CN109828184B - Voltage sag source identification method based on mutual approximate entropy - Google Patents
Voltage sag source identification method based on mutual approximate entropy Download PDFInfo
- Publication number
- CN109828184B CN109828184B CN201910047165.7A CN201910047165A CN109828184B CN 109828184 B CN109828184 B CN 109828184B CN 201910047165 A CN201910047165 A CN 201910047165A CN 109828184 B CN109828184 B CN 109828184B
- Authority
- CN
- China
- Prior art keywords
- waveform
- sag
- voltage sag
- sample
- mutual approximation
- 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
Landscapes
- Measurement Of Current Or Voltage (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a voltage sag source identification method based on mutual approximate entropy, which comprises the following steps: (1) establishing a sample waveform library; (2) preprocessing data; (3) calculating mutual approximate entropy values of the waveform to be matched and the sample waveform, and keeping the minimum entropy value and the information of the corresponding sample; (4) and (3) identifying the type of the sag source: judging whether the minimum entropy value is within a threshold range or not, and if not, judging that the undetermined result is reliable, namely the undetermined result is the sag type of the waveform to be matched; if the waveform exceeds the range, the waveform to be matched is judged not to belong to any sag type in the waveform library. The method has higher accuracy in identifying the voltage sag source according to the actually measured waveform, the required sampling window is short, the algorithm is simple and easy to realize, engineering personnel are helped to correctly judge the type and the generation reason of the voltage sag source to a certain extent, targeted theoretical guidance is provided for governing the voltage sag problem, and the method has great application value and prospect.
Description
Technical Field
The invention relates to a method for identifying an electric energy quality disturbance source, in particular to a method for identifying a voltage sag source based on mutual approximate entropy.
Background
With the increasing levels of industrial equipment, building electrical automation and intelligence, the problem of voltage sag is more and more significant for the production and operation of large industrial and commercial users, and particularly, in industries applying a large amount of power electronic equipment such as semiconductor manufacturing, precision instrument processing, automobile manufacturing and the like, the voltage sag is very sensitive, and the power electronic equipment can trip and stop operation when the effective voltage value is lower than 90% and the duration reaches more than 1-2 cycles. Voltage sag is a common power quality problem, voltage sag phenomena are caused by motor starting, transformer switching, short-circuit faults and the like, production interruption and delay caused by voltage sag interference are in an obvious rising trend, direct and indirect economic losses caused by the voltage sag phenomena are serious day by day, and higher requirements are provided for power supply quality. The voltage waveform characteristics caused by different sag sources are different, the sag sources can be accurately identified, the local voltage sag conditions can be analyzed, compensated and restrained in a targeted manner, and meanwhile, the method can be used as a basis for coordination disputes between a power supply department and users and is an essential step in the management of the voltage sag problem.
The voltage sag source identification method is taken as a current research hotspot, and attracts a plurality of scholars at home and abroad to participate in related research. The existing voltage sag source identification method mainly comprises the main steps of information acquisition, feature extraction, sample training and classification identification, researches are mainly carried out on waveform features of voltage sag, a large number of samples are trained to carry out voltage sag source identification by extracting reasonable feature quantities, and numerous achievements are obtained. The basic idea of the algorithm is to convert the sag time domain characteristic into the frequency domain characteristic by using methods such as double wavelet transformation, Prony method, S transformation and the like, extract the characteristic quantity according to artificially set characteristic items, and then identify the sag source by using classification models such as a neural network algorithm, a support vector machine algorithm and the like. The existing voltage sag source identification methods have the following problems: the problem of phase change of three-phase voltage is not considered only by processing and classifying the effective values of the sag voltage waveforms. A large amount of sample training is required to ensure the accuracy of the voltage sag source identification. In addition, the method is required to be established on the basis of accurate and proper feature quantity extraction, improper feature quantity selection can directly influence voltage sag source classification, even completely different results are generated, and the difficulty of feature quantity extraction is further increased due to the fact that the actual waveform of the voltage sag is easily influenced by external factors.
Aiming at the problems, a voltage sag source identification method which solves the problem that the existing method seriously depends on the accuracy of characteristic quantity extraction, has small calculation amount, high identification efficiency and higher identification accuracy is urgent.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the defects of research on the aspect of voltage sag source identification at the present stage, the invention aims to provide a voltage sag source identification method based on mutual approximate entropy so as to effectively avoid the problems of difficult convergence, excessively complex algorithm and the like in the traditional method.
The technical scheme is as follows: a voltage sag source identification method based on mutual approximate entropy comprises the following steps:
(1) establishing a sample waveform library;
(2) preprocessing data;
(3) calculating mutual approximate entropy values of the waveform to be matched and the sample waveform, and keeping the minimum entropy value and the information of the corresponding sample;
(4) and (4) temporarily reducing source type identification.
Specifically, the step (1) includes:
(11) analyzing the change conditions of the amplitude and the phase angle of the voltage sag waveform caused by various short-circuit faults and the change conditions of the amplitude and the phase angle of various sag after transmission and transformation by the transformer;
(12) summarizing all the waveform types of sag caused by short-circuit faults according to the voltage sag type vector diagrams and the collected actually-measured sag waveform data;
(13) a library of standard sample waveforms covering these representative waveforms is established.
The step (2) comprises the following steps:
(21) filtering and denoising the obtained temporary drop waveform data;
(22) extracting a voltage sag depression domain;
(23) the data obtained were normalized.
Preferably, in the step (22), the voltage sag depression domain is extracted by using wavelet transform.
Further, the step (3) specifically includes the following steps:
(31) for the measured waveform time series i (t) and the sample waveform time series j (t) defineA window with the length of m, and constructing N-m +1 m-dimensional vectors X for i (t) and j (t) respectivelyp、Xq:
Xp=[i(p),···,i(p+m-1)]
p=1,2,···,N-m+1
Xq=[j(q),···,j(q+m-1)]
q=1,2,···,N-m+1
Wherein, p and q are respectively the serial numbers of the actually measured waveform sequence and the sample waveform sequence;
(32) describing X using ∞ -norm of vectorpAnd XqDistance d (X) therebetweenp,Xq)=||Xp-Xq||∞;
(33) Given a similar tolerance r, X is counted for each p valuepAnd all Xq(q ═ 1,2, ·, N-m +1) the number N of vector distances less than rp,m,rAnd calculating Np,m,rRatio C to the total number of vectors (N-m +1)p,m,r:
(34) First to Cp,m,rTaking the logarithm and averaging it over all p to obtain the degree of cross-correlation between the two curves:
(35) increasing the window length to m +1, and repeating the operation processes of the steps (31) to (34) to obtain phim+1,r;
(36) And (3) calculating to obtain a mutual approximation entropy value related to m and r:
CAE(m,r)=Φm,r-Φm+1,r。
furthermore, in the step (4), the actually measured voltage sag waveform and the waveform with the minimum mutual approximation entropy in the sample library are classified as the same voltage sag; judging a threshold value, and if the threshold value does not exceed the range, judging that the undetermined result is reliable, namely the sag type of the waveform to be matched; if the waveform exceeds the range, the waveform to be matched is judged not to belong to any sag type in the waveform library.
Has the advantages that: compared with the prior art, the invention has the following remarkable progress: 1. the required sampling window is short, the steps of extracting characteristic quantity and a large number of training steps are reduced, the calculated amount is small, the recognition efficiency is high, and the algorithm is simple and easy to realize; 2. the problems of difficult convergence, excessively complex algorithm and the like in the traditional method are effectively avoided, and the problem that the existing method seriously depends on the accuracy of characteristic quantity extraction can be reduced and avoided; 3. the method has higher accuracy in the aspect of identifying the voltage sag source according to the actually measured waveform; 4. the method can help engineers correctly judge the type and the generation reason of the voltage sag source, provides a targeted theoretical guidance for managing the voltage sag problem, and has great application value and prospect.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a diagram illustrating the principle of mutual approximation entropy;
FIG. 3 is a graph of the mutual approximation entropy for different r values.
Fig. 4 is a vector diagram of voltage transients for various short circuit fault conditions.
Detailed Description
The technical scheme of the invention is further explained by combining the drawings and the specific embodiments.
As shown in fig. 1, a voltage sag source identification method based on mutual approximate entropy includes the following steps:
step one, establishing a sample waveform library. The change conditions of the amplitude and the phase angle of the voltage sag waveform caused by various short-circuit faults and the change conditions of the amplitude and the phase angle of various sag after transmission and transformation by the transformer are analyzed. By combining the voltage sag type vector diagrams of fig. 4 and the collected various actually measured sag waveform data, all the waveform types of sag caused by short-circuit faults are summarized, and a standard sample waveform library covering the typical waveforms is established.
And step two, preprocessing the data. And filtering and denoising the obtained sag waveform data, extracting a voltage sag depression domain by using wavelet transformation, and standardizing the obtained data to prepare for the next calculation.
And step three, calculating the mutual approximation entropy of the waveform to be matched and the sample waveform. And calculating the mutual approximate entropy of the waveform to be matched and each waveform in the sample library, and keeping the minimum entropy value and the information of the corresponding sample. The method comprises the following steps:
31. for the actually measured waveform time sequence i (t) and the sample waveform time sequence j (t), a window with the length of m is specified, and N-m +1 m-dimensional vectors X are respectively constructed for the i (t) and the j (t)p、XqWherein
Xp=[i(p),···,i(p+m-1)]
p=1,2,···,N-m+ 1
Xq=[j(q),···,j(q+m-1)]
q=1,2,···,N-m+ 1
Wherein p and q are respectively the serial numbers of the actually measured waveform sequence and the sample waveform sequence;
32. describing X using ∞ -norm of vectorpAnd XqDistance d (X) therebetweenp,Xq)=||Xp-Xq||∞;
33. Given a similar tolerance r, X is counted for each p valuepAnd all Xq(q ═ 1,2, ·, N-m +1) the number N of vector distances less than rp,m,rAnd calculating Np,m,rRatio C to the total number of vectors (N-m +1)p,m,r:
A principle explanation is given in connection with fig. 2. Let m be 2, vector Xp=[i(p),i(p+1)]I.e. the line segment connecting two adjacent points of data in the graph (a). When p is 8, with Xp(8) For example, a similarity margin r is specified, and X is specifiedp(8) R is the region I, Xp(9) R is region II if XqFall within regions I and II, respectively, indicating that they are within a similar tolerance r to Xp(8) Similarly, the line segment is changed to the entry mode (e.g., X in the diagram (b))q(8)、Xq(15)、Xq(19)、Xq(24))。
34. First to Cp,m,rTaking the logarithm and averaging it over all p to obtain the degree of cross-correlation between the two curves:
35. increasing the window length to m +1, and repeating the operation process from the step 31 to the step 34 to obtain phim+1,r;
36. And (3) calculating to obtain a mutual approximation entropy value related to m and r:
CAE(m,r)=Φm,r-Φm+1,r
and step four, identifying the type of the sag source. The smaller the mutual approximation entropy value is, the greater the similarity degree of the two waveforms is, and the temporarily measured voltage sag waveform and the waveform with the minimum mutual approximation entropy in the sample library belong to the same voltage sag. Judging a threshold value, and if the threshold value does not exceed the range, judging that the undetermined result is reliable, namely the sag type of the waveform to be matched; if the waveform exceeds the range, the waveform to be matched is judged not to belong to any sag type in the waveform library, and finally voltage sag waveform matching is achieved. And step three, obtaining a mutual approximation entropy value between the waveform to be matched and each sample, wherein the entropy value is smaller if the matching degree is high, and the entropy value is larger if the matching degree is low, so that the waveform type can be identified according to the minimum CAE value of the waveform to be matched and the samples of the same type. However, if the waveform to be matched is an abnormal waveform and does not belong to any waveform in the sample library, the obtained CAE value is larger, and the minimum value is selected for type judgment, so that the type judgment is not reasonable, and a threshold judgment is added as the basis for final judgment. According to the mutual approximation entropy diagram corresponding to different r values in the embodiment simulation shown in fig. 3, the CAE values of the waveform a and the waveform of the same type are less than 0.3, the CAE values of the waveform B to the waveform G and the waveform of the same type are sequentially obtained according to the method, finally, the union of all the results is obtained, and the CAE value is less than or equal to 0.4, so that the threshold selection standard of the method is that the CAE value is less than or equal to 0.4.
Examples
Model parameters:
according to the voltage sag three-phase vector diagram under various short-circuit fault conditions in the figure 4, MATLAB and a formula are used for establishing sample waveform data of 7 sag types. In the method, the initial length m of the window is 2, and the similarity tolerance r is 0.3.
Taking 350 groups of actual voltage sag waveform data, calculating mutual approximation entropy between the actual waveform and 7 types of sample waveforms in the sample library, wherein the average mutual approximation entropy actual sag waveform is shown in table 1. The mutual approximate entropy of the actual waveform and the sample waveform of the sag type of the actual waveform is minimum, and the average value is about 0.3; the mutual approximation entropy of the actual waveform and the sample waveforms of other sag types is large, and the average value is between 0.6 and 1. The method is easy to classify when matching the waveform and has good discrimination.
Table 1: calculation result of mutual approximate entropy average value of actually measured sag waveform and various sample waveforms in waveform library
Inputting the measured waveform into the model established by the method, and performing sag type matching according to the entropy calculation result, wherein the matching result and the accuracy are shown in table 2. The matching accuracy of each sag type and the 7-type sag matching accuracy are all over 94%, wherein the matching accuracy of the A-type sag, the B-type sag and the E-type sag can reach 100%. The method has good accuracy and effectiveness.
Table 2: accuracy of identification result of sag source of actually measured voltage sag waveform
Type of voltage sag | Total number to be matched | Match correct number | Accuracy rate |
A | 50 | 50 | 100% |
B | 50 | 50 | 100% |
C | 50 | 49 | 98% |
D | 50 | 47 | 94% |
E | 50 | 50 | 100% |
F | 50 | 48 | 96% |
G | 50 | 49 | 98% |
In order to verify the superiority of the mutual approximation entropy method in matching the voltage sag waveform, the method is compared with an SVM method and a BP neural network method, and the accuracy rate of matching the voltage sag waveform is shown in table 3. The voltage sag waveform matching method based on the mutual approximation entropy principle has the judgment accuracy as high as 98%, and is more superior to 55.43% and 80.29% of a BP neural network method and an SVM method.
Table 3: accuracy rate comparison of different sag source identification methods
Type of voltage sag | BP neural network | SVM | Mutual approximate entropy |
A | 66% | 78% | 100% |
B | 82% | 80% | 100% |
C | 46% | 76% | 98% |
D | 78% | 78% | 94% |
E | 74% | 88% | 100% |
F | 66% | 82% | 96% |
G | 42% | 80% | 98% |
In summary, the method provided by the invention is based on the mutual approximate entropy concept, and the similarity of two time sequences is evaluated through the magnitude of the entropy value, so that the sag source identification function is realized. The method comprises the steps of establishing a sample waveform library, preparing data, constructing a model, finally judging a calculation result, processing the data layer by layer and presenting an effective result. Firstly, establishing various types of voltage sag standard sample waveform libraries according to analysis of various types of voltage sag three-phase voltage vectors and by combining collected voltage sag waveform data caused by various short-circuit faults; then filtering and denoising the sag waveforms to be matched, extracting a depression domain, unifying the time sequence length, and performing standardized calculation; and then calculating the mutual approximate entropy value of the waveform to be matched and the sample waveform. Calculating the mutual approximate entropy of the waveform to be matched and each waveform in the sample library, and reserving the minimum entropy value and the information of the corresponding sample; finally, judging whether the minimum entropy value is within a threshold range, if not, judging that the undetermined result is reliable, namely the undetermined result is the sag type of the waveform to be matched; if the waveform exceeds the range, the waveform to be matched is judged not to belong to any sag type in the waveform library. Based on the comparison of the test data and the test result, the total accuracy of the identification result of the voltage sag source identification method is up to 98%.
Claims (4)
1. A voltage sag source identification method based on mutual approximate entropy is characterized by comprising the following steps:
(1) establishing a sample waveform library;
(2) preprocessing data;
(3) calculating a mutual approximation entropy value of a waveform to be matched and a sample waveform, and specifically comprising:
(31) for the actually measured waveform time sequence i (t) and the sample waveform time sequence j (t), a window with the length of m is specified, and N-m +1 m-dimensional vectors X are respectively constructed for the i (t) and the j (t)p、Xq:
Xp=[i(p),···,i(p+m-1)]
p=1,2,···,N-m+1
Xq=[j(q),···,j(q+m-1)]
q=1,2,···,N-m+1
Wherein, p and q are respectively the serial numbers of the actually measured waveform sequence and the sample waveform sequence;
(32) describing X using ∞ -norm of vectorpAnd XqDistance d (X) therebetweenp,Xq)=||Xp-Xq||∞;
(33) Given a similar tolerance r, X is counted for each p valuepAnd all Xq(q ═ 1,2, ·, N-m +1) the number N of vector distances less than rp,m,rAnd calculating Np,m,rRatio C to the total number of vectors (N-m +1)p,m,r:
(34) First to Cp,m,rTaking the logarithm and averaging it over all p to obtain the degree of cross-correlation between the two curves:
(35) increasing the window length to m +1, and repeating the operation processes of the steps (31) to (34) to obtain phim+1,r;
(36) And (3) calculating to obtain a mutual approximation entropy value related to m and r:
CAE(m,r)=Φm,r-Φm+1,r;
(4) identifying the type of the sag source, which comprises the following specific steps:
the smaller the mutual approximation entropy value is, the greater the similarity degree of the waveform to be matched and the sample waveform is, and the actually measured voltage sag waveform and the waveform with the minimum mutual approximation entropy in the sample library are classified as the same voltage sag;
selecting a minimum mutual approximation entropy value from the mutual approximation entropy values obtained in the step (3), judging whether the minimum mutual approximation entropy value is within a threshold range, if the minimum mutual approximation entropy value does not exceed the threshold range, judging that an undetermined result is reliable, namely the undetermined result is a sag type of the waveform to be matched, and if the minimum mutual approximation entropy value exceeds the range, judging that the waveform to be matched does not belong to any sag type in a waveform library; the threshold value is selected according to the criterion that CAE is less than or equal to 0.4.
2. The mutual approximation entropy-based voltage sag source identification method according to claim 1, wherein the step (1) specifically comprises:
(11) analyzing the change conditions of the amplitude and the phase angle of the voltage sag waveform caused by various short-circuit faults and the change conditions of the amplitude and the phase angle of various sag after transmission and transformation by the transformer;
(12) summarizing all the waveform types of sag caused by short-circuit faults according to the voltage sag type vector diagrams and the collected actually-measured sag waveform data;
(13) a library of standard sample waveforms covering these representative waveforms is established.
3. The voltage sag source identification method based on mutual approximation entropy of claim 2, wherein: the step (2) specifically comprises:
(21) filtering and denoising the obtained temporary drop waveform data;
(22) extracting a voltage sag depression domain;
(23) the data obtained were normalized.
4. The mutual approximation entropy-based voltage sag source identification method according to claim 3, wherein: in the step (22), the voltage sag depression domain is extracted by using wavelet transform.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910047165.7A CN109828184B (en) | 2019-01-18 | 2019-01-18 | Voltage sag source identification method based on mutual approximate entropy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910047165.7A CN109828184B (en) | 2019-01-18 | 2019-01-18 | Voltage sag source identification method based on mutual approximate entropy |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109828184A CN109828184A (en) | 2019-05-31 |
CN109828184B true CN109828184B (en) | 2020-11-03 |
Family
ID=66860366
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910047165.7A Active CN109828184B (en) | 2019-01-18 | 2019-01-18 | Voltage sag source identification method based on mutual approximate entropy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109828184B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027503A (en) * | 2019-12-18 | 2020-04-17 | 广东电网有限责任公司 | Method for adaptively unifying time scales of power quality data |
CN112114186B (en) * | 2020-08-14 | 2022-09-23 | 广西电网有限责任公司电力科学研究院 | Voltage sag source identification method and device based on distance discriminant analysis |
CN112131956B (en) * | 2020-08-27 | 2022-08-26 | 国网湖北省电力有限公司电力科学研究院 | Voltage sag source classification method based on difference hash algorithm |
CN112036318B (en) * | 2020-09-01 | 2023-10-20 | 海南电网有限责任公司电力科学研究院 | Voltage sag source homogeneous integration identification method |
CN112285410B (en) * | 2020-09-29 | 2022-07-01 | 国网宁夏电力有限公司中卫供电公司 | Method, medium and system for estimating severity of voltage sag |
CN113125886B (en) * | 2021-04-16 | 2023-10-27 | 南京工程学院 | Positioning method for power quality disturbance source |
CN114254712A (en) * | 2021-12-30 | 2022-03-29 | 国网江苏省电力有限公司宿迁供电分公司 | Adaboost-BP-based voltage sag type identification method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20070080913A (en) * | 2006-02-09 | 2007-08-14 | 고려대학교 산학협력단 | System and method for determining areas of vulnerability for voltage sags assessment, and a medium having computer readable program for executing the method |
CN102608493A (en) * | 2011-01-25 | 2012-07-25 | 华北电力科学研究院有限责任公司 | Method and device for positioning voltage sag source |
CN108693469A (en) * | 2018-06-12 | 2018-10-23 | 广东电网有限责任公司 | The method for diagnosing faults and device of GIS device |
-
2019
- 2019-01-18 CN CN201910047165.7A patent/CN109828184B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20070080913A (en) * | 2006-02-09 | 2007-08-14 | 고려대학교 산학협력단 | System and method for determining areas of vulnerability for voltage sags assessment, and a medium having computer readable program for executing the method |
CN102608493A (en) * | 2011-01-25 | 2012-07-25 | 华北电力科学研究院有限责任公司 | Method and device for positioning voltage sag source |
CN108693469A (en) * | 2018-06-12 | 2018-10-23 | 广东电网有限责任公司 | The method for diagnosing faults and device of GIS device |
Non-Patent Citations (2)
Title |
---|
Uncertainty assessment on failure accident of voltage-sensitive equipment due to voltage sag by maximum hybrid entropy;Wang Ying等;《Power System Technology》;20121130;第36卷(第11期);全文 * |
电压暂降特性及严重程度综合评估方法研究;杨家莉;《中国优秀硕士学位论文全文数据库工程科技II辑》;20180315;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN109828184A (en) | 2019-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109828184B (en) | Voltage sag source identification method based on mutual approximate entropy | |
CN109829497B (en) | Supervised learning-based station area user identification and discrimination method | |
CN109740641A (en) | A kind of area user identification zone method clustered based on principal component analysis and k-means | |
CN107979086B (en) | Voltage sag reason identification method based on EM algorithm and gradient lifting tree | |
CN109816033A (en) | A method of the supervised learning based on optimization carries out area user identification zone | |
CN108009730B (en) | Photovoltaic power station system health state analysis method | |
CN107025365A (en) | A kind of non-intruding load discrimination method for user side | |
CN110687393B (en) | Valve short-circuit protection fault positioning method based on VMD-SVD-FCM | |
CN111505434B (en) | Method for identifying fault hidden danger of low-voltage distribution meter box line and meter box | |
CN107589341B (en) | Single-phase grounding online fault positioning method based on distribution automation main station | |
CN109541344B (en) | SVM-based fault identification method for modular multi-level direct current power transmission system | |
CN112782523B (en) | Power distribution network single-phase earth fault line selection method based on dynamic mode matching distance | |
CN106548013B (en) | Utilize the voltage sag source identification method for improving incomplete S-transformation | |
CN111080105A (en) | Transformer area user-to-user relationship identification method and system based on voltage time sequence data | |
CN109784276A (en) | A kind of voltage dip feature extraction based on DBN and temporarily drop source discrimination method | |
CN113191253A (en) | Non-invasive load identification method based on feature fusion under edge machine learning | |
CN114359674A (en) | Non-invasive load identification method based on metric learning | |
CN112510817A (en) | Intelligent identification method for low-voltage topological relation of transformer area | |
Kangping et al. | Analysis on residential electricity consumption behavior using improved k-means based on simulated annealing algorithm | |
CN103823158B (en) | Use the malfunction route selection method for resonant grounded system of not bending moment | |
CN113659564B (en) | Low-voltage distribution network topology identification method and system based on voltage fluctuation feature clustering | |
CN116502149A (en) | Low-voltage power distribution network user-transformation relation identification method and system based on current characteristic conduction | |
CN110968073A (en) | Double-layer tracing identification method for commutation failure reasons of HVDC system | |
Wei et al. | Detection of users-transformer relationship in the secondary power distribution system with smart meter data | |
CN109787219B (en) | Intelligent identification method for voltage sag |
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 |