CN108537385A - A kind of non-intrusion type residential electricity consumption load recognition methods - Google Patents
A kind of non-intrusion type residential electricity consumption load recognition methods Download PDFInfo
- Publication number
- CN108537385A CN108537385A CN201810327871.2A CN201810327871A CN108537385A CN 108537385 A CN108537385 A CN 108537385A CN 201810327871 A CN201810327871 A CN 201810327871A CN 108537385 A CN108537385 A CN 108537385A
- Authority
- CN
- China
- Prior art keywords
- individual
- data
- value
- household appliance
- appliance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of non-intrusion type residential electricity consumption load recognition methods, include the following steps：S1 make the general power after fitting and total harmonic wave and actual measurement general power and total harmonic wave value it is closest, by electric appliance load identification problem optimization；S2 calculates the power features value of each household appliance using formula, and current harmonics frequency spectrum increasing value is calculated using FFT；Then the basic data that can represent the data group of household appliance feature into household appliance is filtered out according to basic data screening method；S3 acquires current value, the voltage value of a certain moment resident bus, calculates general power；S4 generates M initial population using quasi-random Halton sequences, is that this M individual carries out binary coding；S5 calculates the adaptive value of each individual and carries out genetic manipulation.
Description
Technical field
The present invention relates to power loads to identify field, is identified more particularly, to a kind of non-intrusion type residential electricity consumption load
Method.
Background technology
Load identification usually has two methods of intrusive and non-intrusion type, the former is dedicated solely in the setting of each individual load
Vertical load detection sensor, monitors each load condition data related with acquisition, finally carries out data summarization.The latter only supplies always
Load detection sensor is arranged in electrical circuit, using soft and hardware technology, voluntarily identifies different load input operating mode and obtains related number
According to.
Take intrusive load identification that there is following defect：Although 1) invasion mode implementation process application technology difficulty is low,
Existing mature technology scheme can be utilized to solve, but need to change and participate in data acquisition target supply line topological diagram, it can be to adopting
The daily life of collection object causes unnecessary trouble, reduces the enthusiasm that data acquisition target participates in a certain extent；
2) household appliance of each family of modern society is numerous, and installation site dispersion, acquisition cost can increase with collecting device quantity
It linearly increases.It causes hardware cost high, is unfavorable for the popularization and application of large area.
Invention content
Present invention aim to address said one or multiple defects, propose a kind of non-intrusion type residential electricity consumption load identification
Method.
To realize the above goal of the invention, the technical solution adopted is that：
A kind of non-intrusion type residential electricity consumption load recognition methods, includes the following steps：
S1：Based on electric appliance load identifying purpose is realized, i.e., to make the total work of the general power and total harmonic wave and actual measurement after fitting
Rate and the value of total harmonic wave are closest, convert electric appliance load identification problem to the optimization problem for solving following formula, target
Function is
Wherein P (t) is the general power collected in a certain resident's circuit of any moment, P=[P1,P2,...,PN] ' it is N
Performance number when a electric operation, I (t) are the total harmonic wave collected in a certain resident's circuit of any moment, I=[I1,
I2,...,IN] ' be N number of electric operation when harmonic wave, S=[s1,s2,...,sN], wherein siIndicate the operation shape of i-th of electric appliance
The operating status of state, electric appliance load indicates that 0 expression electric appliance is closed with 0 or 1, and 1 indicates that electric appliance is in operating status,
Then siIt is 0 or 1；S*P indicates that fitting general power, S*I are to indicate to be fitted total harmonic wave, and λ is weight factor；
S2：The basic data of household appliance, including current value and voltage value are acquired, each household electrical appliances is calculated using formula and sets
Standby power features value calculates current harmonics frequency spectrum increasing value using FFT；Then energy is filtered out according to basic data screening method
The data group of household appliance feature is represented into basic data P, I of household appliance, and has identified household appliance number；Wherein P is
The power of household appliance, I are the current harmonics data of household appliance；
S3：Current value, the voltage value of a certain moment resident bus are acquired, general power P (t) and total harmonic content I is calculated
(t)；
S4：M initial population is generated using quasi-random Halton sequencesBinary system volume is carried out for this M individual
Code, and the group algebraically δ of crossover probability pc, mutation probability pm and iteration are set, concurrently set K=0；
S5：Calculate the adaptive value of each individual
S6：Genetic manipulation is carried out to each individual；
S7：K=k+1 is enabled, step S4 and S5 is repeated, works as K>Terminate when=δ.
Preferably, the ranging from λ ∈ [0,1] of weight factor λ described in step S1.
Preferably, it includes calculating within 10 times to calculate current harmonics spectral magnitude using FFT described in step S2
Current harmonics spectral magnitude.
Preferably, the data group that can represent household appliance feature is filtered out according to basic data screening method described in step S2
Include the following steps at basic data P, I of household appliance：
S2.1：To the power Ps of each collected household electrical appliance ' and current harmonics data I', note D=(P', I')；
S2.2：To the D data set duplicate removals of each household electrical appliance；
S2.3：D data sets are arranged based on fundamental wave data ascending order；
S2.4：The fundamental wave of each row of data and the fundamental wave data difference d of lastrow in D data sets are calculated, if difference d>=
0.1, then the row data are selected into basic data in D
Preferably, the ranging from pc ∈ [0.49,0.99] of crossover probability pc described in step S4, the range of mutation probability pm
For pm ∈ [0.0001,0.1], group's algebraically ranging from δ ∈ [200,500] of iteration.
Preferably, step S6 includes the following steps：
S6.1：Selection operation is carried out to individual, wherein the probability that each individual is selected is
And it is selected using wheel disc bet method：Calculate the accumulated probability q of each individuali,
[0,1] section generates a uniform pseudo random number r, individual k is selected, if qk-1＜ r ＜=qkSelected individual is added to
In group of new generation；
S6.2：Crossover operation is carried out using single-point interior extrapolation method, i.e., the individual random pair two-by-two in population randomly selects 1
A crossover location carries out crossover operation to i-th pair individual, a uniform pseudo random number r is generated in [0,1] section, if r<
Pc, the new individual that crossover operation generates later are added in group of a new generation；
S6.3：Using basic bit mutation method carry out mutation operation, that is, randomly select 1 variable position, to i-th individual into
Row variation operates, and a uniform pseudo random number r is generated in [0,1] section, if r<Pm, what is generated after mutation operation is new
Individual is added in group of new generation.
Compared with prior art, the beneficial effects of the invention are as follows：
The required acquisition terminal quantity of the present invention is few, simple installation, safeguards simply, convenient for promoting
Description of the drawings
Fig. 1 is the flow chart of the present invention.
Specific implementation mode
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent；
Below in conjunction with drawings and examples, the present invention is further elaborated.
Embodiment 1
A kind of non-intrusion type residential electricity consumption load recognition methods, includes the following steps：
S1：Based on electric appliance load identifying purpose is realized, i.e., to make the total work of the general power and total harmonic wave and actual measurement after fitting
Rate and the value of total harmonic wave are closest, convert electric appliance load identification problem to the optimization problem for solving following formula, target
Function is
Wherein P (t) is the general power collected in a certain resident's circuit of any moment, P=[P1,P2,...,PN] ' it is N
Performance number when a electric operation, I (t) are the total harmonic wave collected in a certain resident's circuit of any moment, I=[I1,
I2,...,IN] ' be N number of electric operation when harmonic wave, S=[s1,s2,...,sN], wherein siIndicate the operation shape of i-th of electric appliance
The operating status of state, electric appliance load indicates that 0 expression electric appliance is closed with 0 or 1, and 1 indicates that electric appliance is in operating status,
Then siIt is 0 or 1；S*P indicates that fitting general power, S*I are to indicate to be fitted total harmonic wave, and λ is weight factor；
S2：The basic data of household appliance, including current value and voltage value are acquired, each household electrical appliances is calculated using formula and sets
Standby power features value calculates current harmonics frequency spectrum increasing value using FFT；Then energy is filtered out according to basic data screening method
The data group of household appliance feature is represented into basic data P, I of household appliance, and has identified household appliance number；Wherein P is
The power of household appliance, I are the current harmonics data of household appliance；
S3：Current value, the voltage value of a certain moment resident bus are acquired, general power P (t) and total harmonic content I is calculated
(t)；
S4：M initial population is generated using quasi-random Halton sequencesBinary system volume is carried out for this M individual
Code, and the group algebraically δ of crossover probability pc, mutation probability pm and iteration are set, concurrently set K=0；
S5：Calculate the adaptive value of each individual
S6：Genetic manipulation is carried out to each individual；
S7：K=k+1 is enabled, step S4 and S5 is repeated, works as K>Terminate when=δ.
Preferably, the ranging from λ ∈ [0,1] of weight factor λ described in step S1.
Preferably, it includes calculating within 10 times to calculate current harmonics spectral magnitude using FFT described in step S2
Current harmonics spectral magnitude.
Preferably, the data group that can represent household appliance feature is filtered out according to basic data screening method described in step S2
Include the following steps at basic data P, I of household appliance：
S2.1：To the power Ps of each collected household electrical appliance ' and current harmonics data I', note D=(P', I')；
S2.2：To the D data set duplicate removals of each household electrical appliance；
S2.3：D data sets are arranged based on fundamental wave data ascending order；
S2.4：The fundamental wave of each row of data and the fundamental wave data difference d of lastrow in D data sets are calculated, if difference d>=
0.1, then the row data are selected into basic data in D
Preferably, the ranging from pc ∈ [0.49,0.99] of crossover probability pc described in step S4, the range of mutation probability pm
For pm ∈ [0.0001,0.1], group's algebraically ranging from δ ∈ [200,500] of iteration.
Preferably, step S6 includes the following steps：
S6.1：Selection operation is carried out to individual, wherein the probability that each individual is selected is
And it is selected using wheel disc bet method：Calculate the accumulated probability q of each individuali,
[0,1] section generates a uniform pseudo random number r, individual k is selected, if qk-1＜ r ＜=qkSelected individual is added to
In group of new generation；
S6.2：Crossover operation is carried out using single-point interior extrapolation method, i.e., the individual random pair two-by-two in population randomly selects 1
A crossover location carries out crossover operation to i-th pair individual, a uniform pseudo random number r is generated in [0,1] section, if r<
Pc, the new individual that crossover operation generates later are added in group of a new generation；
S6.3：Using basic bit mutation method carry out mutation operation, that is, randomly select 1 variable position, to i-th individual into
Row variation operates, and a uniform pseudo random number r is generated in [0,1] section, if r<Pm, what is generated after mutation operation is new
Individual is added in group of new generation.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
All any modification, equivalent and improvement etc., should be included in the claims in the present invention made by within the spirit and principle of invention
Protection domain within.
Claims (6)
1. a kind of non-intrusion type residential electricity consumption load recognition methods, which is characterized in that include the following steps：
S1：Based on realize electric appliance load identifying purpose, i.e., to make the general power after fitting and total harmonic wave and actual measurement general power and
The value of total harmonic wave is closest, converts electric appliance load identification problem to the optimization problem for solving following formula, object function
For
Wherein P (t) is the general power collected in a certain resident's circuit of any moment, P=[P1,P2,...,PN] ' it is N number of electricity
Performance number when device is run, I (t) are the total harmonic wave collected in a certain resident's circuit of any moment, I=[I1,I2,...,
IN] ' be N number of electric operation when harmonic wave, S=[s1,s2,...,sN], wherein siIndicate the operating status of i-th of electric appliance, electric appliance
The operating status of load indicates that 0 expression electric appliance is closed with 0 or 1, and 1 indicates that electric appliance is in operating status, then siIt is 0
Or 1；S*P indicates that fitting general power, S*I are to indicate to be fitted total harmonic wave, and λ is weight factor；
S2：The basic data of household appliance, including current value and voltage value are acquired, each household appliance is calculated using formula
Power features value calculates current harmonics frequency spectrum increasing value using FFT；Then being filtered out according to basic data screening method can represent
The data group of household appliance feature at household appliance basic data P, I, and identified household appliance number；Wherein P is household electrical appliances
The power of equipment, I are the current harmonics data of household appliance；
S3：Current value, the voltage value of a certain moment resident bus are acquired, general power P (t) and total harmonic content I (t) are calculated；
S4：M initial population is generated using quasi-random Halton sequencesBinary coding is carried out for this M individual,
And the group algebraically δ of crossover probability pc, mutation probability pm and iteration are set, concurrently set K=0；
S5：Calculate the adaptive value of each individual
S6：Genetic manipulation is carried out to each individual；
S7：K=k+1 is enabled, step S4 and S5 is repeated, works as K>Terminate when=δ.
2. a kind of non-intrusion type residential electricity consumption load recognition methods according to claim 1, which is characterized in that step S1 institutes
State the ranging from λ ∈ [0,1] of weight factor λ.
3. a kind of non-intrusion type residential electricity consumption load recognition methods according to claim 1, which is characterized in that step S2 institutes
It includes the current harmonics spectral magnitude calculated within 10 times to state and calculate current harmonics spectral magnitude using FFT.
4. a kind of non-intrusion type residential electricity consumption load recognition methods according to claim 1, which is characterized in that step S2 institutes
State basic data P, the I packet for being filtered out according to basic data screening method and capable of representing the data group of household appliance feature into household appliance
Include following steps：
S2.1：To the power Ps of each collected household electrical appliance ' and current harmonics data I', note D=(P', I')；
S2.2：To the D data set duplicate removals of each household electrical appliance；
S2.3：D data sets are arranged based on fundamental wave data ascending order；
S2.4：The fundamental wave of each row of data and the fundamental wave data difference d of lastrow in D data sets are calculated, if difference d>=0.1,
Then the row data are selected into basic data in D.
5. a kind of non-intrusion type residential electricity consumption load recognition methods according to claim 1, which is characterized in that step S4 institutes
The ranging from pc ∈ [0.49,0.99] of crossover probability pc, the ranging from pm ∈ [0.0001,0.1] of mutation probability pm are stated, iteration
Group's algebraically ranging from δ ∈ [200,500].
6. a kind of non-intrusion type residential electricity consumption load recognition methods according to claim 1, which is characterized in that step S6 packets
Include following steps：
S6.1：Selection operation is carried out to individual, wherein the probability that each individual is selected is
And it is selected using wheel disc bet method：Calculate the accumulated probability q of each individuali, in [0,1]
Section generates a uniform pseudo random number r, individual k is selected, if qk-1＜ r ＜=qkSelected individual is added to a new generation
In group；
S6.2：Crossover operation is carried out using single-point interior extrapolation method, i.e., the individual random pair two-by-two in population randomly selects 1 friendship
Vent is set, and crossover operation is carried out to i-th pair individual, a uniform pseudo random number r is generated in [0,1] section, if r<Pc is handed over
The new individual that fork operation generates later is added in group of new generation；
S6.3：Mutation operation is carried out using basic bit mutation method, that is, randomly selects 1 variable position, i-th of individual is become
ETTHER-OR operation generates a uniform pseudo random number r, if r in [0,1] section<Pm, the new individual that mutation operation generates later
It is added in group of new generation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810327871.2A CN108537385A (en) | 2018-04-12 | 2018-04-12 | A kind of non-intrusion type residential electricity consumption load recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810327871.2A CN108537385A (en) | 2018-04-12 | 2018-04-12 | A kind of non-intrusion type residential electricity consumption load recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108537385A true CN108537385A (en) | 2018-09-14 |
Family
ID=63479950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810327871.2A Pending CN108537385A (en) | 2018-04-12 | 2018-04-12 | A kind of non-intrusion type residential electricity consumption load recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108537385A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934303A (en) * | 2019-03-25 | 2019-06-25 | 宁夏隆基宁光仪表股份有限公司 | A kind of non-invasive household electrical appliance load recognition methods, device and storage medium |
| CN110146758A (en) * | 2019-05-28 | 2019-08-20 | 四川长虹电器股份有限公司 | Non-intrusion type electrical appliance recognition based on cross entropy |
| CN111178393A (en) * | 2019-12-11 | 2020-05-19 | 广东浩迪智云技术有限公司 | Electric appliance power consumption classification metering method and device based on intelligent electric meter |
| CN117194924A (en) * | 2023-09-26 | 2023-12-08 | 北京市计量检测科学研究院 | Method, system, equipment and medium for identifying indoor charging behavior of electric bicycle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103001230A (en) * | 2012-11-16 | 2013-03-27 | 天津大学 | Non-invasive power load monitoring and decomposing current mode matching method |
| CN105529700A (en) * | 2015-12-07 | 2016-04-27 | 河南许继仪表有限公司 | Non-invasive online load decomposition device |
| CN106093652A (en) * | 2016-07-07 | 2016-11-09 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function |
| CN106815677A (en) * | 2016-12-09 | 2017-06-09 | 国网北京市电力公司 | The recognition methods of non-intrusion type load and device |
| CN107330517A (en) * | 2017-06-14 | 2017-11-07 | 华北电力大学 | One kind is based on S_Kohonen non-intrusion type resident load recognition methods |
-
2018
- 2018-04-12 CN CN201810327871.2A patent/CN108537385A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103001230A (en) * | 2012-11-16 | 2013-03-27 | 天津大学 | Non-invasive power load monitoring and decomposing current mode matching method |
| CN105529700A (en) * | 2015-12-07 | 2016-04-27 | 河南许继仪表有限公司 | Non-invasive online load decomposition device |
| CN106093652A (en) * | 2016-07-07 | 2016-11-09 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function |
| CN106815677A (en) * | 2016-12-09 | 2017-06-09 | 国网北京市电力公司 | The recognition methods of non-intrusion type load and device |
| CN107330517A (en) * | 2017-06-14 | 2017-11-07 | 华北电力大学 | One kind is based on S_Kohonen non-intrusion type resident load recognition methods |
Non-Patent Citations (3)
| Title |
|---|
| 崔灿: "《面向智能用电的非侵入式居民负荷监测关键技术研究》", 《中国博士学位论文全文数据库 工程科技II辑》 * |
| 郭凯: "《遗传算法的3种改进方法和分析》", 《电子测试》 * |
| 陈沛帅 等: "《电子商务技术支撑体系研究与应用》", 31 December 2008 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934303A (en) * | 2019-03-25 | 2019-06-25 | 宁夏隆基宁光仪表股份有限公司 | A kind of non-invasive household electrical appliance load recognition methods, device and storage medium |
| CN110146758A (en) * | 2019-05-28 | 2019-08-20 | 四川长虹电器股份有限公司 | Non-intrusion type electrical appliance recognition based on cross entropy |
| CN110146758B (en) * | 2019-05-28 | 2021-02-09 | 四川长虹电器股份有限公司 | Non-invasive electrical appliance identification method based on cross entropy |
| CN111178393A (en) * | 2019-12-11 | 2020-05-19 | 广东浩迪智云技术有限公司 | Electric appliance power consumption classification metering method and device based on intelligent electric meter |
| CN117194924A (en) * | 2023-09-26 | 2023-12-08 | 北京市计量检测科学研究院 | Method, system, equipment and medium for identifying indoor charging behavior of electric bicycle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537385A (en) | A kind of non-intrusion type residential electricity consumption load recognition methods | |
| CN105972761B (en) | A kind of non-intrusion type air conditioner load monitoring method | |
| CN102508036B (en) | On-line remote monitoring method and device for pollution state of disk insulator | |
| CN103647276A (en) | Electric energy quality early warning system and method thereof | |
| CN105425079B (en) | Washing machine based on real-time mean power frequency-domain analysis runs non-intruding discrimination method | |
| CN112633924B (en) | District electric energy substitution demand analysis method based on load decomposition | |
| CN107340459A (en) | A kind of DC Line Fault arc method for measuring and system | |
| JP2013109742A (en) | Method and system for detecting electrical appliances based on user feedback information | |
| CN108256559A (en) | A kind of low pressure stealing method for positioning user based on the local outlier factor | |
| CN107247201A (en) | Electric oven non-intruding discrimination method based on power and time response | |
| CN109299134B (en) | Method for identifying electric appliance under non-invasive monitoring system | |
| CN105911342A (en) | Power-duration-time-characteristic-based non-intrusive identification method of electric cooker | |
| CN112101110A (en) | Non-invasive load identification method for user side of power system | |
| CN111722028A (en) | Load identification method based on high-frequency data | |
| CN103837764B (en) | Electric energy quality detection method for household solar photovoltaic power generation | |
| CN108152574A (en) | A kind of non-intruding discrimination method of the running of microwave oven based on mixing criterion | |
| CN115907168A (en) | Abnormal data processing system for power load prediction | |
| CN112421608B (en) | Household load prediction method based on Markov from bottom to top | |
| Gao et al. | High-impedance arc fault modeling for distribution networks based on dynamic geometry dimension | |
| CN116317096B (en) | Drawer type sampling control cabinet system based on artificial intelligence | |
| CN109460419A (en) | A kind of equipment state change events monitoring method | |
| CN113922361B (en) | Potential safety hazard and fault protection method based on non-invasive distribution and utilization electricity information decomposition | |
| CN112949563B (en) | Non-invasive load identification method based on variable point detection and improved KNN algorithm | |
| CN202548079U (en) | On-line remote monitoring device for dirty state of disc type insulator | |
| CN113655337B (en) | Non-invasive electric equipment operation sequence identification method and identification system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180914 |
|
| RJ01 | Rejection of invention patent application after publication |