CN106443244B - Electrical equipment type discrimination method and system - Google Patents
Electrical equipment type discrimination method and system Download PDFInfo
- Publication number
- CN106443244B CN106443244B CN201610799505.8A CN201610799505A CN106443244B CN 106443244 B CN106443244 B CN 106443244B CN 201610799505 A CN201610799505 A CN 201610799505A CN 106443244 B CN106443244 B CN 106443244B
- Authority
- CN
- China
- Prior art keywords
- electrical equipment
- steady state
- transient
- characteristic vector
- electrical
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention relates to a kind of electrical equipment type discrimination method and systems, wherein method includes the following steps: the first electrical parameter for acquiring various electrical equipments to be identified respectively；Feature extraction is carried out to first electrical parameter, obtains the first steady state characteristic and the first transient characteristic of each electrical equipment, and generate first steady state characteristic vector sum the first transient characteristic vector of each electrical equipment respectively；Acquire the second electrical parameter of each electrical equipment in actual work；Feature extraction is carried out to second electrical parameter and obtains the second steady state characteristic and the second transient characteristic of each electrical equipment, and generates second steady state characteristic vector sum the second transient characteristic vector of each electrical equipment respectively；According to the first steady state characteristic vector of each electrical equipment, the first transient characteristic vector, second steady state characteristic vector sum the second transient characteristic vector, the type identification model for establishing each electrical equipment recognizes the type of electrical equipment, improves the accuracy of electrical equipment type identification.
Description
Technical field
The present invention relates to intelligent power technical fields, more particularly to a kind of electrical equipment type discrimination method and system.
Background technique
With deepening continuously for smart grid development, smart grid field technology also constantly makes a breakthrough, comprising: crucial skill
The research of art and standard, key equipment development, demand side management practices, power grid and user interaction service and marketing automation system
Construction etc., wherein the research of key technology and standard includes: that power information acquisition system, intelligent electric energy meter, electric car fill
Key technology research such as electric equipment and facility, power optical fiber to family etc., and formulated power information acquisition technique field and electricity
The company standards such as electrical automobile charge and discharge electro-technical field.
Power load electricity consumption monitoring and recognition methods are always the key technology of intelligent power field, and are also to use telecommunications
Cease the important technology of acquisition system.Traditional power load monitoring method is: first installing power information for each electrical equipment and adopts
Collect sensor, then the power load of each region is monitored with monitoring master station communication by indoor WLAN.
But the power load of this intrusive mood monitoring system Construction higher cost, operation and maintenance difficulty, while may
Shadow is caused to user's production and living；In addition, power information acquisition sensor and monitoring main website carry out data using WLAN
Communicate meeting so that user power utilization information there are security risks.Although non-intrusion type power load identification system and side has been proposed
Method, however, with electrical equipment type gradually increase and the continuous complication of used technology, existing power load are distinguished
Knowledge method is it is difficult to ensure that the accuracy of non-intrusion type power load identification system.
Shown in sum up, the accuracy of existing power load discrimination method is lower.
Summary of the invention
Based on this, it is necessary to for the lower technical problem of the accuracy of existing electrical equipment load discrimination method, mention
For a kind of electrical equipment type discrimination method and system.
A kind of electrical equipment type discrimination method, includes the following steps:
The first electrical parameter of various electrical equipments to be identified is acquired respectively；Wherein, first electrical parameter includes electricity consumption
Voltage, electric current, active power waveform and reactive power waveform of the equipment in unlatching, stable operation and shut-down process；
Feature extraction is carried out to first electrical parameter, obtains the first steady state characteristic and the first transient state of each electrical equipment
Feature, and according to first steady state characteristic and the first transient characteristic generate respectively the first steady state characteristic of each electrical equipment to
Amount and the first transient characteristic vector；
Acquire the second electrical parameter of each electrical equipment in actual work；Wherein, second electrical parameter includes using
Active power waveform and reactive power waveform when electric equipment works；
Feature extraction is carried out to second electrical parameter and obtains the second steady state characteristic and the second transient state of each electrical equipment
Feature, and according to second steady state characteristic and the second transient characteristic generate respectively the second steady state characteristic of each electrical equipment to
Amount and the second transient characteristic vector；
According to the first steady state characteristic vector, the first transient characteristic vector, the second steady state characteristic vector of each electrical equipment
With the second transient characteristic vector, the type identification model of each electrical equipment is established, and using type identification model to each
The type of a electrical equipment is recognized.
Above-mentioned electrical equipment type discrimination method, by acquiring various electrical equipments to be identified in unlatching, stable operation
With voltage, electric current, active power waveform and the reactive power waveform in shut-down process, and to above-mentioned parameter carry out feature extraction obtain
To the first steady state characteristic and the first transient characteristic of each electrical equipment, and it is special according to first steady state characteristic and the first transient state
Sign generates first steady state characteristic vector sum the first transient characteristic vector of each electrical equipment respectively；Then, it acquires described each
The active power waveform and reactive power waveform of electrical equipment in actual work, and feature extraction is carried out to above-mentioned parameter and is obtained respectively
The second steady state characteristic and the second transient characteristic of a electrical equipment, and according to second steady state characteristic and the second transient characteristic point
Second steady state characteristic vector sum the second transient characteristic vector of each electrical equipment is not generated；Finally, according to each electrical equipment
The first steady state characteristic vector, the first transient characteristic vector, second steady state characteristic vector sum the second transient characteristic vector, establish each
The type of a electrical equipment recognizes model, and is recognized using type identification model to the type of each electrical equipment.
Electrical equipment type discrimination method of the invention passes through the active power waveform and reactive power of each electrical equipment to acquisition
The analysis of waveform realizes the type identification to electrical equipment, improves the accuracy of electrical equipment type identification.
A kind of electrical equipment type identification system, comprising:
First acquisition module, for acquiring the first electrical parameter of various electrical equipments to be identified respectively；Wherein, described
One electrical parameter includes voltage of the electrical equipment in unlatching, stable operation and shut-down process, electric current, active power waveform and idle
Power waveform；
First extraction module obtains the first of each electrical equipment for carrying out feature extraction to first electrical parameter
Steady state characteristic and the first transient characteristic, and each electricity consumption is generated according to first steady state characteristic and the first transient characteristic respectively and is set
First standby steady state characteristic vector sum the first transient characteristic vector；
Second acquisition module, for acquiring the second electrical parameter of each electrical equipment in actual work；Wherein, described
Active power waveform and reactive power waveform when second electrical parameter includes electrical equipment work；
Second extraction module obtains the second steady of each electrical equipment for carrying out feature extraction to second electrical parameter
State feature and the second transient characteristic, and each electrical equipment is generated according to second steady state characteristic and the second transient characteristic respectively
Second steady state characteristic vector sum the second transient characteristic vector；
Module is recognized, for the first steady state characteristic vector, the first transient characteristic vector, second according to each electrical equipment
Steady state characteristic vector sum the second transient characteristic vector, establishes the type identification model of each electrical equipment, and utilizes the type
Identification model recognizes the type of each electrical equipment.
