CN109271925A - A kind of electrical equipment kind identification method on intelligent socket - Google Patents
A kind of electrical equipment kind identification method on intelligent socket Download PDFInfo
- Publication number
- CN109271925A CN109271925A CN201811074038.8A CN201811074038A CN109271925A CN 109271925 A CN109271925 A CN 109271925A CN 201811074038 A CN201811074038 A CN 201811074038A CN 109271925 A CN109271925 A CN 109271925A
- Authority
- CN
- China
- Prior art keywords
- electrical equipment
- characteristic
- parameter
- gauss model
- mixed gauss
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- 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
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01R—ELECTRICALLY-CONDUCTIVE CONNECTIONS; STRUCTURAL ASSOCIATIONS OF A PLURALITY OF MUTUALLY-INSULATED ELECTRICAL CONNECTING ELEMENTS; COUPLING DEVICES; CURRENT COLLECTORS
- H01R24/00—Two-part coupling devices, or either of their cooperating parts, characterised by their overall structure
- H01R24/20—Coupling parts carrying sockets, clips or analogous contacts and secured only to wire or cable
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the electrical equipment kind identification methods on a kind of intelligent socket.Acquire the electric signal on socket, characteristic parameter is calculated using metering chip, the characteristic inscribed when obtaining each electrical equipment establishes mixed Gauss model, group is construed as mixed Gauss model parameter, acquires the mixed Gauss model parameter of all four characteristic parameters of electrical equipment；Total mixed Gauss model parameter library is established, one group of characteristic of electrical equipment to be identified is inputted, total mixed Gauss model parameter library is successively brought into and calculates acquisition probability value, takes and is used as appliance type corresponding to probability value maximum.The present invention can identify the appliance type to work instantly according to the data information acquired from domestic electric network where electrical equipment, and the electrical equipment being directed in family has good accuracy and robustness.
Description
Technical field
The present invention relates to a kind of electrical appliance recognitions, know more particularly, to the electrical equipment type on a kind of intelligent socket
Other method, belongs to electric network data process field.
Background technique
With the development of the social economy, energy-efficient idea is also gradually taken seriously.More and more enterprises or family's root
According to the working condition of electric appliance, energy-efficient purpose is realized by different control technologies.In order to understand the working condition of electrical equipment,
It needs to be monitored electric appliance, monitors the working condition of electric appliance.Therefore, it is necessary to a kind of electric appliance recognizer, which kind of electricity can know that
Device equipment is working.Based on this target, a kind of effective electrical appliance recognition is needed, which is acquired electric power data,
Electrical equipment character pair library is established, and according to recognizer, identify which kind of electric appliance is working, and identification working condition is sent out
Give control terminal.
Summary of the invention
There is which electrical equipment working in order to grasp on intelligent socket, the present invention provides on a kind of intelligent socket
Electrical equipment kind identification method can be identified according to the data information acquired from domestic electric network where electrical equipment and be worked instantly
Appliance type.
As shown in Figure 1, the present invention the technical solution to solve the technical problem is that:
Step 1: electrical signal circuitry is converted into the input value range of metering chip by the electric signal on acquisition socket；
Step 2: calculating characteristic parameter using metering chip, characteristic parameter includes electric current, voltage, active power and idle function
Rate is as feature；
In specific implementation, the characteristic parameter of active power and reactive power is to calculate to obtain by electric current and voltage.
Step 3: repeating step 1~step 2 and obtain corresponding one group of characteristic of each electrical equipment each moment, for the moment
Carve corresponding one group of characteristic, i-th group of characteristic xiIncluding when electric current, voltage, active power and the reactive power inscribed, and
Establish the mixed Gauss model of following formula:
Wherein, p indicates that the probability value of characteristic, i indicate that the group ordinal number of characteristic, m indicate characteristic
Group sum, k indicate that the ordinal number of characteristic parameter, k=1-4, k=1 indicate current characteristic parameter, and k=2 indicates voltage characteristic parameter, k
=3 indicate that active power characteristic parameter, k=4 indicate reactive power characteristic parameter；N(xi|μk,Σk) indicate the i-th of electrical equipment
The corresponding mixed Gaussian function of k-th of characteristic parameter in group characteristic, πkIt is kth in i-th group of characteristic of electrical equipment
The weight factor of a characteristic parameter, μkIt is the mean value of k-th of characteristic parameter in all groups of characteristics of electrical equipment, ΣkIt is electricity
The covariance of k-th of characteristic parameter in all groups of characteristics of device equipment；xiIndicate i-th group of characteristic of electrical equipment,
Including i-th group it is corresponding when inscribe electric current, voltage, active power and reactive power collected；
Step 4: by weight factor πk, mean μkWith covariance ΣkGroup is construed as the mixed Gaussian mould of k-th of characteristic parameter
Shape parameter θk=(πk,μk,Σk), electrical equipment all four is acquired by EM algorithm (EM) for j-th of electrical equipment
The mixed Gauss model parameter of a characteristic parameterJ ∈ [1, D], k ∈ [Isosorbide-5-Nitrae], D indicate electrical equipment
Total quantity；
Step 5: establishing total mixed Gauss model parameter library θ for each electrical equipmentM, total mixed Gauss model parameter library
θMA part be mixed Gauss model parameter by all four characteristic parameters of electrical equipmentStructure
At another part is by the mixed Gauss model parameter of each characteristic parameter of different electrical equipmentsIt
Between be expressed as per mixed Gauss model parameter fused two-by-two with permutation and combination methodj,j'∈[1,
D],Indicate the mixed Gauss model parameter of a characteristic parameter of the jth kth of electrical equipment ' a ', θjj' indicate that j-th of electric appliance is set
Fused mixed Gauss model parameter under the combination of standby and jth ' a electrical equipment, indicates that two electrical equipments work at the same time with this
When mixed Gauss model parameter；
Step 6: inputting one group of characteristic x of the electrical equipment to be identified at certain momenti, successively bring total mixing Gaussian mode into
Shape parameter library θMIn each mixed Gauss model parameter, calculate and obtain probability value p, electricity corresponding to corresponding probability value p maximum
Appliance type of the combination of device equipment or electrical equipment as electrical equipment to be identified.Whole electric appliance identification process of the invention
As shown in Figure 1.
Beneficial effects of the present invention:
The present invention can identify the electric appliance to work instantly according to the data information acquired from domestic electric network where electrical equipment
Type is a kind of effective recognition methods of electrical equipment type.And the present invention is when can identify different appliance type work in combination
Electrical appliance state, being directed to electrical equipment in family has good accuracy and robustness.
Detailed description of the invention
Attached drawing 1 is the flow chart of electric appliance identification process of the present invention.
Attached drawing 2 is the structure chart of embodiment microgrid energy system.
Specific embodiment
Invention is further described in detail with reference to the accompanying drawings and detailed description.
The embodiment and its implementation process implemented according to the complete method of the content of present invention are as follows:
Step 1, Fig. 1 are the structure charts of whole system, and whole system structure includes that network voltage samples preprocessing module, electricity
Net current sample preprocessing module, metering chip, microprocessor and memory module composition.
As shown in Fig. 2, specific implementation uses following electrical equipment data collection system, electrical equipment data collection system packet
Include network voltage sampling preprocessing module, power network current sampling preprocessing module, metering chip, microprocessor and memory；Electricity
The input terminal that net voltage sample preprocessing module, power network current sample preprocessing module is connected to the power grid electricity where electrical equipment
On the road, the output end that network voltage sampling preprocessing module, power network current sample preprocessing module is connected to metering chip, measures
Chip is connected through microprocessor with memory.Preprocessing module, power network current sampling pretreatment are sampled by network voltage respectively
The voltage and current of module acquisition electrical equipment.
Step 2, according to above-mentioned model, the present invention is by taking coffee machine, refrigerator and mobile phone as an example.Corresponding data are obtained,
The data of coffee machine are 14 groups in present invention experiment, and the data of refrigerator are 120 groups, and mobile telephone data is 127 groups, in total 261
Group data.
Step 3 passes through mixed Gauss model, acquires the corresponding gauss hybrid models parameter of three electrical equipments are as follows:
Step 4, the mixed Gauss model parameter obtained according to step 3, establish total mixed Gauss model parameter library θM, this hair
It is bright to assume at most working together there are two electrical equipment simultaneously, therefore the quantity of total mixed Gauss model parameter library is 28
Group.
Step 5, according to experimental data, bring into mixed Gauss model parameter library, acquire corresponding to probability value maximum
Electrical equipment type is to identify appliance type.
