CN106443244A - Electric equipment type identification method and system - Google Patents

Electric equipment type identification method and system Download PDF

Info

Publication number
CN106443244A
CN106443244A CN201610799505.8A CN201610799505A CN106443244A CN 106443244 A CN106443244 A CN 106443244A CN 201610799505 A CN201610799505 A CN 201610799505A CN 106443244 A CN106443244 A CN 106443244A
Authority
CN
China
Prior art keywords
electrical equipment
transient
steady state
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.)
Granted
Application number
CN201610799505.8A
Other languages
Chinese (zh)
Other versions
CN106443244B (en
Inventor
李秋硕
肖勇
李鹏
钱斌
孙宇军
王岩
赵云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China South Power Grid International Co ltd
Original Assignee
China South Power Grid International Co ltd
Power Grid Technology Research Center of China Southern Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China South Power Grid International Co ltd, Power Grid Technology Research Center of China Southern Power Grid Co Ltd filed Critical China South Power Grid International Co ltd
Priority to CN201610799505.8A priority Critical patent/CN106443244B/en
Publication of CN106443244A publication Critical patent/CN106443244A/en
Application granted granted Critical
Publication of CN106443244B publication Critical patent/CN106443244B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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 invention relates to a method and a system for identifying the type of electric equipment, wherein the method comprises the following steps: respectively collecting first electrical parameters of various electrical equipment to be identified; extracting the characteristics of the first electrical parameters to obtain first steady-state characteristics and first transient characteristics of each electric device, and respectively generating first steady-state characteristic vectors and first transient characteristic vectors of each electric device; acquiring second electrical parameters of each piece of electrical equipment during actual working; extracting the second electrical parameter to obtain a second steady-state feature and a second transient-state feature of each electric device, and respectively generating a second steady-state feature vector and a second transient-state feature vector of each electric device; according to the first steady-state feature vector, the first transient-state feature vector, the second steady-state feature vector and the second transient-state feature vector of each electric device, the type identification model of each electric device is established to identify the type of the electric device, and the accuracy of type identification of the electric device is improved.

Description

Electrical equipment type discrimination method and system
Technical field
The present invention relates to intelligent power technical field, more particularly to a kind of electrical equipment type discrimination method and system.
Background technology
With deepening continuously of intelligent grid development, intelligent grid art also constantly makes a breakthrough, including：Crucial skill The research of art and standard, key equipment development, dsm are put into practice, electrical network and user interaction service and marketing automation system Build etc., wherein, the research of key technology and standard includes：Power information acquisition system, intelligent electric energy meter, electric automobile fill Electric equipment and the key technology research such as 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 is always the key technology in intelligent power field with recognition methodss, and is also to use telecommunications The important technology of breath acquisition system.Traditional power load monitoring method is：First for each electrical equipment, power information is installed to adopt Collection sensor, then the power load of regional is monitored with monitoring master station communication by indoor WLAN.
But, the power load monitoring system construction cost of this intrusive mood is higher, operation maintenance is difficult, may simultaneously Shadow is caused to user's productive life；Additionally, power information collection sensor and monitoring main website carry out data using WLAN Communication can make user power utilization information there is potential safety hazard.Although having been proposed for non-intrusion type power load identification system and side Method, however, with electrical equipment species gradually increase and adopted technology continuous complication, existing power load distinguishes Knowledge method is it is difficult to ensure that the accuracy of non-intrusion type power load identification system.
To sum up shown, the accuracy of existing power load discrimination method is relatively low.
Content of the invention
Based on this it is necessary to for the relatively low technical problem of the accuracy of existing electrical equipment load discrimination method, carry For a kind of electrical equipment type discrimination method and system.
A kind of electrical equipment type discrimination method, comprises the steps：
Gather the first electrical quantity of various electrical equipments to be identified respectively；Wherein, described first electrical quantity includes electricity consumption Equipment is opening, the voltage in stable operation and shut-down process, electric current, active power waveform and reactive power waveform；
Feature extraction is carried out to described first electrical quantity, obtains the first steady state characteristic and first transient state of each electrical equipment Feature, and according to described 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；
The second electrical quantity during collection each electrical equipment real work described；Wherein, described second electrical quantity includes using Active power waveform during electric equipment work and reactive power waveform；
Described second electrical quantity is carried out with the second steady state characteristic and the second transient state that feature extraction obtains each electrical equipment Feature, and according to described 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 each electrical equipment first steady state characteristic vector, first transient characteristic vector, second steady state characteristic vector With the second transient characteristic vector, set up the type identification model of each electrical equipment, and using described type identification model to each The type of individual electrical equipment is recognized.
Above-mentioned electrical equipment type discrimination method, by gathering various electrical equipments to be identified in unlatching, stable operation With the voltage in shut-down process, electric current, active power waveform and reactive power waveform, and feature extraction is carried out to above-mentioned parameter obtain To the first steady state characteristic and first transient characteristic of each electrical equipment and special according to described first steady state characteristic and the first transient state Levy first steady state characteristic vector sum the first transient characteristic vector generating each electrical equipment respectively；Then, gather described each Active power waveform during electrical equipment real work and reactive power waveform, and feature extraction is carried out to above-mentioned parameter obtain respectively Second steady state characteristic of individual electrical equipment and the second transient characteristic, and divided according to described second steady state characteristic and the second transient characteristic Do not generate second steady state characteristic vector sum the second transient characteristic vector of each electrical equipment；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, set up each The type identification model of individual electrical equipment, and using described type identification model, the type of each electrical equipment is recognized. The electrical equipment type discrimination method of the present invention, by active power waveform and the reactive power of each electrical equipment to collection The analysis of waveform, it is achieved that recognizing to the type of electrical equipment, improves the accuracy of electrical equipment type identification.
A kind of electrical equipment type identification system, including：
First acquisition module, for gathering the first electrical quantity of various electrical equipments to be identified respectively；Wherein, described One electrical quantity includes the voltage opening, in stable operation and shut-down process for the electrical equipment, electric current, active power waveform and idle Power waveform；
First extraction module, for carrying out feature extraction to described first electrical quantity, obtains the first of each electrical equipment Steady state characteristic and the first transient characteristic, and each electricity consumption is generated respectively according to described first steady state characteristic and the first transient characteristic set First standby steady state characteristic vector sum the first transient characteristic vector；
Second acquisition module, for gathering the second electrical quantity during each electrical equipment real work described；Wherein, described Second electrical quantity includes active power waveform and reactive power waveform during electrical equipment work；
Second extraction module, obtains the second steady of each electrical equipment for described second electrical quantity is carried out with feature extraction State feature and the second transient characteristic, and each electrical equipment is generated respectively according to described second steady state characteristic and the second transient characteristic Second steady state characteristic vector sum the second transient characteristic vector；
Identification module, for according to each electrical equipment first steady state characteristic vector, first transient characteristic vector, second Steady state characteristic vector sum second transient characteristic vector, sets up the type identification model of each electrical equipment, and utilizes described type Identification model recognizes to the type of each electrical equipment.
Above-mentioned electrical equipment type identification system, is existed by first time acquisition module collection various electrical equipments to be identified Voltage in unlatching, stable operation and shut-down process, electric current, active power waveform and reactive power waveform, and carry using first Delivery block carries out the first steady state characteristic and the first transient characteristic that feature extraction obtains each electrical equipment to above-mentioned parameter, and root Generate the first steady state characteristic vector sum first of each electrical equipment according to described first steady state characteristic and the first transient characteristic respectively Transient characteristic vector；Then, by active power ripple during the second acquisition module collection each electrical equipment real work described Shape and reactive power waveform, and above-mentioned parameter is carried out with feature extraction obtains each electrical equipment using the second extraction module Two steady state characteristics and the second transient characteristic, and each electricity consumption is generated respectively according to described second steady state characteristic and the second transient characteristic Second steady state characteristic vector sum the second transient characteristic vector of equipment；Finally, by recognizing 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, set up each The type identification model of electrical equipment, and using described type identification model, the type of each electrical equipment is recognized.This The electrical equipment type identification system of invention, by active power waveform and the reactive power ripple of each electrical equipment to collection The analysis of shape, it is achieved that recognizing to the type of electrical equipment, improves the accuracy of power load identification.
Brief description
Fig. 1 is the electrical equipment type discrimination method flow chart of one of embodiment of the present invention；
Fig. 2 is the electrical equipment type discrimination method flow chart of an alternative embodiment of the invention；
Fig. 3 is the structural representation of the electrical equipment type identification system of one of embodiment of the present invention；
Fig. 4 is the structural representation of the electrical equipment type identification system of an alternative embodiment of the invention.
Specific embodiment
In order to further illustrate the effect of technological means that the present invention taken and acquirement, below in conjunction with the accompanying drawings and preferably Embodiment, to technical scheme, carries out clear and complete description.
As shown in figure 1, Fig. 1 is the electrical equipment type discrimination method flow chart of one of embodiment of the present invention, bag Include following steps：
Step S101：Gather the first electrical quantity of various electrical equipments to be identified respectively；Wherein, described first electrical quantity The voltage opening, in stable operation and shut-down process, electric current, active power waveform and reactive power ripple including electrical equipment Shape；
In this step, by the first of electrical equipment including active power waveform and reactive power waveform for the collection Electrical quantity, lays a good foundation for the feature extraction for subsequent step, also provides for accurate recognition electrical equipment type hereinafter Reliable data refer, is the important step improving electrical equipment type identification precision.
