A method and system for evaluating the degree of defect of secondary equipment in a power system

By establishing a knowledge graph of correlation relationships between devices in the power system, evaluating the degree of defects of secondary equipment in the power system, solving the problems of evaluation efficiency and low quality caused by failure to consider equipment correlation in the prior art, and achieving more accurate and comprehensive defect analysis.

CN118917698BActive Publication Date: 2024-12-03GUOSHUI INVESTMENT GRP DIAOBINGSHANFENGDIAN CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411399280.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-09
Publication Date
2024-12-03
Estimated Expiration
2044-10-09

AI Technical Summary

Technical Problem

The prior art fails to fully consider the interrelationship between equipment when evaluating defects of secondary equipment in power system, resulting in low defect handling efficiency and quality, increasing operating risks.

Method used

By obtaining the detection data set of the target device and the associated device, a knowledge graph of the correlation relationship between multiple parameters is established, and analyses are conducted to evaluate the degree of defects of the target device, consider the mutual influence between the devices, and improve judgment accuracy.

Benefits of technology

It improves the accuracy and efficiency of defect evaluation, comprehensively considers the different situations of the target equipment, reduces the errors caused by single data analysis, and realizes targeted analysis and judgment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917698B_ABST
    Figure CN118917698B_ABST
Patent Text Reader

Abstract

The present application discloses a method and system for evaluating the degree of defects in secondary equipment in a power system, and relates to the technical field of equipment defect evaluation. The method includes obtaining and judging the comprehensive judgment results of the target detection data set, the comprehensive judgment results of the auxiliary detection data set one, and the auxiliary detection data set two, which are divided into the comprehensive judgment results of the three being all normal, all abnormal, the comprehensive judgment result of the target detection data set being normal and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two being normal, the comprehensive judgment result of the target detection data set being normal and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two being abnormal, the comprehensive judgment result of the target detection data set being abnormal and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two being normal, and different situations correspond to different defect degree evaluation results. The present invention provides a method and system for evaluating the degree of defects in secondary equipment in a power system, and improves the accuracy of the evaluation results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of equipment defect assessment, and in particular to a method and system for assessing the degree of defects in secondary equipment in a power system. Background Art

[0002] Secondary equipment in power systems refers to low-voltage electrical equipment that monitors, controls, regulates, and protects the operation of primary equipment in power systems, and provides operating conditions or production command signals to operation and maintenance personnel. The evaluation of the degree of defects in secondary equipment in power systems is crucial to ensure the reliability and safety of power systems.

[0003] In the prior art, the defect assessment of secondary equipment only analyzes the data of the equipment to be tested, without considering the influence of the correlation between other equipment. The existence of these problems affects the efficiency and quality of defect handling and increases the operation risk of the power system. Therefore, it is necessary to take corresponding improvement measures to address these deficiencies. Summary of the invention

[0004] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a method and system for evaluating the degree of defects of secondary equipment in a power system.

[0005] In a first aspect, the present application provides a method for evaluating the degree of defects of secondary equipment in a power system, the method comprising:

[0006] Obtain a target detection data set of the target device, an auxiliary detection data set one of the auxiliary device one, and an auxiliary detection data set two of the auxiliary device two; when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all normal, output a first-category target defect assessment result; when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all abnormal, output a second-category target defect assessment result; when the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are both normal, output a third-category target defect assessment result;

[0007] When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the first test situation is output, all the remaining devices to be tested are collected, and a first reference spectrum is established according to the target device, the auxiliary device 1, the auxiliary device 2 and all the remaining devices to be tested. According to the first test situation, a first type of preprocessing spectrum 1 is established, and the first reference spectrum and the first type of preprocessing spectrum 1 are compared and judged to obtain a spontaneous defect pre-determination result;

[0008] According to the spontaneous defect pre-determination result, a first-class pre-processing spectrum 2 and a first-class pre-processing spectrum 3 are established, and the difference between the first reference spectrum and the first-class pre-processing spectrum 2 is extracted by comparison to obtain a difference result 1, and the difference between the first reference spectrum and the second-class pre-processing spectrum 3 is extracted by comparison to obtain a difference result 2, and the difference result 1 and the difference result 2 are compared and judged to obtain a first-class target defect assessment result;

[0009] When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are abnormal, the second test situation is output, and according to the second test situation, the second type of preprocessing spectrum one and the second type of preprocessing spectrum two are established, and the first reference spectrum is respectively compared with the second type of preprocessing spectrum one and the second type of preprocessing spectrum two to obtain the second type of comparison result and the third type of comparison result, and when the overlap between the second type of comparison result and the third type of comparison result is greater than or equal to the preset judgment threshold, the second type of target defect assessment result is output;

[0010] When the overlap between the second-category comparison result and the third-category comparison result is less than the preset judgment threshold, the first-category target defect assessment result is output; when the overlap between the second-category comparison result and the third-category comparison result is greater than or equal to the preset judgment threshold, a second-category preprocessing graph 2 is established, and the second-category preprocessing graph 2 is compared with the second-category preprocessing graph 2 to obtain a fourth-category comparison result; when the overlap between the fourth-category comparison result is less than the preset judgment threshold, the third-category target defect assessment result is output.

[0011] Preferably, a target device is obtained, and based on the target device, auxiliary device 1 and auxiliary device 2 that are most associated with the target device are obtained;

[0012] Respectively detecting all parameter data of the target device, auxiliary device 1 and auxiliary device 2 to obtain a target detection data set, an auxiliary detection data set 1 and an auxiliary detection data set 2;

[0013] Respectively judging the comprehensive abnormal conditions of the target detection data set, the auxiliary detection data set 1 and the auxiliary detection data set 2; when the comprehensive judgment results of the target detection data set, the auxiliary detection data set 1 and the auxiliary detection data set 2 are all normal, judging the defect degree of the target device to be zero, and outputting the first type of target defect assessment result;

[0014] When the comprehensive judgment results of the target detection data set, the auxiliary detection data set 1, and the auxiliary detection data set 2 are all abnormal, the defect degree of the target equipment is determined to be the first level, and the second type of target defect assessment result is output;

[0015] When the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 are both normal, the defect degree of the target equipment is determined to be the second level, and the third type target defect assessment result is output.

[0016] Preferably, when the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the auxiliary device corresponding to one of the abnormal comprehensive judgment results is named as an abnormal device, and the auxiliary device corresponding to one of the normal comprehensive judgment results is named as a normal device, and the first test situation is output;

[0017] Collect all remaining devices to be tested, and establish a knowledge graph of the association relationship between multiple generic parameters contained in the target device, the abnormal device and all remaining devices to be tested, and a knowledge graph of the association relationship between multiple generic parameters contained in the target device, the normal device and all remaining devices to be tested, respectively, when the devices are under abnormal operation and normal operation conditions, and output a first reference graph, in which the abnormal device is located at the association relationship subordinate position of the target device, and all remaining devices to be tested are located at the association relationship subordinate position of the abnormal device;

[0018] According to the first test situation, extract the target item parameter with the largest change amplitude and normal in the target detection data set, extract the first type of abnormal parameter one of the data abnormality in the abnormal device and the first type of remaining abnormal parameter one of the data abnormality in all the remaining devices to be tested;

[0019] Establish a knowledge graph of the association relationship between the target item parameter, the first type of abnormal parameter 1 and the first type of remaining abnormal parameter 1, and output the first type of preprocessing graph 1;

[0020] The first reference spectrum and the first type of preprocessed spectrum are compared to obtain a first type of comparison result. When the overlap of the first type of comparison result is less than a preset judgment threshold, it is preliminarily pre-determined that the defect abnormality of the abnormal equipment is spontaneous, and a spontaneous defect pre-determination result is output.

[0021] Preferably, according to the spontaneous defect pre-determination result, a first type of normal parameter one in which the data in the abnormal device is normal and a first type of remaining normal parameter one in which the data in all remaining devices to be tested are normal are extracted;

[0022] Establish a knowledge graph of the association relationship between the target item parameter, the first type normal parameter 1 and the first type remaining normal parameter 1, and output the first type preprocessing graph 2;

[0023] Extracting the first type of normal parameter 2 of normal data in the normal device;

[0024] Establish a knowledge graph of the association relationship between the target item parameter, the first type normal parameter 2 and the first type remaining normal parameter 1, and output the first type preprocessing graph 3;

[0025] Comparing and extracting the difference between the first reference spectrum and the first type of preprocessed spectrum 2 to obtain a difference result 1, and comparing and extracting the difference between the first reference spectrum and the second type of preprocessed spectrum 3 to obtain a difference result 2, and comparing the difference result 1 and the difference result 2 to obtain a second type of comparison result;

[0026] When the overlap of the second type of comparison results is greater than or equal to the preset judgment threshold, the defect anomaly of the abnormal equipment is finally determined to be spontaneous, and the defect degree of the target equipment is determined to be zero, and the first type of target defect assessment result is output.

[0027] Preferably, when the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the second condition to be tested is output;

[0028] Extracting a second type of abnormal parameter 1 of the data abnormality in the auxiliary detection data set 1;

[0029] Establish a knowledge graph of the association relationship between the target item parameter, the second type of abnormal parameter one and the first type of remaining abnormal parameter one, and output the second type of preprocessing graph one;

[0030] Extracting a second type of abnormal parameter 2 of the data abnormality in the auxiliary detection data set 2;

[0031] Establish a knowledge graph of the association relationship between the target item parameter, the second type of abnormal parameter 2 and the first type of remaining abnormal parameter 1, and output the second type of preprocessing graph 2;

[0032] The first reference spectrum is compared with the second type of preprocessed spectrum one and the second type of preprocessed spectrum two to obtain the second type of comparison results and the third type of comparison results. When the overlap between the second type of comparison results and the third type of comparison results is greater than or equal to the preset judgment threshold, it is determined that the defect anomalies of auxiliary equipment one and auxiliary equipment two are induced by the target equipment, and the defect degree of the target equipment is determined to be the first level, and the second type of target defect assessment result is output.

[0033] Preferably, when the overlap between the second type comparison result and the third type comparison result is less than a preset judgment threshold, it is determined that the defect anomaly of the auxiliary device 1 and the auxiliary device 2 is caused by themselves, and the defect degree of the target device is determined to be zero, and the first type target defect assessment result is output;

[0034] When the overlap degree between the second comparison result and one of the third comparison results is greater than or equal to a preset judgment threshold, the auxiliary device corresponding to one of the results whose overlap degree is greater than or equal to the preset judgment threshold is named as a first pre-judgment device, and the auxiliary device corresponding to one of the results whose overlap degree is less than the preset judgment threshold is named as a second pre-judgment device;

[0035] Establish a knowledge graph of the association relationship between the abnormal multiple category parameters contained in the first pre-judgment device, the second pre-judgment device and all the remaining devices to be tested, and output the second category pre-processing graph 2;

[0036] The second type of preprocessing spectrum 2 and the second type of preprocessing spectrum 2 are compared to obtain a fourth type of comparison result. When the overlap of the fourth type of comparison result is less than the preset judgment threshold, it is determined that the defect anomaly of the first pre-judgment device is induced by the target device, and the defect anomaly of the second pre-judgment device is caused by itself, and the defect degree of the target device is determined to be the second level, and the third type of target defect assessment result is output.

[0037] In a second aspect, a power system secondary equipment defect degree assessment system includes:

[0038] The device data detection unit is used to obtain a target detection data set of the target device, an auxiliary detection data set one of the auxiliary device one, and an auxiliary detection data set two of the auxiliary device two, and when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all normal, output a first type of target defect assessment result; when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all abnormal, output a second type of target defect assessment result; when the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are both normal, output a third type of target defect assessment result;

[0039] A relationship map establishment unit is used to determine that when the comprehensive judgment result of the target detection data set is normal and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, output a first test situation, collect all remaining devices to be tested, and establish a first reference map according to the target device, auxiliary device 1, auxiliary device 2 and all remaining devices to be tested. According to the first test situation, a first type of preprocessing map 1 is established, and the first reference map and the first type of preprocessing map 1 are compared and judged to obtain a spontaneous defect pre-determination result;

[0040] A spectrum comparison and analysis unit 1 is used to establish a first-class preprocessing spectrum 2 and a first-class preprocessing spectrum 3 according to the spontaneous defect pre-determination result, compare and extract the difference between the first reference spectrum and the first-class preprocessing spectrum 2 to obtain a difference result 1, and compare and extract the difference between the first reference spectrum and the second-class preprocessing spectrum 3 to obtain a difference result 2, and compare and judge the difference result 1 and the difference result 2 to obtain a first-class target defect assessment result;

[0041] The second atlas comparison and analysis unit is used to determine that when the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are abnormal, the second test situation is output, and according to the second test situation, the second type of preprocessing atlas one and the second type of preprocessing atlas two are established, and the first reference atlas is respectively compared with the second type of preprocessing atlas one and the second type of preprocessing atlas two to obtain the second type of comparison result and the third type of comparison result, and when the overlap between the second type of comparison result and the third type of comparison result is greater than or equal to the preset judgment threshold, the second type of target defect assessment result is output;

[0042] The spectrum comparison and analysis unit three is used to determine that when the overlap between the second category comparison result and the third category comparison result is less than a preset judgment threshold, the first category target defect assessment result is output; when the overlap between the second comparison result and the third category comparison result is greater than or equal to the preset judgment threshold, a second category preprocessing spectrum two is established, and the second category preprocessing spectrum two is compared with the second category preprocessing spectrum two to obtain a fourth category comparison result; when the overlap between the fourth category comparison result is less than the preset judgment threshold, the third category target defect assessment result is output.

[0043] Compared with the prior art, the present invention has the following characteristics and beneficial effects:

[0044] By extracting the two auxiliary devices with the greatest correlation from other devices associated with the target device, namely auxiliary device one and auxiliary device two, the abnormal and normal conditions of the associated parameter data of the two auxiliary devices can be used as a reference object for judging the defect degree of the target device and a verification and comparison object for the judgment, so as to improve the accuracy of the entire analysis process and the final judgment result. By establishing a knowledge graph of the association relationship between the multiple parameter data of each of the three, and comparing and analyzing the various knowledge graphs established, it is possible to avoid the large error in the final judgment result caused by only performing a single data abnormality analysis of multiple parameters on the target device, thereby reducing the efficiency of the entire analysis work. In addition, a differentiated analysis of different conditions is performed on the various knowledge graphs established between the target device and auxiliary device one and auxiliary device two, so as to more comprehensively consider the defect degree caused by the target device, expand the consideration of diversity in different situations, and realize targeted analysis and judgment of the defect degree level of the target device. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flowchart of a method for evaluating the degree of defects of secondary equipment in a power system mainly embodied in this embodiment.

[0046] Figure 2 It is a structural block diagram of a power system secondary equipment defect degree assessment system mainly embodied in this embodiment. DETAILED DESCRIPTION

[0047] The present invention is further described in detail below in conjunction with the following examples.

[0048] Reference Figure 1 , a method and system for evaluating the degree of defect of secondary equipment in a power system, the method comprising the following steps:

[0049] S1. Obtain a target detection dataset of the target device, an auxiliary detection dataset one of auxiliary device one, and an auxiliary detection dataset two of auxiliary device two. When the comprehensive judgment results of the target detection dataset, the auxiliary detection dataset one, and the auxiliary detection dataset two are all normal, output a first-category target defect assessment result. When the comprehensive judgment results of the target detection dataset, the auxiliary detection dataset one, and the auxiliary detection dataset two are all abnormal, output a second-category target defect assessment result. When the comprehensive judgment result of the target detection dataset is abnormal and the comprehensive judgment results of the auxiliary detection dataset one and the auxiliary detection dataset two are both normal, output a third-category target defect assessment result.

[0050] S2. When the comprehensive judgment result of the target detection data set is normal and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, output the first test condition, collect all the remaining devices to be tested, and establish a first reference spectrum according to the target device, auxiliary equipment 1, auxiliary equipment 2 and all the remaining devices to be tested. According to the first test condition, establish a first type of preprocessing spectrum 1, compare and judge the first reference spectrum and the first type of preprocessing spectrum 1 to obtain a spontaneous defect pre-determination result.

[0051] S3. According to the spontaneous defect pre-determination results, establish the first type of preprocessing spectrum two and the first type of preprocessing spectrum three, compare and extract the difference between the first reference spectrum and the first type of preprocessing spectrum two to obtain the difference result one, and compare and extract the difference between the first reference spectrum and the second type of preprocessing spectrum three to obtain the difference result two, compare and judge the difference result one and the difference result two to obtain the first type of target defect assessment result.

[0052] S4. When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are abnormal, the second test situation is output, and according to the second test situation, a second type of preprocessing spectrum one and a second type of preprocessing spectrum two are established, and the first reference spectrum is respectively compared with the second type of preprocessing spectrum one and the second type of preprocessing spectrum two to obtain a second type of comparison result and a third type of comparison result. When the overlap between the second type of comparison result and the third type of comparison result is greater than or equal to the preset judgment threshold, the second type of target defect assessment result is output.

[0053] S5. When the degree of overlap between the second-category comparison result and the third-category comparison result is less than the preset judgment threshold, the first-category target defect assessment result is output; when the degree of overlap between the second-category comparison result and the third-category comparison result is greater than or equal to the preset judgment threshold, a second-category preprocessing spectrum 2 is established, and the second-category preprocessing spectrum 2 is compared with the second-category preprocessing spectrum 2 to obtain a fourth-category comparison result; when the degree of overlap between the fourth-category comparison result is less than the preset judgment threshold, the third-category target defect assessment result is output.

[0054] Specifically, two auxiliary devices with the greatest correlation, namely auxiliary device one and auxiliary device two, are extracted from other devices associated with the target device, so that the abnormal and normal conditions of the associated parameter data of the two auxiliary devices can be used as a reference object for judging the defect degree of the target device and a verification and comparison object for the judgment, so as to improve the accuracy of the entire analysis process and the final judgment result. A knowledge graph of the association relationship between multiple parameter data of each of the three is established, and the various knowledge graphs established are compared and analyzed with each other to avoid the large error in the final judgment result caused by only performing a single data abnormality analysis of multiple parameters of the target device, thereby reducing the efficiency of the entire analysis work. Differential analysis of different conditions is performed on the various knowledge graphs established between the target device and auxiliary device one and auxiliary device two, so as to more comprehensively consider the defect degree caused by the target device, expand the consideration of diversity in different situations, and realize targeted analysis and judgment of the defect degree level of the target device.

[0055] The specific step S1 includes the following sub-steps:

[0056] A target device is obtained, and based on the target device, an auxiliary device 1 and an auxiliary device 2 that are most associated with the target device are obtained.

[0057] All parameter data of the target device, auxiliary device 1 and auxiliary device 2 are detected respectively to obtain a target detection data set, an auxiliary detection data set 1 and an auxiliary detection data set 2.

[0058] The comprehensive abnormal conditions of the target detection data set, auxiliary detection data set one and auxiliary detection data set two are judged respectively. When the comprehensive judgment results of the target detection data set, auxiliary detection data set one and auxiliary detection data set two are all normal, the defect degree of the target equipment is judged to be zero, and the first type of target defect assessment result is output.

[0059] When the comprehensive judgment results of the target detection data set, the auxiliary detection data set 1 and the auxiliary detection data set 2 are all abnormal, the defect degree of the target equipment is determined to be the first level, and the second type of target defect assessment result is output.

[0060] When the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are both normal, the defect degree of the target equipment is determined to be the second level, and the third type of target defect assessment result is output.

[0061] Specifically, if the target device is device A, auxiliary device one is device B and auxiliary device two is device C, and the information correlation between devices B and C and device A is the highest, that is, if device A is abnormal, devices B and C are very likely to be abnormal. The parameter data involved in the secondary equipment specifically includes multiple categories, mainly including measuring meters, insulation monitoring devices, control and signal devices, relay protection and automatic devices, DC power supply equipment, high-frequency wave arresters, backup automatic transfer devices, etc. The target detection data set, auxiliary detection data set one and auxiliary detection data set two (the parameter items contained in these three data sets all refer to the multiple categories of data mentioned above) are respectively judged for the comprehensive abnormal conditions of the target detection data set, auxiliary detection data set one and auxiliary detection data set two (referring to the case of statistical analysis of the abnormal item data in the target detection data set of the target device, for example, when the statistics show that the data belonging to the DC power supply equipment, the high-frequency wave arrester and the backup automatic transfer device are all abnormal, the weight ratio (important proportion value) of the abnormal parameter items to the total parameter items can be used for judgment, and the comprehensive judgment The comprehensive judgment result of the target detection data set is abnormal), when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one and the auxiliary detection data set two are all normal, it means that there is no defect in the target equipment, and the safety of the target equipment meets the standard, and the first type of target defect assessment result is determined (such as the defect degree is zero). When the comprehensive judgment results of the target detection data set, the auxiliary detection data set one and the auxiliary detection data set two are all abnormal, it means that the defect degree of the target equipment is extremely large, and it causes the associated auxiliary equipment one and auxiliary equipment two to be induced. At this time, the defect degree of the target equipment is the most serious, that is, the defect degree level is determined to be the first level, that is, the second type of target defect assessment result (that is, the most serious level) is output. When the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are all normal, it means that the defect degree of the target equipment has not yet affected the associated auxiliary equipment one and auxiliary equipment two. At this time, the defect degree severity level of the target equipment is determined to be the second level, that is, the third type of target defect assessment result is output.

[0062] The specific step S2 includes the following sub-steps:

[0063] When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two is abnormal, the auxiliary device corresponding to one of the abnormal comprehensive judgment results is named as an abnormal device, and the auxiliary device corresponding to one of the normal comprehensive judgment results is named as a normal device, and the first test situation is output.

[0064] Collect all the remaining devices under test, and establish a knowledge graph of the association relationship between the multiple generic parameters contained in the target device, the abnormal device and all the remaining devices under test respectively when the devices are under abnormal operation and normal operation conditions, as well as a knowledge graph of the association relationship between the multiple generic parameters contained in the target device, the normal device and all the remaining devices under test, and output a first reference graph, in which the abnormal device is located at the association relationship subordinate position of the target device, and all the remaining devices under test are located at the association relationship subordinate position of the abnormal device.

[0065] According to the first test situation, the target item parameters with the largest variation and normal in the target detection data set are extracted, the first type of abnormal parameter one of the data abnormality in the abnormal device and the first type of remaining abnormal parameter one of the data abnormality in all remaining devices to be tested are extracted.

[0066] A knowledge graph of the association relationship between the target item parameter, the first type of abnormal parameter one and the first type of remaining abnormal parameter one is established, and the first type of preprocessing graph one is output.

[0067] The first reference spectrum and the first type of preprocessed spectrum are compared to obtain a first type of comparison result. When the overlap of the first type of comparison result is less than a preset judgment threshold, it is preliminarily pre-determined that the defect abnormality of the abnormal equipment is spontaneous, and a spontaneous defect pre-determination result is output.

[0068] Specifically, when the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two is abnormal, it is difficult to directly judge whether the target device has defects to what extent, and whether the abnormality of one of the auxiliary devices is caused by the data with large changes in the target device. Therefore, further data correlation analysis is required, that is, this judgment result is used as the first test case, and the above-mentioned auxiliary device with abnormality is used as the abnormal device, and the auxiliary device with normal comprehensive judgment result is used as the normal device, and all remaining devices to be tested (that is, other devices that need to be detected and judged for the degree of defects except the target device, auxiliary device one and auxiliary device two) are collected, and the first reference map (there are different degrees of correlation between these devices, that is, there is a correlation and influence between the multiple parameters contained in each, so a knowledge map of the correlation relationship can be established, which is similar to a tree structure Figure 1The same association relationship knowledge map is formed to facilitate the understanding of the influence association relationship between all parameter items in various devices, which is conducive to judging whether defects are induced between target and abnormal devices, that is, enhancing the reliable scientific research on developability data), and the position establishment relationship of the first reference map is that the parameter item in device A is in the first position, the parameter item in device B is in the second subordinate position, that is, below device A, and the parameter items in all remaining devices to be tested are in the third subordinate position, that is, below device B, so as to form an association relationship knowledge map similar to a tree diagram, respectively under abnormal operation and normal operation conditions of the equipment (the abnormal operation condition here refers to the coverage range of abnormalities of device A that will affect other devices under abnormal conditions, and the data operation association relationship range between device A and other devices under the same normal conditions), target item parameters (such as all parameter items contained in device A are A1, A2, and A3, among which the data of A1 has the largest fluctuation range, but the data of A1 is Normal data, then A1 data is the target item parameter), the first type of abnormal parameter one (if the abnormal device is device B, and all parameter items contained in device B are B1, B2, B3, B4, among which B2 and B3 data are abnormal, that is, B2 and B3 are the first type of abnormal parameter one), the first type of remaining abnormal parameter one (the explanation is the same as the first type of abnormal parameter one, no further explanation is given here, if it is D1, D2, D4, E1, E3), the first type of preprocessing spectrum one (that is, establishing A1 and B2, B 3 and the knowledge graph of the association relationship between different parameter items of the four types of equipment, namely D1, D2, D4, E1, and E3), the first type of comparison results (i.e., comparing the overlap of the association routes of the two knowledge graphs). When the overlap of the first type of comparison results is less than the preset judgment threshold (if the preset judgment threshold is set to 60%, if the overlap of the first type of comparison results is 50%), it is preliminarily pre-judged that the defect anomaly of the abnormal equipment is spontaneous, and further verification is needed in the future to reduce the probability of misjudgment.

[0069] The specific step S3 includes the following sub-steps:

[0070] According to the spontaneous defect pre-determination result, the first type normal parameter one in which the data in the abnormal device is normal and the first type remaining normal parameter one in which the data in all the remaining devices to be tested are normal are extracted.

[0071] A knowledge graph of the association relationship between the target item parameter, the first type normal parameter one and the first type remaining normal parameter one is established, and the first type preprocessing graph two is output.

[0072] Extract the first type of normal parameters of normal data in normal equipment.

[0073] A knowledge graph of the association relationship between the target item parameter, the first-category normal parameter two and the first-category remaining normal parameter one is established, and the first-category preprocessing graph three is output.

[0074] The difference between the first reference spectrum and the first type of preprocessed spectrum 2 is extracted by comparison to obtain difference result 1, and the difference between the first reference spectrum and the second type of preprocessed spectrum 3 is extracted by comparison to obtain difference result 2. The difference result 1 and the difference result 2 are compared to obtain the second type of comparison result.

[0075] When the overlap of the second type of comparison results is greater than or equal to the preset judgment threshold, the defect anomaly of the abnormal equipment is finally determined to be spontaneous, and the defect degree of the target equipment is determined to be zero, and the first type of target defect assessment result is output.

[0076] Specifically, based on the spontaneous defect pre-determination results obtained by the above judgment, the next step of data analysis is carried out, the first type of normal parameter one (according to the above example: B1, B4 data are normal, that is, the first type of normal parameter one), the first type of remaining normal parameter one (if it is D3, D5, E2, E4, E5, E6), the first type of pre-processing map two (the same as the explanation of the first type of pre-processing map one, that is, to establish the association relationship knowledge map between different parameter items of the four types of equipment A1 and B1, B4 and D3, D5, E2, E4, E5, E6), the first type of normal parameter two (combined with the above example explanation , if the normal device is device C, if all parameter items contained in device C are C1, C2, C3, and these three parameter items are normal), the first type of preprocessing graph three (establishing the association relationship knowledge graph between different parameter items of four types of devices, A1 and C1, C2, C3, D3, D5, E2, E4, E5, E6), it should be noted that, for example: the first type of preprocessing graph three, A1 and C1, C2, C3, D3, D5, E2, E4, E5, E6, these parameter items are not all successfully established association relationship graphs, only A1 and C1, C2, C3, D3, D5, E2, Parameter items with up-down association relationships among E4, E5, and E6 are graphed. For example, if D5 and E2 do not form an up-down association relationship, they are removed. Finally, A1 and C1, C2, C3 and D3, E4, E5, and E6 are used to construct a knowledge graph of successful association relationships. The difference between the first reference graph and the first type of preprocessed graph 2 and the second type of preprocessed graph 3 is extracted by comparison to obtain difference result 1 and difference result 2 (if the association routes of the first reference graph and the first type of preprocessed graph 2 are compared for overlap, the association relationship of the non-overlapping part can be extracted. Partial knowledge graphs, similarly, compare the overlap of the association routes of the first reference graph and the second type of preprocessing graph to extract the association relationship partial knowledge graph of the non-overlapping part), the second type of comparison results (finally, compare the overlap of the association routes of the two knowledge graphs of the association relationship partial knowledge graph corresponding to the difference result one and the association relationship partial knowledge graph corresponding to the difference result two), the overlap of the second type of comparison results (if the overlap is 70%), it is finally determined that the defect anomaly of the abnormal equipment is spontaneous, and the defect degree of the target equipment is zero, which belongs to the first type of target defect assessment result.

[0077] The specific step S4 includes the following sub-steps:

[0078] When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, outputting the second test situation;

[0079] Extract the second type of abnormal parameters one of the data anomalies in the auxiliary detection data set one.

[0080] A knowledge graph of the association relationship between the target item parameter, the second type abnormal parameter one and the first type remaining abnormal parameter one is established, and the second type preprocessing graph one is output.

[0081] Extract the second type of abnormal parameters of the data anomaly in the auxiliary detection data set 2.

[0082] A knowledge graph of the association relationship between the target item parameter, the second type of abnormal parameter 2 and the first type of remaining abnormal parameter 1 is established, and the second type of preprocessing graph 2 is output.

[0083] The first reference spectrum is compared with the second type of preprocessed spectrum one and the second type of preprocessed spectrum two to obtain the second type of comparison results and the third type of comparison results. When the overlap between the second type of comparison results and the third type of comparison results is greater than or equal to the preset judgment threshold, it is determined that the defect anomalies of auxiliary equipment one and auxiliary equipment two are induced by the target equipment, and the defect degree of the target equipment is determined to be the first level, and the second type of target defect assessment result is output.

[0084] Specifically, when the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are abnormal (that is, device A is normal, devices B and C are abnormal, then the defect abnormality of devices B and C is very likely to be caused spontaneously, so a direct judgment cannot be made, and further verification judgment is required, and this judgment situation is taken as the second test situation), the second type of abnormal parameter one (if the auxiliary detection data set one is B6, B7, B8, B9, B10, and the data abnormalities are B6, B7, B8, which are the second type of abnormal parameter one), the second type of preprocessing map one (establishing a knowledge map of the association relationship between different parameter items of the four types of devices A1 and B6, B7, B8 and D1, D2, D4, E1, E3), the second type of abnormal parameter two (if the auxiliary detection data set two is C4, C5, C6, and the data abnormalities are The most common ones are C5 and C6, which are the second type of abnormal parameters one), the second type of preprocessing map two (establishing the association relationship knowledge map between A1 and different parameter items of the four types of equipment, namely, C5, C6, D1, D2, D4, E1, and E3), and comparing the first reference map with the second type of preprocessing map one and the second type of preprocessing map two to obtain the second type of comparison results and the third type of comparison results (comparing the association routes of the first reference map with the second type of preprocessing map one knowledge map respectively. If the overlap of the second type of comparison results is 65% and the overlap of the third type of comparison results is 70%), the overlap of the second type of comparison results and the third type of comparison results is greater than or equal to the preset judgment threshold, then it can be determined that the defect anomalies of auxiliary equipment one and auxiliary equipment two are induced by the target equipment, and the defect degree of the target equipment is determined to be the first level, that is, it belongs to the second type of target defect assessment result.

[0085] The specific step S5 includes the following sub-steps:

[0086] When the overlap between the second and third comparison results is less than the preset judgment threshold, it is determined that the defect anomalies of auxiliary equipment one and auxiliary equipment two are caused by themselves, and the defect degree of the target equipment is determined to be zero, and the first type of target defect assessment result is output.

[0087] When the degree of overlap between the second comparison result and one of the third comparison results is greater than or equal to a preset judgment threshold, the auxiliary device corresponding to one of the results whose degree of overlap is greater than or equal to the preset judgment threshold is named as a first pre-judgment device, and the auxiliary device corresponding to one of the results whose degree of overlap is less than the preset judgment threshold is named as a second pre-judgment device.

[0088] A knowledge graph of the association relationship between the abnormal multiple categorical parameters contained in the first pre-judgment device, the second pre-judgment device and all the remaining devices to be tested is established, and the second type of preprocessing graph 2 is output.

[0089] The second type of preprocessing spectrum two and the second type of preprocessing spectrum two are compared to obtain the fourth type of comparison result. When the overlap of the fourth type of comparison result is less than the preset judgment threshold, it is determined that the defect anomaly of the first pre-judgment device is induced by the target device, and the defect anomaly of the second pre-judgment device is caused by itself, and the defect degree of the target device is determined to be the second level, and the third type of target defect assessment result is output.

[0090] Specifically, if the overlap between the second and third comparison results is 50% and 50% respectively, and the overlap between the second and third comparison results is less than the preset judgment threshold (60%), it can be determined that the defect anomalies of auxiliary equipment one and auxiliary equipment two are caused by themselves, and the defect degree of the target equipment is determined to be zero, that is, it belongs to the first category of target defect assessment results. If the overlap between the second comparison results is 65% and the overlap between the third comparison results is 55%, it can be preliminarily pre-judged that the defect anomaly of auxiliary equipment one is induced by equipment A, and the defect anomaly of auxiliary equipment two is caused by itself, but further verification and judgment are required. The auxiliary equipment corresponding to one of the results with a overlap greater than or equal to the preset judgment threshold is named the first pre-judgment device (that is, the auxiliary equipment one mentioned above), and the auxiliary equipment corresponding to the result with a overlap less than the preset judgment threshold is named the first pre-judgment device (that is, the auxiliary equipment one mentioned above). The auxiliary device corresponding to one of the results of the judgment threshold is named the second pre-judgment device (that is, the above-mentioned auxiliary device 2), the second type of preprocessing graph 2 (that is, the knowledge graph for establishing the association relationship between different parameter items of the four types of equipment B6, B7, B8 and C5, C6 and D1, D2, D4, E1, E3), and the second type of preprocessing graph 2 is compared with the second type of preprocessing graph 2 to obtain the fourth type of comparison result (that is, the association routes of the second type of preprocessing graph 2 and the second type of preprocessing graph 2 are compared for the overlap, if the overlap of the fourth type of comparison result is 55%), it can be determined that the defect anomaly of the first pre-judgment device is induced by the target device, and the defect anomaly of the second pre-judgment device is caused by itself, and the defect degree of the target device is determined to be the second level, that is, it belongs to the third type of target defect assessment result.

[0091] A power system secondary equipment defect degree assessment system, by applying a power system secondary equipment defect degree assessment method as described above, includes an equipment data detection unit, a relationship map establishment unit, a map comparison and analysis unit 1, a map comparison and analysis unit 2 and a map comparison and analysis unit 3, with reference to Figure 2, obtain the target detection data set of the target device, the auxiliary detection data set 1 of the auxiliary device 1 and the auxiliary detection data set 2 of the auxiliary device 2 through the device data detection unit, when the comprehensive judgment results of the target detection data set, the auxiliary detection data set 1 and the auxiliary detection data set 2 are all normal, output the first type of target defect evaluation result, when the comprehensive judgment results of the target detection data set, the auxiliary detection data set 1 and the auxiliary detection data set 2 are all abnormal, output the second type of target defect evaluation result, when the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 are both normal, output the third type of target defect evaluation result; establish through the relationship map The unit judges that when the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the first test situation is output, all the remaining devices to be tested are collected, and a first reference spectrum is established according to the target device, auxiliary device 1, auxiliary device 2 and all the remaining devices to be tested. According to the first test situation, a first type of pre-processed spectrum 1 is established, and the first reference spectrum and the first type of pre-processed spectrum 1 are compared and judged to obtain the spontaneous defect pre-determination result. The spectrum comparison and analysis unit 1 establishes the first type of pre-processed spectrum 2 and the first type of pre-processed spectrum 3 according to the spontaneous defect pre-determination result, and compares and extracts the first reference spectrum and the first type of pre-processed spectrum 2. The difference result 1 is obtained by comparing and extracting the difference part between the first reference spectrum and the second type preprocessing spectrum 3, and the difference result 2 is obtained by comparing and judging the difference result 1 and the difference result 2 to obtain the first type target defect assessment result; when the comprehensive judgment result of the target detection data set is normal and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the second test situation is output, and according to the second test situation, the second type preprocessing spectrum 1 and the second type preprocessing spectrum 2 are established, and the first reference spectrum is respectively compared with the second type preprocessing spectrum 1 and the second type preprocessing spectrum 2 to obtain the second type comparison result When the overlap between the second and third comparison results is greater than or equal to the preset judgment threshold, the second target defect assessment result is output. When the overlap between the second and third comparison results is less than the preset judgment threshold, the first target defect assessment result is output. When the overlap between the second and third comparison results is greater than or equal to the preset judgment threshold, the second preprocessing atlas is established. The fourth comparison result is obtained by comparing the second preprocessing atlas with the second preprocessing atlas. When the overlap between the fourth comparison result is less than the preset judgment threshold, the third target defect assessment result is output.

[0092] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for evaluating the degree of defect of secondary equipment in a power system, characterized in that: The following steps are involved: Obtain a target detection data set of the target device, an auxiliary detection data set one of the auxiliary device one, and an auxiliary detection data set two of the auxiliary device two; when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all normal, output a first-category target defect assessment result; when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all abnormal, output a second-category target defect assessment result; when the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are both normal, output a third-category target defect assessment result; When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the first test situation is output, all the remaining devices to be tested are collected, and a first reference spectrum is established according to the target device, the auxiliary device 1, the auxiliary device 2 and all the remaining devices to be tested. According to the first test situation, a first type of preprocessing spectrum 1 is established, and the first reference spectrum and the first type of preprocessing spectrum 1 are compared and judged to obtain a spontaneous defect pre-determination result; According to the spontaneous defect pre-determination result, a first-class pre-processing spectrum 2 and a first-class pre-processing spectrum 3 are established, and the difference between the first reference spectrum and the first-class pre-processing spectrum 2 is extracted by comparison to obtain a difference result 1, and the difference between the first reference spectrum and the second-class pre-processing spectrum 3 is extracted by comparison to obtain a difference result 2, and the difference result 1 and the difference result 2 are compared and judged to obtain a first-class target defect assessment result; When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are abnormal, the second test situation is output, and according to the second test situation, the second type of preprocessing spectrum one and the second type of preprocessing spectrum two are established, and the first reference spectrum is respectively compared with the second type of preprocessing spectrum one and the second type of preprocessing spectrum two to obtain the second type of comparison result and the third type of comparison result, and when the overlap between the second type of comparison result and the third type of comparison result is greater than or equal to the preset judgment threshold, the second type of target defect assessment result is output; When the overlap between the second-category comparison result and the third-category comparison result is less than the preset judgment threshold, the first-category target defect assessment result is output; when the overlap between the second-category comparison result and the third-category comparison result is greater than or equal to the preset judgment threshold, a second-category preprocessing graph 2 is established, and the second-category preprocessing graph 2 is compared with the second-category preprocessing graph 2 to obtain a fourth-category comparison result; when the overlap between the fourth-category comparison result is less than the preset judgment threshold, the third-category target defect assessment result is output.

2. A method for evaluating the degree of defect of secondary equipment in a power system according to claim 1, characterized in that: The steps of obtaining a target detection data set of a target device, an auxiliary detection data set one of an auxiliary device one, and an auxiliary detection data set two of an auxiliary device two, and outputting a first-category target defect assessment result when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all normal, and outputting a second-category target defect assessment result when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all abnormal, and outputting a third-category target defect assessment result when the comprehensive judgment result of the target detection data set is abnormal and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are both normal, are specifically as follows: Acquire a target device, and acquire, based on the target device, an auxiliary device 1 and an auxiliary device 2 that are most associated with the target device; Respectively detecting all parameter data of the target device, auxiliary device 1 and auxiliary device 2 to obtain a target detection data set, an auxiliary detection data set 1 and an auxiliary detection data set 2; Respectively judging the comprehensive abnormal conditions of the target detection data set, the auxiliary detection data set 1 and the auxiliary detection data set 2; when the comprehensive judgment results of the target detection data set, the auxiliary detection data set 1 and the auxiliary detection data set 2 are all normal, judging the defect degree of the target device to be zero, and outputting the first type of target defect assessment result; When the comprehensive judgment results of the target detection data set, the auxiliary detection data set 1, and the auxiliary detection data set 2 are all abnormal, the defect degree of the target equipment is determined to be the first level, and the second type of target defect assessment result is output; When the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 are both normal, the defect degree of the target equipment is determined to be the second level, and the third type target defect assessment result is output.

3. A method for evaluating the degree of defect of secondary equipment in a power system according to claim 2, characterized in that: When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the first test situation is output, all the remaining devices to be tested are collected, and a first reference spectrum is established according to the target device, the auxiliary device 1, the auxiliary device 2 and all the remaining devices to be tested. According to the first test situation, a first type of preprocessing spectrum 1 is established, and the first reference spectrum and the first type of preprocessing spectrum 1 are compared and judged to obtain the spontaneous defect pre-determination result. The steps are specifically as follows: When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the auxiliary device corresponding to one of the abnormal comprehensive judgment results is named as an abnormal device, and the auxiliary device corresponding to one of the normal comprehensive judgment results is named as a normal device, and the first test situation is output; Collect all remaining devices to be tested, and establish a knowledge graph of the association relationship between multiple generic parameters contained in the target device, the abnormal device and all remaining devices to be tested, and a knowledge graph of the association relationship between multiple generic parameters contained in the target device, the normal device and all remaining devices to be tested, respectively, when the devices are under abnormal operation and normal operation conditions, and output a first reference graph, in which the abnormal device is located at the association relationship subordinate position of the target device, and all remaining devices to be tested are located at the association relationship subordinate position of the abnormal device; According to the first test situation, extract the target item parameter with the largest change amplitude and normal in the target detection data set, extract the first type of abnormal parameter one of the data abnormality in the abnormal device and the first type of remaining abnormal parameter one of the data abnormality in all the remaining devices to be tested; Establish a knowledge graph of the association relationship between the target item parameter, the first type of abnormal parameter 1 and the first type of remaining abnormal parameter 1, and output the first type of preprocessing graph 1; The first reference spectrum and the first type of preprocessed spectrum are compared to obtain a first type of comparison result. When the overlap of the first type of comparison result is less than a preset judgment threshold, it is preliminarily pre-determined that the defect abnormality of the abnormal equipment is spontaneous, and a spontaneous defect pre-determination result is output.

4. A method for evaluating the degree of defect of secondary equipment in a power system according to claim 3, characterized in that: According to the spontaneous defect pre-determination result, the first type pre-processing spectrum 2 and the first type pre-processing spectrum 3 are established, the difference between the first reference spectrum and the first type pre-processing spectrum 2 is compared and extracted to obtain the difference result 1, and the difference between the first reference spectrum and the second type pre-processing spectrum 3 is compared and extracted to obtain the difference result 2, and the difference result 1 and the difference result 2 are compared and judged to obtain the first type target defect assessment result, specifically, the steps are as follows: Extracting the first type of normal parameter 1 with normal data in the abnormal device and the first type of remaining normal parameter 1 with normal data in all remaining devices to be tested according to the spontaneous defect pre-determination result; Establish a knowledge graph of the association relationship between the target item parameter, the first type normal parameter 1 and the first type remaining normal parameter 1, and output the first type preprocessing graph 2; Extracting the first type of normal parameter 2 of normal data in the normal device; Establish a knowledge graph of the association relationship between the target item parameter, the first type normal parameter 2 and the first type remaining normal parameter 1, and output the first type preprocessing graph 3; Comparing and extracting the difference between the first reference spectrum and the first type of preprocessed spectrum 2 to obtain a difference result 1, and comparing and extracting the difference between the first reference spectrum and the second type of preprocessed spectrum 3 to obtain a difference result 2, and comparing the difference result 1 and the difference result 2 to obtain a second type of comparison result; When the overlap of the second type of comparison results is greater than or equal to the preset judgment threshold, the defect anomaly of the abnormal equipment is finally determined to be spontaneous, and the defect degree of the target equipment is determined to be zero, and the first type of target defect assessment result is output.

5. A method for evaluating the degree of defect of secondary equipment in a power system according to claim 3, characterized in that: When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, the second test situation is output, and according to the second test situation, the second type of preprocessing spectrum 1 and the second type of preprocessing spectrum 2 are established, and the first reference spectrum is respectively compared with the second type of preprocessing spectrum 1 and the second type of preprocessing spectrum 2 to obtain the second type of comparison result and the third type of comparison result. When the overlap between the second type of comparison result and the third type of comparison result is greater than or equal to the preset judgment threshold, the step of outputting the second type of target defect assessment result is specifically as follows: When the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, outputting a second condition to be tested; Extracting a second type of abnormal parameter 1 of the data abnormality in the auxiliary detection data set 1; Establish a knowledge graph of the association relationship between the target item parameter, the second type of abnormal parameter one and the first type of remaining abnormal parameter one, and output the second type of preprocessing graph one; Extracting a second type of abnormal parameter 2 of the data abnormality in the auxiliary detection data set 2; Establish a knowledge graph of the association relationship between the target item parameter, the second type of abnormal parameter 2 and the first type of remaining abnormal parameter 1, and output the second type of preprocessing graph 2; The first reference spectrum is compared with the second type of preprocessed spectrum one and the second type of preprocessed spectrum two to obtain the second type of comparison results and the third type of comparison results. When the overlap between the second type of comparison results and the third type of comparison results is greater than or equal to the preset judgment threshold, it is determined that the defect anomalies of auxiliary equipment one and auxiliary equipment two are induced by the target equipment, and the defect degree of the target equipment is determined to be the first level, and the second type of target defect assessment result is output.

6. A method for evaluating the degree of defect of secondary equipment in a power system according to claim 5, characterized in that: When the overlap between the second-category comparison result and the third-category comparison result is less than the preset judgment threshold, the first-category target defect assessment result is output; when the overlap between the second-category comparison result and the third-category comparison result is greater than or equal to the preset judgment threshold, the second-category preprocessing spectrum 2 is established, and the second-category preprocessing spectrum 2 and the second-category preprocessing spectrum 2 are compared to obtain the fourth-category comparison result; when the overlap between the fourth-category comparison result and the third-category target defect assessment result is output, the specific steps are: When the overlap between the second type comparison result and the third type comparison result is less than the preset judgment threshold, it is determined that the defect anomaly of the auxiliary device 1 and the auxiliary device 2 is caused by themselves, and the defect degree of the target device is determined to be zero, and the first type target defect assessment result is output; When the overlap degree between the second comparison result and one of the third comparison results is greater than or equal to a preset judgment threshold, the auxiliary device corresponding to one of the results whose overlap degree is greater than or equal to the preset judgment threshold is named as a first pre-judgment device, and the auxiliary device corresponding to one of the results whose overlap degree is less than the preset judgment threshold is named as a second pre-judgment device; Establish a knowledge graph of the association relationship between the abnormal multiple category parameters contained in the first pre-judgment device, the second pre-judgment device and all the remaining devices to be tested, and output the second category pre-processing graph 2; The second type of preprocessing spectrum 2 and the second type of preprocessing spectrum 2 are compared to obtain a fourth type of comparison result. When the overlap of the fourth type of comparison result is less than the preset judgment threshold, it is determined that the defect anomaly of the first pre-judgment device is induced by the target device, and the defect anomaly of the second pre-judgment device is caused by itself, and the defect degree of the target device is determined to be the second level, and the third type of target defect assessment result is output.

7. A power system secondary equipment defect degree assessment system, characterized in that: The system is used to implement a method for evaluating the degree of defects of secondary equipment in a power system according to any one of claims 1 to 6, comprising: The device data detection unit is used to obtain a target detection data set of the target device, an auxiliary detection data set one of the auxiliary device one, and an auxiliary detection data set two of the auxiliary device two, and when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all normal, output a first type of target defect assessment result; when the comprehensive judgment results of the target detection data set, the auxiliary detection data set one, and the auxiliary detection data set two are all abnormal, output a second type of target defect assessment result; when the comprehensive judgment result of the target detection data set is abnormal, and the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are both normal, output a third type of target defect assessment result; A relationship map establishment unit is used to determine that when the comprehensive judgment result of the target detection data set is normal and one of the comprehensive judgment results of the auxiliary detection data set 1 and the auxiliary detection data set 2 is abnormal, output a first test situation, collect all remaining devices to be tested, and establish a first reference map according to the target device, auxiliary device 1, auxiliary device 2 and all remaining devices to be tested. According to the first test situation, a first type of preprocessing map 1 is established, and the first reference map and the first type of preprocessing map 1 are compared and judged to obtain a spontaneous defect pre-determination result; The spectrum comparison and analysis unit 1 is used to establish the first type of preprocessing spectrum 2 and the first type of preprocessing spectrum 3 according to the spontaneous defect pre-determination result, compare and extract the difference between the first reference spectrum and the first type of preprocessing spectrum 2 to obtain the difference result 1, and compare and extract the difference between the first reference spectrum and the second type of preprocessing spectrum 3 to obtain the difference result 2, and compare and judge the difference result 1 and the difference result 2 to obtain the first type of target defect assessment result; The second atlas comparison and analysis unit is used to determine that when the comprehensive judgment result of the target detection data set is normal, and one of the comprehensive judgment results of the auxiliary detection data set one and the auxiliary detection data set two are abnormal, the second test situation is output, and according to the second test situation, the second type of preprocessing atlas one and the second type of preprocessing atlas two are established, and the first reference atlas is respectively compared with the second type of preprocessing atlas one and the second type of preprocessing atlas two to obtain the second type of comparison result and the third type of comparison result, and when the overlap between the second type of comparison result and the third type of comparison result is greater than or equal to the preset judgment threshold, the second type of target defect assessment result is output; The spectrum comparison and analysis unit three is used to determine that when the overlap between the second category comparison result and the third category comparison result is less than a preset judgment threshold, the first category target defect assessment result is output; when the overlap between the second comparison result and the third category comparison result is greater than or equal to the preset judgment threshold, a second category preprocessing spectrum two is established, and the second category preprocessing spectrum two is compared with the second category preprocessing spectrum two to obtain a fourth category comparison result; when the overlap between the fourth category comparison result is less than the preset judgment threshold, the third category target defect assessment result is output.

Citation Information

Patent Citations

  • Equipment operation chain state monitoring method based on knowledge graph

    CN113420162A

  • Electric power secondary system defect diagnosis knowledge graph construction method and system

    CN117609514A