Above-mentioned electrical equipment type identification system acquires various electrical equipments to be identified by first time acquisition module and exists
Unlatching, stable operation and voltage, electric current, active power waveform and reactive power waveform in shut-down process, and mentioned using first
Modulus block carries out feature extraction to above-mentioned parameter and obtains the first steady state characteristic and the first transient characteristic of each electrical equipment, and root
Generate the first steady state characteristic vector sum first of each electrical equipment respectively according to first steady state characteristic and the first transient characteristic
Transient characteristic vector；Then, the active power wave of each electrical equipment in actual work is acquired by the second acquisition module
Shape and reactive power waveform, and feature extraction is carried out to above-mentioned parameter using the second extraction module and obtains the of each electrical equipment
Two steady state characteristics and the second transient characteristic, and each electricity consumption is generated according to second steady state characteristic and the second transient characteristic respectively
Second steady state characteristic vector sum the second transient characteristic vector of equipment；Finally, by identification module according to each electrical equipment
First steady state characteristic vector, the first transient characteristic vector, second steady state characteristic vector sum the second transient characteristic vector, are established each
The type of electrical equipment recognizes model, and is recognized using type identification model to the type of each electrical equipment.This
The electrical equipment type identification system of invention passes through the active power waveform and reactive power wave of each electrical equipment to acquisition
The analysis of shape realizes the type identification to electrical equipment, improves the accuracy of power load identification.
Detailed description of the invention
Fig. 1 is the electrical equipment type discrimination method flow chart of one of embodiment of the invention；
Fig. 2 is the electrical equipment type discrimination method flow chart of another embodiment of the invention；
Fig. 3 is the structural schematic diagram of the electrical equipment type identification system of one of embodiment of the invention；
Fig. 4 is the structural schematic diagram of the electrical equipment type identification system of another embodiment of the invention.
Specific embodiment
In order to further illustrate the effect of technological means adopted by the present invention and acquirement, with reference to the accompanying drawing and preferably
Embodiment carries out clear and complete description to technical solution of the present invention.
As shown in FIG. 1, FIG. 1 is the electrical equipment type discrimination method flow chart of one of embodiment of the invention, packets
Include following steps:
Step S101: the first electrical parameter of various electrical equipments to be identified is acquired respectively；Wherein, first electrical parameter
Voltage, electric current, active power waveform and reactive power wave including electrical equipment in unlatching, stable operation and shut-down process
Shape；
In this step, by acquiring first of the electrical equipment including active power waveform and reactive power waveform
Electrical parameter is also provided for laying a good foundation for the feature extraction of subsequent step for accurate recognition electrical equipment type hereinafter
Reliable data reference is the important step for improving electrical equipment type identification precision.
Step S102: feature extraction is carried out to first electrical parameter, obtains the first steady state characteristic of each electrical equipment
With the first transient characteristic, and the first of each electrical equipment is generated respectively according to first steady state characteristic and the first transient characteristic
Steady state characteristic vector sum the first transient characteristic vector；Wherein, the first steady state characteristic vector sum the first transient characteristic vector structure
At first eigenvector；
In this step, feature extraction is carried out by the first electrical parameter to each electrical equipment, obtains each electricity consumption and sets
Standby the first steady state characteristic and the first transient characteristic, and according to described and according to first steady state characteristic and the first transient characteristic
First steady state characteristic vector sum the first transient characteristic vector of each electrical equipment is generated respectively.It should be noted that this step
Described in first the first transient characteristic of steady state characteristic vector sum vector respectively by the steady state characteristic and transient state of each electrical equipment
Feature composition, it may also be said to, first steady state characteristic vector sum the first transient characteristic vector described in this step constitutes each
The feature database of electrical equipment, each of first steady state characteristic vector sum the first transient characteristic vector element all represent certain class
The characteristic value of electrical equipment, therefore, the present invention pass through each electrical equipment of acquisition in the in actual work in the next steps
Two electrical parameters, and second steady state characteristic vector sum the second transient characteristic vector is further obtained, and then to each electrical equipment class
Type is recognized, and is finally recognized to the power load in some region, and to find fortuitous event as early as possible, danger coefficient is dropped
To minimum.
Step S103: the second electrical parameter of acquisition each electrical equipment in actual work；Wherein, the second electricity ginseng
Number includes voltage, electric current, active power waveform and the reactive power waveform of electrical equipment in actual work；
In practical applications, some region can be selected, and acquires of the electrical equipment in the region in actual work
Two electrical parameters, it is important to note that including the available power waveform of corresponding electrical equipment and useless in the second electrical parameter
Power waveform, furthermore it is also possible to include the parameters such as voltage, electric current.In this step, pass through the available power of acquisition electrical equipment
Waveform and useless power waveform carry out feature extraction to these parameters for subsequent step, obtain the of each electrical equipment
Two steady state characteristic vector sum the second transient characteristic vectors, for it is final to each electrical equipment type carry out identification provide it is reliable
Reference frame.
In practical applications, the first electrical parameter described in step S101 can be recognizes to electrical equipment type
It just obtains and is stored in advance before, and the second electrical parameter described in step S103 is carried out to electrical equipment type
It is obtained in real time online during identification.
Step S104: to second electrical parameter carry out feature extraction obtain each electrical equipment the second steady state characteristic and
Second transient characteristic, and the second steady of each electrical equipment is generated according to second steady state characteristic and the second transient characteristic respectively
State feature vector and the second transient characteristic vector；Wherein, the second steady state characteristic vector sum the second transient characteristic vector is constituted
Second feature vector；
In this step, feature extraction is carried out by the second electrical parameter to electrical equipment and obtains the of each electrical equipment
Two steady state characteristics and the second transient characteristic, and each electricity consumption is generated according to second steady state characteristic and the second transient characteristic respectively
Second steady state characteristic vector sum the second transient characteristic vector of equipment.It should be noted that the second stable state described in this step
Feature vector and the second transient characteristic vector are made of the steady state characteristic and transient characteristic of each electrical equipment actual motion respectively,
It may also be said that second steady state characteristic vector sum the second transient characteristic vector described in this step constitutes each electrical equipment
The feature database of actual motion state, each of second steady state characteristic vector sum the second transient characteristic vector element all represent
The characteristic value of certain class electrical equipment some parameter in actual motion, for being carried out to each electrical equipment type for subsequent step
Identification, finally recognizes the power load in some region, to find fortuitous event as early as possible, danger coefficient is dropped to most
It is low.
Step S105: according to the first steady state characteristic vector of each electrical equipment, the first transient characteristic vector, the second stable state
Feature vector and the second transient characteristic vector, establish the type identification model of each electrical equipment, and are recognized using the type
Model recognizes the type of each electrical equipment.
In this step, surely according to the first steady state characteristic vector of each electrical equipment, the first transient characteristic vector, second
State feature vector and the second transient characteristic vector, establish the type identification model of each electrical equipment, and are distinguished using the type
Know model to recognize the type of each electrical equipment.It should be noted that the input parameter of type identification model is vector,
Final output is also vector, the vector being made of the similarity of electrical equipment type.Therefore, in practical applications, if knowing
Road inputs the value minimum of which element in the output vector after some parameter, then exports the index of the element, that is, know
Road index, has also been known that electrical equipment type corresponding with the parameter.
In practical applications, since the first electrical parameter includes electrical equipment in unlatching, stable operation and shut-down process
Voltage, electric current, active power waveform and reactive power waveform, to the first electrical parameter carry out feature extraction after obtain first
Steady state characteristic vector sum the first transient characteristic vector equally includes operating parameter of the electrical equipment in each state, therefore,
The operating status of each electrical equipment can also equally be picked out by recognizing model according to the type of foundation.
Above-mentioned electrical equipment type discrimination method, by acquiring various electrical equipments to be identified in unlatching, stable operation
With voltage, electric current, active power waveform and the reactive power waveform in shut-down process, and to above-mentioned parameter carry out feature extraction obtain
To the first steady state characteristic and the first transient characteristic of each electrical equipment, and it is special according to first steady state characteristic and the first transient state
Sign generates first steady state characteristic vector sum the first transient characteristic vector of each electrical equipment respectively；Then, it acquires described each
Voltage, electric current, active power waveform and the reactive power waveform of electrical equipment in actual work, and feature is carried out to above-mentioned parameter
Extraction obtains the second steady state characteristic and the second transient characteristic of each electrical equipment, and according to second steady state characteristic and second
Transient characteristic generates second steady state characteristic vector sum the second transient characteristic vector of each electrical equipment respectively；Finally, according to each
First steady state characteristic vector of a electrical equipment, the first transient characteristic vector, second the second transient characteristic of steady state characteristic vector sum
Vector establishes the type identification model of each electrical equipment, and using type identification model to the class of each electrical equipment
Type is recognized.Electrical equipment type discrimination method of the invention passes through the active power wave of each electrical equipment to acquisition
The analysis of shape and reactive power waveform realizes the type identification to electrical equipment, improves the standard of electrical equipment type identification
Exactness.
Electrical equipment type discrimination method of the invention, the type of the electrical equipment are distinguished in one of the embodiments,
It is as follows to know model:
In formula,Indicate the first eigenvector and each electrical equipment in actual work by electrical equipment to be identified
Second feature vector between similarity constitute vector, K1、K2Indicate real number, and K1+K2=1,It indicates by wait distinguish
First steady state characteristic vector sum of the electrical equipment of knowledge is in actual work between the second steady state characteristic vector of each electrical equipment
Similarity constitute vector,It indicates each in actual work by the first transient characteristic vector sum of electrical equipment to be identified
The vector that similarity between second transient characteristic vector of electrical equipment is constituted,Indicate the second steady of each electrical equipment
State feature vector,Indicate the second steady state characteristic vector of K electrical equipment,Indicate K
First steady state characteristic vector of a electrical equipmentWith the second steady state characteristic vector of the electrical equipmentBetween difference to
Amount,Indicate transient characteristic that m section in all M transient state segmentation of each electrical equipment of histogram feature parameter forms to
Amount,Indicate m sections of histogram feature parameter composition in all M transient state segmentations of K electrical equipment
Second transient characteristic vector, M'PIndicate the number of active relevant parameter in subvector, M'QIndicate idle relevant parameter in subvector
Number.
The stable state of electrical equipment type discrimination method of the invention in one of the embodiments, the electrical equipment is special
Sign includes: active power, reactive power, power-factor angle, odd harmonic electric current under the electrical equipment steady operational status
With the phase difference and Current harmonic distortion rate of fundamental current.
In practical applications, the K1 and K2 in formula (1), preferably 0.5, so that the steady state characteristic similarity of electrical equipment
Influence with transient characteristic similarity to electrical equipment type is consistent, improves the accuracy of identification.It should be noted that formula
(1) inWithIndicate vector, for popular, R is the first eigenvector and reality by electrical equipment to be identified
The vector of similarity composition in the application of border between the second feature vector of each electrical equipment, for example, R=0.001,
0.002, corresponding each numerical value 0.012,0.201 }, and in R is electrical equipment and " electromagnetic oven, micro-wave oven, ice to be identified
Similarity between case, washing machine ", in the identification model pre-established, R can export the corresponding rope of the smallest element of similarity
Draw, by taking the numerical value of above-mentioned R vector as an example, similarity it is minimum be " 0.001 ", corresponding index is 0, then, the index is corresponding
The type of electrical equipment be exactly " electromagnetic oven ".
Electricity consumption when formula (2) is used to calculate the first steady state characteristic vector sum actual motion in electrical equipment feature database is set
Steady state characteristic similarity between the second standby steady state characteristic vector, wherein vector RWFirst elementWhat is calculated is the first steady state characteristic vector of the 1st electrical equipment in electrical equipment feature databaseWith with
The second steady state characteristic vector when the actual motion of electric equipmentBetween steady state characteristic similarity, other elements are same,
It should be noted that the latter half in formula (2), by by the first steady state characteristic vectorWith the second steady state characteristic vectorIn the absolute value of the difference of 5 steady state characteristic parameters be added, the steady state characteristic similarity both finally obtained.Utilize root
According to the steady state characteristic similarity that formula (2) is calculated, the accuracy rate of the electrical equipment type finally recognized is higher, this is also
The present invention improves identification precision critical step.
In the above-described embodiments, the n in formula (2) indicates the number of parameters of the steady state characteristic of electrical equipment, in this implementation
Define that the steady state characteristic of electrical equipment includes active power, reactive power, power-factor angle, odd harmonic electric current and base in example
5 parameters such as the phase difference of wave electric current and Current harmonic distortion rate, therefore, the value of n is 1 to 5 in formula (2).In reality
In, if the value range for increasing the perhaps number of parameters n of reduction electrical equipment steady state characteristic also increase accordingly or subtracts
It is few.
Electricity consumption when formula (3) is used to calculate the first transient characteristic vector sum actual motion in electrical equipment feature database is set
Transient characteristic similarity between the second standby transient characteristic vector, likewise, vectorFirst elementWhat is calculated is the first transient characteristic vector of the 1st electrical equipment in electrical equipment feature database
With the second transient characteristic vector of electrical equipment corresponding when actual motionBetween transient characteristic similarity, whereinWithRespectively indicate the subvector of m sections of histogram feature parameter composition in all M transient state segmentations, M'PIt indicates in subvector
The number of active relevant parameter, M'QIndicate the number of idle relevant parameter in subvector.
Electrical equipment type discrimination method of the invention in one of the embodiments, it is described that the electrical parameter is carried out
Feature extraction, the step of obtaining the steady state characteristic of each electrical equipment may include:
In formula, P indicates the active power of electrical equipment, UhIndicate h subharmonic voltage virtual value, IhIndicate h subharmonic
Current effective value, θhIndicating that h subharmonic current lags the phase of the subharmonic voltage, Q indicates the reactive power of electrical equipment,Indicate that the power-factor angle of electrical equipment, arctan () indicate arctan function, αidxIndicate the odd harmonic electricity of electrical equipment
Stream and fundamental current phase difference, idx=[(h_odd-1)/2] ∈ { 1,2,3 ... }, h_odd ∈ { 1,3,5,7 ... } indicate that electric current is humorous
Wave number, β1Indicate the fundamental current phase of electrical equipment, ITHDIndicate current harmonics total harmonic distortion,Table
Show the current effective value of electrical equipment.
In the above-described embodiments, feature is carried out by the electrical parameter under each electrical equipment steady operational status to acquisition
It extracts, the steady state characteristic of each electrical equipment is obtained, for recognizing to the type of electrical equipment for subsequent step.It needs
It is bright, the electrical parameter that acquires in electrical equipment discrimination method of the invention while containing active power waveform and reactive power
Waveform, which greatly improves the accuracy of electrical equipment type identification.
As shown in Fig. 2, Fig. 2 is the electrical equipment type discrimination method flow chart of another embodiment of the invention, it is described
The step S102 for generating the first transient characteristic vector of each electrical equipment may include:
Step S1021: active power waveform and reactive power of each electrical equipment in unlatching or shut-down process are recorded
Waveform；
Step S1022: the active power waveform and reactive power waveform are carried out by discrete sheet according to the sampling period respectively
Show, for example, the active power waveform and reactive power waveform can be expressed as follows:
Step S1023: the active power waveform and reactive power waveform are divided into M sections respectively, obtain active power wave
The sequence segment of shape and reactive power waveform, still for above formula, the sequence segment after segmentation is expressed as follows:
Step S1024: histogram sequence point is carried out to the sequence segment of the active power waveform and reactive power waveform
Analysis, obtains the first transient characteristic vector of each electrical equipment.
In the above-described embodiments, by aforesaid operations, electrical equipment type discrimination method of the invention, which realizes to treat, to be distinguished
The extraction of the transient characteristic of the electrical equipment of knowledge.
Electrical equipment type discrimination method of the invention in one of the embodiments, it is described to second electrical parameter
Carrying out the step of feature extraction obtains the second steady state characteristic and the second transient characteristic of each electrical equipment can also include:
According to second electrical parameter, the initial time of each electrical equipment transient process is judged；
Extract the second steady state characteristic and the second transient characteristic of each electrical equipment.
When can in the following way, judge the starting of each electrical equipment transient process in one of the embodiments,
It carves:
According to second electrical parameter, the duration of each electrical equipment transient power waveform is judged；
According to the duration of each electrical equipment transient power waveform, the analysis data of each electrical equipment are selected
Window length W0(the power data point number for including in data window)；
Using the analysis data window length of each electrical equipment, the initial time of each electrical equipment transient process is judged.
In practical applications, the maximum active power that i-th of data window Yu i+1 data window can be calculated separately, when
The absolute value of the difference of maximum active power is more than preset active power threshold k in former and later two data windows2When
It determines in i+1 data window, electrical equipment is in transient process, then judges electrical equipment in i-th of data window
Transient process start time.
The analysis data window length using each electrical equipment in one of the embodiments, judges each electricity consumption
The step of initial time of equipment transient process may include:
Successively record the wattful power of j-th of sampling time point and j+1 sampling time point in each electrical equipment data window
Rate, and calculate difference between the two；
When the difference is more than preset active power threshold k2When, determine that sampling time point j is corresponding uses
The initial time of electric equipment transient process.
In practical applications, electrical equipment type discrimination method of the invention, can be since electrical equipment transient process
The power difference at two neighboring moment in active power waveform time sequence is recorded in a sequence S by the moment0In, when
Sequence S0Some subsequence S1In the value of element be respectively less than and set active power threshold K3, and subsequence S1Length it is big
In analysis data window length W0Half, that is, can determine whether subsequence S1Electrical equipment is in stable state in the corresponding period, that is,
It says, subsequence S1First element be the initial time of steady-state process and the end time of transient process at the time of correspond to,
And the last one element is the end time of steady-state process at the time of correspond to, and therefore, can according to need and extracts electrical equipment
Steady state characteristic and transient state is active and reactive power waveform time sequence P and Q, and calculate separately transient state active power and idle
Power features value, moreover, the transient-wave length of time series when electrical equipment is less than time threshold T1When, judge this transient state mistake
Journey is shut-down process, is otherwise opening process.
Electrical equipment type discrimination method of the invention in one of the embodiments, it is described according to the described each of foundation
Type identification model the step of recognizing to the type of each electrical equipment of a electrical equipment includes:
Model is recognized according to the type of each electrical equipment of foundation, electrical equipment index is calculated；
Electrical equipment index is input in the electrical equipment library being made of each electrical equipment, comparison is acquired
The second electrical parameter corresponding to electrical equipment type.
In practical applications, the present invention is according to steady state characteristic similarity and transient characteristic similarity calculation as a result, output is comprehensive
Close the highest electrical equipment index of similarity, i.e. realization power load type and operating status on-line identification.
As shown in figure 3, Fig. 3 is the structural representation of the electrical equipment type identification system of another embodiment of the invention
Figure, comprising:
First acquisition module 101, for acquiring the first electrical parameter of various electrical equipments to be identified respectively；Wherein, institute
State the first electrical parameter include voltage of the electrical equipment in unlatching, stable operation and shut-down process, electric current, active power waveform and
Reactive power waveform；
In the first acquisition module 101, by acquiring the electricity consumption including active power waveform and reactive power waveform
First electrical parameter of equipment, the feature extraction of rear subsequent step are laid a good foundation, and are also accurate recognition electrical equipment type hereinafter
Reliable data reference is provided, is the important step for improving electrical equipment type identification precision.
First extraction module 102 obtains the of each electrical equipment for carrying out feature extraction to first electrical parameter
One steady state characteristic and the first transient characteristic, and each electricity consumption is generated according to first steady state characteristic and the first transient characteristic respectively
First steady state characteristic vector sum the first transient characteristic vector of equipment；
In the first extraction module 102, feature extraction is carried out by the first electrical parameter to each electrical equipment, is obtained each
The first steady state characteristic and the first transient characteristic of a electrical equipment, and according to described and according to first steady state characteristic and first
Transient characteristic generates first steady state characteristic vector sum the first transient characteristic vector of each electrical equipment respectively.It needs to illustrate
It is that first the first transient characteristic of steady state characteristic vector sum vector described in this step is special by the stable state of each electrical equipment respectively
Transient characteristic of seeking peace composition, it may also be said to, first steady state characteristic vector sum the first transient characteristic vector structure described in this step
At the feature database of each electrical equipment, each of first steady state characteristic vector sum the first transient characteristic vector element all generations
Table the characteristic value of certain class electrical equipment, therefore, the present invention passes through each electrical equipment of acquisition in practical work in the next steps
The second electrical parameter when making, and second steady state characteristic vector sum the second transient characteristic vector is further obtained, and then to each use
Electric equipment type is recognized, and is finally recognized to the power load in some region, to find fortuitous event as early as possible, will be endangered
Dangerous coefficient is preferably minimized.
Second acquisition module 103, for acquiring the second electrical parameter of each electrical equipment in actual work；Wherein,
Second electrical parameter includes voltage, electric current, active power waveform and the reactive power waveform of electrical equipment in actual work；
In practical applications, some region can be selected, and acquires of the electrical equipment in the region in actual work
Two electrical parameters, it is important to note that including the available power waveform of corresponding electrical equipment and useless in the second electrical parameter
Power waveform, furthermore it is also possible to include the parameters such as voltage, electric current.In this step, pass through the available power of acquisition electrical equipment
Waveform and useless power waveform carry out feature extraction to these parameters for subsequent step, obtain the of each electrical equipment
Two steady state characteristic vector sum the second transient characteristic vectors, for it is final to each electrical equipment type carry out identification provide it is reliable
Reference frame.
Second extraction module 104 obtains the of each electrical equipment for carrying out feature extraction to second electrical parameter
Two steady state characteristics and the second transient characteristic, and each electricity consumption is generated according to second steady state characteristic and the second transient characteristic respectively
Second steady state characteristic vector sum the second transient characteristic vector of equipment；
In the second extraction module 104, feature extraction is carried out by the second electrical parameter to electrical equipment and obtains each use
The second steady state characteristic and the second transient characteristic of electric equipment, and given birth to respectively according to second steady state characteristic and the second transient characteristic
At second steady state characteristic vector sum the second transient characteristic vector of each electrical equipment.It should be noted that described in this step
Second the second transient characteristic of steady state characteristic vector sum vector respectively by the steady state characteristic of each electrical equipment actual motion and temporarily
State feature composition, it may also be said to, second steady state characteristic vector sum the second transient characteristic vector described in this step constitutes respectively
The feature database of a electrical equipment actual motion state, each of second steady state characteristic vector sum the second transient characteristic vector member
Element all represents the characteristic value of certain class electrical equipment some parameter in actual motion, for setting to each electricity consumption for subsequent step
Standby type is recognized, and is finally recognized to the power load in some region, to find fortuitous event as early as possible, is by danger
Number is preferably minimized.
Recognize module 105, for according to the first steady state characteristic vector of each electrical equipment, the first transient characteristic vector,
Second steady state characteristic vector sum the second transient characteristic vector establishes the type identification model of each electrical equipment, and described in utilization
Type identification model recognizes the type of each electrical equipment.
Identification module 105 in, according to the first steady state characteristic vector of each electrical equipment, the first transient characteristic vector,
Second steady state characteristic vector sum the second transient characteristic vector establishes the type identification model of each electrical equipment, and described in utilization
Type identification model recognizes the type of each electrical equipment.It should be noted that the input parameter of type identification model
It is vector, final output is also vector, the vector being made of electrical equipment type.Therefore, in practical applications, if it is known that
Input the output after some parameter the result is that vector which element, that is, the index of vector has also been known that and the ginseng
The corresponding electrical equipment type of number.
In practical applications, since the first electrical parameter includes electrical equipment in unlatching, stable operation and shut-down process
Voltage, electric current, active power waveform and reactive power waveform, to the first electrical parameter carry out feature extraction after obtain first
Steady state characteristic vector sum the first transient characteristic vector equally includes operating parameter of the electrical equipment in each state, therefore,
The operating status of each electrical equipment can also equally be picked out by recognizing model according to the type of foundation.
Above-mentioned electrical equipment type identification system acquires various electricity consumptions to be identified by first time acquisition module 101 and sets
Standby voltage, electric current, active power waveform and reactive power waveform in unlatching, stable operation and shut-down process, and utilize the
One extraction module 102 carries out feature extraction to above-mentioned parameter and obtains the first steady state characteristic and the first transient state spy of each electrical equipment
It levies, and generates the first steady state characteristic vector of each electrical equipment respectively according to first steady state characteristic and the first transient characteristic
With the first transient characteristic vector；Then, each electrical equipment having in actual work is acquired by the second acquisition module 103
Function power waveform and reactive power waveform, and using the second extraction module 104 to above-mentioned parameter carry out feature extraction obtain it is each
The second steady state characteristic and the second transient characteristic of electrical equipment, and distinguished according to second steady state characteristic and the second transient characteristic
Generate second steady state characteristic vector sum the second transient characteristic vector of each electrical equipment；Finally, passing through identification 105 basis of module
First steady state characteristic vector of each electrical equipment, the first transient characteristic vector, second the second transient state of steady state characteristic vector sum are special
Vector is levied, establishes the type identification model of each electrical equipment, and using type identification model to each electrical equipment
Type is recognized.Electrical equipment type identification system of the invention passes through the active power of each electrical equipment to acquisition
The analysis of waveform and reactive power waveform realizes the type identification to electrical equipment, improves the accurate of power load identification
Degree.
Electrical equipment type identification system of the invention, the type of the electrical equipment are distinguished in one of the embodiments,
It is as follows to know model:
In formula,Indicate the first eigenvector and each electrical equipment in actual work by electrical equipment to be identified
Second feature vector between similarity constitute vector, K1、K2Indicate real number, and K1+K2=1,It indicates by wait distinguish
First steady state characteristic vector sum of the electrical equipment of knowledge is in actual work between the second steady state characteristic vector of each electrical equipment
Similarity constitute vector,It indicates each in actual work by the first transient characteristic vector sum of electrical equipment to be identified
The vector that similarity between second transient characteristic vector of a electrical equipment is constituted,Indicate the second of each electrical equipment
Steady state characteristic vector,Indicate the second steady state characteristic vector of K electrical equipment,Indicate K
First steady state characteristic vector of a electrical equipmentWith the second steady state characteristic vector of the electrical equipmentBetween difference to
Amount,Indicate transient characteristic that m section in all M transient state segmentation of each electrical equipment of histogram feature parameter forms to
Amount,Indicate m sections of histogram feature parameter composition in all M transient state segmentations of K electrical equipment
Second transient characteristic vector, M'PIndicate the number of active relevant parameter in subvector, M'QIndicate idle relevant parameter in subvector
Number.
The stable state of electrical equipment type identification system of the invention in one of the embodiments, the electrical equipment is special
Sign includes: active power, reactive power, power-factor angle, odd harmonic electric current under the electrical equipment steady operational status
With the phase difference and Current harmonic distortion rate of fundamental current.
In practical applications, the K1 and K2 in formula (1), preferably 0.5, so that the steady state characteristic similarity of electrical equipment
Influence with transient characteristic similarity to electrical equipment type is consistent, improves the accuracy of identification.It should be noted that formula
(1) inWithIndicate vector, for popular, R is the first eigenvector and reality by electrical equipment to be identified
The vector of similarity composition in the application of border between the second feature vector of each electrical equipment, for example, R=0.001,
0.002, corresponding each numerical value 0.012,0.201 }, and in R is electrical equipment and " electromagnetic oven, micro-wave oven, ice to be identified
Similarity between case, washing machine ", in the identification model pre-established, R can export the corresponding rope of the smallest element of similarity
Draw, by taking the numerical value of above-mentioned R vector as an example, similarity it is minimum be " 0.001 ", corresponding index is 0, then, the index is corresponding
The type of electrical equipment be exactly " electromagnetic oven ".
Formula (2) is used to calculate electricity consumption when the first steady state characteristic vector sum actual motion in electrical equipment feature database
Steady state characteristic similarity between second steady state characteristic vector of equipment, wherein vector RWFirst elementWhat is calculated is the first steady state characteristic vector of the 1st electrical equipment in electrical equipment feature databaseWith electricity consumption
The second steady state characteristic vector when the actual motion of equipmentBetween steady state characteristic similarity, other elements are same, need
It should be noted that the latter half in formula (2), by by the first steady state characteristic vectorWith the second steady state characteristic vector
In the absolute value of the difference of 5 steady state characteristic parameters be added, the steady state characteristic similarity both finally obtained.Using according to public affairs
The steady state characteristic similarity that formula (2) is calculated, the accuracy rate of the electrical equipment type finally recognized is higher, this is also this hair
Bright raising identification precision critical step.
In the above-described embodiments, the n in formula (2) indicates the number of parameters of the steady state characteristic of electrical equipment, in this implementation
Define that the steady state characteristic of electrical equipment includes active power, reactive power, power-factor angle, odd harmonic electric current and base in example
5 parameters such as the phase difference of wave electric current and Current harmonic distortion rate, therefore, the value of n is 1 to 5 in formula (2).In reality
In, if the value range for increasing the perhaps number of parameters n of reduction electrical equipment steady state characteristic also increase accordingly or subtracts
It is few.
Electricity consumption when formula (3) is used to calculate the first transient characteristic vector sum actual motion in electrical equipment feature database is set
Transient characteristic similarity between the second standby transient characteristic vector, likewise, vectorFirst elementWhat is calculated is the first transient characteristic vector of the 1st electrical equipment in electrical equipment feature database
With the second transient characteristic vector of electrical equipment corresponding when actual motionBetween transient characteristic similarity, whereinWithRespectively indicate the subvector of m sections of histogram feature parameter composition in all M transient state segmentations, M'PIt indicates in subvector
The number of active relevant parameter, M'QIndicate the number of idle relevant parameter in subvector.
Electrical equipment type identification system of the invention in one of the embodiments, first extraction module 102 is also
For carrying out feature extraction to the electrical parameter, obtaining the steady state characteristic of each electrical equipment:
In formula, P indicates the active power of electrical equipment, UhIndicate h subharmonic voltage virtual value, IhIndicate h subharmonic
Current effective value, θhIndicating that h subharmonic current lags the phase of the subharmonic voltage, Q indicates the reactive power of electrical equipment,Indicate that the power-factor angle of electrical equipment, arctan () indicate arctan function, αidxIndicate the odd harmonic electricity of electrical equipment
Stream and fundamental current phase difference, idx=[(h_odd-1)/2] ∈ { 1,2,3 ... }, h_odd ∈ { 1,3,5,7 ... } indicate that electric current is humorous
Wave number, β1Indicate the fundamental current phase of electrical equipment, ITHDIndicate current harmonics total harmonic distortion,Table
Show the current effective value of electrical equipment.
In the above-described embodiments, feature is carried out by the electrical parameter under each electrical equipment steady operational status to acquisition
It extracts, the steady state characteristic of each electrical equipment is obtained, for recognizing to the type of electrical equipment for subsequent step.It needs
It is bright, the electrical parameter that acquires in electrical equipment discrimination method of the invention while containing active power waveform and reactive power
Waveform, which greatly improves the accuracy of electrical equipment type identification.
As shown in figure 4, Fig. 4 is the structural representation of the electrical equipment type identification system of another embodiment of the invention
Figure, first extraction module 102 may include:
Logging modle 1021, for recording active power waveform and nothing of each electrical equipment in unlatching or shut-down process
Function power waveform；
Discrete block 1022, for being carried out the active power waveform and reactive power waveform respectively according to the sampling period
Discrete representation, for example, the active power waveform and reactive power waveform can be expressed as follows:
Segmentation module 1023 is had for the active power waveform and reactive power waveform to be divided into M sections respectively
The sequence segment of function power waveform and reactive power waveform, still for above formula, the sequence segment after segmentation is expressed as follows:
Analysis module 1024 carries out histogram for the sequence segment to the active power waveform and reactive power waveform
Sequence analysis, obtains the first transient characteristic vector of each electrical equipment.
In the above-described embodiments, by aforesaid operations, electrical equipment type identification system of the invention, which realizes to treat, to be distinguished
The extraction of the transient characteristic of the electrical equipment of knowledge.
Electrical equipment type identification system of the invention in one of the embodiments, second extraction module 104 is also
It can be used for:
According to second electrical parameter, the initial time of each electrical equipment transient process is judged；
Extract the second steady state characteristic and the second transient characteristic of each electrical equipment.
When can in the following way, judge the starting of each electrical equipment transient process in one of the embodiments,
It carves:
According to second electrical parameter, the duration of each electrical equipment transient power waveform is judged；
According to the duration of each electrical equipment transient power waveform, the analysis data of each electrical equipment are selected
Window length W0(the power data point number for including in data window)；
Using the analysis data window length of each electrical equipment, the initial time of each electrical equipment transient process is judged.
In practical applications, the maximum active power that i-th of data window Yu i+1 data window can be calculated separately, when
The absolute value of the difference of maximum active power is more than preset active power threshold k in former and later two data windows2When
It determines in i+1 data window, electrical equipment is in transient process, then judges electrical equipment in i-th of data window
Transient process start time.
Electrical equipment type identification system of the invention in one of the embodiments, can also be sharp with the following method
With the analysis data window length of each electrical equipment, the initial time of each electrical equipment transient process is judged:
Successively record the wattful power of j-th of sampling time point and j+1 sampling time point in each electrical equipment data window
Rate, and calculate difference between the two；
When the difference is more than preset active power threshold k2When, determine that sampling time point j is corresponding uses
The initial time of electric equipment transient process.
In practical applications, electrical equipment type identification system of the invention, can be since electrical equipment transient process
The power difference at two neighboring moment in active power waveform time sequence is recorded in a sequence S by the moment0In, when
Sequence S0Some subsequence S1In the value of element be respectively less than and set active power threshold K3, and subsequence S1Length it is big
In analysis data window length W0Half, that is, can determine whether subsequence S1Electrical equipment is in stable state in the corresponding period, that is,
It says, subsequence S1First element be the initial time of steady-state process and the end time of transient process at the time of correspond to,
And the last one element is the end time of steady-state process at the time of correspond to, and therefore, can according to need and extracts electrical equipment
Steady state characteristic and transient state is active and reactive power waveform time sequence P and Q, and calculate separately transient state active power and idle
Power features value, moreover, the transient-wave length of time series when electrical equipment is less than time threshold T1When, judge this transient state mistake
Journey is shut-down process, is otherwise opening process.
Electrical equipment type identification system of the invention in one of the embodiments, the identification module 105 can be with
For:
Model is recognized according to the type of each electrical equipment of foundation, electrical equipment index is calculated；
Electrical equipment index is input in the electrical equipment library being made of each electrical equipment, comparison is acquired
The second electrical parameter corresponding to electrical equipment type.
In practical applications, electrical equipment type identification system of the invention, it is special according to steady state characteristic similarity and transient state
Similarity calculation is levied as a result, the highest electrical equipment index of output integrated similarity, i.e. realization power load type and operation shape
State on-line identification.
Electrical equipment type discrimination method of the invention and system, at the same it is special from active power waveform and reactive power waveform
Electrical equipment transient characteristic is extracted in sign, and uses new transient characteristic similarity calculating method, thus in electrical equipment type
Gradually increase and the continuous complexity of used technology turn to non-intrusion type power load identification propose technological challenge in the case where,
Guarantee the identification accuracy of non-intrusion type power load identification system, it is final to improve non-intrusion type power load identification technique system
And the practicability of Related product.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (8)
1. a kind of electrical equipment type discrimination method, which comprises the steps of:
The first electrical parameter of various electrical equipments to be identified is acquired respectively；Wherein, first electrical parameter includes electrical equipment
Voltage, electric current, active power waveform and reactive power waveform in unlatching, stable operation and shut-down process；
Feature extraction is carried out to first electrical parameter, the first steady state characteristic and the first transient state for obtaining each electrical equipment are special
It levies, and generates the first steady state characteristic vector of each electrical equipment respectively according to first steady state characteristic and the first transient characteristic
With the first transient characteristic vector；
Acquire the second electrical parameter of each electrical equipment in actual work；Wherein, second electrical parameter includes that electricity consumption is set
Standby voltage, electric current, active power waveform and reactive power waveform in actual work；
Feature extraction is carried out to second electrical parameter and obtains the second steady state characteristic and the second transient characteristic of each electrical equipment,
And generate the second steady state characteristic vector sum of each electrical equipment respectively according to second steady state characteristic and the second transient characteristic
Second transient characteristic vector；
According to the first steady state characteristic vector, the first transient characteristic vector, the second steady state characteristic vector sum of each electrical equipment
Two transient characteristic vectors establish the type identification model of each electrical equipment, and using type identification model to each use
The type of electric equipment is recognized；The type identification model of the electrical equipment is as follows:
In formula,Indicate by electrical equipment to be identified first eigenvector and each electrical equipment in actual work the
The vector that similarity between two feature vectors is constituted, K1、K2Indicate real number, and K1+K2=1,It indicates by use to be identified
The similarity structure of second steady state characteristic vector of each electrical equipment in first steady state characteristic vector sum real work of electric equipment
At vector,It indicates by each electrical equipment in the first transient characteristic vector sum real work of electrical equipment to be identified
The second transient characteristic vector between similarity constitute vector,Indicate the steady state characteristic vector of each electrical equipment,
Indicate the second steady state characteristic vector of K electrical equipment,Indicate the steady state characteristic vector of k-th electrical equipmentWith the second steady state characteristic vector of the electrical equipmentBetween difference value vector,Indicate each electrical equipment all M
The transient characteristic vector of m sections of histogram feature parameter composition in transient state segmentation,Indicate that all M of K electrical equipment are a temporarily
Second transient characteristic vector of m sections of histogram feature parameter composition in state segmentation；
The step of first transient characteristic vector for generating each electrical equipment includes:
Record active power waveform and reactive power waveform of each electrical equipment in unlatching or shut-down process；
The active power waveform and reactive power waveform are subjected to discrete representation respectively according to the sampling period；
The active power waveform and reactive power waveform are divided into M sections respectively, obtain active power waveform and reactive power wave
The sequence segment of shape；
Histogram sequence analysis is carried out to the sequence segment of the active power waveform and reactive power waveform, obtains each electricity consumption
First transient characteristic vector of equipment.
2. electrical equipment type discrimination method according to claim 1, which is characterized in that the stable state of the electrical equipment is special
Sign includes: active power, reactive power, power-factor angle, odd harmonic electric current under the electrical equipment steady operational status
With the phase difference and Current harmonic distortion rate of fundamental current.
3. electrical equipment type discrimination method according to claim 2, which is characterized in that described to be carried out to the electrical parameter
Feature extraction, the step of obtaining the steady state characteristic of each electrical equipment include:
In formula, P indicates the active power of electrical equipment, UhIndicate h subharmonic voltage virtual value, IhIndicate h subharmonic current
Virtual value, θhIndicating that h subharmonic current lags the phase of the subharmonic voltage, Q indicates the reactive power of electrical equipment,Table
Show the power-factor angle of electrical equipment,Indicate arctan function, αidxIndicate the odd harmonic electric current of electrical equipment
With fundamental current phase difference, idx=[(h_odd-1)/2] ∈ { 1,2,3 ... }, h_odd ∈ { 1,3,5,7 ... } indicate current harmonics
Number, β1Indicate the fundamental current phase of electrical equipment, ITHDIndicate current harmonics total harmonic distortion,It indicates
The current effective value of electrical equipment.
4. electrical equipment type discrimination method according to claim 1, which is characterized in that described to second electrical parameter
Carrying out the step of feature extraction obtains the second steady state characteristic and the second transient characteristic of each electrical equipment includes:
According to second electrical parameter, the initial time of each electrical equipment transient process is judged；
Extract the second steady state characteristic and the second transient characteristic of each electrical equipment.
5. electrical equipment type discrimination method according to claim 4, which is characterized in that described to be joined according to second electricity
Number, the step of judging the initial time of each electrical equipment transient process include:
According to second electrical parameter, the duration of each electrical equipment transient power waveform is judged；
According to the duration of each electrical equipment transient power waveform, select the analysis data window of each electrical equipment long
Degree；
Using the analysis data window length of each electrical equipment, the initial time of each electrical equipment transient process is judged.
6. electrical equipment type discrimination method according to claim 5, which is characterized in that described to utilize each electrical equipment
Analysis data window length, the step of judging the initial time of each electrical equipment transient process includes:
Successively record in each electrical equipment data window active power between present sample time point and next sampling time point
Difference；
When the difference is more than preset active power threshold value, determine that present sample time point is that corresponding electricity consumption is set
The initial time of standby transient process.
7. electrical equipment type discrimination method according to claim 1, which is characterized in that described according to the described each of foundation
Type identification model the step of recognizing to the type of each electrical equipment of a electrical equipment includes:
Model is recognized according to the type of each electrical equipment of foundation, electrical equipment index is calculated；
Electrical equipment index is input in the electrical equipment library being made of each electrical equipment, the acquired is compared
Electrical equipment type corresponding to two electrical parameters.
8. a kind of electrical equipment type identification system characterized by comprising
First acquisition module, for acquiring the first electrical parameter of various electrical equipments to be identified respectively；Wherein, first electricity
Parameter includes voltage, electric current, active power waveform and reactive power of the electrical equipment in unlatching, stable operation and shut-down process
Waveform；
First extraction module obtains the first stable state of each electrical equipment for carrying out feature extraction to first electrical parameter
Feature and the first transient characteristic, and each electrical equipment is generated according to first steady state characteristic and the first transient characteristic respectively
First steady state characteristic vector sum the first transient characteristic vector；
Second acquisition module, for acquiring the second electrical parameter of each electrical equipment in actual work；Wherein, described second
Active power waveform and reactive power waveform when electrical parameter includes electrical equipment work；
Second extraction module obtains the second stable state spy of each electrical equipment for carrying out feature extraction to second electrical parameter
It seeks peace the second transient characteristic, and generates the of each electrical equipment respectively according to second steady state characteristic and the second transient characteristic
Two steady state characteristic vector sum the second transient characteristic vectors；
Module is recognized, for the first steady state characteristic vector, the first transient characteristic vector, the second stable state according to each electrical equipment
Feature vector and the second transient characteristic vector, establish the type identification model of each electrical equipment, and are recognized using the type
Model recognizes the type of each electrical equipment；
The type identification model of the electrical equipment is as follows:
In formula,Indicate by electrical equipment to be identified first eigenvector and each electrical equipment in actual work the
The vector that similarity between two feature vectors is constituted, K1、K2Indicate real number, and K1+K2=1,It indicates by be identified
The similarity of second steady state characteristic vector of each electrical equipment in first steady state characteristic vector sum real work of electrical equipment
The vector of composition,Expression is set by each electricity consumption in the first transient characteristic vector sum real work of electrical equipment to be identified
The vector that similarity between the second standby transient characteristic vector is constituted,Indicate the steady state characteristic vector of each electrical equipment,Indicate the second steady state characteristic vector of K electrical equipment,Indicate the steady state characteristic of k-th electrical equipment
VectorWith the second steady state characteristic vector of the electrical equipmentBetween difference value vector,Indicate that each electrical equipment is all
The transient characteristic vector of m sections of histogram feature parameter composition in M transient state segmentation,Indicate all M of K electrical equipment
Second transient characteristic vector of m sections of histogram feature parameter composition in a transient state segmentation；
The step of first transient characteristic vector for generating each electrical equipment includes:
Record active power waveform and reactive power waveform of each electrical equipment in unlatching or shut-down process；
The active power waveform and reactive power waveform are subjected to discrete representation respectively according to the sampling period；
The active power waveform and reactive power waveform are divided into M sections respectively, obtain active power waveform and reactive power wave
The sequence segment of shape；
Histogram sequence analysis is carried out to the sequence segment of the active power waveform and reactive power waveform, obtains each electricity consumption
First transient characteristic vector of equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610799505.8A CN106443244B (en) | 2016-08-31 | 2016-08-31 | Electrical equipment type discrimination method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610799505.8A CN106443244B (en) | 2016-08-31 | 2016-08-31 | Electrical equipment type discrimination method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106443244A CN106443244A (en) | 2017-02-22 |
| CN106443244B true CN106443244B (en) | 2019-05-10 |
Family
ID=58165500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610799505.8A Active CN106443244B (en) | 2016-08-31 | 2016-08-31 | Electrical equipment type discrimination method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106443244B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BR112019025082A2 (en) * | 2017-06-14 | 2020-06-16 | Mitsubishi Electric Corporation | COMPOSITION OF LOW GLYCEMIC CARBOHYDRATE AVAILABLE, NET NUTRITIONAL COMPOSITION, AND USE OF A CARBOHYDRATE COMPOSITION |
| CN107271824A (en) * | 2017-07-22 | 2017-10-20 | 华映科技（集团）股份有限公司 | Single-line type electrical equipment type automatic identification method |
| CN108152630B (en) * | 2017-12-26 | 2023-11-14 | 江苏智臻能源科技有限公司 | Non-invasive IH electric cooker operation identification method based on mixing criterion |
| CN108376346B (en) * | 2018-02-23 | 2021-05-25 | 南京飞腾电子科技有限公司 | User electricity consumption behavior analysis method and device |
| CN109765443A (en) * | 2019-01-17 | 2019-05-17 | 创炘源智能科技(上海)有限公司 | Detect the device and method of the electric appliance load on power supply line |
| CN110135452B (en) * | 2019-03-27 | 2023-08-08 | 广东浩迪创新科技有限公司 | Illegal electric appliance identification method and system based on intelligent electric meter |
| CN110514889A (en) * | 2019-07-19 | 2019-11-29 | 浙江万胜智能科技股份有限公司 | A kind of method and system of non-intrusion type household electricity remained capacity |
| CN110426554B (en) * | 2019-08-09 | 2022-03-18 | 威胜集团有限公司 | Household load electrical characteristic extraction method and device and computer readable storage medium |
| CN113224580B (en) * | 2021-05-27 | 2021-12-14 | 中山市佰源凯照明电器有限公司 | Wall socket with automatic fire extinguishing type protection structure |
| CN114629759B (en) * | 2022-03-16 | 2023-05-23 | 中国电子科技集团公司第十研究所 | Method and system for identifying fine features of aerial target communication signal |
| CN116780537A (en) * | 2023-08-24 | 2023-09-19 | 国网天津市电力公司宝坻供电分公司 | Non-invasive load monitoring method, device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101924393A (en) * | 2010-08-11 | 2010-12-22 | 徐文远 | Method and system for estimating load model parameters of electric system on line |
| CN103105556A (en) * | 2013-01-30 | 2013-05-15 | 西安交通大学 | Intelligent power grid load testing and recognition method based on steady state and transient state characteristic joint matching |
| CN103217603A (en) * | 2013-03-22 | 2013-07-24 | 重庆大学 | Recognition method of on-line monitoring of power consumption of non-intrusive household appliances |
| CN105186693A (en) * | 2015-09-28 | 2015-12-23 | 南方电网科学研究院有限责任公司 | Non-intrusive mode electrical load identification system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10139437B2 (en) * | 2014-02-18 | 2018-11-27 | Encored Technologies, Inc. | Apparatus, server, system and method for energy measuring |
-
2016
- 2016-08-31 CN CN201610799505.8A patent/CN106443244B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101924393A (en) * | 2010-08-11 | 2010-12-22 | 徐文远 | Method and system for estimating load model parameters of electric system on line |
| CN103105556A (en) * | 2013-01-30 | 2013-05-15 | 西安交通大学 | Intelligent power grid load testing and recognition method based on steady state and transient state characteristic joint matching |
| CN103217603A (en) * | 2013-03-22 | 2013-07-24 | 重庆大学 | Recognition method of on-line monitoring of power consumption of non-intrusive household appliances |
| CN105186693A (en) * | 2015-09-28 | 2015-12-23 | 南方电网科学研究院有限责任公司 | Non-intrusive mode electrical load identification system and method |
Non-Patent Citations (1)
| Title |
|---|
| 基于特征相似度的非侵入式用电负荷识别模型研究;赵云等;《电气应用》;20150630;199-203 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106443244A (en) | 2017-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106443244B (en) | Electrical equipment type discrimination method and system | |
| CN111428355B (en) | Modeling method for intelligent comprehensive statistics of power load numbers | |
| CN105186693A (en) | Non-intrusive mode electrical load identification system and method | |
| CN111027408A (en) | Load identification method based on support vector machine and V-I curve characteristics | |
| CN106208041B (en) | A kind of Distribution Network Harmonics current estimation method based on piecewise constant independent component analysis | |
| CN109598451A (en) | A kind of non-intrusion type load discrimination method based on PCA Yu LSTM neural network | |
| CN109784388A (en) | Stealing user identification method and device | |
| CN102890776A (en) | Method for searching emoticons through facial expression | |
| CN104392056B (en) | A kind of directly driven wind-powered unit modeling method and device | |
| CN109360579A (en) | Charging pile phonetic controller and system | |
| CN114236234A (en) | Electrical appliance characteristic identification method based on fundamental wave and harmonic wave mixed criterion | |
| CN111652761B (en) | Multi-source feature fusion electricity stealing behavior detection method based on evidence theory | |
| CN113887912A (en) | Non-invasive load identification method for deeply learning downward embedded equipment | |
| CN110135452A (en) | Violation electrical appliance recognition and system based on intelligent electric meter | |
| CN114444539A (en) | Power load identification method, apparatus, device, medium, and program product | |
| CN112615428A (en) | Line loss analysis and treatment system and method | |
| CN110361609B (en) | Extra-high voltage equipment monitoring system and method | |
| CN115456034A (en) | Automatic identification and monitoring method and system for electric bicycle charging | |
| CN113687610B (en) | Method for protecting terminal information of GAN-CNN power monitoring system | |
| CN110047013A (en) | It is anti-specially to become user's discontinuous form stealing electricity method | |
| Dan et al. | Review of non-intrusive load appliance monitoring | |
| Zhang et al. | Theories, applications and trends of non-technical losses in power utilities using machine learning | |
| CN106845763B (en) | Power grid reliability analysis method and device | |
| CN109670526A (en) | A kind of interference source type discrimination method, device, equipment and the storage medium of power grid | |
| CN110222788A (en) | A kind of the load identifying system and method for intelligent socket |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210611 Address after: 510700 3rd, 4th and 5th floors of building J1 and 3rd floor of building J3, No.11 Kexiang Road, Science City, Luogang District, Guangzhou City, Guangdong Province Patentee after: China Southern Power Grid Research Institute Co.,Ltd. Address before: 510080 water Donggang 8, Dongfeng East Road, Yuexiu District, Guangzhou, Guangdong. Patentee before: China Southern Power Grid Research Institute Co.,Ltd. Patentee before: CSG POWER GRID TECHNOLOGY RESEARCH CENTER |
|
| TR01 | Transfer of patent right |