Step S102：Feature extraction is carried out to described first electrical quantity, obtains the first steady state characteristic of each electrical equipment With the first transient characteristic, and generate the first of each electrical equipment respectively according to described first steady state characteristic and the first transient characteristic Steady state characteristic vector sum first transient characteristic vector；Wherein, described first steady state characteristic vector sum the first transient characteristic vector structure Become first eigenvector；
In this step, by feature extraction is carried out to the first electrical quantity of each electrical equipment, obtain each electricity consumption and set The first standby steady state characteristic and the first transient characteristic, and according to described and according to described first steady state characteristic and the first transient characteristic Generate first steady state characteristic vector sum the first transient characteristic vector of each electrical equipment respectively.It should be noted that this step Described in first steady state characteristic vector sum the first transient characteristic vector respectively by each electrical equipment steady state characteristic and transient state 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 represents certain class The eigenvalue of electrical equipment, therefore, the present invention passes through to gather each electrical equipment in real work the in subsequent step Two electrical quantitys, and obtain second steady state characteristic vector sum the second transient characteristic vector further, and then to each electrical equipment class Type is recognized, and finally the power load in certain region is recognized, to find fortuitous event as early as possible, danger coefficient is dropped To minimum.
Step S103：The second electrical quantity during collection each electrical equipment real work described；Wherein, described second electricity ginseng Several voltages including during electrical equipment real work, electric current, active power waveform and reactive power waveform；
In actual applications, certain region can be selected, and gather during the electrical equipment real work in this region Two electrical quantitys, it is important to note that the second electrical quantity includes the available power waveform of corresponding electrical equipment and useless Power waveform, furthermore it is also possible to include the parameters such as voltage, electric current.In this step, by gathering the available power of electrical equipment These parameters are carried out feature extraction for subsequent step by waveform and useless power waveform, obtain the of each electrical equipment Two steady state characteristic vector sum the second transient characteristic vectors, carry out identification offer reliably for final to each electrical equipment type Reference frame.
In actual applications, the first electrical quantity described in step S101 can be that electrical equipment type is being recognized Before with regard to obtaining in advance and being stored, and the second electrical quantity described in step S103 is that electrical equipment type is being carried out Obtain in real time online during identification.
Step S104：Described second electrical quantity is carried 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 respectively according to described second steady state characteristic and the second transient characteristic State characteristic vector and the second transient characteristic vector；Wherein, described second steady state characteristic vector sum the second transient characteristic vector is constituted Second feature vector；
In this step, by the second electrical quantity of electrical equipment is carried out with feature extraction obtains each electrical equipment Two steady state characteristics and the second transient characteristic, and each electricity consumption is generated respectively according to described second steady state characteristic and the second transient characteristic 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 Characteristic vector and the second transient characteristic vector are made up 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 represents The eigenvalue of certain class electrical equipment certain parameter in actual motion, is carried out to each electrical equipment type for subsequent step Identification, finally recognizes to the power load in certain region, to find fortuitous event as early as possible, danger coefficient is dropped to Low.
Step S105：According to each electrical equipment first steady state characteristic vector, first transient characteristic vector, the second stable state Characteristic vector and the second transient characteristic vector, set up the type identification model of each electrical equipment, and using described type identification Model recognizes to the type of each electrical equipment.
In this step, according to the first steady state characteristic vector of each electrical equipment, the first transient characteristic vector, second steady State characteristic vector and the second transient characteristic vector, are set up the type identification model of each electrical equipment, and are distinguished using described type Know model the type of each electrical equipment is recognized.It should be noted that the |input paramete of type identification model is vector, Final output is also vector, the vector being made up of the similarity of electrical equipment type.Therefore, in actual applications, if knowing Road inputs the value minimum of which element in the output vector after certain parameter, then export the index of this element, i.e. know Road index, has also been known that the electrical equipment type corresponding with this parameter.
In actual applications, because the first electrical quantity includes electrical equipment in unlatching, stable operation and shut-down process Voltage, electric current, active power waveform and reactive power waveform, the first electrical quantity is carried out with first obtaining after feature extraction Steady state characteristic vector sum first transient characteristic vector equally includes the operational factor in each state for the electrical equipment, therefore, Type identification model according to setting up equally can also pick out the running status of each electrical equipment.
Above-mentioned electrical equipment type discrimination method, by gathering various electrical equipments to be identified in unlatching, stable operation With the voltage in shut-down process, electric current, active power waveform and reactive power waveform, and feature extraction is carried out to above-mentioned parameter obtain To the first steady state characteristic and first transient characteristic of each electrical equipment and special according to described first steady state characteristic and the first transient state Levy first steady state characteristic vector sum the first transient characteristic vector generating each electrical equipment respectively；Then, gather described each Voltage during electrical equipment real work, electric current, active power waveform and reactive power waveform, and feature is carried out to above-mentioned parameter Extract the second steady state characteristic and the second transient characteristic obtaining each electrical equipment, and according to described 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 individual electrical equipment, the first transient characteristic vector, second steady state characteristic vector sum the second transient characteristic Vector, sets up the type identification model of each electrical equipment, and utilizes the class to each electrical equipment for the described type identification model Type is recognized.The electrical equipment type discrimination method of the present invention, by the active power ripple of each electrical equipment to collection The analysis of shape and reactive power waveform, it is achieved that recognizing to the type of electrical equipment, improves the standard of electrical equipment type identification Exactness.
Wherein in an embodiment, the electrical equipment type discrimination method of the present invention, the type of described electrical equipment is distinguished Know model as follows：
In formula,Represent by each electrical equipment when first eigenvector of electrical equipment to be identified and real work Second feature vector between similarity constitute vector, K1、K2All represent real number, and K1+K2=1,Represent by waiting to distinguish During the first steady state characteristic vector sum real work of electrical equipment known between the second steady state characteristic vector of each electrical equipment Similarity constitute vector,Represent by electrical equipment to be identified the first transient characteristic vector sum real work when each The vector that similarity between second transient characteristic vector of electrical equipment is constituted,Represent the second steady of each electrical equipment State characteristic vector,Represent the second steady state characteristic vector of K electrical equipment,Represent k-th First steady state characteristic vector of electrical equipmentThe second steady state characteristic vector with this electrical equipmentBetween difference value vector,Represent the transient characteristic vector of the histogram feature parameter composition of m section in all M transient state segmentations of each electrical equipment,The second of the histogram feature parameter composition of m section in all M transient state segmentations of K electrical equipment of expression Transient characteristic vector, M'PRepresent the number of active relevant parameter in subvector, M'QRepresent the number of idle relevant parameter in subvector Mesh.
Wherein in an embodiment, the electrical equipment type discrimination method of the present invention, the stable state of described electrical equipment is special Levy including：Active power under described electrical equipment steady operational status, reactive power, power-factor angle, odd harmonic electric current Phase contrast and Current harmonic distortion rate with fundamental current.
In actual applications, K1 and K2 in formula (1), preferably 0.5 so that the steady state characteristic similarity of electrical equipment Consistent with the impact to electrical equipment type for the transient characteristic similarity, improve the accuracy of identification.It should be noted that formula (1) inWithAll represent vector, popular for, R is by the first eigenvector of electrical equipment to be identified and reality The vector of the similarity composition between the second feature vector of each electrical equipment in the application of border, for example, R=0.001, 0.002nd, 0.012,0.201 }, and each numerical value in R corresponding be electrical equipment to be identified and " electromagnetic oven, microwave oven, ice Similarity between case, washing machine ", in the identification model pre-building, R can export the minimum corresponding rope of element of similarity Draw, what similarity was minimum is " 0.001 ", and corresponding index is 0 taking the numerical value of above-mentioned R vector as a example, then, this index corresponds to The type of electrical equipment be exactly " electromagnetic oven ".
The electricity consumption that formula (2) is used for calculating during the first steady state characteristic vector sum actual motion in electrical equipment feature database sets Steady state characteristic similarity between the second standby steady state characteristic vector, wherein, vectorial RWFirst elementMeter Calculate is the first steady state characteristic vector of the 1st electrical equipment in electrical equipment feature databaseDuring with the actual motion of electrical equipment Second steady state characteristic vectorBetween steady state characteristic similarity, other elements same it should be noted that in formula (2) latter half, by vectorial by the first steady state characteristicWith the second steady state characteristic vectorIn 5 steady state characteristic parameters The absolute value of difference be added, finally give both steady state characteristic similarities.Using calculated steady according to formula (2) State characteristic similarity, the accuracy rate of the electrical equipment type finally recognizing is higher, and this is also that the present invention improves identification precision Critical step.
In the above-described embodiments, the n in formula (2) represents the number of parameters of the steady state characteristic of electrical equipment, in this enforcement 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 contrast of ripple electric current and Current harmonic distortion rate, therefore, in formula (2), the value of n is 1 to 5.In reality In application, if increasing or reduce the number of parameters of electrical equipment steady state characteristic, the span of n also accordingly increases or subtracts Few.
Formula (3) is used for calculating electrical equipment during the first transient characteristic vector sum actual motion in electrical equipment feature database The second transient characteristic vector between transient characteristic similarity, likewise, vectorialFirst element Calculate is the first transient characteristic vector of the 1st electrical equipment in electrical equipment feature databaseCorresponding with during actual motion use Second transient characteristic vector of electric equipmentBetween transient characteristic similarity, wherein,WithRepresent all M respectively temporarily The subvector of the histogram feature parameter composition of m section, M' in state segmentationPRepresent the number of active relevant parameter in subvector, M'QRepresent the number of idle relevant parameter in subvector.
Wherein in an embodiment, the electrical equipment type discrimination method of the present invention, described described electrical quantity is carried out Feature extraction, the step obtaining the steady state characteristic of each electrical equipment can include：
In formula, P represents the active power of electrical equipment, UhRepresent h subharmonic voltage virtual value, IhRepresent h subharmonic Current effective value, θhRepresent the phase place of h subharmonic current this subharmonic voltage delayed, Q represents the reactive power of electrical equipment,Represent the power-factor angle of electrical equipment, arctan (.) represents arctan function, αidxRepresent the odd harmonic electricity of electrical equipment Stream and fundamental current phase contrast, idx=[(h_odd-1)/2] ∈ { 1,2,3 ... }, h_odd ∈ { 1,3,5,7 ... } represent that electric current is humorous Ripple number of times, β1Represent the fundamental current phase place of electrical equipment, ITHDRepresent current harmonics total harmonic distortion,Table Show the current effective value of electrical equipment.
In the above-described embodiments, by feature is carried out to the electrical quantity under each electrical equipment steady operational status obtaining Extract, obtain the steady state characteristic of each electrical equipment, for subsequent step, the type of electrical equipment is recognized.Need Bright, in the electrical equipment discrimination method of the present invention, the electrical quantity of collection contains active power waveform and reactive power simultaneously 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 an alternative embodiment of the invention, described Step S102 generating the first transient characteristic vector of each electrical equipment can include：
Step S1021：Record active power waveform in unlatching or shut-down process for each electrical equipment and reactive power Waveform；
Step S1022：Described active power waveform and reactive power waveform are carried out respectively by discrete sheet according to the sampling period Show, for example, it is possible to described active power waveform and reactive power waveform are expressed as follows：
Step S1023：Respectively described active power waveform and reactive power waveform are divided into M section, obtain active power ripple Shape and the sequence segment of reactive power waveform, still as a example above formula, the sequence segment after segmentation is expressed as follows：
Step S1024：Carry out histogram sequence to the sequence segment of described active power waveform and reactive power waveform to divide Analysis, obtains the first transient characteristic vector of each electrical equipment.
In the above-described embodiments, by aforesaid operations, the electrical equipment type discrimination method of the present invention achieves to treat to be distinguished The extraction of the transient characteristic of electrical equipment known.
Wherein in an embodiment, the electrical equipment type discrimination method of the present invention, described to described second electrical quantity The step carrying out the second steady state characteristic and the second transient characteristic that feature extraction obtains each electrical equipment can also include：
According to described second electrical quantity, judge the initial time of each electrical equipment transient process；
Extract the second steady state characteristic and second transient characteristic of each electrical equipment.
Wherein in an embodiment, can in the following way, judge each electrical equipment transient process initial when Carve：
According to described second electrical quantity, judge the duration of each electrical equipment transient power waveform；
According to the duration of each electrical equipment transient power waveform described, select the analytical data of each electrical equipment Window length W0(power data comprising in data window is counted out)；
Using the analytical data window length of each electrical equipment, judge the initial time of each electrical equipment transient process.
In actual applications, the maximum active power of i-th data window and i+1 data window can be calculated respectively, when In former and later two data windows, the absolute value of the difference of maximum active power exceedes active power threshold k set in advance2When, you can Determine that electrical equipment is in transient process, subsequently judges electrical equipment in i-th data window in i+1 data window Transient process start time.
Wherein in an embodiment, the described analytical data window length using each electrical equipment, judge each electricity consumption The step of the initial time of equipment transient process can include：
Record the wattful power of j-th sampling time point and j+1 sampling time point in each electrical equipment data window successively Rate, and calculate difference between the two；
When described difference exceedes active power threshold k set in advance2When, judge that sampling time point j is corresponding using The initial time of electric equipment transient process.
In actual applications, the electrical equipment type discrimination method of the present invention, can be from the beginning of electrical equipment transient process Moment, by the power difference record in two neighboring moment in active power waveform time sequence in sequence S0In, when Sequence S0Certain subsequence S1In the value of element respectively less than set active power threshold K3, and subsequence S1Length big In analytical data window length W0Half, you can judge subsequence S1In the corresponding time period, electrical equipment is in stable state, that is, Say, subsequence S1First element corresponding moment be steady-state process initial time, be also the end time of transient process, And last element corresponding moment is the end time of steady-state process, therefore, it can extract as needed electrical equipment Steady state characteristic and transient state is active and reactive power waveform time sequence P and Q, and calculate transient state active power and idle respectively Power features value, and, when the transient-wave length of time series of electrical equipment is less than time threshold T1When, judge this transient state mistake Journey is shut-down process, otherwise for opening process.
Wherein in an embodiment, the electrical equipment type discrimination method of the present invention, described described each according to set up The step that the type identification model of individual electrical equipment is recognized to the type of each electrical equipment includes：
The type identification model of each electrical equipment according to set up, is calculated electrical equipment index；
Described electrical equipment index is input in the electrical equipment storehouse being made up of each electrical equipment, contrast is gathered The electrical equipment type corresponding to the second electrical quantity.
In actual applications, the present invention, according to steady state characteristic similarity and transient characteristic Similarity Measure result, exports comprehensive Close similarity highest electrical equipment index, that is, realize power load type and running status on-line identification.
As shown in figure 3, Fig. 3 is the structural representation of the electrical equipment type identification system of an alternative embodiment of the invention Figure, including：
First acquisition module 101, for gathering the first electrical quantity of various electrical equipments to be identified respectively；Wherein, institute State the first electrical quantity include the voltage opening, in stable operation and shut-down process for the electrical equipment, electric current, active power waveform and Reactive power waveform；
In the first acquisition module 101, by electricity consumption including active power waveform and reactive power waveform for the collection First electrical quantity of equipment, the feature extraction of rear subsequent step is laid a good foundation, also for accurate recognition electrical equipment type hereinafter Provide reliable data refer, be the important step improving electrical equipment type identification precision.
First extraction module 102, for carrying out feature extraction to described first electrical quantity, obtains the of each electrical equipment One steady state characteristic and the first transient characteristic, and each electricity consumption is generated respectively according to described first steady state characteristic and the first transient characteristic First steady state characteristic vector sum the first transient characteristic vector of equipment；
In the first extraction module 102, by feature extraction is carried out to the first electrical quantity of each electrical equipment, obtain each First steady state characteristic of individual electrical equipment and the first transient characteristic, and according to described and according to described 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.Need explanation It is that the stable state by each electrical equipment is special respectively for first steady state characteristic vector sum the first transient characteristic vector described in this step Transient characteristic of seeking peace composition it may also be said to, described in this step first steady state characteristic vector sum the first transient characteristic vector structure The feature database of each electrical equipment, each of first steady state characteristic vector sum the first transient characteristic vector element all generations are become The eigenvalue of certain class electrical equipment by table, and therefore, the present invention passes through to gather each electrical equipment in actual work in subsequent step The second electrical quantity when making, and obtain second steady state characteristic vector sum the second transient characteristic vector further, and then to each use Electric equipment type is recognized, and finally the power load in certain region is recognized, to find fortuitous event as early as possible, will endanger Dangerous coefficient is preferably minimized.
Second acquisition module 103, for gathering the second electrical quantity during each electrical equipment real work described；Wherein, Described second electrical quantity includes voltage during electrical equipment real work, electric current, active power waveform and reactive power waveform；
In actual applications, certain region can be selected, and gather during the electrical equipment real work in this region Two electrical quantitys, it is important to note that the second electrical quantity includes the available power waveform of corresponding electrical equipment and useless Power waveform, furthermore it is also possible to include the parameters such as voltage, electric current.In this step, by gathering the available power of electrical equipment These parameters are carried out feature extraction for subsequent step by waveform and useless power waveform, obtain the of each electrical equipment Two steady state characteristic vector sum the second transient characteristic vectors, carry out identification offer reliably for final to each electrical equipment type Reference frame.
Second extraction module 104, for described second electrical quantity is carried out with feature extraction obtains each electrical equipment Two steady state characteristics and the second transient characteristic, and each electricity consumption is generated respectively according to described second steady state characteristic and the second transient characteristic Second steady state characteristic vector sum the second transient characteristic vector of equipment；
In the second extraction module 104, obtain each use by the second electrical quantity of electrical equipment is carried out with feature extraction Second steady state characteristic of electric equipment and the second transient characteristic, and given birth to respectively according to described second steady state characteristic and the second transient characteristic Become 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 steady state characteristic vector sum the second transient characteristic vector respectively by the steady state characteristic and temporarily of each electrical equipment actual motion 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 individual electrical equipment actual motion state, each of second steady state characteristic vector sum the second transient characteristic vector unit Element all represents the eigenvalue of certain class electrical equipment certain parameter in actual motion, for subsequent step, each electricity consumption is set Standby type is recognized, and finally the power load in certain region is recognized, to find fortuitous event as early as possible, by dangerous system Number is preferably minimized.
Identification module 105, for according to each electrical equipment first steady state characteristic vector, first transient characteristic vector, Second steady state characteristic vector sum the second transient characteristic vector, sets up the type identification model of each electrical equipment, and using described Type identification model recognizes to the type of each electrical equipment.
Identification module 105 in, according to each electrical equipment first steady state characteristic vector, first transient characteristic vector, Second steady state characteristic vector sum the second transient characteristic vector, sets up the type identification model of each electrical equipment, and using described Type identification model recognizes to the type of each electrical equipment.It should be noted that the |input paramete of type identification model It is vector, final output is also vector, the vector being made up of electrical equipment type.Therefore, in actual applications, if it is known that Output result after inputting certain parameter is which element of vector, i.e. vectorial index, has also been known that and this ginseng The corresponding electrical equipment type of number.
In actual applications, because the first electrical quantity includes electrical equipment in unlatching, stable operation and shut-down process Voltage, electric current, active power waveform and reactive power waveform, the first electrical quantity is carried out with first obtaining after feature extraction Steady state characteristic vector sum first transient characteristic vector equally includes the operational factor in each state for the electrical equipment, therefore, Type identification model according to setting up equally can also pick out the running status of each electrical equipment.
Above-mentioned electrical equipment type identification system, gathers various electricity consumptions to be identified by first time acquisition module 101 and sets Standby voltage opening, in stable operation and shut-down process, electric current, active power waveform and reactive power waveform, and utilize the One extraction module 102 carries out the first steady state characteristic and the first transient state spy that feature extraction obtains each electrical equipment to above-mentioned parameter Levy, and generate the first steady state characteristic vector of each electrical equipment according to described first steady state characteristic and the first transient characteristic respectively With the first transient characteristic vector；Then, having during each electrical equipment real work described is gathered by the second acquisition module 103 Work(power waveform and reactive power waveform, and using the second extraction module 104, feature extraction is carried out to above-mentioned parameter and obtain each Second steady state characteristic of electrical equipment and the second transient characteristic, and according to described second steady state characteristic and the second transient characteristic difference Generate second steady state characteristic vector sum the second transient characteristic vector of each electrical equipment；Finally, by recognizing module 105 basis First steady state characteristic vector of each electrical equipment, the first transient characteristic vector, second steady state characteristic vector sum the second transient state are special Levy vector, set up the type identification model of each electrical equipment, and using described type identification model to each electrical equipment Type is recognized.The electrical equipment type identification system of the present invention, by the active power of each electrical equipment to collection The analysis of waveform and reactive power waveform, it is achieved that recognizing to the type of electrical equipment, improves the accurate of power load identification Degree.
Wherein in an embodiment, the electrical equipment type identification system of the present invention, the type of described electrical equipment is distinguished Know model as follows：
In formula,Represent by each electrical equipment when first eigenvector of electrical equipment to be identified and real work Second feature vector between similarity constitute vector, K1、K2All represent real number, and K1+K2=1,Represent by be identified The first steady state characteristic vector sum real work of electrical equipment when each electrical equipment second steady state characteristic vector between phase The vector constituting like degree,Each electricity consumption when representing the first transient characteristic vector sum real work by electrical equipment to be identified The vector that similarity between second transient characteristic vector of equipment is constituted,Represent the second steady state characteristic of each electrical equipment Vector,Represent the second steady state characteristic vector of K electrical equipment,Represent k-th electrical equipment First steady state characteristic vectorThe second steady state characteristic vector with this electrical equipmentBetween difference value vector,Represent each The transient characteristic vector of the histogram feature parameter composition of m section in all M transient state segmentations of electrical equipment, Second transient characteristic vector of the histogram feature parameter composition of m section in all M transient state segmentations of K electrical equipment of expression, M'PRepresent the number of active relevant parameter in subvector, M'QRepresent the number of idle relevant parameter in subvector.
Wherein in an embodiment, the electrical equipment type identification system of the present invention, the stable state of described electrical equipment is special Levy including：Active power under described electrical equipment steady operational status, reactive power, power-factor angle, odd harmonic electric current Phase contrast and Current harmonic distortion rate with fundamental current.
In actual applications, K1 and K2 in formula (1), preferably 0.5 so that the steady state characteristic similarity of electrical equipment Consistent with the impact to electrical equipment type for the transient characteristic similarity, improve the accuracy of identification.It should be noted that formula (1) inWithAll represent vector, popular for, R is by the first eigenvector of electrical equipment to be identified and reality The vector of the similarity composition between the second feature vector of each electrical equipment in the application of border, for example, R=0.001, 0.002nd, 0.012,0.201 }, and each numerical value in R corresponding be electrical equipment to be identified and " electromagnetic oven, microwave oven, ice Similarity between case, washing machine ", in the identification model pre-building, R can export the minimum corresponding rope of element of similarity Draw, what similarity was minimum is " 0.001 ", and corresponding index is 0 taking the numerical value of above-mentioned R vector as a example, then, this index corresponds to The type of electrical equipment be exactly " electromagnetic oven ".
Formula（2）For calculating electricity consumption during 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, vectorial RWFirst element Calculate is the first steady state characteristic vector of the 1st electrical equipment in electrical equipment feature databaseActual motion with electrical equipment When second steady state characteristic vectorBetween steady state characteristic similarity, other elements same it should be noted that in public affairs Formula（2）Latter half, by by first steady state characteristic vectorWith the second steady state characteristic vectorIn 5 steady state characteristics ginseng The absolute value of the difference of number is added, and finally gives both steady state characteristic similarities.Using according to formula（2）Calculated Steady state characteristic similarity, the accuracy rate of the electrical equipment type finally recognizing is higher, and this is also that the present invention improves identification accurately Degree critical step.
In the above-described embodiments, the n in formula (2) represents the number of parameters of the steady state characteristic of electrical equipment, in this enforcement 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 contrast of ripple electric current and Current harmonic distortion rate, therefore, in formula (2), the value of n is 1 to 5.In reality In application, if increasing or reduce the number of parameters of electrical equipment steady state characteristic, the span of n also accordingly increases or subtracts Few.
Formula (3) is used for calculating electrical equipment during the first transient characteristic vector sum actual motion in electrical equipment feature database Transient characteristic similarity between second transient characteristic vector, likewise, vectorialFirst elementCalculate Be the 1st electrical equipment in electrical equipment feature database first transient characteristic vectorElectricity consumption corresponding with during actual motion sets The second standby transient characteristic vectorBetween transient characteristic similarity, wherein,WithRepresent that all M transient state are divided respectively The subvector of the histogram feature parameter composition of Duan Zhong m section, M'PRepresent the number of active relevant parameter in subvector, M'QTable Show the number of idle relevant parameter in subvector.
Wherein in an embodiment, the electrical equipment type identification system of the present invention, described first extraction module 102 is also For feature extraction being carried out to described electrical quantity, obtaining the steady state characteristic of each electrical equipment：
In formula, P represents the active power of electrical equipment, UhRepresent h subharmonic voltage virtual value, IhRepresent h subharmonic Current effective value, θhRepresent the phase place of h subharmonic current this subharmonic voltage delayed, Q represents the reactive power of electrical equipment,Represent the power-factor angle of electrical equipment, arctan (.) represents arctan function, αidxRepresent the odd harmonic electricity of electrical equipment Stream and fundamental current phase contrast, idx=[(h_odd-1)/2] ∈ { 1,2,3 ... }, h_odd ∈ { 1,3,5,7 ... } represent that electric current is humorous Ripple number of times, β1Represent the fundamental current phase place of electrical equipment, ITHDRepresent current harmonics total harmonic distortion,Table Show the current effective value of electrical equipment.
In the above-described embodiments, by feature is carried out to the electrical quantity under each electrical equipment steady operational status obtaining Extract, obtain the steady state characteristic of each electrical equipment, for subsequent step, the type of electrical equipment is recognized.Need Bright, in the electrical equipment discrimination method of the present invention, the electrical quantity of collection contains active power waveform and reactive power simultaneously 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 an alternative embodiment of the invention Figure, described first extraction module 102 can include：
Logging modle 1021, for recording active power waveform in unlatching or shut-down process for each electrical equipment and nothing Work(power waveform；
Discrete block 1022, for carrying out described active power waveform and reactive power waveform respectively according to the sampling period Discrete representation, for example, it is possible to described active power waveform and reactive power waveform are expressed as follows：
Segmentation module 1023, for respectively described active power waveform and reactive power waveform being divided into M section, is had Work(power waveform and the sequence segment of reactive power waveform, still as a example above formula, the sequence segment after segmentation is expressed as follows：
Analysis module 1024, for entering column hisgram to the sequence segment of described active power waveform and reactive power waveform Sequence analysis, obtain the first transient characteristic vector of each electrical equipment.
In the above-described embodiments, by aforesaid operations, the electrical equipment type identification system of the present invention achieves to treat to be distinguished The extraction of the transient characteristic of electrical equipment known.
Wherein in an embodiment, the electrical equipment type identification system of the present invention, described second extraction module 104 is also Can be used for：
According to described second electrical quantity, judge the initial time of each electrical equipment transient process；
Extract the second steady state characteristic and second transient characteristic of each electrical equipment.
Wherein in an embodiment, can in the following way, judge each electrical equipment transient process initial when Carve：
According to described second electrical quantity, judge the duration of each electrical equipment transient power waveform；
According to the duration of each electrical equipment transient power waveform described, select the analytical data of each electrical equipment Window length W0(power data comprising in data window is counted out)；
Using the analytical data window length of each electrical equipment, judge the initial time of each electrical equipment transient process.
In actual applications, the maximum active power of i-th data window and i+1 data window can be calculated respectively, when In former and later two data windows, the absolute value of the difference of maximum active power exceedes active power threshold k set in advance2When, you can Determine that electrical equipment is in transient process, subsequently judges electrical equipment in i-th data window in i+1 data window Transient process start time.
Wherein in an embodiment, the electrical equipment type identification system of the present invention, profit with the following method can also be adopted With the analytical data window length of each electrical equipment, judge the initial time of each electrical equipment transient process：
Record the wattful power of j-th sampling time point and j+1 sampling time point in each electrical equipment data window successively Rate, and calculate difference between the two；
When described difference exceedes active power threshold k set in advance2When, judge that sampling time point j is corresponding using The initial time of electric equipment transient process.
In actual applications, the electrical equipment type identification system of the present invention, can be from the beginning of electrical equipment transient process Moment, by the power difference record in two neighboring moment in active power waveform time sequence in sequence S0In, when Sequence S0Certain subsequence S1In the value of element respectively less than set active power threshold K3, and subsequence S1Length big In analytical data window length W0Half, you can judge subsequence S1In the corresponding time period, electrical equipment is in stable state, that is, Say, subsequence S1First element corresponding moment be steady-state process initial time, be also the end time of transient process, And last element corresponding moment is the end time of steady-state process, therefore, it can extract as needed electrical equipment Steady state characteristic and transient state is active and reactive power waveform time sequence P and Q, and calculate transient state active power and idle respectively Power features value, and, when the transient-wave length of time series of electrical equipment is less than time threshold T1When, judge this transient state mistake Journey is shut-down process, otherwise for opening process.
Wherein in an embodiment, the electrical equipment type identification system of the present invention, described identification module 105 is acceptable For：
The type identification model of each electrical equipment according to set up, is calculated electrical equipment index；
Described electrical equipment index is input in the electrical equipment storehouse being made up of each electrical equipment, contrast is gathered The electrical equipment type corresponding to the second electrical quantity.
In actual applications, the electrical equipment type identification system of the present invention, special according to steady state characteristic similarity and transient state Levy Similarity Measure result, output integrated similarity highest electrical equipment indexes, that is, realize power load type and run shape State on-line identification.
The electrical equipment type discrimination method of the present invention and system, simultaneously special from active power waveform and reactive power waveform Levy middle extraction electrical equipment transient characteristic, and using new transient characteristic similarity calculating method, thus in electrical equipment species Gradually increase and using the constantly complexity of technology turn to non-intrusion type power load identification propose technological challenge in the case of, Ensure the identification accuracy of non-intrusion type power load identification system, final raising non-intrusion type power load identification technique system And the practicality of Related product.
Each technical characteristic of embodiment described above can arbitrarily be combined, for making description succinct, not to above-mentioned reality The all possible combination of each technical characteristic applied in example is all described, as long as however, the combination of these technical characteristics is not deposited In contradiction, all it is considered to be the scope of this specification record.
Embodiment described above only have expressed the several embodiments of the present invention, and its description is more concrete and detailed, but simultaneously Can not 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 Say, without departing from the inventive concept of the premise, some deformation can also be made and improve, these broadly fall into the protection of the present invention Scope.Therefore, the protection domain of patent of the present invention should be defined by claims.

Claims (10)

1. a kind of electrical equipment type discrimination method is it is characterised in that comprise the steps：
Gather the first electrical quantity of various electrical equipments to be identified respectively；Wherein, described first electrical quantity includes electrical equipment Voltage in unlatching, stable operation and shut-down process, electric current, active power waveform and reactive power waveform；
Feature extraction is carried out to described first electrical quantity, the first steady state characteristic and the first transient state that obtain each electrical equipment are special Levy, and generate the first steady state characteristic vector of each electrical equipment according to described first steady state characteristic and the first transient characteristic respectively With the first transient characteristic vector；
The second electrical quantity during collection each electrical equipment real work described；Wherein, described second electrical quantity includes electricity consumption and sets Voltage during standby real work, electric current, active power waveform and reactive power waveform；
Described second electrical quantity is carried out with the second steady state characteristic and the second transient characteristic that feature extraction obtains each electrical equipment, And the second steady state characteristic vector sum of each electrical equipment is generated respectively according to described second steady state characteristic and the second transient characteristic Second transient characteristic vector；
According to the first steady state characteristic vector of each electrical equipment, the first transient characteristic vector, the second steady state characteristic vector sum the Two transient characteristic vectors, are set up the type identification model of each electrical equipment, and using described type identification model, each are used The type of electric equipment is recognized.
2. electrical equipment type discrimination method according to claim 1 is it is characterised in that the type of described electrical equipment is distinguished Know model as follows：
R - = K 1 · R W - + K 2 · R Z - ;
R W - = 1 1 + D i s t ( X 0 - , X 1 - ) 1 1 + D i s t ( X 0 - , X 2 - ) . . . 1 1 + D i s t ( X 0 - , X K - ) ;
R Z - = Σ m = 1 M 1 1 + D i s t ( Y 0 , m - , Y 1 , m - ) M Σ m = 1 M 1 1 + D i s t ( Y 0 , m - , Y 2 , m - ) M . . . Σ m = 1 M 1 1 + D i s t ( Y 0 , m - , Y K , m - ) M ;
In formula,Represent by the of each electrical equipment when first eigenvector of electrical equipment to be identified and real work The vector that similarity between two characteristic vectors is constituted, K1、K2All represent real number, and K1+K2=1,Represent by use to be identified The similarity structure of the second steady state characteristic vector of each electrical equipment in first steady state characteristic vector sum real work of electric equipment The vector becoming,Represent by each electrical equipment in the first transient characteristic vector sum real work of electrical equipment to be identified Second transient characteristic vector between similarity constitute vector,Represent the steady state characteristic vector of each electrical equipment, Represent the second steady state characteristic vector of K electrical equipment,Represent the steady state characteristic vector of k-th electrical equipmentThe second steady state characteristic vector with this electrical equipmentBetween difference value vector,Represent all M of each electrical equipment The transient characteristic vector of the histogram feature parameter composition of m section in transient state segmentation,The all M of K electrical equipment of expression are individual temporarily Second transient characteristic vector of the histogram feature parameter composition of m section in state segmentation.
3. electrical equipment type discrimination method according to claim 1 is it is characterised in that the stable state of described electrical equipment is special Levy including：Active power under described electrical equipment steady operational status, reactive power, power-factor angle, odd harmonic electric current Phase contrast and Current harmonic distortion rate with fundamental current.
4. electrical equipment type discrimination method according to claim 3 is it is characterised in that described carried out to described electrical quantity Feature extraction, the step obtaining the steady state characteristic of each electrical equipment includes：
In formula, P represents the active power of electrical equipment, UhRepresent h subharmonic voltage virtual value, IhRepresent h subharmonic current Virtual value, θhRepresent the phase place of h subharmonic current this subharmonic voltage delayed, Q represents the reactive power of electrical equipment,Table Show the power-factor angle of electrical equipment, arctan (.) represents arctan function, αidxRepresent the odd harmonic electric current of electrical equipment With fundamental current phase contrast, idx=[(h_odd-1)/2] ∈ { 1,2,3 ... }, h_odd ∈ { 1,3,5,7 ... } represent current harmonics Number of times, β1Represent the fundamental current phase place of electrical equipment, ITHDRepresent current harmonics total harmonic distortion,Represent The current effective value of electrical equipment.
5. electrical equipment type discrimination method according to claim 1 is it is characterised in that each electrical equipment of described generation First transient characteristic vector step include：
Record active power waveform in unlatching or shut-down process for each electrical equipment and reactive power waveform；
Described active power waveform and reactive power waveform are carried out respectively by discrete representation according to the sampling period；
Respectively described active power waveform and reactive power waveform are divided into M section, obtain active power waveform and reactive power ripple The sequence segment of shape；
Histogram sequence analysis is carried out to the sequence segment of described active power waveform and reactive power waveform, obtains each electricity consumption First transient characteristic vector of equipment.
6. electrical equipment type discrimination method according to claim 1 it is characterised in that described to described second electrical quantity The step carrying out the second steady state characteristic and the second transient characteristic that feature extraction obtains each electrical equipment includes：
According to described second electrical quantity, judge the initial time of each electrical equipment transient process；
Extract the second steady state characteristic and second transient characteristic of each electrical equipment.
7. electrical equipment type discrimination method according to claim 6 is it is characterised in that described join according to the described second electricity Number, judges that the step of the initial time of each electrical equipment transient process includes：
According to described second electrical quantity, judge the duration of each electrical equipment transient power waveform；
According to the duration of each electrical equipment transient power waveform described, select the analytical data window of each electrical equipment long Degree；
Using the analytical data window length of each electrical equipment, judge the initial time of each electrical equipment transient process.
8. electrical equipment type discrimination method according to claim 7 it is characterised in that described using each electrical equipment Analytical data window length, judge that the step of the initial time of each electrical equipment transient process includes：
Record in each electrical equipment data window active power between present sample time point and next sampling time point successively Difference；
When described difference exceedes active power threshold value set in advance, judge that present sample time point is corresponding electricity consumption and sets The initial time of standby transient process.
9. electrical equipment type discrimination method according to claim 1 is it is characterised in that described described each according to set up The step that the type identification model of individual electrical equipment is recognized to the type of each electrical equipment includes：
The type identification model of each electrical equipment according to set up, is calculated electrical equipment index；
Described electrical equipment index is input in the electrical equipment storehouse being made up of each electrical equipment, contrast obtains the gathering Electrical equipment type corresponding to two electrical quantitys.
10. a kind of electrical equipment type identification system is it is characterised in that include：
First acquisition module, for gathering the first electrical quantity of various electrical equipments to be identified respectively；Wherein, described first electricity Parameter includes voltage in unlatching, stable operation and shut-down process for the electrical equipment, electric current, active power waveform and reactive power Waveform；
First extraction module, for carrying out feature extraction to described first electrical quantity, obtains the first stable state of each electrical equipment Feature and the first transient characteristic, and each electrical equipment is generated respectively according to described first steady state characteristic and the first transient characteristic First steady state characteristic vector sum the first transient characteristic vector；
Second acquisition module, for gathering the second electrical quantity during each electrical equipment real work described；Wherein, described second Electrical quantity includes active power waveform and reactive power waveform during electrical equipment work；
Second extraction module, obtains the second stable state spy of each electrical equipment for described second electrical quantity is carried out with feature extraction Seek peace the second transient characteristic, and generate the of each electrical equipment according to described second steady state characteristic and the second transient characteristic respectively Two steady state characteristic vector sum the second transient characteristic vectors；
Identification module, for according to each electrical equipment first steady state characteristic vector, first transient characteristic vector, the second stable state Characteristic vector and the second transient characteristic vector, set up the type identification model of each electrical equipment, and using described type identification Model recognizes to the type of each electrical equipment.
CN201610799505.8A 2016-08-31 2016-08-31 Electric equipment type identification method and system Active CN106443244B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610799505.8A CN106443244B (en) 2016-08-31 2016-08-31 Electric equipment type identification method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610799505.8A CN106443244B (en) 2016-08-31 2016-08-31 Electric equipment type identification method and system

Publications (2)

Publication Number Publication Date
CN106443244A true CN106443244A (en) 2017-02-22
CN106443244B 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 Electric equipment type identification method and system

Country Status (1)

Country Link
CN (1) CN106443244B (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN108152630A (en) * 2017-12-26 2018-06-12 江苏智臻能源科技有限公司 A kind of non-intrusion type IH electric cookers based on mixing criterion run discrimination method
CN108376346A (en) * 2018-02-23 2018-08-07 南京飞腾电子科技有限公司 User power utilization 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
CN110135452A (en) * 2019-03-27 2019-08-16 广东浩迪创新科技有限公司 Violation electrical appliance recognition and system based on intelligent electric meter
CN110426554A (en) * 2019-08-09 2019-11-08 威胜集团有限公司 Household loads electric characteristic extracting method, device and computer readable storage medium
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
CN110720046A (en) * 2017-06-14 2020-01-21 三菱电机株式会社 Device and method for diagnosing deterioration with age
CN113224580A (en) * 2021-05-27 2021-08-06 中山市佰源凯照明电器有限公司 Wall socket with automatic fire extinguishing type protection structure
CN114629759A (en) * 2022-03-16 2022-06-14 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 signals
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 (5)

* Cited by examiner, † Cited by third party
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
US20150355246A1 (en) * 2014-02-18 2015-12-10 Encored Technologies, Inc. Apparatus, server, system and method for energy measuring
CN105186693A (en) * 2015-09-28 2015-12-23 南方电网科学研究院有限责任公司 Non-invasive electrical load identification system and method

Patent Citations (5)

* Cited by examiner, † Cited by third party
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
US20150355246A1 (en) * 2014-02-18 2015-12-10 Encored Technologies, Inc. Apparatus, server, system and method for energy measuring
CN105186693A (en) * 2015-09-28 2015-12-23 南方电网科学研究院有限责任公司 Non-invasive electrical load identification system and method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
赵云等: "基于特征相似度的非侵入式用电负荷识别模型研究", 《电气应用》 *

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110720046B (en) * 2017-06-14 2022-03-18 三菱电机株式会社 Device and method for diagnosing deterioration with age
CN110720046A (en) * 2017-06-14 2020-01-21 三菱电机株式会社 Device and method for diagnosing deterioration with age
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
CN108152630A (en) * 2017-12-26 2018-06-12 江苏智臻能源科技有限公司 A kind of non-intrusion type IH electric cookers based on mixing criterion run discrimination 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
CN108376346A (en) * 2018-02-23 2018-08-07 南京飞腾电子科技有限公司 User power utilization behavior analysis method and device
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
CN110135452A (en) * 2019-03-27 2019-08-16 广东浩迪创新科技有限公司 Violation electrical appliance recognition and system based on intelligent electric meter
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
CN110426554A (en) * 2019-08-09 2019-11-08 威胜集团有限公司 Household loads electric characteristic extracting method, device and computer readable storage medium
CN113224580A (en) * 2021-05-27 2021-08-06 中山市佰源凯照明电器有限公司 Wall socket with automatic fire extinguishing type protection structure
CN114629759A (en) * 2022-03-16 2022-06-14 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 signals
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

Also Published As

Publication number Publication date
CN106443244B (en) 2019-05-10

Similar Documents

Publication Publication Date Title
CN106443244A (en) Electric equipment type identification method and system
CN111244954B (en) Non-invasive load identification method and device
CN106786534B (en) A kind of non-intrusive electrical load transient process discrimination method and system
CN110633744B (en) Region identification method for intelligent electric meter
CN111428355B (en) Modeling method for intelligent comprehensive statistics of power load numbers
CN106483370A (en) Non-intrusion type household loads real-time identification method based on multi-feature fusion and device
CN109784388A (en) Stealing user identification method and device
CN102982394A (en) Power distribution network load parameter identification method and system
CN103675610B (en) Characterization factor extracting method in shelf depreciation on-line checking
CN108765004A (en) A method of user's electricity stealing is identified based on data mining
CN103678766A (en) Abnormal electricity consumption client detection method based on PSO algorithm
CN106908671A (en) A kind of non-intrusion type household loads intelligent detecting method and system
CN109165604A (en) The recognition methods of non-intrusion type load and its test macro based on coorinated training
CN110488112A (en) Classification metering method non-intrusion type load identification and its realized based on recognition result
CN103617568A (en) Setting method for abnormal data determination threshold in steady-state power quality early-warning mechanism
CN109767054A (en) Efficiency cloud appraisal procedure and edge efficiency gateway based on deep neural network algorithm
CN104392056B (en) A kind of directly driven wind-powered unit modeling method and device
CN109840691B (en) Non-invasive polynomial electric quantity estimation method based on deep neural network
CN110244099A (en) Stealing detection method based on user's voltage
CN110110907B (en) Method for extracting characteristic parameters of low-voltage transformer area
CN113723844A (en) Low-voltage transformer area theoretical line loss calculation method based on ensemble learning
CN110489783A (en) A kind of low-voltage platform area line loss per unit zone of reasonableness estimation method based on QRNN
CN113902062A (en) Transformer area line loss abnormal reason analysis method and device based on big data
CN113887912A (en) Non-invasive load identification method for deeply learning downward embedded equipment
CN114184870A (en) Non-invasive load identification method and equipment

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 South Power Grid International Co.,Ltd.

Address before: 510080 water Donggang 8, Dongfeng East Road, Yuexiu District, Guangzhou, Guangdong.

Patentee before: China South Power Grid International Co.,Ltd.

Patentee before: POWER GRID TECHNOLOGY RESEARCH CENTER. CHINA SOUTHERN POWER GRID

TR01 Transfer of patent right