CN114487805A - Circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm - Google Patents
Circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm Download PDFInfo
- Publication number
- CN114487805A CN114487805A CN202210061086.3A CN202210061086A CN114487805A CN 114487805 A CN114487805 A CN 114487805A CN 202210061086 A CN202210061086 A CN 202210061086A CN 114487805 A CN114487805 A CN 114487805A
- Authority
- CN
- China
- Prior art keywords
- data
- circuit breaker
- fault
- genetic algorithm
- physical quantity
- 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
Images
Classifications
-
- 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
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
Abstract
The invention provides a circuit breaker fault diagnosis method based on a genetic algorithm and a clustering algorithm, which relates to the technical field of fault diagnosis and comprises the following steps of S1, collecting characteristic data outside multi-element faults of a circuit breaker, and preprocessing the data; s2, constructing a plurality of groups of physical quantity combinations according to the characteristic data of the circuit breaker with multiple faults obtained by preprocessing in the step S1, and evaluating the plurality of groups of physical quantity combinations by using a genetic algorithm; s3, constructing a multi-dimensional criterion of the breaker fault by adopting a genetic algorithm; s4, judging the breaker fault through a K-mean clustering method according to the breaker fault multidimensional criterion constructed in the step S3; the genetic algorithm is adopted to combine and screen the multi-dimensional physical quantity information of the circuit breaker, random combination of different physical quantities is realized through the genetic algorithm, the characteristics of each physical quantity are explored one by one, the optimal circuit breaker fault criterion is screened out, and the problem that the existing circuit breaker fault diagnosis algorithm does not have universality is solved.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a breaker fault diagnosis method based on a genetic algorithm and a clustering algorithm.
Background
A high-voltage circuit breaker is an important electrical device, and may fail due to lightning strike, external force, high temperature, improper operation, and the like during the operation of an electric power system. The normal operation of the power system is affected by the fault of the high-voltage circuit breaker, so that the fault needs to be identified in time and corresponding countermeasures need to be taken.
At present, the fault diagnosis of the circuit breaker has more available criteria, and mainly comprises electric signals such as voltage and current, acoustic signals, temperature signals and the like. However, most judgment methods only involve one or two criteria, can only aim at one or more types of faults, and have no universality in fault diagnosis.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a breaker fault diagnosis method based on a genetic algorithm and a clustering algorithm.
The invention solves the technical problems through the following technical means: a breaker fault diagnosis method based on a genetic algorithm and a clustering algorithm comprises the following steps:
s1, collecting characteristic data outside the multi-element fault of the circuit breaker, and preprocessing the data;
s2, constructing a plurality of groups of physical quantity combinations according to the external characteristic data of the multi-element faults of the circuit breaker, which are obtained by preprocessing in the step S1, and evaluating the plurality of groups of physical quantity combinations by using a genetic algorithm;
s3, constructing a breaker fault multidimensional criterion by adopting a genetic algorithm according to the plurality of groups of physical quantity combinations constructed in the step S2;
and S4, judging the breaker fault through a K-mean clustering method according to the breaker fault multidimensional criterion constructed in the step S3.
Furthermore, the external characteristic data of the multi-element fault of the circuit breaker comprises corresponding operation data under a normal operation state and a fault state of the circuit breaker.
Further, the operation data comprises current, voltage, electric signals, temperature signals and sound signals.
Further, the data preprocessing comprises the steps of carrying out data transformation on the collected multi-element fault external characteristic data to realize data normalization, eliminating outlier samples and integrating the data into a database.
Further, a multi-dimensional criterion of the breaker fault is constructed by adopting a genetic algorithm, and the method specifically comprises the following steps:
s31, randomly generating 10 sets of initial physical quantity combination vectors as a first-generation physical quantity combination based on the preprocessed multivariate external fault characteristic data in the step S1: the physical quantity combination only comprises 0 and 1, the number of the vector elements is consistent with the number of the physical quantities in the preprocessed multivariate fault external characteristic data, wherein 0 represents that the physical quantities are not contained in the physical quantity combination, and 1 represents that the physical quantities are contained in the physical quantity combination;
s32, evaluating the first-generation physical quantity combination through a fitness function in the genetic algorithm, wherein the fitness function is as follows: carrying out K-mean value clustering analysis on the data group by using the physical quantity combination to obtain the difference value between the sample center of the result and the actually classified sample center; calculating the average distance between each group of data and each classification center by a K-means clustering method, wherein the classification center is the average value vector of each sample in the known classification, adding the group of data into a group with the minimum average distance, and updating the classification center of the group until all the data are classified; in summary, if the actual known classification center vector is
To a certain physical quantity combination
The fitness function f (x) is expressed as:
wherein the smaller F (x) the better, the population is iterated in the direction of decreasing F (x);
s33, after the fitness function is used for evaluating the first generation 10 groups of physical quantities, five groups with the minimum fitness are selected for intersection, and the intersection mode is as follows: selecting a tangent point between a certain two elements, and combining all elements of the male parent vector 1 before the tangent point and all elements of the male parent vector 2 after the tangent point into a new subvector;
s34, introducing a concept of cross rate: setting the crossing rate as eta c (0 < eta c < 1), randomly generating a number i between 0 and 1 before crossing, if i < eta c, performing crossing operation, otherwise, selecting any one of the two male parent vectors as a next generation sub-vector, and setting the crossing rate to be 80-90%;
s35, adding a mutation operator, setting the mutation rate as eta m (0 < eta m < 1), randomly generating a number j between 0 and 1 for each element of the sub-vector during cross operation, and if j < eta m, carrying out non-operation on the element, wherein the mutation rate is 0.5-1%;
and S36, after the operation of the steps S31-S35 is executed, one iteration is finished, whether a physical quantity combination with the fitness meeting the requirement exists in the sub-vectors or not is judged, if yes, the loop is skipped, and if not, the steps S31-S35 are continuously executed.
Further, in step S3, dynamic programming is added to the genetic algorithm, and the optimal physical quantity combination obtained by the genetic algorithm improved by the dynamic programming is used as the multi-dimensional criterion of the breaker fault.
Further, dynamic programming is added into the genetic algorithm, and the specific operation method comprises the following steps: the number of non-zero elements in the vector is taken as a state quantity S, different S represents different stages, whether the vector with the fitness meeting the requirement exists or not is judged from the condition that S is 1 in all vectors generated by limited iteration times, if the vector exists, the search is stopped, if the vector does not exist, the search is continued in the condition that S is 1+ n, and n is a positive integer.
Further, in step S4, the method for determining the breaker fault by K-means clustering using the optimal physical quantity combination obtained by the dynamic programming improved genetic algorithm as the breaker fault multidimensional criterion specifically includes the following steps:
s41, calculating operation data of the collected characteristic data of the circuit breaker outside the multi-element fault in the normal operation state in the step S1, and taking the operation data as a sample center initial value;
s42, clustering breaker fault multidimensional criterion data collected in the operation of the breaker according to the initial value of the sample center, calculating the Euclidean distance between the group of criterion data and the sample center, and classifying the Euclidean distance into the class with the closest distance;
s43, if the group of criterion data is classified into normal operation state data, the circuit breaker is judged to work normally, and if the group of criterion data is classified into fault state data, the circuit breaker is judged to have a fault corresponding to the fault state;
s44, if the actual operation condition of the circuit breaker is consistent with the judgment result, the group of criterion data is recorded into the data, and the sample center is recalculated;
and S45, collecting the next group of breaker multidimensional criterion data and repeatedly executing the steps S41-S44.
Compared with the prior art, the invention has the following beneficial effects:
(1) and screening the multi-dimensional variable information through a dynamic programming improved genetic algorithm, and realizing fault diagnosis according to the circuit breaker parameters by using a clustering method. The method provided by the invention is not specific to a certain type or a certain types of faults, but is based on various physical quantity information, the data is processed and analyzed by adopting the ideas of big data and artificial intelligence, the optimal fault criterion is obtained, and good clustering analysis is realized by utilizing the criterion.
(2) And combining and screening the multi-dimensional physical quantity information of the circuit breaker by adopting a genetic algorithm, wherein the screening standard is whether accurate cluster analysis can be realized. Through a genetic algorithm, the method realizes random combination of different physical quantities, explores the characteristics of each physical quantity one by one, screens out the optimal fault criterion of the circuit breaker, brings different types of signals such as sound, light, electricity and the like into fault diagnosis of the circuit breaker, plays a role simultaneously, can be applied to various fault types, and solves the problem that the existing circuit breaker fault diagnosis algorithm does not have universality.
(3) The dynamic programming idea is added on the basis of the traditional genetic algorithm, the optimal clustering effect is realized by adopting the least physical quantity, the dimensionality of the fault criterion of the circuit breaker is reduced, the rapidity of the algorithm in fault diagnosis is ensured, and the burden of data acquisition is reduced.
(4) The K-means clustering method is combined with the genetic algorithm. The K-means clustering algorithm is simple in principle, convenient to operate and high in calculation speed, and the sample center of the K-means clustering algorithm is more and more stable along with the increase of the operation time, so that the effect in actual operation is better and better, the complexity of the algorithm is reduced, and the reliability of fault diagnosis is ensured.
(4) The method is formed by combining several types of common simple algorithms, is easy to program, and simultaneously realizes the effect of mutual optimization among the algorithms.
Drawings
Fig. 1 is a flowchart illustrating a circuit breaker fault diagnosis method based on a genetic algorithm and a clustering algorithm according to an embodiment of the present invention;
FIG. 2 illustrates a method of operation of a crossover operator;
FIG. 3 illustrates a method of operation of a mutation operator.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention is described in further detail below with reference to the accompanying drawings:
the invention provides a breaker fault diagnosis method based on a genetic algorithm and a clustering algorithm, and aims to solve the problems that the existing breaker fault diagnosis method is lack of universality and single in use data.
The circuit breaker fault diagnosis method based on the genetic algorithm and the clustering algorithm screens multi-dimensional variable information through the genetic algorithm improved through dynamic planning, and analyzes the circuit breaker parameters through the clustering method, so that universal circuit breaker fault diagnosis applying multi-dimensional fault criteria is realized.
The flow chart of the circuit breaker fault diagnosis method based on the genetic algorithm and the clustering algorithm is shown in figure 1, and mainly comprises the following steps:
s1, collecting characteristic data outside the multi-element fault of the circuit breaker, and preprocessing the data;
s2, constructing a plurality of groups of physical quantity combinations according to the characteristic data of the circuit breaker with multiple faults obtained by preprocessing in the step S1, and evaluating the plurality of groups of physical quantity combinations by using a genetic algorithm;
s3, constructing a breaker fault multidimensional criterion by adopting a genetic algorithm according to the plurality of groups of physical quantity combinations constructed in the step S2;
and S4, judging the breaker fault through a K-mean clustering method according to the breaker fault multidimensional criterion constructed in the step S3.
The circuit breaker fault diagnosis method based on the genetic algorithm and the clustering algorithm needs to acquire characteristic data outside multiple faults of the circuit breaker and preprocess the characteristic data; collecting multi-dimensional physical quantity data of current, voltage and other electrical signals of the circuit breaker, temperature signals, sound signals and the like and inputting the data into an algorithm, wherein the collected data comprises corresponding operation data of the circuit breaker in a normal operation state and various common fault states, and enough groups are ensured so as to ensure the accuracy of a genetic algorithm result.
The circuit breaker fault diagnosis method based on the genetic algorithm and the clustering algorithm comprises the steps of carrying out data transformation on collected characteristic data outside multiple faults to realize data normalization, removing outlier samples and integrating the data into a database.
The invention provides a breaker fault diagnosis method based on a genetic algorithm and a clustering algorithm, wherein the genetic algorithm constructs breaker fault multidimensional criterion, and the method comprises the following steps:
s31, based on the preprocessed multivariate fault external characteristic data, randomly generating a plurality of groups of initial physical quantity combination vectors as a first-generation physical quantity combination, wherein the invention takes 10 groups of initial physical quantity combination vectors as the first-generation physical quantity combination: the physical quantity combination only comprises 0 and 1, the number of the vector elements is consistent with the number of the physical quantities in the preprocessed multivariate fault external characteristic data, wherein 0 represents that the physical quantities are not contained in the physical quantity combination, namely the physical quantities are not considered when the clustering analysis is carried out, and 1 represents that the physical quantities are contained in the physical quantity combination;
s32, evaluating the first-generation physical quantity combination through a fitness function in a genetic algorithm, wherein the fitness function needs to be defined: carrying out K-mean value clustering analysis on the data group by using the physical quantity combination to obtain the difference value between the sample center of the result and the actually classified sample center; the K-means clustering method is to calculate the average distance between each group of data and each classification center (i.e. the average vector of each sample in the known classification), add the group of data into the group with the minimum average distance, and update the classification center of the group until all data are classified; in summary, if the actual known classification center vector is
To a certain physical quantity combination
The fitness function f (x) is expressed as:
wherein the smaller F (x) the better, the population should be iterated in the direction of decreasing F (x);
s33, after evaluating the first 10 groups of physical quantities by using the fitness function, selecting five groups with the minimum fitness for intersection, where the intersection method is as shown in fig. 2, and the specific operation mode is as follows: selecting a tangent point between a certain two elements, and combining all elements of the male parent vector 1 before the tangent point and all elements of the male parent vector 2 after the tangent point into a new subvector;
s34, introducing a concept of cross rate: setting the crossing rate as eta c (eta c is more than 0 and less than 1), randomly generating a number i between 0 and 1 before crossing, if i is less than eta c, carrying out crossing operation, otherwise, selecting any one of the two male parent vectors as a next generation sub-vector, and generally setting the crossing rate to be about 80-90%;
s35, adding mutation operators to increase the randomness of the combination, as shown in FIG. 3: setting the variation rate as eta m (0 < eta m < 1), randomly generating a number j between 0 and 1 for each element of the subvector during the cross operation, and if j < eta m, performing the variation operation, namely performing non-operation on the element, wherein the variation rate is preferably between 0.5 and 1 percent;
and S36, after the above operations are completed, one iteration is finished, whether a physical quantity combination with the fitness (the fitness is set by a worker according to the actual situation, and is not limited herein) meeting the requirement exists in the sub-vectors is judged, if yes, the loop is skipped, and if not, the iteration is continued (namely, the technology executes the steps S31-S35) until the condition is met.
According to the breaker fault diagnosis method based on the genetic algorithm and the clustering algorithm, dynamic programming is added into the genetic algorithm, and fault diagnosis with the best effect is guaranteed to be carried out by adopting the least physical quantity; the method takes the optimal physical quantity combination obtained by a dynamic programming improved genetic algorithm as the multi-dimensional criterion of the breaker fault, and comprises the following specific operation methods: the number of non-zero elements in the vector is used as a state quantity S, different S represents different stages, in all vectors generated by limited iteration times, whether the vectors with the fitness meeting the requirement exist is judged from S-1, if the vectors exist, the searching is stopped, if the vectors do not exist, the searching is continued in the S-2 state until the vectors meeting the requirement are found in the S-1 + n state, and n is a positive integer.
The invention provides a circuit breaker fault diagnosis method based on a genetic algorithm and a clustering algorithm, which is characterized in that in step S4, the circuit breaker fault is judged by a K-mean clustering method according to the optimal physical quantity combination obtained by the genetic algorithm improved by dynamic planning as the multidimensional criterion of the circuit breaker fault, and the method specifically comprises the following steps:
s41, calculating operation data of the collected characteristic data of the circuit breaker outside the multi-element fault in the normal operation state in the step S1, and taking the operation data as a sample center initial value;
s42, clustering breaker fault multidimensional criterion data collected in the operation of the breaker according to the initial value of the sample center, calculating the Euclidean distance between the group of criterion data and the sample center, and classifying the Euclidean distance into the class with the closest distance;
s43, if the group of criterion data is classified into normal operation state data, the circuit breaker is judged to work normally, and if the group of criterion data is classified into fault state data, the circuit breaker is judged to have a fault corresponding to the fault state; corresponding countermeasures should be taken;
s44, if the actual operation condition of the circuit breaker is consistent with the judgment result, the group of criterion data is recorded into the data, and the sample center is recalculated;
s45, collecting the next group of breaker multidimensional criterion data and repeatedly executing the steps S41-S44.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (8)
1. A breaker fault diagnosis method based on genetic algorithm and clustering algorithm is characterized in that: the method comprises the following steps:
s1, collecting characteristic data outside the multi-element fault of the circuit breaker, and preprocessing the data;
s2, constructing a plurality of groups of physical quantity combinations according to the characteristic data of the circuit breaker with multiple faults obtained by preprocessing in the step S1, and evaluating the plurality of groups of physical quantity combinations by using a genetic algorithm;
s3, constructing a breaker fault multidimensional criterion by adopting a genetic algorithm according to the plurality of groups of physical quantity combinations constructed in the step S2;
and S4, judging the breaker fault through a K-mean clustering method according to the breaker fault multidimensional criterion constructed in the step S3.
2. The circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm as claimed in claim 1, characterized in that: the multi-element fault external characteristic data of the circuit breaker comprises corresponding operation data under the normal operation state and the fault state of the circuit breaker.
3. The circuit breaker fault diagnosis method based on the genetic algorithm and the clustering algorithm as claimed in claim 2, characterized in that: the operation data comprises current, voltage, electric signals, temperature signals and sound signals.
4. The circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm as claimed in claim 1, characterized in that: and the data preprocessing comprises the steps of carrying out data transformation on the acquired characteristic data outside the multi-element fault to realize data normalization, eliminating outlier samples and integrating the data into a database.
5. The circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm as claimed in claim 1, characterized in that: the method for constructing the multi-dimensional criterion of the breaker fault by adopting the genetic algorithm specifically comprises the following steps:
s31, randomly generating 10 sets of initial physical quantity combination vectors as a first-generation physical quantity combination based on the preprocessed multivariate external fault characteristic data in the step S1: the physical quantity combination only comprises 0 and 1, the number of the vector elements is consistent with the number of the physical quantities in the preprocessed multivariate fault external characteristic data, wherein 0 represents that the physical quantities are not contained in the physical quantity combination, and 1 represents that the physical quantities are contained in the physical quantity combination;
s32, evaluating the first-generation physical quantity combination through a fitness function in the genetic algorithm, wherein the fitness function is as follows: performing K-means clustering on the data group by using the physical quantity combinationThe difference value between the sample center of the analysis result and the actual classification sample center is obtained; calculating the average distance between each group of data and each classification center by a K-means clustering method, wherein the classification center is the average value vector of each sample in the known classification, adding the group of data into a group with the minimum average distance, and updating the classification center of the group until all the data are classified; in summary, if the actual known classification center vector is
To a certain physical quantity combination
The fitness function f (x) is expressed as:
iterating the population in the direction of decreasing F (x);
s33, after the fitness function is used for evaluating the first generation 10 groups of physical quantities, five groups with the minimum fitness are selected for intersection, and the intersection mode is as follows: selecting a tangent point between a certain two elements, and combining all elements of the male parent vector 1 before the tangent point and all elements of the male parent vector 2 after the tangent point into a new subvector;
s34, introducing a concept of cross rate: setting the crossing rate as eta c (0 < eta c < 1), randomly generating a number i between 0 and 1 before crossing, if i < eta c, performing crossing operation, otherwise, selecting any one of the two male parent vectors as a next generation sub-vector, and setting the crossing rate to be 80-90%;
s35, adding a mutation operator, setting the mutation rate as eta m (0 < eta m < 1), randomly generating a number j between 0 and 1 for each element of the sub-vector during cross operation, and if j < eta m, carrying out non-operation on the element, wherein the mutation rate is 0.5-1%;
and S36, after the operation of the steps S31-S35 is executed, one iteration is finished, whether a physical quantity combination with the fitness meeting the requirement exists in the sub-vectors or not is judged, if yes, the loop is skipped, and if not, the steps S31-S35 are continuously executed.
6. The circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm as claimed in claim 1, characterized in that: in step S3, dynamic programming is added to the genetic algorithm, and an optimal physical quantity combination obtained by the genetic algorithm improved by the dynamic programming is used as a multi-dimensional criterion for breaker failure.
7. The circuit breaker fault diagnosis method based on the genetic algorithm and the clustering algorithm as claimed in claim 6, wherein: adding dynamic programming into the genetic algorithm, wherein the specific operation method comprises the following steps: the number of non-zero elements in the vector is taken as a state quantity S, different S represents different stages, whether the vector with the fitness meeting the requirement exists or not is judged from the condition that S is 1 in all vectors generated by limited iteration times, if the vector exists, the search is stopped, if the vector does not exist, the search is continued in the condition that S is 1+ n, and n is a positive integer.
8. The circuit breaker fault diagnosis method based on the genetic algorithm and the clustering algorithm as claimed in claim 6, wherein: in step S4, the method for determining a breaker fault by K-means clustering using the optimal physical quantity combination obtained by the dynamic programming improved genetic algorithm as a breaker fault multidimensional criterion specifically includes the following steps:
s41, calculating operation data of the collected characteristic data of the circuit breaker outside the multi-element fault in the normal operation state in the step S1, and taking the operation data as a sample center initial value;
s42, clustering breaker fault multidimensional criterion data collected in the operation of the breaker according to the initial value of the sample center, calculating the Euclidean distance between the group of criterion data and the sample center, and classifying the Euclidean distance into the class with the closest distance;
s43, if the group of criterion data is classified into normal operation state data, the circuit breaker is judged to work normally, if the group of criterion data is classified into fault state data, the circuit breaker is judged to have a fault corresponding to the fault state;
s44, if the actual operation condition of the circuit breaker is consistent with the judgment result, the group of criterion data is recorded into the data, and the sample center is recalculated;
and S45, collecting the next group of breaker multidimensional criterion data and repeatedly executing the steps S41-S44.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210061086.3A CN114487805A (en) | 2022-01-19 | 2022-01-19 | Circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210061086.3A CN114487805A (en) | 2022-01-19 | 2022-01-19 | Circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114487805A true CN114487805A (en) | 2022-05-13 |
Family
ID=81472915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210061086.3A Pending CN114487805A (en) | 2022-01-19 | 2022-01-19 | Circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114487805A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116087692A (en) * | 2023-04-12 | 2023-05-09 | 国网四川省电力公司电力科学研究院 | Distribution network tree line discharge fault identification method, system, terminal and medium |
-
2022
- 2022-01-19 CN CN202210061086.3A patent/CN114487805A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116087692A (en) * | 2023-04-12 | 2023-05-09 | 国网四川省电力公司电力科学研究院 | Distribution network tree line discharge fault identification method, system, terminal and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110162018B (en) | Incremental equipment fault diagnosis method based on knowledge distillation and hidden layer sharing | |
| Yang et al. | Random forests classifier for machine fault diagnosis | |
| CN108680348A (en) | A kind of breaker mechanical fault diagnosis method and system based on random forest | |
| CN112084237A (en) | Power system abnormity prediction method based on machine learning and big data analysis | |
| Gabrys et al. | Combining labelled and unlabelled data in the design of pattern classification systems | |
| CN112699605B (en) | Charging pile fault element prediction method and system | |
| CN111027629A (en) | Power distribution network fault outage rate prediction method and system based on improved random forest | |
| Perry et al. | Imbalanced classification using genetically optimized cost sensitive classifiers | |
| CN111062520B (en) | Hostname feature prediction method based on random forest algorithm | |
| CN115469227A (en) | Set variational self-encoder and dynamic regular lithium battery abnormity detection method | |
| CN114487805A (en) | Circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm | |
| CN110674940B (en) | Multi-index anomaly detection method based on neural network | |
| Yang et al. | Fault diagnosis system of induction motors using feature extraction, feature selection and classification algorithm | |
| Patel et al. | FLOps: on learning important time series features for real-valued prediction | |
| Reif et al. | Meta2-features: Providing meta-learners more information | |
| KR101827124B1 (en) | System and Method for recognizing driving pattern of driver | |
| CN105353306B (en) | Method of Motor Fault Diagnosis and device and electric appliance | |
| Li | The hybrid credit scoring strategies based on knn classifier | |
| Paul et al. | Series AC arc fault detection using decision tree-based machine learning algorithm and raw current | |
| Sahni et al. | Aided selection of sampling methods for imbalanced data classification | |
| Narasimha Prasad et al. | CC-SLIQ: performance enhancement with 2 K split points in SLIQ decision tree algorithm | |
| Hammami et al. | Weighted-features construction as a bi-level problem | |
| CN113496255B (en) | Power distribution network mixed observation point distribution method based on deep learning and decision tree driving | |
| Lubinsky | Tree structured interpretable regression | |
| Kim et al. | Anomaly pattern detection in streaming data based on the transformation to multiple binary-valued data streams |
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 |