Detection data abnormity identification method and system for distribution network line

Abstract

The invention provides a detection data abnormity identification method and system for a distribution network line, and belongs to the technical field of power systems, and the method specifically comprises the steps: taking the deviation conditions of operation data in different unit time periods and rated operation data of detection equipment, and power waveform distortion data as the basis, determining suspected supersaturation moments in adjacent time periods, acquiring distribution interval data of the suspected supersaturation moments, and determining whether the abnormal probability of the detection data of the detection equipment meets the requirement according to the distance duration between the different suspected supersaturation moments and the current moment. On the basis of the prediction result of the operation data in the current time period and the power waveform distortion data in the adjacent time period, the anomaly detection processing method of the detection equipment is determined, and the anomaly detection processing accuracy is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, and particularly relates to a method and system for identifying abnormal detection data for distribution network lines. Background Art

[0002] In order to detect and process distribution network lines and power equipment in the distribution network lines, various types of Internet of Things (IoT) detection devices are often set up in the distribution network lines. Due to the influence of the external environment and the reliability of the devices themselves, the detection data will inevitably deviate.

[0003] In order to identify and process abnormal detection data, in the invention patent application CN202111248366.7, "An Abnormal Monitoring System Applying Big Data to Smart Grid", cross-verification is performed on abnormal base station nodes and cross-base station nodes based on base station detection data and cross-detection data to perform abnormal monitoring and judgment, realizing the identification and processing of abnormal data. However, the following technical problems exist in the above technical solution: For the CT in the distribution network line, once there is an abnormality in the distortion degree of the operating power, transmission current, or voltage in the distribution network line, it will inevitably cause the CT to become oversaturated, thus affecting the accuracy of the measurement results within a certain period. Therefore, if the above factors are ignored, the reliability of the abnormal identification results of the detection data cannot be guaranteed.

[0004] In view of the above technical problems, specifically, the present application provides a method and system for identifying abnormal detection data for distribution network lines. Summary of the Invention

[0005] To achieve the object of the present invention, the present invention adopts the following technical solutions: Specifically, in a first aspect, the present application provides a system for identifying abnormal detection data for distribution network lines, specifically including: An operating data prediction module, a distortion data acquisition module, and a detection method output module; Wherein the operating data prediction module is responsible for determining the prediction result of the operating data of the distribution network line in the current period; The distortion data acquisition module is responsible for determining the power waveform distortion data in the adjacent period; The detection method output module is responsible for determining the abnormal detection processing method of the detection device based on the prediction result of the operating data in the current period and the power waveform distortion data in the adjacent period.

[0006] A further technical solution lies in that the prediction result of the operating data includes the predicted current of the distribution network line at different times.

[0007] A further technical solution is that the adjacent time period is a time period whose interval duration from the current time period is within a preset time period range.

[0008] A further technical solution is that the power waveform distortion data in the adjacent time period includes the current waveform distortion rates at different moments in the adjacent time period.

[0009] A further technical solution is to determine the processing method for anomaly detection of the detection device, which specifically includes: Determine the reference distortion rate of the current time period based on the average value of the current waveform distortion rates at different moments in the adjacent time period; Based on the reference distortion rate and the predicted currents at different moments, determine the fluctuation range of the predicted currents at different moments, and use the fluctuation range and the rated current of the detection device to determine the moments when the fluctuation range is greater than the rated current, and take them as the matching fluctuation moments; Determine the comprehensive risk coefficient according to the proportion of the number of the matching fluctuation moments, and use the comprehensive risk coefficient to determine the processing method for anomaly detection of the detection device.

[0010] In a second aspect, the present application provides a method for identifying abnormal detection data for a distribution network line, which is applied to the above-mentioned method for identifying abnormal detection data for a distribution network line, and specifically includes: S1 When it is determined that the historical operation data of the detection device in the distribution network line within the preset operation power range meets the requirements for the oversaturated operation state, proceed to the next step; S2 Obtain the operation data of the distribution network line in the adjacent time period of the current time period, and based on the deviation between the operation data in different unit time periods and the rated operation data of the detection device, as well as the power waveform distortion data, determine the suspected oversaturated moments in the adjacent time period; S3 Obtain the distribution interval data of the suspected oversaturated moments, and combine the distance duration between different suspected oversaturated moments and the current moment. When it is determined that the abnormal probability of the detection data of the detection device meets the requirements, based on the prediction result of the operation data in the current time period and the power waveform distortion data in the adjacent time period, determine the processing method for anomaly detection of the detection device.

[0011] The beneficial effects of the present invention are as follows: Based on the distribution interval data of suspected supersaturation moments and the distance durations between different suspected supersaturation moments and the current moment, determine whether the abnormal probability of the detection data of the detection device meets the requirements. Thus, not only the differences in the superimposed risks of supersaturation caused by the differences in the distribution interval data of suspected supersaturation moments are considered, but also the distance durations between different suspected supersaturation moments and the current moment are further combined, realizing the comprehensive consideration of the differences in the influence degrees of different suspected supersaturation moments on the current moment, ensuring the accuracy of the evaluation and processing of the abnormal probability of the detection data of the detection device, and also laying a foundation for generating a differential abnormal detection processing method according to the differences in abnormal probabilities.

[0012] Based on the prediction results of the operation data in the current time period and the power waveform distortion data in the adjacent time periods, determine the abnormal detection processing method of the detection device, realizing the assessment of the risk of supersaturation of the detection device from the deviation between the operation data and the rated operation data of the detection device and the magnitude of the power waveform distortion risk, ensuring the accuracy of the detection and processing of the detection device with a relatively high supersaturation risk, and at the same time improving the detection and processing efficiency of the detection device with a relatively low supersaturation risk.

[0013] A further technical solution is that the preset operation power range is an operation power range that coincides with the rated operation current of the detection device.

[0014] A further technical solution is that the historical operation data includes the historical operation times in the preset operation power range and the operation durations of different historical operation times.

[0015] A further technical solution is that determining that the supersaturated operation state of the detection device meets the requirements specifically includes: Based on the historical operation data of the detection device in the preset operation power range in the distribution network line, determine the historical operation times of the detection device in the preset operation power range; Based on the interval durations between different historical operation times, determine the aggregated operation times among the historical operation times; Based on the historical operation times and the proportion of the aggregated operation times in the historical operation times, determine the historical supersaturation risk coefficient of the detection device, and use the historical supersaturation risk coefficient to determine whether the supersaturated operation state of the detection device meets the requirements.

[0016] A further technical solution is that the aggregated operation times are the historical operation times with the interval durations between adjacent historical operation times within a preset duration range.

[0017] A further technical solution is that the method for determining the abnormal detection processing method of the detection device is: Determine the deviation amount between the operating current at different times in the current period and the rated operating current of the detection device based on the prediction result of the operating data in the current period, and use the deviation amount to determine the oversaturation attention time in the current period; Determine the current waveform distortion time in the adjacent period based on the power waveform distortion data in the adjacent period; Determine the comprehensive risk coefficient of the detection device according to the average value of the quantity proportion of the oversaturation attention time and the quantity proportion of the current waveform distortion time, and use the comprehensive risk coefficient to determine the processing method for the abnormal detection of the detection device.

[0018] A further technical solution lies in that using the comprehensive risk coefficient to determine the processing method for the abnormal detection of the detection device specifically includes: When the comprehensive risk coefficient of the detection device is greater than the preset risk coefficient value, use the preset abnormal detection method to perform abnormal identification processing on the detection data of the detection device; When the comprehensive risk coefficient of the detection device is not greater than the preset risk coefficient value: When the comprehensive risk coefficient of the detection device is less than the preset coefficient threshold, it is determined that there is no need to perform abnormal detection on the detection device; When the comprehensive risk coefficient of the detection device is not less than the preset coefficient threshold, use the second preset abnormal detection method to perform abnormal identification processing on the detection data of the detection device.

[0019] A further technical solution lies in that the preset duration is greater than the second preset duration.

[0020] On the other hand, the present invention provides a computer system, including: a memory and a processor connected by communication, and a computer program stored on the memory and capable of running on the processor, wherein when the processor runs the computer program, it executes the above-mentioned method for abnormal identification of detection data for a distribution network line.

[0021] Other features and advantages will be described in the following specification, and part of them will become obvious from the specification or be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0022] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes a detailed description as follows. Description of the Drawings

[0023] By referring to the accompanying drawings and describing its exemplary embodiments in detail, the above and other features and advantages of the present invention will become more obvious.

[0024] Figure 1 It is a framework diagram of a detection data anomaly recognition system for a distribution network line; Figure 2 It is a flowchart of a method for detecting data anomaly recognition of a distribution network line; Figure 3 It is a flowchart for determining that the oversaturated operating state of the detection device meets the requirements; Figure 4 It is a flowchart of a method for determining the historical oversaturation risk coefficient of the detection device. Detailed implementation mode

[0025] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote the same or similar structures, and thus their detailed description will be omitted.

[0026] The terms "a", "an", "the", and "said" are used to denote the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to mean an open inclusion and mean that there may be additional elements / components / etc. in addition to the listed elements / components / etc.

[0027] Example 1 As Figure 1 shown, the present application provides a detection data anomaly recognition system for a distribution network line, specifically including: An operating data prediction module, a distortion data acquisition module, and a detection method output module; Wherein the operating data prediction module is responsible for determining the prediction result of the operating data of the distribution network line in the current period; The distortion data acquisition module is responsible for determining the power waveform distortion data in the adjacent period; The detection method output module is responsible for determining the anomaly detection processing method of the detection device based on the prediction result of the operating data in the current period and the power waveform distortion data in the adjacent period.

[0028] Furthermore, the prediction result of the operating data includes the predicted current of the distribution network line at different times.

[0029] It should be noted that the adjacent period is a period whose interval duration from the current period is within a preset duration range.

[0030] Specifically, the power waveform distortion data in the adjacent time period includes the current waveform distortion rates at different moments in the adjacent time period.

[0031] It should be noted that the method for determining the abnormal detection of the detection device specifically includes: Determine the reference distortion rate of the current time period based on the average value of the current waveform distortion rates at different moments in the adjacent time period; Based on the reference distortion rate and the predicted current at different moments, determine the fluctuation range of the predicted current at different moments, and use the fluctuation range and the rated current of the detection device to determine the moments when the fluctuation range is greater than the rated current, and use them as the matching fluctuation moments; Determine the comprehensive risk coefficient according to the proportion of the number of the matching fluctuation moments, and use the comprehensive risk coefficient to determine the method for abnormal detection of the detection device.

[0032] Embodiment 2 Second, as Figure 2 shown, the present application provides a method for identifying abnormal detection data for a distribution network line, which is applied to the above-mentioned method for identifying abnormal detection data for a distribution network line, and specifically includes: S1 When determining that the historical operation data of the detection device in the preset operation power range meets the requirements for the oversaturated operation state, proceed to the next step; S2 Obtain the operation data of the adjacent time period of the current time period of the distribution network line, and determine the suspected oversaturated moments in the adjacent time period based on the deviation between the operation data in different unit time periods and the rated operation data of the detection device and the power waveform distortion data; S3 Obtain the distribution interval data of the suspected oversaturated moments, and combine the distance duration between different suspected oversaturated moments and the current moment. When determining that the abnormal probability of the detection data of the detection device meets the requirements, determine the method for abnormal detection of the detection device based on the prediction result of the operation data in the current time period and the power waveform distortion data in the adjacent time period.

[0033] Furthermore, the preset operation power range is an operation power range that coincides with the rated operation current of the detection device.

[0034] Specifically, the historical operation data includes the historical operation times in the preset operation power range and the operation durations of different historical operation times.

[0035] It should be noted that, as Figure 3 shown, determining that the oversaturated operation state of the detection device meets the requirements specifically includes: Determine the historical operation times of the detection device within the preset operating power range based on the historical operation data of the detection device in the distribution network line within the preset operating power range; Determine the aggregated operation times among the historical operation times based on the interval duration between different historical operation times; Determine the historical oversaturation risk coefficient of the detection device based on the historical operation times and the proportion of the aggregated operation times in the historical operation times, and use the historical oversaturation risk coefficient to determine whether the oversaturated operation state of the detection device meets the requirements.

[0036] Further, the aggregated operation times are the historical operation times with the interval duration between adjacent historical operation times within the preset duration range.

[0037] It should be noted that as Figure 4 shown, the method for determining the historical oversaturation risk coefficient of the detection device is: Determine the basic weight value based on the preset weight value corresponding to the historical operation times; Determine the historical oversaturation risk coefficient of the detection device according to the average value of the basic weight value and the proportion of the aggregated operation times in the historical operation times.

[0038] Further, the value range of the historical oversaturation risk coefficient of the detection device is between 0 and 1. When the historical oversaturation risk coefficient of the detection device is greater than the preset insurance risk coefficient threshold, it is determined that the oversaturated operation state of the detection device does not meet the requirements.

[0039] It should be noted that when the oversaturated operation state of the detection device does not meet the requirements, the preset anomaly detection method is used to perform anomaly identification processing on the detection data of the detection device.

[0040] Optionally, determining that the oversaturated operation state of the detection device meets the requirements specifically includes: S11 Determine the historical operation times of the detection device within the preset operating power range based on the historical operation data of the detection device in the distribution network line within the preset operating power range, and combine the operation duration of different historical operation times to determine the basic oversaturation risk coefficient of the detection device; S12 Determine the aggregated operation times among the historical operation times based on the interval duration between different historical operation times, and determine the oversaturation superposition risk coefficient of the detection device based on the interval duration between different aggregated operation times and adjacent historical operation times, different aggregated operation times, and the operation duration of adjacent historical operation times; S13 determines the historical oversaturation risk coefficient of the detection device based on the basic oversaturation risk coefficient and the oversaturation superposition risk coefficient of the detection device, and uses the historical oversaturation risk coefficient to determine whether the oversaturated operating state of the detection device meets the requirements.

[0041] It can be understood that the historical oversaturation risk coefficient of the detection device is the sum of the basic oversaturation risk coefficient and the oversaturation superposition risk coefficient of the detection device.

[0042] Optionally, the above step S11 includes the following content: S111 uses the historical operation data of the detection device in the power distribution line within the preset operation power range to determine the historical operation times of the detection device within the preset operation power range. When the historical operation times do not meet the requirements, it is determined that the oversaturated operating state of the detection device does not meet the requirements. When the historical operation times meet the requirements, it proceeds to step S112; S112 is based on the operation durations of different historical operation times. The sum of the operation durations of different historical operation times is used as the cumulative operation duration. When the cumulative operation duration does not meet the requirements, it is determined that the oversaturated operating state of the detection device does not meet the requirements. When the cumulative operation duration meets the requirements, it proceeds to step S113; S113 uses the historical operation times with operation durations greater than the preset operation duration as the risk operation times. When there are risk operation times, it proceeds to step S114. When there are no risk operation times, it proceeds to step S115; S114 When the risk operation times are greater than the preset risk operation times threshold, it is determined that the oversaturated operating state of the detection device does not meet the requirements. When the risk operation times are not greater than the preset risk operation times threshold, it proceeds to step S115; S115 determines the basic oversaturation risk coefficient of the detection device based on the historical operation times of the detection device within the preset operation power range and the operation durations of different historical operation times. When the basic oversaturation risk coefficient of the detection device is within the preset oversaturation risk coefficient range, it is determined that the oversaturated operating state of the detection device meets the requirements. When the basic oversaturation risk coefficient of the detection device is not within the preset oversaturation risk coefficient range, it proceeds to step S12.

[0043] Optionally, the above step S12 includes the following content: S121 determines the aggregated operation times in the historical operation times based on the interval durations between different historical operation times. When the aggregated operation times do not meet the requirements, it is determined that the oversaturated operating state of the detection device does not meet the requirements. When the aggregated operation times meet the requirements, it proceeds to step S122; S122 determines the superposition risk coefficient of different aggregation operation times based on the interval duration between different aggregation operation times and adjacent historical operation times, different aggregation operation times, and the operation duration of adjacent historical operation times. When there are aggregation operation times with superposition risk coefficients not meeting the requirements, it proceeds to step S123; when there are no aggregation operation times with superposition risk coefficients not meeting the requirements, it proceeds to step S124; S123 When the aggregation operation times with superposition risk coefficients not meeting the requirements do not meet the requirements, it determines that the oversaturated operation state of the detection device does not meet the requirements. When the aggregation operation times with superposition risk coefficients not meeting the requirements meet the requirements, it proceeds to step S124; S124 determines the oversaturated superposition risk coefficient of the detection device based on the interval duration between different aggregation operation times and adjacent historical operation times, different aggregation operation times, and the operation duration of adjacent historical operation times. When the oversaturated superposition risk coefficient of the detection device is within the preset superposition risk coefficient range, it proceeds to step S125; when the oversaturated superposition risk coefficient of the detection device is not within the preset superposition risk coefficient range, it proceeds to step S13; S125 When the basic oversaturation risk coefficient of the detection device is greater than the preset basic risk coefficient threshold, it determines that the oversaturated operation state of the detection device does not meet the requirements. When the basic oversaturation risk coefficient of the detection device is not greater than the preset basic risk coefficient threshold, it proceeds to step S13.

[0044] Further, the adjacent time period is a time period whose interval duration from the current time period is within a preset time period range.

[0045] It should be noted that the deviation situation from the rated operation data of the detection device includes the deviation amount of the operating current at different moments within a unit time period from the rated operating current of the detection device.

[0046] Specifically, the power waveform distortion data includes the current waveform distortion moments within a unit time period and the current waveform distortion rate at the current waveform distortion moments.

[0047] It can be understood that the method for determining the suspected oversaturated moments in the adjacent time period is as follows: Taking the unit time period closest to the moment as the reference unit time period, based on the deviation amount of the operating current at different moments within the reference unit time period from the rated operating current of the detection device, determining the proportion of the number of moments with deviation amounts within the preset deviation amount range within the reference unit time period, and taking it as the deviation moment number proportion; Based on the power waveform distortion data, determining the proportion of the number of current waveform distortion moments within the reference unit time period; Determine the basic risk coefficient at the moment based on the deviation rate between the operating current and the rated operating current at that moment and the average value of the current waveform distortion rate. Determine the weighted sum of risk coefficients at that moment through the proportion of the number of deviation moments, the proportion of the number of current waveform distortion moments, and the weights of the basic risk coefficient, and use the weighted sum of risk coefficients to determine whether that moment is a suspected oversaturation moment.

[0048] Specifically, when the weighted sum of risk coefficients at that moment is greater than the preset weight threshold, it is determined that that moment is a suspected oversaturation moment.

[0049] Optionally, the method for determining the suspected oversaturation moment in the adjacent time period is as follows: Obtain the operating current at that moment. When the deviation rate between the operating current at that moment and the rated operating current is within the preset deviation rate range, it is determined that that moment is a suspected oversaturation moment; When the deviation rate between the operating current at that moment and the rated operating current is not within the preset deviation rate range: Obtain the current waveform distortion rate at that moment. When the current waveform distortion rate at that moment is not greater than the preset distortion rate threshold and the amount of the operating current at that moment less than the rated operating current is greater than the preset current threshold, it is determined that that moment does not belong to the suspected oversaturation moment; When the current waveform distortion rate at that moment is greater than the preset distortion rate threshold or the amount of the operating current at that moment less than the rated operating current is not greater than the preset current threshold: Based on the current waveform distortion rate at that moment and the deviation rate between the operating current at that moment and the rated operating current, determine the basic risk coefficient at that moment. When the basic risk coefficient at that moment does not meet the requirements, it is determined that that moment is a suspected oversaturation moment; When the basic risk coefficient at that moment meets the requirements: Take the unit time period closest to that moment as the reference unit time period. Based on the deviation amount between the operating current at different moments in the reference unit time period and the rated operating current of the detection device, determine the proportion of the number of moments within the preset deviation amount range in the reference unit time period, and use it as the proportion of the number of deviation moments; Based on the power waveform distortion data, determine the proportion of the number of current waveform distortion moments in the reference unit time period. When either the proportion of the number of deviation moments or the proportion of the number of current waveform distortion moments does not meet the requirements, it is determined that that moment is a suspected oversaturation moment; When both the proportion of the number of deviation moments and the proportion of the number of current waveform distortion moments meet the requirements: Determine the weight sum of the risk coefficients of the moments by the weight sum of the proportion of the number of deviation moments, the proportion of the number of current waveform distortion moments, and the basic risk coefficient, and use the weight sum of the risk coefficients to determine whether the moment is a suspected supersaturation moment.

[0050] Specifically, determining that the abnormal probability of the detection data of the detection device meets the requirements specifically includes: Using the distribution interval data of the suspected supersaturation moments to determine the number of suspected supersaturation moments in the adjacent time period; According to the interval duration between different suspected supersaturation moments and adjacent suspected supersaturation moments, and the interval duration between the suspected supersaturation moment and the current moment, determine the supersaturation influence coefficients of different suspected supersaturation moments; Determine the abnormal coefficient of the detection data of the detection device by the sum of the supersaturation influence coefficients of different suspected supersaturation moments, and use the abnormal coefficient of the detection data to determine whether the abnormal probability of the detection data of the detection device meets the requirements.

[0051] Further, the supersaturation influence coefficient of the suspected supersaturation moment is determined according to the average value of the preset superposition risk coefficient corresponding to the interval duration with the adjacent suspected supersaturation moment and the preset interference risk coefficient corresponding to the interval duration between the suspected supersaturation moment and the current moment.

[0052] In addition, it should be noted that when the abnormal coefficient of the detection data of the detection device is greater than the preset data abnormal coefficient threshold, it is determined that the abnormal probability of the detection data of the detection device does not meet the requirements.

[0053] Further, when the abnormal probability of the detection data of the detection device does not meet the requirements, use the preset abnormal detection method to perform abnormal identification processing on the detection data of the detection device.

[0054] Optionally, determining that the abnormal probability of the detection data of the detection device meets the requirements specifically includes: Using the distribution interval data of the suspected supersaturation moments to determine the number of suspected supersaturation moments in the adjacent time period. When the number of suspected supersaturation moments in the adjacent time period does not meet the requirements, use the preset abnormal detection method to perform abnormal identification processing on the detection data of the detection device; When the number of suspected supersaturation moments in the adjacent time period meets the requirements: When the number of suspected supersaturation moments in the adjacent time period is less than the preset number of supersaturation moments, it is determined that the abnormal probability of the detection data of the detection device meets the requirements; When the number of suspected supersaturation moments in the adjacent time period is not less than the preset number of supersaturation moments: Determine the suspected supersaturation moments with the interval durations between different suspected supersaturation moments and the current moment within the preset interval duration range, and use them as the supersaturation influence moments. When the number of the supersaturation influence moments does not meet the requirements, use the preset anomaly detection method to perform anomaly identification processing on the detection data of the detection device; When the number of the supersaturation influence moments meets the requirements: Based on the interval durations between different adjacent supersaturation influence moments and the number of supersaturation influence moments, determine the influence coefficient evaluation value. When the influence coefficient evaluation value does not meet the requirements, use the preset anomaly detection method to perform anomaly identification processing on the detection data of the detection device; When the influence coefficient evaluation value meets the requirements: According to the interval durations between different suspected supersaturation moments and adjacent suspected supersaturation moments, and the interval durations between suspected supersaturation moments and the current moment, determine the supersaturation influence coefficients of different suspected supersaturation moments. When the number of suspected supersaturation moments with the supersaturation influence coefficients within the preset influence coefficient interval does not meet the requirements, use the preset anomaly detection method to perform anomaly identification processing on the detection data of the detection device; When the number of suspected supersaturation moments with the supersaturation influence coefficients within the preset influence coefficient interval meets the requirements: Determine the detection data anomaly coefficient of the detection device through the sum of the supersaturation influence coefficients of different suspected supersaturation moments, and use the detection data anomaly coefficient to determine whether the anomaly probability of the detection data of the detection device meets the requirements.

[0055] Furthermore, the prediction result of the operation data in the current period is determined according to the weather data in the current period and the load prediction model.

[0056] It can be understood that the method for determining the processing method of the anomaly detection of the detection device is: Based on the prediction result of the operation data in the current period, determine the deviation amount between the operating current at different moments in the current period and the rated operating current of the detection device, and use the deviation amount to determine the supersaturation attention moments in the current period; Based on the power waveform distortion data in the adjacent period, determine the current waveform distortion moments in the adjacent period; According to the average value of the proportion of the number of supersaturation attention moments and the proportion of the number of current waveform distortion moments, determine the comprehensive risk coefficient of the detection device, and use the comprehensive risk coefficient to determine the processing method of the anomaly detection of the detection device.

[0057] Furthermore, using the comprehensive risk coefficient to determine the processing method of the anomaly detection of the detection device specifically includes: When the comprehensive risk coefficient of the detection device is greater than the preset risk coefficient value, the abnormal identification process of the detection data of the detection device is performed by using a preset abnormal detection method; When the comprehensive risk coefficient of the detection device is not greater than the preset risk coefficient value: When the comprehensive risk coefficient of the detection device is less than the preset coefficient threshold, it is determined that there is no need to perform abnormal detection on the detection device; When the comprehensive risk coefficient of the detection device is not less than the preset coefficient threshold, the abnormal identification process of the detection data of the detection device is performed by using a second preset abnormal detection method.

[0058] It should be noted that the preset abnormal detection method is to use the detection data within a preset time period adjacent to the moment as the input quantity, and use a preset abnormal identification model to perform the abnormal identification process of the detection data at the moment.

[0059] Furthermore, the second preset abnormal detection method is to use the detection data within a second preset time period adjacent to the oversaturated attention moment as the input quantity, and use a preset abnormal identification model to perform the abnormal identification process of the detection data at the oversaturated attention moment.

[0060] Specifically, the preset time period is greater than the second preset time period.

[0061] Optionally, the method for determining the processing method of the abnormal detection of the detection device is: Based on the prediction results of the operation data in the current time period, determine the deviation amount between the operating current at different moments in the current time period and the rated operating current of the detection device, and use the deviation amount to determine the oversaturated attention moment in the current time period; Based on the deviation amount between the operating current at the oversaturated attention moment in the current time period and the rated operating current of the detection device and the interval between different adjacent oversaturated attention moments, determine the predicted risk coefficient in the current time period; Based on the power waveform distortion data in the adjacent time period, determine the current waveform distortion rate at different moments in the adjacent time period, determine the distortion risk coefficient in the current time period according to the current waveform distortion rate at different moments in the adjacent time period, determine the comprehensive risk coefficient in the current time period based on the predicted risk coefficient and the distortion risk coefficient, and use the comprehensive risk coefficient to determine the processing method of the abnormal detection of the detection device.

[0062] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of devices, equipment, and non-volatile computer storage media, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the corresponding descriptions in the method embodiments.

[0063] The specific embodiments of this specification are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0064] The above description is only for one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, various modifications and changes can be made to one or more embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. A detection data anomaly recognition system for a distribution network line, characterized in that, Specifically include: An operating data prediction module, a distortion data acquisition module, and a detection method output module; Among them, the operating data prediction module is responsible for determining the prediction result of the operating data of the distribution network line in the current period; The distortion data acquisition module is responsible for determining the power waveform distortion data in the adjacent period; The detection method output module is responsible for determining the abnormal detection processing method of the detection device based on the prediction result of the operating data in the current period and the power waveform distortion data in the adjacent period.

2. The detection data anomaly recognition system for distribution network lines according to claim 1, characterized in that The prediction result of the operating data includes the predicted current of the distribution network line at different times.

3. The detection data anomaly recognition system for distribution network lines according to claim 1, characterized in that The power waveform distortion data in the adjacent period includes the current waveform distortion rate at different times in the adjacent period.

4. The detection data anomaly recognition system for distribution network lines according to claim 1, wherein Determining the abnormal detection processing method of the detection device specifically includes: Determining the reference distortion rate of the current period based on the average value of the current waveform distortion rates at different times in the adjacent period; Based on the reference distortion rate and the predicted current at different times, determining the fluctuation range of the predicted current at different times, and using the fluctuation range and the rated current of the detection device to determine the moments when the fluctuation range is greater than the rated current, and taking them as the matching fluctuation moments; Determining the comprehensive risk coefficient according to the proportion of the number of the matching fluctuation moments, and using the comprehensive risk coefficient to determine the abnormal detection processing method of the detection device.

5. A method for identifying abnormal detection data of a distribution network line, which is applied to the method for identifying abnormal detection data of a distribution network line according to any one of claims 1-4, and is characterized in that, Specifically include: Based on the historical operating data of the detection device in the distribution network line within the preset operating power range, when it is determined that the oversaturated operating state of the detection device meets the requirements, proceed to the next step; Obtaining the operating data of the distribution network line in the adjacent period of the current period, and determining the suspected oversaturated moments in the adjacent period based on the deviation of the operating data within different unit periods from the rated operating data of the detection device and the power waveform distortion data; Obtaining the distribution interval data of the suspected oversaturated moments, and combining the distance duration between different suspected oversaturated moments and the current moment, when it is determined that the abnormal probability of the detection data of the detection device meets the requirements, determining the abnormal detection processing method of the detection device based on the prediction result of the operating data in the current period and the power waveform distortion data in the adjacent period.

6. The detection data anomaly recognition method for distribution network lines according to claim 5, characterized in that, The preset operating power range is the operating power range that coincides with the rated operating current of the detection device.

7. The method for identifying abnormal detection data for distribution network lines according to claim 5, wherein, The historical operating data includes the historical operating times within the preset operating power range and the operating durations of different historical operating times.

8. The method for identifying abnormal detection data for a distribution network line according to claim 5, wherein Determining that the oversaturated operating state of the detection device meets the requirements specifically includes: Based on the historical operating data of the detection device in the distribution network line within the preset operating power range, determining the historical operating times of the detection device within the preset operating power range; Determining the aggregated operating times in the historical operating times based on the interval duration between different historical operating times; Determine the historical oversaturation risk coefficient of the detection device based on the historical number of runs and the proportion of the aggregated number of runs in the historical number of runs, and use the historical oversaturation risk coefficient to determine whether the oversaturated operating state of the detection device meets the requirements.

9. The method for identifying abnormal detection data for a distribution network line according to claim 5, characterized in that, The method for determining the processing method of the anomaly detection of the detection device is as follows: Based on the prediction results of the operating data in the current period, determine the deviation amount between the operating current at different times in the current period and the rated operating current of the detection device, and use the deviation amount to determine the oversaturation attention moment in the current period; Based on the power waveform distortion data in the adjacent period, determine the current waveform distortion moment in the adjacent period; Determine the comprehensive risk coefficient of the detection device according to the average value of the proportion of the number of oversaturation attention moments and the proportion of the number of current waveform distortion moments, and use the comprehensive risk coefficient to determine the processing method of the anomaly detection of the detection device.

10. The method for abnormal detection data recognition for distribution network lines according to claim 9, wherein, Using the comprehensive risk coefficient to determine the processing method of the anomaly detection of the detection device specifically includes: When the comprehensive risk coefficient of the detection device is greater than the preset risk coefficient value, use the preset anomaly detection method to perform anomaly recognition processing on the detection data of the detection device; When the comprehensive risk coefficient of the detection device is not greater than the preset risk coefficient value: When the comprehensive risk coefficient of the detection device is less than the preset coefficient threshold, it is determined that there is no need to perform anomaly detection on the detection device; When the comprehensive risk coefficient of the detection device is not less than the preset coefficient threshold, use the second preset anomaly detection method to perform anomaly recognition processing on the detection data of the detection device.

Images