CN113033633A - Equipment type identification method combining power fingerprint knowledge and neural network - Google Patents
Equipment type identification method combining power fingerprint knowledge and neural network Download PDFInfo
- Publication number
- CN113033633A CN113033633A CN202110267278.5A CN202110267278A CN113033633A CN 113033633 A CN113033633 A CN 113033633A CN 202110267278 A CN202110267278 A CN 202110267278A CN 113033633 A CN113033633 A CN 113033633A
- Authority
- CN
- China
- Prior art keywords
- fingerprint knowledge
- device type
- type identification
- knowledge
- neural network
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a device type identification method combining power fingerprint knowledge and a neural network, which comprises the following steps: s1, acquiring voltage and current sampling data when the equipment is used; s2, setting a time interval, and dividing the data obtained in the S1; s3, converting the data obtained in the S2 into common electrical characteristic quantities; s4, inputting the electrical characteristic quantity obtained in the S3 into a knowledge extraction model to obtain an electrical fingerprint knowledge point of the equipment; s5, encoding the electric power fingerprint knowledge points obtained in the S4, and splicing the electric power fingerprint knowledge points with the electric characteristic quantity obtained in the S3 to obtain a total characteristic vector; and S6, inputting the total feature vector obtained in the S5 into the trained neural network to obtain the device type. Compared with the traditional load identification method, the method organically combines the machine learning method and the knowledge driving method, can greatly reduce the requirement on data volume, can accelerate the convergence data and judgment speed of the model, and can improve the accuracy of the model.
Description
Technical Field
The invention relates to a device type identification method combining power fingerprint knowledge and a neural network, and belongs to the technical field of load identification.
Background
With the gradual improvement of the electrical measurement system of the power grid, more and more electrical measurement devices are put into use, and load identification by utilizing monitoring data becomes possible. The load identification methods proposed at present are numerous, but mainly focus on a complete data-driven machine learning method, and less people consider combining expert experience and knowledge to perform load identification. For example, chinese patent application (publication No. CN105974219B) proposes a load identification method based on full data driving by using voltage, current and power factor, and has the disadvantage that the three devices with relatively close data size cannot be identified; for example, chinese patent publication No. CN111914899A proposes to combine artificial rules with machine learning for recognition, which is combined with partial knowledge, but the knowledge is derived from a data-driven decision tree and is not interpretable expert experience and knowledge.
Based on this, how to reasonably combine the expert knowledge system and the machine learning method is the key point for improving the load identification accuracy.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the device type identification method combining power fingerprint knowledge and a neural network is provided to solve the technical problems in the prior art.
The technical scheme adopted by the invention is as follows: a method of device type identification incorporating power fingerprint knowledge and a neural network, the method comprising the steps of:
step S1, acquiring voltage and current sampling data when the equipment is used;
step S2, setting a time interval, and cutting the voltage and current sampling data obtained in the step S1;
step S3, converting the data obtained in the step S2 into common electrical characteristic quantities;
step S4, inputting the electrical characteristic quantity obtained in the step S3 into a knowledge extraction model to obtain power fingerprint knowledge points of the equipment;
and S5, encoding the electric power fingerprint knowledge points obtained in the step S4, and splicing the electric power fingerprint knowledge points with the electric characteristic quantity obtained in the step S3 to obtain a total characteristic vector.
And S6, inputting the total feature vector obtained in the step S5 into the trained neural network to obtain the device type.
The voltage and current sampling data obtained in step S1 is the original sampling data with a sampling frequency greater than 100 Hz.
The common electrical characteristic quantities in step S3 include active power, reactive power, apparent power, voltage amplitude, current amplitude, power factor, 0-31 th harmonic current amplitude and phase.
In step S4, the power fingerprint knowledge points are: electrical external characteristics, state-time varying characteristics, and the like. The electrical external characteristic description device represents characteristics of an external circuit, and is particularly represented by resistance, sensitivity, nonlinearity and the like, for example, most heating devices such as a hot water kettle and the like are resistance type devices, most devices containing a motor are sensitivity devices, and most devices with an electronic display screen and the like are nonlinearity devices such as a computer and a television. The state time-varying characteristic describes whether the electrical characteristic quantity of the equipment tends to be stable when the equipment works, for example, the working state of the equipment such as a hot water kettle, a charger and the like is stable, and a television and a computer are determined according to actual conditions.
The method for realizing the knowledge extraction model of the electrical external characteristics comprises the following steps:
voltage harmonic U obtained in step S3iAnd current harmonics IiCalculating the impedance value Z of each sub-harmonici：
Calculating the variation coefficient c of each harmonic impedance valuev
Wherein sigmazAs a standard deviation of the impedance values of the respective harmonics,
the average value of each harmonic impedance value is obtained;
thirdly, if the coefficient of variation is larger than or equal to 10%, judging that the external characteristic of the equipment is nonlinear, and if the coefficient of variation is smaller than 10%, entering the next step;
fourthly, according to the power factor cos phi obtained in the step S3, if the power factor is larger than or equal to 0.98, the external characteristic of the equipment is judged to be resistive, and if the power factor is smaller than 0.98, the external characteristic of the equipment is judged to be inductive.
The encoding method in step S5 may be any other encoding method, such as one-hot code or sequential encoding.
Wherein, the neural network training mode in step S6 is: the method comprises the steps of collecting voltage and current data of partial equipment in advance, obtaining total characteristic vector data through steps S2-S5, and finally inputting the total characteristic vector data into a neural network for feedback training until the neural network can accurately identify 95% of training equipment.
The invention has the beneficial effects that: compared with the prior art, the method for identifying the equipment type by combining the power fingerprint knowledge with the neural network has the thought that the traditional load identification method depends on data driving, and a large amount of data needs to be input to train the network to achieve a certain effect.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention is further described with reference to the accompanying drawings and specific embodiments.
Example 1: as shown in fig. 1, a device type identification method combining power fingerprint knowledge and a neural network includes the following steps:
and step S1, collecting voltage and current data of 100 (including 20) household electric devices in advance through the intelligent socket, wherein the sampling frequency of the intelligent socket is 6.4kHz, the sampling precision is 0.5 level, and the sampling time is 10S.
And step S2, setting a time interval of 0.02S, dividing the voltage and current sampling data of each device obtained in the step S1 into 500 data segments, and obtaining 5 ten thousand data segments by 100 devices.
Step S3, step CThe voltage and current sampling data segment obtained in S2 is calculated to obtain electrical characteristic quantity, such as 0-11 th harmonic U of voltagei0-11 th harmonic of the current Ii(where i represents the number of times), the apparent power S, the reactive power Q, and the power factor cos φ are calculated. Wherein the harmonic of the voltage and the current is calculated by a fast Fourier transform algorithm (FFT), and the apparent power S, the reactive power Q and the power factor cos phi are calculated according to the following formula:
S＝UI
where U and I are the voltage and current effective values, respectively.
Step S4 is to input the electrical characteristic quantity obtained in step S3 to the knowledge extraction model, and obtain the electrical fingerprint knowledge points of the device, such as electrical external characteristics and state time-varying characteristics. The knowledge extraction model of the electrical external characteristics is as follows:
voltage harmonic U obtained in step S3iAnd current harmonics IiCalculating the impedance value Z of each sub-harmonici。
Calculating the variation coefficient c of each harmonic impedance valuev
Wherein sigmazAs a standard deviation of the impedance values of the respective harmonics,
is the average value of the impedance values of the harmonics.
Thirdly, if the coefficient of variation is larger than or equal to 10%, judging that the external characteristic of the equipment is nonlinear, and if the coefficient of variation is smaller than 10%, entering the next step.
Fourthly, according to the power factor cos phi obtained in the step S3, if the power factor is larger than or equal to 0.98, the external characteristic of the equipment is judged to be resistive, and if the power factor is smaller than 0.98, the external characteristic of the equipment is judged to be inductive.
And S5, encoding the electric power fingerprint knowledge points obtained in the step S4, and splicing the electric power fingerprint knowledge points with the electric characteristic quantity obtained in the step S3 to obtain a total characteristic vector. The coding mode adopts sequential coding, for example, the resistance of the electrical external characteristic is represented by 0, the sensitivity is represented by 1, and the nonlinearity is represented by 2; the steady operation of the state-varying characteristic is represented by 0, and the unstable operation is represented by 1. The total feature vector then includes: 0-11 th harmonic U of voltagei0-11 th harmonic of the current Ii(where i represents the number of times), calculating the apparent power S, the reactive power Q, the power factor cos phi, the electrical external characteristics, the state time varying characteristics, and a total of 52-dimensional data, wherein each voltage current harmonic comprises a 2-dimensional array (amplitude and phase).
Step S6, inputting the total feature vector obtained in the step S5 into a trained neural network model, wherein the training mode is as follows: and inputting the pre-collected equipment data into a neural network for judgment, and then continuously adjusting parameters of the neural network until 95% of training data can be identified by a network model. Wherein the neural network model parameters are set as: the number of the network layers is 3, the number of neurons in each layer is 52, 20 and 10 respectively, a full connection mode is adopted among the layers, and a neuron activation function is set to be a sigmoid function. And finally, inputting the data to be recognized into the trained model to obtain a recognition result.
Through the steps, the type of the load equipment can be identified according to the data measured by the measuring terminal.
The invention provides a device type identification method combining power fingerprint knowledge and a neural network, which is based on the idea that a traditional load identification method depends on data driving and needs to input a large amount of data to train the network to achieve a certain effect, and the invention provides the load identification method combining power fingerprint expert knowledge.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present invention, and therefore, the scope of the present invention should be determined by the scope of the claims.
Claims (10)
1. A device type identification method combining power fingerprint knowledge and a neural network is characterized in that: the method comprises the following steps:
step S1, acquiring voltage and current sampling data when the equipment is used;
step S2, setting a time interval, and cutting the voltage and current sampling data obtained in the step S1;
s3, inputting the cut voltage and current sampling data obtained in the S2 into a plurality of trained knowledge extraction models to obtain power fingerprint knowledge points of the equipment;
step S4, converting the cut voltage and current sampling data obtained in the step S2 into common electrical characteristic quantities;
step S5, encoding the electric power fingerprint knowledge points obtained in the step S3, and splicing the electric power fingerprint knowledge points with the electric characteristic quantity obtained in the step S4 to obtain a total characteristic vector;
and S6, inputting the total feature vector obtained in the step S5 into the trained neural network to obtain the device type.
2. The method for device type identification combining power fingerprint knowledge and neural networks of claim 1, wherein: the voltage and current sampling data obtained in step S1 is the original sampling data having a sampling frequency greater than 100 Hz.
3. The method for device type identification combining power fingerprint knowledge and neural networks of claim 1, wherein: the common electrical characteristic quantities described in step S4 are active power, reactive power, apparent power, voltage amplitude, current amplitude, power factor, 0-31 th harmonic current amplitude and phase.
4. The method for device type identification combining power fingerprint knowledge and neural networks of claim 1, wherein: the power fingerprint knowledge points in step S3 are: electrical external properties and state-time varying properties.
5. The method for device type identification combining power fingerprint knowledge and neural networks of claim 4, wherein: the electrical external characteristics are: the characteristics of the device embodied in the external circuit are described, embodied as resistive, inductive, nonlinear.
6. The method for device type identification combining power fingerprint knowledge and neural networks of claim 4, wherein: the method for realizing the knowledge extraction model of the electrical external characteristics comprises the following steps:
voltage harmonic U obtained in step S3iAnd current harmonics IiCalculating the impedance value Z of each sub-harmonici：
Calculating the variation coefficient c of each harmonic impedance valuev
Wherein sigmazAs a standard deviation of the impedance values of the respective harmonics,
the average value of each harmonic impedance value is obtained;
thirdly, if the coefficient of variation is larger than or equal to 10%, judging that the external characteristic of the equipment is nonlinear, and if the coefficient of variation is smaller than 10%, entering the next step;
fourthly, according to the power factor cos phi obtained in the step S3, if the power factor is larger than or equal to 0.98, the external characteristic of the equipment is judged to be resistive, and if the power factor is smaller than 0.98, the external characteristic of the equipment is judged to be inductive.
7. The method for device type identification combining power fingerprint knowledge and neural networks of claim 4, wherein: the state-time-varying characteristic is: it is described whether or not the electrical characteristic quantity tends to be stable when the apparatus is in operation.
8. The method for device type identification combining power fingerprint knowledge and neural networks of claim 1, wherein: the encoding method in step S5 adopts one-hot code, sequential encoding or any other encoding method.
9. The method for device type identification combining power fingerprint knowledge and neural networks of claim 1, wherein: the neural network training method of step S6 includes: the method comprises the steps of collecting voltage and current data of partial equipment in advance, obtaining total characteristic vector data through steps S2-S5, and finally inputting the total characteristic vector data into a neural network for feedback training until the neural network can accurately identify 95% of training equipment.
10. The method for device type identification combining power fingerprint knowledge and neural networks of claim 1, wherein: the neural network model parameters are set as: the number of the network layers is 3, the number of neurons in each layer is 52, 20 and 10 respectively, a full connection mode is adopted among the layers, and a neuron activation function is set to be a sigmoid function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110267278.5A CN113033633B (en) | 2021-03-12 | 2021-03-12 | Equipment type identification method combining power fingerprint knowledge and neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110267278.5A CN113033633B (en) | 2021-03-12 | 2021-03-12 | Equipment type identification method combining power fingerprint knowledge and neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113033633A true CN113033633A (en) | 2021-06-25 |
| CN113033633B CN113033633B (en) | 2022-12-09 |
Family
ID=76469760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110267278.5A Active CN113033633B (en) | 2021-03-12 | 2021-03-12 | Equipment type identification method combining power fingerprint knowledge and neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033633B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114511007A (en) * | 2022-01-17 | 2022-05-17 | 上海梦象智能科技有限公司 | Non-invasive electrical fingerprint identification method based on multi-scale feature perception |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105866593A (en) * | 2016-05-19 | 2016-08-17 | 国家电网公司 | Online identification system for power load energy efficiency fingerprints |
| CN105913006A (en) * | 2016-04-08 | 2016-08-31 | 湖南工业大学 | Electricity load type identification method |
| CN108920457A (en) * | 2018-06-15 | 2018-11-30 | 腾讯大地通途（北京）科技有限公司 | Address Recognition method and apparatus and storage medium |
| CN109782086A (en) * | 2018-12-25 | 2019-05-21 | 武汉中原电子信息有限公司 | A kind of non-intruding load recognition methods based on the analysis of various dimensions signal |
| CN109813978A (en) * | 2018-12-25 | 2019-05-28 | 武汉中原电子信息有限公司 | A kind of non-intruding load-type recognition methods of variation characteristic between comprehensive transient characteristic and stable state |
| CN110544177A (en) * | 2019-08-15 | 2019-12-06 | 广州水沐青华科技有限公司 | Load identification method based on power fingerprint and computer readable storage medium |
| CN110555369A (en) * | 2019-07-16 | 2019-12-10 | 浙江工业大学 | MLCDTL-based non-intrusive load identification method |
| CN110956220A (en) * | 2019-12-11 | 2020-04-03 | 深圳市活力天汇科技股份有限公司 | Non-invasive household appliance load identification method |
| CN110991818A (en) * | 2019-11-14 | 2020-04-10 | 广西电网有限责任公司电力科学研究院 | Load identification method integrating event detection and neural network |
| CN111368904A (en) * | 2020-02-29 | 2020-07-03 | 华南理工大学 | Electrical equipment identification method based on electric power fingerprint |
| CN111382789A (en) * | 2020-03-06 | 2020-07-07 | 云南电网有限责任公司电力科学研究院 | Power load identification method and system based on machine learning |
| CN111428816A (en) * | 2020-04-17 | 2020-07-17 | 贵州电网有限责任公司 | Non-invasive load decomposition method |
| CN111582357A (en) * | 2020-04-30 | 2020-08-25 | 华南理工大学 | Electric power fingerprint identification method based on multi-dimensional integration |
-
2021
- 2021-03-12 CN CN202110267278.5A patent/CN113033633B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913006A (en) * | 2016-04-08 | 2016-08-31 | 湖南工业大学 | Electricity load type identification method |
| CN105866593A (en) * | 2016-05-19 | 2016-08-17 | 国家电网公司 | Online identification system for power load energy efficiency fingerprints |
| CN108920457A (en) * | 2018-06-15 | 2018-11-30 | 腾讯大地通途（北京）科技有限公司 | Address Recognition method and apparatus and storage medium |
| CN109782086A (en) * | 2018-12-25 | 2019-05-21 | 武汉中原电子信息有限公司 | A kind of non-intruding load recognition methods based on the analysis of various dimensions signal |
| CN109813978A (en) * | 2018-12-25 | 2019-05-28 | 武汉中原电子信息有限公司 | A kind of non-intruding load-type recognition methods of variation characteristic between comprehensive transient characteristic and stable state |
| CN110555369A (en) * | 2019-07-16 | 2019-12-10 | 浙江工业大学 | MLCDTL-based non-intrusive load identification method |
| CN110544177A (en) * | 2019-08-15 | 2019-12-06 | 广州水沐青华科技有限公司 | Load identification method based on power fingerprint and computer readable storage medium |
| CN110991818A (en) * | 2019-11-14 | 2020-04-10 | 广西电网有限责任公司电力科学研究院 | Load identification method integrating event detection and neural network |
| CN110956220A (en) * | 2019-12-11 | 2020-04-03 | 深圳市活力天汇科技股份有限公司 | Non-invasive household appliance load identification method |
| CN111368904A (en) * | 2020-02-29 | 2020-07-03 | 华南理工大学 | Electrical equipment identification method based on electric power fingerprint |
| CN111382789A (en) * | 2020-03-06 | 2020-07-07 | 云南电网有限责任公司电力科学研究院 | Power load identification method and system based on machine learning |
| CN111428816A (en) * | 2020-04-17 | 2020-07-17 | 贵州电网有限责任公司 | Non-invasive load decomposition method |
| CN111582357A (en) * | 2020-04-30 | 2020-08-25 | 华南理工大学 | Electric power fingerprint identification method based on multi-dimensional integration |
Non-Patent Citations (5)
| Title |
|---|
| CHANGBAO XU等: "《Research on Feeder Power Balancing Technology Based on SNOP Droop Control》", 《 2019 IEEE 10TH INTERNATIONAL SYMPOSIUM ON POWER ELECTRONICS FOR DISTRIBUTED GENERATION SYSTEMS (PEDG)》 * |
| SHENG WU等: "《Research on Features of Residential Loads and Establishment of Feature Library》", 《2018 2ND IEEE CONFERENCE ON ENERGY INTERNET AND ENERGY SYSTEM INTEGRATION (EI2)》 * |
| 张秋雁等: "《基于扩展面板大数据的电力经济特征提取新方法》", 《电网与清洁能源》 * |
| 谈竹奎等: "《用电负荷指纹管理的层次化系统设计》", 《电测与仪表》 * |
| 黄光磊: "《直流电缆局部放电与泄漏电流特性及类型识别研究》", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114511007A (en) * | 2022-01-17 | 2022-05-17 | 上海梦象智能科技有限公司 | Non-invasive electrical fingerprint identification method based on multi-scale feature perception |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113033633B (en) | 2022-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Veerasamy et al. | LSTM recurrent neural network classifier for high impedance fault detection in solar PV integrated power system | |
| CN105425118B (en) | A kind of Multi-information acquisition fault arc detection method and device | |
| Du et al. | Single line-to-ground faulted line detection of distribution systems with resonant grounding based on feature fusion framework | |
| CN110991818B (en) | Load identification method integrating event detection and neural network | |
| Pindoriya et al. | Composite reliability evaluation using Monte Carlo simulation and least squares support vector classifier | |
| CN110111015A (en) | A kind of power quality analysis method based on the multiple dimensioned arrangement entropy of variation mode decomposition | |
| CN110276409A (en) | A kind of time series method for detecting abnormality, device, server and storage medium | |
| CN107942160A (en) | The method for building up of line parameter circuit value characteristic identification model based on BP neural network | |
| CN109359665B (en) | Household appliance load identification method and device based on support vector machine | |
| CN110543921A (en) | cable early fault identification method based on waveform learning | |
| CN113033633B (en) | Equipment type identification method combining power fingerprint knowledge and neural network | |
| CN107330573A (en) | A kind of state evaluating method and device of photovoltaic system key equipment | |
| CN106874511A (en) | A kind of database for corroding quantity of electric charge forecasting system based on insulator metal accessory | |
| CN114444539A (en) | Power load identification method, apparatus, device, medium, and program product | |
| Wang et al. | Dynamic equivalent method of PMSG‐based wind farm for power system stability analysis | |
| CN117371207A (en) | Extra-high voltage converter valve state evaluation method, medium and system | |
| CN115469184A (en) | New energy transmission line fault identification method based on convolutional network | |
| CN111239484A (en) | Non-invasive load electricity consumption information acquisition method for non-resident users | |
| CN115712871A (en) | Power electronic system fault diagnosis method combining resampling and integrated learning | |
| CN115795360A (en) | Cable fault detection method based on artificial neural network | |
| CN115528684A (en) | Ultra-short-term load prediction method and device and electronic equipment | |
| CN115856530A (en) | Edge side online arc fault detection method and system based on multidimensional entropy characteristics | |
| CN112731208B (en) | Low-voltage line fault and abnormity on-line monitoring method, equipment and medium | |
| CN109284936A (en) | A kind of electricity quality evaluation method based on the output of cloud graph visualization | |
| CN115374823A (en) | TLBO algorithm-based power quality disturbance classification method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |