Partial discharge detection method and device based on multi-source data fusion

Abstract

The invention provides a partial discharge detection method and device based on multi-source data fusion, and belongs to the technical field of partial discharge detection, and the method specifically comprises the steps: based on the distribution data of partial discharge detection reliable moments of different switch cabinets after a partial discharge detection reliable time period, when it is determined that partial discharge detection processing cannot be carried out through employing a first detection strategy, determining that partial discharge detection processing cannot be carried out through employing a second detection strategy; partial discharge detection matching time periods of different switch cabinets are determined according to the distribution data of the partial discharge detection reliable moments of the different switch cabinets in different unit time periods, and according to the distribution data of the partial discharge detection matching time periods and coincident data of the different switch cabinets and other switch cabinets in the different partial discharge detection matching time periods, the partial discharge detection matching time periods of the different switch cabinets are determined. The partial discharge detection method and the partial discharge detection time period of different switch cabinets are determined, and the partial discharge detection processing efficiency is improved.

Description

Technical Field

[0001] This invention belongs to the field of partial discharge detection technology, and particularly relates to a partial discharge detection method and device based on multi-source data fusion. Background Technology

[0002] 10kV and 35kV high-voltage switchgear are the most widely used and numerous electrical equipment. Due to various problems in design, manufacturing, installation, operating environment, equipment maintenance, and line access, the failure rate is relatively high. Existing technical solutions often utilize conventional pulse current methods, ultra-high frequency (UHF) methods, ultrasonic methods, and transient earth voltage (TEV) methods. However, using any one of these partial discharge detection methods inevitably leads to a low accuracy rate in partial discharge detection.

[0003] To address the aforementioned technical issues, existing solutions include acoustic-electric joint detection, acoustic-optical joint detection, and optical-electric joint detection. However, all of these suffer from low detection accuracy, low detection efficiency, and insufficient detection reliability. To resolve these issues, a digital multifunctional partial discharge diagnostic device is designed, taking into account the portability required for field applications. This device integrates detection modules such as acoustic imaging, infrared thermal imaging temperature measurement, UHF / HF current partial discharge, ultrasonic waves, and transient ground waves. It adopts a miniaturized, one-handed, optimized design. Through multidimensional detection using acoustic, optical, and electrical fusion, the reliability of partial discharge detection and processing can be improved.

[0004] Furthermore, for switching equipment, infrared images often exhibit certain anomalies when partial discharge occurs. Additionally, due to differences in operating voltage and current, the reliability of partial discharge detection varies at different times. This makes it crucial to determine whether infrared imaging can be used to identify and process suspected partial discharge devices based on the distribution data of reliable moments. This is to avoid the inability to accurately verify the detection results due to the limited number of reliable moments after the infrared image detection period, and to generate differentiated partial discharge detection methods, which is an urgent technical problem to be solved.

[0005] Specifically, this application provides a partial discharge detection method and device based on multi-source data fusion, which has more application scenarios, a wider range of applications, and more accurate detection results. Summary of the Invention

[0006] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, in the first aspect, this application provides a partial discharge detection method based on multi-source data fusion, which specifically includes: S1 uses the load forecast data of the switchgear as a basis to determine the operating data of the switchgear at different times in a future preset period, and determines the reliable time for partial discharge detection of different switchgear based on the historical detection results of partial discharge signals under different operating data. S2 determines the distribution data of the reliable partial discharge detection time of the switchgear in different unit time periods within a future preset time period, and determines the reliable partial discharge detection time period in the unit time period based on the distribution data; S3, based on the distribution data of the reliable partial discharge detection times of different switchgear after the reliable partial discharge detection period, determines that the first detection strategy cannot be used for partial discharge detection processing, and then proceeds to the next step. S4 determines the partial discharge detection matching time period for different switchgears by using the distribution data of the reliable partial discharge detection time of different switchgears in different unit time periods. Based on the distribution data of the partial discharge detection matching time period and the overlap data with other switchgears in different partial discharge detection matching time periods, the detection method and partial discharge detection time period for different switchgears are determined.

[0007] A further technical solution is that the load prediction data of the switchgear is determined based on the prediction results of the power consumption data of the power equipment controlled by the switchgear.

[0008] A further technical solution is that the future preset time period is determined based on the number of switch cabinets being tested, specifically based on the partial discharge analysis time of different switch cabinets and the number of switch cabinets being tested.

