CN112488871A - Method and system for eliminating redundant data of original input features of power grid - Google Patents
Method and system for eliminating redundant data of original input features of power grid Download PDFInfo
- Publication number
- CN112488871A CN112488871A CN202011151906.5A CN202011151906A CN112488871A CN 112488871 A CN112488871 A CN 112488871A CN 202011151906 A CN202011151906 A CN 202011151906A CN 112488871 A CN112488871 A CN 112488871A
- Authority
- CN
- China
- Prior art keywords
- power grid
- characteristic
- correlation factor
- original input
- data set
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012360 testing method Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 16
- 230000008030 elimination Effects 0.000 claims description 14
- 238000003379 elimination reaction Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000000546 chi-square test Methods 0.000 claims description 5
- 238000010998 test method Methods 0.000 claims description 4
- 230000001052 transient effect Effects 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008570 general process Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a method and a system for eliminating redundant data of original input features of a power grid, wherein the method comprises the following steps: acquiring an original input characteristic data set of a power grid; discretizing each characteristic quantity in the power grid original input characteristic data set to form a power grid input characteristic discrete data set; calculating a characteristic association factor set corresponding to the power grid input characteristic discrete data set based on a card method; and judging a threshold value of each correlation factor in the characteristic correlation factor set, and rejecting redundant characteristic quantity in the power grid original input characteristic data set based on a judgment result. In the embodiment of the invention, the redundant features in the input features can be effectively eliminated by utilizing the correlation degree between the input features, so that the stability of the final data is higher.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a method and a system for eliminating redundant data of original input features of a power grid.
Background
In recent years, deep learning is one of the current common artificial intelligence methods, and has a cross-over development in the aspects of feature extraction, classification and discrimination, and the like, and the deep learning has a very strong fitting capability to a nonlinear system such as a power grid. Because the redundancy of the original input features of the power grid is high, the training effect of machine learning can be influenced if the original input features are not processed, however, the selection of the original input features of the power grid at the present stage is mainly completed manually, and the method is limited by personal power grid professional knowledge, namely, the original input features of the power grid selected by different technicians have large difference, so that the redundant features cannot be effectively removed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a method and a system for removing redundant data of original input features of a power grid.
In order to solve the above problems, the present invention provides a method for removing redundant data of original input features of a power grid, wherein the method comprises:
acquiring an original input characteristic data set of a power grid;
discretizing each characteristic quantity in the power grid original input characteristic data set to form a power grid input characteristic discrete data set;
calculating a characteristic association factor set corresponding to the power grid input characteristic discrete data set based on a card method;
and judging a threshold value of each correlation factor in the characteristic correlation factor set, and rejecting redundant characteristic quantity in the power grid original input characteristic data set based on a judgment result.
Optionally, the power grid original input feature data set includes steady-state feature data before a fault and transient-state feature data after the fault.
Optionally, the calculating a feature association factor set corresponding to the power grid input feature discrete data set based on the card method includes:
and calculating test statistics between every two discrete characteristic quantities in the power grid input characteristic discrete data set based on a card method, and forming the characteristic association factor set.
Optionally, the performing threshold judgment on each correlation factor in the feature correlation factor set, and removing the redundant feature quantity in the power grid original input feature data set based on the judgment result includes:
acquiring an ith correlation factor in the characteristic correlation factor set, and judging whether the ith correlation factor is greater than a preset threshold value;
if the ith correlation factor is judged to be larger than the preset threshold value, removing the discrete characteristic quantity corresponding to the ith correlation factor;
judging whether i < N is true or not;
if the i < N is true, returning to obtain the (i + 1) th correlation factor in the characteristic correlation factor set;
and if i < N is not true, finishing the elimination processing of the redundant characteristic quantity in the power grid original input characteristic data set.
Optionally, after determining whether the ith correlation factor is greater than a preset threshold, the method further includes:
and if the ith correlation factor is judged to be less than or equal to the preset threshold value, adding the two discrete characteristic quantities corresponding to the ith correlation factor into the power grid input characteristic training set, and continuously judging whether i < N is true or not.
In addition, the embodiment of the invention also provides a system for removing the redundant data of the original input features of the power grid, which comprises the following steps:
the acquisition module is used for acquiring an original input characteristic data set of the power grid;
the processing module is used for carrying out discretization processing on each characteristic quantity in the power grid original input characteristic data set and forming a power grid input characteristic discrete data set;
the calculation module is used for calculating a characteristic association factor set corresponding to the power grid input characteristic discrete data set based on a card method test method;
and the eliminating module is used for judging the threshold value of each correlation factor in the characteristic correlation factor set and eliminating the redundant characteristic quantity in the power grid original input characteristic data set based on the judgment result.
Optionally, the power grid original input feature data set includes steady-state feature data before a fault and transient-state feature data after the fault.
Optionally, the calculation module is configured to calculate a test statistic between every two discrete feature quantities in the power grid input feature discrete data set based on a chi-square test method, and form the feature association factor set.
Optionally, the eliminating module includes:
the first judging unit is used for acquiring the ith association factor in the characteristic association factor set and judging whether the ith association factor is larger than a preset threshold value or not; if the ith correlation factor is judged to be larger than the preset threshold value, removing the discrete characteristic quantity corresponding to the ith correlation factor;
a second judging unit for judging whether i < N is true; if the i < N is true, returning to obtain the (i + 1) th correlation factor in the characteristic correlation factor set; and if i < N is not true, finishing the elimination processing of the redundant characteristic quantity in the power grid original input characteristic data set.
Optionally, the first determining unit is further configured to add the two discrete feature quantities corresponding to the ith correlation factor to the power grid input feature training set after determining that the ith correlation factor is less than or equal to the preset threshold, and continue to jump to the second determining unit for execution.
In the embodiment of the invention, through discretizing each characteristic quantity contained in the original input characteristic data set of the power grid, the complexity of the subsequent correlation analysis of the input characteristics can be reduced, and the working efficiency is improved; the redundant features in the input features can be effectively eliminated by utilizing the correlation degree between the input features, the burden of personnel can be reduced compared with the manual selection mode adopted at the present stage, and meanwhile, the existence of subjective factors can be avoided, so that the stability of the final data is higher.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for eliminating redundant data of original input features of a power grid, which is disclosed by the embodiment of the invention;
fig. 2 is a schematic structural composition diagram of a power grid original input feature redundant data elimination system disclosed in the embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Fig. 1 shows a schematic flow chart of a method for removing redundant data of original input features of a power grid in an embodiment of the present invention, where the method includes:
s101, acquiring an original input characteristic data set of a power grid;
in the embodiment of the invention, a part of power grid original input characteristic values are randomly selected from a power grid operation database by a power technician, and the power grid original input characteristic values can be steady-state characteristic data before a fault or transient characteristic data after the fault, so that a power grid original input characteristic data set is formed. Before and after the fault, the data fluctuation conditions which may occur such as branch power, bus voltage, generator output and the like are mainly used.
S102, discretizing each characteristic quantity in the power grid original input characteristic data set, and forming a power grid input characteristic discrete data set;
in the embodiment of the present invention, since the branch power, the bus voltage, and the generator output included in the power grid original input feature data set are continuous variables, if the abnormal data is directly screened out from the continuous variables, the complexity and the space overhead of the algorithm will not be increased, and here, the general process of discretizing each continuous variable includes: after sequencing each characteristic quantity in the power grid original input characteristic data set according to a rule from small to large, defining each characteristic quantity as a discrete interval, and forming the power grid input characteristic discrete data set under the condition of not changing the size of original sample data.
S103, calculating a characteristic association factor set corresponding to the power grid input characteristic discrete data set based on a card method test method;
in the embodiment of the invention, the test statistic between every two discrete characteristic quantities in the power grid input characteristic discrete data set is calculated based on a chi-square test method, and the characteristic association factor set is formed, wherein the test statistic X2The calculation method is as follows:
in the formula, AiIs a characteristic value of the i-th interval, EiIs AiExpected value of, NOA total number of samples, N, in the grid input feature discrete datasetiIs the number of samples in the i-th interval, CiIs the proportion of the characteristic value of the ith interval in the total number of samples. It should be noted that, because the discrete grid input feature data set is only a result of sorting each feature quantity in the original grid input feature data set, and any one sorted feature quantity is used as a single interval, it cannot be determined whether a feature value of the ith interval is repeated with a feature value of an adjacent interval, that is, CiThe value of (a) is an indeterminate value, which is determined by the occurrence frequency of the characteristic value of the ith interval in the total number of samples.
In addition, the test statistic between every two discrete characteristic quantities is calculated in a sequential cross calculation mode, namely the test statistic between the first interval and the second interval is calculated firstly, then the test statistic between the second interval and the third interval is calculated, then the test statistic between the third interval and the fourth interval is calculated, and the results are analogically stored in sequence, so that the close association of all the intervals can be ensured.
And S104, performing threshold judgment on each correlation factor in the characteristic correlation factor set, and rejecting redundant characteristic quantity in the power grid original input characteristic data set based on a judgment result.
The specific implementation process comprises the following steps:
(1) acquiring an ith correlation factor in the characteristic correlation factor set, and judging whether the ith correlation factor is greater than a preset threshold value;
in the implementation process, the ith correlation factor is the ith test statistic, and if the ith correlation factor is judged to be larger than the preset threshold value, the step (2) is continuously executed; and (4) if the ith correlation factor is judged to be less than or equal to the preset threshold value, continuing to execute the step (3). The preset threshold is a confidence level parameter manually acquired according to statistical knowledge, and is verified by a power technician according to empirical knowledge.
(2) Removing the discrete characteristic quantity corresponding to the ith correlation factor;
in the implementation process, because each association factor in the feature association factor set is arranged in sequence and each association factor represents the correlation between two discrete feature quantities in adjacent intervals, when the ith association factor is greater than the preset threshold, the elimination processing of abnormal data is completed by calling the judgment result of the (i-1) th association factor, and then the step (4) is skipped to execute. The elimination processing of the abnormal data comprises the following steps: when the (i-1) th association factor is larger than the preset threshold value, rejecting the minimum value of the two discrete characteristic quantities corresponding to the (i) th association factor; and when the (i-1) th association factor is smaller than or equal to the preset threshold, rejecting the maximum value in the two discrete characteristic quantities corresponding to the (i) th association factor.
(3) Adding two discrete characteristic quantities corresponding to the ith correlation factor into a power grid input characteristic training set, namely, two discrete characteristic quantities corresponding to the ith correlation factor are both non-redundant values, and then skipping to the step (4) for execution;
(4) judging whether i < N is satisfied, wherein the judgment result comprises the following steps: if the i < N is established, returning to obtain the (i + 1) th association factor in the feature association factor set, and continuously carrying out elimination judgment on the (i + 1) th association factor; and if i < N is not true, finishing the elimination processing of the redundant characteristic quantity in the power grid original input characteristic data set. Wherein N is the total number of correlation factors included in the characteristic correlation factor set.
Fig. 2 is a schematic structural composition diagram of a power grid original input feature redundant data elimination system in an embodiment of the present invention, where the system includes:
an obtaining module 201, configured to obtain an original input feature data set of a power grid;
in the embodiment of the invention, a part of power grid original input characteristic values are randomly selected from a power grid operation database by a power technician, and the power grid original input characteristic values can be steady-state characteristic data before a fault or transient characteristic data after the fault, so that a power grid original input characteristic data set is formed. Before and after the fault, the data fluctuation conditions which may occur such as branch power, bus voltage, generator output and the like are mainly used.
The processing module 202 is configured to perform discretization processing on each feature quantity in the power grid original input feature data set, and form a power grid input feature discrete data set;
in the embodiment of the present invention, since the branch power, the bus voltage, and the generator output included in the power grid original input feature data set are continuous variables, if the abnormal data is directly screened out from the continuous variables, the complexity and the space overhead of the algorithm will not be increased, and here, the general process of discretizing each continuous variable includes: after sequencing each characteristic quantity in the power grid original input characteristic data set according to a rule from small to large, defining each characteristic quantity as a discrete interval, and forming the power grid input characteristic discrete data set under the condition of not changing the size of original sample data.
The calculating module 203 is used for calculating a characteristic association factor set corresponding to the power grid input characteristic discrete data set based on a chi-square test method;
in the embodiment of the invention, the test statistic between every two discrete characteristic quantities in the power grid input characteristic discrete data set is calculated based on a chi-square test method, and the characteristic association factor set is formed, wherein the test statistic X2The calculation method is as follows:
in the formula, AiIs a characteristic value of the i-th interval, EiIs AiExpected value of, NOA total number of samples, N, in the grid input feature discrete datasetiIs the number of samples in the i-th interval, CiIs the proportion of the characteristic value of the ith interval in the total number of samples. It should be noted that, because the discrete grid input feature data set is only a result of sorting each feature quantity in the original grid input feature data set, and any one sorted feature quantity is used as a single interval, it cannot be determined whether a feature value of the ith interval is repeated with a feature value of an adjacent interval, that is, CiThe value of (a) is an indeterminate value, which is determined by the occurrence frequency of the characteristic value of the ith interval in the total number of samples.
In addition, the test statistic between every two discrete characteristic quantities is calculated in a sequential cross calculation mode, namely the test statistic between the first interval and the second interval is calculated firstly, then the test statistic between the second interval and the third interval is calculated, then the test statistic between the third interval and the fourth interval is calculated, and the results are analogically stored in sequence, so that the close association of all the intervals can be ensured.
A rejecting module 204, configured to perform threshold judgment on each correlation factor in the feature correlation factor set, and reject redundant feature quantities in the power grid original input feature data set based on a judgment result; the eliminating module 204 includes a first determining unit and a second determining unit.
Further, the specific implementation process of the first determining unit includes the following steps:
(1) acquiring an ith correlation factor in the characteristic correlation factor set, and judging whether the ith correlation factor is greater than a preset threshold value;
in the implementation process, the ith correlation factor is the ith test statistic, and if the ith correlation factor is judged to be larger than the preset threshold value, the step (2) is continuously executed; and (4) if the ith correlation factor is judged to be less than or equal to the preset threshold value, continuing to execute the step (3). The preset threshold is a confidence level parameter manually acquired according to statistical knowledge, and is verified by a power technician according to empirical knowledge.
(2) Removing the discrete characteristic quantity corresponding to the ith correlation factor;
in the implementation process, because each correlation factor in the feature correlation factor set is arranged in sequence and each correlation factor represents the correlation between two discrete feature quantities in adjacent intervals, when the ith correlation factor is greater than the preset threshold, the elimination processing of abnormal data is completed by calling the judgment result of the (i-1) th correlation factor, and then the second judgment unit is skipped to execute the abnormal data. The elimination processing of the abnormal data comprises the following steps: when the (i-1) th association factor is larger than the preset threshold value, rejecting the minimum value of the two discrete characteristic quantities corresponding to the (i) th association factor; and when the (i-1) th association factor is smaller than or equal to the preset threshold, rejecting the maximum value in the two discrete characteristic quantities corresponding to the (i) th association factor.
(3) And adding the two discrete characteristic quantities corresponding to the ith correlation factor into a power grid input characteristic training set, namely, the two discrete characteristic quantities corresponding to the ith correlation factor are both non-redundant values, and then skipping to the second judgment unit for execution.
Further, the second determining unit is configured to determine whether i < N is satisfied, and the determination result includes: if the i < N is established, returning to obtain the (i + 1) th association factor in the feature association factor set, and continuously carrying out elimination judgment on the (i + 1) th association factor; and if i < N is not true, finishing the elimination processing of the redundant characteristic quantity in the power grid original input characteristic data set. Wherein N is the total number of correlation factors included in the characteristic correlation factor set.
In the embodiment of the invention, through discretizing each characteristic quantity contained in the original input characteristic data set of the power grid, the complexity of the subsequent correlation analysis of the input characteristics can be reduced, and the working efficiency is improved; the redundant features in the input features can be effectively eliminated by utilizing the correlation degree between the input features, the burden of personnel can be reduced compared with the manual selection mode adopted at the present stage, and meanwhile, the existence of subjective factors can be avoided, so that the stability of the final data is higher.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
The method and the system for removing the redundant data of the original input features of the power grid provided by the embodiment of the invention are described in detail, a specific embodiment is adopted in the method to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for eliminating redundant data of original input features of a power grid is characterized by comprising the following steps:
acquiring an original input characteristic data set of a power grid;
discretizing each characteristic quantity in the power grid original input characteristic data set to form a power grid input characteristic discrete data set;
calculating a characteristic association factor set corresponding to the power grid input characteristic discrete data set based on a card method;
and judging a threshold value of each correlation factor in the characteristic correlation factor set, and rejecting redundant characteristic quantity in the power grid original input characteristic data set based on a judgment result.
2. The method for removing the redundant data of the original input features of the power grid according to claim 1, wherein the original input feature data set of the power grid comprises steady-state feature data before a fault and transient-state feature data after the fault.
3. The method for eliminating redundant data of original input features of a power grid according to claim 1, wherein the calculating of the feature association factor set corresponding to the discrete data set of the input features of the power grid based on the chi-square test method comprises:
and calculating test statistics between every two discrete characteristic quantities in the power grid input characteristic discrete data set based on a card method, and forming the characteristic association factor set.
4. The method for removing the redundant data of the original input features of the power grid according to claim 1, wherein the step of performing threshold judgment on each correlation factor in the feature correlation factor set and removing the redundant feature quantity in the original input feature data set of the power grid based on the judgment result comprises the steps of:
acquiring an ith correlation factor in the characteristic correlation factor set, and judging whether the ith correlation factor is greater than a preset threshold value;
if the ith correlation factor is judged to be larger than the preset threshold value, removing the discrete characteristic quantity corresponding to the ith correlation factor;
judging whether i is greater than N;
if i is greater than N, returning to obtain the (i + 1) th correlation factor in the characteristic correlation factor set;
and if i is less than N, finishing the elimination processing of the redundant characteristic quantity in the original input characteristic data set of the power grid.
5. The method for eliminating the redundant data of the original input features of the power grid according to claim 4, wherein after judging whether the ith correlation factor is greater than a preset threshold value, the method further comprises the following steps:
and if the ith correlation factor is judged to be less than or equal to the preset threshold value, adding the two discrete characteristic quantities corresponding to the ith correlation factor into the power grid input characteristic training set, and continuously judging whether i is less than N.
6. A system for removing redundant data of original input features of a power grid is characterized by comprising:
the acquisition module is used for acquiring an original input characteristic data set of the power grid;
the processing module is used for carrying out discretization processing on each characteristic quantity in the power grid original input characteristic data set and forming a power grid input characteristic discrete data set;
the calculation module is used for calculating a characteristic association factor set corresponding to the power grid input characteristic discrete data set based on a card method test method;
and the eliminating module is used for judging the threshold value of each correlation factor in the characteristic correlation factor set and eliminating the redundant characteristic quantity in the power grid original input characteristic data set based on the judgment result.
7. The grid primary input feature redundant data culling system of claim 6, wherein the grid primary input feature data set comprises steady state feature data before a fault and transient state feature data after the fault.
8. The system for removing the redundant data of the primary input features of the power grid according to claim 6, wherein the computing module is configured to compute test statistics between every two discrete feature quantities in the discrete data sets of the input features of the power grid based on a card method test method, and form the feature association factor set.
9. The system for rejecting the redundant data of the primary input features of the power grid according to claim 6, wherein the rejection module comprises:
the first judging unit is used for acquiring the ith association factor in the characteristic association factor set and judging whether the ith association factor is larger than a preset threshold value or not; if the ith correlation factor is judged to be larger than the preset threshold value, removing the discrete characteristic quantity corresponding to the ith correlation factor;
the second judgment unit is used for judging whether i is less than N; if i is greater than N, returning to obtain the (i + 1) th correlation factor in the characteristic correlation factor set; and if i is less than N, finishing the elimination processing of the redundant characteristic quantity in the original input characteristic data set of the power grid.
10. The system for removing redundant data of original input features of a power grid according to claim 9, wherein the first determining unit is further configured to add two discrete feature quantities corresponding to an ith correlation factor to the power grid input feature training set after determining that the ith correlation factor is less than or equal to the preset threshold, and continue to jump to the second determining unit for execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011151906.5A CN112488871A (en) | 2020-10-23 | 2020-10-23 | Method and system for eliminating redundant data of original input features of power grid |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011151906.5A CN112488871A (en) | 2020-10-23 | 2020-10-23 | Method and system for eliminating redundant data of original input features of power grid |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112488871A true CN112488871A (en) | 2021-03-12 |
Family
ID=74927060
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011151906.5A Pending CN112488871A (en) | 2020-10-23 | 2020-10-23 | Method and system for eliminating redundant data of original input features of power grid |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112488871A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102930275A (en) * | 2012-10-29 | 2013-02-13 | 福州大学 | Remote sensing image feature selection method based on Cramer's V index |
CN104125584A (en) * | 2013-04-27 | 2014-10-29 | 中国移动通信集团福建有限公司 | Service index realization prediction method aiming at network service and apparatus thereof |
CN106019084A (en) * | 2016-06-16 | 2016-10-12 | 上海交通大学 | Power distribution and utilization data association-based medium-voltage power grid line fracture fault diagnosis method |
CN106250442A (en) * | 2016-07-26 | 2016-12-21 | 新疆大学 | The feature selection approach of a kind of network security data and system |
CN107704610A (en) * | 2017-10-18 | 2018-02-16 | 国网上海市电力公司 | A kind of power distribution network operation data event correlation analysis system and analysis method |
CN109492857A (en) * | 2018-09-18 | 2019-03-19 | 中国电力科学研究院有限公司 | A kind of distribution network failure risk class prediction technique and device |
CN109977151A (en) * | 2019-03-28 | 2019-07-05 | 北京九章云极科技有限公司 | A kind of data analysing method and system |
CN111614491A (en) * | 2020-05-06 | 2020-09-01 | 国网电力科学研究院有限公司 | Power monitoring system oriented safety situation assessment index selection method and system |
CN111611748A (en) * | 2020-05-25 | 2020-09-01 | 上海大学 | Data-driven material reverse design method and system |
-
2020
- 2020-10-23 CN CN202011151906.5A patent/CN112488871A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102930275A (en) * | 2012-10-29 | 2013-02-13 | 福州大学 | Remote sensing image feature selection method based on Cramer's V index |
CN104125584A (en) * | 2013-04-27 | 2014-10-29 | 中国移动通信集团福建有限公司 | Service index realization prediction method aiming at network service and apparatus thereof |
CN106019084A (en) * | 2016-06-16 | 2016-10-12 | 上海交通大学 | Power distribution and utilization data association-based medium-voltage power grid line fracture fault diagnosis method |
CN106250442A (en) * | 2016-07-26 | 2016-12-21 | 新疆大学 | The feature selection approach of a kind of network security data and system |
CN107704610A (en) * | 2017-10-18 | 2018-02-16 | 国网上海市电力公司 | A kind of power distribution network operation data event correlation analysis system and analysis method |
CN109492857A (en) * | 2018-09-18 | 2019-03-19 | 中国电力科学研究院有限公司 | A kind of distribution network failure risk class prediction technique and device |
CN109977151A (en) * | 2019-03-28 | 2019-07-05 | 北京九章云极科技有限公司 | A kind of data analysing method and system |
CN111614491A (en) * | 2020-05-06 | 2020-09-01 | 国网电力科学研究院有限公司 | Power monitoring system oriented safety situation assessment index selection method and system |
CN111611748A (en) * | 2020-05-25 | 2020-09-01 | 上海大学 | Data-driven material reverse design method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108664010A (en) | Generating set fault data prediction technique, device and computer equipment | |
CN110108992B (en) | Cable partial discharge fault identification method and system based on improved random forest algorithm | |
CN111614491A (en) | Power monitoring system oriented safety situation assessment index selection method and system | |
CN110322368A (en) | A kind of harmonic data method for detecting abnormality, terminal device and storage medium | |
CN114386537A (en) | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment | |
CN112070720A (en) | Transformer substation equipment defect identification method based on deep learning model | |
CN116401532A (en) | Method and system for recognizing frequency instability of power system after disturbance | |
CN113162037B (en) | Power system transient voltage stability self-adaptive evaluation method and system | |
CN113919763A (en) | Power grid disaster analysis method and device based on fuzzy evaluation matrix | |
CN116664335B (en) | Intelligent monitoring-based operation analysis method and system for semiconductor production system | |
CN116739829B (en) | Big data-based power data analysis method, system and medium | |
CN112488871A (en) | Method and system for eliminating redundant data of original input features of power grid | |
CN111898446A (en) | Single-phase earth fault studying and judging method based on multi-algorithm normalization analysis | |
CN116070384A (en) | Transient stability evaluation method and system based on power grid feature arrangement importance | |
CN111814834A (en) | High-voltage cable partial discharge mode identification method, computer equipment and storage medium | |
CN116401954A (en) | Prediction method, prediction device, equipment and medium for cycle life of lithium battery | |
CN116400168A (en) | Power grid fault diagnosis method and system based on depth feature clustering | |
CN107886113B (en) | Electromagnetic spectrum noise extraction and filtering method based on chi-square test | |
CN107784015B (en) | Data reduction method based on online historical data of power system | |
CN109888338B (en) | SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics | |
CN113449409A (en) | Method and equipment for storing sample data of offshore wind turbine fault diagnosis model | |
CN111582446B (en) | System for neural network pruning and neural network pruning processing method | |
CN112434839B (en) | Distribution transformer heavy overload risk prediction method and electronic equipment | |
CN114047413A (en) | GIS partial discharge identification method and system based on MIV and MEA-LVQ neural network | |
CN115204285A (en) | Method, device and equipment for establishing rating model |
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 |