CN114336666B - Reactive harmonic integrated compensator - Google Patents
Reactive harmonic integrated compensator Download PDFInfo
- Publication number
- CN114336666B CN114336666B CN202210032858.0A CN202210032858A CN114336666B CN 114336666 B CN114336666 B CN 114336666B CN 202210032858 A CN202210032858 A CN 202210032858A CN 114336666 B CN114336666 B CN 114336666B
- Authority
- CN
- China
- Prior art keywords
- scheme
- retrieval
- current
- reactive
- compensation
- 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
- Y02E40/30—Reactive power compensation
-
- 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)
Abstract
The invention disclosesA reactive harmonic integrated compensator belongs to the technical field of reactive compensation and comprises an acquisition module, a scheme library, a compensation module and a server; the acquisition module is used for acquiring reactive current data to obtain corrected three-phase reactive current i aq’ 、i bq’ 、i cq’ (ii) a The scheme library is used for storing compensation schemes, acquiring historical detection data of the current power grid and setting a compensation scheme template according to the acquired historical detection data; marking the characteristic words in the compensation scheme template and establishing a template characteristic word set; establishing a scheme retrieval formula according to the template feature word set, and acquiring a plurality of retrieval schemes through the scheme retrieval formula; preprocessing the acquired retrieval schemes to acquire feature words of each retrieval scheme; and establishing a retrieval feature word set, mapping the retrieval feature word set and the template feature word set to a vector space to construct a MeSH space matrix, realizing intelligent reactive power compensation, improving the quality of electric energy accessed to a power grid, and ensuring the normal operation of various devices.
Description
Technical Field
The invention belongs to the technical field of reactive compensation, and particularly relates to a reactive harmonic integrated compensator.
Background
In recent years, various inductive loads are widely used, which bring convenience to social production and life, and simultaneously generate a large amount of reactive power, which is particularly prominent in a power distribution network, so that the problem of reactive power of the power distribution network is urgently solved. The reactive compensation has the functions of ensuring the reliable operation of electric equipment, improving the power factor, reducing the circuit loss and preventing the increase of the equipment capacity, and the functions can obviously improve the electric energy quality. Therefore, a reactive harmonic integrated compensator is needed to solve the above problems.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides a reactive harmonic integrated compensator.
The purpose of the invention can be realized by the following technical scheme:
the reactive harmonic integrated compensator comprises an acquisition module, a scheme library, a compensation module and a server;
the acquisition module is used for acquiring reactive current data to obtain corrected three-phase reactive current i aq ’、i bq ’、i cq '; the scheme library is used for storing compensation schemes, and the specific method comprises the following steps:
acquiring historical detection data of a current power grid, and setting a compensation scheme template according to the acquired historical detection data; marking the characteristic words in the compensation scheme template and establishing a template characteristic word set; establishing a scheme retrieval formula according to the template feature word set, and acquiring a plurality of retrieval schemes through the scheme retrieval formula; preprocessing the acquired retrieval schemes to acquire the feature words of each retrieval scheme; establishing a retrieval characteristic word set, mapping the retrieval characteristic word set and the template characteristic word set to a vector space to construct a MeSH space matrix, calculating the similarity between the retrieval characteristic word set and each template characteristic word set, marking the retrieval characteristic word set with the similarity lower than a threshold value X1 as a useless word set, deleting retrieval schemes corresponding to the useless word set, marking the rest retrieval schemes as supplement schemes, and storing the compensation schemes in a scheme library; identifying three-phase reactive current in all compensation schemes in the scheme library, and marking the identified three-phase reactive current on the corresponding compensation scheme as a matching label;
the compensation module acquires the collected correction three-phase reactive current i aq ’、i bq ’、i cq ' marking the data as matching data, inputting the matching data into a scheme library for matching to obtain a corresponding compensation scheme, and performing reactive compensation on the power grid according to the obtained compensation scheme.
Further, the working method of the acquisition module comprises the following steps:
the instantaneous values of the three-phase circuit currents are respectively marked as i a 、i b 、i c Converting the instantaneous value of the three-phase circuit current to an alpha-beta two-phase orthogonal coordinate system through park conversion, and calculating two-phase instantaneous currents i alpha and i beta; the calculation formula is as follows:
instantaneous active component i of three-phase circuit p Instantaneous reactive component i q Respectively as follows:
detecting voltage waveform and current waveform of a power grid to obtain voltage waveform information and current waveform information, drawing a voltage waveform diagram and a current waveform diagram according to the obtained voltage waveform information and current waveform information, respectively marking the voltage waveform diagram and the current waveform diagram as a voltage detection waveform diagram and a current detection waveform diagram, establishing a voltage correction model and a current correction model, correcting the voltage detection waveform diagram through the voltage correction model, and obtaining a voltage correction waveform diagram and corresponding voltage correction data; correcting the current detection oscillogram through a current correction model to obtain a current correction oscillogram and corresponding current correction data;
according to the formula
Calculating active power p and reactive power q;
the direct current components of active power p and reactive power q respectively are to be
Reactive current can be obtained through inverse transformation, and the three-phase reactive current calculation formula is as follows:
setting a collection correction model, inputting the three-phase reactive current, current correction data and voltage correction data into the collection correction model to obtain a corrected three-phase reactive current i aq ’、i bq ’、i cq ’。
Further, the air conditioner is provided with a fan,
further, the method for establishing the scheme retrieval formula according to the template feature word set comprises the following steps:
and establishing a retrieval model, inputting the template feature word set into the retrieval model, acquiring a scheme retrieval formula, and retrieving contents according to the scheme retrieval formula.
And further, setting an enhanced learning unit, acquiring recorded data searched according to a scheme searching formula, grading according to the searched recorded data and the compensation scheme reserved after screening, not performing operation when the grading is qualified, acquiring corresponding recorded data when the grading is unqualified, modifying the scheme searching formula, integrating the modified scheme searching formula and the corresponding input data into self-learning data, and inputting the self-learning data into a searching model for relearning.
Further, the method for preprocessing the acquired retrieval schemes and acquiring the feature words of each retrieval scheme comprises the following steps:
cleaning the retrieval scheme; acquiring a word segmentation word bank, a stop word bank and a feature word bank, and segmenting the cleaned retrieval scheme based on the word segmentation word bank; and removing stop words from the segmented retrieval scheme according to the stop word lexicon, and extracting the feature words from the retrieval scheme of the stop words on the basis of the feature word lexicon.
Compared with the prior art, the invention has the beneficial effects that: the intelligent reactive compensation is realized, the quality of electric energy accessed to a power grid is improved, the normal operation of various devices is ensured, and the service life of the used devices is prolonged; through the mutual matching among the acquisition module, the scheme library and the compensation module, the quality of the electric energy currently accessed to the power grid is improved in time, the power supply quality of the circuit is fundamentally improved, and the adverse effect of the current voltage quality on social life and production is effectively avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic block diagram of the present invention;
fig. 2 is a schematic diagram of an acquisition module of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1 to 2, the reactive harmonic integrated compensator includes an acquisition module, a scheme library, a compensation module, and a server;
the acquisition module is used for acquiring reactive current data, and the specific method comprises the following steps:
the instantaneous values of the three-phase circuit currents are respectively marked as i a 、i b 、i c Converting the instantaneous value of the three-phase circuit current to an alpha-beta two-phase orthogonal coordinate system through park conversion, and calculating two-phase instantaneous currents i alpha and i beta; the calculation formula is as follows:
then the instantaneous active component i of the three-phase circuit p Instantaneous reactive component i q Respectively as follows:
detecting voltage waveform and current waveform of a power grid to obtain voltage waveform information and current waveform information, drawing a voltage waveform diagram and a current waveform diagram according to the obtained voltage waveform information and current waveform information, respectively marking the voltage waveform diagram and the current waveform diagram as a voltage detection waveform diagram and a current detection waveform diagram, establishing a voltage correction model and a current correction model, correcting the voltage detection waveform diagram through the voltage correction model, and obtaining a voltage correction waveform diagram and corresponding voltage correction data; correcting the current detection oscillogram through a current correction model to obtain a current correction oscillogram and corresponding current correction data;
according to the formula
Calculating active power p and reactive power q, wherein:
the dc components of active power p and reactive power q, respectively. Will be provided with
Reactive current can be obtained through inverse transformation, and the three-phase reactive current calculation formula is as follows:
The voltage correction model and the current correction model are established based on a CNN network or a DNN network, and are trained by establishing a voltage training set and a current training set respectively, wherein the voltage training set comprises a voltage detection oscillogram, a voltage correction oscillogram and current correction data which are correspondingly arranged, the current training set comprises a current detection oscillogram, a current correction oscillogram and current correction data which are correspondingly arranged, and the voltage correction data are arranged according to the correction process of the voltage detection oscillogram and the requirements of subsequent data processing; the current correction data is set according to the correction process of the current detection waveform diagram and the requirement of subsequent data processing.
The acquisition and correction model is established based on a CNN network or a DNN network, and is trained by establishing an acquisition training set, wherein the acquisition training set comprises three-phase reactive current, current correction data, voltage correction data and correspondingly set corrected three-phase reactive current.
The scheme library is used for storing compensation schemes, and the specific method comprises the following steps:
acquiring historical detection data of a current power grid, and setting a compensation scheme template according to the acquired historical detection data; marking the characteristic words in the compensation scheme template and establishing a template characteristic word set; the method comprises the steps that labeling statistics can be carried out in the process of setting a compensation scheme template, a scheme retrieval formula is established according to a template feature word set, and a plurality of retrieval schemes are obtained through the scheme retrieval formula; preprocessing the acquired retrieval schemes to acquire the feature words of each retrieval scheme; establishing a retrieval characteristic word set, mapping the retrieval characteristic word set and the template characteristic word set to a vector space to construct a MeSH space matrix, calculating the similarity between the retrieval characteristic word set and each template characteristic word set, marking the retrieval characteristic word set with the similarity lower than a threshold value X1 as a useless word set, deleting retrieval schemes corresponding to the useless word set, marking the rest retrieval schemes as supplement schemes, and storing the compensation schemes in a scheme library; and identifying the three-phase reactive current in all the compensation schemes in the scheme library, and marking the identified three-phase reactive current as a matching label on the corresponding compensation scheme.
The method for constructing the MeSH space matrix by mapping the retrieval feature word set and the template feature word set to the vector space comprises the following steps:
when the characteristic words in the template characteristic word set exist in the retrieval characteristic word set, marking the characteristic words by 1, otherwise marking the characteristic words by 0; for example: retrieving vector results corresponding to feature word sets
When all the characteristic words in the search characteristic word set are marked with 1 or 0, calculating the searchAnd mapping the retrieval feature word set to a vector space according to the weight values of all the feature words marked as 1 in the same retrieval feature word set, and forming a MeSH space matrix by adopting all the retrieval feature word sets mapped to the vector space.
The compensation scheme template is set by an expert group according to historical detection data;
the method for establishing the scheme retrieval formula according to the template feature word set comprises the following steps:
establishing a retrieval model, inputting a template feature word set into the retrieval model, acquiring a scheme retrieval formula, retrieving contents according to the scheme retrieval formula, setting an enhanced learning unit, evaluating the contents retrieved by using the scheme retrieval formula through the enhanced learning unit, and relearning the retrieval model;
acquiring recorded data searched according to a scheme retrieval formula, grading according to the searched recorded data and the data reserved after screening, not performing operation when the grading is qualified, acquiring corresponding recorded data when the grading is unqualified, modifying the scheme retrieval formula, integrating the modified scheme retrieval formula and corresponding input data into self-learning data, and inputting the self-learning data into a retrieval model for relearning;
the data retained after screening in scoring based on the retrieved record data and the data retained after screening means the scheme data remaining after screening the retrieved scheme data.
The retrieval model is established based on a neural network model and is trained by taking a template feature word set and a correspondingly set scheme retrieval formula as a training set.
The method for preprocessing the acquired retrieval schemes and acquiring the feature words of each retrieval scheme comprises the following steps:
cleaning the retrieval scheme; because the retrieval scheme is generally from a basic corpus database, such as an article description table, an article attribute table and the like provided by a big data platform, the article data is very irregular, json character strings are arranged in the article data, and a plurality of special symbols are arranged in the article data, a Spark program is adopted to carry out regular matching automatic processing to carry out data cleaning before word segmentation, such as punctuation removal, word removal, text format conversion, html webpage label removal and the like;
acquiring a word segmentation word bank, a stop word bank and a feature word bank, and segmenting the cleaned retrieval scheme based on the word segmentation word bank; removing stop words, such as words without practical meaning, such as ' o ', ' wool ', ' and the like, from the segmented search scheme according to the stop word lexicon; and extracting the feature words from the search scheme of the removed stop words based on the feature word library.
The word segmentation word bank, the stop word bank and the feature word bank can all use the existing word segmentation word bank, stop word bank and feature word bank, the feature word bank can be composed of a common feature word bank and a feature word bank, the feature word bank is generally composed of self-defined words serving as feature words and can be increased or decreased manually, and in the specific implementation, words with IDF values larger than a preset weight threshold value and/or the self-defined words serving as feature words can be updated to the feature word bank, so that the feature word bank is continuously filled, and the feature words extracted according to the feature word bank can reflect a retrieval scheme;
the method for segmenting the cleaned retrieval scheme based on the segmentation word bank comprises the following steps: because Chinese does not have a clear segmentation signature, a hidden Markov model may be preferred for distributed segmentation to separate articles into sets of terms.
The compensation module is used for carrying out reactive compensation according to the acquired data, and the specific method comprises the following steps:
acquiring collected corrected three-phase reactive current i aq ’、i bq ’、i cq ' marking as matching data, inputting the matching data into a scheme library for matching to obtain a corresponding compensation scheme, and performing reactive compensation on the power grid according to the obtained compensation scheme.
The above formulas are all calculated by removing dimensions and taking numerical values thereof, the formula is a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest real situation, and the preset parameters and the preset threshold value in the formula are set by the technical personnel in the field according to the actual situation or obtained by simulating a large amount of data.
The working principle of the invention is as follows: the acquisition module is used for acquiring reactive current data to obtain corrected three-phase reactive current i aq ’、i bq ’、i cq '; acquiring historical detection data of a current power grid, and setting a compensation scheme template according to the acquired historical detection data; marking the characteristic words in the compensation scheme template and establishing a template characteristic word set; establishing a scheme retrieval formula according to the template feature word set, and acquiring a plurality of retrieval schemes through the scheme retrieval formula; preprocessing the acquired retrieval schemes to acquire the feature words of each retrieval scheme; establishing a retrieval characteristic word set, mapping the retrieval characteristic word set and the template characteristic word set to a vector space to construct a MeSH space matrix, calculating the similarity between the retrieval characteristic word set and each template characteristic word set, marking the retrieval characteristic word set with the similarity lower than a threshold value X1 as a useless word set, deleting retrieval schemes corresponding to the useless word set, marking the rest retrieval schemes as supplement schemes, and storing the compensation schemes in a scheme library; identifying three-phase reactive current in all compensation schemes in the scheme library, and marking the identified three-phase reactive current as a matching label on the corresponding compensation scheme; the compensation module acquires the collected correction three-phase reactive current i aq ’、i bq ’、i cq ' marking the data as matching data, inputting the matching data into a scheme library for matching to obtain a corresponding compensation scheme, and performing reactive compensation on the power grid according to the obtained compensation scheme.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (6)
1. The reactive harmonic integrated compensator is characterized by comprising an acquisition module, a scheme library, a compensation module and a server;
the acquisition module is used for acquiring reactive current data to obtain corrected three-phase reactive current i aq ’、i bq ’、i cq '; the scheme library is used for storing compensation schemes, and the specific method comprises the following steps:
acquiring historical detection data of a current power grid, and setting a compensation scheme template according to the acquired historical detection data; marking the characteristic words in the compensation scheme template and establishing a template characteristic word set; establishing a scheme retrieval formula according to the template feature word set, and acquiring a plurality of retrieval schemes through the scheme retrieval formula; preprocessing the acquired retrieval schemes to acquire feature words of each retrieval scheme; establishing a retrieval characteristic word set, mapping the retrieval characteristic word set and the template characteristic word set to a vector space to construct a MeSH space matrix, calculating the similarity between the retrieval characteristic word set and each template characteristic word set, marking the retrieval characteristic word set with the similarity lower than a threshold value X1 as a useless word set, deleting retrieval schemes corresponding to the useless word set, marking the rest retrieval schemes as supplement schemes, and storing the compensation schemes in a scheme library; identifying three-phase reactive current in all compensation schemes in the scheme library, and marking the identified three-phase reactive current on the corresponding compensation scheme as a matching label;
the compensation module acquires the collected correction three-phase reactive current i aq ’、i bq ’、i cq ' marking the data as matching data, inputting the matching data into a scheme library for matching to obtain a corresponding compensation scheme, and performing reactive compensation on the power grid according to the obtained compensation scheme.
2. The reactive harmonic integrated compensator of claim 1, wherein the working method of the acquisition module comprises:
the instantaneous values of the three-phase circuit currents are respectively marked as i a 、i b 、i c Converting the instantaneous value of the three-phase circuit current to an alpha-beta two-phase orthogonal coordinate system through park conversion to calculate two-phase instantaneous currents i alpha and i beta; the calculation formula is as follows:
then the instantaneous active component i of the three-phase circuit p Instantaneous reactive component i q Respectively as follows:
detecting voltage waveform and current waveform of a power grid to obtain voltage waveform information and current waveform information, drawing a voltage waveform diagram and a current waveform diagram according to the obtained voltage waveform information and current waveform information, respectively marking the voltage waveform diagram and the current waveform diagram as a voltage detection waveform diagram and a current detection waveform diagram, establishing a voltage correction model and a current correction model, correcting the voltage detection waveform diagram through the voltage correction model, and obtaining a voltage correction waveform diagram and corresponding voltage correction data; correcting the current detection oscillogram through a current correction model to obtain a current correction oscillogram and corresponding current correction data;
according to the formula
Calculating active power p and reactive power q;
the direct current components of active power p and reactive power q respectively are to be
Reactive current can be obtained through inverse transformation, and the three-phase reactive current calculation formula is as follows:
setting a collection correction model, inputting the three-phase reactive current, current correction data and voltage correction data into the collection correction model to obtain a corrected three-phase reactive current i aq ’、i bq ’、i cq ’。
3. The reactive harmonic integrated compensator of claim 2,
4. the reactive harmonic integrated compensator of claim 1, wherein the method of establishing a scheme search from the template feature word set comprises:
and establishing a retrieval model, inputting the template feature word set into the retrieval model, acquiring a scheme retrieval formula, and retrieving contents according to the scheme retrieval formula.
5. The reactive power and harmonic integrated compensator according to claim 4, wherein a reinforcement learning unit is provided to obtain recorded data retrieved according to a scheme retrieval formula, score according to the retrieved recorded data and the compensation scheme retained after screening, do not operate when the score is qualified, obtain corresponding recorded data when the score is unqualified, modify the scheme retrieval formula, integrate the modified scheme retrieval formula and corresponding input data into self-learning data, and input the self-learning data into a retrieval model for relearning.
6. The reactive harmonic integrated compensator according to claim 1, wherein the obtained search schemes are preprocessed, and the method for obtaining the feature words of each search scheme comprises:
cleaning the retrieval scheme; acquiring a word segmentation word bank, a stop word bank and a feature word bank, and segmenting the cleaned retrieval scheme based on the word segmentation word bank; and removing stop words from the segmented retrieval scheme according to the stop word lexicon, and extracting the feature words from the retrieval scheme of the stop words on the basis of the feature word lexicon.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210032858.0A CN114336666B (en) | 2022-01-12 | 2022-01-12 | Reactive harmonic integrated compensator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210032858.0A CN114336666B (en) | 2022-01-12 | 2022-01-12 | Reactive harmonic integrated compensator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114336666A CN114336666A (en) | 2022-04-12 |
| CN114336666B true CN114336666B (en) | 2022-12-27 |
Family
ID=81027672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210032858.0A Active CN114336666B (en) | 2022-01-12 | 2022-01-12 | Reactive harmonic integrated compensator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114336666B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI239439B (en) * | 2004-03-24 | 2005-09-11 | Uis Abler Electronics Co Ltd | Reactive power compensating device |
| CN101122909B (en) * | 2006-08-10 | 2010-06-16 | 株式会社日立制作所 | Text message indexing unit and text message indexing method |
| CN201994670U (en) * | 2010-10-26 | 2011-09-28 | 中国电力科学研究院 | Low-voltage dynamic generalized reactive power compensation device |
| CN103199533B (en) * | 2013-03-13 | 2016-08-03 | 南方电网科学研究院有限责任公司 | Optimal Design of Passive Power Filter method based on two point form operating mode |
| CN107579522A (en) * | 2017-09-11 | 2018-01-12 | 云南电网有限责任公司西双版纳供电局 | Coordinated control system based on Ip Iq theories harmonic wave controls and reactive-load compensation |
-
2022
- 2022-01-12 CN CN202210032858.0A patent/CN114336666B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114336666A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105608218B (en) | The method for building up of intelligent answer knowledge base establishes device and establishes system | |
| CN109960800A (en) | Weakly supervised file classification method and device based on Active Learning | |
| CN109614488B (en) | Text classification and image recognition-based distribution network live working condition judgment method | |
| CN107506389B (en) | Method and device for extracting job skill requirements | |
| CN108280051B (en) | Detection method, device and the equipment of error character in a kind of text data | |
| CN110781671A (en) | Knowledge mining method for intelligent IETM fault maintenance record text | |
| CN109800416A (en) | A kind of power equipment title recognition methods | |
| CN104216979B (en) | Chinese technique patent automatic classifying system and the method that patent classification is carried out using the system | |
| CN107145573A (en) | The problem of artificial intelligence customer service robot, answers method and system | |
| CN111143571B (en) | Entity labeling model training method, entity labeling method and device | |
| CN113157860B (en) | Electric power equipment maintenance knowledge graph construction method based on small-scale data | |
| Ding et al. | Research on text information mining technology of substation inspection based on improved Jieba | |
| CN113901214B (en) | Method and device for extracting form information, electronic equipment and storage medium | |
| CN106611016A (en) | Image retrieval method based on decomposable word pack model | |
| CN114336666B (en) | Reactive harmonic integrated compensator | |
| CN110704638A (en) | Clustering algorithm-based electric power text dictionary construction method | |
| CN112148735B (en) | Construction method for structured form data knowledge graph | |
| CN112036179B (en) | Electric power plan information extraction method based on text classification and semantic frame | |
| CN112560480A (en) | Task community discovery method, device, equipment and storage medium | |
| CN110941910A (en) | Intelligent auxiliary method and system for power grid three-dimensional design review | |
| CN112765314B (en) | Power information retrieval method based on power ontology knowledge base | |
| CN113762589A (en) | Power transmission and transformation project change prediction system and method | |
| CN113961549A (en) | Medical data integration method and system based on data warehouse | |
| Liu et al. | Historical Similar Ticket Matching and Extraction used for Power Grid Maintenance Work Ticket Decision Making | |
| CN113051912B (en) | Domain word recognition method and device based on word forming rate |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220824 Address after: 528400 room 1105-1, digital building, No. 16, exhibition East Road, Torch Development Zone, Zhongshan City, Guangdong Province Applicant after: Zhongshan Jingming Intelligent Energy Technology Co.,Ltd. Address before: 528437 room 1301-1, digital building, No. 16, exhibition East Road, Torch Development Zone, Zhongshan City, Guangdong Province Applicant before: Huasheng intelligent (Guangdong) equipment Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |