CN111832653A - XGboost algorithm-based lightning arrester defect diagnosis method and system - Google Patents
XGboost algorithm-based lightning arrester defect diagnosis method and system Download PDFInfo
- Publication number
- CN111832653A CN111832653A CN202010675970.7A CN202010675970A CN111832653A CN 111832653 A CN111832653 A CN 111832653A CN 202010675970 A CN202010675970 A CN 202010675970A CN 111832653 A CN111832653 A CN 111832653A
- Authority
- CN
- China
- Prior art keywords
- lightning arrester
- xgboost
- defect
- classifier
- algorithm
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003745 diagnosis Methods 0.000 title claims abstract description 17
- 238000012544 monitoring process Methods 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims description 31
- 230000015654 memory Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000004590 computer program Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 229920002379 silicone rubber Polymers 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 239000013585 weight reducing agent Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The application discloses lightning arrester defect diagnosis method and system based on XGboost algorithm, including: acquiring real-time monitoring data of the lightning arrester to be diagnosed; and inputting real-time monitoring data of the lightning arrester to be diagnosed into a pre-constructed lightning arrester defect identification information model based on an XGboost algorithm, and outputting the defect type of the lightning arrester to be diagnosed. The XGBoost algorithm is used for assisting in judging the defects of the lightning arrester on site, so that the workload of operation and maintenance workers is reduced.
Description
Technical Field
The application relates to the technical field of lightning arrester defect diagnosis, in particular to a lightning arrester defect diagnosis method and system based on an XGboost algorithm.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The lightning arrester is important overvoltage protection equipment in a transformer substation, and the normal operation of the lightning arrester has important significance on the safe and stable operation of the transformer substation. However, the lightning arrester is prone to failure or heating under the influence of factors such as internal moisture and valve plate aging, and even explodes in severe cases, so that the operation safety of a power grid is affected. Aiming at the assessment of the running state of the lightning arrester and the diagnosis of faults, the data are analyzed and applied by methods such as a leakage current method, a resistive current third harmonic method, a fundamental wave method and the like based on monitoring data at present.
The total leakage current method identifies faults according to the rising degree of the total leakage current measured on the grounding lead, but the method has lower sensitivity and is easy to leak and judge because the proportion of the resistive current to the total current is lower;
the resistive current third harmonic method identifies faults according to the rising degree of the sum of the resistive current third harmonics of each phase in the grounding wire, and the harmonic waves of a power grid can also cause the rise of the sum of the resistive current third harmonics, so that misjudgment is caused;
the conventional compensation method reflects the fault through the resistance current, but the measurement error of the resistance current is larger due to the interference of a power frequency electromagnetic field of a transformer substation.
Based on the defect data, the existing research is also applied to a certain extent, and the neural network has the excellent performance of approximating a nonlinear function with any precision, but has the risk of overfitting on a small sample training set. Classification of regression trees, while efficient, is too weak to learn a single tree and also tends to fall into an over-fitting problem. And the defects of the lightning arrester and the operation and maintenance data are mainly texts and cannot be directly quantitatively analyzed.
The inventor finds out how to expand data dimensionality on the basis of the prior art and further improve the accuracy of lightning arrester defect judgment and the feasibility of maintenance strategy specification by using an intelligent analysis algorithm, and the problem is urgently needed to be solved at present.
Disclosure of Invention
In order to overcome the defects of the prior art, the application provides a lightning arrester defect diagnosis method and system based on an XGboost algorithm;
in a first aspect, the application provides a lightning arrester defect diagnosis method based on an XGboost algorithm;
the lightning arrester defect diagnosis method based on the XGboost algorithm comprises the following steps:
acquiring real-time monitoring data of the lightning arrester to be diagnosed;
and inputting real-time monitoring data of the lightning arrester to be diagnosed into a pre-constructed lightning arrester defect identification information model based on an XGboost algorithm, and outputting the defect type of the lightning arrester to be diagnosed.
In a second aspect, the application also provides a lightning arrester defect diagnosis system based on the XGboost algorithm;
lightning arrester defect diagnosis system based on XGboost algorithm includes:
an acquisition module configured to: acquiring real-time monitoring data of the lightning arrester to be diagnosed;
a diagnostic module configured to: and inputting real-time monitoring data of the lightning arrester to be diagnosed into a pre-constructed lightning arrester defect identification information model based on an XGboost algorithm, and outputting the defect type of the lightning arrester to be diagnosed.
In a third aspect, the present application further provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method of the first aspect.
In a fourth aspect, the present application also provides a computer-readable storage medium for storing computer instructions which, when executed by a processor, perform the steps of the method of the first aspect.
Compared with the prior art, the beneficial effects of this application are:
1. the method reflects the nonlinear correlation between the state quantity of the lightning arrester defects and the defects, selects an integrated learning algorithm XGboost which has nonlinear segmentation capability and a good overfitting control mechanism on a small sample training set, establishes a lightning arrester defect classification model, and samples attributes when each tree is constructed, so that the training speed is high, and the effect is good.
2. And a Bayesian optimization algorithm is adopted to automatically select the global optimal hyper-parameter, so that the classification performance is improved.
3. The XGBoost algorithm is used for assisting in judging the defects of the lightning arrester on site, so that the workload of operation and maintenance workers is reduced.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flow chart of a method of the first embodiment;
FIG. 2 is a diagram of an XGboost algorithm addition model.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The first embodiment provides a lightning arrester defect diagnosis method based on an XGboost algorithm;
as shown in fig. 1, the method for diagnosing the defect of the lightning arrester based on the XGboost algorithm includes:
s101: acquiring real-time monitoring data of the lightning arrester to be diagnosed;
s102: and inputting real-time monitoring data of the lightning arrester to be diagnosed into a pre-constructed lightning arrester defect identification information model based on an XGboost algorithm, and outputting the defect type of the lightning arrester to be diagnosed.
As one or more embodiments, the pre-constructed XGboost algorithm-based lightning arrester defect identification information model; the construction process comprises the following steps:
and constructing an arrester defect identification information model based on an XGboost algorithm according to the collected arrester historical defect data samples.
Further, the pre-constructed lightning arrester defect identification information model based on the XGboost algorithm; the construction process comprises the following steps:
constructing a training set, wherein the training set is historical monitoring data of the lightning arrester with known lightning arrester defect types;
constructing an XGboost classifier;
and inputting the training set into an XGboost classifier, training the XGboost classifier, and outputting the trained XGboost classifier, namely the XGboost algorithm-based lightning arrester defect identification information model.
Further, inputting the training set into an XGboost classifier, training the XGboost classifier, and outputting the trained XGboost classifier; the method comprises the following steps:
inputting the training set into an XGboost classifier, searching an optimal parameter combination for the XGboost classifier based on a Bayesian optimization algorithm, inputting the optimal parameter combination into the XGboost classifier, training the XGboost classifier, and outputting the trained XGboost classifier.
Further, an optimal parameter combination is searched for the XGboost classifier based on a Bayesian optimization algorithm, and the method specifically comprises the following steps:
randomly generating a super-parameter initial value according to the number and the range of the XGboost super-parameters;
inputting historical monitoring data of the lightning arrester with known defect types of the lightning arrester into a Gaussian model, and correcting the Gaussian model to obtain a corrected Gaussian model;
extracting a parameter combination to be evaluated from the modified Gaussian model;
substituting the parameter combination to be evaluated into an XGboost classifier for training;
when the error of the XGboost classifier is smaller than a set threshold value, terminating training, and outputting a corresponding parameter combination and a trained XGboost classifier;
and when the error of the XGboost classifier is larger than or equal to the set threshold, continuously correcting the Gaussian model until the classification precision of the XGboost classifier reaches the set requirement.
Further, the parameter combination to be evaluated is extracted from the modified gaussian model by using the function MPI.
It should be understood that aiming at parameter optimization of the XGboost classifier, a Bayesian optimization algorithm is introduced, lightning arrester monitoring data are input into a Gaussian model, model output is obtained, and mean and variance are obtained. Using extraction function MPI (maximum likelihood of improvement) to select parameter combination point x to be evaluated next step from the modified Gaussian modeliMake the Gaussian model more robust with respect to other combinations of candidate setsThe true distribution of the objective function is quickly and accurately approached.
And substituting the globally optimal parameter combination into the XGboost classifier for training. If the error of the newly selected parameter combination meets the target requirement, stopping the algorithm execution and exiting, and outputting the corresponding parameter combination and the prediction classification (x) of the modeli,f(xi)). If f (x)i) If not, (x) will bei,f(xi) Input the gaussian model, modify the gaussian model, and execute the previous step again until the set accuracy requirement is met.
Illustratively, the training set is historical lightning arrester monitoring data of known lightning arrester defect types; the method comprises the following steps: defect historical data, online monitoring data, lightning data and standing book data.
Illustratively, the defect history data includes: defect entry _ ID, voltage class, line, device type, manufacturer, commissioning date, defect location, defect category, or netbook name.
Illustratively, the online monitoring data includes: the monitoring device comprises a monitoring device identification, monitoring time, average wind speed within a set time range, average wind direction within a set time range, maximum wind speed, standard wind speed, air temperature, humidity, air pressure, rainfall, precipitation intensity or illumination radiation intensity.
Illustratively, the lightning data includes: longitude, latitude, or peak.
Illustratively, the ledger data includes: the lightning arrester comprises an arrester ID, an equipment code, a voltage grade, a rated voltage, a rated frequency, a manufacturer, an operation date, a model, an insulator type, a continuous operation voltage, a power frequency reference voltage, a power frequency discharge voltage, a nominal discharge current, a lightning impulse residual voltage, a creepage specific distance, a direct current reference voltage, the presence or absence of an equalizing ring, a full current initial value, a resistive current initial value or a large current impulse current value.
Illustratively, the known defect type tag includes: poor grounding, abnormal action, unsatisfactory hydrophobicity of silicon rubber, poor joint, heat generation, damaged online instrument, abnormal display, poor sealing of a leakage ammeter, moisture in the ammeter, looseness, fuzziness, obvious change of a measured value of U1mA compared with a specified value of a manufacturing factory, color change, obvious discharge trace, overproof leakage current indicated value, damage, inclination, deformation, failure of an action counter, zero leakage meter indication, damage, jamming of a pointer, corrosion, pressure alarm, damage, cracking of an outer sleeve, poor sealing, glass breakage, water inlet or unqualified insulation resistance.
Illustratively, the lightning arrester to be diagnosed real-time monitoring data comprises: and monitoring data, operation and maintenance and test data on line.
For one or more embodiments, the XGboost classifier is trained on the criteria that the number of training passes reaches a set number or that the loss function reaches a minimum.
XGboost is a supervised algorithm that is superimposed by multiple base learners into a strong learner. In a sample set containing n samples G ═ x1,y1),(x2,y2),…,(xn,yn) Upper training model, where xiAnd E is X, yi is E Y, X is a characteristic quantity data set, and Y is a defect category set.
The XGboost's base learner selects a classification regression tree, as shown in FIG. 2, where a single classification regression tree is often too simple to effectively classify faults, using K classifiers (M)1，M2，…，Mk) The integrated tree models are added to predict the classification target values.
The training process of the model comprises the following steps:
1) and randomly generating parameter initial values according to the number and the range of the XGboost over-parameters.
TABLE 1 XGboost parameter ranges and meanings
| Parameter range | Meaning of parameters | |
| eta | (0.01,0.3) | Feature weight reduction factor |
| max_depth | (2,16) | Maximum tree depth |
| min_child_weight | (0.1,10) | Sum of leaf node weights |
| subsample | (0.5,1.0) | Proportion of samples sampled randomly |
| lambda | (0,10) | L2 regularization term for weights |
| alpha | (0,10) | L1 regularization term for weights |
| gamma | (0,20) | Minimum loss function descent value |
| colsamplee_bytree | (0.5,1.0) | Random sampling proportion of features |
2) Inputting a training sample set, G ═ x1,y1),(x2,y2),…,(xn,yn) Where x) isiBelongs to X, yi belongs to Y. The lightning arrester on-line monitoring data is unbalanced in normal operation and data proportion under each fault, and layered sampling is adopted to ensure that the proportion of label samples used for training is the same as that of an original data set.
3) And inputting the lightning arrester monitoring data into a Gaussian model by using a Bayesian optimization algorithm to obtain model output and obtain a mean value and a variance. Using extraction function MPI (maximum probability of improvement) to select parameter combination point x to be evaluated next step from the modified Gaussian modeli。
The extraction function can be expressed as:
f(x+) Is the maximum value, is the coefficient, (x) is the variance, and u (x) is the mean.
4) And substituting the globally optimal parameter combination into the XGboost classifier for training. If the error of the newly selected parameter combination meets the target requirement, stopping the algorithm execution and exiting, and outputting the corresponding parameter combination and the prediction classification (x) of the modeli,f(xi)). If f (x)i) If not, (x) will bei,f(xi) Input the gaussian model, modify the gaussian model, and execute the previous step again until the set accuracy requirement is met. And evaluating the probability output of the classifier by adopting a logarithmic loss function as an evaluation standard of the model parameters, wherein the corresponding parameters of a small loss function are excellent.
The log loss is:
wherein N is the number of samples, M is the number of categories, yijIndicating that the ith sample belongs to the class j and is 1, otherwise is 0, pijRepresenting the probability that the ith sample is predicted as class j。
TABLE 2 simulation results
The embodiment II also provides a lightning arrester defect diagnosis system based on the XGBoost algorithm;
lightning arrester defect diagnosis system based on XGboost algorithm includes:
an acquisition module configured to: acquiring real-time monitoring data of the lightning arrester to be diagnosed;
a diagnostic module configured to: and inputting real-time monitoring data of the lightning arrester to be diagnosed into a pre-constructed lightning arrester defect identification information model based on an XGboost algorithm, and outputting the defect type of the lightning arrester to be diagnosed.
It should be noted that the above-mentioned acquisition module and the diagnosis module correspond to steps S101 to S102 in the first embodiment, and the above-mentioned modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure of the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
In the foregoing embodiments, the descriptions of the embodiments have different emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical functional division, and in actual implementation, there may be other divisions, for example, multiple modules may be combined or integrated into another system, or some features may be omitted, or not executed.
EXAMPLE III
The present embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, a processor is connected with the memory, the one or more computer programs are stored in the memory, and when the electronic device runs, the processor executes the one or more computer programs stored in the memory, so as to make the electronic device execute the method according to the first embodiment.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software.
The method in the first embodiment may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here.
Those of ordinary skill in the art will appreciate that the various illustrative elements, i.e., algorithm steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
Example four
The present embodiments also provide a computer-readable storage medium for storing computer instructions, which when executed by a processor, perform the method of the first embodiment.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. The lightning arrester defect diagnosis method based on the XGboost algorithm is characterized by comprising the following steps of:
acquiring real-time monitoring data of the lightning arrester to be diagnosed;
and inputting real-time monitoring data of the lightning arrester to be diagnosed into a pre-constructed lightning arrester defect identification information model based on an XGboost algorithm, and outputting the defect type of the lightning arrester to be diagnosed.
2. The method of claim 1, wherein the pre-constructed XGboost algorithm based lightning arrester defect identification information model; the construction process comprises the following steps:
and constructing an arrester defect identification information model based on an XGboost algorithm according to the collected arrester historical defect data samples.
3. The method according to claim 1 or 2, wherein the pre-constructed model of lightning arrester defect identification information based on the XGboost algorithm; the construction process comprises the following steps:
constructing a training set, wherein the training set is historical monitoring data of the lightning arrester with known lightning arrester defect types;
constructing an XGboost classifier;
and inputting the training set into an XGboost classifier, training the XGboost classifier, and outputting the trained XGboost classifier, namely the XGboost algorithm-based lightning arrester defect identification information model.
4. The method of claim 3, wherein the training set is input into an XGboost classifier, the XGboost classifier is trained, and the trained XGboost classifier is output; the method comprises the following steps:
inputting the training set into an XGboost classifier, searching an optimal parameter combination for the XGboost classifier based on a Bayesian optimization algorithm, inputting the optimal parameter combination into the XGboost classifier, training the XGboost classifier, and outputting the trained XGboost classifier.
5. The method of claim 4, wherein the step of finding the optimal combination of parameters for the XGboost classifier based on a bayesian optimization algorithm comprises the steps of:
randomly generating a super-parameter initial value according to the number and the range of the XGboost super-parameters;
inputting historical monitoring data of the lightning arrester with known defect types of the lightning arrester into a Gaussian model, and correcting the Gaussian model to obtain a corrected Gaussian model;
extracting a parameter combination to be evaluated from the modified Gaussian model;
substituting the parameter combination to be evaluated into an XGboost classifier for training;
when the error of the XGboost classifier is smaller than a set threshold value, terminating training, and outputting a corresponding parameter combination and a trained XGboost classifier;
and when the error of the XGboost classifier is larger than or equal to the set threshold, continuously correcting the Gaussian model until the classification precision of the XGboost classifier reaches the set requirement.
6. The method of claim 5, wherein the extracting the combination of parameters to be evaluated from the modified Gaussian model is performed using a function MPI to extract the combination of parameters to be evaluated from the modified Gaussian model.
7. The method of claim 3, wherein the training set is arrester historical monitoring data for known arrester defect types; the method comprises the following steps: defect historical data, online monitoring data, lightning data and standing book data.
8. Lightning arrester defect diagnosis system based on XGboost algorithm, characterized by includes:
an acquisition module configured to: acquiring real-time monitoring data of the lightning arrester to be diagnosed;
a diagnostic module configured to: and inputting real-time monitoring data of the lightning arrester to be diagnosed into a pre-constructed lightning arrester defect identification information model based on an XGboost algorithm, and outputting the defect type of the lightning arrester to be diagnosed.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executable on the processor, the computer instructions when executed by the processor performing the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the method of any one of claims 1 to 7.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2019106459945 | 2019-07-17 | ||
| CN201910645994 | 2019-07-17 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111832653A true CN111832653A (en) | 2020-10-27 |
Family
ID=72923195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010675970.7A Pending CN111832653A (en) | 2019-07-17 | 2020-07-14 | XGboost algorithm-based lightning arrester defect diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111832653A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508053A (en) * | 2020-11-10 | 2021-03-16 | 泽恩科技有限公司 | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework |
| CN112595919A (en) * | 2020-12-31 | 2021-04-02 | 国网浙江省电力有限公司经济技术研究院 | Fault detection system, method and device of lightning arrester and server |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508083A (en) * | 2011-11-22 | 2012-06-20 | 广东电网公司电力科学研究院 | Method for monitoring arrester on line |
| CN106650037A (en) * | 2016-11-30 | 2017-05-10 | 国网江苏省电力公司盐城供电公司 | State diagnosis method of lightning arrester based on support vector machine regression |
| CN107045089A (en) * | 2017-01-20 | 2017-08-15 | 上海欧忆能源科技有限公司 | Arrester condition diagnosing system |
| CN107622236A (en) * | 2017-09-15 | 2018-01-23 | 安徽农业大学 | Based on bee colony and gradient lifting decision Tree algorithms crops disease diagnosing method for early warning |
| CN109064074A (en) * | 2018-09-26 | 2018-12-21 | 广东电网有限责任公司 | Arrester method for diagnosing status, system and equipment |
| CN109190670A (en) * | 2018-08-02 | 2019-01-11 | 大连理工大学 | A kind of charging pile failure prediction method based on expansible boosted tree |
| CN109840541A (en) * | 2018-12-05 | 2019-06-04 | 国网辽宁省电力有限公司信息通信分公司 | A kind of network transformer Fault Classification based on XGBoost |
-
2020
- 2020-07-14 CN CN202010675970.7A patent/CN111832653A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508083A (en) * | 2011-11-22 | 2012-06-20 | 广东电网公司电力科学研究院 | Method for monitoring arrester on line |
| CN106650037A (en) * | 2016-11-30 | 2017-05-10 | 国网江苏省电力公司盐城供电公司 | State diagnosis method of lightning arrester based on support vector machine regression |
| CN107045089A (en) * | 2017-01-20 | 2017-08-15 | 上海欧忆能源科技有限公司 | Arrester condition diagnosing system |
| CN107622236A (en) * | 2017-09-15 | 2018-01-23 | 安徽农业大学 | Based on bee colony and gradient lifting decision Tree algorithms crops disease diagnosing method for early warning |
| CN109190670A (en) * | 2018-08-02 | 2019-01-11 | 大连理工大学 | A kind of charging pile failure prediction method based on expansible boosted tree |
| CN109064074A (en) * | 2018-09-26 | 2018-12-21 | 广东电网有限责任公司 | Arrester method for diagnosing status, system and equipment |
| CN109840541A (en) * | 2018-12-05 | 2019-06-04 | 国网辽宁省电力有限公司信息通信分公司 | A kind of network transformer Fault Classification based on XGBoost |
Non-Patent Citations (1)
| Title |
|---|
| 赵文俊;张强;刘磊;宋家友;: "基于AdaBoost与GABP的模拟电路软故障诊断方法", 计算机测量与控制, no. 12, 25 December 2017 (2017-12-25) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508053A (en) * | 2020-11-10 | 2021-03-16 | 泽恩科技有限公司 | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework |
| CN112595919A (en) * | 2020-12-31 | 2021-04-02 | 国网浙江省电力有限公司经济技术研究院 | Fault detection system, method and device of lightning arrester and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106321368B (en) | Marine wind electric field wake losses measurement method based on operation blower SCADA data | |
| WO2020127336A1 (en) | An improved method for evaluating pipe condition | |
| CN106650037A (en) | State diagnosis method of lightning arrester based on support vector machine regression | |
| CN110619479B (en) | Fault judgment model modeling method and fault judgment method for photovoltaic module | |
| CN107992665B (en) | Online fault diagnosis and analysis method for alternating current filter of extra-high voltage converter station | |
| CN111104736B (en) | Abnormal data detection method, device, medium and equipment based on time sequence | |
| CN111832653A (en) | XGboost algorithm-based lightning arrester defect diagnosis method and system | |
| CN111288973B (en) | Method and device for obtaining flow rate of sea surface, computer equipment and storage medium | |
| CN111191727A (en) | Gas pressure regulator fault diagnosis method, system, terminal and computer storage medium based on PSO-KPCA-LVQ | |
| CN117371337B (en) | Water conservancy model construction method and system based on digital twin | |
| CN113850330A (en) | Power distribution network fault cause detection method based on short-time Fourier transform and convolutional neural network | |
| CN103440410A (en) | Main variable individual defect probability forecasting method | |
| CN111191725A (en) | RBF fault diagnosis method, system, terminal and computer storage medium based on PCA data processing | |
| CN115829145A (en) | Photovoltaic power generation capacity prediction system and method | |
| CN113721182B (en) | Method and system for evaluating reliability of online performance monitoring result of power transformer | |
| CN110096723B (en) | High-voltage switch cabinet insulation state analysis method based on operation and maintenance detection big data | |
| CN113377750B (en) | Hydrological data cleaning method and system | |
| CN117056678B (en) | Machine pump equipment operation fault diagnosis method and device based on small sample | |
| CN117630800A (en) | Fault diagnosis method and system for automatic calibrating device of electric energy meter | |
| CN111060755A (en) | Electromagnetic interference diagnosis method and device | |
| CN105741184A (en) | Transformer state evaluation method and apparatus | |
| CN114139408A (en) | Power transformer health state assessment method | |
| CN116069565B (en) | Method and device for replacing board card | |
| CN113379120B (en) | Power distribution network equipment fault prediction method and system | |
| CN116681356A (en) | Method for processing data by power plant equipment state database system |
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 |