[0009] A further technical solution is that the historical detection results of the partial discharge signal are determined based on the number of successful identifications and the success rate of the partial discharge using the infrared device of the partial discharge detection equipment under the abnormal partial discharge conditions of the switchgear under the operating data.

[0010] A further technical solution is that the operating data includes operating voltage and operating current.

[0011] A further technical solution is that the method for determining the reliable moment of partial discharge detection in the switchgear is as follows: Based on the historical detection results of the partial discharge signal under the corresponding operating data at the time, the identification success rate of the switchgear under the abnormal partial discharge condition under the operating data is determined; Based on the recognition success rate, determine whether the time is a reliable time for partial discharge detection of the switchgear.

[0012] A further technical solution is that the partial discharge detection matching period of the switch cabinet is a unit time period in which the number of reliable partial discharge detection moments meets the requirements. Specifically, a unit time period in which the number of reliable partial discharge detection moments is greater than a threshold can be used as the partial discharge detection matching period.

[0013] A further technical solution is that the method for determining the partial discharge detection method of the switchgear is as follows: The number of partial discharge detection matching time periods of the switchgear is determined based on the distribution data of the partial discharge detection matching time periods of the switchgear. Based on the overlap data between the partial discharge detection matching time period of the switchgear and the partial discharge detection matching time period of other switchgear, determine the number of switchgears with overlapping partial discharge detection matching time periods for different partial discharge detection matching time periods. The method for detecting partial discharge of the switchgear is determined by the number of partial discharge detection matching time periods of the switchgear and the number of overlapping switchgears with different partial discharge detection matching time periods.

[0014] In a second aspect, the present invention provides a computer device, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned partial discharge detection method based on multi-source data fusion when running the computer program.

[0015] The beneficial effects of this invention are as follows: Based on the distribution data of reliable partial discharge detection times for different switchgear after the reliable partial discharge detection period, it is determined whether the first detection strategy can be used for partial discharge detection processing. This fully considers the reliability of the verification processing for switchgear with suspected partial discharge after the reliable partial discharge detection period, avoiding the technical problem of insufficient reliability of verification processing caused by a large number of switchgear with a small number of reliable partial discharge detection times after the reliable partial discharge detection period. This ensures the reliability of partial discharge detection processing while guaranteeing the efficiency of partial discharge detection.

[0016] Based on the distribution data of partial discharge detection matching time periods and the overlap data with other switchgear in different partial discharge detection matching time periods, the detection methods for partial discharge of different switchgear are determined. This realizes the determination of the detection method of switchgear based on the number of partial discharge detection matching time periods and the overlap with other switchgear. This ensures the efficiency of partial discharge detection using infrared image positioning for switchgear with a large number of partial discharge detection matching time periods and a small number of overlaps with other switchgear, while also ensuring the reliability of partial discharge detection processing for some switchgear.

[0017] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0020] Figure 1 This is a flowchart of a partial discharge detection method based on multi-source data fusion; Figure 2 This is a flowchart illustrating the method for determining the reliable moment of partial discharge detection in switchgear; Figure 3 This is a flowchart illustrating the method for determining the reliable period for partial discharge detection within a unit time period; Figure 4 This is a flowchart illustrating the method for determining the detection method of partial discharge in switchgear. Detailed Implementation

[0021] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0022] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and to mean that there may be other elements / components / etc. in addition to the listed elements / components / etc.

[0023] Example 1 To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, a partial discharge detection method based on multi-source data fusion is provided, specifically including: S1 uses the load forecast data of the switchgear as a basis to determine the operating data of the switchgear at different times in a future preset period, and determines the reliable time for partial discharge detection of different switchgear based on the historical detection results of partial discharge signals under different operating data. Furthermore, the load forecast data of the switchgear is determined based on the forecast results of the power consumption data of the power equipment controlled by the switchgear.

[0024] Optionally, the predicted electricity consumption data of the power equipment is determined based on the average value of the historical electricity consumption data of the power equipment in different time periods. Alternatively, it can be based on the historical electricity consumption data of the power equipment in different time periods, combined with weather data, and processed using a neural network model to predict the electricity consumption data.

[0025] Specifically, the future preset time period is determined based on the number of switchgear units tested, and specifically based on the partial discharge analysis time of different switchgear units and the number of switchgear units tested.

[0026] It should be noted that the historical detection results of the partial discharge signal are determined based on the number of times and the success rate of partial discharge identification using the infrared device of the partial discharge detection equipment under the abnormal partial discharge conditions of the switchgear under the operating data.

[0027] Furthermore, the operating data includes operating voltage and operating current.

[0028] Specifically, such as Figure 2 As shown, the method for determining the reliable moment of partial discharge detection in the switchgear is as follows: Based on the historical detection results of the partial discharge signal under the corresponding operating data at the time, the identification success rate of the switchgear under the abnormal partial discharge condition under the operating data is determined; Based on the recognition success rate, determine whether the time is a reliable time for partial discharge detection of the switchgear.

[0029] Optionally, when the recognition success rate is above 0.9, the time of determination is considered the reliable time for partial discharge detection of the switchgear.

[0030] S2 determines the distribution data of the reliable partial discharge detection time of the switchgear in different unit time periods within a future preset time period, and determines the reliable partial discharge detection time period in the unit time period based on the distribution data; Specifically, such as Figure 3 As shown, the method for determining the reliable period for partial discharge detection within the unit time period is as follows: Based on the distribution data of reliable partial discharge detection times of switchgear within the unit time period, the number of reliable partial discharge detection times of different switchgear within the unit time period is determined and used as the matching detection times. By using the overlap data of matching detection times of different switchgear, the number of overlap times of matching detection times of switchgear at different times is determined. By measuring the number of overlapping detection times of the switchgear at different times, it is determined whether the unit time period is a reliable time period for partial discharge detection.

[0031] Specifically, the number of overlapping detection times of switchgear at different times determines whether the unit time period is a reliable time period for partial discharge detection, including: The moment when the number of overlaps in the matching detection of the switchgear exceeds the preset number of overlaps is taken as the overlap moment. When there is a unit time period with a number of overlapping moments that is greater than the preset threshold for the number of overlapping moments, the unit time period with the most overlapping moments is taken as the reliable time period for partial discharge detection. If the number of non-overlapping moments is greater than the preset threshold for the number of overlapping moments per unit time period, then it is determined that there is no reliable time period for partial discharge detection.

[0032] It should be noted that when there is no reliable period for partial discharge detection, it is determined that the first detection strategy cannot be used for partial discharge detection and processing.

[0033] S4 determines the partial discharge detection matching time period for different switchgears by using the distribution data of the reliable partial discharge detection time of different switchgears in different unit time periods. Based on the distribution data of the partial discharge detection matching time period and the overlap data with other switchgears in different partial discharge detection matching time periods, the detection method and partial discharge detection time period for different switchgears are determined.

[0034] Furthermore, the partial discharge detection matching period of the switchgear is a unit time period in which the number of reliable partial discharge detection moments meets the requirements. Specifically, a unit time period in which the number of reliable partial discharge detection moments is greater than the threshold can be used as the partial discharge detection matching period.

[0035] Specifically, such as Figure 4 As shown, the method for determining the detection method of partial discharge in the switchgear is as follows: The number of partial discharge detection matching time periods of the switchgear is determined based on the distribution data of the partial discharge detection matching time periods of the switchgear. Based on the overlap data between the partial discharge detection matching time period of the switchgear and the partial discharge detection matching time period of other switchgear, determine the number of switchgears with overlapping partial discharge detection matching time periods for different partial discharge detection matching time periods. The method for detecting partial discharge of the switchgear is determined by the number of partial discharge detection matching time periods of the switchgear and the number of overlapping switchgears with different partial discharge detection matching time periods.

[0036] In one possible embodiment, when the number of partial discharge detection matching time periods of the switchgear is large, i.e. greater than the threshold, the first partial discharge detection matching time period can be used as the partial discharge detection time period. In the partial discharge detection time period, infrared images are first used to determine whether there is a suspected partial discharge. When there is a suspected partial discharge, the full amount of partial discharge detection data source is used to perform partial discharge detection in the partial discharge detection matching time period with the fewest overlapping switchgear.

[0037] Additionally, it should be noted that partial discharge detection is unnecessary when there is no suspected partial discharge. However, when the number of partial discharge detection matching time periods for switchgear is small, it is necessary to further determine whether there are multiple partial discharge detection matching time periods with the number of overclosed switchgear less than the preset overclosed number threshold. If there are multiple partial discharge detection matching time periods with the number of overclosed switchgear less than the preset overclosed number threshold, the first partial discharge detection matching time period with the number of overclosed switchgear less than the preset overclosed number threshold is taken as the partial discharge detection time period. In the partial discharge detection time period, infrared images are first used to determine whether there is suspected partial discharge. If there is suspected partial discharge, partial discharge detection is performed using the full partial discharge detection data source in the partial discharge detection matching time period with the fewest overclosed switchgear.

[0038] Specifically, when there is no partial discharge detection matching period with a number of multiple overclosed switch cabinets less than the preset overclosed number threshold, the partial discharge detection matching period with the fewest number of overclosed switch cabinets is taken as the partial discharge detection period, and partial discharge detection is performed directly using the full partial discharge detection data source.

[0039] Additionally, it should be noted that using infrared images to determine the presence of suspected partial discharge specifically includes: When there is a location in the infrared image where the temperature exceeds a preset temperature threshold, it is determined that there is a suspected partial discharge.

[0040] In addition, partial discharge detection is performed using all partial discharge detection data sources. Based on the partial discharge detection results from different partial discharge detection data sources, abnormal partial discharge detection data sources are identified in the partial discharge detection results. When the number of abnormal partial discharge detection data sources in the partial discharge detection results is greater than 3, it is determined that the switchgear has partial discharge.

[0041] Example 2 In a second aspect, the present invention provides a computer device, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned partial discharge detection method based on multi-source data fusion when running the computer program.

[0042] In another possible embodiment, the method for determining the reliable moment of partial discharge detection of the switchgear is as follows: Based on the historical detection results of the partial discharge signal under the corresponding operating data at the time, determine the number of times the switchgear is successfully identified as being under abnormal partial discharge conditions under the operating data. Based on the number of successful identifications, determine whether the moment is a reliable moment for partial discharge detection of the switchgear.

[0043] It should be noted that when the number of successful identifications exceeds the preset threshold for the number of successful identifications, the time is determined to be the reliable time for partial discharge detection of the switchgear.

[0044] Example 3 Optionally, if it is determined that the first detection strategy cannot be used for partial discharge detection and processing, specifically including: S31 takes the period after the reliable partial discharge detection period within the future preset period as the target analysis period, and determines the number of reliable partial discharge detection times for different switch cabinets based on the distribution data of the reliable partial discharge detection times for different switch cabinets in the target analysis period. It should be noted that before proceeding to the next step, it is also necessary to determine whether there are switchgear units that lack reliable partial discharge detection moments, and whether the number of reliable partial discharge detection moments for different switchgear units meets the requirements. Specifically, this includes the following two scenarios: Scenario 1: When there is a switch cabinet that does not have a reliable moment for partial discharge detection, it is determined that the first detection strategy cannot be used for partial discharge detection.

[0045] Scenario 2: When there is no switchgear without a reliable partial discharge detection moment, if the number of reliable partial discharge detection moments for different switchgears all meet the requirements, that is, if the number of reliable partial discharge detection moments for different switchgears is relatively large, then it can be determined that the first detection strategy can be used for partial discharge detection processing.

[0046] Only when neither Situation 1 nor Situation 2 meets the requirements is it necessary to verify the determination of the deviation switchgear.

[0047] S32 determines the verification deviation switchgear based on the number of reliable partial discharge detection times for different switchgears, and determines the detection deviation value of different verification deviation switchgears based on the overlap data between the reliable partial discharge detection times of different verification deviation switchgears and other verification deviation switchgears. It should be noted that before proceeding to the next step, it is also necessary to determine whether the number of check deviation switchgear meets the requirements, and whether the number of check deviation switchgear with deviation values ​​greater than the preset deviation threshold meets the requirements. The threshold method can be used to determine whether the requirements are met.

[0048] In one possible embodiment, the moment when the number of overlaps with other verification deviation switch cabinets is greater than a preset overlap threshold is first taken as the moment of reliable partial discharge detection. The detection matching value is determined by multiplying the difference between the reliable moment of partial discharge detection of the verification deviation switch cabinet and the moment of abnormal overlap with a preset scaling factor. The detection deviation value is determined based on the difference between 1 and the detection matching value.

[0049] Furthermore, it is understandable that when the number of switchgear for verifying deviations is insufficient, i.e. when the number of switchgear for verifying deviations is large, the reliability of verification processing is also low. Therefore, it can be directly determined that the first detection strategy cannot be used for partial discharge detection processing.

[0050] Furthermore, if there are a large number of switchgear with a detection deviation value greater than 0.3, it can be determined directly that the first detection strategy cannot be used for partial discharge detection. Only when there are a small number of switchgear with a detection deviation value greater than 0.3, it is necessary to proceed to the next step to determine the verification deviation factor.

[0051] S33 determines the verification deviation factor based on the number of verification deviation switchgear and the detection deviation values ​​of different verification deviation switchgear, and determines whether the first detection strategy can be used for partial discharge detection processing through the verification deviation factor.

[0052] In one possible embodiment, the verification deviation factor can be determined by multiplying the number of verification deviation switchgears by the average detection deviation value of different verification deviation switchgears. Specifically, when the verification deviation factor is greater than the preset deviation factor threshold, the first detection strategy cannot be used for partial discharge detection.

[0053] Example 4 In another possible embodiment, the method for determining the reliable period for partial discharge detection within the unit time period is as follows: S21 determines the number of reliable partial discharge detection times for different switchgear within the unit time period based on the distribution data of the reliable partial discharge detection times of the switchgear within the unit time period, and uses them as the matching detection times. It should be noted that in the above steps, it is also necessary to determine whether the number of switchgear without matching detection time meets the requirements and whether the average number of matching detection times of different switchgear meets the requirements. Specifically, this is determined by using a threshold method.

[0054] It is understandable that if the number of switchgear that does not have a matching detection time does not meet the requirements, since there are a large number of switchgear that meet the detection reliability requirements, i.e., the number is too large, it can be directly determined that the unit time period does not belong to the reliable time period for partial discharge detection. Furthermore, even if the number of switchgear without matching detection times meets the requirements, if the average number of matching detection times for different switchgear is too small, since the reliability of partial discharge detection for different switchgear meets the requirements, it can be directly determined that the unit time period does not belong to the reliable time period for partial discharge detection. Only when the average number of matching detection times for different switchgear is not too small is it necessary to determine the overlapping detection time.

[0055] S22 uses the overlap data of the matching detection times of different switch cabinets to determine the number of overlaps in the matching detection times of switch cabinets at different times, and determines the overlap detection time based on the number of overlaps in the matching detection times of switch cabinets at different times. Understandably, before proceeding to the next step, it is necessary to determine whether the number of overlapping detection moments meets the requirements. Specifically, when the number of overlapping detection moments in the unit time period is small, infrared detection cannot accurately locate switchgear with partial discharge abnormalities. Therefore, in the above time period, it can be directly determined that the unit time period does not belong to the reliable time period for partial discharge detection.

[0056] Furthermore, it should be noted that, even if the number of overlapping detection times meets the requirements, it is still necessary to further determine whether the matching detection times of all switch cabinets fall within the overlapping detection times of the unit time period. If there are a large number of switch cabinets whose matching detection times do not fall within the overlapping detection times, that is, if the number of switch cabinets that do not fall within the overlapping detection times does not meet the requirements, it can also be directly determined that the unit time period does not belong to the reliable period for partial discharge detection. In one possible embodiment, the requirement is determined by a threshold.

[0057] S23 determines the partial discharge detection reliability value for the unit time period based on the number and distribution data of the overlapping detection times, and determines whether the unit time period is a reliable partial discharge detection period based on the partial discharge detection reliability value.

[0058] Furthermore, it should be noted that in one possible embodiment, the reliability value of partial discharge detection is determined based on the proportion of overlapping detection times in the unit time period, and its value ranges from 0 to 1. When the reliability value of partial discharge detection is less than a certain threshold, it is determined that the unit time period does not belong to the reliable time period of partial discharge detection. When the reliability value of partial discharge detection is not less than a certain threshold, the unit time period with the largest reliability value of partial discharge detection is taken as the reliable time period of partial discharge detection.

[0059] S3, based on the distribution data of the reliable partial discharge detection times of different switchgear after the reliable partial discharge detection period, determines that the first detection strategy cannot be used for partial discharge detection processing, and then proceeds to the next step. Specifically, determining that the first detection strategy cannot be used for partial discharge detection and processing includes: The period following the reliable partial discharge detection period within the future preset time period is taken as the target analysis period. Based on the distribution data of the reliable partial discharge detection times of different switchgear in the target analysis period, the number of reliable partial discharge detection times of different switchgear is determined. The verification deviation switchgear is determined based on the number of reliable partial discharge detection times for different switchgear. Based on the number of the verification deviation switchgear, it can be determined whether the first detection strategy can be used for partial discharge detection.

[0060] Furthermore, when the number of the verification deviation switchgear is less than the preset threshold for the number of verification switchgear, it is determined that the first detection strategy can be used for partial discharge detection.

[0061] It should be noted that the first detection strategy first uses infrared images to screen switchgear with suspected partial discharge, and performs partial discharge detection using full partial discharge detection data sources at the corresponding reliable partial discharge detection time for switchgear with suspected partial discharge. For switchgear that does not belong to the category of suspected partial discharge, there is no need to perform partial discharge detection processing.

[0062] It is understood that the full range of partial discharge detection data sources are derived from acoustic imaging, infrared thermal imaging temperature measurement, ultra-high frequency / high frequency current partial discharge, ultrasonic waves, and transient ground waves for partial discharge detection.

[0063] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0064] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0065] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A partial discharge detection method based on multi-source data fusion, characterized in that, Specifically, it includes: Based on the load forecast data of the switchgear, the operating data of the switchgear at different times in a future preset period are determined, and the reliable time for partial discharge detection of different switchgear is determined based on the historical detection results of partial discharge signals under different operating data. Determine the distribution data of reliable partial discharge detection times for switchgear in different unit time periods within a future preset time period, and determine the reliable partial discharge detection time periods in the unit time period based on the distribution data; Based on the distribution data of the reliable partial discharge detection times of different switchgear after the reliable partial discharge detection period, if it is determined that the first detection strategy cannot be used for partial discharge detection processing, proceed to the next step. The distribution data of the reliable partial discharge detection time of different switchgear in different unit time periods are used to determine the partial discharge detection matching time period of different switchgear. Based on the distribution data of the partial discharge detection matching time period and the overlap data with other switchgear in different partial discharge detection matching time periods, the detection method and partial discharge detection time period of different switchgear are determined.

2. The partial discharge detection method based on multi-source data fusion as described in claim 1, characterized in that, The load forecast data for the switchgear is determined based on the forecast results of the power consumption data of the power equipment controlled by the switchgear.

3. The partial discharge detection method based on multi-source data fusion as described in claim 1, characterized in that, The predicted power consumption data of the power equipment is determined based on the average value of the historical power consumption data of the power equipment in different time periods.

4. The partial discharge detection method based on multi-source data fusion as described in claim 1, characterized in that, The preset time period is determined based on the number of switchgear units tested, and specifically based on the partial discharge analysis time and the number of switchgear units tested for different switchgear units.

5. The partial discharge detection method based on multi-source data fusion as described in claim 1, characterized in that, The operating data includes operating voltage and operating current.

6. The partial discharge detection method based on multi-source data fusion as described in claim 1, characterized in that, The method for determining the reliable period for partial discharge detection within the unit time period is as follows: Based on the distribution data of reliable partial discharge detection times of switchgear within the unit time period, the number of reliable partial discharge detection times of different switchgear within the unit time period is determined and used as the matching detection times. By using the overlap data of matching detection times of different switchgear, the number of overlap times of matching detection times of switchgear at different times is determined. By measuring the number of overlapping detection times of the switchgear at different times, it is determined whether the unit time period is a reliable time period for partial discharge detection.

7. The partial discharge detection method based on multi-source data fusion as described in claim 1, characterized in that, If it is determined that the first detection strategy cannot be used for partial discharge detection and processing, specifically including: The period following the reliable partial discharge detection period within the future preset time period is taken as the target analysis period. Based on the distribution data of the reliable partial discharge detection times of different switchgear in the target analysis period, the number of reliable partial discharge detection times of different switchgear is determined. The verification deviation switchgear is determined based on the number of reliable partial discharge detection times for different switchgear. Based on the number of the verification deviation switchgear, it can be determined whether the first detection strategy can be used for partial discharge detection.

8. The partial discharge detection method based on multi-source data fusion as described in claim 1, characterized in that, The first detection strategy is to first use infrared images to screen switchgear with suspected partial discharge, and then perform partial discharge detection using full partial discharge detection data sources for switchgear with suspected partial discharge at the corresponding reliable partial discharge detection time. For switchgear that does not belong to the category of suspected partial discharge, there is no need to perform partial discharge detection processing.

9. The partial discharge detection method based on multi-source data fusion as described in claim 1, characterized in that, The method for determining the partial discharge detection method of the switchgear is as follows: The number of partial discharge detection matching time periods of the switchgear is determined based on the distribution data of the partial discharge detection matching time periods of the switchgear. Based on the overlap data between the partial discharge detection matching time period of the switchgear and the partial discharge detection matching time period of other switchgear, determine the number of switchgears with overlapping partial discharge detection matching time periods for different partial discharge detection matching time periods. The method for detecting partial discharge of the switchgear is determined by the number of partial discharge detection matching time periods of the switchgear and the number of overlapping switchgears with different partial discharge detection matching time periods.

10. A computer device, comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a partial discharge detection method based on multi-source data fusion as described in any one of claims 1-9.

Images