The present invention handles 261 groups of data in step 1, and it is remaining less than after the data of average current to remove current value
158 groups of data bring this 158 groups of data into after identification, and the accuracy of identification is 82.3524%.
Claims (5)
1. the electrical equipment kind identification method on a kind of intelligent socket, it is characterised in that: method the following steps are included:
Step 1: the electric signal on acquisition socket is input to metering chip；
Step 2: calculating characteristic parameter using metering chip, characteristic parameter includes that electric current, voltage, active power and reactive power are made
It is characterized；
Step 3: repeating step 1~step 2 and obtain corresponding one group of characteristic of each electrical equipment each moment, i-th group special
Levy data xiIncluding when electric current, voltage, active power and the reactive power inscribed, and establish the mixed Gaussian mould of following formula
Type:
Wherein, p indicates that the probability value of characteristic, i indicate that the group ordinal number of characteristic, m indicate that the group of characteristic is total
Number, k indicate the ordinal number of characteristic parameter；N(xi|μk,Σk) indicate k-th of characteristic parameter in i-th group of characteristic of electrical equipment
Corresponding mixed Gaussian function, πkIt is the weight factor of k-th of characteristic parameter in i-th group of characteristic of electrical equipment, μkIt is electricity
The mean value of k-th of characteristic parameter, Σ in all groups of characteristics of device equipmentkIt is in all groups of characteristics of electrical equipment
The covariance of k characteristic parameter；xiIndicate i-th group of characteristic of electrical equipment；
Step 4: by weight factor πk, mean μkWith covariance ΣkGroup is construed as the mixed Gauss model ginseng of k-th of characteristic parameter
Number θk=(πk,μk,Σk), all four spies of electrical equipment are acquired by EM algorithm (EM) for j-th of electrical equipment
Levy the mixed Gauss model parameter of parameterJ ∈ [1, D], k ∈ [Isosorbide-5-Nitrae], D indicate the total of electrical equipment
Quantity；
Step 5: establishing total mixed Gauss model parameter library θ for electrical equipmentM, total mixed Gauss model parameter library θMOne
It point is the mixed Gauss model parameter by all four characteristic parameters of electrical equipmentIt constitutes, another portion
Dividing is by the mixed Gauss model parameter of each characteristic parameter of different electrical equipmentsBetween with arrangement group
Conjunction mode be expressed as per mixed Gauss model parameter fused two-by-twoJ, j' ∈ [1, D],It indicates
The mixed Gauss model parameter of a characteristic parameter of the jth kth of electrical equipment ' a ', θjj' indicate j-th of electrical equipment and jth ' a
Fused mixed Gauss model parameter under electrical equipment combination；
Step 6: inputting one group of characteristic x of the electrical equipment to be identified at certain momenti, successively bring total mixed Gauss model ginseng into
Number library θMIn each mixed Gauss model parameter, calculate and obtain probability value p, electric appliance corresponding to corresponding probability value p maximum is set
Appliance type of standby or electrical equipment the combination as electrical equipment to be identified.
2. the electrical equipment kind identification method on a kind of intelligent socket according to claim 1, it is characterised in that: described
The ordinal number k of characteristic parameter be taken as k=1-4, k=1 indicates current characteristic parameter, and k=2 indicates voltage characteristic parameter, k=3 table
It is shown with function power features parameter, k=4 indicates reactive power characteristic parameter.
3. the electrical equipment kind identification method on a kind of intelligent socket according to claim 1, it is characterised in that: described
Electrical signal circuitry is converted into the input value range of metering chip before electric signal is input to metering chip by step 1.
4. the electrical equipment kind identification method on a kind of intelligent socket according to claim 1, it is characterised in that: described
Metering chip through network voltage sampling preprocessing module, power network current sampling preprocessing module be connected to where electrical equipment
On mains-power circuit.
5. the electrical equipment kind identification method on a kind of intelligent socket according to claim 1, it is characterised in that: described
Electrical equipment be coffee machine, refrigerator and mobile phone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811074038.8A CN109271925A (en) | 2018-09-14 | 2018-09-14 | A kind of electrical equipment kind identification method on intelligent socket |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811074038.8A CN109271925A (en) | 2018-09-14 | 2018-09-14 | A kind of electrical equipment kind identification method on intelligent socket |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109271925A true CN109271925A (en) | 2019-01-25 |
Family
ID=65188290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811074038.8A Pending CN109271925A (en) | 2018-09-14 | 2018-09-14 | A kind of electrical equipment kind identification method on intelligent socket |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109271925A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580502A (en) * | 2019-08-20 | 2019-12-17 | 上海纺织节能环保中心 | Factor hidden Markov load decomposition method based on Gaussian mixture |
| CN110850220A (en) * | 2019-11-29 | 2020-02-28 | 苏州大学 | Electrical appliance detection method, device and system |
| CN111090014A (en) * | 2019-12-17 | 2020-05-01 | 深圳华建电力物联技术有限公司 | Electrical appliance identification method and device based on Gaussian model |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273920A (en) * | 2017-05-27 | 2017-10-20 | 西安交通大学 | A kind of non-intrusion type household electrical appliance recognition methods based on random forest |
-
2018
- 2018-09-14 CN CN201811074038.8A patent/CN109271925A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273920A (en) * | 2017-05-27 | 2017-10-20 | 西安交通大学 | A kind of non-intrusion type household electrical appliance recognition methods based on random forest |
Non-Patent Citations (1)
| Title |
|---|
| ANTONIO RIDI,ET AL: "《AUTOMATIC IDENTIFICATION OF ELECTRICAL APPLIANCES USING SMART PLUGS》", 《THE 8TH INTERNATIONAL WORKSHOP ON SYSTEMS, SIGNAL PROCESSING AND THEIR APPLICATIONS 2013: SPECIAL SESSIONS》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580502A (en) * | 2019-08-20 | 2019-12-17 | 上海纺织节能环保中心 | Factor hidden Markov load decomposition method based on Gaussian mixture |
| CN110850220A (en) * | 2019-11-29 | 2020-02-28 | 苏州大学 | Electrical appliance detection method, device and system |
| CN111090014A (en) * | 2019-12-17 | 2020-05-01 | 深圳华建电力物联技术有限公司 | Electrical appliance identification method and device based on Gaussian model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110350528A (en) | A kind of low-voltage platform area topology automatic identification method | |
| CN109271925A (en) | A kind of electrical equipment kind identification method on intelligent socket | |
| CN106208041B (en) | A kind of Distribution Network Harmonics current estimation method based on piecewise constant independent component analysis | |
| CN107153150A (en) | A kind of power distribution network over-voltage fault type recognition method and device | |
| CN108074035B (en) | Multi-scene distributed photovoltaic access power distribution network operation risk assessment method | |
| WO2019056753A1 (en) | Dynamic equivalent modeling method for distributed photovoltaic power station cluster | |
| CN105938578A (en) | Large-scale photovoltaic power station equivalent modeling method based on clustering analysis | |
| CN106154163B (en) | Battery life state identification method | |
| CN111628494B (en) | Low-voltage distribution network topology identification method and system based on logistic regression method | |
| CN106771846B (en) | Power transmission line fault phase selection based on fuzzy reasoning pulse nerve membranous system | |
| CN111308260B (en) | Electric energy quality monitoring and electric appliance fault analysis system based on wavelet neural network and working method thereof | |
| CN108073722A (en) | The automatic check device and method of a kind of newly-built substation boss station figure and model | |
| CN112633658A (en) | Low-voltage distribution area topological relation identification method based on CNN-LSTM | |
| CN107091958B (en) | Power transmission line parameter online identification system and identification method thereof | |
| CN103869192A (en) | Smart power grid line loss detection method and system | |
| CN116008714B (en) | Anti-electricity-stealing analysis method based on intelligent measurement terminal | |
| CN103887792B (en) | A kind of low-voltage distribution network modeling method containing distributed power source | |
| CN112819649A (en) | Method and device for determining station area subscriber change relationship | |
| CN109301870A (en) | A kind of more feed-in power system capacity optimization methods of power electronics | |
| CN105974223A (en) | Method used for carrying out on-line detection on electric equipment work state and system thereof | |
| CN113702767B (en) | Island direct-current microgrid fault diagnosis method based on wavelet sliding window energy | |
| CN113205190B (en) | Energy storage safety early warning system of smart power grid | |
| CN106383280B (en) | The voltage transformer Model test Method of line model is maked somebody a mere figurehead based on two nodes | |
| CN109767353A (en) | A kind of photovoltaic power generation power prediction method based on probability-distribution function | |
| CN110190990B (en) | Automatic identification method and device for network topological structure of low-voltage distribution area |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |