CN105891634A - Electric appliance type identification device - Google Patents
Electric appliance type identification device Download PDFInfo
- Publication number
- CN105891634A CN105891634A CN201610214754.6A CN201610214754A CN105891634A CN 105891634 A CN105891634 A CN 105891634A CN 201610214754 A CN201610214754 A CN 201610214754A CN 105891634 A CN105891634 A CN 105891634A
- Authority
- CN
- China
- Prior art keywords
- appliance type
- current
- load
- appliance
- classifier
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- 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
Abstract
An electric appliance type identification device comprises an information acquisition module, an information processing module and a communication module, is abundant in characteristic information by adopting the electric appliance starting current characteristics comprising the starting process time, the starting current maximum value and the starting current maximum value time and the load current frequency spectrum characteristics of the electric appliances simultaneously as the identification characteristics, and is high in identification accuracy by adopting a combined classifier comprising a BP neural network classifier and a Bayes classifier to identify and classify, and simultaneously considering the characteristics of the BP neural network classifier and the Bayes classifier to identify comprehensively, and the provided starting current characteristic and load current frequency spectrum characteristic obtaining methods are simple and reliable. The electric appliance type identification device can be used in the collective public places needing the electrical appliance management, such as the student dormitories, the large-scale pedlars' markets, etc., and also can be used at other power consumption equipment management places needing the electric appliance type identification and statistics.
Description
Technical field
The present invention relates to a kind of equipment identification and sorter, especially relate to a kind of appliance type identification device.
Background technology
At present, the electric appliance load property identification method of main flow includes electric appliance load identification side based on bearing power coefficient of colligation algorithm
Method, electric appliance load recognition methods based on electromagnetic induction, electric appliance load recognition methods based on neural network algorithm, based on the cycle
The electric appliance load recognition methods etc. of property discrete transform algorithm.Various methods all can to a certain degree realize electric appliance load character
Identifying, but owing to characteristic properties is single, means of identification is single, generally there is generalization ability not and can not entirely accurate identification
Problem.
Summary of the invention
It is an object of the invention to, for the defect of present prior art, it is provided that a kind of appliance type being capable of efficient identification
Identify device.Described device includes information acquisition module, message processing module, communication module.
Described information acquisition module is for gathering the load current of electrical equipment and being converted into current digital signal;Described current digital signal
It is sent to message processing module;Described message processing module, according to the current digital signal of input, uses assembled classifier to carry out electricity
Device type identification;Described communication module is for sending the appliance type recognition result of message processing module to host computer.
The input feature vector of described assembled classifier includes the starting current feature of electrical equipment and the load current spectrum signature of electrical equipment;Described
Assembled classifier includes BP neural network classifier and Bayes classifier;When described starting current feature includes start-up course
Between, starting current maximum, the starting current maximum time.
Described information acquisition module includes current sensor, preamplifier, wave filter, A/D converter;Described information processing
The core of module is DSP, or is ARM, or is single-chip microcomputer, or is FPGA.
Described A/D converter can use the A/D converter that the core of message processing module includes.
Described information acquisition module, message processing module, all or part of function of communication module are integrated in a piece of SoC
On.
Described communication module also receives the related work instruction of host computer;Communication mode bag between described communication module and host computer
Include communication and wire communication mode;Described communication includes ZigBee, bluetooth, WiFi, 433MHz number
Biography mode;Described wire communication mode includes 485 buses, CAN, the Internet, power carrier mode.
Described load current spectrum signature is prepared by the following:
Step one, the steady state current signals of acquisition electric appliance load, and it is converted into the steady-state current digital signal of correspondence;
Step 2, steady-state current digital signal is carried out Fourier transform, obtain load current spectral characteristic;
Step 3, using the nth harmonic signal relative magnitude in load current spectral characteristic as load current spectrum signature, its
In, n=1,2 ..., M;Described M represents that harmonic wave high reps and M are more than or equal to 5.
In described assembled classifier, BP neural network classifier is Main classification device, and Bayes classifier is subsidiary classification device.
Described assembled classifier carries out appliance type knowledge method for distinguishing: when Main classification device successfully realizes appliance type identification, main
The recognition result that appliance type recognition result is assembled classifier of grader;When Main classification device fails to realize appliance type identification,
And the recognition result of Main classification device is 2 kinds or two or more appliance type, by Main classification device export 2 kinds or two or more
In appliance type recognition result, the appliance type that in the output of subsidiary classification device, probability is the highest is known as the appliance type of assembled classifier
Other result;When Main classification device fails to realize failing to provide in appliance type identification, and the recognition result of Main classification device the electrical equipment of identification
During type, the appliance type that in being exported by subsidiary classification device, probability is the highest is as the appliance type recognition result of assembled classifier.
Described starting current feature is prepared by the following by message processing module:
Before step 1, appliance starting, start the load current continuous sampling to electrical equipment and load current size is judged;When
When load current virtual value is more than ε, it is determined that electrical equipment starts start and turn to step 2;Described ε is the numerical value more than 0;
Step 2, load current to electrical equipment carry out continuous sampling, and protect with power frequency period for unit computational load current effective value
Deposit;Calculate the meansigma methods of the load current virtual value of nearest N number of power frequency period;Each within nearest N number of power frequency period
The load current virtual value of power frequency period is compared with the meansigma methods of the load current virtual value of this N number of power frequency period, and fluctuate width
When degree is respectively less than the relative error range E set, it is determined that electric appliance load enters steady statue, turns to step 3;Described N takes
Value scope is 50-500;The span of described E is 2%-20%;
Step 3, the meansigma methods of the load current virtual value within nearest N number of power frequency period is had as electric appliance load steady-state current
Valid value;Electrical equipment is started Startup time to the time between nearest N number of power frequency period initial time as the start-up course time;
Electrical equipment is started Startup time to the time between the maximum power frequency period of load current virtual value within the start-up course time as opening
The streaming current maximum time;By the load current virtual value of starting current maximum time place power frequency period and electric appliance load stable state
Ratio between current effective value is as starting current maximum.
The input feature vector of described assembled classifier also includes electric appliance load steady-state current virtual value.
The invention has the beneficial effects as follows: use the starting current feature of electrical equipment, the load current spectrum signature of electrical equipment and electricity simultaneously
Device load steady state current effective value enriches as the identification feature of described appliance type identification device, characteristic information;Employing includes
The assembled classifier of BP neural network classifier and Bayes classifier is identified classification, takes into account BP neural network classifier
Comprehensively identifying with the feature of Bayes classifier, generalization ability is high with recognition accuracy;When including start-up course of offer
Between, starting current maximum, the starting current maximum time at interior starting current characteristic-acquisition method, and load current frequency
Spectrum signature acquisition methods is simple, reliable.
Accompanying drawing explanation
Fig. 1 is the structural representation of appliance type identification device embodiment of the present invention;
Fig. 2 is the start-up course current waveform of electric filament lamp desk lamp;
Fig. 3 is the start-up course current waveform of the resistive loads such as resistance furnace;
Fig. 4 is the start-up course current waveform of monophase machine class load;
Fig. 5 is computer and the start-up course current waveform of Switching Power Supply class load;
Fig. 6 is the flow chart that appliance type identification device carries out appliance type identification.
Detailed description of the invention
Below in conjunction with accompanying drawing, the invention will be further described.
Fig. 1 is the structural representation of appliance type identification device embodiment of the present invention, at information acquisition module 101, information
Reason module 102, communication module 103.
Information acquisition module 102 is for gathering the load current of electrical equipment and load current being converted into current digital signal, electric current number
Word signal is sent to message processing module 102.Information acquisition module include current sensor, preamplifier, wave filter,
The ingredients such as A/D converter, are respectively completed the sensing of load current signal, amplify, filter and analog-digital conversion function.When negative
When load current range is bigger, the preamplifier with programmable function can be selected, or be further added by before A/D converter
One independent programmable amplifier, carries out Discrete control to the load current that scope is bigger and amplifies, make input to A/D converter
Voltage signal range be maintained at rational interval, it is ensured that conversion accuracy.Wave filter is used for filtering high fdrequency component, it is to avoid frequency spectrum mixes
Folded.
Message processing module 102, according to the current digital signal of input, uses and includes that BP neural network classifier and Bayes divide
The assembled classifier of class device realizes appliance type identification.The input feature vector of assembled classifier includes starting current feature and the electricity of electrical equipment
The load current spectrum signature of device.The core of message processing module 102 is DSP, ARM, single-chip microcomputer, or is
FPGA.When the core of message processing module includes A/D converter and this A/D converter meet require time, information gathering
A/D converter in module 101 can use the A/D converter that the core of message processing module 102 includes.
Recognition result, for realizing the communication between host computer, is sent to host computer by communication module 103.Communication module 102
And the communication mode between host computer includes communication and wire communication mode, and the communication that can use includes
The modes such as ZigBee, bluetooth, WiFi, 433MHz number biography, can include 485 buses, CAN in the wire communication mode used
The modes such as bus, the Internet, power carrier.Communication module 103 can also receive the related work instruction of host computer, completes to refer to
Fixed task.Host computer can be the server of administration section, it is also possible to be various work stations, or various mobile whole
End.
Information acquisition module 101, message processing module 102, all or part of function of communication module 103 can be integrated in
On a piece of SoC, reduce device volume, convenient installation.
Different electric equipments has different starting current features.It is illustrated in figure 2 the start-up course current wave of electric filament lamp desk lamp
Shape.Electric filament lamp is by filament electrified regulation to incandescent state, utilizes heat radiation to send the electric light source of visible ray.The filament of electric filament lamp
Generally with resistant to elevated temperatures tungsten manufacture, but the resistance of tungsten varies with temperature greatly, with RtRepresent the tungsten filament electricity when t DEG C
Resistance, with R0Represent the tungsten filament resistance when 0 DEG C, then both have following relation
Rt=R0(1+0.0045t)
Such as, if the temperature that the filament of electric filament lamp (tungsten filament) is when normal work is 2000 DEG C, one " 220V 100W "
Resistance when 2000 DEG C of normal work of the filament of electric filament lamp be
Its resistance of 0 DEG C when no power is
Its resistance of 20 DEG C when no power is
R20=R0(1+0.0045t)=52.8 Ω
I.e. electric filament lamp exceedes 9 times of its rated current at the immediate current starting energising, and maximum starting current occurs on startup
Carve.Along with the rising of electric filament lamp tungsten filament temperature, the load current of electric filament lamp exponentially reduces, subsequently into stable shape
State.
If electric appliance load steady-state current virtual value is IW, and definition electric appliance load current effective value entrance electric appliance load steady-state current
Within the relative error range of one setting of virtual value and stably within this relative error range, then electric appliance load enters steady
Determine state.Relative error range can be set as 10%, it is also possible to be set as the 2%-20% such as 2%, 5%, 15%, 20% it
Between value.In Fig. 2, the relative error range set is as 10%, when the load current of electric filament lamp is exponentially reduced to it
IW10% range of error time, such as the moment T in Fig. 2S, start-up course terminates.The start-up course time of electric filament lamp is
TS。IWFor virtual value.
Select start-up course time, starting current maximum I*, starting current maximum time special as the starting current of electrical equipment
Levy;Starting current maximum is per unit value, i.e. starting current maximum I* is maximum virtual value I of starting currentMBear with electrical equipment
Carry steady-state current virtual value IWRatio.
In Fig. 2, the start-up course time of electric filament lamp is TS;Starting current maximum I* is IM/IW, its value about 9-10 it
Between;The starting current maximum time is TM, TM=0.
It is illustrated in figure 3 the start-up course current waveform of the resistive loads such as resistance furnace.The resistive loads such as resistance furnace generally use
The lectrothermal alloy wire such as nickel chromium triangle, ferrum-chromium-aluminum, its common feature is that resistance temperature correction factor is little, and resistance value is stable.With the trade mark it is
As a example by the nichrome wire of Cr20Ni80, its resistance correction factor when 1000 DEG C is 1.014, when i.e. 1000 DEG C relative to
When 20 DEG C, the trade mark is that the nichrome wire resistance of Cr20Ni80 only increases by 1.4%.Therefore, the resistive load such as resistance furnace is logical
Steady statue is entered, the start-up course time T of the resistive load such as resistance furnace when electrically activatingS=0;Starting current maximum
I*=1;Starting current maximum time TM=0.
It is illustrated in figure 4 the start-up course current waveform of monophase machine class load.The load of monophase machine class had both had inductive load
Characteristic, has again counter electromotive force load characteristic.Startup time, due to the effect of inductance, the starting current of Startup time is 0;
Rise rapidly with after current, before counter electromotive force of motor does not sets up, reach current peak IM;Hereafter, motor speed increases
Adding, motor load electric current progressively reduces, until entering steady statue.In Fig. 4, the start-up course time of monophase machine class load
For TS;Starting current maximum I* is IM/IW;The starting current maximum time is TM。
It is illustrated in figure 5 computer and the start-up course current waveform of Switching Power Supply class load.Computer and the load of Switching Power Supply class
Because the impact on electric capacity charging, can produce a surge current the biggest in startup moment, its peak value can reach steady-state current to be had
Valid value IWSeveral times to tens times, the time is 1 to 2 power frequency period.In Fig. 5, computer and Switching Power Supply class load
The start-up course time is TS, about 1 to 2 power frequency period;Starting current maximum I* is IM/IW;Starting current maximum
Time is TM=0.
The method of the starting current feature obtaining electrical equipment is:
Before appliance starting, when load current value is 0 (being not keyed up) or the least (being in holding state), message processing module
102 i.e. start load current is carried out continuous sampling;The load current value virtual value obtained when sampling starts more than 0 or opens
When beginning more than the standby current of electrical equipment, i.e. judging that electrical equipment has been started up, recording this moment is T0.With a less non-negative threshold
Value ε distinguishes the load current value before and after appliance starting, when special hour of ε value, such as, during ε value 1mA, described knowledge
Other device does not consider ideal case, and i.e. thinking standby is also the starting state of electrical equipment;When ε value is less but it is more than the standby of electrical equipment
During electric current, such as, during ε value 20mA, the holding state of electrical equipment can be considered inactive state by described identification device, but
Simultaneously the most also can the least electrical equipment of Partial Power cause Lou identification.
Message processing module 102 carries out continuous sampling to load current, and with power frequency period for unit computational load current effective value
And preserve;When electrical equipment has been started up, and after continuous sampling reaches N number of power frequency period, the nearest N of Continuous plus while sampling
Meansigma methods I of the load current virtual value of individual power frequency periodV;Message processing module 102 is to every within nearest N number of power frequency period
The load current virtual value of individual power frequency period compares with the meansigma methods of the load current virtual value of this N number of power frequency period, by mistake
When difference (or fluctuation) amplitude is respectively less than the relative error range E set, it is determined that electric appliance load enters steady statue, this nearest N
The initial time of individual power frequency period is the finish time of start-up course, and recording this moment is T1。
Using the meansigma methods of the load current virtual value within nearest N number of power frequency period as electric appliance load steady-state current virtual value
IW;Electrical equipment is started Startup time T0To nearest N number of power frequency period initial time T1Between time as the start-up course time
TS;By T0To T1Within load current virtual value maximum power frequency period place moment be recorded as T2, by T0To T2Between
Time is as starting current maximum time TM;By T2The load current virtual value of place power frequency period and electric appliance load stable state electricity
Stream virtual value IWBetween ratio as starting current maximum I*.
Owing to not knowing electric appliance load steady-state current virtual value I in advanceW, therefore, by N number of power frequency period, i.e. one section continue time
Between TPWithin fluctuation range less than the meansigma methods of load current virtual value during the relative error range E set as electric appliance load
Steady-state current virtual value IW.Owing to the start-up course of ordinary appliances load is very fast, so, TPSpan be 1-10s, allusion quotation
Type value is 2s, and the typical value that span is 50-500, N of corresponding power frequency period quantity N is 100.Described phase
The typical value that span is 2%-20%, E to range of error E is 10%.
The input feature vector of assembled classifier also includes the load current spectrum signature of electrical equipment.The load current spectrum signature of electrical equipment is by believing
Breath processing module 102 controls information acquisition module 101, is obtained by following steps:
Step one, enter after steady statue until electric appliance load, obtain the steady state current signals of electric appliance load, and be converted into right
The steady-state current digital signal answered.
Step 2, steady-state current digital signal is carried out Fourier transform, obtain load current spectral characteristic.For ensureing Fourier
Being smoothed out of conversion, at the steady state current signals of aforementioned acquisition electric appliance load, and is converted into the steady-state current numeral of correspondence
During signal, the accuracy and speed of A/D converter needs to meet the requirement of Fourier transform, and sample frequency can be set as
10kHz, or other numerical value;Message processing module 102 carries out FFT computing to the steady-state current digital signal collected,
Calculate its frequency spectrum.
Step 3, using the nth harmonic signal relative magnitude in load current spectral characteristic as load current spectrum signature, its
In, n=1,2 ..., M;When forming the input feature value of assembled classifier, nth harmonic signal relative magnitude is in input
According to 1 in characteristic vector, 2 ..., the order of M is arranged in order.Due to load current spectral characteristic mainly by odd harmonic group
Becoming, in addition to minority electric equipment, even-order harmonic component is almost 0, accordingly it is also possible to by harmonic wave in load current spectral characteristic
Number of times be the secondary odd harmonic signal relative magnitude of n as load current spectrum signature, wherein, n=1,3 ..., M.Institute
Stating harmonic signal relative magnitude is harmonic signal amplitude and electric appliance load steady-state current virtual value IWRatio.During n=1 1 time
Harmonic wave is fundamental frequency.Described M represents harmonic wave high reps, and generally, M is more than or equal to 5.
In assembled classifier, BP neural network classifier is Main classification device, and Bayes classifier is subsidiary classification device.Combination point
The input feature vector of class device includes aforesaid starting current feature and load current spectrum signature, and the input feature vector of assembled classifier is simultaneously
Input feature vector and the input feature vector of Bayes classifier as BP neural network classifier.
Being illustrated in figure 6 appliance type identification device and carry out the flow chart of appliance type identification, appliance type identification device carries out electricity
The method of device type identification is:
Step A, wait appliance starting;
Step B, collection appliance starting current data also preserve, until appliance starting process terminates;
The appliance starting current data that step C, analysis gather, obtains the starting current feature of electrical equipment;
Step D, gather electrical equipment steady operation time data and preserve;
Data during the electrical equipment steady operation that step E, analysis gather, obtain the load current spectrum signature of electrical equipment;
Step F, using starting current feature and load current spectrum signature as the input feature vector of assembled classifier;Assembled classifier
Carry out appliance type identification;
Step G, output appliance type recognition result.
Described assembled classifier carries out appliance type knowledge method for distinguishing: when Main classification device successfully realizes appliance type identification, the most main
When the recognition result of grader output is that in unique appliance type, i.e. recognition result, unique appliance type is for being, by Main classification
The appliance type of device identification is as the appliance type recognition result of assembled classifier;Know when Main classification device fails to realize appliance type
Not, and the recognition result of Main classification device be 2 kinds or two or more appliance type, i.e. recognition result have 2 kinds or 2 kinds with
When upper appliance type is for being, by Main classification device export 2 kinds or two or more appliance type recognition result in, subsidiary classification device
The appliance type that in output, probability is the highest is as the appliance type recognition result of assembled classifier;When Main classification device fails to realize electrical equipment
Type identification, and the recognition result of Main classification device fail to be given in the appliance type of identification, i.e. recognition result and there is no appliance type
During for being, the appliance type that in being exported by subsidiary classification device, probability is the highest is as the appliance type recognition result of assembled classifier.
As a example by a simple embodiment 1, illustrate that assembled classifier carries out appliance type and knows method for distinguishing.It is provided with a group
Closing grader, its input feature vector is x={TS, I*, TM, A1, A2, A3, A4, A5, wherein, TSIt it is start-up course
Time, unit is ms;I* is starting current maximum;TMBeing the starting current maximum time, unit is ms;A1、A2、
A3、A4、A5For the 1-5 rd harmonic signal relative magnitude in load current spectral characteristic.The output of assembled classifier is { B1,
B2, B3, B4, B1、B2、B3、B4Represent assembled classifier respectively to electric filament lamp, resistance furnace, hair-dryer, computer
Recognition result exports, recognition result B1、B2、B3、B4Value be two-value key words sorting.The input feature vector of Main classification device
Also it is x={TS, I*, TM, A1, A2, A3, A4, A5, its output is { F1, F2, F3, F4, F1、F2、
F3、F4Represent Main classification device respectively the recognition result of electric filament lamp, resistance furnace, hair-dryer, computer is exported, recognition result
F1、F2、F3、F4Value be also two-value key words sorting.The input feature vector of subsidiary classification device is similarly x={TS, I*,
TM, A1, A2, A3, A4, A5, its output is { P (y1| x), P (y2| x), P (y3| x), P (y4| x) },
P(y1|x)、P(y2|x)、P(y3|x)、P(y4| x) be subsidiary classification device output posterior probability, P (y1|x)、P(y2|x)、
P(y3|x)、P(y4| the mutual size between x) shows that the current input feature of subsidiary classification device represents that identified electrical equipment belongs to white
Vehement lamp, resistance furnace, hair-dryer, the probability size of computer.
In embodiment 1, B1、B2、B3、B4Key words sorting and F1、F2、F3、F4Key words sorting all take 1,0.
When key words sorting is 1, corresponding appliance type mates with current input feature, for confirm recognition result, the most accordingly
Appliance type recognition result is yes;When key words sorting is 0, corresponding appliance type does not mates with input feature vector, fails to become true
The recognition result recognized, corresponding appliance type recognition result is no in other words.
In embodiment 1, if the recognition result key words sorting of certain Main classification device is F1F2F3F4=0100, then it is assumed that main point
Class device successfully realizes appliance type identification, therefore, does not consider the recognition result of subsidiary classification device, directly makes B1B2B3B4=
0100, i.e. the recognition result of assembled classifier is: identified electrical equipment is resistance furnace.
In embodiment 1, if the recognition result key words sorting of certain Main classification device is F1F2F3F4=1010, then it is assumed that main point
Class device fails to realize appliance type identification, and the recognition result of Main classification device is 2 kinds or two or more appliance type;Set this again
Time subsidiary classification device recognition result meet P (y1|x)<P(y3| x), then make B1B2B3B4=0010, i.e. the knowledge of assembled classifier
Other result is: identified electrical equipment is hair-dryer.
In embodiment 1, if the recognition result key words sorting of certain Main classification device is F1F2F3F4=0000, then it is assumed that main point
Class device fails to realize failing to provide in appliance type identification, and the recognition result of Main classification device the appliance type of identification;Set again now
The recognition result of subsidiary classification device meets P (y1|x)>P(y2| x) and P (y1|x)>P(y3| x) and P (y1|x)>P(y4| x), then make
B1B2B3B4=1000, i.e. the recognition result of assembled classifier is: identified electrical equipment is electric filament lamp.
Assembled classifier, the recognition result key words sorting of Main classification device can also use other scheme, such as, respectively with classification
Labelling 1 ,-1, or 0,1, or-1,1, and other schemes represent corresponding electric appliance recognition result be yes,
No.The key words sorting scheme of assembled classifier and Main classification device can be identical, it is also possible to differs.
In the input feature vector of described assembled classifier, it is also possible to include electric appliance load steady-state current virtual value IW.Such as, have 2
Planting different electrical equipment, electric cautery and resistance furnace need to identify, electric cautery, resistance furnace are all pure resistor loads, and all have resistance
Temperature correction coefficient is little, the common feature that resistance value is stable.Therefore, the aforesaid starting current feature of simple dependence and load current
They cannot be made a distinction by spectrum signature.Input feature vector increases electric appliance load steady-state current virtual value IWAfter, electric cautery merit
Rate is little, electric appliance load steady-state current virtual value IWLittle;Resistance furnace power is big, electric appliance load steady-state current virtual value IWGreatly, special
Levying difference, assembled classifier can carry out and complete identifying.
Subsidiary classification device is Bayes classifier.NBC grader (Naive Bayes Classifier), TAN can be selected to classify
Three kinds of Bayes classifiers such as device (crown pruning), BAN grader (Bayes classifier of enhancing)
Among one as subsidiary classification device.
Embodiment 2 selects NBC grader as subsidiary classification device.Naive Bayes Classification is defined as follows:
(1) set x={a1,a2,…,amIt is an item to be sorted, and each a is x characteristic attribute;
(2) there is category set C={y1,y2,…,yn};
(3) calculate P (y1|x),P(y2|x),…,P(yn|x);
If (4) P (yk| x)=max{P (y1|x),P(y2|x),…,P(yn| x) }, then x ∈ yk。
The concrete grammar calculating the (3) each conditional probability in step is:
1. find the item set to be sorted of a known classification as training sample set;
2. statistics obtains the conditional probability estimation of each characteristic attribute lower of all categories;
P(a1|y1),P(a2|y1),…,P(am|y1);
P(a1|y2),P(a2|y2),…,P(am|y2);
…;
P(a1|yn),P(a2|yn),…,P(am|yn)。
3. according to Bayes theorem, have:
Because denominator is constant for all categories, as long as therefore molecule is maximized by we;Again because at naive Bayesian
In each characteristic attribute be conditional sampling, so having:
In embodiment 2, the input feature vector of assembled classifier is { TS, I*, TM, A1, A3, A5, IW, wherein, TS
Being the start-up course time, unit is ms;I* is starting current maximum;TMBeing the starting current maximum time, unit is
ms;A1、A3、A5For 1 in load current spectral characteristic, 3,5 odd harmonic signal relative magnitude;IWBear for electrical equipment
Carrying steady-state current virtual value, unit is ampere.Require that the electrical equipment classification identified is electric filament lamp, resistance furnace, electric fan, calculating
Mechanical, electrical flatiron.Make the characteristic attribute combination x={a of Naive Bayes Classifier1,a2,a3,a4,a5,a6,a7Element in } with
Element sequentially { T in the input feature vector set of assembled classifierS, I*, TM, A1, A3, A5, IWOne_to_one corresponding;Piao
The output category set C={y of element Bayes classifier1,y2,y3,y4,y5The most respectively with electrical equipment classification electric filament lamp, resistance furnace,
Electric fan, computer, electric cautery one_to_one corresponding.
The process of training NBC grader includes:
1, characteristic attribute is carried out segmentation division, carry out sliding-model control.In embodiment 2, the characteristic attribute discretization taked
Method is:
a1: { a1<50,50≤a1≤1000,a1>1000};
a2: { a2<7,7≤a2≤11,a2>11};
a3: { a3<20,20≤a3≤300,a3>300};
a4: { a4<0.7,0.7≤a4≤0.9,a4>0.9};
a5: { a5<0.02,0.02≤a5≤0.05,a5>0.05};
a6: { a6<0.01,0.01≤a6≤0.035,a6>0.035};
a7: { a7<0.45,a7≥0.45}。
2, every electric appliances type is all gathered, and how group sample is as training sample, calculate every electric appliances type sample all simultaneously
The ratio occupied in appliance type sample, calculates P (y the most respectively1)、P(y2)、P(y3)、P(y4)、P(y5).When every class
When electrical equipment all gathers identical sample size, such as, every electric appliances all gathers the sample more than 100 groups, wherein every electric appliances with
Machine selects 100 groups of samples as training sample, and other are then as test sample, and total training sample is 500 groups, and has
P(y1)=P (y2)=P (y3)=P (y4)=P (y5)=0.2.
3, calculating the frequency (ratio) of each characteristic attribute segmentation under each class condition of training sample, statistics obtains of all categories
The conditional probability of each characteristic attribute lower is estimated, statistical computation the most respectively
P(a1<50|y1)、P(50≤a1≤1000|y1)、P(a1>1000|y1);
P(a1<50|y2)、P(50≤a1≤1000|y2)、P(a1>1000|y2);
…;
P(a1<50|y5)、P(50≤a1≤1000|y5)、P(a1>1000|y5);
P(a2<7|y1)、P(7≤a2≤11|y1)、P(a2>11|y1);
P(a2<7|y2)、P(7≤a2≤11|y2)、P(a2>11|y2);
…;
P(a2<7|y5)、P(7≤a2≤11|y5)、P(a2>11|y5);
P(a3<20|y1)、P(20≤a3≤300|y1)、P(a3>300|y1);
P(a3<20|y2)、P(20≤a3≤300|y2)、P(a3>300|y2);
…;
P(a3<20|y5)、P(20≤a3≤300|y5)、P(a3>300|y5);
P(a4<0.7|y1)、P(0.7≤a4≤0.9|y1)、P(a4>0.9|y1);
P(a4<0.7|y2)、P(0.7≤a4≤0.9|y2)、P(a4>0.9|y2);
…;
P(a4<0.7|y5)、P(0.7≤a4≤0.9|y5)、P(a4>0.9|y5);
P(a5<0.02|y1)、P(0.02≤a5≤0.05|y1)、P(a5>0.05|y1);
P(a5<0.02|y2)、P(0.02≤a5≤0.05|y2)、P(a5>0.05|y2);
P(a5<0.02|y5)、P(0.02≤a5≤0.05|y5)、P(a5>0.05|y5);
P(a6<0.01|y1)、P(0.01≤a6≤0.035|y1)、P(a6>0.035|y1);
P(a6<0.01|y2)、P(0.01≤a6≤0.035|y2)、P(a6>0.035|y2);
…;
P(a6<0.01|y5)、P(0.01≤a6≤0.035|y5)、P(a6>0.035|y5);
P(a7<0.45|y1)、P(a7≥0.45|y1);
P(a7<0.45|y2)、P(a7≥0.45|y2);
…;
P(a7<0.45|y5)、P(a7≥0.45|y5)。
Through above-mentioned step 1, step 2, step 3, NBC classifier training completes.Wherein, step 1 is to characteristic attribute
Carrying out segmentation to divide by manually determining, when each input feature vector is carried out disperse segmentaly, the quantity of segmentation is 2 sections or 2
More than Duan, such as, in embodiment 2, feature a1-a6All it is divided into 3 sections, feature a7It is divided into 2 sections.Each feature is specifically divided
For how many sections, the result after test sample can be tested by the selection of fragmentation threshold according to the Bayes classifier after training is adjusted
Whole.Step 2, step 3 have been calculated by message processing module 102 or computer.
The method using Bayes classifier to carry out classifying in the present invention is:
1, using the input feature vector of assembled classifier as the input feature vector of Bayes classifier.In example 2, by combination point
Input feature vector set { the T of class deviceS, I*, TM, A1, A3, A5, IWAs the input feature vector x of Bayes classifier, and
There is x={a1,a2,a3,a4,a5,a6,a7}。
2, the conditional probability of each characteristic attribute of all categories lower obtained according to training is estimated, determines each input feature vector attribute respectively
Segmentation place and determine its probability P (a to every electric appliances classification1|y1)~P (am|yn), wherein, electrical equipment category set is
C={y1,y2,…,yn}.In embodiment 2, electrical equipment category set C={y1,y2,y3,y4,y5The corresponding electrical equipment classification represented
It is electric filament lamp, resistance furnace, electric fan, computer, electric cautery, determines P (a1|y1)~P (a7|y5) method be use training
The conditional probability of each characteristic attribute obtained during NBC grader is estimated.
3, according to formula
Calculate every kind of other posterior probability of electric type.Because denominator P (x) is constant for all electrical equipment classifications, P (x)=1 is made to replace
P (x) value that generation is actual, the mutual size not affected between every kind of electrical equipment classification posterior probability compares, and now has
In embodiment 2, have
Use test sample that the Bayes classifier trained is tested, decide whether to adjust input spy according to test result
The discretization method (i.e. adjusting number of fragments and threshold value) levied, re-training Bayes classifier.
Main classification device is BP neural network classifier, selects 3 layers of BP neural network classifier as Main classification device.By BP
In neural network classifier input feature value, the quantity of the quantity of element, i.e. input feature vector is as the nodes of input layer, example
As, 8 in embodiment 1, or 7 in embodiment 2.The quantity of the appliance type identified by needs is as output
Node layer number, such as, in embodiment 1, output layer node is 4, and output identifies electric filament lamp, resistance furnace, blowing respectively
Machine, the result of computer;In embodiment 2, output layer node is 5, and output identifies electric filament lamp, resistance furnace, electric wind respectively
Fan, computer, the result of electric cautery.The number of nodes of middle hidden layer rule of thumb takes, such as, and embodiment 1, embodiment
In 2, the number of nodes of hidden layer can be chosen in the range of 6-15.Every electric appliances type is all gathered and organizes sample more, such as,
All gather 200 groups of samples;Randomly select some groups therein, such as 150 groups samples as training sample, remaining conduct
Test sample, is trained BP neural network classifier and tests.Multi input, 3 layers of BP neutral net of multi output are divided
Class device is due to the coupling between multi output, it is possible to can not identify sample completely when training or test;Even if
It is sample can be identified completely when training or test, is restricted by generalization ability, to newly inputted a certain feature
When attribute is identified, the recognition result that Main classification device likely exports is unique appliance type, or recognition result is 2 kinds
Or two or more appliance type, or fail to provide the appliance type of identification.
3 layers of BP neural network classifier that Main classification device can also select multiple single node to export collectively constitute, each single node
3 layers of BP neural network classifier correspondence identification one appliance type of output, such as, can use 4 lists in embodiment 1
3 layers of BP neural network classifier of node output identify electric filament lamp, resistance furnace, hair-dryer, computer respectively;Embodiment 2
In can use 3 layers of BP neural network classifier of 5 single node output identify respectively electric filament lamp, resistance furnace, electric fan,
Computer, electric cautery.When Main classification device selects 3 layers of BP neural network classifier of multiple single node output to collectively constitute, institute
The input layer number having 3 layers of BP neural network classifier that single node exports is element in Main classification device input feature value
Quantity;The number of nodes of middle hidden layer rule of thumb takes, hidden in the middle of 3 layers of BP neural network classifier of each single node output
The number of nodes of layer can be identical, it is also possible to different, selects according to respective needs.The neutral net one exported with non-single node
More sample, need all to gather every electric appliances type to organize sample, such as, all gather 200 groups of samples;If randomly selecting therein
Dry group, such as 150 groups samples are as training sample, and remaining as test sample, the BP exporting each single node is neural
Network classifier is trained and tests.3 layers of BP neural network classifier that Main classification device selects multiple single node to export are common
During composition, 3 layers of BP neural network classifier of each single node output only need to be performed the identification of a kind of appliance type, each
The training of network is relatively easy.Due to 3 layers of BP neural network classifier group that now Main classification device is exported by multiple single node
Become, separate between 3 layers of BP neural network classifier of each single node output, therefore, a certain characteristic attribute is known
Time other, the recognition result that Main classification device likely exports is unique appliance type, or recognition result be 2 kinds or 2 kinds with
Upper appliance type, or fail to provide the appliance type of identification.
The training method of BP neural network classifier can use gradient descent method, it would however also be possible to employ particle group optimizing, heredity are calculated
The optimization methods such as method.Sample collection uses the method for the starting current feature of aforesaid acquisition electrical equipment and obtains the load current of electrical equipment
The method of spectrum signature.
Claims (10)
1. an appliance type identification device, it is characterised in that include information acquisition module, message processing module, communication module;
Described information acquisition module is for gathering the load current of electrical equipment and being converted into current digital signal;Described current digital signal is sent
To message processing module;
Described message processing module, according to the current digital signal of input, uses assembled classifier to carry out appliance type identification;
Described communication module is for sending the appliance type recognition result of message processing module to host computer;
The input feature vector of described assembled classifier includes the starting current feature of electrical equipment and the load current spectrum signature of electrical equipment;
Described assembled classifier includes BP neural network classifier and Bayes classifier;
Described starting current feature includes start-up course time, starting current maximum, starting current maximum time.
2. appliance type identification device as claimed in claim 1, it is characterised in that described information acquisition module includes current sense
Device, preamplifier, wave filter, A/D converter;The core of described message processing module is DSP, or is ARM,
Or it is single-chip microcomputer, or is FPGA.
3. appliance type identification device as claimed in claim 2, it is characterised in that described A/D converter uses information processing mould
The A/D converter that the core of block includes.
4. appliance type identification device as claimed in claim 1, it is characterised in that described information acquisition module, information processing mould
Block, all or part of function of communication module are integrated on a piece of SoC.
5. appliance type identification device as claimed in claim 1, it is characterised in that described communication module also receives the phase of host computer
Close work order;Communication mode between described communication module and host computer includes communication and wire communication mode;Institute
State communication and include that ZigBee, bluetooth, WiFi, 433MHz number pass mode;Described wire communication mode includes 485
Bus, CAN, the Internet, power carrier mode.
6. the appliance type identification device as according to any one of claim 1-5, it is characterised in that in described assembled classifier,
BP neural network classifier is Main classification device, and Bayes classifier is subsidiary classification device.
7. appliance type identification device as claimed in claim 6, it is characterised in that described assembled classifier carries out appliance type knowledge
Method for distinguishing is: when Main classification device successfully realizes appliance type identification, and the appliance type recognition result of Main classification device is combination point
The recognition result of class device;When Main classification device fails to realize appliance type identification, and the recognition result of Main classification device is 2 kinds or 2
The above appliance type of kind, in 2 kinds exported by Main classification device or two or more appliance type recognition result, subsidiary classification device is defeated
Go out the middle probability the highest appliance type appliance type recognition result as assembled classifier;When Main classification device fails to realize electric type
Type identification, and the recognition result of Main classification device fail the appliance type providing identification time, in being exported by subsidiary classification device, probability is
High appliance type is as the appliance type recognition result of assembled classifier.
8. appliance type identification device as claimed in claim 6, it is characterised in that described load current spectrum signature is by following
Method obtains:
Step one, the steady state current signals of acquisition electric appliance load, and it is converted into the steady-state current digital signal of correspondence;
Step 2, steady-state current digital signal is carried out Fourier transform, obtain load current spectral characteristic;
Step 3, using the nth harmonic signal relative magnitude in load current spectral characteristic as load current spectrum signature, wherein, n
=1,2 ..., M;Described M represents that harmonic wave high reps and M are more than or equal to 5.
9. appliance type identification device as claimed in claim 6, it is characterised in that described starting current feature is by information processing mould
Block is prepared by the following:
Before step 1, appliance starting, start the load current continuous sampling to electrical equipment and load current size is judged;Work as load
When current effective value is more than ε, it is determined that electrical equipment starts start and turn to step 2;Described ε is the numerical value more than 0;
Step 2, load current to electrical equipment carry out continuous sampling, and preserve with power frequency period for unit computational load current effective value;
Calculate the meansigma methods of the load current virtual value of nearest N number of power frequency period;Each power frequency within nearest N number of power frequency period
The load current virtual value in cycle is compared with the meansigma methods of the load current virtual value of this N number of power frequency period, and fluctuating margin is equal
During less than the relative error range E set, it is determined that electric appliance load enters steady statue, turns to step 3;The value model of described N
Enclose for 50-500;The span of described E is 2%-20%;
Step 3, using effective as electric appliance load steady-state current for the meansigma methods of the load current virtual value within nearest N number of power frequency period
Value;Electrical equipment is started Startup time to the time between nearest N number of power frequency period initial time as the start-up course time;Will
Electrical equipment starts Startup time to the time between the maximum power frequency period of load current virtual value within the start-up course time as startup
The current maxima time;By the load current virtual value of starting current maximum time place power frequency period and electric appliance load stable state electricity
Ratio between stream virtual value is as starting current maximum.
10. appliance type identification device as claimed in claim 9, it is characterised in that the input feature vector of described assembled classifier also wraps
Include electric appliance load steady-state current virtual value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610214754.6A CN105891634A (en) | 2016-04-08 | 2016-04-08 | Electric appliance type identification device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610214754.6A CN105891634A (en) | 2016-04-08 | 2016-04-08 | Electric appliance type identification device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105891634A true CN105891634A (en) | 2016-08-24 |
Family
ID=57012794
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610214754.6A Pending CN105891634A (en) | 2016-04-08 | 2016-04-08 | Electric appliance type identification device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105891634A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135393A (en) * | 2019-05-27 | 2019-08-16 | 湖南工业大学 | Electrical load starting operation identification device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104158285A (en) * | 2013-05-16 | 2014-11-19 | 北京中科泛美科技有限公司 | Power consumption monitoring system for power consumption terminal |
CN104237786A (en) * | 2014-09-10 | 2014-12-24 | 海信(山东)冰箱有限公司 | Identification circuit and household appliance |
CN204086431U (en) * | 2014-09-28 | 2015-01-07 | 杭州久笛电子科技有限公司 | A kind of electricity consumption load management intelligent terminal |
CN105372541A (en) * | 2015-12-24 | 2016-03-02 | 山东大学 | Household appliance intelligent set total detection system based on pattern recognition and working method thereof |
-
2016
- 2016-04-08 CN CN201610214754.6A patent/CN105891634A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104158285A (en) * | 2013-05-16 | 2014-11-19 | 北京中科泛美科技有限公司 | Power consumption monitoring system for power consumption terminal |
CN104237786A (en) * | 2014-09-10 | 2014-12-24 | 海信(山东)冰箱有限公司 | Identification circuit and household appliance |
CN204086431U (en) * | 2014-09-28 | 2015-01-07 | 杭州久笛电子科技有限公司 | A kind of electricity consumption load management intelligent terminal |
CN105372541A (en) * | 2015-12-24 | 2016-03-02 | 山东大学 | Household appliance intelligent set total detection system based on pattern recognition and working method thereof |
Non-Patent Citations (3)
Title |
---|
梁正习: "《漏电保护器实用技术》", 30 September 1995 * |
王娟等: "基于BP神经网络的负载识别和C语言实现", 《河北省科学院学报》 * |
陈彪等: "基于RBF网络和贝叶斯分类器融合的人脸识别方法", 《电子产品世界》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135393A (en) * | 2019-05-27 | 2019-08-16 | 湖南工业大学 | Electrical load starting operation identification device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105866581B (en) | A kind of appliance type recognition methods | |
CN105759148B (en) | A kind of electrical appliance type judgement method | |
CN105913006A (en) | Electricity load type identification method | |
CN105913005A (en) | Electric appliance load type intelligent identification method and device | |
CN105785187B (en) | A kind of students' dormitory electrical appliance type judgement method | |
US8756181B2 (en) | System and method employing a self-organizing map load feature database to identify electric load types of different electric loads | |
CN106909101B (en) | A kind of non-intrusion type household electrical appliance sorter and method | |
US20130138669A1 (en) | System and method employing a hierarchical load feature database to identify electric load types of different electric loads | |
Ghosh et al. | An improved load feature extraction technique for smart Homes using fuzzy-based NILM | |
CN105891633A (en) | Dormitory electric apparatus type determination device | |
CN108875783A (en) | A kind of extreme learning machine Diagnosis Method of Transformer Faults towards unbalanced dataset | |
Du et al. | Support vector machine based methods for non-intrusive identification of miscellaneous electric loads | |
CN110070048A (en) | Device type recognition methods and system based on double secondary K-means clusters | |
CN109784276A (en) | A kind of voltage dip feature extraction based on DBN and temporarily drop source discrimination method | |
CN105759149B (en) | Students' dormitory electrical appliance type detector | |
CN109376944A (en) | The construction method and device of intelligent electric meter prediction model | |
CN105868790A (en) | Electrical load type recognizer | |
CN111582357A (en) | Electric power fingerprint identification method based on multi-dimensional integration | |
CN105913010A (en) | Electric appliance type determination device | |
CN109376752A (en) | A kind of PTM-WKNN classification method and device based on unbalanced dataset | |
CN105913009A (en) | Electric appliance type identifier | |
CN110135392A (en) | A kind of electrical load kind identification method | |
CN105891634A (en) | Electric appliance type identification device | |
CN105866580A (en) | Electric appliance type determining apparatus | |
CN109657695A (en) | A kind of fuzzy division clustering method and device based on definitive operation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160824 |
|
RJ01 | Rejection of invention patent application after publication |