CN118094264A - Intelligent power capacitor partial discharge detection method and system - Google Patents
Intelligent power capacitor partial discharge detection method and system Download PDFInfo
- Publication number
- CN118094264A CN118094264A CN202410524224.6A CN202410524224A CN118094264A CN 118094264 A CN118094264 A CN 118094264A CN 202410524224 A CN202410524224 A CN 202410524224A CN 118094264 A CN118094264 A CN 118094264A
- Authority
- CN
- China
- Prior art keywords
- current data
- power capacitor
- partial discharge
- hierarchical clustering
- change
- 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
- 239000003990 capacitor Substances 0.000 title claims abstract description 54
- 238000001514 detection method Methods 0.000 title claims abstract description 28
- 230000008859 change Effects 0.000 claims abstract description 76
- 230000002159 abnormal effect Effects 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 36
- 239000013598 vector Substances 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000000513 principal component analysis Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 235000012571 Ficus glomerata Nutrition 0.000 claims description 3
- 244000153665 Ficus glomerata Species 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 101100379079 Emericella variicolor andA gene Proteins 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention relates to the technical field of data processing, and provides an intelligent power capacitor partial discharge detection method and system, wherein the method comprises the following steps: collecting a plurality of current data of a power capacitor; obtaining hierarchical clustering trees from the current data through hierarchical clustering; acquiring a first parent node of each current data according to the parent node of each current data belonging to different layers in the hierarchical clustering tree; acquiring abnormal probability of each current data according to the change of other current data in the father node of the current data, the merging threshold value of the first father node of the current data and the distribution of the first father node of other current data in the first father node; and carrying out partial discharge detection on the current data of the power capacitor according to the abnormal probability. The invention aims to solve the problem that partial discharge detection is carried out through a fixed threshold value, so that an error occurs in a detection result.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent power capacitor partial discharge detection method and system.
Background
In normal use, the capacitor will not discharge if no external circuit is connected. However, in some cases, such as the internal defect, aging or damage of the capacitor, or the failure of the capacitor and the external circuit, partial discharge may occur. Partial discharge is one of the manifestations of capacitor anomalies, typically manifested as intermittent discharge of a certain partial area of the capacitor; this discharge phenomenon occurs in the form of short pulses or flashes of light, accompanied by localized high temperature and sound generation. When partial discharge occurs, its presence can be perceived by detecting a current or voltage change across the capacitor.
When the partial discharge detection is carried out on the power capacitor, the existing method detects larger abnormal values obtained in the clustering process, however, the larger abnormal values are only abnormal current data possibly occurring in a large amount of current data, all partial discharge phenomena can not be completely detected by carrying out the partial discharge detection as a basis, and meanwhile, the abnormal current data are interfered by various factors, for example, the environment interference and measurement errors can possibly cause the abnormality of the current data, and further, the partial discharge detection result is error.
Disclosure of Invention
The invention provides an intelligent power capacitor partial discharge detection method and system, which are used for solving the problem that the detection result is error caused by the existing partial discharge detection through fixed threshold, and the adopted technical scheme is as follows:
In a first aspect, an embodiment of the present invention provides an intelligent power capacitor partial discharge detection method, including the steps of:
Collecting a plurality of current data of a power capacitor;
Obtaining hierarchical clustering trees from the current data through hierarchical clustering, wherein each layer of the hierarchical clustering trees comprises a plurality of father nodes, and the father nodes comprise a plurality of current data; acquiring a first parent node of each current data according to the parent node of each current data belonging to different layers in the hierarchical clustering tree;
Acquiring abnormal probability of each current data according to the change of other current data in the father node of the current data, the merging threshold value of the first father node of the current data and the distribution of the first father node of other current data in the first father node;
and carrying out partial discharge detection on the current data of the power capacitor according to the abnormal probability.
Optionally, the hierarchical clustering tree is obtained by hierarchical clustering of the pair of current data, and the specific method comprises the following steps:
And carrying out hierarchical clustering on all the current data, and obtaining a hierarchical clustering tree by using absolute values of differences among the current data as distance measurement.
Optionally, the specific obtaining method of the first parent node of each current data includes:
For any current data, the parent node to which the current data is divided for the first time in the hierarchical cluster tree is marked as the first parent node of the current data.
Optionally, the abnormal probability of each current data is obtained by a specific method that:
Obtaining a variance change sequence of each current data according to variances of the current data in the first father node and other father nodes of the current data; acquiring a hierarchical change rate of each current data based on the variance change sequence; combining the merging threshold value and the distribution of the first father node, the specific formula for calculating the abnormal probability is as follows:
Wherein, Represents the/>Abnormal probability of individual current data,/>Represents the/>The rate of change of the gradation of the individual current data,Represents the/>Merge threshold of first parent node of individual current data,/>Represents the/>The number of layers of the first father node of the current data in the hierarchical clustering tree,/>Representing the total layer number of hierarchical clustering tree,/>Represents the/>Number of current data in first parent node of individual current data,/>Represents the/>Except for the first/>, in the first parent node of the current dataOther than the current data/>The number of layers of the first father node of the current data in the hierarchical clustering tree,/>An exponential function based on a natural constant is represented.
Optionally, the method for obtaining the variance variation sequence of each current data includes the following specific steps:
For any current data, after a first father node is obtained, traversing the father nodes of the current data in each layer from bottom to top in sequence, and the like until the current data in the first layer of the hierarchical clustering tree belong to the father nodes, and obtaining a plurality of father nodes of the current data and the sequence of the father nodes;
And calculating variances of all current data in any father node of the current data, arranging the variances of all father nodes of the current data according to the corresponding father node sequence, and marking the obtained sequence as a variance change sequence of the current data.
Optionally, the specific method for obtaining the hierarchical change rate of each current data includes:
Performing principal component analysis based on the variance change sequence to obtain the hierarchical change direction of each current data;
for the level change direction of any one current data, if the level change direction is smaller than or equal to Setting the gradation change rate of the current data to 0; if the direction of the level change is greater than/>The hierarchy change direction is related to/>As the rate of change of the gradation of the current data.
Optionally, the method for obtaining the hierarchical change direction of each current data includes the following specific steps:
For any variance change sequence of current data, constructing a two-dimensional coordinate system by taking the sequence value of elements in the variance change sequence as an abscissa and taking the variance value as an ordinate, and converting each element in the variance change sequence into a coordinate point in the coordinate system; taking all coordinate points as the input of a PCA algorithm, and outputting to obtain a plurality of two-dimensional vectors and projection values corresponding to each two-dimensional vector; and taking the included angle between the projection direction corresponding to the two-dimensional vector corresponding to the maximum projection value and the horizontal right direction as the hierarchy change direction of the current data.
Optionally, the method for detecting partial discharge of the current data of the power capacitor according to the anomaly probability includes the following specific steps:
An abnormal threshold value is preset, and if the abnormal probability of any one current data is larger than the abnormal threshold value, the power capacitor is partially discharged at the corresponding moment of the current data.
Optionally, the collecting the plurality of current data of the power capacitor includes the following specific steps:
And installing a current sensor on the power capacitor, and acquiring current data from the power capacitor to the current moment through the current sensor according to a preset sampling time interval to obtain a plurality of current data.
In a second aspect, another embodiment of the present invention provides an intelligent power capacitor partial discharge detection system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implementing the steps of the above method when executing the computer program.
The beneficial effects of the invention are as follows: according to the invention, hierarchical clustering is carried out on a large amount of current data, a hierarchical clustering tree is constructed, and abnormal probability is obtained by analyzing parent nodes of each layer of the hierarchical clustering tree based on the current data, so that abnormal current data caused by other interference factors can be avoided by carrying out partial discharge detection through the abnormal probability, and the current data with higher abnormal probability accords with the partial discharge phenomenon; the hierarchical clustering tree is constructed, the number of layers of the first father node of other current data in the first father node is obtained and analyzed based on the father nodes of the current data divided in the hierarchical clustering tree, and the abnormal probability is quantified by combining the change of the other current data in the father node, so that the abnormal probability can reflect the difference between the current data and the whole current data to further display the abnormality, and the abnormal influence caused by the environmental interference or measurement error is reduced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of an intelligent power capacitor partial discharge detection method according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of an intelligent power capacitor partial discharge detection method according to an embodiment of the invention is shown, the method includes the following steps:
and S001, collecting a plurality of current data of the power capacitor.
The purpose of this embodiment is to detect the partial discharge phenomenon of the power capacitor, so as to realize fault early warning of the power capacitor, and when the partial discharge phenomenon of the power capacitor occurs, the current and the voltage on the power capacitor will change.
Specifically, a current sensor is installed on a power capacitor, the current sensor is used for collecting current data from the beginning of the power capacitor to the current moment, the current moment is the latest moment, and a sampling time interval is set to 1 second, so that a plurality of current data are obtained.
Step S002, hierarchical clustering is carried out on the current data to obtain a hierarchical clustering tree; acquiring the hierarchical change rate of each current data according to the father node of each current data belonging to different layers in the hierarchical clustering tree; and acquiring the abnormal probability of each current data according to the hierarchical change rate of the current data and the merging threshold value and distribution of the father nodes.
Preferably, in one embodiment of the present invention, the hierarchical clustering tree is obtained by hierarchical clustering on the current data, including the following specific methods:
Hierarchical clustering is carried out on all current data, the current data is subjected to hierarchical clustering by adopting a bottom-up clustering method, the uppermost layer in the obtained hierarchical clustering tree is the first layer, the hierarchical clustering tree is obtained by adopting the absolute value of the difference value between the current data as the distance measurement, each layer in the hierarchical clustering tree comprises a plurality of father nodes, each father node comprises a plurality of current data, and the father nodes are the categories of the current data in the layer.
Preferably, in one embodiment of the present invention, according to a parent node to which each current data belongs in a hierarchical cluster tree, a hierarchical change rate of each current data is obtained, including the following specific methods:
For any current data, marking the parent node of the current data which is divided into the hierarchical clustering tree for the first time as the first parent node of the current data, traversing the parent nodes of the current data which belong to each layer from bottom to top in sequence, and the like until the current data belongs to the parent nodes of the first layer in the hierarchical clustering tree, and obtaining a plurality of parent nodes of the current data and the sequence of the parent nodes; it should be noted that, because of hierarchical clustering, the first parent node of the current data does not necessarily appear in the lowest layer in the hierarchical clustering tree; and calculating variances of all current data in any father node of the current data, arranging the variances of all father nodes of the current data according to the corresponding father node sequence, and marking the obtained sequence as a variance change sequence of the current data.
Further, constructing a two-dimensional coordinate system by taking the sequence value of the elements in the variance change sequence as an abscissa and the variance value as an ordinate, and converting each element in the variance change sequence into a coordinate point in the coordinate system; taking all coordinate points as input of a principal component analysis algorithm, wherein the principal component analysis algorithm is the principal component analysis algorithm, outputting a plurality of two-dimensional vectors and projection values corresponding to the two-dimensional vectors, wherein the two-dimensional vectors are actually a projection direction, and the principal component analysis algorithm is the principal component analysis algorithm in the prior art and is not repeated in the embodiment; the projection direction corresponding to the two-dimensional vector corresponding to the maximum projection value and the included angle between the horizontal direction and the right direction are used as the level change direction of the current data, and the value range of the level change direction isIf the direction of the level change is less than or equal to/>Setting the gradation change rate of the current data to 0; if the direction of the level change is greater than/>Changing the direction of the hierarchy andAs a rate of change of the gradation of the current data; and acquiring the hierarchical change rate of each current data according to the method.
It should be noted that, because the current data is hierarchically clustered and clustered from bottom to top, and meanwhile, the randomness of the current data under partial discharge is larger, the larger the variance of the current data in the parent node to which the layer number changes belongs, that is, the more and more abnormal current data are clustered into the parent node in the clustering process of the current data, the larger the probability that the parent node is the category of abnormal current data aggregation, and the larger the variance change trend is, the larger the abnormal probability of the current data is, the larger the hierarchical change rate is due to analysis of the maximum projection direction of the variance change sequence so as to reflect the variance change trend.
Optionally, in other embodiments, a variance change sequence is obtained for any one current data according to the above method, a slope is calculated through coordinate points corresponding to elements in the variance change sequence (where the first coordinate point does not perform slope calculation), arctangent values of the average value of the slopes of all coordinate points are obtained, and the arctangent values are recorded as the level change direction of the current data, and if the level change direction is smaller than or equal to the level change directionSetting the gradation change rate of the current data to 0; if the direction of the level change is greater than/>The hierarchy change direction is related to/>As the rate of change of the gradation of the current data.
Preferably, in one embodiment of the present invention, the abnormal probability of each current data is obtained according to the level change rate of the current data, the merging threshold and the distribution of the parent node, including the following specific methods:
For the first The current data is obtained to the/>After the first father node of the current data, if the first father node has a merging threshold in the hierarchical clustering process, the merging threshold of the first father node is directly obtained, wherein the merging threshold of the father node is obtained in the hierarchical clustering process as the existing method, and the embodiment is not repeated; acquisition of the/>First parent nodes of other current data in the first parent nodes of the current data, then the/>Abnormal probability of individual current data/>The calculation method of (1) is as follows:
Wherein, Represents the/>Hierarchical rate of change of individual current data,/>Represents the/>Merge threshold of first parent node of individual current data,/>Represents the/>The number of layers of the first father node of the current data in the hierarchical clustering tree,/>Representing the total layer number of hierarchical clustering tree,/>Represents the/>Number of current data in first parent node of individual current data,/>Represents the/>Except for the first/>, in the first parent node of the current dataOther than the current data/>The number of layers of the first father node of the current data in the hierarchical clustering tree,/>Representing an exponential function based on a natural constant, the present embodiment employs/>Model to present inverse proportional relationship and normalization process,/>For inputting the model, an implementer can set an inverse proportion function and a normalization function according to actual conditions; the anomaly probability of each current data is obtained according to the above method.
The abnormal probability of the current data is quantified through the level change rate of the current data, the combination threshold value of the first father node, the layer number of the first father node and the distribution of the first father nodes of other current data in the first father node; the larger the level change rate of the current data is, the larger the variance increasing trend of the father node is, the higher the possibility that the father node is of an abnormal current data type is, and the higher the abnormal probability of the current data is; the smaller the merging threshold value of the first father node is, the smaller the similarity is indicated, the current data can be divided into the first father node, and the greater the possibility that the first father node contains abnormal current data, the greater the abnormal probability of the current data is; the smaller the layer number of the first father node is, the higher the layer number of the first father node is in the hierarchical clustering tree, the later the current data is in the hierarchical clustering tree and is divided into the father nodes, the difference exists between the current data and most of the current data, and the greater the abnormal probability of the current data is; the smaller the number of layers of the first parent node of other current data in the first parent node of the current data is, the greater the possibility of abnormality of the other current data is, the greater the possibility that the first parent node of the current data contains abnormal current data is, and the greater the possibility of abnormality of the current data is.
So far, by constructing a hierarchical clustering tree, quantifying the hierarchical change rate based on parent nodes of the current data divided in the hierarchical clustering tree, the hierarchical change rate can reflect the trend that the current data is divided into abnormal current data types, and further reflect the possibility of abnormality of the current data; the abnormal probability is quantified based on the hierarchical change rate, and the abnormal probability is quantified by combining the layer number of the first father node and the layer number of the current data when the current data is divided for the first time in the hierarchical clustering tree, so that the abnormal probability can reflect the difference between the current data and the whole current data, thereby presenting abnormality, and reducing the abnormal influence caused by environmental interference or measurement error.
Step S003, partial discharge detection is performed on the current data of the power capacitor according to the abnormality probability.
Preferably, in one embodiment of the present invention, the partial discharge detection is performed on the current data of the power capacitor according to the anomaly probability, including the specific method that:
After the abnormal probability of each current data is obtained, an abnormal threshold is preset, the abnormal threshold is described by 0.68, and if the abnormal probability of the current data is greater than the abnormal threshold, the power capacitor is partially discharged at the corresponding moment of the current data.
It should be noted that, because the anomaly probability is obtained based on the hierarchical clustering tree, after new current data is obtained, the corresponding anomaly probability can be obtained directly according to the clustering condition of the new current data in the hierarchical clustering tree, so as to realize partial discharge detection.
Therefore, the abnormal probability is obtained by carrying out hierarchical clustering on a large amount of current data and constructing a hierarchical clustering tree and analyzing parent nodes of each layer in the hierarchical clustering tree based on the current data, so that the current data abnormality caused by other interference factors can be avoided by carrying out partial discharge detection through the abnormal probability, and the current data with larger abnormal probability accords with the partial discharge phenomenon.
Another embodiment of the present invention provides an intelligent power capacitor partial discharge detection system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the above method steps S001 to S003 when executing the computer program.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. An intelligent power capacitor partial discharge detection method is characterized by comprising the following steps:
Collecting a plurality of current data of a power capacitor;
Obtaining hierarchical clustering trees from the current data through hierarchical clustering, wherein each layer of the hierarchical clustering trees comprises a plurality of father nodes, and the father nodes comprise a plurality of current data; acquiring a first parent node of each current data according to the parent node of each current data belonging to different layers in the hierarchical clustering tree;
Acquiring abnormal probability of each current data according to the change of other current data in the father node of the current data, the merging threshold value of the first father node of the current data and the distribution of the first father node of other current data in the first father node;
and carrying out partial discharge detection on the current data of the power capacitor according to the abnormal probability.
2. The method for detecting the partial discharge of the intelligent power capacitor according to claim 1, wherein the hierarchical clustering tree is obtained by hierarchical clustering of the pair of current data, comprises the following specific steps:
And carrying out hierarchical clustering on all the current data, and obtaining a hierarchical clustering tree by using absolute values of differences among the current data as distance measurement.
3. The method for detecting partial discharge of an intelligent power capacitor according to claim 1, wherein the specific obtaining method of the first parent node of each current data is as follows:
For any current data, the parent node to which the current data is divided for the first time in the hierarchical cluster tree is marked as the first parent node of the current data.
4. The method for detecting partial discharge of an intelligent power capacitor according to claim 1, wherein the abnormal probability of each current data is specifically obtained by:
Obtaining a variance change sequence of each current data according to variances of the current data in the first father node and other father nodes of the current data; acquiring a hierarchical change rate of each current data based on the variance change sequence; combining the merging threshold value and the distribution of the first father node, the specific formula for calculating the abnormal probability is as follows:
Wherein, Represents the/>Abnormal probability of individual current data,/>Represents the/>Hierarchical rate of change of individual current data,/>Represents the/>Merge threshold of first parent node of individual current data,/>Represents the/>The number of layers of the first father node of the current data in the hierarchical clustering tree,/>Representing the total layer number of hierarchical clustering tree,/>Represents the/>Number of current data in first parent node of individual current data,/>Represents the/>Except for the first/>, in the first parent node of the current dataOther than the current data/>The number of layers of the first father node of the current data in the hierarchical clustering tree,/>An exponential function based on a natural constant is represented.
5. The method for detecting partial discharge of an intelligent power capacitor according to claim 4, wherein the obtaining the variance variation sequence of each current data comprises the following specific steps:
For any current data, after a first father node is obtained, traversing the father nodes of the current data in each layer from bottom to top in sequence, and the like until the current data in the first layer of the hierarchical clustering tree belong to the father nodes, and obtaining a plurality of father nodes of the current data and the sequence of the father nodes;
And calculating variances of all current data in any father node of the current data, arranging the variances of all father nodes of the current data according to the corresponding father node sequence, and marking the obtained sequence as a variance change sequence of the current data.
6. The method for detecting partial discharge of an intelligent power capacitor according to claim 4, wherein the hierarchical rate of change of each current data is obtained by:
Performing principal component analysis based on the variance change sequence to obtain the hierarchical change direction of each current data;
for the level change direction of any one current data, if the level change direction is smaller than or equal to Setting the gradation change rate of the current data to 0; if the direction of the level change is greater than/>The hierarchy change direction is related to/>As the rate of change of the gradation of the current data.
7. The method for detecting partial discharge of an intelligent power capacitor according to claim 6, wherein the step of obtaining the hierarchical direction of each current data comprises the following specific steps:
For any variance change sequence of current data, constructing a two-dimensional coordinate system by taking the sequence value of elements in the variance change sequence as an abscissa and taking the variance value as an ordinate, and converting each element in the variance change sequence into a coordinate point in the coordinate system; taking all coordinate points as the input of a PCA algorithm, and outputting to obtain a plurality of two-dimensional vectors and projection values corresponding to each two-dimensional vector; and taking the included angle between the projection direction corresponding to the two-dimensional vector corresponding to the maximum projection value and the horizontal right direction as the hierarchy change direction of the current data.
8. The method for detecting partial discharge of an intelligent power capacitor according to claim 1, wherein the method for detecting partial discharge of current data of the power capacitor according to abnormal probability comprises the following specific steps:
An abnormal threshold value is preset, and if the abnormal probability of any one current data is larger than the abnormal threshold value, the power capacitor is partially discharged at the corresponding moment of the current data.
9. The method for detecting partial discharge of an intelligent power capacitor according to claim 1, wherein the collecting the plurality of current data of the power capacitor comprises the following specific steps:
And installing a current sensor on the power capacitor, and acquiring current data from the power capacitor to the current moment through the current sensor according to a preset sampling time interval to obtain a plurality of current data.
10. An intelligent power capacitor partial discharge detection system comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor implements the steps of an intelligent power capacitor partial discharge detection method according to any one of claims 1-9 when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524224.6A CN118094264A (en) | 2024-04-29 | 2024-04-29 | Intelligent power capacitor partial discharge detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524224.6A CN118094264A (en) | 2024-04-29 | 2024-04-29 | Intelligent power capacitor partial discharge detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118094264A true CN118094264A (en) | 2024-05-28 |
Family
ID=91156640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410524224.6A Pending CN118094264A (en) | 2024-04-29 | 2024-04-29 | Intelligent power capacitor partial discharge detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118094264A (en) |
-
2024
- 2024-04-29 CN CN202410524224.6A patent/CN118094264A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7930122B2 (en) | Evaluating anomaly for one-class classifiers in machine condition monitoring | |
| CN111709465B (en) | Intelligent identification method for rough difference of dam safety monitoring data | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| CN111967509A (en) | Method and device for processing and detecting data acquired by industrial equipment | |
| US7716152B2 (en) | Use of sequential nearest neighbor clustering for instance selection in machine condition monitoring | |
| CN115982602B (en) | Photovoltaic transformer electrical fault detection method | |
| KR20210017651A (en) | Method for Fault Detection and Fault Diagnosis in Semiconductor Manufacturing Process | |
| CN112565187B (en) | Power grid attack detection method, system, equipment and medium based on logistic regression | |
| CN110858072B (en) | Method and device for determining running state of equipment | |
| CN116914917A (en) | Big data-based monitoring and management system for operation state of power distribution cabinet | |
| CN117273489A (en) | Photovoltaic state evaluation method and device | |
| CN112949735A (en) | Liquid hazardous chemical substance volatile concentration abnormity discovery method based on outlier data mining | |
| CN116610938A (en) | Method and equipment for detecting unsupervised abnormality of semiconductor manufacture in curve mode segmentation | |
| CN117237678A (en) | Method, device, equipment and storage medium for detecting abnormal electricity utilization behavior | |
| CN115495274B (en) | Exception handling method based on time sequence data, network equipment and readable storage medium | |
| CN118094264A (en) | Intelligent power capacitor partial discharge detection method and system | |
| KR102486463B1 (en) | Method and Apparatus for Real Time Fault Detection Using Time series data According to Degradation | |
| CN117970061B (en) | High-voltage power capacitor fault early warning method and system | |
| CN113869373A (en) | Equipment abnormality detection method and device, computer equipment and storage medium | |
| CN115511106B (en) | Method, device and readable storage medium for generating training data based on time sequence data | |
| CN117407824B (en) | Health detection method, equipment and medium of power time synchronization device | |
| WO2023073941A1 (en) | Error factor estimation device, error factor estimation method, and computer-readable medium | |
| CN117668684B (en) | Power grid electric energy data anomaly detection method based on big data analysis | |
| KR102486462B1 (en) | Method and Apparatus for Fault Detection Using Pattern Learning According to Degradation | |
| CN117407264B (en) | Method, device, computer equipment and medium for predicting memory aging residual time |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |