CN115563477B - Harmonic data identification method, device, computer equipment and storage medium - Google Patents
Harmonic data identification method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115563477B CN115563477B CN202211533808.7A CN202211533808A CN115563477B CN 115563477 B CN115563477 B CN 115563477B CN 202211533808 A CN202211533808 A CN 202211533808A CN 115563477 B CN115563477 B CN 115563477B
- Authority
- CN
- China
- Prior art keywords
- harmonic content
- harmonic
- data
- content data
- typical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/40—Arrangements for reducing harmonics
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present application relates to a harmonic data identification method, apparatus, computer device, storage medium and computer program product. The method comprises the following steps: classifying the harmonic content curves of the measurement terminals to obtain corresponding harmonic content typical curves with typical categories; clustering the typical harmonic content curves according to the industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the typical harmonic content curves; carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data; and determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data. By adopting the method, the identification accuracy of harmonic data of measurement terminals in different industries can be improved.
Description
Technical Field
The present application relates to the field of big data technology, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for identifying harmonic data.
Background
With development of construction work of the power system, more and more new energy power equipment is continuously connected into the power system, and the negative influence of harmonic data abnormality is more serious.
In the traditional technology, the harmonic data is mainly subjected to abnormality identification through a machine learning model, however, the types and the number of industries to which measurement terminals in the current power system belong are various, and the machine learning model can only effectively identify the abnormality of the harmonic data of a single type of measurement terminal, so that the problem of low accuracy in identifying the harmonic data of measurement terminals in different industries exists.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a harmonic data recognition method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the recognition accuracy of harmonic data for different industry measurement terminals.
In a first aspect, the present application provides a method of harmonic data identification. The method comprises the following steps:
classifying the harmonic content curves of the measurement terminals to obtain corresponding harmonic content typical curves with typical categories;
clustering the typical harmonic content curves according to the industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the typical harmonic content curves;
Carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data;
and determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data.
In one embodiment, performing local outlier identification on each harmonic content data in the harmonic content data domain to obtain an outlier identification result of each harmonic content data, where the outlier identification result includes:
determining target harmonic content data which are the same as industry types corresponding to the harmonic content data from the harmonic content data domain according to the industry types corresponding to the harmonic content data;
obtaining a distance neighborhood of each harmonic content data according to the Gaussian distance between each harmonic content data and the target harmonic content data corresponding to each harmonic content data;
calculating local outlier factors of the harmonic content data according to the distance neighborhood of the harmonic content data;
and carrying out outlier identification on the harmonic content data according to the local outlier factors of the harmonic content data to obtain outlier identification results of the harmonic content data.
In one embodiment, determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data comprises:
acquiring the number of harmonic content data identified as outlier data in the outlier identification result;
and under the condition that the quantity meets the preset abnormal quantity condition, confirming that the identification result of the harmonic content rate curve is abnormal.
In one embodiment, classifying the harmonic content curves of the measurement terminals to obtain a harmonic content typical curve with a typical class, which corresponds to the harmonic content curve, includes:
acquiring a classification radius and the minimum harmonic quantity;
screening to obtain a first clustering center from the harmonic content curve according to the classification radius and the minimum harmonic quantity;
and clustering the harmonic content curves according to the first clustering center to obtain a classification result of the harmonic content curves, and obtaining a harmonic content typical curve with a typical class corresponding to the classification result.
In one embodiment, clustering the typical harmonic content curve according to the industry type of the measurement terminal corresponding to the typical harmonic content curve to obtain a harmonic content data field corresponding to the typical harmonic content curve, including:
Acquiring a preset clustering quantity;
acquiring the harmonic content rate typical curves of the preset clustering quantity from the harmonic content rate typical curves, and taking the harmonic content rate typical curves as a second clustering center;
and clustering the harmonic content typical curve according to the industry type of the measuring terminal corresponding to the second aggregation center to obtain the harmonic content data field of the preset clustering number corresponding to the harmonic content typical curve.
In one embodiment, before the classifying the harmonic content curves of the measurement terminals to obtain the harmonic content typical curves with the corresponding categories as typical categories, the method further includes:
acquiring harmonic data of the measurement terminal in a target time period according to a preset sampling frequency;
and calculating to obtain a harmonic content curve of the measurement terminal according to the harmonic data.
In a second aspect, the present application also provides a harmonic data identification apparatus. The device comprises:
the curve classification module is used for classifying the harmonic content curves of the measurement terminals to obtain a harmonic content typical curve with a typical class corresponding to the harmonic content curves;
the curve clustering module is used for clustering the typical harmonic content curves according to the industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the typical harmonic content curves;
The outlier identification module is used for carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data;
and the harmonic identification module is used for determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
classifying the harmonic content curves of the measurement terminals to obtain corresponding harmonic content typical curves with typical categories;
clustering the typical harmonic content curves according to the industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the typical harmonic content curves;
carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data;
And determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
classifying the harmonic content curves of the measurement terminals to obtain corresponding harmonic content typical curves with typical categories;
clustering the typical harmonic content curves according to the industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the typical harmonic content curves;
carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data;
and determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
Classifying the harmonic content curves of the measurement terminals to obtain corresponding harmonic content typical curves with typical categories;
clustering the typical harmonic content curves according to the industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the typical harmonic content curves;
carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data;
and determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data.
The method, the device, the computer equipment, the storage medium and the computer program product for identifying the harmonic data are used for classifying the harmonic content curves of the measurement terminal to obtain the corresponding typical harmonic content curves with typical categories; clustering the typical harmonic content curves according to the industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the typical harmonic content curves; carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data; and determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data. By adopting the method, the typical characteristics are classified from the harmonic content curve of the measurement terminal, and then the data fields of all industry types are obtained by clustering the harmonic content typical curve, so that the obtained harmonic content data in the harmonic content data fields have both the typical characteristics and the industry characteristics, and the abnormality in the harmonic oil content curve is identified by utilizing local outliers, thereby effectively improving the identification accuracy of the harmonic data of the measurement terminals of different industries.
Drawings
FIG. 1 is an application environment diagram of a harmonic data identification method in one embodiment;
FIG. 2 is a flow chart of a method of identifying harmonic data in one embodiment;
FIG. 3 is a flow chart of a method for identifying harmonic data in another embodiment;
FIG. 4 is a flow chart of a method for identifying harmonic data in yet another embodiment;
FIG. 5 is a block diagram of a harmonic data identification apparatus in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The harmonic data identification method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein, the measurement terminal 101 communicates with the measurement master station 102 through a network. The data storage system may store data that the metrology master station 102 needs to process, such as harmonic content curves, harmonic content data fields, outlier recognition results, and the like. The data storage system may be integrated on the measurement master station 102 or may be located on the cloud or other network server. The measurement master station is equipment for receiving harmonic data of the measurement terminal and carrying out anomaly identification. The measurement terminal refers to equipment for collecting harmonic data of power users.
In one embodiment, as shown in fig. 2, a method for identifying harmonic data is provided, and the method is applied to the measurement master station in fig. 1 for illustration, and includes the following steps:
step S201, classifying the harmonic content curves of the measurement terminals to obtain a harmonic content typical curve with a typical class.
The harmonic data refers to the amount of electricity generated in the current associated with the fundamental frequency. The harmonic content representative curve refers to a curve capable of characterizing a characteristic of the harmonic content curve.
Specifically, the measurement master station collects harmonic data of the measurement terminal in a target time period, and calculates and obtains harmonic content corresponding to the harmonic data; and drawing a harmonic content curve of the measurement terminal according to the harmonic content. The terminal classifies the harmonic content curves through a clustering algorithm to obtain a typical harmonic content curve with a typical class and an atypical harmonic content curve with an atypical class so as to obtain a typical harmonic content curve capable of representing typical characteristics of the harmonic content curve.
Step S202, clustering the typical harmonic content curves according to industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the industry types.
The harmonic content data field refers to a cluster group obtained by clustering a typical curve of harmonic content, and the cluster group contains harmonic content data in the typical curve of harmonic content.
Specifically, the measurement master station determines the industry type of the measurement terminal according to the file of the measurement terminal; and clustering the harmonic content typical curves according to industry types of the measuring terminals corresponding to the harmonic content typical curves to obtain cluster groups corresponding to each industry type, and taking the cluster groups corresponding to each industry type as a harmonic content data field corresponding to each industry type.
Step S203, carrying out local outlier recognition on each harmonic content data in the harmonic content data domain to obtain outlier recognition results of each harmonic content data.
Wherein the outlier recognition result is used to describe whether each harmonic content data in the harmonic content data domain belongs to a normal data point or an abnormal data point.
Specifically, the measurement master station performs local outlier identification on each harmonic content data in the harmonic content data domain, and can identify whether the harmonic content data in each harmonic content data domain belongs to an outlier class or a normal class according to a gaussian distance between the harmonic content data and each harmonic content data in the harmonic content data domain closest to the harmonic content data, so that the measurement master station obtains an outlier identification result of each harmonic content data.
Step S204, determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data.
Specifically, the measurement master station counts the number of the harmonic content data of the outlier category as the outlier identification result according to the outlier identification result of each harmonic content data; when the number of the outlier categories exceeds a preset number threshold, the measurement master station confirms that the identification result of the harmonic content curve of the measurement terminal is abnormal, and harmonic data corresponding to the harmonic content curve is also abnormal, namely the harmonic data of the measurement terminal is abnormal; otherwise, confirming that the identification result of the harmonic content rate curve of the measurement terminal is normal, and then the harmonic data corresponding to the harmonic content rate curve is also normal, namely the harmonic data of the measurement terminal is normal. The preset number threshold includes, but is not limited to, 60%,80% and 90%, although other values may be set.
In the harmonic data identification method, the harmonic content rate curve of the measurement terminal is classified to obtain a corresponding typical harmonic content rate curve with a typical class; clustering the typical harmonic content curves according to the industry types of the measuring terminals corresponding to the typical harmonic content curves to obtain harmonic content data fields corresponding to the typical harmonic content curves; carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data; and determining the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data. By adopting the method, the typical characteristics are classified from the harmonic content curve of the measurement terminal, and then the data fields of all industry types are obtained by clustering the harmonic content typical curve, so that the obtained harmonic content data in the harmonic content data fields have both the typical characteristics and the industry characteristics, and the abnormality in the harmonic oil content curve is identified by utilizing local outliers, thereby effectively improving the identification accuracy of the harmonic data of the measurement terminals of different industries.
In one embodiment, the step S203 performs local outlier identification on each harmonic content data in the harmonic content data domain to obtain an outlier identification result of each harmonic content data, which specifically includes the following contents: according to industry types corresponding to the harmonic content data, determining target harmonic content data which are the same as the industry types corresponding to the harmonic content data from a harmonic content data domain; obtaining a distance neighborhood of each harmonic content data according to the Gaussian distance between each harmonic content data and the target harmonic content data corresponding to each harmonic content data; according to the distance neighborhood of each harmonic content data, calculating to obtain local outlier factors of each harmonic content data; and carrying out outlier identification on each harmonic content data according to the local outlier factor of each harmonic content data to obtain an outlier identification result of each harmonic content data.
Specifically, the measurement master station uses the harmonic content data points except the harmonic content data points needing to be subjected to outlier identification in the harmonic content data field as target harmonic content data points, and then the measurement master station calculates the Gaussian distance between each harmonic content data in the harmonic content data field and each other target harmonic content data point. The measurement master station calculates a distance neighborhood of the harmonic content data point according to the Gaussian distance between the harmonic content data and other target harmonic content data points; and carrying out local outlier factor (Local Outlier Factor, LOF) processing on the distance neighborhood of the harmonic content data point to obtain the Gaussian kernel local outlier factor of the harmonic content data point. The measurement master station compares the Gaussian kernel local outlier factor of the harmonic content data point with an outlier threshold to obtain a comparison result; under the condition that the Gaussian kernel local outlier factor of the harmonic content data point is larger than an outlier threshold value as a comparison result, confirming that the harmonic content data point is outlier recognition result as abnormal; and when the Gaussian kernel local outlier factor of the harmonic content data point is smaller than the outlier threshold as a comparison result or is equal to the outlier threshold as a comparison result, confirming that the harmonic content data point is normal as an outlier recognition result. Wherein the outlier threshold may be set to 1.
In this embodiment, the measurement master station obtains a distance neighborhood of each harmonic content data according to a gaussian distance between each harmonic content data and a target harmonic content data corresponding to each harmonic content data; further, according to the distance neighborhood of each harmonic content data, calculating to obtain local outlier factors of each harmonic content data; and finally, carrying out outlier identification on each harmonic content data according to the local outlier factor of each harmonic content data to obtain an outlier identification result of each harmonic content data, carrying out outlier identification on the harmonic content data belonging to the same industry type, and representing the outlier identification result of the harmonic data of the measuring terminal by utilizing the outlier identification of each harmonic content data in the harmonic content data domain, thereby effectively improving the identification accuracy of the harmonic data of the measuring terminals of different industries.
In one embodiment, the step S204 determines the identification result of the harmonic content curve according to the outlier identification result of each harmonic content data, which specifically includes the following steps: acquiring the number of harmonic content data identified as outlier data in the outlier identification result; and under the condition that the quantity meets the preset abnormal quantity condition, confirming that the identification result of the harmonic content rate curve is abnormal.
The measuring master station can also synthesize outlier recognition results of the harmonic content data in each target time period to determine recognition results of the harmonic content curve. Specifically, the measurement master station counts the quantity of the harmonic content data of which the outlier identification result is an outlier class in each target time period according to the outlier identification result of each harmonic content data; under the condition that the number of outlier categories in each target time period exceeds a preset number threshold, the measurement master station confirms that the identification result of the harmonic content curve of the measurement terminal is abnormal, and harmonic data corresponding to the harmonic content curve is also abnormal; otherwise, confirming that the identification result of the harmonic content rate curve of the measurement terminal is normal, and the harmonic data corresponding to the harmonic content rate curve is also normal. The preset number threshold includes, but is not limited to, 60%,80% and 90%, although other values may be set.
In this embodiment, the measurement master station confirms the identification result of the collected harmonic content curve according to the number of harmonic content data identified as outlier data in each target time period, so that the abnormal condition of the harmonic content curve can be more accurately identified, and the identification accuracy of the collected harmonic data in different time periods is greatly improved.
In one embodiment, the step S201 performs a classification process on the harmonic content curve of the measurement terminal to obtain a harmonic content typical curve with a typical class corresponding to the harmonic content curve, which specifically includes the following steps: acquiring a classification radius and the minimum harmonic quantity; screening from the harmonic content curve according to the classification radius and the minimum harmonic quantity to obtain a first clustering center; and clustering the harmonic content curves according to the first clustering center to obtain a classification result of the harmonic content curves, and obtaining a typical harmonic content curve with a typical class corresponding to the classification result.
The first clustering center is obtained in the process of classifying the harmonic content curve of the measurement terminal. The classification radius refers to a radius parameter for searching the harmonic content curve. The minimum harmonic number refers to the minimum number of harmonic content curves covered over the classification radius.
The measurement master station can adopt a clustering algorithm based on density to classify the harmonic content curves of the measurement terminals, so as to obtain the corresponding typical harmonic content curves with typical categories. Specifically, the required parameters of the clustering algorithm based on density of the main measuring station, namely the classification processing radius and the minimum harmonic number. According to the classification radius and the minimum harmonic quantity, screening from the harmonic content curves to obtain a first cluster center, wherein the first cluster center can be obtained by searching the quantity of other harmonic content curves covered by each harmonic content curve within the classification radius (for distinguishing from other quantities, the quantity can be called as curve coverage quantity here), comparing the curve coverage quantity of the harmonic content curve with the minimum harmonic quantity to obtain a curve quantity comparison result, and taking the harmonic content curve as the first cluster center when the curve quantity comparison result is that the curve coverage quantity of the harmonic content curve is larger than the minimum harmonic quantity; when the curve number comparison result is that the curve coverage number of the harmonic content curve is equal to the minimum harmonic number, the harmonic content curve is set as a boundary point. And the measurement master station performs density clustering on the harmonic content curves except the first clustering center and the boundary points according to the first clustering center and the boundary points to obtain a classification result of the harmonic content curves. The classification result comprises a typical harmonic content curve with a typical class and an atypical harmonic content curve with an atypical class. The measurement master station extracts a typical harmonic content curve with a typical class from the classification result of the harmonic content curve.
In the embodiment, a first clustering center is obtained by screening from a harmonic content rate curve according to a classification radius and the minimum harmonic quantity; and clustering the harmonic content curves according to the first clustering center to obtain a classification result of the harmonic content curves, so that a harmonic content typical curve with a typical type corresponding to the classification result can be used as a processing basis to execute a subsequent harmonic data identification step, and the classification of typical characteristics from the harmonic content curve of the measurement terminal is realized, thereby improving the identification accuracy of the harmonic data.
In one embodiment, the step S202 performs clustering processing on the typical harmonic content curves according to the industry type of the measurement terminal corresponding to the typical harmonic content curves to obtain the harmonic content data fields corresponding to the typical harmonic content curves, and specifically includes the following steps: acquiring a preset clustering quantity; acquiring a harmonic content rate typical curve of a preset clustering number from the harmonic content rate typical curve, and taking the harmonic content rate typical curve as a second aggregation center; and clustering the typical curves of the harmonic content according to the second aggregation center to obtain a harmonic content data field of a preset clustering number corresponding to the typical curves of the harmonic content.
The preset clustering quantity refers to the quantity of harmonic content data fields obtained by the needed clustering; the preset cluster number may be set to be the total number of industry types of the typical curve of the harmonic content, for example, the typical curve of the harmonic content contains 5 industry types, and the measurement master station may set the preset cluster number to be 5; the preset cluster number can also be set to be the large direction number corresponding to the industry type of the typical curve of the harmonic content, for example, 5 industry types of the typical curve of the harmonic content can be summarized into 3 industry major categories, and then the measurement master station can set the preset cluster number to be 3. The second clustering center is a clustering center obtained in the process of clustering the typical curves of the harmonic content.
The measurement master station can perform clustering processing on a typical curve of the harmonic content based on K-means (K-means) clustering. Specifically, the measurement master station obtains a preset clustering number; then randomly selecting a preset clustering number of harmonic content rate typical curves from the harmonic content rate typical curves to serve as second aggregation centers (for convenience of distinguishing, the harmonic content rate typical curves except the second aggregation centers in the harmonic content rate typical curves can be used as to-be-classified harmonic content rate typical curves); according to the industry type of the measuring terminal corresponding to the second aggregation center, the industry type of the measuring terminal corresponding to the typical curve of the harmonic content to be classified is respectively obtained, and the distances between the typical curve of the harmonic content to be classified and each second aggregation center are respectively obtained; clustering the second cluster center closest to the typical curve of the harmonic content to be classified into a cluster group; after all the typical curves of the harmonic content rate are subjected to cluster division, calculating new second clustering centers in each cluster again, then carrying out cluster division on the typical curves of the harmonic content rate to be classified except the new second clustering centers in the typical curves of the harmonic content rate again according to the new second clustering centers, repeatedly calculating the new second clustering centers in each cluster, and then calculating the new second clustering centers according to the new second clustering centers; and carrying out cluster division on the to-be-classified harmonic content typical curves except for the new second aggregation center in the harmonic content typical curves again until the change of each cluster meets the preset change ending condition, and taking the preset number of clusters obtained at the moment as a harmonic content data field of the preset clustering number.
In this embodiment, the measurement master station obtains a harmonic content rate typical curve of a preset cluster number from the harmonic content rate typical curves, and uses the harmonic content rate typical curve as a second cluster center; and clustering is carried out on the typical harmonic content curves according to the second aggregation center to obtain harmonic content data fields with preset clustering numbers corresponding to the typical harmonic content curves, so that the obtained harmonic content data fields not only contain typical characteristics of the harmonic content curves, but also contain industry characteristics of the harmonic content curves, and the identification accuracy of harmonic data of measurement terminals of different industries is greatly improved.
In one embodiment, before classifying the harmonic content rate curve of the measurement terminal to obtain a harmonic content rate typical curve with a typical class, the method further includes: acquiring harmonic data of the measurement terminal in a target time period according to a preset sampling frequency; and calculating to obtain a harmonic content curve of the measurement terminal according to the harmonic data.
Specifically, the measurement master station may collect harmonic data of the measurement terminal according to a preset sampling frequency in a plurality of target time periods; and carrying out ratio processing on the root mean square value of the harmonic component and the root mean square value of the fundamental component of the harmonic data to obtain the harmonic content data of the measurement terminal in a plurality of target time periods. And the measurement master station draws a curve according to the harmonic content to obtain a harmonic content curve of the measurement terminal in a plurality of target time periods.
In the embodiment, harmonic data of the measurement terminal in a target time period is acquired through preset sampling frequency; and then calculating to obtain a harmonic content rate curve of the measurement terminal according to the harmonic data, so that in subsequent processing, a subsequent harmonic data identification step is executed by taking the harmonic content rate curve as a basis, rather than directly using the harmonic data for identification, and the identification accuracy of the harmonic data of the measurement terminal is improved.
In one embodiment, as shown in fig. 3, another method for identifying harmonic data is provided, and the method is applied to the measurement master station in fig. 1 for illustration, and includes the following steps:
step S301, acquiring harmonic data of a measurement terminal in a target time period according to a preset sampling frequency; and calculating to obtain a harmonic content curve of the measurement terminal according to the harmonic data.
Step S302, acquiring a classification radius and the minimum harmonic quantity; and screening from the harmonic content curves according to the classification radius and the minimum harmonic quantity to obtain a first clustering center.
Step S303, clustering the harmonic content curves according to the first clustering center to obtain a classification result of the harmonic content curves, and obtaining a typical harmonic content curve with a typical class corresponding to the classification result.
Step S304, obtaining a preset clustering number; and acquiring a harmonic content rate typical curve of a preset clustering number from the harmonic content rate typical curve to serve as a second aggregation center.
Step S305, clustering the typical curves of the harmonic content according to the industry types of the measuring terminals corresponding to the second aggregation centers to obtain the harmonic content data fields of the preset clustering quantity corresponding to the typical curves of the harmonic content.
Step S306, determining target harmonic content data with the same industry type as the corresponding harmonic content data from the harmonic content data domain according to the industry type corresponding to the harmonic content data.
Step S307, a distance neighborhood of each harmonic content data is obtained according to the Gaussian distance between each harmonic content data and the target harmonic content data corresponding to each harmonic content data.
Step S308, according to the distance neighborhood of each harmonic content data, calculating to obtain the local outlier factor of each harmonic content data.
Step S309, performing outlier identification on each harmonic content data according to the local outlier factor of each harmonic content data to obtain outlier identification results of each harmonic content data.
Step S310, obtaining the number of harmonic content data identified as outlier data in the outlier identification result; and under the condition that the quantity meets the preset abnormal quantity condition, confirming that the identification result of the harmonic content rate curve is abnormal.
The harmonic data identification method can realize the following beneficial effects: the typical characteristics are classified from the harmonic content rate curve of the measurement terminal, and then the data fields of all industry types are obtained by clustering the harmonic content rate typical curve, so that the obtained harmonic content rate data in the harmonic content rate data fields have typical characteristics and industry characteristics, and the abnormality in the harmonic oil content rate curve is identified by utilizing local outliers, so that the identification accuracy of the harmonic data of the measurement terminals of different industries is effectively improved.
In order to more clearly clarify the harmonic data identification method provided in the embodiments of the present disclosure, the harmonic data identification method will be specifically described in the following with a specific embodiment. As shown in fig. 4, another method for identifying harmonic data is provided, which can be applied to the measurement master station in fig. 1, and specifically includes the following contents:
step S401, the measurement master station sends a time-period harmonic data acquisition task to the measurement terminal: the measuring master station collects harmonic data of the measuring terminal in three target time periods of 9:00-11:00, 14:00-16:00 and 23:00-01:00 (the next day) with 15 minutes/time as a preset sampling frequency.
Step S402, a density-based clustering algorithm is adopted to obtain a typical curve of harmonic content: the measurement master station obtains harmonic content rate curves of three target time periods according to the collected harmonic data, and the measurement master station performs density clustering on the harmonic content rate curves to obtain a harmonic content rate typical curve with a typical class corresponding to the measurement master station.
Step S403, clustering the typical curves of the harmonic content based on a K-means clustering algorithm: and the measurement master station performs K-means clustering treatment on the harmonic content typical curve according to the industry type of the measurement terminal corresponding to the harmonic content typical curve to obtain a harmonic content data field corresponding to the harmonic content typical curve.
Step S404, identifying an abnormality of the harmonic data based on the local outlier factor: carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain Gaussian kernel local outlier factors of each harmonic content data, and confirming that the harmonic content data point is abnormal as an outlier identification result under the condition that the Gaussian kernel local outlier factor of the harmonic content data point is larger than 1; otherwise, confirming that the harmonic content data point is normal as an outlier recognition result. Counting the quantity of harmonic content data of which the outlier identification result is an outlier class by the measuring master station in each target time period; under the condition that the number of outliers in three target time periods of 9:00-11:00, 14:00-16:00 and 23:00-01:00 (the next day) exceeds 80%, the measurement master station confirms that the identification result of the harmonic content curve of the measurement terminal is abnormal, and the harmonic data of the measurement terminal is abnormal; otherwise, the harmonic data of the measurement terminal is normal.
In this embodiment, a typical class of harmonic content typical curves are obtained by clustering through the harmonic content typical curves of the harmonic data in the three target time periods, and a harmonic content data field is obtained by clustering according to the industry type of the measurement terminal corresponding to the harmonic content typical curves, so that the obtained harmonic content data in the harmonic content data field has both typical characteristics and industry characteristics, and further, the abnormality in the harmonic oil content curves is identified by utilizing local outliers, and the identification accuracy of the harmonic data of the measurement terminal is effectively improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a harmonic data recognition device for realizing the above related harmonic data recognition method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the one or more harmonic data recognition devices provided below may be referred to the limitation of the harmonic data recognition method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 5, there is provided a harmonic data recognition apparatus 500 comprising: a curve classification module 501, a curve clustering module 502, an outlier identification module 503, and a harmonic identification module 504, wherein:
the curve classification module 501 is configured to classify the harmonic content curves of the measurement terminals to obtain a harmonic content typical curve with a typical class.
The curve clustering module 502 is configured to perform clustering processing on the typical harmonic content curves according to the industry type of the measurement terminal corresponding to the typical harmonic content curves, so as to obtain a harmonic content data field corresponding to the typical harmonic content curves.
The outlier recognition module 503 is configured to perform local outlier recognition on each harmonic content data in the harmonic content data domain, so as to obtain an outlier recognition result of each harmonic content data.
The harmonic identification module 504 is configured to determine an identification result of the harmonic content curve according to an outlier identification result of each harmonic content data.
In one embodiment, the outlier identification module is further configured to determine, from the harmonic content data field, target harmonic content data that is the same as the industry type corresponding to each harmonic content data according to the industry type corresponding to each harmonic content data; obtaining a distance neighborhood of each harmonic content data according to the Gaussian distance between each harmonic content data and the target harmonic content data corresponding to each harmonic content data; according to the distance neighborhood of each harmonic content data, calculating to obtain local outlier factors of each harmonic content data; and carrying out outlier identification on each harmonic content data according to the local outlier factor of each harmonic content data to obtain an outlier identification result of each harmonic content data.
In one embodiment, the harmonic identification module is further configured to obtain a number of harmonic content data identified as outlier data in the outlier identification result; and under the condition that the quantity meets the preset abnormal quantity condition, confirming that the identification result of the harmonic content rate curve is abnormal.
In one embodiment, the curve classification module 501 is further configured to obtain a classification radius and a minimum harmonic number; screening from the harmonic content curve according to the classification radius and the minimum harmonic quantity to obtain a first clustering center; and clustering the harmonic content curves according to the first clustering center to obtain a classification result of the harmonic content curves, and obtaining a typical harmonic content curve with a typical class corresponding to the classification result.
In one embodiment, the curve clustering module 502 is further configured to obtain a preset number of clusters; acquiring a harmonic content rate typical curve of a preset clustering number from the harmonic content rate typical curve, and taking the harmonic content rate typical curve as a second aggregation center; and clustering the typical curve of the harmonic content according to the industry type of the measuring terminal corresponding to the second aggregation center to obtain a harmonic content data field of a preset clustering number corresponding to the typical curve of the harmonic content.
In one embodiment, the harmonic data recognition device 500 further includes a harmonic acquisition module, configured to acquire harmonic data of the measurement terminal in the target time period according to a preset sampling frequency; and calculating to obtain a harmonic content curve of the measurement terminal according to the harmonic data.
The respective modules in the above harmonic data recognition apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, the internal structure of which may be as shown in FIG. 6. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing harmonic data, harmonic content curves and other data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of harmonic data identification.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method of harmonic data identification, the method comprising:
collecting harmonic data of the measurement terminal according to a preset sampling frequency in a plurality of target time periods;
carrying out ratio processing on the root mean square value of the harmonic component and the root mean square value of the fundamental component of the harmonic data to obtain harmonic content data of the measuring terminal in a plurality of target time periods; the harmonic content data are used for drawing a harmonic content curve of the measurement terminal;
Classifying the harmonic content curves of the measurement terminals to obtain corresponding harmonic content typical curves with typical categories;
clustering the harmonic content typical curves according to industry types of the measuring terminals corresponding to the harmonic content typical curves to obtain harmonic content data fields corresponding to the harmonic content typical curves of each industry type;
carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data;
counting the number of the harmonic content data of which the outlier identification result is of an outlier type in each target time period according to the outlier identification result of each harmonic content data;
under the condition that the number of outlier categories in each target time period exceeds a preset number threshold, confirming that the identification result of the harmonic content curve of the measurement terminal is abnormal, and the harmonic data of the measurement terminal is also abnormal; otherwise, confirming that the identification result of the harmonic content curve of the measurement terminal is normal, and the harmonic data of the measurement terminal is also normal;
The step of classifying the harmonic content rate curve of the measurement terminal to obtain a corresponding harmonic content rate typical curve with a typical class, which comprises the following steps:
acquiring a classification radius and the minimum harmonic quantity;
screening to obtain a first clustering center and boundary points from the harmonic content curve according to the classification radius and the minimum harmonic quantity;
and clustering the harmonic content curves except the first clustering center and the boundary points according to the first clustering center and the boundary points to obtain a classification result of the harmonic content curves, and obtaining a harmonic content typical curve with a typical class corresponding to the classification result.
2. The method of claim 1, wherein said locally outlier identifying each harmonic content data in said harmonic content data field to obtain outlier identification of each harmonic content data comprises:
determining target harmonic content data which are the same as industry types corresponding to the harmonic content data from the harmonic content data domain according to the industry types corresponding to the harmonic content data;
Obtaining a distance neighborhood of each harmonic content data according to the Gaussian distance between each harmonic content data and the target harmonic content data corresponding to each harmonic content data;
calculating local outlier factors of the harmonic content data according to the distance neighborhood of the harmonic content data;
and carrying out outlier identification on the harmonic content data according to the local outlier factors of the harmonic content data to obtain outlier identification results of the harmonic content data.
3. The method according to claim 1, wherein the clustering the harmonic content representative curves according to the industry types of the measurement terminals corresponding to the harmonic content representative curves to obtain harmonic content data fields corresponding to the harmonic content representative curves of each industry type includes:
acquiring a preset clustering quantity;
acquiring the harmonic content rate typical curves of the preset clustering quantity from the harmonic content rate typical curves, and taking the harmonic content rate typical curves as a second clustering center;
and clustering the harmonic content typical curves according to industry types of the measuring terminals corresponding to the second aggregation centers to obtain harmonic content data fields corresponding to the harmonic content typical curves of each industry type.
4. A method according to any one of claims 1 to 3, further comprising, before classifying the harmonic content curves of the measurement terminals to obtain a harmonic content representative curve of a representative class corresponding to the harmonic content representative curve:
acquiring harmonic data of the measurement terminal in the target time period according to a preset sampling frequency;
and calculating to obtain a harmonic content curve of the measurement terminal according to the harmonic data.
5. A harmonic data identification apparatus, the apparatus comprising:
collecting harmonic data of the measurement terminal according to a preset sampling frequency in a plurality of target time periods; carrying out ratio processing on the root mean square value of the harmonic component and the root mean square value of the fundamental component of the harmonic data to obtain harmonic content data of the measuring terminal in a plurality of target time periods; the harmonic content data are used for drawing a harmonic content curve of the measurement terminal;
the curve classification module is used for classifying the harmonic content curves of the measurement terminals to obtain a harmonic content typical curve with a typical class corresponding to the harmonic content curves;
the curve clustering module is used for clustering the harmonic content typical curves according to industry types of the measuring terminals corresponding to the harmonic content typical curves to obtain harmonic content data fields corresponding to the harmonic content typical curves of each industry type;
The outlier identification module is used for carrying out local outlier identification on each harmonic content data in the harmonic content data domain to obtain outlier identification results of each harmonic content data;
the harmonic identification module is used for counting the number of the harmonic content data of which the outlier identification result is an outlier class in each target time period according to the outlier identification result of each harmonic content data; under the condition that the number of outlier categories in each target time period exceeds a preset number threshold, confirming that the identification result of the harmonic content curve of the measurement terminal is abnormal, and the harmonic data of the measurement terminal is also abnormal; otherwise, confirming that the identification result of the harmonic content curve of the measurement terminal is normal, and the harmonic data of the measurement terminal is also normal;
the curve classification module is also used for acquiring classification processing radius and minimum harmonic quantity; screening to obtain a first clustering center and boundary points from the harmonic content curve according to the classification radius and the minimum harmonic quantity; and clustering the harmonic content curves except the first clustering center and the boundary points according to the first clustering center and the boundary points to obtain a classification result of the harmonic content curves, and obtaining a harmonic content typical curve with a typical class corresponding to the classification result.
6. The apparatus of claim 5, wherein the outlier identification module is further configured to determine, from the harmonic content data field, target harmonic content data of a same industry type as the respective harmonic content data according to the industry type corresponding to the respective harmonic content data; obtaining a distance neighborhood of each harmonic content data according to the Gaussian distance between each harmonic content data and the target harmonic content data corresponding to each harmonic content data; calculating local outlier factors of the harmonic content data according to the distance neighborhood of the harmonic content data; and carrying out outlier identification on the harmonic content data according to the local outlier factors of the harmonic content data to obtain outlier identification results of the harmonic content data.
7. The apparatus of claim 5, wherein the curve clustering module is further configured to obtain a preset number of clusters; acquiring the harmonic content rate typical curves of the preset clustering quantity from the harmonic content rate typical curves, and taking the harmonic content rate typical curves as a second clustering center; and clustering the harmonic content typical curves according to industry types of the measuring terminals corresponding to the second aggregation centers to obtain harmonic content data fields corresponding to the harmonic content typical curves of each industry type.
8. The device according to claim 5, wherein the harmonic data recognition device further comprises a harmonic acquisition module, configured to acquire harmonic data of the measurement terminal in the target time period according to a preset sampling frequency; and calculating to obtain a harmonic content curve of the measurement terminal according to the harmonic data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211533808.7A CN115563477B (en) | 2022-12-02 | 2022-12-02 | Harmonic data identification method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211533808.7A CN115563477B (en) | 2022-12-02 | 2022-12-02 | Harmonic data identification method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115563477A CN115563477A (en) | 2023-01-03 |
| CN115563477B true CN115563477B (en) | 2023-05-02 |
Family
ID=84770280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211533808.7A Active CN115563477B (en) | 2022-12-02 | 2022-12-02 | Harmonic data identification method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115563477B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116756597B (en) * | 2023-08-16 | 2023-11-14 | 山东泰开电力电子有限公司 | Wind turbine generator harmonic data real-time monitoring method based on artificial intelligence |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485089B (en) * | 2016-10-21 | 2019-03-12 | 福州大学 | The interval parameter acquisition methods of harmonic wave user's typical condition |
| CN108416103A (en) * | 2018-02-05 | 2018-08-17 | 武汉大学 | A kind of method for diagnosing faults of electric automobile of series hybrid powder AC/DC convertor |
| CN112800231B (en) * | 2021-03-31 | 2021-07-20 | 南方电网数字电网研究院有限公司 | Power data verification method and device, computer equipment and storage medium |
| CN113743519A (en) * | 2021-09-09 | 2021-12-03 | 中国南方电网有限责任公司 | Power grid bus typical load curve identification method |
-
2022
- 2022-12-02 CN CN202211533808.7A patent/CN115563477B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115563477A (en) | 2023-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107679734A (en) | It is a kind of to be used for the method and system without label data classification prediction | |
| CN116167010B (en) | Rapid identification method for abnormal events of power system with intelligent transfer learning capability | |
| CN114519514B (en) | Low-voltage transformer area reasonable line loss value measuring and calculating method, system and computer equipment | |
| CN115412371B (en) | Big data security protection method and system based on Internet of things and cloud platform | |
| CN115563477B (en) | Harmonic data identification method, device, computer equipment and storage medium | |
| CN111522968A (en) | Knowledge graph fusion method and device | |
| CN114997256A (en) | Method and device for detecting abnormal power of wind power plant and storage medium | |
| CN106570104A (en) | Multi-partition clustering preprocessing method of stream data | |
| CN115617784A (en) | Data processing system and processing method for informationized power distribution | |
| CN117787572B (en) | Abnormal electricity utilization user identification method and device, storage medium and electronic equipment | |
| CN114021425B (en) | Power system operation data modeling and feature selection method and device, electronic equipment and storage medium | |
| CN111709668A (en) | Power grid equipment parameter risk identification method and device based on data mining technology | |
| CN117556369B (en) | Power theft detection method and system for dynamically generated residual error graph convolution neural network | |
| CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
| CN117036060A (en) | Vehicle insurance fraud recognition method, device and storage medium | |
| CN115035966B (en) | Superconductor screening method, device and equipment based on active learning and symbolic regression | |
| CN116561607A (en) | Method and device for detecting abnormality of resource interaction data and computer equipment | |
| CN113656937A (en) | Method, device, storage medium and processor for identifying topology of power equipment | |
| CN115526368A (en) | Power battery capacity prediction method, device and equipment | |
| CN115209441A (en) | Method, device, equipment and storage medium for predicting base station out-of-service alarm | |
| CN113723835B (en) | Water consumption evaluation method and terminal equipment for thermal power plant | |
| CN113705920B (en) | Method for generating water data sample set for thermal power plant and terminal equipment | |
| CN117078112B (en) | Energy consumption detection method and data analysis system applied to enterprise abnormal electricity management | |
| CN116029614A (en) | Power quality assessment method, device and computer equipment for power distribution network area | |
| Tian et al. | Nonlinear Data Classification of Power Internet of Things Considering Transient and Steady State |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |