CN113722328A - Multi-source time-space analysis algorithm for high-voltage switchgear faults - Google Patents
Multi-source time-space analysis algorithm for high-voltage switchgear faults Download PDFInfo
- Publication number
- CN113722328A CN113722328A CN202111033819.4A CN202111033819A CN113722328A CN 113722328 A CN113722328 A CN 113722328A CN 202111033819 A CN202111033819 A CN 202111033819A CN 113722328 A CN113722328 A CN 113722328A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- analysis
- fault characteristic
- characteristic quantity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 62
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 59
- 238000012512 characterization method Methods 0.000 claims abstract description 35
- 230000007547 defect Effects 0.000 claims abstract description 9
- 238000009413 insulation Methods 0.000 claims abstract description 9
- 238000010219 correlation analysis Methods 0.000 claims description 15
- 238000010835 comparative analysis Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 13
- 238000012731 temporal analysis Methods 0.000 claims description 11
- 238000004141 dimensional analysis Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a multi-source space-time analysis algorithm for faults of high-voltage switchgear, which comprises the following steps: firstly, acquiring various fault characterization quantity data of high-voltage switch equipment, and storing the data into a database; the invention provides theoretical support for realizing multi-dimensional comprehensive analysis of the high-voltage switch equipment by analyzing the incidence relation among various fault characteristic quantities and the relation between the incidence relation and the fault characteristic in a multi-dimensional way, and simultaneously, the analysis of the fault characteristic quantities is not limited to the comparison of absolute thresholds, and the comparison of transverse data and longitudinal data is carried out simultaneously so as to ensure that the fault judgment is more three-dimensional and accurate, finally, an algorithm model between the fault characteristic quantities and the fault characteristic of the high-voltage switch equipment is established, and a multi-source time-space analysis algorithm of the temperature and the insulation defect of the switch cabinet is formed so as to improve the accuracy of defect alarm, reduce false alarm and false alarm, and be beneficial to improving operation and maintenance efficiency and reducing safety risk.
Description
Technical Field
The invention belongs to the field of high-voltage switchgear fault analysis, and particularly relates to a multi-source time-space analysis algorithm for high-voltage switchgear faults.
Background
In the existing life, a high-voltage switch device is an electrical appliance with a rated voltage of 1kV or more, which is mainly used for switching on and off a conductive loop, and is a general term formed by connecting a high-voltage switch, corresponding control, measurement, protection and regulation devices, accessories, shells, supports and other parts, and electrical and mechanical parts thereof, and is an important control device for switching on and off a loop, cutting off and isolating faults.
However, in actual use of the existing high-voltage switchgear fault analysis algorithm, multidimensional analysis cannot be performed on the incidence relation between various characteristic quantities of a high-voltage switchgear fault and the relation between the incidence relation and fault characteristics, so that theoretical support cannot be provided for comprehensive analysis, and meanwhile, in actual application of the existing analysis algorithm, comparison analysis cannot be performed on transverse data and longitudinal data, so that an algorithm model between the characteristic quantities and the fault characteristics cannot be formed, so that the accuracy of defect alarm is poor, false alarm and false alarm are easy to occur, operation and maintenance efficiency is not improved, certain safety risk exists, and practical application is not facilitated.
The invention content is as follows:
the invention aims to provide a multi-source space-time analysis algorithm for high-voltage switchgear faults in order to solve the problems, and the problems in the background art are solved.
In order to solve the above problems, the present invention provides a technical solution:
the multi-source space-time analysis algorithm for the faults of the high-voltage switch equipment comprises the following steps:
s1, firstly, acquiring various fault characterization quantity data of the high-voltage switch equipment, and storing the data into a database;
s2, acquiring fault characteristics of the high-voltage switch equipment, storing the fault characteristics into a database, and simultaneously respectively carrying out multi-dimensional analysis and correlation analysis on the fault characteristics and the acquired data of various fault characteristic quantities to obtain correlation among the characteristic quantities and the relation between the correlation and the fault characteristics;
s3, respectively acquiring fault characteristic quantity data and transverse data and longitudinal data of fault characteristics, and respectively carrying out comparative analysis on the fault characteristic quantity data and the transverse data and the longitudinal data of the fault characteristics;
s4, establishing an algorithm model between fault characteristic quantity data and fault characteristics of the high-voltage switch equipment according to the multidimensional analysis and correlation analysis results and the comparison analysis results of transverse data and longitudinal data, training and optimizing the algorithm model to obtain a trained model, and forming a multi-source time-space analysis algorithm of the temperature and insulation defects of the switch cabinet;
and S5, finally, substituting the real-time fault characteristic quantity data into the algorithm model between the fault characteristic quantity data and the fault characteristics of the high-voltage switchgear to obtain the real-time fault characteristics of the high-voltage switchgear.
Preferably, the data of the fault-indicating amount in the step S1 includes temperature data, arc data, insulation data, humidity data, and partial discharge data.
Preferably, the specific operation steps of the multidimensional analysis and the correlation analysis in step S2 are as follows:
s21, firstly, establishing a fact table and a dimensional table according to the obtained data of various fault characterization quantities of the high-voltage switchgear and the fault characteristics of the high-voltage switchgear, and establishing a multi-dimensional analysis model;
s22, sequentially substituting the acquired various fault characteristic quantity data of the high-voltage switch equipment into a multi-dimensional analysis model for absolute threshold analysis and comparison, extracting various fault characteristics to which the fault characteristic quantity data possibly belong, and recording as a set A;
s23, sequentially substituting the acquired fault characteristics of the high-voltage switch equipment into a multidimensional analysis model for absolute threshold analysis and comparison, extracting various fault characteristic quantity data which may occur to the fault characteristics, and recording the data as a set B;
s24, simultaneously carrying out similarity association on various fault characteristics to which the fault characteristic quantity data belongs and all fault characteristics in the database, extracting the associated fault characteristics, and recording as a set C;
and S25, finally, carrying out similarity association on various fault characteristic quantity data which may occur in the fault characteristic and all fault characteristic quantity data in the database, and extracting the associated fault characteristic quantity data, wherein the data is recorded as a set D.
Preferably, the horizontal data in step S3 is cross-sectional data, i.e., a set of cases of different fault signatures on the same fault characteristic, and the vertical data in step S3 is longitude data, i.e., a set of cases of the same fault signature on different fault characteristics.
Preferably, the specific operation steps of the comparative analysis in step S3 are as follows:
s31, firstly, acquiring the condition of each fault characteristic quantity data on the same fault characteristic, and carrying out integration processing and storage on the condition, and recording the condition as a set E;
s32, acquiring the conditions of the same fault characterization on different fault characteristics, and performing integration processing and storage on the conditions, wherein the conditions are recorded as a set F;
s33, comparing and analyzing the condition of a plurality of fault characterization quantity data on the same fault characteristic with the condition of the fault characterization on different fault characteristics respectively;
s34, obtaining the result of the comparative analysis, recording the same fault characteristic quantity on the same fault characteristic and the same fault characteristic quantity on different fault characteristics, and recording as a set E n F.
Preferably, the specific operation steps of training and adjusting the algorithm model between the fault characteristic quantity and the fault characteristic of the high-voltage switchgear in step S4 are as follows:
s41, substituting the historical fault characteristic quantity data of the high-voltage switch equipment into the preliminarily obtained algorithm model between the fault characteristic quantity and the fault characteristic of the high-voltage switch equipment to train the high-voltage switch equipment;
s42, firstly, carrying out multidimensional analysis and correlation analysis on a plurality of historical fault characteristic quantity data through an algorithm model between the fault characteristic quantity and the fault characteristic of the high-voltage switch equipment to obtain the correlation among various historical fault characteristic quantity data of the high-voltage switch equipment and the relation between the correlation and the fault characteristic;
s43, collecting various historical fault characteristic quantity data of the high-voltage switch equipment and transverse data and longitudinal data of fault characteristics, carrying out comparative analysis on the collected data and the longitudinal data, and analyzing to obtain fault characteristics corresponding to the various historical fault characteristic quantity data of the high-voltage switch equipment;
and S44, comparing the fault characteristics obtained by training with standard fault characteristics corresponding to various historical fault characterization quantity data of the high-voltage switch equipment, wherein the same fault characteristics are correct, and the different fault characteristics are corrected and optimized.
Preferably, the multi-source spatio-temporal analysis algorithm formula in step S4 is: v ∈ [ A ≧ B ≧ C ≧ D ≧ F ] -.
Preferably, in the multi-source space-time analysis algorithm formula, V is a fault characteristic, and angmax is fault characteristic quantity data.
The invention has the beneficial effects that: according to the invention, through multidimensional analysis of the incidence relation among various fault characteristic quantities and the relation between the incidence relation and the fault characteristics, theoretical support is provided for realizing multidimensional comprehensive analysis of high-voltage switch equipment, meanwhile, the analysis of the fault characteristic quantities is not limited to the comparison of absolute thresholds, and the comparison of transverse data and longitudinal data is performed simultaneously, so that the fault judgment is more three-dimensional and accurate, finally, an algorithm model between the fault characteristic quantities and the fault characteristics of the high-voltage switch equipment is established, and a multi-source time-space analysis algorithm of the temperature and the insulation defects of the switch cabinet is formed, so that the accuracy of defect alarm is improved, the false alarm and the false alarm are reduced, and the operation and maintenance efficiency is improved and the safety risk is reduced.
Description of the drawings:
for ease of illustration, the invention is described in detail by the following detailed description and the accompanying drawings.
FIG. 1 is a flow chart of a multi-source spatio-temporal analysis algorithm for high-voltage switchgear faults of the present invention.
The specific implementation mode is as follows:
as shown in fig. 1, the following technical solutions are adopted in the present embodiment:
example (b):
the multi-source space-time analysis algorithm for the faults of the high-voltage switch equipment comprises the following steps:
s1, firstly, acquiring various fault characterization quantity data of the high-voltage switch equipment, and storing the data into a database;
s2, acquiring fault characteristics of the high-voltage switch equipment, storing the fault characteristics into a database, and simultaneously respectively carrying out multi-dimensional analysis and correlation analysis on the fault characteristics and the acquired data of various fault characteristic quantities to obtain correlation among the characteristic quantities and the relation between the correlation and the fault characteristics;
s3, respectively acquiring fault characteristic quantity data and transverse data and longitudinal data of fault characteristics, and respectively carrying out comparative analysis on the fault characteristic quantity data and the transverse data and the longitudinal data of the fault characteristics;
s4, establishing an algorithm model between fault characteristic quantity data and fault characteristics of the high-voltage switch equipment according to the multidimensional analysis and correlation analysis results and the comparison analysis results of transverse data and longitudinal data, training and optimizing the algorithm model to obtain a trained model, and forming a multi-source time-space analysis algorithm of the temperature and insulation defects of the switch cabinet;
and S5, finally, substituting the real-time fault characteristic quantity data into the algorithm model between the fault characteristic quantity data and the fault characteristics of the high-voltage switchgear to obtain the real-time fault characteristics of the high-voltage switchgear.
Wherein the fault characteristic data in the step S1 includes temperature data, arc data, insulation data, humidity data, and partial discharge data.
The specific operation steps of the multidimensional analysis and the correlation analysis in the step S2 are as follows:
s21, firstly, establishing a fact table and a dimensional table according to the obtained data of various fault characterization quantities of the high-voltage switchgear and the fault characteristics of the high-voltage switchgear, and establishing a multi-dimensional analysis model;
s22, sequentially substituting the acquired various fault characteristic quantity data of the high-voltage switch equipment into a multi-dimensional analysis model for absolute threshold analysis and comparison, extracting various fault characteristics to which the fault characteristic quantity data possibly belong, and recording as a set A;
s23, sequentially substituting the acquired fault characteristics of the high-voltage switch equipment into a multidimensional analysis model for absolute threshold analysis and comparison, extracting various fault characteristic quantity data which may occur to the fault characteristics, and recording the data as a set B;
s24, simultaneously carrying out similarity association on various fault characteristics to which the fault characteristic quantity data belongs and all fault characteristics in the database, extracting the associated fault characteristics, and recording as a set C;
and S25, finally, carrying out similarity association on various fault characteristic quantity data which may occur in the fault characteristic and all fault characteristic quantity data in the database, and extracting the associated fault characteristic quantity data, wherein the data is recorded as a set D.
The horizontal data in step S3 is cross-sectional data, i.e., a set of cases of different fault signatures on the same fault characteristic, and the vertical data in step S3 is longitude data, i.e., a set of cases of the same fault signature on different fault characteristics.
The specific operation steps of the comparative analysis in the step S3 are as follows:
s31, firstly, acquiring the condition of each fault characteristic quantity data on the same fault characteristic, and carrying out integration processing and storage on the condition, and recording the condition as a set E;
s32, acquiring the conditions of the same fault characterization on different fault characteristics, and performing integration processing and storage on the conditions, wherein the conditions are recorded as a set F;
s33, comparing and analyzing the condition of a plurality of fault characterization quantity data on the same fault characteristic with the condition of the fault characterization on different fault characteristics respectively;
s34, obtaining the result of the comparative analysis, recording the same fault characteristic quantity on the same fault characteristic and the same fault characteristic quantity on different fault characteristics, and recording as a set E n F.
In step S4, the specific operation steps of training and tuning the algorithm model between the fault characterization quantity and the fault characteristic of the high-voltage switchgear are as follows:
s41, substituting the historical fault characteristic quantity data of the high-voltage switch equipment into the preliminarily obtained algorithm model between the fault characteristic quantity and the fault characteristic of the high-voltage switch equipment to train the high-voltage switch equipment;
s42, firstly, carrying out multidimensional analysis and correlation analysis on a plurality of historical fault characteristic quantity data through an algorithm model between the fault characteristic quantity and the fault characteristic of the high-voltage switch equipment to obtain the correlation among various historical fault characteristic quantity data of the high-voltage switch equipment and the relation between the correlation and the fault characteristic;
s43, collecting various historical fault characteristic quantity data of the high-voltage switch equipment and transverse data and longitudinal data of fault characteristics, carrying out comparative analysis on the collected data and the longitudinal data, and analyzing to obtain fault characteristics corresponding to the various historical fault characteristic quantity data of the high-voltage switch equipment;
and S44, comparing the fault characteristics obtained by training with standard fault characteristics corresponding to various historical fault characterization quantity data of the high-voltage switch equipment, wherein the same fault characteristics are correct, and the different fault characteristics are corrected and optimized.
Wherein, the multi-source spatio-temporal analysis algorithm formula in the step S4 is: v ∈ [ A ≧ B ≧ C ≧ D ≧ F ] -.
In the multi-source space-time analysis algorithm formula, V is a fault characteristic, and angmax is fault characteristic quantity data.
Specifically, the method comprises the following steps: in practical application, firstly, an algorithm model between fault characteristic quantity data and fault characteristics of the high-voltage switchgear needs to be established, and the specific operation steps are as follows: acquiring various fault characterization quantity data of the high-voltage switch equipment, and storing the data into a database; then, acquiring fault characteristics of the high-voltage switch equipment, storing the fault characteristics into a database, and simultaneously respectively carrying out multidimensional analysis and correlation analysis on the fault characteristics and the acquired data of various fault characterization quantities to obtain correlation relations among the various characterization quantities and relations between the correlation relations and the fault characteristics; then respectively acquiring fault characteristic quantity data and transverse data and longitudinal data of fault characteristics, and respectively carrying out comparative analysis on the fault characteristic quantity data and the transverse data and the longitudinal data of the fault characteristics; establishing an algorithm model between fault characteristic quantity data and fault characteristics of the high-voltage switch equipment according to multidimensional analysis and correlation analysis results, transverse data and longitudinal data comparison analysis results, training and optimizing the algorithm model to obtain a trained model, and simultaneously forming a multi-source time-space analysis algorithm of the temperature and insulation defects of the switch cabinet, wherein the specific operation steps of training and optimizing the algorithm model between the fault characteristic quantity and the fault characteristics of the high-voltage switch equipment are as follows: substituting the historical fault characteristic quantity data of the high-voltage switch equipment into an algorithm model between the preliminarily obtained fault characteristic quantity and the fault characteristic of the high-voltage switch equipment to train the high-voltage switch equipment; firstly, carrying out multidimensional analysis and correlation analysis on a plurality of historical fault characteristic quantity data through an algorithm model between the fault characteristic quantity and the fault characteristic of the high-voltage switch equipment to obtain the correlation among various historical fault characteristic quantity data of the high-voltage switch equipment and the relation between the correlation and the fault characteristic; then, collecting various historical fault characteristic quantity data of the high-voltage switch equipment and transverse data and longitudinal data of fault characteristics, carrying out comparative analysis on the data, and analyzing to obtain fault characteristics corresponding to the various historical fault characteristic quantity data of the high-voltage switch equipment; and comparing the fault characteristics obtained by training with standard fault characteristics corresponding to various historical fault characterization quantity data of the high-voltage switch equipment, wherein the same fault characteristics are correct, and the different fault characteristics are more correct and optimal.
When the method is used, firstly, real-time fault characteristic quantity data of the high-voltage switch equipment are obtained and then substituted into the established algorithm model between the fault characteristic quantity data and the fault characteristics of the high-voltage switch equipment for calculation and analysis;
firstly, carrying out multidimensional analysis and association analysis, wherein the specific operation steps are as follows: firstly, establishing a fact table and a dimensional table and establishing a multidimensional analysis model according to the acquired real-time fault characterization quantity data of the high-voltage switchgear and the fault characteristics of the high-voltage switchgear; then substituting the acquired real-time fault characteristic quantity data of the high-voltage switch equipment into a multidimensional analysis model for absolute threshold analysis and comparison, and extracting various fault characteristics which the fault characteristic quantity data may belong to, and recording as a set A; then, sequentially substituting the acquired fault characteristics of the high-voltage switch equipment into a multidimensional analysis model for absolute threshold analysis and comparison, extracting various fault characteristic quantity data which may occur to the fault characteristics, and recording the data as a set B; simultaneously carrying out similarity correlation on various fault characteristics belonging to the real-time fault characterization quantity data and all fault characteristics in the database, extracting the correlated fault characteristics, and recording as a set C; similarity association is carried out on various fault characteristic quantity data which are possibly generated by fault characteristics and all fault characteristic quantity data in a database, and the associated fault characteristic quantity data are extracted and recorded as a set D;
then, comparing and analyzing transverse data and longitudinal data, and specifically comprising the following operation steps: firstly, acquiring the condition of each fault characterization quantity data on the same fault characteristic, and carrying out integration processing and storage on the condition, and recording the condition as a set E; then, acquiring the conditions of real-time fault characterization on different fault characteristics, and performing integrated processing and storage on the conditions, and recording the conditions as a set F; then comparing and analyzing the conditions of a plurality of fault characterization quantity data on the same fault characteristic with the conditions of the real-time fault characterization on different fault characteristics; obtaining a comparison analysis result, recording the same condition of the fault characteristic quantity on the same fault characteristic and the same condition of the real-time fault characteristic quantity on different fault characteristics, and recording as a set E n F;
the multi-source time-space analysis is carried out through an algorithm model between the fault characterization quantity and the fault characteristics of the high-voltage switch equipment after training and tuning, V is angmax (angmax) is larger than the size of A (N) B (N) C (N) D (E (N) F), V is the fault characteristic, angmax is fault characterization quantity data, and the fault characteristic of the high-voltage switch equipment corresponding to the real-time fault characterization quantity data can be obtained through calculation.
In the description of the present invention, it is to be understood that the terms "coaxial", "bottom", "one end", "top", "middle", "other end", "upper", "one side", "top", "inner", "front", "center", "both ends", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
Furthermore, the terms "first", "second", "third", "fourth" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated, whereby the features defined as "first", "second", "third", "fourth" may explicitly or implicitly include at least one such feature.
In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "disposed," "connected," "secured," "screwed" and the like are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; the terms may be directly connected or indirectly connected through an intermediate, and may be communication between two elements or interaction relationship between two elements, unless otherwise specifically limited, and the specific meaning of the terms in the present invention will be understood by those skilled in the art according to specific situations.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The multi-source space-time analysis algorithm for the faults of the high-voltage switchgear is characterized by comprising the following steps:
s1, firstly, acquiring various fault characterization quantity data of the high-voltage switch equipment, and storing the data into a database;
s2, acquiring fault characteristics of the high-voltage switch equipment, storing the fault characteristics into a database, and simultaneously respectively carrying out multi-dimensional analysis and correlation analysis on the fault characteristics and the acquired data of various fault characteristic quantities to obtain correlation among the characteristic quantities and the relation between the correlation and the fault characteristics;
s3, respectively acquiring fault characteristic quantity data and transverse data and longitudinal data of fault characteristics, and respectively carrying out comparative analysis on the fault characteristic quantity data and the transverse data and the longitudinal data of the fault characteristics;
s4, establishing an algorithm model between fault characteristic quantity data and fault characteristics of the high-voltage switch equipment according to the multidimensional analysis and correlation analysis results and the comparison analysis results of transverse data and longitudinal data, training and optimizing the algorithm model to obtain a trained model, and forming a multi-source time-space analysis algorithm of the temperature and insulation defects of the switch cabinet;
and S5, finally, substituting the real-time fault characteristic quantity data into the algorithm model between the fault characteristic quantity data and the fault characteristics of the high-voltage switchgear to obtain the real-time fault characteristics of the high-voltage switchgear.
2. The multi-source spatio-temporal analysis algorithm for the faults of the high-voltage switchgear according to claim 1, wherein the fault characterization data in the step S1 comprise temperature data, arc data, insulation data, humidity data and partial discharge data.
3. The multi-source spatio-temporal analysis algorithm for the faults of the high-voltage switchgear according to claim 1, wherein the specific operation steps of the multi-dimensional analysis and the correlation analysis in the step S2 are as follows:
s21, firstly, establishing a fact table and a dimensional table according to the obtained data of various fault characterization quantities of the high-voltage switchgear and the fault characteristics of the high-voltage switchgear, and establishing a multi-dimensional analysis model;
s22, sequentially substituting the acquired various fault characteristic quantity data of the high-voltage switch equipment into a multi-dimensional analysis model for absolute threshold analysis and comparison, extracting various fault characteristics to which the fault characteristic quantity data possibly belong, and recording as a set A;
s23, sequentially substituting the acquired fault characteristics of the high-voltage switch equipment into a multidimensional analysis model for absolute threshold analysis and comparison, extracting various fault characteristic quantity data which may occur to the fault characteristics, and recording the data as a set B;
s24, simultaneously carrying out similarity association on various fault characteristics to which the fault characteristic quantity data belongs and all fault characteristics in the database, extracting the associated fault characteristics, and recording as a set C;
and S25, finally, carrying out similarity association on various fault characteristic quantity data which may occur in the fault characteristic and all fault characteristic quantity data in the database, and extracting the associated fault characteristic quantity data, wherein the data is recorded as a set D.
4. The multi-source spatio-temporal analysis algorithm for high-voltage switchgear faults according to claim 1, characterized in that the transverse data in step S3 are cross-sectional data, i.e. a set of cases of different fault signatures on the same fault characteristic, and the longitudinal data in step S3 are longitudinal data, i.e. a set of cases of the same fault signature on different fault characteristics.
5. The multi-source spatio-temporal analysis algorithm for the faults of the high-voltage switchgear according to claim 1, wherein the specific operation steps of the contrastive analysis in the step S3 are as follows:
s31, firstly, acquiring the condition of each fault characteristic quantity data on the same fault characteristic, and carrying out integration processing and storage on the condition, and recording the condition as a set E;
s32, acquiring the conditions of the same fault characterization on different fault characteristics, and performing integration processing and storage on the conditions, wherein the conditions are recorded as a set F;
s33, comparing and analyzing the condition of a plurality of fault characterization quantity data on the same fault characteristic with the condition of the fault characterization on different fault characteristics respectively;
s34, obtaining the result of the comparative analysis, recording the same fault characteristic quantity on the same fault characteristic and the same fault characteristic quantity on different fault characteristics, and recording as a set E n F.
6. The multi-source space-time analysis algorithm for the faults of the high-voltage switchgear according to claim 1, wherein the specific operation steps of training and adjusting the algorithm model between the fault characterization quantity and the fault characteristics of the high-voltage switchgear in the step S4 are as follows:
s41, substituting the historical fault characteristic quantity data of the high-voltage switch equipment into the preliminarily obtained algorithm model between the fault characteristic quantity and the fault characteristic of the high-voltage switch equipment to train the high-voltage switch equipment;
s42, firstly, carrying out multidimensional analysis and correlation analysis on a plurality of historical fault characteristic quantity data through an algorithm model between the fault characteristic quantity and the fault characteristic of the high-voltage switch equipment to obtain the correlation among various historical fault characteristic quantity data of the high-voltage switch equipment and the relation between the correlation and the fault characteristic;
s43, collecting various historical fault characteristic quantity data of the high-voltage switch equipment and transverse data and longitudinal data of fault characteristics, carrying out comparative analysis on the collected data and the longitudinal data, and analyzing to obtain fault characteristics corresponding to the various historical fault characteristic quantity data of the high-voltage switch equipment;
and S44, comparing the fault characteristics obtained by training with standard fault characteristics corresponding to various historical fault characterization quantity data of the high-voltage switch equipment, wherein the same fault characteristics are correct, and the different fault characteristics are corrected and optimized.
7. The multi-source spatio-temporal analysis algorithm for the faults of the high-voltage switchgear according to claim 1, wherein the formula of the multi-source spatio-temporal analysis algorithm in the step S4 is as follows: v ∈ [ A ≧ B ≧ C ≧ D ≧ F ] -.
8. The multi-source spatio-temporal analysis algorithm for the faults of the high-voltage switchgear is characterized in that V is a fault characteristic and angmax is fault characteristic quantity data in the formula of the multi-source spatio-temporal analysis algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111033819.4A CN113722328B (en) | 2021-09-03 | 2021-09-03 | Multisource space-time analysis algorithm for faults of high-voltage switch equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111033819.4A CN113722328B (en) | 2021-09-03 | 2021-09-03 | Multisource space-time analysis algorithm for faults of high-voltage switch equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113722328A true CN113722328A (en) | 2021-11-30 |
| CN113722328B CN113722328B (en) | 2023-12-12 |
Family
ID=78681657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111033819.4A Active CN113722328B (en) | 2021-09-03 | 2021-09-03 | Multisource space-time analysis algorithm for faults of high-voltage switch equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113722328B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116186017A (en) * | 2023-04-25 | 2023-05-30 | 蓝色火焰科技成都有限公司 | Big data collaborative supervision method and platform |
| CN116893336A (en) * | 2023-07-11 | 2023-10-17 | 浙江和能电力设备有限公司 | High-low voltage switching device and method thereof |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070093842A (en) * | 2006-03-15 | 2007-09-19 | 오므론 가부시키가이샤 | Process abnormality analyzing apparatus and process abnormality analyzing method and storage medium |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN106774054A (en) * | 2016-11-25 | 2017-05-31 | 国网技术学院 | GIS device analysis system and method based on the identification of complicated unstructured data |
| CN107124291A (en) * | 2017-03-06 | 2017-09-01 | 国网上海市电力公司 | A kind of adjusting device monitoring analysis system and method based on big data |
| CN108460144A (en) * | 2018-03-14 | 2018-08-28 | 西安华光信息技术有限责任公司 | A kind of coal equipment fault early-warning system and method based on machine learning |
| CN108761320A (en) * | 2018-05-08 | 2018-11-06 | 国网天津市电力公司 | Switch cabinet comprehensive monitors analysis platform on-line |
| CN109936113A (en) * | 2019-03-29 | 2019-06-25 | 国网浙江省电力有限公司 | A kind of protection act intelligent diagnosing method and system based on random forests algorithm |
| CN110018389A (en) * | 2019-02-21 | 2019-07-16 | 国网山东省电力公司临沂供电公司 | A kind of transmission line of electricity on-line fault monitoring method and system |
| CN112257988A (en) * | 2020-09-29 | 2021-01-22 | 中广核工程有限公司 | Complex accident feature identification and risk early warning system and method for nuclear power plant |
| CN112462736A (en) * | 2020-11-13 | 2021-03-09 | 华北电力大学 | Wind turbine generator fault diagnosis method based on data analysis |
-
2021
- 2021-09-03 CN CN202111033819.4A patent/CN113722328B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070093842A (en) * | 2006-03-15 | 2007-09-19 | 오므론 가부시키가이샤 | Process abnormality analyzing apparatus and process abnormality analyzing method and storage medium |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN106774054A (en) * | 2016-11-25 | 2017-05-31 | 国网技术学院 | GIS device analysis system and method based on the identification of complicated unstructured data |
| CN107124291A (en) * | 2017-03-06 | 2017-09-01 | 国网上海市电力公司 | A kind of adjusting device monitoring analysis system and method based on big data |
| CN108460144A (en) * | 2018-03-14 | 2018-08-28 | 西安华光信息技术有限责任公司 | A kind of coal equipment fault early-warning system and method based on machine learning |
| CN108761320A (en) * | 2018-05-08 | 2018-11-06 | 国网天津市电力公司 | Switch cabinet comprehensive monitors analysis platform on-line |
| CN110018389A (en) * | 2019-02-21 | 2019-07-16 | 国网山东省电力公司临沂供电公司 | A kind of transmission line of electricity on-line fault monitoring method and system |
| CN109936113A (en) * | 2019-03-29 | 2019-06-25 | 国网浙江省电力有限公司 | A kind of protection act intelligent diagnosing method and system based on random forests algorithm |
| CN112257988A (en) * | 2020-09-29 | 2021-01-22 | 中广核工程有限公司 | Complex accident feature identification and risk early warning system and method for nuclear power plant |
| CN112462736A (en) * | 2020-11-13 | 2021-03-09 | 华北电力大学 | Wind turbine generator fault diagnosis method based on data analysis |
Non-Patent Citations (4)
| Title |
|---|
| TIMEA ILLES-SEIFERT 等: "Exploring the relationship of history characteristics and defect count: an empirical study", 《DEFECTS \'08: PROCEEDINGS OF THE 2008 WORKSHOP ON DEFECTS IN LARGE SOFTWARE SYSTEMS》, pages 11 - 15 * |
| 何俊达: "高压电容器组自动测温系统设计与应用", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, pages 042 - 169 * |
| 杨洋: "基于水电大数据算法平台的故障模型验证", 《电力大数据》, pages 74 - 81 * |
| 茹秋实: "干式空心电抗器故障监测与预警技术研究现状与展望", 《电力设备管理》, pages 218 - 219 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116186017A (en) * | 2023-04-25 | 2023-05-30 | 蓝色火焰科技成都有限公司 | Big data collaborative supervision method and platform |
| CN116893336A (en) * | 2023-07-11 | 2023-10-17 | 浙江和能电力设备有限公司 | High-low voltage switching device and method thereof |
| CN116893336B (en) * | 2023-07-11 | 2024-04-02 | 宁夏隆基电气有限公司 | High-low voltage switching device and method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113722328B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113722328A (en) | Multi-source time-space analysis algorithm for high-voltage switchgear faults | |
| CN110726494B (en) | High-voltage switch cabinet temperature monitoring system and monitoring method | |
| US10422715B2 (en) | GIS leak monitoring method based on vibration signal | |
| CN105718748A (en) | Online monitoring data processing method | |
| CN112381668B (en) | Information extraction method for power grid faults | |
| CN108919044A (en) | A kind of unit style distribution network failure active identification method based on mutual verification scheme | |
| WO2023092760A1 (en) | Diagnosis method and diagnosis apparatus based on thermal vision | |
| CN212159921U (en) | Transient overvoltage and overcurrent monitoring device | |
| CN112611987A (en) | Transformer voiceprint vibration monitoring system and method based on Internet of things technology | |
| CN111555163A (en) | 10kV switchgear intelligent operation and detection system and method based on edge calculation | |
| CN113604815B (en) | Voltage monitoring system and voltage acquisition method for small chamber of electrolytic cell of water electrolysis hydrogen production equipment | |
| CN113917282B (en) | Distribution network fault quick positioning system based on short-circuit current | |
| CN115078924A (en) | System and method for judging transformer defects by combining dissolved gas in oil and iron core grounding current | |
| CN114924220A (en) | Abnormity evaluation method, device and system for electronic transformer digitization device | |
| Moldoveanu et al. | Intelligent system for the on-line real time monitoring of high voltage substations | |
| CN115902531A (en) | New energy automobile high-voltage load insulation fault positioning method and monitoring platform | |
| CN113609183A (en) | Method and system for studying and judging data acquisition fault in power distribution management | |
| CN110927534A (en) | Dry-type air-core reactor interturn insulation degradation on-line monitoring device | |
| CN110323593B (en) | Universal power taking device and method installed without power outage | |
| CN216746241U (en) | Intelligent switching station integrated monitoring device | |
| CN117791244A (en) | Intelligent connector of low-voltage drawer cabinet | |
| CN216746493U (en) | Box temperature monitoring system and box-type transformer comprising same | |
| CN114062838B (en) | DC wiring fault positioning method and device and medium-voltage DC power distribution equipment | |
| CN105182054A (en) | Over-voltage monitoring method of three-phase circuit | |
| CN112036742B (en) | Method for evaluating running health state of power distribution room equipment |
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 |