CN117828448A - Internal partial discharge temperature anomaly identification system for primary and secondary fusion ring main unit - Google Patents
Internal partial discharge temperature anomaly identification system for primary and secondary fusion ring main unit Download PDFInfo
- Publication number
- CN117828448A CN117828448A CN202410238450.8A CN202410238450A CN117828448A CN 117828448 A CN117828448 A CN 117828448A CN 202410238450 A CN202410238450 A CN 202410238450A CN 117828448 A CN117828448 A CN 117828448A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- case
- temperature
- ring main
- test
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 271
- 230000001052 transient effect Effects 0.000 claims abstract description 109
- 238000012544 monitoring process Methods 0.000 claims abstract description 70
- 238000004140 cleaning Methods 0.000 claims abstract description 57
- 230000002159 abnormal effect Effects 0.000 claims abstract description 43
- 230000000694 effects Effects 0.000 claims abstract description 31
- 239000011159 matrix material Substances 0.000 claims description 49
- 238000000034 method Methods 0.000 claims description 31
- 230000008569 process Effects 0.000 claims description 27
- 238000004458 analytical method Methods 0.000 claims description 14
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 230000003631 expected effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 206010000117 Abnormal behaviour Diseases 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Landscapes
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses an internal partial discharge temperature anomaly identification system for a secondary fusion ring main unit, and belongs to the technical field of ring main units. The classified storage of the equipment control parameters taking the first test data cluster as a storage carrier is realized through the partial discharge test cases; recording transient warning degrees of temperature sensors in different transient periods in the partial discharge test case by taking the second test data cluster as a storage carrier; the first data cleaning is carried out on the second test data cluster through temperature monitoring points arranged in the ring main unit, and the second data cleaning is carried out on the second test data cluster through analyzing the feedback effect value of each transient period; carrying out case classification while analyzing the case feature similarity among the partial discharge test cases through a case classification iteration model, so as to integrate a first test data cluster; and furthermore, the abnormal control parameter range of the ring main unit can be integrated while analyzing the abnormal behavior characteristics of the partial discharge temperature based on the operation data of the ring main unit.
Description
Technical Field
The invention relates to the technical field of ring main units, in particular to an internal partial discharge temperature anomaly identification system for a secondary fusion ring main unit.
Background
The partial discharge temperature refers to the temperature characteristic of the equipment in the partial discharge process, and in the partial discharge test, temperature measuring equipment such as a thermal infrared imager is generally used for monitoring and measuring the surface or internal temperature of the equipment so as to acquire partial discharge temperature data of the equipment;
in the prior art, equipment temperature is generally monitored through tools such as a sensor, but the requirements on the running performance of the equipment inside the ring main unit are different due to the change of an electric power allocation task, so that the traditional equipment temperature monitoring mode cannot be combined with the change of the running performance of the equipment, and the abnormal behavior of the partial discharge temperature of the ring main unit is intelligently diagnosed.
Disclosure of Invention
The invention aims to provide an internal partial discharge temperature anomaly identification system for a secondary fusion ring main unit so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
a unusual identification system of inside partial discharge temperature for a secondary fuses looped netowrk cabinet, this system includes: the device comprises a partial discharge test module, an abnormality identification module, a monitoring range right dividing module, a data cleaning module, a feature matrix module and an iteration analysis module;
the local discharge test module is used for storing the control parameters of the internal equipment of the ring main unit of each local discharge test case, forming a local discharge test data sample base, and classifying and storing the control parameters of the internal equipment of the ring main unit by taking the first test data cluster as a storage carrier;
the abnormal recognition module is used for collecting the partial discharge temperature data received by each temperature sensor based on the transient period in the partial discharge test case, and recording the transient warning degree of the temperature sensor in different transient periods in the partial discharge test case by taking the second test data cluster as a storage carrier;
the monitoring range belongs to the weight dividing module, divides different weights based on temperature monitoring points and generates a weight set;
the data cleaning module comprises a first data cleaning unit and a second data cleaning unit, wherein the first data cleaning unit is used for performing first data cleaning on a second test data cluster based on the right set and the first test data cluster; the second data cleaning unit analyzes the feedback effect value of each transient period based on each transient period in the partial discharge test case, and performs second data cleaning on the second test data cluster based on the feedback effect value of the transient period;
the feature matrix module is used for collecting all second test data clusters after the second data cleaning, and recording partial discharge temperature abnormal features in a matrix form to generate a case feature matrix;
the iterative analysis module comprises a case classification unit and a data integration unit, wherein the case classification unit is used for iteratively analyzing case feature similarity among the partial discharge test cases based on a case feature matrix and performing case classification based on the feature similarity; the data integration unit integrates the first test data cluster based on the case classification result to form an abnormal control parameter range of the equipment in the ring main unit and outputs the abnormal control parameter range in a form of a table.
Further, the partial discharge test module further comprises a partial discharge test case library unit and a first test data cluster unit;
the local discharge test case library unit is used for establishing a local discharge test data sample library based on the local discharge test cases, and storing control parameters of the ring main unit internal equipment of each local discharge test case in the local discharge test data sample library, wherein the control parameters are used for setting the operation performance of the ring main unit internal equipment based on an electric power allocation task;
the first test data cluster unit is configured to uniformly number the partial discharge test cases and the internal devices of the ring main unit, generate a first test data cluster based on the partial discharge test data sample library, and record the first test data cluster asWherein, the method comprises the steps of, wherein,representing the corresponding generation of a first test data cluster of the partial discharge test case i->And the control parameter which is correspondingly set by the ring main unit internal equipment R is represented, and the total number of the ring main unit internal equipment R is represented.
Further, the abnormality identification module further comprises a partial discharge temperature data collection unit and a second test data cluster unit;
the partial discharge temperature data collection unit is used for collecting partial discharge temperature data in the range of temperature monitoring points received by each temperature sensor at the temperature monitoring points based on temperature monitoring points arranged in the ring main unit, wherein the partial discharge temperature data received by each temperature sensor are collected based on transient periods in a partial discharge test case;
the second test data cluster unit is used for respectively carrying out unified numbering on temperature monitoring points arranged in the ring main unit and each temperature sensor at the temperature monitoring points, and is based on transient state circumference in the partial discharge test case iGenerating a second test data cluster, denoted asWherein->Representing the kth transient period in the partial discharge test case i at the h temperature monitoring point, corresponding to the generated second test data cluster,/and the like>Represents the transient state warning degree of the E-th temperature sensor, E represents the total number of the temperature sensors, and the transient state warning degree is +.>In order to be the ratio of the temperature value monitored by the temperature sensor e to the temperature abnormality alarm threshold value in the kth transient period.
Further, the specific process of dividing the different generic rights based on the temperature monitoring points is as follows:
based on each temperature sensor at the temperature monitoring point, different ownership of the monitoring object is divided for the temperature monitoring point range, and the temperature monitoring point range corresponding to the h temperature monitoring point is recorded asWherein->And the right set is used for indicating the right set formed by the internal equipment of the ring main unit monitored by the e-th temperature sensor at the h-th temperature monitoring point.
Further, the specific process of executing the first data cleansing by the first data cleansing unit is as follows:
based on temperature monitoring point rangeAnd a first test data cluster +>For the second test numberAnd carrying out first data cleaning according to the clusters, wherein the first data cleaning mode is as follows:
based on serial numbers of devices in ring main unit, first test data clusters are extractedThe ring main unit internal equipment contained in the system and generating a first test equipment set, which is marked as +.>；
Based on temperature monitoring point rangeAnalyzing any one of the right sets and the first test device set>The matching performance between the two is calculated, the applicable matching degree of the temperature sensor is calculated, and the specific calculation formula is as follows:
；
wherein,indicating the suitability of the temperature sensor e, < ->Representing a first set of test devicesAnd right set->The number of ring main unit internal devices contained in the intersection set +.>Representing the set of rights +.>Number of ring main unit internal devices contained in the ring main unitAn amount of;
presetting an applicability threshold, and if the applicability matching degree of the temperature sensor e is larger than or equal to the applicability threshold, clustering a second test dataThe transient state warning degree of the medium temperature sensor e is reserved, otherwise, the transient state warning degree of the temperature sensor e is distributed from the second test data cluster +.>Medium clearing; when the temperature monitoring point is within->All right sets of (a) and the first test equipment set +.>After the matching analysis, the second test data cluster is updated +.>And marking the updated second test data cluster as +.>。
Further, the specific process of analyzing the feedback effect value of each transient period is as follows:
based on each transient period in the partial discharge test case i, a transient feedback set is generated and recorded asWherein->Indicates the duration of the kth transient period, < +.>Representing the total number of transient periods contained in the partial discharge test case i;
based on the transient feedback set, analyzing the test effect of the partial discharge test case, and calculating the feedback effect value of each transient period, wherein the specific calculation formula is as follows:
；
wherein,and (3) representing a feedback effect value of the kth transient period in the partial discharge test case i, wherein fe represents an expected effect value.
Further, the specific process of executing the second data cleansing by the second data cleansing unit is as follows:
and carrying out second data cleaning on the second test data cluster based on the feedback effect value of the transient period, wherein the second data cleaning mode is as follows:
presetting a feedback threshold value if the feedback effect valueIf the feedback threshold value is greater than or equal to the feedback threshold value, retaining the updated second test data cluster corresponding to the kth transient period +.>Otherwise, the second test data cluster is cleared +.>。
Further, the specific process of recording the partial discharge temperature anomaly characteristic in the form of a matrix is as follows:
collecting all second test data clusters after the second data cleaning, and constructing a partial discharge temperature abnormal characteristic matrix by taking a transient period as a collecting range of the second test data clusters with a unified scale, wherein the row number of the partial discharge temperature abnormal characteristic matrix is equal to the number of a temperature monitoring point, and the column number of the partial discharge temperature abnormal characteristic matrix is equal to the number of a temperature sensor;
after the second data cleaning, mapping all collected second test data clusters in the local discharge test case i with the kth transient period as a collecting range of unified scale to the local dischargeForming a case feature matrix in the temperature anomaly feature matrix, and marking asWherein H represents the total number of partial discharge monitoring points, E represents the total number of temperature sensors, and the case feature matrix is +.>Any one matrix element is marked as +.>If transient warning degree->Greater than or equal to 1, orderOtherwise let->Wherein->；
According to the technical scheme, as the power allocation task has different requirements on the running performance of the internal equipment of the ring main unit, the change characteristic of the partial discharge temperature has the characteristic of disordered temperature perception change characteristic rule caused by different temperature perception change characteristics and transient period changes of the monitoring points; through the first data cleaning, the suitability of the temperature sensor at different monitoring points can be analyzed by combining the characteristics of different partial discharge test cases, and the data acquired by the unsuitable temperature sensor need to be cleaned so as to ensure the effectiveness of partial discharge temperature abnormal data; the method has the advantages that the effectiveness of the transient period can be analyzed by combining the characteristics of the transient periods of different partial discharge test cases through the second data cleaning, the transient refers to the fluctuation transition period of the running performance of the equipment, namely the transition from one stable state to the other stable state, the duration of the transient period reflects the partial discharge stability of the equipment, the collection of partial discharge temperature data is not facilitated for the transient period with the shorter duration, the feedback effect value of the transient period is quantitatively analyzed based on the probability of the approach degree to the effect expected value, and the greater the feedback effect value of the transient period is, the closer the feedback effect value is to the effect expected value; the transient state warning degree is the ratio of the temperature value monitored by the temperature sensor to the temperature abnormality warning threshold value, the greater the ratio is, the greater the abnormality degree of the range temperature sensed by the temperature sensor is, the abnormal state of the range temperature sensed by the temperature sensor is distinguished by the condition that the ratio is 1, the abnormal state is 1, and the abnormal state is not abnormal.
Further, the specific process of case classification based on feature similarity is as follows:
constructing a case classification iteration model, taking all case feature matrixes formed by the corresponding partial discharge test cases i as sample input of the L-th iteration classification, and marking as；
Taking all case feature matrixes formed by the corresponding partial discharge test cases j as sample input of the L+1st iteration classificationWherein->Representing a case feature matrix correspondingly formed by partial discharge test cases j by taking the kth transient period as the collecting range of the unified scale,/>Representing the total number of transient periods contained in the partial discharge test case j, and i+.j;
the output result of the L-th iteration classification is recorded asAnd->The output result of the L+1st iteration classification is marked as +.>And->；
The process of the L+1st iteration classification is as follows:
selecting all case feature matrixes formed by any partial discharge test case x as analog input of L+1st iteration classification, and marking asWherein->Representing a case feature matrix correspondingly formed by partial discharge test case x by taking the mth transient period as the collecting range of the unified scale,/for the test case x>Represents the total number of transient periods contained in partial discharge test case x, and +.>；
Based on sample inputAnd analog input +.>The case feature similarity between the partial discharge test case j and the partial discharge test case x is calculated, and the specific calculation formula is as follows:
；
wherein,representing the similarity of case features between the partial discharge test case j and the partial discharge test case x,representing case feature matrix->And case feature matrix->The number of 1's contained in the intersection set, +.>Representing case feature matrix->And case feature matrix->The number of 1's contained in the union set;
presetting a similarity threshold, if the case features are similarIf the similarity threshold is greater than or equal to the similarity threshold, storing the partial discharge test case into the output result +.>In (a) and (b);
when collectingAfter carrying out case feature similarity analysis between all the partial discharge test cases and the partial discharge test case j, entering the next iteration; after the iteration classification of all the partial discharge test cases is finished, stopping iteration, and outputting an output result of each iteration;
according to the technical scheme, the case classification iterative model is a clustering analysis model based on temperature anomaly characteristics, and the case feature matrix in the sample input and the case feature matrix in the analog input are subjected to feature similarity comparison in turn, so that the dual characteristics of different monitoring points and different transient periods can be combined to classify the partial discharge test cases; and for the partial discharge test cases of the same type, the similarity of temperature abnormal characteristics is met.
Further, the specific process of integrating the first test data cluster based on the case classification result is as follows:
randomly select one output resultBased on the first test data cluster +.>In outputting the result->In the first test data cluster corresponding to each partial discharge test case, obtaining the maximum value and the minimum value of the control parameters correspondingly set by the ring main unit internal equipment r, obtaining the abnormal control parameter range of the ring main unit internal equipment r, and recording in a table form.
Compared with the prior art, the invention has the following beneficial effects: in the internal partial discharge temperature anomaly identification system for the secondary fusion ring main unit, the classified storage of the equipment control parameters by taking the first test data cluster as a storage carrier is realized through the partial discharge test cases; recording transient warning degrees of temperature sensors in different transient periods in the partial discharge test case by taking the second test data cluster as a storage carrier; the first data cleaning is carried out on the second test data cluster through temperature monitoring points arranged in the ring main unit, and the second data cleaning is carried out on the second test data cluster through analyzing the feedback effect value of each transient period; carrying out case classification while analyzing the case feature similarity among the partial discharge test cases through a case classification iteration model, so as to integrate a first test data cluster; and furthermore, the abnormal control parameter range of the ring main unit can be integrated while analyzing the abnormal behavior characteristics of the partial discharge temperature based on the operation data of the ring main unit.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
In the drawings: fig. 1 is a schematic structural diagram of an internal partial discharge temperature anomaly identification system for a secondary fusion ring main unit.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions: the utility model provides an inside partial discharge temperature anomaly identification system for a secondary fuses looped netowrk cabinet, this system includes: the device comprises a partial discharge test module, an abnormality identification module, a monitoring range right dividing module, a data cleaning module, a feature matrix module and an iteration analysis module;
the local discharge test module is used for storing the control parameters of the internal equipment of the ring main unit of each local discharge test case, forming a local discharge test data sample library, and classifying and storing the control parameters of the internal equipment of the ring main unit by taking the first test data cluster as a storage carrier;
the partial discharge test module further comprises a partial discharge test case library unit and a first test data cluster unit;
the local discharge test case library unit is used for establishing a local discharge test data sample library based on the local discharge test cases, and storing control parameters of the ring main unit internal equipment of each local discharge test case in the local discharge test data sample library, wherein the control parameters are used for setting the operation performance of the ring main unit internal equipment based on an electric power allocation task;
the first test data cluster unit is used for respectively carrying out unified numbering on the partial discharge test cases and the ring main unit internal equipment, generating a first test data cluster based on the partial discharge test data sample base and recording asWherein->Representing the corresponding generation of a first test data cluster of the partial discharge test case i->The control parameters which are correspondingly set for the ring main unit internal equipment R are represented, and the R represents the total number of the ring main unit internal equipment;
the abnormal identification module is used for collecting the partial discharge temperature data received by each temperature sensor based on the transient period in the partial discharge test case, and recording the transient warning degree of the temperature sensor in different transient periods in the partial discharge test case by taking the second test data cluster as a storage carrier;
the abnormal identification module further comprises a partial discharge temperature data collection unit and a second test data cluster unit;
the local discharge temperature data collection unit is used for collecting local discharge temperature data in the range of temperature monitoring points received by each temperature sensor at the temperature monitoring points based on temperature monitoring points arranged in the ring main unit, wherein the local discharge temperature data received by each temperature sensor are collected based on transient periods in local discharge test cases;
the second test data cluster unit is used for respectively carrying out unified numbering on the temperature monitoring points arranged in the ring main unit and each temperature sensor at the temperature monitoring points, generating a second test data cluster based on the transient period in the partial discharge test case i, and marking the second test data cluster asWherein->Representing the kth transient period in the partial discharge test case i at the h temperature monitoring point, corresponding to the generated second test data cluster,/and the like>Represents the transient state warning degree of the E-th temperature sensor, E represents the total number of the temperature sensors, and the transient state warning degree is +.>In the kth transient period, the ratio of the temperature value monitored by the temperature sensor e to the temperature abnormality alarm threshold value is set;
the monitoring range ownership dividing module is used for dividing different ownership based on temperature monitoring points and generating an ownership set;
the specific process of dividing different generic rights based on temperature monitoring points is as follows:
based on each temperature sensor at the temperature monitoring point, different ownership of the monitoring object is divided for the temperature monitoring point range, and the temperature monitoring point range corresponding to the h temperature monitoring point is recorded asWherein->Representing a right set formed by the internal equipment of the ring main unit monitored by the e-th temperature sensor at the h-th temperature monitoring point;
the data cleaning module comprises a first data cleaning unit and a second data cleaning unit, wherein the first data cleaning unit is based on the right set and the first test data cluster,the second test data cluster performs first data cleaning; the second data cleaning unit is used for analyzing the feedback effect value of each transient period based on each transient period in the partial discharge test case and performing second data cleaning on the second test data cluster based on the feedback effect value of the transient period;
the specific process of performing the first data cleansing by the first data cleansing unit is as follows:
based on temperature monitoring point rangeAnd a first test data cluster +>Performing a first data cleaning on the second test data cluster, wherein the first data cleaning is performed by the following wayThe following steps:
based on serial numbers of devices in ring main unit, first test data clusters are extractedThe ring main unit internal equipment contained in the system and generating a first test equipment set, which is marked as +.>；
Based on temperature monitoring point rangeAnalyzing any one of the right sets and the first test device set>The matching performance between the two is calculated, the applicable matching degree of the temperature sensor is calculated, and the specific calculation formula is as follows:
；
wherein,indicating the suitability of the temperature sensor e, < ->Representing a first set of test devicesAnd right set->The number of ring main unit internal devices contained in the intersection set +.>Representing the set of rights +.>The number of the ring main unit internal devices contained in the ring main unit;
preset suitability threshold, if temperatureThe applicability matching degree of the sensor e is larger than or equal to the applicability threshold value, and the second test data is clusteredThe transient state warning degree of the medium temperature sensor e is reserved, otherwise, the transient state warning degree of the temperature sensor e is distributed from the second test data cluster +.>Medium clearing; when the temperature monitoring point is within->All right sets of (a) and the first test equipment set +.>After the matching analysis, the second test data cluster is updated +.>And marking the updated second test data cluster as +.>；
The specific process of analyzing the feedback effect value of each transient period is as follows:
based on each transient period in the partial discharge test case i, a transient feedback set is generated and recorded asWherein->Indicates the duration of the kth transient period, < +.>Representing the total number of transient periods contained in the partial discharge test case i;
based on the transient feedback set, analyzing the test effect of the partial discharge test case, and calculating the feedback effect value of each transient period, wherein the specific calculation formula is as follows:
；
wherein,feedback effect values of the kth transient period in the partial discharge test case i are represented, and fe represents an expected effect value;
the specific process of performing the second data cleaning by the second data cleaning unit is as follows:
based on the feedback effect value of the transient period, performing second data cleaning on the second test data cluster, wherein the second data cleaning mode is as follows:
presetting a feedback threshold, if the feedback effect value is greater than or equal to the feedback threshold, reserving an updated second test data cluster corresponding to the kth transient periodOtherwise, the second test data cluster is cleared +.>；
The feature matrix module is used for collecting all second test data clusters after the second data cleaning, and recording partial discharge temperature abnormal features in a matrix form to generate a case feature matrix;
the specific process of recording the partial discharge temperature anomaly characteristic in the form of a matrix is as follows:
collecting all second test data clusters after the second data cleaning, and constructing a partial discharge temperature abnormal characteristic matrix by taking a transient period as a collecting range of the second test data clusters with a unified scale, wherein the row number of the partial discharge temperature abnormal characteristic matrix is equal to the number of a temperature monitoring point, and the column number of the partial discharge temperature abnormal characteristic matrix is equal to the number of a temperature sensor;
after the second data cleaning, mapping all collected second test data clusters in the local discharge test case i with the kth transient period as a collecting range of unified scale into a local discharge temperature abnormal characteristic matrix to form a case characteristic matrix, and marking the case characteristic matrix asWherein H represents the total number of partial discharge monitoring points, E represents the total number of temperature sensors, and the case feature matrix is +.>Any one matrix element is marked as +.>If transient warning degree->Greater than or equal to 1, orderOtherwise let->Wherein->；
The iterative analysis module comprises a case classification unit and a data integration unit, the case classification unit is used for iteratively analyzing case feature similarity among the partial discharge test cases based on the case feature matrix and performing case classification based on the feature similarity; the data integration unit integrates the first test data cluster based on the case classification result to form an abnormal control parameter range of the equipment in the ring main unit and outputs the abnormal control parameter range in a form of a table;
the specific process of case classification based on feature similarity is as follows:
constructing a case classification iteration model, taking all case feature matrixes formed by the corresponding partial discharge test cases i as sample input of the L-th iteration classification, and marking as；
Taking all case feature matrixes formed by the corresponding partial discharge test cases j as sample input of the L+1st iteration classificationWherein->Representing a case feature matrix correspondingly formed by partial discharge test cases j by taking the kth transient period as the collecting range of the unified scale,/>Representing the total number of transient periods contained in the partial discharge test case j, and i+.j;
the output result of the L-th iteration classification is recorded asAnd->The output result of the L+1st iteration classification is marked as +.>And->；
The process of the L+1st iteration classification is as follows:
selecting all case feature matrixes formed by any partial discharge test case x as analog input of L+1st iteration classification, and marking asWherein->Representing a case feature matrix correspondingly formed by partial discharge test case x by taking the mth transient period as the collecting range of the unified scale,/for the test case x>Represents the total number of transient periods contained in partial discharge test case x, and +.>；
Based on sample inputAnd analog input +.>The case feature similarity between the partial discharge test case j and the partial discharge test case x is calculated, and the specific calculation formula is as follows:
；
wherein,representing the similarity of case features between the partial discharge test case j and the partial discharge test case x,representing case feature matrix->And case feature matrix->The number of 1's contained in the intersection set, +.>Representing case feature matrix->And case feature matrix->The number of 1's contained in the union set;
presetting a similarity threshold, if the case features are similarIf the similarity threshold is greater than or equal to the similarity threshold, storing the partial discharge test case into the output result +.>In (a) and (b);
when collectingAfter carrying out case feature similarity analysis between all the partial discharge test cases and the partial discharge test case j, entering the next iteration; after the iteration classification of all the partial discharge test cases is finished, stopping iteration, and outputting an output result of each iteration;
based on the case classification result, the specific process of integrating the first test data cluster is as follows:
randomly select one output resultBased on the first test data cluster +.>In outputting the result->Obtaining the maximum value and the minimum value of control parameters corresponding to the internal equipment r of the ring main unit in a first test data cluster corresponding to each partial discharge test case, obtaining an abnormal control parameter range of the internal equipment r of the ring main unit, and recording in a form of a table;
for example, during a first iteration, a sample input is selected for the corresponding formation of local test case 1Selecting analog input corresponding to any one of local test cases 2 except local test case 1>The local test case 2 is stored into the output result +.>In (2), output the result->And selecting any local test case 3 except the local test cases 1 and 2 for analysis, if the similarity of case characteristics between the local test case 1 and the local test case 3 is high, storing the local test case 3 into the output result +.>In (2), output the result->。
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention and is not intended to limit the present invention, but although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A unusual identification system of inside partial discharge temperature for a secondary fuses looped netowrk cabinet, its characterized in that, the system includes: the device comprises a partial discharge test module, an abnormality identification module, a monitoring range right dividing module, a data cleaning module, a feature matrix module and an iteration analysis module;
the local discharge test module is used for storing the control parameters of the internal equipment of the ring main unit of each local discharge test case, forming a local discharge test data sample base, and classifying and storing the control parameters of the internal equipment of the ring main unit by taking the first test data cluster as a storage carrier;
the abnormal recognition module is used for collecting the partial discharge temperature data received by each temperature sensor based on the transient period in the partial discharge test case, and recording the transient warning degree of the temperature sensor in different transient periods in the partial discharge test case by taking the second test data cluster as a storage carrier;
the monitoring range belongs to the weight dividing module, divides different weights based on temperature monitoring points and generates a weight set;
the data cleaning module comprises a first data cleaning unit and a second data cleaning unit, wherein the first data cleaning unit is used for performing first data cleaning on a second test data cluster based on the right set and the first test data cluster; the second data cleaning unit analyzes the feedback effect value of each transient period based on each transient period in the partial discharge test case, and performs second data cleaning on the second test data cluster based on the feedback effect value of the transient period;
the feature matrix module is used for collecting all second test data clusters after the second data cleaning, and recording partial discharge temperature abnormal features in a matrix form to generate a case feature matrix;
the iterative analysis module comprises a case classification unit and a data integration unit, wherein the case classification unit is used for iteratively analyzing case feature similarity among the partial discharge test cases based on a case feature matrix and performing case classification based on the feature similarity; the data integration unit integrates the first test data cluster based on the case classification result to form an abnormal control parameter range of the equipment in the ring main unit and outputs the abnormal control parameter range in a form of a table.
2. The system for identifying abnormal internal partial discharge temperature of a secondary fusion ring main unit according to claim 1, wherein the partial discharge test module further comprises a partial discharge test case library unit and a first test data cluster unit;
the local discharge test case library unit is used for establishing a local discharge test data sample library based on the local discharge test cases, and storing control parameters of the ring main unit internal equipment of each local discharge test case in the local discharge test data sample library, wherein the control parameters are used for setting the operation performance of the ring main unit internal equipment based on an electric power allocation task;
the first test data cluster unit is configured to uniformly number the partial discharge test cases and the internal devices of the ring main unit, generate a first test data cluster based on the partial discharge test data sample library, and record the first test data cluster asWherein->Representing the corresponding generation of a first test data cluster of the partial discharge test case i->And the control parameter which is correspondingly set by the ring main unit internal equipment R is represented, and the total number of the ring main unit internal equipment R is represented.
3. The internal partial discharge temperature anomaly identification system for a secondary fusion ring main unit according to claim 2, wherein the anomaly identification module further comprises a partial discharge temperature data collection unit and a second test data cluster unit;
the partial discharge temperature data collection unit is used for collecting partial discharge temperature data in the range of temperature monitoring points received by each temperature sensor at the temperature monitoring points based on temperature monitoring points arranged in the ring main unit, wherein the partial discharge temperature data received by each temperature sensor are collected based on transient periods in a partial discharge test case;
the second test data cluster unitThe system is used for respectively carrying out unified numbering on temperature monitoring points arranged in the ring main unit and all temperature sensors at the temperature monitoring points, generating a second test data cluster based on the transient period in the partial discharge test case i, and marking the second test data cluster asWherein->Representing the kth transient period in the partial discharge test case i at the h temperature monitoring point, corresponding to the generated second test data cluster,/and the like>Represents the transient state warning degree of the E-th temperature sensor, E represents the total number of the temperature sensors, and the transient state warning degree is +.>In order to be the ratio of the temperature value monitored by the temperature sensor e to the temperature abnormality alarm threshold value in the kth transient period.
4. The system for identifying abnormal internal partial discharge temperature of a secondary fusion ring main unit according to claim 3, wherein the specific process of dividing different generic rights based on temperature monitoring points is as follows:
based on each temperature sensor at the temperature monitoring point, different ownership of the monitoring object is divided for the temperature monitoring point range, and the temperature monitoring point range corresponding to the h temperature monitoring point is recorded asWherein->And the right set is used for indicating the right set formed by the internal equipment of the ring main unit monitored by the e-th temperature sensor at the h-th temperature monitoring point.
5. The system for identifying abnormal internal partial discharge temperature of a secondary fusion ring main unit according to claim 4, wherein the specific process of performing the first data cleaning by the first data cleaning unit is as follows:
based on temperature monitoring point rangeAnd a first test data cluster +>And performing first data cleaning on the second test data cluster, wherein the first data cleaning mode is as follows:
based on serial numbers of devices in ring main unit, first test data clusters are extractedThe ring main unit internal equipment contained in the system and generating a first test equipment set, which is marked as +.>；
Based on temperature monitoring point rangeAnalyzing any one of the right sets and the first test device set>The matching performance between the two is calculated, the applicable matching degree of the temperature sensor is calculated, and the specific calculation formula is as follows:
；
wherein,indicating the suitability of the temperature sensor e, < ->Representing a first set of test devices->And right set->The number of ring main unit internal devices contained in the intersection set +.>Representing the set of rights +.>The number of the ring main unit internal devices contained in the ring main unit;
presetting an applicability threshold, and if the applicability matching degree of the temperature sensor e is larger than or equal to the applicability threshold, clustering a second test dataThe transient state warning degree of the medium temperature sensor e is reserved, otherwise, the transient state warning degree of the temperature sensor e is distributed from the second test data cluster +.>Medium clearing; when the temperature monitoring point is within->All the attribute rights sets are the same as the first test equipment setAfter the matching analysis, the second test data cluster is updated +.>And marking the updated second test data cluster as +.>。
6. The system for identifying abnormal internal partial discharge temperature of a secondary fusion ring main unit according to claim 5, wherein the specific process of analyzing the feedback effect value of each transient period is as follows:
based on each transient period in the partial discharge test case i, a transient feedback set is generated and recorded asWherein->Indicates the duration of the kth transient period, < +.>Representing the total number of transient periods contained in the partial discharge test case i;
based on the transient feedback set, analyzing the test effect of the partial discharge test case, and calculating the feedback effect value of each transient period, wherein the specific calculation formula is as follows:
；
wherein,and (3) representing a feedback effect value of the kth transient period in the partial discharge test case i, wherein fe represents an expected effect value.
7. The internal partial discharge temperature anomaly identification system for a secondary fusion ring main unit according to claim 6, wherein the specific process of performing the second data cleaning by the second data cleaning unit is as follows:
and carrying out second data cleaning on the second test data cluster based on the feedback effect value of the transient period, wherein the second data cleaning mode is as follows:
presetting a feedback threshold value if the feedback effect valueIf the feedback threshold value is greater than or equal to the feedback threshold value, retaining the updated second test data cluster corresponding to the kth transient period +.>Otherwise, the second test data cluster is cleared +.>。
8. The system for identifying abnormal internal partial discharge temperature of a secondary fusion ring main unit according to claim 7, wherein the specific process of recording abnormal characteristic of partial discharge temperature in a matrix form is as follows:
collecting all second test data clusters after the second data cleaning, and constructing a partial discharge temperature abnormal characteristic matrix by taking a transient period as a collecting range of the second test data clusters with a unified scale, wherein the row number of the partial discharge temperature abnormal characteristic matrix is equal to the number of a temperature monitoring point, and the column number of the partial discharge temperature abnormal characteristic matrix is equal to the number of a temperature sensor;
after the second data cleaning, mapping all collected second test data clusters in the local discharge test case i with the kth transient period as a collecting range of unified scale into the local discharge temperature abnormal feature matrix to form a case feature matrix, and marking the case feature matrix asWherein H represents the total number of partial discharge monitoring points, E represents the total number of temperature sensors, and the case feature matrix is +.>Any one matrix element is marked as +.>If transient warning degree->Greater than or equal to 1, orderOtherwise let->Wherein->。
9. The system for identifying abnormal internal partial discharge temperature of a secondary fusion ring main unit according to claim 8, wherein the specific process of case classification based on feature similarity is as follows:
constructing a case classification iteration model, taking all case feature matrixes formed by the corresponding partial discharge test cases i as sample input of the L-th iteration classification, and marking as；
Taking all case feature matrixes formed by the corresponding partial discharge test cases j as sample input of the L+1st iteration classificationWherein->Representing a case feature matrix correspondingly formed by partial discharge test cases j by taking the kth transient period as the collecting range of the unified scale,/>Representing the total number of transient periods contained in the partial discharge test case j, and i+.j;
output junction classifying the L-th iterationThe fruit is recorded asAnd->The output result of the L+1st iteration classification is recorded asAnd->；
The process of the L+1st iteration classification is as follows:
selecting all case feature matrixes formed by any partial discharge test case x as analog input of L+1st iteration classification, and marking asWherein->Representing a case feature matrix correspondingly formed by partial discharge test case x by taking the mth transient period as the collecting range of the unified scale,/for the test case x>Represents the total number of transient periods contained in partial discharge test case x, and +.>；
Based on sample inputAnd analog input +.>The case feature similarity between the partial discharge test case j and the partial discharge test case x is calculated, and the specific calculation formula is as follows:
；
wherein,representing the similarity of case features between the partial discharge test case j and the partial discharge test case x,representing case feature matrix->And case feature matrix->The number of 1's contained in the intersection set, +.>Representing case feature matrix->And case feature matrix->The number of 1's contained in the union set;
presetting a similarity threshold, if the case features are similarIf the similarity threshold is greater than or equal to the similarity threshold, storing the partial discharge test case into the output result +.>In (a) and (b);
when collectingAll partial discharge test cases and partial discharge test case jAfter the case feature similarity analysis, entering the next iteration; and after the iteration classification of all the partial discharge test cases is finished, stopping the iteration, and outputting an output result of each iteration.
10. The system for identifying abnormal internal partial discharge temperature of a secondary fusion ring main unit according to claim 9, wherein the specific process of integrating the first test data cluster based on the case classification result is as follows:
randomly select one output resultBased on the first test data cluster +.>In outputting the result->In the first test data cluster corresponding to each partial discharge test case, obtaining the maximum value and the minimum value of the control parameters correspondingly set by the ring main unit internal equipment r, obtaining the abnormal control parameter range of the ring main unit internal equipment r, and recording in a table form.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410238450.8A CN117828448A (en) | 2024-03-04 | 2024-03-04 | Internal partial discharge temperature anomaly identification system for primary and secondary fusion ring main unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410238450.8A CN117828448A (en) | 2024-03-04 | 2024-03-04 | Internal partial discharge temperature anomaly identification system for primary and secondary fusion ring main unit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117828448A true CN117828448A (en) | 2024-04-05 |
Family
ID=90508239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410238450.8A Pending CN117828448A (en) | 2024-03-04 | 2024-03-04 | Internal partial discharge temperature anomaly identification system for primary and secondary fusion ring main unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117828448A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118092901A (en) * | 2024-04-25 | 2024-05-28 | 矽柏(南京)信息技术有限公司 | Data management method and system for interface development |
-
2024
- 2024-03-04 CN CN202410238450.8A patent/CN117828448A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118092901A (en) * | 2024-04-25 | 2024-05-28 | 矽柏(南京)信息技术有限公司 | Data management method and system for interface development |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117828448A (en) | Internal partial discharge temperature anomaly identification system for primary and secondary fusion ring main unit | |
| US8255522B2 (en) | Event detection from attributes read by entities | |
| CN112434208A (en) | Training of isolated forest and identification method and related device of web crawler of isolated forest | |
| JP5772546B2 (en) | Operation quality prediction device, operation quality prediction method, computer program, and computer-readable storage medium | |
| CN111860692B (en) | Abnormal data detection method based on K-media in Internet of things environment | |
| CN116148679A (en) | Battery health state prediction method and related device | |
| CN115510302B (en) | Intelligent factory data classification method based on big data statistics | |
| CN111191909A (en) | Electricity stealing identification system based on data analysis of typical electricity stealing industry and historical electricity stealing sample library | |
| CN115905990A (en) | Transformer oil temperature abnormity monitoring method based on density aggregation algorithm | |
| US11954945B2 (en) | Systems and methods for analyzing machine performance | |
| CN116522156A (en) | Equipment state data analysis system and method based on energy management platform | |
| CN115617784A (en) | Data processing system and processing method for informationized power distribution | |
| CN102385632A (en) | Method and system for log automatic classification and notification | |
| CN112330095A (en) | Quality management method based on decision tree algorithm | |
| CN116049766A (en) | Multisource data anomaly monitoring system based on digital twin | |
| CN114610553A (en) | Intelligent equipment detection system and detection method thereof | |
| CN117783745B (en) | Data online monitoring method and system for battery replacement cabinet | |
| CN117277566B (en) | Power grid data analysis power dispatching system and method based on big data | |
| CN107451029A (en) | A kind of information processing method and device, equipment | |
| Wang et al. | An artificial immune and incremental learning inspired novel framework for performance pattern identification of complex electromechanical systems | |
| CN117171157A (en) | Clearing data acquisition and cleaning method based on data analysis | |
| CN110874601B (en) | Method for identifying running state of equipment, state identification model training method and device | |
| CN115062725B (en) | Hotel income anomaly analysis method and system | |
| CN117675230A (en) | Knowledge-graph-based oil well data integrity identification method | |
| CN108627242B (en) | Ring cooling machine air leakage rate detection method based on blind source separation unilateral detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |