CN113722145B - Method and device for rapidly identifying homologous anomaly in vacuum semantic environment - Google Patents
Method and device for rapidly identifying homologous anomaly in vacuum semantic environment Download PDFInfo
- Publication number
- CN113722145B CN113722145B CN202111297361.3A CN202111297361A CN113722145B CN 113722145 B CN113722145 B CN 113722145B CN 202111297361 A CN202111297361 A CN 202111297361A CN 113722145 B CN113722145 B CN 113722145B
- Authority
- CN
- China
- Prior art keywords
- characteristic
- homologous
- branch
- odd
- feature
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000002159 abnormal effect Effects 0.000 claims abstract description 84
- 230000005856 abnormality Effects 0.000 claims abstract description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 6
- 230000008859 change Effects 0.000 abstract description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F11/1076—Parity data used in redundant arrays of independent storages, e.g. in RAID systems
- G06F11/1096—Parity calculation or recalculation after configuration or reconfiguration of the system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1448—Management of the data involved in backup or backup restore
Abstract
The invention discloses a method and a device for rapidly identifying homologous abnormality in a vacuum semantic environment, wherein the method comprises the following steps: obtaining waveform characteristics in double sets of bus differential protection current branch channels without channel semantic identification, and judging whether values of the waveform characteristics in at least two current branch channels are smaller than corresponding homologous characteristic thresholds or not; if the values of the waveform characteristics in the at least two current branch channels are not less than the corresponding homologous characteristic threshold values, combining the waveform characteristics in the at least two current branch channels into corresponding characteristic sequences; counting the number of odd numbers and even numbers of the characteristic sequences; and when the odd number and the even number coexist in the characteristic sequence, carrying out abnormal branch positioning on at least two current branch channels. The problem that the bus differential protection device in the prior art needs to depend on the limitation condition of pre-configuration of the channel semantic environment in the homologous detection is solved, and therefore the system configuration complexity and the daily workload caused by rapid change of a power grid structure are greatly reduced.
Description
Technical Field
The invention belongs to the technical field of intelligent substation sampling loop abnormity diagnosis, and particularly relates to a method and a device for rapidly identifying homologous abnormity in a vacuum semantic environment.
Background
When the power grid is in a high-quality new normal state, the intelligent application requirement of big data is urgent, and the improvement of the intelligent level is urgently needed particularly in the aspects of system linkage, prospective precontrol, auxiliary decision and the like. The conventional remote circuit abnormity accurate diagnosis scheme realizes the conversion from the surface hidden danger to the deep hidden danger, and has a good effect of improving the power grid analysis and diagnosis capability in advance. However, the recording homologous detection of the two sets of protection devices faces the actual situation that the identification information of the internal channel of the unique bus differential protection device of the power system is generally completely absent (vacuum), the similarity calculation method based on the word meaning editing distance in the prior art cannot be implemented, and the homologous detection seems to be an insurmountable step for the normal operation of the whole set of system.
At present, for the actual condition that the channel identification information is generally completely absent (vacuum), the solutions that can be provided mainly surround the schemes of configuring the channel information comparison relation table in advance, upgrading and configuring all protection devices, and the like. On one hand, the feasibility of power failure configuration work under the requirement of high-reliability operation and maintenance of a power grid is protected, and only the workload is increased in the early stage of the construction of the early warning system, the rapid change of the power grid structure cannot be adapted to, operation and maintenance personnel at a dispatching end are highly dependent on mastering new, changed and expanded engineering projects in global monitoring equipment at any time, and the like, so that the 'intelligent mode' under the background of big data fusion is necessary to be greatly discounted. On the other hand, the artificial intelligence-based training model achieves the expected effect when aiming at the situation that whether huge and complex tidal current operation data of the power system can be overlapped under the condition of limited amount of station data with limited characteristic range and different power grid geographic frame information fingerprints, and even the data granularity is seriously damaged, so that the professional field is particularly cautious in the selection of the technical route.
Disclosure of Invention
The invention provides a method and a device for rapidly identifying homologous anomalies in a vacuum semantic environment, which are used for solving at least one of the technical problems.
In a first aspect, the present invention provides a method for rapidly identifying homologous anomalies in a vacuum semantic environment, which is characterized by comprising: obtaining waveform characteristics in double sets of bus differential protection current branch channels without channel semantic identification, and judging whether values of the waveform characteristics in at least two current branch channels are both smaller than corresponding homologous characteristic thresholds; if the values of the waveform characteristics in at least two of the current branch channels are not less than the corresponding homologous characteristic threshold values, combining all the waveform characteristics in at least two of the current branch channels into a corresponding characteristic sequence; counting the number of odd and even numbers of the characteristic sequence based on the principle that the number of abnormal waveform characteristic combinations caused by abnormal characteristic waveforms is an odd number; when an odd number and an even number coexist in the characteristic sequence, performing abnormal branch positioning on at least two current branch channels, wherein the abnormal branch positioning specifically comprises the following steps: when the odd and even combinations in the feature sequence are '1' + 'even numbers', judging that the abnormal branch is a '1' + '1' characteristic channel, and simultaneously judging that the branch corresponding to the '1' + '1' is a homologous branch, recording the homologous branch to a homologous information backup table, and updating the feature sequence with the even number of '2' into the homologous information backup table; when the odd and even combinations in the characteristic sequence are '1' + 'odd' + 'even', the abnormal branch is judged to be a '1' characteristic channel, and the characteristic sequence with the even number of '2' is updated to enter a homologous information backup table; when the combination of the odd number and the even number in the characteristic sequence is 'odd number not 1' + 'even number', judging that the abnormal branch exists in the characteristic channels with 'odd number not 1', and updating the characteristic sequence with '2' as the even number into the homologous information backup table.
In a second aspect, the present invention provides a device for rapidly identifying homologous anomalies in a vacuum semantic environment, including: the judging module is configured to obtain waveform characteristics in the current branch channels of the double-set bus differential protection without channel semantic identification, and judge whether values of the waveform characteristics in at least two current branch channels are both smaller than corresponding homologous characteristic thresholds; the combination module is configured to combine all waveform characteristics in at least two current branch channels into a corresponding characteristic sequence if the values of the waveform characteristics in at least two current branch channels are not less than the corresponding homologous characteristic threshold values; the counting module is configured to count the number of odd numbers and even numbers of the characteristic sequences based on the principle that the number of abnormal waveform characteristic combinations caused by abnormal characteristic waveforms is an odd number; the analysis module is configured to perform abnormal branch positioning on at least two current branch channels when an odd number and an even number coexist in the feature sequence, wherein the abnormal branch positioning specifically includes: when the odd and even combinations in the feature sequence are '1' + 'even numbers', judging that the abnormal branch is a '1' + '1' characteristic channel, and simultaneously judging that the branch corresponding to the '1' + '1' is a homologous branch, recording the homologous branch to a homologous information backup table, and updating the feature sequence with the even number of '2' into the homologous information backup table; when the odd and even combinations in the characteristic sequence are '1' + 'odd' + 'even', the abnormal branch is judged to be a '1' characteristic channel, and the characteristic sequence with the even number of '2' is updated to enter a homologous information backup table; when the combination of the odd number and the even number in the characteristic sequence is 'odd number not 1' + 'even number', judging that the abnormal branch exists in the characteristic channels with 'odd number not 1', and updating the characteristic sequence with '2' as the even number into the homologous information backup table.
In a third aspect, an electronic device is provided, comprising: the system comprises at least one processor and a memory which is in communication connection with the at least one processor, wherein the memory stores instructions which can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the steps of the homologous anomaly rapid identification method in the vacuum semantic environment according to any embodiment of the invention.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, the computer program including program instructions, which when executed by a computer, cause the computer to execute the steps of a method for quickly identifying homologous anomalies in a vacuum semantic environment according to any one of the embodiments of the present invention.
The utility model provides a homologous anomaly quick identification method and device under vacuum semantic environment, adopts and causes the principle that unusual waveform feature combination number is the odd based on unusual characteristic waveform, right the quantity statistics count of odd, even is carried out to the feature sequence for whether there are unusual branch and unusual branch position through the judgement of the characteristic odd-even in the feature sequence, solved among the prior art that the homologism detection of bus differential protection device needs to rely on the restriction condition of pre-configuration channel semantic environment, thereby reduced the daily work volume that system configuration complexity and grid structure rapid change brought by a wide margin.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a flowchart of a method for rapidly identifying homologous anomalies in a vacuum semantic environment according to an embodiment of the present invention;
fig. 2 is a block diagram of a device for rapidly identifying homologous anomalies in a vacuum semantic environment according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a method for rapidly identifying homologous anomalies in a vacuum semantic environment is shown.
As shown in fig. 1, a method for rapidly identifying homologous anomalies in a vacuum semantic environment includes the following steps: step S101, obtaining waveform characteristics in double sets of bus differential protection current branch channels without channel semantic identification, and judging whether values of the waveform characteristics in at least two current branch channels are both smaller than corresponding homologous characteristic threshold values.
In this embodiment, the waveform characteristics include a fundamental wave characteristic, a direct current characteristic, a harmonic component characteristic, and a current initial angle characteristic, and if values of the fundamental wave characteristic, the direct current characteristic, the harmonic component characteristic, and the current initial angle characteristic in at least two of the current branch channels are not less than corresponding fundamental wave characteristic threshold values, direct current characteristic threshold values, harmonic component characteristic threshold values, and current initial angle characteristic threshold values, the waveform characteristics in at least two of the current branch channels are combined into corresponding characteristic sequences.
Step S102, if the values of the waveform features in at least two of the current branch channels are not less than the corresponding homologous feature threshold, combining all the waveform features in at least two of the current branch channels into a corresponding feature sequence.
In the embodiment, by considering and fusing a plurality of and multiple homologous feature identification conditions (a fundamental wave feature threshold value, a direct current feature threshold value, a harmonic component feature threshold value and a current initial angle feature threshold value), the accuracy of feature combination identification can be improved, the misjudgment can be reduced, the homologous information backup table corresponding to one can be established quickly and accurately, and in addition, the phenomenon that abnormal branches cannot be positioned can be avoided as much as possible, so that the positioning accuracy is improved.
And step S103, counting the number of odd numbers and even numbers of the characteristic sequences based on the principle that the number of the abnormal waveform characteristic combinations caused by the abnormal characteristic waveforms is an odd number.
In this embodiment, the statistical counting of the number of odd and even numbers is performed on the feature sequence by using the principle that the number of abnormal waveform feature combinations is an odd number due to the abnormal feature waveform, so that whether an abnormal branch exists and the position of the abnormal branch is determined by the feature parity in the feature sequence.
Step S104, when an odd number and an even number coexist in the characteristic sequence, performing abnormal branch positioning on at least two current branch channels, wherein the method specifically comprises the following steps:
when the odd and even combinations in the feature sequence are '1' + 'even numbers', judging that the abnormal branch is a '1' + '1' characteristic channel, and simultaneously judging that the branch corresponding to the '1' + '1' is a homologous branch, recording the homologous branch to a homologous information backup table, and updating the feature sequence with the even number of '2' into the homologous information backup table;
when the odd and even combinations in the characteristic sequence are '1' + 'odd' + 'even', the abnormal branch is judged to be a '1' characteristic channel, and the characteristic sequence with the even number of '2' is updated to enter a homologous information backup table;
when the combination of the odd number and the even number in the characteristic sequence is 'odd number not 1' + 'even number', judging that the abnormal branch exists in the characteristic channels with 'odd number not 1', and updating the characteristic sequence with '2' as the even number into the homologous information backup table.
According to the method, under the condition that the time windows of double-set bus protection wave recording files in the early warning range of the sampling loop of the transformer substation with the voltage level of 220kV or above are consistent and the unique current loop abnormal point exists, the odd number and the even number of the abnormal waveform feature combination are counted by adopting the principle that the number of the abnormal waveform feature combination is the odd number based on the abnormal feature waveform, so that whether the abnormal branch exists and the position of the abnormal branch is judged according to the feature odd number and the even number in the feature sequence, the limiting condition that the homologism detection of a bus differential protection device in the prior art needs to depend on the semantic environment of a pre-configured channel is solved, and the system configuration complexity and the daily workload caused by the rapid change of a power grid structure are greatly reduced. Compared with the artificial intelligence method which needs abundant data training, such as machine learning, neural network and the like, adopted in the prior art, the method is easier to understand and master, and the function realization is simpler; meanwhile, compared with the method based on the upper and lower limit range matching of channel data, the temporary fault and steady state resolution and the feature matching, the method based on the mutation feature search matching and the like in the prior art, the method is realized in an algorithm.
In some optional embodiments, the method further comprises: and when the characteristic sequences are even numbers, automatically recording and matching channels of at least two current branch channels, and storing the channels in an established homologous information backup table. Therefore, the channel which enters the homologous information backup can be directly subjected to homologous comparison, the number counting mode judgment of odd numbers and even numbers is not performed any more, when two abnormal points occur in the homologous channel backed up by the homologous information backup table due to unforeseen reasons, the homologous information backup table is deleted, and the characteristic sequence combination is reestablished.
In a specific embodiment, a method for rapidly identifying homologous anomalies in a vacuum semantic environment of the application includes the following steps: (1) the system automatically carries out homologous comparison (fundamental component comparison) in a conventional mode on the branch channels with the established one-to-one correspondence according to the homologous information backup table, and deletes the homologous information backup table when two groups of abnormal channels appear in the step, namely all the channels are regarded as not establishing the one-to-one correspondence; (2) the system extracts the waveform characteristics of the branch channels (without channel semantic identifiers) which do not establish the one-to-one correspondence relationship, and stores the waveform characteristics as a corresponding characteristic sequence combination; (3) counting the number of odd numbers and even numbers of the extracted waveform feature combinations; (4) when all waveform feature combinations are even numbers, judging that the abnormality identification conclusion is abnormal, starting automatic recording and matching of feature channels, updating and storing a homologous information backup table, and ending the whole process; (5) when the waveform feature combination has odd and even numbers, performing next abnormal branch positioning; (6) when the odd and even combination is ' 1 ' + ' 2 or 4 or 6 or other even numbers, the abnormal branch can be judged to be ' 1 ' + ' 1 ' characteristic channel, meanwhile, the branch corresponding to ' 1 ' + ' 1 ' can be judged to be the homologous branch, the homologous information backup table is updated, and the even ' 2 ' combination characteristic is updated to enter the homologous information backup table; (7) when the odd and even combination is ' 1 ' + ' 3 or 5 or 7 or other odd ' + ' 2 or 4 or 6 or other even numbers, the abnormal branch can be judged to be ' 1 ' number characteristic channel, and the even ' 2 ' combination characteristic is updated to enter the homologous information backup table; (8) when the odd and even combination is '3 or 5 or 7 or other odd' + '2 or 4 or 6 or other even numbers', the abnormal branch can be judged to exist in the characteristic channels of '3 or 5 or 7 or other odd numbers', and the even '2' combination characteristic is updated to enter the homologous information backup table; (9) when the waveform feature combinations are all odd numbers of '3, 5, 7 or other odd numbers', the abnormality identification conclusion can be judged to be abnormal.
The following detailed analysis is performed by combining with the examples, the number of the substation bus differential branches is generally different from 5 to 10, the detailed judgment process is shown by taking 6 bus differential branches as examples, and the number of other branches and the characteristic matching condition belong to one of typical modes.
1) A typical mode one:
table 1-1 the features identify the correspondence,
table 1-2 statistics of combinations of features,
and (3) analysis: as shown in tables 1-1 and 1-2 above, the parent difference is A \ B double set, and the respective waveform characteristics are labeled in the waveform characteristic column, such as characteristic 1. Wherein A1 represents the first branch of the A set of mother difference record waves, and B2 represents the second branch of the B set of mother difference record waves, the same applies below. When the threshold values of the four homologous characteristics (fundamental wave, direct current, 3-order harmonic wave and current initial angle) meet the conditions, the column of the similarity is processed with equal sign, otherwise, the column is processed with unequal sign.
According to the principle of pairing branches one by one, the number of any feature combination in the typical mode I is 2, all the branch features can be automatically recorded and matched, the number counting mode judgment logic of odd numbers and even numbers is not needed in the subsequent flow, and the mode can be judged to have no abnormal branch.
2) Typical mode two
| Wave recording of A set | Degree of similarity | B set of recording | Waveform characteristics of A set | Waveform characteristics of B set |
| A1 | ＝ | B1 | Characteristic 1 | Characteristic 1 |
| A2 | ≠ | B2 | Characteristic 2-1 | Characteristic 2-2 |
| A3 | ＝ | B3 | Characteristic 3 | Characteristic 3 |
| A4 | ＝ | B4 | Characteristic 4 | Characteristic 4 |
| A5 | ＝ | B5 | Characteristic 5 | Characteristic 5 |
| A6 | ＝ | B6 | Characteristic 6 | Characteristic 6 |
Table 2-1 the features identify the correspondence,
| characteristic combination | Number of | Odd/even |
| Characteristic 1 | 2 | Doll |
| Characteristic 2-1 | 1 | Magic card |
| Characteristic 2-2 | 1 | Magic card |
| Characteristic 3 | 2 | Doll |
| Characteristic 4 | 2 | Doll |
| Characteristic 5 | 2 | Doll |
| Characteristic 6 | 2 | Doll |
TABLE 2-2 feature combination statistics
And (3) analysis: as shown in tables 2-1 and 2-2, the number of the features 2-1 and 2-2 is 1, and the other feature combinations are even numbers, that is, 1 path of each of the A, B sets of branch channels cannot be matched with all other branches, and the odd and even number combinations show "1" + "1" + "2 or 4 or 6 or other even numbers, so that the abnormal branch can be determined to be the feature 2-1 and 2-2 channels. In this case, the other features in the table except for feature 2-X may be successfully matched and the backup table of the homologous information may be updated, or may not be successfully matched (e.g., feature 1, feature 3, feature 4, feature 5, and feature 6), but not identical to features 2-1 and 2-2. After early warning, the branch interval names corresponding to the characteristics 2-1 and 2-2 are consulted on site, and homologous comparison abnormal intervals A2 and B2 are positioned according to the one-to-one correspondence.
3) A typical mode three:
| wave recording of A set | Degree of similarity | B set of recording | Waveform characteristics of A set | Waveform characteristics of B set |
| A1 | ＝ | B1 | Characteristic 1 | Characteristic 1 |
| A2 | ≠ | B2 | Characteristic 1 | Characteristic 2-2 |
| A3 | ＝ | B3 | Characteristic 3 | Characteristic 3 |
| A4 | ＝ | B4 | Characteristic 4 | Characteristic 4 |
| A5 | ＝ | B5 | Characteristic 5 | Characteristic 5 |
| A6 | ＝ | B6 | Characteristic 6 | Characteristic 6 |
Table 3-1 the features identify the correspondence,
table 3-2 statistics of combinations of features,
and (3) analysis: as shown in tables 3-1 and 3-2, the number of the features 2-2 is 1, the number of the feature 1 combinations is 3 (including a1\ a2\ B1 channels), and the other feature combinations are even numbers, that is, when 1 path of a certain branch channel of the a set matches with 1 branch of the A, B set, 1 path of a certain branch channel of the B set fails to match with all other branches, and the odd and even combinations are "1" + "3, 5, 7, or other odd" + "2, 4, 6, or other even numbers", the abnormal branch can be determined as the feature 2-2 channel. In this case, the features 3, 4, 5, and 6 in the table may be successfully matched and the backup table of the homologous information may be updated, or may not be successfully matched (e.g., feature 4 is equal to feature 5 is equal to feature 6), but is not the same as feature 1 and feature 2-2. After early warning, the uniqueness of the characteristic 2-2 is considered, the branch interval name corresponding to the characteristic 2-2 is consulted on site, and homologous comparison abnormal intervals are located according to the one-to-one correspondence relationship, namely A2 and B2.
4) The typical mode is four:
| wave recording of A set | Degree of similarity | B set of recording | Waveform characteristics of A set | Waveform characteristics of B set |
| A1 | ＝ | B1 | Characteristic 1 | Characteristic 1 |
| A2 | ≠ | B2 | Characteristic 2-1 | Characteristic 3 |
| A3 | ＝ | B3 | Characteristic 3 | Characteristic 3 |
| A4 | ＝ | B4 | Characteristic 4 | Characteristic 4 |
| A5 | ＝ | B5 | Characteristic 5 | Characteristic 5 |
| A6 | ＝ | B6 | Characteristic 6 | Characteristic 6 |
Table 4-1 the feature recognition correspondence,
| characteristic combination | Number of | Odd/even |
| Characteristic 1 | 2 | Doll |
| Characteristic 2-1 | 1 | Magic card |
| Characteristic 3 | 3 | Magic card |
| Characteristic 4 | 2 | Doll |
| Characteristic 5 | 2 | Doll |
| Characteristic 6 | 2 | Doll |
Table 4-2 feature combination statistics,
and (3) analysis: as shown in tables 4-1 and 4-2, the number of the features 2-1 is 1, the number of the feature 3 combinations is 3 (including a3\ B2\ B3 channels), and the other feature combinations are even numbers, that is, 1 path occurs in a certain branch channel of the B set and 1 branch matches with each of the A, B set, 1 path occurs in a certain branch channel of the a set of recording waves and cannot match with all other branches, the odd and even combinations are "1" + "3 or 5 or 7 or other odd" + "2 or 4 or 6 or other even numbers", and it can be determined that the abnormal branch is the feature 2-1 channel. In this case, the features 1, 4, 5, and 6 in the table may be successfully matched and the backup table of the homologous information may be updated, or may not be successfully matched (for example, feature 1 is equal to feature 4, and feature 5 is equal to feature 6), but is not the same as feature 3 and feature 2-1. After early warning, the uniqueness of the characteristic 2-1 is considered, the branch interval name corresponding to the characteristic 2-1 is consulted on site, and homologous comparison abnormal intervals A2 and B2 are positioned according to the one-to-one correspondence.
5) A typical mode five:
| wave recording of A set | Degree of similarity | B set of recording | Waveform characteristics of A set | Waveform characteristics of B set |
| A1 | ＝ | B1 | Characteristic 1 | Characteristic 1 |
| A2 | ≠ | B2 | Characteristic 2-1 | Characteristic 3 |
| A3 | ＝ | B3 | Characteristic 3 | Characteristic 3 |
| A4 | ＝ | B4 | Characteristic 3 | Characteristic 3 |
| A5 | ＝ | B5 | Characteristic 5 | Characteristic 5 |
| A6 | ＝ | B6 | Characteristic 6 | Characteristic 6 |
Table 5-1 the features identify the correspondence,
| characteristic combination | Number of | Odd/even |
| Characteristic 1 | 2 | Doll |
| Characteristic 2-1 | 1 | Magic card |
| Characteristic 3 | 5 | Magic card |
| Characteristic 5 | 2 | Doll |
| Characteristic 6 | 2 | Doll |
Table 5-2 feature combination statistics,
and (3) analysis: similar to the exemplary mode four, only other cases where the odd and even combinations are "1" + "3 or 5 or 7 or other odd" + "2 or 4 or 6 or other even" are illustrated. At this time, the features 1, 5 and 6 in the table may be successfully matched and the homologous information backup table is updated, or the matching may not be successful (for example, feature 1 is equal to feature 5 is equal to feature 6), after the early warning, the branch interval name corresponding to the feature 2-1 is referred to on site in consideration of the uniqueness of the feature 2-1, and the homologous comparison abnormal intervals are located as a2 and B2 according to the one-to-one correspondence.
6) Typical mode six:
| wave recording of A set | Degree of similarity | B set of recording | Waveform characteristics of A set | Waveform characteristics of B set |
| A1 | ＝ | B1 | Characteristic 1 | Characteristic 1 |
| A2 | ≠ | B2 | Characteristic 1 | Characteristic 3 |
| A3 | ＝ | B3 | Characteristic 3 | Characteristic 3 |
| A4 | ＝ | B4 | Characteristic 4 | Characteristic 4 |
| A5 | ＝ | B5 | Characteristic 5 | Characteristic 5 |
| A6 | ＝ | B6 | Characteristic 6 | Characteristic 6 |
Table 6-1 the features identify the correspondence,
| characteristic combination | Number of | Odd/even |
| Characteristic 1 | 3 | Magic card |
| Characteristic 3 | 3 | Magic card |
| Characteristic 4 | 2 | Doll |
| Characteristic 5 | 2 | Doll |
| Characteristic 6 | 2 | Doll |
Table 6-2 feature combination statistics,
and (3) analysis: as shown in tables 6-1 and 6-2, the number of feature 1 and feature 3 combinations is 3 (including a1\ a2\ A3\ B1\ B2\ B3 channels), and the other feature combinations are even numbers, that is, the homologous abnormal branch and the other different two channels have matchable situations, and the odd and even combinations are "3 or 5 or 7 or other odd" + "2 or 4 or 6 or other even numbers", so that the abnormal branch can be determined to exist in the odd characteristic combination channel. The features 4, 5, and 6 in the table may be successfully matched and update the backup table of the homologous information, or may not be successfully matched (e.g., feature 4 is equal to feature 5 is equal to feature 6), but are not the same as features 1 and 3. After early warning, all branch interval names corresponding to the characteristics 1 and 3 are consulted on site, and homologous comparison abnormal intervals are positioned to be A2 and B2 according to one-to-one correspondence.
7) The typical mode seven:
| wave recording of A set | Degree of similarity | B set of recording | Waveform characteristics of A set | Waveform characteristics of B set |
| A1 | ＝ | B1 | Characteristic 1 | Characteristic 1 |
| A2 | ≠ | B2 | Characteristic 1 | Characteristic 3 |
| A3 | ＝ | B3 | Characteristic 3 | Characteristic 3 |
| A4 | ＝ | B4 | Characteristic 3 | Characteristic 3 |
| A5 | ＝ | B5 | Characteristic 1 | Characteristic 1 |
| A6 | ＝ | B6 | Characteristic 1 | Characteristic 1 |
Table 7-1 the features identify the correspondence,
| characteristic combination | Number of | Odd/even |
| Characteristic 1 | 7 | Magic card |
| Characteristic 3 | 5 | Magic card |
Table 7-2 feature combination statistics,
and (3) analysis: as shown in tables 7-1 and 7-2, only two feature combinations of feature 1 and feature 3 exist, both feature combinations are odd numbers, and the odd and even combination is "3 or 5 or 7 or other odd numbers" + "3 or 5 or 7 or other odd numbers", so that the abnormal branch can be determined to exist certainly. Because the combination quantity of the characteristics 1 and 3 is odd, the homologous information backup table cannot be updated, after early warning, all branch interval names corresponding to the characteristics 1 and 3 are consulted on site, and homologous comparison abnormal intervals are positioned according to a one-to-one correspondence relationship and are A2 and B2.
The above seven exemplary patterns cover odd and even feature combination types with all numbers of branches. The typical modes I, II, III, IV and V complete accurate abnormal branch positioning, and the typical modes six and seven can only early warn the existence of abnormal branches, but cannot give specific branch positioning. But the condition of fusing a plurality of and multiple homologous feature recognition is adopted, so that the situations of six and seven typical modes can be avoided as much as possible, and the positioning accuracy is improved. In summary, based on the above seven types of prediction modes, the homologous detection target of the sampling loop hidden danger diagnosis system is completed.
Referring to fig. 2, a block diagram of a device for rapidly identifying homologous anomalies in a vacuum semantic environment is shown.
As shown in fig. 2, the apparatus 200 for rapidly identifying homologous anomalies includes a determining module 210, a combining module 220, a counting module 230, and an analyzing module 240.
The judging module 210 is configured to obtain waveform characteristics in two sets of bus differential protection current branch channels without channel semantic identifiers, and judge whether values of the waveform characteristics in at least two current branch channels are both smaller than corresponding homologous characteristic thresholds; a combining module 220 configured to combine all waveform features in at least two of the current branch channels into a corresponding one of the feature sequences if the values of the waveform features in at least two of the current branch channels are not less than the corresponding homologous feature threshold values; the counting module 230 is configured to count the number of odd-numbered and even-numbered characteristic sequences based on the principle that the number of abnormal waveform characteristic combinations caused by abnormal characteristic waveforms is an odd number; an analysis module 240 configured to perform abnormal branch location on at least two of the current branch channels when an odd number and an even number coexist in the feature sequence, wherein the abnormal branch location specifically includes: when the odd and even combinations in the feature sequence are '1' + 'even numbers', judging that the abnormal branch is a '1' + '1' characteristic channel, and simultaneously judging that the branch corresponding to the '1' + '1' is a homologous branch, recording the homologous branch to a homologous information backup table, and updating the feature sequence with the even number of '2' into the homologous information backup table; when the odd and even combinations in the characteristic sequence are '1' + 'odd' + 'even', the abnormal branch is judged to be a '1' characteristic channel, and the characteristic sequence with the even number of '2' is updated to enter a homologous information backup table; when the combination of the odd number and the even number in the characteristic sequence is 'odd number not 1' + 'even number', judging that the abnormal branch exists in the characteristic channels with 'odd number not 1', and updating the characteristic sequence with '2' as the even number into the homologous information backup table.
It should be understood that the modules depicted in fig. 2 correspond to various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are also applicable to the modules in fig. 2, and are not described again here.
In other embodiments, the present invention further provides a computer-readable storage medium, where computer-executable instructions are stored, where the computer-executable instructions may execute the method for fast identifying homologous anomalies in a vacuum semantic environment in any of the above method embodiments;
as one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
obtaining waveform characteristics in double sets of bus differential protection current branch channels without channel semantic identification, and judging whether values of the waveform characteristics in at least two current branch channels are both smaller than corresponding homologous characteristic thresholds;
if the values of the waveform characteristics in at least two of the current branch channels are not less than the corresponding homologous characteristic threshold values, combining all the waveform characteristics in at least two of the current branch channels into a corresponding characteristic sequence;
counting the number of odd and even numbers of the characteristic sequence based on the principle that the number of abnormal waveform characteristic combinations caused by abnormal characteristic waveforms is an odd number;
and when the odd number and the even number coexist in the characteristic sequence, carrying out abnormal branch positioning on at least two current branch channels.
The computer-readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the homologous abnormality rapid recognition apparatus in a vacuum semantic environment, or the like. Further, the computer-readable storage medium may include high speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the computer readable storage medium optionally includes a memory remotely located from the processor, and the remote memory may be connected to the homologous anomaly fast recognition apparatus in a vacuum semantic environment via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330, and the output device 340 may be connected by a bus or other means, such as the bus connection in fig. 3. The memory 320 is the computer-readable storage medium described above. The processor 310 executes various functional applications and data processing of the server by running the nonvolatile software programs, instructions and modules stored in the memory 320, namely, the method for rapidly identifying homologous anomalies in a vacuum semantic environment of the above-described method embodiment is realized. The input device 330 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the homologous anomaly fast recognition device in a vacuum semantic environment. The output device 340 may include a display device such as a display screen.
The electronic device can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
As an embodiment, the electronic device is applied to a device for rapidly identifying homologous anomalies in a vacuum semantic environment, and is used for a client, and the device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to:
obtaining waveform characteristics in double sets of bus differential protection current branch channels without channel semantic identification, and judging whether values of the waveform characteristics in at least two current branch channels are both smaller than corresponding homologous characteristic thresholds;
if the values of the waveform characteristics in at least two of the current branch channels are not less than the corresponding homologous characteristic threshold values, combining all the waveform characteristics in at least two of the current branch channels into a corresponding characteristic sequence;
counting the number of odd and even numbers of the characteristic sequence based on the principle that the number of abnormal waveform characteristic combinations caused by abnormal characteristic waveforms is an odd number;
and when the odd number and the even number coexist in the characteristic sequence, carrying out abnormal branch positioning on at least two current branch channels.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (5)
1. A method for rapidly identifying homologous anomalies in a vacuum semantic environment is characterized by comprising the following steps:
obtaining waveform characteristics in double sets of bus differential protection current branch channels without channel semantic identification, and judging whether values of the waveform characteristics in at least two current branch channels are smaller than corresponding homologous characteristic threshold values, wherein the waveform characteristics comprise fundamental wave characteristics, direct current characteristics, harmonic component characteristics and current initial angle characteristics;
if the values of the fundamental wave feature, the direct current feature, the harmonic component feature and the current initial angle feature in the at least two current branch channels are not less than the corresponding fundamental wave feature threshold value, the direct current feature threshold value, the harmonic component feature threshold value and the current initial angle feature threshold value, combining all waveform features in the at least two current branch channels into a corresponding feature sequence;
counting the number of odd and even numbers of the characteristic sequence based on the principle that the number of abnormal waveform characteristic combinations caused by abnormal characteristic waveforms is an odd number;
when an odd number and an even number coexist in the characteristic sequence, performing abnormal branch positioning on at least two current branch channels, wherein the abnormal branch positioning specifically comprises the following steps:
when the odd and even combinations in the feature sequence are '1' + 'even numbers', judging that the abnormal branch is a '1' + '1' characteristic channel, and simultaneously judging that the branch corresponding to the '1' + '1' is a homologous branch, recording the homologous branch to a homologous information backup table, and updating the feature sequence with the even number of '2' into the homologous information backup table;
when the odd and even combinations in the characteristic sequence are '1' + 'odd' + 'even', the abnormal branch is judged to be a '1' characteristic channel, and the characteristic sequence with the even number of '2' is updated to enter a homologous information backup table;
when the combination of the odd number and the even number in the characteristic sequence is 'odd number not 1' + 'even number', judging that the abnormal branch exists in the characteristic channels with 'odd number not 1', and updating the characteristic sequence with '2' as the even number into the homologous information backup table.
2. The method for rapidly identifying homologous abnormality in vacuum semantic environment according to claim 1, wherein after counting the number of odd and even numbers of the feature sequences based on the principle that the number of abnormal waveform feature combinations caused by abnormal feature waveforms is odd, the method further comprises:
and when the characteristic sequences are even numbers, automatically recording and matching channels of at least two current branch channels, and storing the channels in an established homologous information backup table.
3. A device for rapidly identifying homologous anomalies in a vacuum semantic environment is characterized by comprising:
the judging module is configured to acquire waveform characteristics in double sets of current branch channels with bus differential protection and without channel semantic identification, and judge whether values of the waveform characteristics in at least two current branch channels are smaller than corresponding homologous characteristic threshold values, wherein the waveform characteristics comprise fundamental wave characteristics, direct current characteristics, harmonic component characteristics and current initial angle characteristics;
the combination module is configured to combine all waveform characteristics in at least two current branch channels into a corresponding characteristic sequence if the values of the fundamental wave characteristic, the direct current characteristic, the harmonic component characteristic and the current initial angle characteristic in at least two current branch channels are not less than the corresponding fundamental wave characteristic threshold value, the direct current characteristic threshold value, the harmonic component characteristic threshold value and the current initial angle characteristic threshold value;
the counting module is configured to count the number of odd numbers and even numbers of the characteristic sequences based on the principle that the number of abnormal waveform characteristic combinations caused by abnormal characteristic waveforms is an odd number;
the analysis module is configured to perform abnormal branch positioning on at least two current branch channels when an odd number and an even number coexist in the feature sequence, wherein the abnormal branch positioning specifically includes:
when the odd and even combinations in the feature sequence are '1' + 'even numbers', judging that the abnormal branch is a '1' + '1' characteristic channel, and simultaneously judging that the branch corresponding to the '1' + '1' is a homologous branch, recording the homologous branch to a homologous information backup table, and updating the feature sequence with the even number of '2' into the homologous information backup table;
when the odd and even combinations in the characteristic sequence are '1' + 'odd' + 'even', the abnormal branch is judged to be a '1' characteristic channel, and the characteristic sequence with the even number of '2' is updated to enter a homologous information backup table;
when the combination of the odd number and the even number in the characteristic sequence is 'odd number not 1' + 'even number', judging that the abnormal branch exists in the characteristic channels with 'odd number not 1', and updating the characteristic sequence with '2' as the even number into the homologous information backup table.
4. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any of claims 1-2.
5. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111297361.3A CN113722145B (en) | 2021-11-04 | 2021-11-04 | Method and device for rapidly identifying homologous anomaly in vacuum semantic environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111297361.3A CN113722145B (en) | 2021-11-04 | 2021-11-04 | Method and device for rapidly identifying homologous anomaly in vacuum semantic environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113722145A CN113722145A (en) | 2021-11-30 |
| CN113722145B true CN113722145B (en) | 2022-03-11 |
Family
ID=78686568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111297361.3A Active CN113722145B (en) | 2021-11-04 | 2021-11-04 | Method and device for rapidly identifying homologous anomaly in vacuum semantic environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113722145B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916989A (en) * | 2010-08-20 | 2010-12-15 | 国网电力科学研究院 | Method for distinguishing effectiveness two-time continuous sampling values of electric power system |
| KR20110059245A (en) * | 2009-11-27 | 2011-06-02 | 주식회사 비콘 | Extraction method of fault point using mother wavelet transform in distribution system |
| CN110011414A (en) * | 2019-03-15 | 2019-07-12 | 云南电网有限责任公司红河供电局 | The intelligent substation sampling circuit failure judgment method compared based on same source data |
| CN110646689A (en) * | 2019-09-10 | 2020-01-03 | 许继集团有限公司 | Traveling wave distance measurement method and device adopting same-source double-sampling mode |
| CN111247442A (en) * | 2017-10-24 | 2020-06-05 | 三菱电机株式会社 | Abnormality diagnosis device, abnormality diagnosis method, and abnormality diagnosis system |
| CN111458598A (en) * | 2020-02-18 | 2020-07-28 | 南京国电南自电网自动化有限公司 | Method for aligning multiple homologous recording waveforms of asynchronous sampling |
| CN112014689A (en) * | 2020-10-19 | 2020-12-01 | 国网江西省电力有限公司电力科学研究院 | Method and device for diagnosing abnormity of current sampling loop |
| CN112506867A (en) * | 2020-11-18 | 2021-03-16 | 中国南方电网有限责任公司 | Recording comparison analysis method based on time deviation management |
| CN112633412A (en) * | 2021-01-05 | 2021-04-09 | 南方电网深圳数字电网研究院有限公司 | Abnormal electricity consumption detection method, equipment and storage medium |
| CN112910089A (en) * | 2021-01-25 | 2021-06-04 | 国网山东省电力公司青岛供电公司 | Transformer substation secondary equipment fault logic visualization method and system |
| CN113238890A (en) * | 2021-07-12 | 2021-08-10 | 国网江西省电力有限公司电力科学研究院 | Current sampling loop abnormity diagnosis method and device based on dynamic record data |
| CN113281609A (en) * | 2021-04-23 | 2021-08-20 | 湖南天联勘测设计有限公司 | Active traveling wave positioning method, system and storage medium for power distribution network fault based on multiple sampling points |
| CN113589100A (en) * | 2021-07-26 | 2021-11-02 | 国电南瑞科技股份有限公司 | Abnormal discharge identification method based on bidirectional long-short term memory and attention mechanism |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750518A (en) * | 2019-10-12 | 2020-02-04 | 华北电力大学 | Simultaneous line loss abnormal data restoration method based on singular value decomposition |
| CN110942084A (en) * | 2019-10-12 | 2020-03-31 | 华北电力大学 | Loss reduction measure making method based on synchronous line loss abnormity identification |
-
2021
- 2021-11-04 CN CN202111297361.3A patent/CN113722145B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110059245A (en) * | 2009-11-27 | 2011-06-02 | 주식회사 비콘 | Extraction method of fault point using mother wavelet transform in distribution system |
| CN101916989A (en) * | 2010-08-20 | 2010-12-15 | 国网电力科学研究院 | Method for distinguishing effectiveness two-time continuous sampling values of electric power system |
| CN111247442A (en) * | 2017-10-24 | 2020-06-05 | 三菱电机株式会社 | Abnormality diagnosis device, abnormality diagnosis method, and abnormality diagnosis system |
| CN110011414A (en) * | 2019-03-15 | 2019-07-12 | 云南电网有限责任公司红河供电局 | The intelligent substation sampling circuit failure judgment method compared based on same source data |
| CN110646689A (en) * | 2019-09-10 | 2020-01-03 | 许继集团有限公司 | Traveling wave distance measurement method and device adopting same-source double-sampling mode |
| CN111458598A (en) * | 2020-02-18 | 2020-07-28 | 南京国电南自电网自动化有限公司 | Method for aligning multiple homologous recording waveforms of asynchronous sampling |
| CN112014689A (en) * | 2020-10-19 | 2020-12-01 | 国网江西省电力有限公司电力科学研究院 | Method and device for diagnosing abnormity of current sampling loop |
| CN112506867A (en) * | 2020-11-18 | 2021-03-16 | 中国南方电网有限责任公司 | Recording comparison analysis method based on time deviation management |
| CN112633412A (en) * | 2021-01-05 | 2021-04-09 | 南方电网深圳数字电网研究院有限公司 | Abnormal electricity consumption detection method, equipment and storage medium |
| CN112910089A (en) * | 2021-01-25 | 2021-06-04 | 国网山东省电力公司青岛供电公司 | Transformer substation secondary equipment fault logic visualization method and system |
| CN113281609A (en) * | 2021-04-23 | 2021-08-20 | 湖南天联勘测设计有限公司 | Active traveling wave positioning method, system and storage medium for power distribution network fault based on multiple sampling points |
| CN113238890A (en) * | 2021-07-12 | 2021-08-10 | 国网江西省电力有限公司电力科学研究院 | Current sampling loop abnormity diagnosis method and device based on dynamic record data |
| CN113589100A (en) * | 2021-07-26 | 2021-11-02 | 国电南瑞科技股份有限公司 | Abnormal discharge identification method based on bidirectional long-short term memory and attention mechanism |
Non-Patent Citations (3)
| Title |
|---|
| Study of Non-Conventional Instrument Transformer and IEC61850 impact on current differential protection;K. L. 等;《2008 IEEE/PES Transmission and Distribution Conference and Exposition: Latin America》;20081010;第1-6页 * |
| 一种高度集成智能变电站二次运维平台的研究与应用;李远 等;《湖北电力》;20190228;第43卷(第1期);第25-30页 * |
| 智能变电站继电保护二次回路在线监测与故障诊断技术;叶远波 等;《电力系统保护与控制》;20161016;第44卷(第20期);第148-153页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113722145A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210512B (en) | Automatic log anomaly detection method and system | |
| CN105303469A (en) | Method and system for line loss abnormal reason data mining and analysis | |
| EP4155974A1 (en) | Knowledge graph construction method and apparatus, check method and storage medium | |
| CN114598539B (en) | Root cause positioning method and device, storage medium and electronic equipment | |
| CN109241169A (en) | The multi-source heterogeneous data fusion geo-database integration method of power distribution network operation information | |
| CN113987190B (en) | Data quality check rule extraction method and system | |
| CN111930597B (en) | Log abnormality detection method based on transfer learning | |
| CN116152016A (en) | Power distribution network fault positioning method, device, equipment and storage medium | |
| CN113722145B (en) | Method and device for rapidly identifying homologous anomaly in vacuum semantic environment | |
| CN116204846B (en) | Method for rapidly positioning abnormal sensor data of power distribution network based on visible graph | |
| CN108121796A (en) | Electric energy metering device failure analysis methods and device based on confidence level | |
| CN110059126B (en) | LKJ abnormal value data-based complex correlation network analysis method and system | |
| CN107025293A (en) | A kind of second power equipment defective data method for digging and system | |
| CN110582091B (en) | Method and apparatus for locating wireless quality problems | |
| US20170242841A1 (en) | Theft detection via adaptive lexical similarity analysis of social media data streams | |
| CN110941910A (en) | Intelligent auxiliary method and system for power grid three-dimensional design review | |
| CN110727538B (en) | Fault positioning system and method based on model hit probability distribution | |
| CN115952165A (en) | Whole-network constant value rapid checking method and system | |
| CN205692170U (en) | A kind of battalion auxiliary tone data pretreatment | |
| US20230011129A1 (en) | Log analyzer for fault detection | |
| CN112380340B (en) | Error data diagnosis method and system between main station, power plant and transformer substation | |
| CN114722971A (en) | Low-voltage transformer area phase identification method | |
| US20220046039A1 (en) | Method, device, and computer program product for abnormality detection | |
| CN110399261B (en) | System alarm clustering analysis method based on co-occurrence graph | |
| CN111143622A (en) | Fault data set construction method based on big data platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |