sub-spectrum and the second sub-spectrum, obtaining the first signal cluster in the first sub-spectrum, determining the first time-domain waveform data set corresponding to the first signal cluster, and the first similarity within the first time-domain waveform data set. If the first similarity is greater than the first threshold, it is determined that the first signal cluster may have an insulation defect. Further, according to the phase angle of the first signal cluster, the phase angle at the symmetric position can be determined, and the second signal cluster can be retrieved in the second sub-spectrum based on the phase angle at the symmetric position.

[0065] The server can determine the time-domain waveform data corresponding to each phase angle according to the phase angle, voltage amplitude, and color of the second signal cluster in the PRPD spectrum, so as to obtain the second time-domain waveform data set. Then, the server can compare the data at the same position in different data sets based on the positions of the samples in the first time-domain waveform data set and the second time-domain waveform data set, so as to obtain the second similarity between the first time-domain waveform data set and the second time-domain waveform data set.

[0066] Step S208, if the second similarity is greater than the second threshold, determine that there is an insulation defect signal in the power equipment to be detected.

[0067] Specifically, if the second similarity is less than or equal to the second threshold, it can be determined that the second similarity between the first time-domain waveform data set and the second time-domain waveform data set is insufficient. That is to say, the distribution symmetry of the scatter points in the PRPD pattern is insufficient, and the PRPD pattern is not the pattern of insulation defects, nor is the time-domain waveform corresponding to the PRPD pattern the time-domain waveform corresponding to insulation defects. If the second similarity is greater than the second threshold, it can be determined that the distribution of the scatter points in the PRPD pattern has symmetry, that is, it satisfies the typical characteristics of insulation defects. Based on this, if the second similarity is greater than the second threshold, the server can determine that there is an insulation defect signal in the power device to be detected.

[0068] In the above insulation defect identification method, by obtaining the PRPD pattern corresponding to the power device to be detected and dividing the PRPD pattern into a first sub-pattern and a second sub-pattern. Obtain the first signal cluster in the first sub-pattern, determine the first time-domain waveform data set corresponding to the first signal cluster, and based on the data corresponding to the first preset number of samples configured in the first time-domain waveform data set and the remaining data, the numbers of both are equal, determine the first similarity. When the first similarity is greater than the first threshold, obtain the second signal cluster in the second sub-pattern, and determine the second time-domain waveform data set corresponding to the second signal cluster, and determine the second similarity based on the first time-domain waveform data set and the second time-domain waveform data set. When the second similarity is greater than the second threshold, determine that there is an insulation defect signal in the power device to be detected, that is, it is recognized that there is an insulation defect in the power device to be detected. Due to the periodicity of the PRPD pattern and the symmetry of the PRPD pattern of insulation defects, dividing the PRPD pattern into a first sub-pattern and a second sub-pattern can filter out the PRPD pattern with noise interference. And by calculating the first similarity between the marked data and the comparison data in the first time-domain waveform data set corresponding to the first sub-pattern, it can be determined whether the first signal cluster is a defective pulse waveform from the same source. After that, after determining that the first signal cluster is a defective pulse waveform from the same source, the corresponding second signal cluster can be found in the second sub-pattern, and it is determined whether the second time-domain waveform data set corresponding to the second signal cluster is similar to the first time-domain waveform data set. If they are similar, it can be determined that the PRPD pattern has symmetry, and the second signal cluster is a defective pulse waveform from the same source, and it is determined that the power device to be detected contains an insulation defect signal. Thus, by combining the PRPD pattern and the time-domain waveform data through the above process to determine whether there is an insulation defect in the power device, the data dimension for insulation defect identification is increased, and the accuracy of insulation defect identification is improved.

[0069] In an exemplary embodiment, the specific implementation process of the step "obtain the first signal cluster in the first sub-pattern, determine the first time-domain waveform data set corresponding to the first signal cluster, and the first similarity within the first time-domain waveform data set" includes:

[0070] Retrieve the signal clusters included in the first sub-spectrum. If any signal cluster with an area greater than the preset area is retrieved, determine the signal cluster as the first signal cluster and the corresponding phase angle of the first signal cluster; based on the phase angle of the first signal cluster, determine the first time-domain waveform data set corresponding to the first signal cluster, and determine the first similarity based on the marked data and comparison data in the first time-domain waveform data set.

[0071] Specifically, the server can configure a sliding window with a preset area and perform a sliding search in the first sub-spectrum through the sliding window to determine whether there is a signal cluster with an area greater than the preset area in the first sub-spectrum. If there is a signal cluster with an area greater than the preset area, determine the signal cluster as the first signal cluster. The server can determine the first time-domain waveform data set corresponding to the first signal cluster according to the phase angle of the first signal cluster. The server can determine the voltage amplitude and color of this phase angle in the PRPD spectrum, and determine the time-domain waveform data corresponding to each phase angle according to the phase angle of the first signal cluster to obtain the first time-domain waveform data set.

[0072] In one example, the phase angle of the first signal cluster can be a range, and this range can contain multiple phase angles. The first time-domain waveform data set is determined after merging the time-domain waveform data corresponding to multiple phase angles. When merging, the server can perform sequential connection according to the magnitude order of the phase angles to obtain the first time-domain waveform data set.

[0073] After that, the server can mark the first preset number of samples in the first time-domain waveform data set according to the preset marking strategy to obtain the marked data, and determine the other samples in the first time-domain waveform data set as the comparison data. For example, the first time-domain waveform data set can be .

[0074] Among them, the first p samples are determined as the marked data, and the samples after p + 1 are determined as the remaining data. is the demarcation data point between the marked data and the remaining data in and is

[0075] In this embodiment, by obtaining the signal cluster with an area greater than the preset area, the first signal cluster in the PRPD spectrum can be obtained, and based on the first signal cluster, the first time-domain waveform data set is obtained, and the first similarity corresponding to the first time-domain waveform data set is obtained, which can improve the accuracy of the first time-domain waveform data set.

[0076] In an exemplary embodiment, the specific implementation process of the step "determine the first similarity based on the marked data and comparison data in the first time-domain waveform data set" includes:

[0077] The calculation formula for determining the first similarity is as follows:

[0078]

[0079] where the first time-domain waveform data set is , the marked data is , the comparison data is , n represents the total number of elements in the first time-domain waveform data set, and C represents the first similarity.

[0080] Specifically, the server can calculate the difference value between the marked data at the corresponding position and the comparison data at the corresponding position respectively to obtain the difference value at each position. The server can divide the positions with difference values by all the positions to be compared to obtain the ratio of the existing differences. The server can use 1 minus this ratio to obtain the ratio without differences, which is used as the first similarity.

[0081] In an example, n can be 2 times the p value. At this time, the calculation formula can determine the data from 1 to p as the marked data and the data from p + 1 to 2p as the comparison data respectively. The server can sequentially compare (w 11 , w 1p+1 ), (w 12 , w 1p+2 )...... (w 1p , w 12p ) to obtain whether there is a difference at each position. The server can subtract W 1c from W 1p to obtain the difference value, and define a group of data with a difference value greater than the preset difference as having a difference, and define a group of data with a difference value less than or equal to the preset difference as having no difference. For the values with differences, 1 can be taken, and for the values with no differences, 0 can be taken. The server can obtain the ratio of the data with differences in all the data based on this. For example, the ratio is 0.2, so as to obtain the first similarity 1 - 0.2 = 0.8.

[0082] In this embodiment, by the marked data and comparison data at each corresponding position, the similarity between the marked data and the comparison data can be determined, so as to obtain the first similarity, which can improve the efficiency and accuracy of determining the first similarity.

[0083] In an exemplary embodiment, the specific implementation process of the step "obtain the second signal group in the second sub-spectrum, determine the second time-domain waveform data set corresponding to the second signal group, and the second similarity between the first time-domain waveform data set and the second time-domain waveform data set" includes:

[0084] Based on the phase angle corresponding to the first signal group, determine the search range in the second sub-spectrum; in the search range, determine the second signal group and the second time-domain waveform data set corresponding to the second signal group; the second time-domain waveform data set is determined by taking the opposite of the time-domain waveform data corresponding to the second signal group; based on the first time-domain waveform data set and the second time-domain waveform data set, determine the second similarity.

[0085] Among them, the search range can be obtained by adding the first angle and the second angle to the phase angle, so as to obtain a search range composed of the sum value of the phase angle and the first angle and the sum value of the phase angle and the second angle. For example, in the PRPD spectrum of a typical defect discharge signal, the signal groups in the positive half cycle (the 1st and 2nd quadrants) and the negative half cycle (the 3rd and 4th quadrants) are corresponding. The phase difference between the centers of the 1st and 3rd quadrants is 180°. Therefore, a range is added, that is, 160° to 200°. The phase angle is f1, the first angle is 160 degrees, and the second angle is 200 degrees. Then the search range is [f1 + 160°, f1 + 200°]. In actual tests, it is almost impossible for f1 to be equal to 10° because the phase angle of 10° corresponds to a voltage close to the zero axis, that is, no power generation occurs when the voltage is zero. Therefore, the actual phase of the discharge can only be at a higher voltage position. From experience, it is approximately 45° to 135°. So the range of the phase angle f1 is specified as [45° to 135°].

[0086] Specifically, the server can construct a search range for the second sub-spectrum retrieval according to the phase angle of the first signal group. The server can use a sliding window corresponding to a preset area in the search range to search whether there is a signal group with an area larger than the preset area in the search range. If there is a signal group with an area larger than the preset area, it is determined that the signal group is the second signal group. The server can determine the time-domain waveform data corresponding to the second signal group according to the phase angle of the second signal group. Since in the PRPD spectrum of a typical defect discharge signal, the signal groups in the positive half cycle (the 1st and 2nd quadrants) and the negative half cycle (the 3rd and 4th quadrants) are corresponding, the server can take the opposite of the time-domain waveform data corresponding to the second signal group and determine the time-domain waveform data after taking the opposite as the second time-domain waveform data set.

[0087] After that, the server can compare the first time-domain waveform data set corresponding to the first signal group with the second time-domain waveform data set corresponding to the second signal group. For each sample in the first time-domain waveform data set and the second time-domain waveform data set, a group of samples at the same position are compared to obtain the similarity corresponding to each group of samples. Finally, the similarities corresponding to all groups of samples are fused to obtain the second similarity.

[0088] In this embodiment, the retrieval range is determined through the phase angle of the first signal group, and the second time-domain waveform data set is determined within the retrieval range. Also, the second similarity is determined through the first time-domain waveform data set and the second time-domain waveform data set. It is possible to accurately obtain the second signal group and the second time-domain waveform data by utilizing the symmetry of the PRPD map with insulation defects, thereby improving the accuracy of determining the second similarity.

[0089] In an exemplary embodiment, the specific implementation process of the step "determine the second similarity based on the first time-domain waveform data set and the second time-domain waveform data set" includes:

[0090] The calculation formula for determining the second similarity is as follows:

[0091]

[0092] where the first time-domain waveform data set is , and the second time-domain waveform data set is , n represents the total number of elements in the first time-domain waveform data set, and E represents the second similarity.

[0093] Specifically, the server can calculate the difference values between the samples at the same position in the first time-domain waveform data set and the second time-domain waveform data set respectively to obtain the difference value of each group of samples. The server can divide the number of samples with difference values by the total number of samples being compared to obtain the ratio of differences. The server uses 1 minus this ratio to obtain the ratio of no differences, which is used as the second similarity.

[0094] In one example, the number of samples in the first time-domain waveform data set and the number of samples in the second time-domain waveform data set can be the same or different. This embodiment of the present application illustrates the case where the number of samples is the same. The server can take samples at the same position from the first time-domain waveform data set and the second time-domain waveform data set respectively to obtain multiple sample groups (w 11 , w 21 ), (w 12 , w 22 )......(w 1n , w 2n), based on multiple sample groups, the formula of W2 - W1 can be executed to obtain the difference values between each sample group. If the difference value is greater than the preset difference, it is determined that there is a difference in this sample group; if the difference value is less than or equal to the preset difference, it is determined that there is no difference in this sample group, that is, this sample group is similar. At the same time, the value of the sample group with a difference can be defined as 1, and the value of the similar sample group can be defined as 0, so as to obtain the sum of W2 - W1, and determine the proportion of this sum in n, so as to obtain the difference degree. Using 1 minus the difference degree, the second similarity can be obtained.

[0095] In this embodiment, by calculating the difference values between the samples at the same positions in the first time-domain waveform data set and the second time-domain waveform data set, the second similarity is obtained, which can improve the efficiency and accuracy of determining the second similarity.

[0096] In an exemplary embodiment, the specific implementation process of the step "divide the PRPD map into a first sub-map and a second sub-map" includes:

[0097] Determine the demarcation line, and based on the demarcation line, divide the PRPD map into a first sub-map and a second sub-map; the demarcation line is a vertical line, and the demarcation point of the demarcation line is located at the position corresponding to 180 degrees.

[0098] Specifically, the server can determine the demarcation point with a phase angle of 180 degrees in the PRPD map, and take a vertical line perpendicular to the abscissa of the PRPD map at the demarcation point to obtain the demarcation line. The server can divide the PRPD map into a first sub-map and a second sub-map on the left and right based on the demarcation line. Usually, the left sub-map can be defined as the first sub-map, and the right sub-map can be defined as the second sub-map.

[0099] In this embodiment, the vertical line made through the demarcation point of 180 degrees for the PRPD map can make full use of the symmetry of the waveforms in the PRPD map, and improve the accuracy and rationality between the first sub-map and the second sub-map obtained by the division.

[0100] In an exemplary embodiment, the specific implementation process of the step "obtain the PRPD map corresponding to the power equipment to be detected" includes:

[0101] Obtain the local discharge signal data stream corresponding to the power equipment to be detected; the local discharge signal data stream includes the moments within the working cycle and the discharge signal amplitudes corresponding to each moment; for each working cycle, based on the number of discharges in each phase segment included in the working cycle and the discharge signal amplitudes corresponding to each moment in the local discharge signal data stream, determine the PRPD map corresponding to the power equipment to be detected.

[0102] Among them, partial discharge occurs in electrical equipment. When there are defects such as air gaps, impurities, and moisture in the insulating medium, under the action of a strong electric field, local discharge phenomena will occur inside the insulation. This will cause the charges in the insulating medium to transfer and redistribute rapidly, forming physical phenomena such as local pulse currents and electromagnetic waves. The initially generated partial discharge signal is an analog signal. For subsequent processing, transmission, and analysis, it needs to be converted into a digital signal through analog-to-digital conversion (ADC) technology. The ADC chip will sample and quantize the analog partial discharge signal according to a certain sampling frequency and quantization accuracy, converting it into a series of discrete digital data, which constitutes the partial discharge signal data stream. The working cycle can be the power frequency cycle.

[0103] Specifically, the server can obtain the discharge signal amplitudes corresponding to multiple power frequency cycles. For each power frequency cycle, the discharge signal amplitude corresponding to each phase angle in the power frequency cycle can be represented as a scatter point in the PRPD pattern. When the traversal of multiple power frequency cycles is completed, scatter points may be repeatedly generated at positions corresponding to similar (identical) phase angles and similar (identical) discharge signal amplitudes. Then, the color of the scatter point at that position can be changed according to the discharge frequency, so as to represent the discharge frequency of the defect of the scatter point.

[0104] In one example, the server inputs the partial discharge signal data stream, and it is required that the input data stream is a two-dimensional data set :

[0105]

[0106] Among them, T k is the k-th moment within the working cycle, Q k is the k-th amplitude of the discharge signal, N k is the k-th discharge frequency of the signal, and k is the number of data measurements. The two-dimensional data set contains T and Q, and N can be represented by the shade of color.

[0107] After that, the server can equally divide the time interval of a power frequency cycle (working cycle) into several (M) phase segments, and the number of discharges in each phase segment can be calculated by the following formula:

[0108]

[0109] As shown in the above formula, M is the several phase segments detected by dividing the power frequency cycle, and h d is the number of discharges in the d-th phase segment. The formatted two-dimensional data set , is filled into the grid, where T is the abscissa, Q is the ordinate, and the shade of the color of the scatter point is used to express the discharge frequency of the defect.

[0110] In this embodiment, by determining the PRPD map corresponding to the power equipment to be detected based on the number of discharges in each phase segment included in the duty cycle and the discharge signal amplitude corresponding to each moment in the partial discharge signal data stream, the accuracy of generating the PRPD map can be improved.

[0111] The following combines a specific embodiment to describe in detail the specific execution process of the above insulation defect identification method.

[0112] First, typical insulation defect detection maps, such as Figure 3 shown, include the PRPD map, the PRPS (Phase-Resolved Pulse Sequenc) map, and the spectrogram, and the lower part also includes the q-t map, the n-t map, and the time-domain waveform, where:

[0113] For the PRPD map, the abscissa is the phase angle (0 - 360°), corresponding to the four quadrants of the sine wave; the ordinate is the discharge amount (pC), reflecting the relationship between the discharge signal and the occurrence phase angle; among them, Figure 3 the PRPD map is the result of taking the opposite number, and its purpose is:

[0114] 1) To display the map features with less screen space;

[0115] 2) To prepare for the next step of comparing the first signal group and the second signal group.

[0116] The PRPS map is based on the three-dimensional coordinates of the PRPD map, and the added coordinate axis represents time. As time increases, the slices of the map increase (migrate) forward, reflecting the relationship between the discharge signal, the occurrence phase angle, and the time accumulation.

[0117] For the spectrogram, the abscissa is the frequency (1 - 100 MHz), and the ordinate is the discharge amplitude (dB or V), reflecting the relationship between the discharge signal amplitude and the frequency distribution;

[0118] For the q-t map, the abscissa is time, and the ordinate is the discharge amount, reflecting the change trend of the discharge amount over time;

[0119] For the n-t map, the abscissa is time, and the ordinate is the discharge density (frequency, number of discharges per second), reflecting the change trend of the discharge density over time;

[0120] For the time-domain waveform, the abscissa is time, and the ordinate is the amplitude, reflecting the relationship between the discharge signal amplitude and time; the relationship with the PRPD map is that each point in the PRPD map can be interpreted as 1 time-domain waveform.

[0121] It can be seen that in the PRPD pattern, the red PD can represent the location where partial discharge exists. In the PRPS pattern, the red PD can represent the location where partial discharge exists. In the spectrum, the red PD can represent the location where partial discharge exists. Additionally, in the spectrum, noise can be represented by green lines. Based on this, both the PRPD pattern and the time-domain waveform can be used as the current mainstream forms of insulation defect detection patterns.

[0122] As Figure 4 shown, for different types of insulation defects, the representations in the PRPD pattern and the time-domain waveform are different. Figure 4 successively shows the PRPD pattern and the time-domain waveform corresponding to internal air-gap discharge, the PRPD pattern and the time-domain waveform corresponding to surface discharge, the PRPD pattern and the time-domain waveform corresponding to semiconductor cracking, and the PRPD pattern and the time-domain waveform corresponding to buffer layer ablation defects. Additionally, as Figure 5 shown, it shows the PRPD pattern and the time-domain waveform under various typical noise interferences. Figure 5 successively shows the PRPD pattern and the time-domain waveform under motor interference, the PRPD pattern and the time-domain waveform under power system / power supply interference, the PRPD pattern and the time-domain waveform under mobile phone / radio interference, and the PRPD pattern and the time-domain waveform under corona discharge. Through the PRPD patterns in Figure 4 and Figure 5 , it can be known that the PRPD pattern of the insulation defect has origin symmetry at the phase angle of 180 degrees. Figure 4 and Figure 5 are both signal patterns without taking the opposite number. In the calculation process of this application, taking the opposite number is required.

[0123] Additionally, from the patterns in Figure 3 and Figure 4 , it can be known that whether it is a typical insulation defect signal or noise interference, there is a certain relationship between its waveform and PRPD. In particular, the pulse waveform of the insulation defect signal forms a corresponding relationship with the cluster signals in different phase segments.

[0124] Therefore, the embodiment of this application proposes a global cross-correlation judgment method for insulation defect detection patterns. It mainly solves the problems that the existing insulation defect judgment methods have insufficient global correlation, resulting in a high misjudgment rate and lack of comparative analysis of time-domain waveform spectra. Then, this method is solidified into a set of computer-executable programs, which can automatically judge and issue an alarm when an insulation defect signal is detected.

[0125] The working process of the global cross-correlation judgment method for insulation defect detection patterns is as Figure 6As shown, specifically for the correlation analysis and judgment algorithm after the segmentation and transformation of the PRPD spectrum and the time-domain waveform diagram, which includes entering the data stream in a format, drawing a grid-like PRPD spectrum, dividing the spectrum into left and right parts with a 180° boundary line, retrieving whether there is a signal cluster in the left part of the spectrum, retrieving the time-domain waveform W1 corresponding to the signal cluster, judging the similarity between the waveform diagram and the marked data, if the similarity is high, start retrieving the signal cluster in the right PRPD spectrum (otherwise return to retrieve the left spectrum), if there is a signal cluster, retrieve the corresponding time-domain waveform W2, and compare the correlation between the waveform after "taking the opposite number" and W1. If the correlation is greater than 80%, an insulation defect signal is detected and an alarm is issued.

[0126] As Figure 6 shown, the specific execution process of the insulation defect identification method includes:

[0127] (1) Format of entering the data stream: The required data stream to be entered is a two-dimensional data set .

[0128] Among them, T is the moment within the working cycle, Q is the amplitude of the discharge signal, N is the discharge frequency of the signal, and n is the number of data measurements.

[0129]

[0130] (2) Drawing a grid-like PRPD spectrum: Divide the time interval of a power frequency cycle into several (M) phase segments in equal proportion, and determine the number of discharges in each phase segment as , which can be calculated by the following formula:

[0131]

[0132] As shown in the above formula, M is several phase segments detected by dividing the power frequency cycle, and h d is the number of discharges in the dth phase segment. The server fills the formatted two-dimensional data stream into the grid, where T is the abscissa and Q is the ordinate, and the frequency of defect discharges is expressed by the depth of the color of the scatter points. Through this spectrum, the distribution characteristics and concentrated areas of the defect signals can be determined. Due to different sampling rates of the device, the number of grids can be increased to 1024*1024. To better demonstrate the method, as Figure 7 shown, a 10*10 grid is drawn for explanation.

[0133] (3) Dividing the PRPD spectrum into left and right parts: Divide the spectrum obtained in (2) into two PRPD spectra according to the 180° boundary line.

[0134] (4) Retrieve in the PRPD spectrum of the left part, aiming to find signal clusters with an area greater than 3*3, and define the phase angles f1 at which these signal clusters appear. The range of f1 is [45° - 135°].

[0135] (5) If a signal cluster is found, find the time-domain waveform of the data points at the corresponding moment. Based on the phase angle , establish the corresponding first time-domain waveform data set of the signal cluster, where the first samples are determined as the labeled data, and the other unlabeled data are determined as comparison data. Both the labeled data and the remaining comparison data are used for comparison and calculation of similarity. The purpose of calculating similarity is to confirm whether all within the signal cluster belong to the same type of signal source.

[0136] (6) Calculate the similarity of the characteristic waveforms within the signal cluster.

[0137] Set: the labeled data set , and the data set for comparison , n is the total number of the first time-domain waveform data set, p = n / 2; construct the calculation formula for the waveform similarity C as follows:

[0138]

[0139] Measure standard of similarity: The larger C is, the more the data set tends to be the same as the labeled sample; the smaller C is, the more the data set tends to be different from the sample.

[0140] (7) If the similarity is greater than 70%, it indicates that it may be the defective pulse waveform of the same source. Save this first time-domain waveform data set, and then retrieve the signal cluster of the PRPD spectrum of the right part. Define the retrieved phase range f2 as:

[0141]

[0142] (8) If a signal cluster is retrieved within the defined phase range, find the time-domain waveform of the corresponding data points, establish the corresponding waveform data and after transposition, obtain the second time-domain waveform data set . The meaning of transposition is to make the amplitude of the corresponding data points the opposite number.

[0143] (9) Judge the correlation of the time-domain waveform where the signal cluster is located. Define the cluster correlation E. If the correlation tends to 0 more, it indicates that there is no correlation. The correlation calculation formula is as follows:

[0144]

[0145] (10) Repeat the above operations (1)-(8) to calculate how many data sets meet the correlation greater than 0.8. And determine this data set as the data set with insulation defects.

[0146] In one example, as Figure 8 shown, this embodiment provides an on-site live detection implementation manner of the global cross-correlation judgment method for insulation defect detection maps. The user will first determine the object to be measured, determine the type of live detection sensor corresponding to the object to be measured, and collect and process the on-site data through the live detection sensor. Then the user will input it into the judgment algorithm associated with the embodiment of the present application to obtain a judgment and recognition result, and display the judgment result to the on-site test user in real time for the user to make a judgment and issue a report.

[0147] In one embodiment, as Figure 9 shown, this embodiment provides an online monitoring implementation manner of the global cross-correlation judgment method for insulation defect detection maps. After the online monitoring device is installed and debugged, the online monitoring device collects and processes the on-site detection data, and inputs the detection data into the associated judgment algorithm of the embodiment of the present application to obtain an identification result. If the identification result is greater than the alarm threshold preset by the system, an alarm will be issued by sound, light or email until the duty personnel retrieve the identification result and monitoring data for manual re-verification and confirmation.

[0148] It should be understood that although each step in the flowcharts involved in the above-described embodiments is shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0149] Based on the same inventive concept, the embodiment of the present application also provides an insulation defect identification device for implementing the above-mentioned insulation defect identification method. The implementation solution provided by this device to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following insulation defect identification device can refer to the limitations on the insulation defect identification method in the above text, and will not be repeated here.

[0150] In an exemplary embodiment, as Figure 10As shown in the figure, an insulation defect identification device 1000 is provided, including: a map division module 1001, a first similarity determination module 1002, a second similarity determination module 1003, and an insulation defect identification module 1004, where:

[0151] The map division module 1001 is configured to obtain a PRPD map corresponding to the power equipment to be detected, and divide the PRPD map into a first sub-map and a second sub-map;

[0152] The first similarity determination module 1002 is configured to obtain a first signal group in the first sub-map, determine a first time-domain waveform data set corresponding to the first signal group, and a first similarity within the first time-domain waveform data set; the first similarity is determined based on the labeled data and the comparison data in the first time-domain waveform data set; the labeled data is the data corresponding to the first preset number of samples configured in the first time-domain waveform set, and the comparison data is the data other than the labeled data in the first time-domain waveform data set, and the number of the labeled data and the comparison data is the same;

[0153] The second similarity determination module 1003 is configured to, if the first similarity is greater than a first threshold, obtain a second signal group in the second sub-map, and determine a second time-domain waveform data set corresponding to the second signal group, and a second similarity between the first time-domain waveform data set and the second time-domain waveform data set; the second signal group is determined based on the phase angle of the first signal group;

[0154] The insulation defect identification module 1004 is configured to, if the second similarity is greater than a second threshold, determine that there is an insulation defect signal in the power equipment to be detected.

[0155] Further, the first similarity determination module 1002 is specifically configured to: retrieve the signal groups included in the first sub-map, if it is retrieved that the area of any signal group is greater than a preset area, determine the signal group as the first signal group, and the phase angle corresponding to the first signal group; based on the phase angle of the first signal group, determine the first time-domain waveform data set corresponding to the first signal group, and determine the first similarity based on the labeled data and the comparison data in the first time-domain waveform data set.

[0156] Further, the first similarity determination module 1002 is specifically further configured to: determine that the calculation formula of the first similarity is as follows:

[0157]

[0158] where the first time-domain waveform data set is and the labeled data is and the comparison data is n represents the total number of elements in the first time-domain waveform data set, and C represents the first similarity.

[0159] Further, the second similarity determination module 1003 is specifically configured to: determine the retrieval range in the second sub-spectrum based on the phase angle corresponding to the first signal cluster; in the retrieval range, determine the second signal cluster and the second time-domain waveform data set corresponding to the second signal cluster; the second time-domain waveform data set is determined by taking the opposite of the data of the time-domain waveform corresponding to the second signal cluster; determine the second similarity based on the first time-domain waveform data set and the second time-domain waveform data set.

[0160] Further, the second similarity determination module 1003 is specifically further configured to: determine the calculation formula of the second similarity as follows:

[0161]

[0162] wherein, the first time-domain waveform data set is , and the second time-domain waveform data set is , n represents the total number of elements in the first time-domain waveform data set, and E represents the second similarity.

[0163] Further, the spectrum division module 1001 is specifically further configured to: determine the demarcation line, and divide the PRPD spectrum into a first sub-spectrum and a second sub-spectrum based on the demarcation line; the demarcation line is a vertical line, and the demarcation point of the demarcation line is located at the position corresponding to 180 degrees.

[0164] Further, the spectrum division module 1001 is specifically further configured to: obtain the partial discharge signal data stream corresponding to the power equipment to be detected; the partial discharge signal data stream includes the moments within the working cycle and the discharge signal amplitudes corresponding to each moment; for each working cycle, determine the PRPD spectrum corresponding to the power equipment to be detected based on the number of discharges in each phase segment included in the working cycle and the discharge signal amplitudes corresponding to each moment in the partial discharge signal data stream.

[0165] Each module in the above insulation defect identification device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in the form of hardware or be independent of it, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0166] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 11As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the PRPD maps of the power equipment to be detected, as well as the time-domain waveform data set. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements an insulation defect identification method.

[0167] Those skilled in the art can understand that Figure 11 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0168] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0169] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0170] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0171] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0172] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0173] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An insulation defect identification method, characterized in that, The method includes: Obtain the PRPD map corresponding to the power equipment to be detected, and divide the PRPD map into a first sub-map and a second sub-map; Obtain the first signal group in the first sub-map, determine the first time-domain waveform data set corresponding to the first signal group, and the first similarity within the first time-domain waveform data set; the first similarity is determined based on the labeled data and comparison data in the first time-domain waveform data set; the labeled data is the data corresponding to the first preset number of samples configured in the first time-domain waveform data set, and the comparison data is the data other than the labeled data in the first time-domain waveform data set, and the number of the labeled data and the comparison data is the same; If the first similarity is greater than the first threshold, obtain the second signal group in the second sub-map, and determine the second time-domain waveform data set corresponding to the second signal group, and the second similarity between the first time-domain waveform data set and the second time-domain waveform data set; the second signal group is determined based on the phase angle of the first signal group; If the second similarity is greater than the second threshold, determine that there is an insulation defect signal in the power equipment to be detected.

2. The method according to claim 1, wherein The obtaining the first signal group in the first sub-map, determining the first time-domain waveform data set corresponding to the first signal group, and the first similarity within the first time-domain waveform data set includes: Retrieve the signal groups included in the first sub-map. If the area of any retrieved signal group is greater than the preset area, determine the signal group as the first signal group and the phase angle corresponding to the first signal group; Based on the phase angle of the first signal group, determine the first time-domain waveform data set corresponding to the first signal group, and determine the first similarity based on the labeled data and comparison data in the first time-domain waveform data set.

3. The method according to claim 2, characterized in that, The determining the first similarity based on the labeled data and comparison data in the first time-domain waveform data set includes: Determine the calculation formula of the first similarity as follows: Among them, the first time-domain waveform data set is , the marker data is , the comparison data is , n represents the total number of elements in the first time-domain waveform data set, and C represents the first similarity.

4. The method according to claim 2, wherein The obtaining the second signal group in the second sub-map, determining the second time-domain waveform data set corresponding to the second signal group, and the second similarity between the first time-domain waveform data set and the second time-domain waveform data set includes: Based on the phase angle corresponding to the first signal group, determine the retrieval range in the second sub-map; In the retrieval range, determine the second signal group and the second time-domain waveform data set corresponding to the second signal group; the second time-domain waveform data set is determined by taking the opposite of the data of the time-domain waveform corresponding to the second signal group; Based on the first time-domain waveform data set and the second time-domain waveform data set, determine the second similarity.

5. The method according to claim 4, wherein The determining the second similarity based on the first time-domain waveform data set and the second time-domain waveform data set includes: Determine the calculation formula of the second similarity as follows: Among them, the first time-domain waveform data set is , the second time-domain waveform data set is , n represents the total number of elements in the first time-domain waveform data set, and E represents the second similarity.

6. The method according to claim 1, wherein The dividing the PRPD map into a first sub-map and a second sub-map includes: Determine the demarcation line, and divide the PRPD map into a first sub-map and a second sub-map based on the demarcation line; the demarcation line is a vertical line, and the demarcation point of the demarcation line is located at the position corresponding to 180 degrees.

7. The method according to claim 1, wherein The obtaining of the PRPD map corresponding to the power equipment to be detected includes: Obtain the partial discharge signal data stream corresponding to the power equipment to be detected; the partial discharge signal data stream includes the moments within the working cycle and the discharge signal amplitudes corresponding to each of the moments. For each working cycle, based on the number of discharges in each phase segment included in the working cycle and the discharge signal amplitudes corresponding to each moment in the partial discharge signal data stream, determine the PRPD map corresponding to the power equipment to be detected.

8. An insulation defect identification device, characterized in that, The device includes: A map division module, configured to obtain the PRPD map corresponding to the power equipment to be detected, and divide the PRPD map into a first sub-map and a second sub-map. A first similarity determination module, configured to obtain the first signal cluster in the first sub-map, determine the first time-domain waveform data set corresponding to the first signal cluster, and the first similarity within the first time-domain waveform data set; the first similarity is determined based on the marked data and the comparison data in the first time-domain waveform data set; the marked data is the data corresponding to the first preset number of samples configured in the first time-domain waveform data set, and the comparison data is the data other than the marked data in the first time-domain waveform data set, and the number of the marked data and the comparison data is the same. A second similarity determination module, configured to, if the first similarity is greater than a first threshold, obtain the second signal cluster in the second sub-map, and determine the second time-domain waveform data set corresponding to the second signal cluster, and the second similarity between the first time-domain waveform data set and the second time-domain waveform data set; the second signal cluster is determined based on the phase angle of the first signal cluster. An insulation defect identification module, configured to, if the second similarity is greater than a second threshold, determine that there is an insulation defect signal in the power equipment to be detected.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images