CN105866580A - Electric appliance type determining apparatus - Google Patents

Abstract

The invention discloses an electric appliance type determining apparatus. The apparatus comprises an information acquisition module, an information processing module and a communication module. The apparatus simultaneously employs a starting current feature of an electric appliance, a fundamental wave voltage current phase difference of the electric appliance and a load current frequency spectrum feature as identification features of electric appliance types, and thus feature information is abundant; a combined classifier including a decision tree classifier and a Bayes classifier is employed for identification classification, features of the decision-tree classifier and the Bayes classifier are taken into consideration for integrated identification, and the identification accuracy is high; and a provided method for obtaining the fundamental wave voltage current phase difference, the starting current feature and the load current frequency spectrum feature is simple and reliable. The electric appliance type determining apparatus can be applied to some collective public places needing electric appliance management such as student dormitories, large-size markets and the like, and can also be applied to other occasions needing electrical equipment management including electric appliance type identification and statistics.

Description

Appliance type judgment means

Technical field

The present invention relates to a kind of equipment identification and sorter, especially relate to a kind of appliance type judgment means.

Background technology

At present, the electric appliance load property identification method of main flow includes electric appliance load based on bearing power coefficient of colligation algorithm Recognition methods, electric appliance load recognition methods based on electromagnetic induction, electric appliance load recognition methods based on neural network algorithm, base Electric appliance load recognition methods etc. in cyclic dispersion mapping algorithm.Various methods can be all to a certain degree to realize electrical equipment to bear Carrying the identification of character, but owing to characteristic properties is single, means of identification is single, generally there is generalization ability not and can not standard completely The problem really identified.

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 electricity being capable of efficient identification Device kind judging device.Described appliance type judgment means 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 electric current number Word signal is sent to message processing module；Described message processing module, according to the current digital signal of input, uses assembled classification Device carries out appliance type identification, judgement；Described communication module is for sending the appliance type recognition result of message processing module extremely Host computer.

The input feature vector of described assembled classifier includes the load current spectrum signature of the starting current feature of electrical equipment, electrical equipment Fundamental voltage current and phase difference with electrical equipment；Described assembled classifier includes decision tree classifier and Bayes classifier；Described Starting current feature includes starting current rush, starting average current, starting current momentum.

Described information acquisition module includes current sensor, preamplifier, wave filter, A/D converter；At described information The core of reason 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 between described communication module and host computer Mode includes communication and wire communication mode；Described communication include ZigBee, bluetooth, WiFi, 433MHz number passes 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 odd harmonic signal relative magnitude that overtone order in load current spectral characteristic is n time as negative Load current spectrum feature, n=1,3 ..., M；Described M represents that harmonic wave high reps and M are more than or equal to 3.

In described assembled classifier, decision tree 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 Time, the recognition result that appliance type recognition result is assembled classifier of Main classification device；When Main classification device fails to realize electric type Type identification, and the recognition result of Main classification device is 2 kinds or two or more appliance type, 2 kinds or 2 exported by Main classification device Planting in above appliance type recognition result, the appliance type that in the output of subsidiary classification device, probability is the highest is as the electricity of assembled classifier Device type identification result；When Main classification device fails to realize failing to be given in appliance type identification, and the recognition result of Main classification device During the appliance type identified, the appliance type that in being exported by subsidiary classification device, probability is the highest is as the appliance type of assembled classifier Recognition result.

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 sentenced Disconnected；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, with power frequency period for unit computational load current effective value And preserve；Calculate the meansigma methods of the load current virtual value of nearest N number of power frequency period；Every within nearest N number of power frequency period The load current virtual value of individual power frequency period, compared with the meansigma methods of the load current virtual value of this N number of power frequency period, fluctuates When amplitude 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, using the meansigma methods of the load current virtual value within nearest N number of power frequency period as electric appliance load stable state electricity Stream；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；Calculate Electrical equipment start to start after the meansigma methods of electric appliance load current effective value within L power frequency period and electric appliance load steady-state current it Between ratio, using this ratio as the startup current rush of electrical equipment；Calculate the electric appliance load within the start-up course time of electrical equipment Ratio between meansigma methods and the electric appliance load steady-state current of current effective value, this ratio is the most electric as the startup of electrical equipment Stream；Calculate electrical equipment starts average current and the product between the start-up course time, using this product as the starting current of electrical equipment Momentum；The span of described L is 1-5.

The input feature vector of described assembled classifier also includes electric appliance load steady-state current.

The fundamental voltage current and phase difference of described electrical equipment is prepared by the following:

Step 1., enter after steady statue until electric appliance load, synchronizes to obtain the steady state voltage signal of electric appliance load, stable state electricity Stream signal, and it is converted into corresponding steady state voltage digital signal, steady-state current digital signal；

Step 2., steady state voltage digital signal, steady-state current digital signal are carried out digital filtering respectively, extracts first-harmonic Voltage signal, fundamental current signal；

Step phase contrast 3., between analytical calculation fundamental voltage signal and fundamental current signal, by fundamental voltage signal And the phase contrast between fundamental current signal is as the fundamental voltage current and phase difference of electrical equipment.

The invention has the beneficial effects as follows: use the load current spectrum signature of the starting current feature of electrical equipment, electrical equipment simultaneously And the fundamental voltage current and phase difference of electrical equipment enriches as the identification feature of described device, characteristic information；Employing includes decision-making The assembled classifier of Tree Classifier and Bayes classifier is identified classification, takes into account decision tree classifier and Bayes classifier Feature comprehensively identify, generalization ability and recognition accuracy are high；There is provided includes the average electricity of startup current rush, startup Stream, starting current momentum at interior starting current characteristic-acquisition method, and load current spectrum signature acquisition methods is simple, can Lean on.

Accompanying drawing explanation

Fig. 1 is the structural representation of the 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 that electrical appliance type judges recognition methods flow chart.

Detailed description of the invention

Below in conjunction with accompanying drawing, the invention will be further described.

Fig. 1 is the structural representation of the embodiment of the present invention, including information acquisition module 101, message processing module 102, leads to Letter module 103.

Information acquisition module 102 is for gathering the load voltage of electrical equipment, load current and load voltage, load current being turned Changing voltage digital signal, current digital signal into, voltage digital signal, current digital signal are sent to message processing module 102. Information acquisition module includes the composition portions such as voltage sensor, current sensor, preamplifier, wave filter, A/D converter Point, it is respectively completed the sensing of load current signal, amplifies, filter and analog-digital conversion function.When load voltage, load current range Time bigger, the preamplifier with programmable function can be selected, or before A/D converter, be further added by an independent journey Control amplifier, carries out Discrete control to the load current that scope is bigger and amplifies, make input to the voltage signal range of A/D converter It is maintained at rational interval, it is ensured that conversion accuracy.Wave filter is used for filtering high fdrequency component, it is to avoid spectral aliasing.

Message processing module 102, according to the voltage digital signal inputted, current digital signal, uses and includes decision tree classification The assembled classifier of device and Bayes classifier realizes appliance type identification, realizes appliance type in other words and judges.Assembled classification The input feature vector of device includes the fundamental voltage electricity of the starting current feature of electrical equipment and the load current spectrum signature of electrical equipment and electrical equipment Stream phase contrast.The core of message processing module 102 is DSP, ARM, single-chip microcomputer, or is FPGA.Core when message processing module Including in the heart A/D converter and this A/D converter and meet when requiring, the A/D converter in information acquisition module 101 can be adopted The A/D converter included by the core of message processing module 102.

Recognition result, for realizing the communication between host computer, is sent to host computer by communication module 103.Communication module Communication mode between 102 and host computer includes communication and wire communication mode, the side wireless communication that can use Formula 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 specify 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, communication module 103 all or part of function can be integrated 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 of electric filament lamp desk lamp Current waveform.Electric filament lamp is by filament electrified regulation to incandescent state, utilizes heat radiation to send the electric light source of visible ray.Electric filament lamp Filament generally with resistant to elevated temperatures tungsten manufacture, but the resistance of tungsten varies with temperature greatly, with R_tRepresent that tungsten filament is when t DEG C Resistance, with R₀Represent the tungsten filament resistance when 0 DEG C, then both have following relation

R_t=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's " The filament of the electric filament lamp resistance when 2000 DEG C of normal work is

$R_t=\frac{U^2}{P}=\frac{220\×220}{100}=484\mathrm{\Ω}$

Its resistance of 0 DEG C when no power is

$R_0=\frac{R_t}{1+0.0045t}=\frac{484}{1+0.0045\×2000}=48.4\mathrm{\Ω}$

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 to exist Startup time.Along with the rising of electric filament lamp tungsten filament temperature, the load current of electric filament lamp exponentially reduces, subsequently into surely Determine state.

If electric appliance load steady-state current is I_W, and definition electric appliance load current effective value entrance electric appliance load steady-state current Within one relative error range set and stably within this relative error range, then electric appliance load enters and stablizes shape State.Relative error range can be set as 10%, it is also possible to is set as between the 2%-20% such as 2%, 5%, 15%, 20% Value.In Fig. 2, the relative error range set is as 10%, when the load current of electric filament lamp is exponentially reduced to its I_W's During 10% range of error, such as the moment T in Fig. 2_S, start-up course terminates.The start-up course time of electric filament lamp is T_S。I_WFor effectively Value.

Select to start current rush I_G, start average current I_D, starting current momentum Q_IStarting current as electrical equipment is special Levy；Start current rush I_G, start average current I_DIt is per unit value.It is specifically defined and is: start current rush I_GFor appliance starting T after beginning₂Electric appliance load current average within time and electric appliance load steady-state current I_WRatio；Start average current I_D For appliance starting time T_SWithin electric appliance load current average and electric appliance load steady-state current I_WRatio；Starting current rushes Amount Q_IFor starting average current I_DWith start-up course time T_SProduct, dimension is ms.Electric appliance load electric current, electric appliance load stable state Electric current is virtual value.T₂Span be 20-100ms, or 1-5 power frequency period；Such as, T₂Value 40ms, i.e. 2 Individual power frequency period.Start current rush I_GReflection is the electric current impulse size in the short time after electric appliance load starts.In part In the start-up course of electrical equipment, as the actual start-up course time T having electrical equipment_SLess than the T set₂Time, when making the start-up course of electrical equipment Between T_SEqual to T₂.Start average current I_DReflection is the electric current entirety size in electric appliance load start-up course.Starting current momentum Q_IReflect is the bulk strength of electric appliance load startup.

In Fig. 2, the startup current rush I of electric filament lamp_GFor T₀(electric filament lamp Startup time, electric current is I₀) to T₂(setting time Carving, electric current is I₂The current average of electric filament lamp and the steady-state current I of electric filament lamp between)_WRatio.Start average current I_DFor T₀(electric filament lamp Startup time) is to T_SThe current average of electric filament lamp and electric filament lamp between (electric filament lamp start-up course end time) Steady-state current I_WRatio.Starting current momentum Q_IAverage current I is started for electric filament lamp_DWith start-up course time T_SProduct.

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 are led to Frequently with 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 board As a example by number being the nichrome wire of Cr20Ni80, its resistance correction factor when 1000 DEG C is 1.014, relative when i.e. 1000 DEG C In 20 DEG C time, the trade mark is that the nichrome wire resistance of Cr20Ni80 only increases by 1.4%.The resistive loads such as resistance furnace open in energising Steady statue is entered, the actual start-up course time T of the resistive load such as resistance furnace time dynamic_S=0, therefore, make resistance furnace etc. The actual start-up course time T of resistive load_S=T₂；Such as, T is worked as₂When being set as 40ms, the start-up course time the most now T_SAlso it is 40ms.Due to resistive load T₀Moment electric current I₀、T₂Moment electric current I₂Steady-state current I with resistive load_WIt is equal, Therefore, the startup current rush I of resistive load_G=1, start average current I_D=1.

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 inductance Property load characteristic, has again counter electromotive force load characteristic.Startup time, due to the effect of inductance, the starting current of Startup time I₀It is 0；Rise rapidly with after current, before counter electromotive force of motor does not sets up, reach current peak I_M；Hereafter, motor speed increases Adding, motor load electric current progressively reduces, until entering steady statue.In Fig. 4, the startup current rush I of monophase machine class load_G For T₀(monophase machine class load Startup time, electric current is I₀) to T₂(in the moment of setting, electric current is I₂Between), monophase machine class is born The current average carried and steady-state current I_WRatio.Start average current I_DFor T₀(monophase machine class load Startup time) extremely T_SThe current average of monophase machine class load and steady-state current I between (monophase machine class load start-up course end time)_W's Ratio.Starting current momentum Q_IAverage current I is started for the load of monophase machine class_DWith start-up course time T_SProduct.

It is illustrated in figure 5 computer and the start-up course current waveform of Switching Power Supply class load.Computer and Switching Power Supply Class load, because the impact on electric capacity charging, can produce a surge current the biggest in startup moment, and its peak value can reach surely State current effective value I_WSeveral times to tens times, the time is 1 to 2 power frequency period.Owing to computer and Switching Power Supply class load The startup time short, its start-up course time T_SLikely to be less than the T set₂；As its start-up course time T_SLess than the T set₂ Time, make T_SEqual to T₂.In Fig. 5, computer and the startup current rush I of Switching Power Supply class load_GFor T₀(computer and switch electricity Source class load Startup time, electric current is I₀) to T₂(in the moment of setting, electric current is I₂Computer and the load of Switching Power Supply class between) Current average and steady-state current I_WRatio.Start average current I_DFor T₀(when computer and the load of Switching Power Supply class start Carve) to T_SComputer and the electricity of Switching Power Supply class load between (computer and Switching Power Supply class load start-up course end time) Levelling average and steady-state current I_WRatio.Starting current momentum Q_ILoad for computer and Switching Power Supply class and start average current I_DWith start-up course time T_SProduct.

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, and when special hour of ε value, such as, during ε value 1mA, described judgement fills Putting and do not consider ideal case, i.e. thinking standby is also the starting state of electrical equipment；When ε value is less but it is more than the standby current of electrical equipment Time, such as, during ε value 20mA, the holding state of electrical equipment can be considered inactive state by described judgment means, but also can simultaneously The least electrical equipment of Partial Power cause and Lou identify.

Message processing module 102 carries out continuous sampling to load current, and with power frequency period for unit computational load electric current Virtual value also preserves；When electrical equipment has been started up, and after continuous sampling reaches N number of power frequency period, while sampling, Continuous plus is Meansigma methods I of the load current virtual value of nearly N number of power frequency period_V；Within message processing module 102 is to nearest N number of power frequency period The load current virtual value of each power frequency period compares with the meansigma methods of the load current virtual value of this N number of power frequency period, When error (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(as Figure 2-Figure 5).

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 I_W； Electrical equipment is started Startup time T₀To nearest N number of power frequency period initial time T₁Between time as start-up course time T_S.Meter Calculate T₀To the T set₂Between the load current meansigma methods of (after i.e. electrical equipment starts to start within 1-5 power frequency period) electric with stable state Stream I_WRatio, using this ratio as the startup current rush I of electrical equipment_G.Calculate T₀To T_SBetween load current meansigma methods with steady State electric current I_WRatio, using this ratio as the startup average current I of electrical equipment_D.Calculate the startup average current I of electrical equipment_DWith startup Process time T_SProduct, using this product as the starting current momentum Q of electrical equipment_I。

Owing to not knowing electric appliance load steady-state current I in advance_W, therefore, by N number of power frequency period, i.e. one section duration T_PIt Interior fluctuation range is electric as electric appliance load stable state less than the meansigma methods of the load current virtual value during relative error range E set Stream I_W.Owing to the start-up course of ordinary appliances load is very fast, so, T_PSpan be 1-10s, typical value is 2s, accordingly The typical value that span is 50-500, N of power frequency period quantity N be 100.The value model of described relative error range E Enclosing the typical value for 2%-20%, E is 10%.

The input feature vector of assembled classifier also includes the load current spectrum signature of electrical equipment.The load current frequency spectrum of electrical equipment is special Levy and controlled information acquisition module 101 by message processing module 102, 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 For corresponding steady-state current digital signal.

Step 2, steady-state current digital signal is carried out Fourier transform, obtain load current spectral characteristic.For ensureing Fu Being smoothed out of vertical leaf transformation, at the steady state current signals of aforementioned acquisition electric appliance load, and is converted into the stable state electricity of correspondence During streaming digital signal, the accuracy and speed of A/D converter needs to meet the requirement of Fourier transform, and sample frequency is permissible It is set as 10kHz, or other numerical value；Message processing module 102 carries out FFT fortune to the steady-state current digital signal collected Calculate, calculate its frequency spectrum.

Step 3, using the nth harmonic signal relative magnitude in load current spectral characteristic as load current spectrum signature, Wherein, n=1,2 ..., M；When forming the input feature value of assembled classifier, nth harmonic signal relative magnitude is input spy Levy according to 1 in vector, 2 ..., the order of M is arranged in order.Owing to load current spectral characteristic is mainly made up of odd harmonic, remove Outside minority electric equipment, even-order harmonic component is almost 0, accordingly it is also possible to be n by overtone order in load current spectral characteristic Secondary odd harmonic signal relative magnitude sequentially as load current spectrum signature, wherein, n=1,3 ..., M.During n=1 1 time Harmonic wave is fundamental frequency.Described harmonic signal relative magnitude is harmonic signal amplitude and electric appliance load steady-state current I_WRatio. Described M represents harmonic wave high reps, and generally, M is more than or equal to 3.

The input feature vector of assembled classifier also includes the fundamental voltage current and phase difference of electrical equipment.Fundamental voltage current and phase difference Resistive, capacitive character, inductive load can be made a distinction, it is also possible to general inductive load and big inductive load Make a distinction.The fundamental voltage current and phase difference of electrical equipment is controlled information acquisition module 101 by message processing module 102, by with Lower step obtains:

Step 1., enter after steady statue until electric appliance load, synchronizes to obtain the steady state voltage signal of electric appliance load, stable state electricity Stream signal, and it is converted into the steady state voltage digital signal of correspondence, steady-state current digital signal.

Step 2., steady state voltage digital signal, steady-state current digital signal are carried out digital filtering respectively, extracts first-harmonic Voltage signal, fundamental current signal.

Step phase contrast 3., between analytical calculation fundamental voltage signal and fundamental current signal, by fundamental voltage signal And the phase contrast between fundamental current signal is as the fundamental voltage current and phase difference of electrical equipment.

Step 2. in steady state voltage digital signal, steady-state current digital signal are carried out digital filtering respectively, its numeral filter Ripple algorithm can select the digital filter algorithm such as Kalman filtering method, Wavelet Transform, Wiener Filter Method, adaptive-filtering.

In assembled classifier, decision tree classifier is Main classification device, and Bayes classifier is subsidiary classification device.Assembled classification The input feature vector of 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 decision tree classifier.

Electrical appliance type judges that recognition methods flow chart, described appliance type judge the concrete of recognition methods as shown in Figure 6 Step 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, voltage when gathering electrical equipment steady operation, current data preserving；

Voltage during the electrical equipment steady operation that step E, analysis gather, current data, obtain the load current frequency spectrum of electrical equipment Feature, fundamental voltage current and phase difference；

Step F, using starting current feature, load current spectrum signature, fundamental voltage current and phase difference as assembled classification The input feature vector of device；Assembled classifier carries out appliance type identification；

Step G, output appliance type recognition result.

Described assembled classifier carries out appliance type knowledge method for distinguishing: know when Main classification device successfully realizes appliance type Not, when i.e. the recognition result of Main classification device output is that in unique appliance type, i.e. recognition result, unique appliance type is for being, Using the appliance type of Main classification device identification as the appliance type recognition result of assembled classifier；When Main classification device fails to realize electricity Device type identification, 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 When two or more appliance type is for being, by Main classification device export 2 kinds or two or more appliance type recognition result in, auxiliary point The appliance type that in the output of class device, probability is the highest is as the appliance type recognition result of assembled classifier；When Main classification device fails reality Failing to be given in the appliance type of identification, i.e. recognition result in existing appliance type identification, and the recognition result of Main classification device does not has When appliance type is for being, the appliance type that in being exported by subsidiary classification device, probability is the highest is known as the appliance type of assembled classifier Other result.

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 one Individual assembled classifier, its input feature vector isWherein, I_GIt is to open Dynamic current rush；I_DIt is to start average current；Q_IIt it is starting current momentum；A₁、A₂、A₃、A₄、A₅For in load current spectral characteristic 1-5 rd harmonic signal relative magnitude,For with the fundamental voltage current and phase difference of electric loading.The output of assembled classifier is {B₁, B₂, B₃, B₄, B₁、B₂、B₃、B₄Represent assembled classifier respectively the identification of electric filament lamp, resistance furnace, hair-dryer, computer is tied Fruit output, recognition result B₁、B₂、B₃、B₄Value be two-value key words sorting.The input feature vector of Main classification device is alsoIts output is { F₁, F₂, F₃, F₄, F₁、F₂、F₃、F₄ Represent Main classification device respectively the recognition result of electric filament lamp, resistance furnace, hair-dryer, computer is exported, identify knot Really F₁、F₂、F₃、F₄Value be also two-value key words sorting.The input feature vector of subsidiary classification device is similarly x=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.Key words sorting When being 1, corresponding appliance type mates with current input feature, for the recognition result confirmed, in other words corresponding 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 the identification of confirmation As a result, 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 classification 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 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；Again If now the recognition result of subsidiary classification device meets P (y₁|x)<P(y₃| x), then make B₁B₂B₃B₄=0010, i.e. assembled classifier Recognition 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 classification device fails to realize failing to provide in appliance type identification, and the recognition result of Main classification device the appliance type of identification；Again If 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 B is made₁B₂B₃B₄=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, use respectively Key words sorting 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 I_W.Such as, there are 2 kinds not With electrical equipment, electric cautery and resistance furnace need identify, electric cautery, resistance furnace are all pure resistor loads, and all have resistance temperature Correction factor is little, the common feature that resistance value is stable.Therefore, the aforesaid starting current feature of simple dependence and load current frequency spectrum They cannot be made a distinction by feature, the fundamental voltage current and phase difference feature of electrical equipment.Input feature vector increases electric appliance load steady State electric current I_WAfter, electric cautery power is little, electric appliance load steady-state current I_WLittle；Resistance furnace power is big, electric appliance load steady-state current I_W Greatly, feature is different, and 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) it In 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,…,a_mIt is an item to be sorted, and each a is x characteristic attribute；

(2) there is category set C={y₁,y₂,…,y_n}；

(3) calculate P (y₁|x),P(y₂|x),…,P(y_n|x)；

If (4) P (y_k| x)=max{P (y₁|x),P(y₂|x),…,P(y_n| x) }, then x ∈ y_k。

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(a_m|y₁)；

P(a₁|y₂),P(a₂|y₂),…,P(a_m|y₂)；

…；

P(a₁|y_n),P(a₂|y_n),…,P(a_m|y_n)。

3. according to Bayes theorem, have:

$P\left(y_i\right|x)=\frac{P\left(x\right|y_i)P\left(y_i\right)}{P\left(x\right)}---\left(1\right)$

Because denominator is constant for all categories, as long as therefore molecule is maximized by we；Again because in simplicity In Bayes, each characteristic attribute is conditional sampling, so having:

$P\left(x\right|y_i)P\left(y_i\right)=P\left(a_1\right|y_i)P\left(a_2\right|y_i)...P\left(a_m\right|y_i)P\left(y_i\right)=P\left(y_i\right)\underset{j=1}{\overset{m}{\&Pi;}}P\left(a_j\right|y_i)$

In embodiment 2, the input feature vector of assembled classifier isWherein, I_GIt is to start current rush；I_DIt is to start average current；Q_IIt it is starting current momentum；A₁、A₃For load current spectral characteristic In 1,3 odd harmonic signal relative magnitude；For the fundamental voltage current and phase difference of electrical equipment, unit is degree, and first-harmonic electricity When pressure is ahead of fundamental current,I_WFor electric appliance load steady-state current, unit is ampere.Require that the electrical equipment classification identified is Electric filament lamp, resistance furnace, electric fan, computer, electric cautery.Make the characteristic attribute combination x={a of Naive Bayes Classifier₁,a₂, a₃,a₄,a₅,a₆,a₇Element in } is with the element in the input feature vector set of assembled classifier sequentially One_to_one corresponding；The output category set C={y of Naive Bayes Classifier₁,y₂,y₃,y₄,y₅} The 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 taked is discrete Change method is:

a₁: { a₁<4.2,4.2≤a₁≤7,a₁>7}；

a₂: { a₂<1.2,1.2≤a₂≤1.9,a₂>1.9}；

a₃: { a₃<120,120≤a₃≤560,a₃>560}；

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<-6,-6≤a₆≤18,a₆>18}；

a₇: { a₇<0.45,a₇≥0.45}。

2, every electric appliances type is all gathered, and how group sample, as training sample, calculates every electric appliances type sample simultaneously and exists The ratio occupied in all appliance type samples, calculates P (y the most respectively₁)、P(y₂)、P(y₃)、P(y₄)、P(y₅).When every class electricity When device all gathers identical sample size, such as, every electric appliances all gathers the sample more than 100 groups, and wherein every electric appliances is random Selecting 100 groups of samples as training sample, 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 all kinds of Not Xia each characteristic attribute conditional probability estimate, statistical computation the most respectively

P(a₁<4.2|y₁)、P(4.2≤a₁≤7|y₁)、P(a₁>7|y₁)；

P(a₁<4.2|y₂)、P(4.2≤a₁≤7|y₂)、P(a₁>7|y₂)；

…；

P(a₁<4.2|y₅)、P(4.2≤a₁≤7|y₅)、P(a₁>7|y₅)；

P(a₂<1.2|y₁)、P(1.2≤a₂≤1.9|y₁)、P(a₂>1.9|y₁)；

P(a₂<1.2|y₂)、P(1.2≤a₂≤1.9|y₂)、P(a₂>1.9|y₂)；

…；

P(a₂<1.2|y₅)、P(1.2≤a₂≤1.9|y₅)、P(a₂>1.9|y₅)；

P(a₃<120|y₁)、P(120≤a₃≤560|y₁)、P(a₃>560|y₁)；

P(a₃<120|y₂)、P(120≤a₃≤560|y₂)、P(a₃>560|y₂)；

…；

P(a₃<120|y₅)、P(120≤a₃≤560|y₅)、P(a₃>560|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<-6|y₁)、P(-6≤a₆≤18|y₁)、P(a₆>18|y₁)；

P(a₆<-6|y₂)、P(-6≤a₆≤18|y₂)、P(a₆>18|y₂)；

…；

P(a₆<-6|y₅)、P(-6≤a₆≤18|y₅)、P(a₆>18|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, characteristic attribute is entered by step 1 Row segmentation divides by manually determining, when each input feature vector is carried out disperse segmentaly, the quantity of segmentation is 2 sections or 2 sections Above, 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 into how many sections, Result after test sample can be tested by the selection of fragmentation threshold according to the Bayes classifier after training is adjusted.Step 2, step 3 has 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, will combination The input feature vector set of graderAs the input feature vector x of Bayes classifier, And have 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 respectively The segmentation place of attribute also determines its probability P (a to every electric appliances classification₁|y₁)～P (a_m|y_n), wherein, electrical equipment category set For C={y₁,y₂,…,y_n}.In embodiment 2, electrical equipment category set C={y₁,y₂,y₃,y₄,y₅The corresponding electrical equipment classification that represents is Electric filament lamp, resistance furnace, electric fan, computer, electric cautery, determine P (a₁|y₁)～P (a₇|y₅) method be use training NBC divide The conditional probability of each characteristic attribute obtained during class device is estimated.

3, according to formula

$P\left(y_i\right|x)=\frac{P\left(x\right|y_i)P\left(y_i\right)}{P\left(x\right)}$

Calculate every kind of other posterior probability of electric type.Because denominator P (x) is constant for all electrical equipment classifications, make P (x) =1 substitutes actual P (x) value, and the mutual size not affected between every kind of electrical equipment classification posterior probability compares, and now has

$P\left(y_i\right|x)=P\left(x\right|y_i)P\left(y_i\right)=P\left(y_i\right)\underset{j=1}{\overset{m}{\&Pi;}}P\left(a_j\right|y_i)$

In embodiment 2, have

$P\left(y_1\right|x)=P\left(x\right|y_1)P\left(y_1\right)=P\left(y_1\right)\underset{j=1}{\overset{7}{\&Pi;}}P\left(a_j\right|y_1);$

$P\left(y_2\right|x)=P\left(x\right|y_2)P\left(y_2\right)=P\left(y_2\right)\underset{j=1}{\overset{7}{\&Pi;}}P\left(a_j\right|y_2);$

$P\left(y_3\right|x)=P\left(x\right|y_3)P\left(y_3\right)=P\left(y_3\right)\underset{j=1}{\overset{7}{\&Pi;}}P\left(a_j\right|y_3);$

$P\left(y_4\right|x)=P\left(x\right|y_4)P\left(y_4\right)=P\left(y_4\right)\underset{j=1}{\overset{7}{\&Pi;}}P\left(a_j\right|y_4);$

$P\left(y_5\right|x)=P\left(x\right|y_5)P\left(y_5\right)=P\left(y_5\right)\underset{j=1}{\overset{7}{\&Pi;}}P\left(a_j\right|y_5).$

Using test sample to test the Bayes classifier trained, it is right to decide whether to adjust according to test result The discretization method (i.e. adjusting number of fragments and threshold value) of input feature vector, re-training Bayes classifier.

Main classification device is decision tree classifier, and the algorithm of decision tree classifier can select ID3, C4.5, CART etc..Implement Example 2 selects to use ID3 decision tree classifier as Main classification device.The several of ID3 decision tree classifier are defined as follows:

If D is the division carried out training tuple by classification, then the entropy of D is expressed as:

$\inf o\left(D\right)=-\underset{i=1}{\overset{u}{\&Sigma;}}{p}_i{\log }_2\left(p_i\right);$

Wherein p_iRepresent the probability that i-th classification occurs in whole training tuple (i.e. sample), can be with belonging to this type of The quantity of other element is divided by training tuple elements total quantity as estimation.The practical significance of entropy represents it is the class label of tuple in D Required average information.

Assume to divide training tuple D by attribute A, then the expectation information that D is divided by A is:

${\mathrm{info}}_A\left(D\right)=-\underset{j=1}{\overset{v}{\&Sigma;}}\frac{\left|D_j\right|}{\left|D\right|}\inf o\left(D_j\right)---\left(2\right)$

And information gain is both differences:

Gain (A)=info (D)-info_A(D) (3)

ID3 algorithm, when needing division every time, calculates the ratio of profit increase of each attribute, then selects the attribute that ratio of profit increase is maximum Divide.

Training ID3 decision tree classifier can use characteristic attribute discretization method, it would however also be possible to employ characteristic attribute continuously Potential disintegrating method.Its concrete grammar is: detect all of attribute, and the attribute selecting information gain maximum produces decision tree knot Point, is set up branch by the different values of this attribute, then subset recursive call the method for each branch is set up decision tree node Branch, until all subsets only comprise same category of data.Finally obtaining a decision tree, it can be used to new Sample is classified.In example 2, every electric appliances type is all gathered and organizes sample more, randomly draw part as training sample This, remaining is as test sample.

The process of characteristic attribute discretization method training ID3 decision tree classifier includes:

1) each characteristic attribute is realized feature differentiation.In embodiment 2, the feature differentiation method taked is:

a₁: { a₁<4.2,4.2≤a₁≤7,a₁>7}；

a₂: { a₂<1.8,a₂≥1.8}；

a₃: { a₃<280,a₃≥280}；

a₄: { a₄<0.85,a₄≥0.85}；

a₅: { a₅<0.1,a₅≥0.05}；

a₆: { a₆<-12,-12≤a₆≤12,a₆>12}；

a₇: { a₇<0.45,a₇≥0.45}。

2) information gain of each attribute is calculated.In example 2, count respectively according to formula (2) and formula (3) for training sample Calculate the information gain of 7 characteristic attributes.

3) select to have the attribute of maximum information gain as division (decision-making) attribute of this division and decision tree node, Obtain division result, set up branch；If sample is all at same class, then this node becomes leaves, and uses such labelling.

4) on the basis of having divided result, recurrence uses abovementioned steps to calculate the Split Attribute of child node, sets up and divides , finally give whole decision tree.

Through above-mentioned step, ID3 decision tree classifier has been trained.Wherein, step 1) characteristic attribute is carried out segmentation Feature differentiation is by manually determining, when each input feature vector is carried out disperse segmentaly, the quantity of segmentation be 2 sections or 2 sections with On, such as, in embodiment 2, feature a₁、a₆It is divided into 3 sections, feature a₂-a₅、a₇All it is divided into 2 sections.Each feature is specifically divided into how many Section, the result after test sample can be tested by the selection of fragmentation threshold according to the decision tree classifier after training is adjusted. Step 2) to step 4) completed by message processing module 102 or computer.

The process of the potential disintegrating method training ID3 decision tree classifier of characteristic attribute includes continuously:

I, the information gain of each attribute is calculated.First element in training sample D is sorted according to characteristic attribute, then each two phase The intermediate point of neighbors can regard potential split point as, and from the beginning of first potential split point, division D also calculates two set Expecting information, the point with minimum expectation information is referred to as the best splitting point of this attribute, and its information is expected as this attribute Information is expected.In example 2, for training sample, find out best splitting point and calculate 7 spies respectively according to formula (2) and formula (3) Levy the information gain of attribute.

II, select to have the attribute of maximum information gain as division (decision-making) attribute of this division and decision tree knot Point, obtains division result, sets up branch；If sample is all at same class, then this node becomes leaves, and uses such labelling.

III, on the basis of having divided result, recurrence uses abovementioned steps to calculate the Split Attribute of child node, sets up and divides , finally give whole decision tree.

During the training of aforementioned decision tree, when all samples of given node belong to same class, terminate recursive procedure, Decision tree has built up.All samples of given node belong to same class, it may be possible to single electric type other confirmation result, also It is probably the negative decision of all appliance type.

During the training of aforementioned decision tree classifier, can be used to Further Division sample when not remaining attribute Time, needing also exist for terminating recursive procedure, but now some subset is not the most pure collection, i.e. element in set is not belonging to same class Not；Increase characteristic attribute at this point it is possible to use, such as, increase by 5 times, 7 times in load current spectral characteristic in example 2 Etc. odd harmonic signal relative magnitude as new characteristic attribute, decision tree is carried out re-training.When training after or again The final part subset of decision tree classifier after training is not pure collection, when the element in its set is not belonging to same category, Do not use subset " majority voting " mode using classifications most for occurrence number in subset as this node classification, but directly by son The all categories concentrated is as this node classification, and the most described decision tree classifier can export multiple electric type other confirmation knot Really.

Main classification device can also select to be made up of multiple two class output decision tree classifiers, and each two class output decision trees are divided Class device correspondence identification one appliance type, such as, can use 4 two class output decision tree classifiers to know respectively in embodiment 1 Other electric filament lamp, resistance furnace, hair-dryer, computer, can use 5 two class output decision tree classifiers to know respectively in embodiment 2 Other electric filament lamp, resistance furnace, electric fan, computer, electric cautery.Main classification device selects multiple two class output decision tree classifiers common During composition, the input feature vector of all two class output decision tree classifiers is the input feature vector of Main classification device, all of training sample This is all as the training sample of each two class output decision tree classifiers.Main classification device selects multiple two class output decision tree classifications When device collectively constitutes, each two class output decision tree classifiers only need to be performed the identification of a kind of appliance type, the instruction of decision tree Practice relatively easy.After the training of certain two class output decision tree classifier described terminates, or increase characteristic attribute again After training terminates, some subset is not the most pure collection, i.e. has subset can't confirm to input whether attribute belongs to the output of this two class During the appliance type that decision tree classifier is identified, it is yes by the node definition at this subset place, i.e. allows this two class export decision-making Tree Classifier judges that the characteristic attribute this time inputted belongs to identified appliance type in this case.Due to now Main classification Device is made up of multiple two class output decision tree classifiers, separate, therefore, to certain between each two class output decision tree classifiers When one characteristic attribute is identified, the recognition result that Main classification device likely exports is unique appliance type, or identifies knot Fruit is 2 kinds or two or more appliance type, or fails to provide the appliance type of identification.

Claims (10)

1. an appliance type judgment means, 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 is believed Number 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 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, the load current spectrum signature of electrical equipment and electricity The fundamental voltage current and phase difference of device；

Described assembled classifier includes decision tree classifier and Bayes classifier；

Described starting current feature includes starting current rush, starting average current, starting current momentum.

2. appliance type judgment means as claimed in claim 1, it is characterised in that described information acquisition module includes that electric current passes Sensor, preamplifier, wave filter, A/D converter；The core of described message processing module is DSP, or is ARM, or is Single-chip microcomputer, or be FPGA.

3. appliance type judgment means as claimed in claim 2, it is characterised in that described A/D converter uses information processing The A/D converter that the core of module includes.

4. appliance type judgment means as claimed in claim 1, it is characterised in that described information acquisition module, information processing Module, all or part of function of communication module are integrated on a piece of SoC.

5. the appliance type judgment means as according to any one of claim 1-4, it is characterised in that described assembled classifier In, decision tree classifier is Main classification device, and Bayes classifier is subsidiary classification device.

6. appliance type judgment means as claimed in claim 5, it is characterised in that described assembled classifier carries out appliance type Knowing method for distinguishing is: when Main classification device successfully realizes appliance type identification, the appliance type recognition result of Main classification device is group Close the recognition result of grader；When Main classification device fails to realize appliance type identification, and the recognition result of Main classification device be 2 kinds or Two or more appliance type of person, in 2 kinds that Main classification device is exported or two or more appliance type recognition result, 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 electricity Device type identification, and the recognition result of Main classification device fail the appliance type providing identification time, by subsidiary classification device export in The highest appliance type of probability is as the appliance type recognition result of assembled classifier.

7. appliance type judgment means as claimed in claim 5, it is characterised in that described load current spectrum signature by with Lower 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 odd harmonic signal relative magnitude that overtone order in load current spectral characteristic is n time as load electricity Stream spectrum signature, wherein, n=1,3 ..., M；Described M represents that harmonic wave high reps and M are more than or equal to 3.

8. appliance type judgment means as claimed in claim 5, it is characterised in that described starting current feature is by information processing Module 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；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 work within nearest N number of power frequency period Frequently 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, fluctuating margin When being respectively 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 the meansigma methods of the load current virtual value within nearest N number of power frequency period as electric appliance load steady-state current； 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；Calculate electricity Device start to start after electric appliance load current effective value within L power frequency period meansigma methods and electric appliance load steady-state current between Ratio, using this ratio as the startup current rush of electrical equipment；Calculate the electric appliance load electricity within the start-up course time of electrical equipment Ratio between meansigma methods and the electric appliance load steady-state current of stream virtual value, using this ratio as the startup average current of electrical equipment； Calculate electrical equipment starts average current and the product between the start-up course time, is rushed as the starting current of electrical equipment by this product Amount；The span of described L is 1-5.

9. appliance type judgment means as claimed in claim 8, it is characterised in that the input feature vector of described assembled classifier is also Including electric appliance load steady-state current.

10. appliance type judgment means as claimed in claim 5, it is characterised in that the fundamental voltage electric current phase of described electrical equipment Potential difference is prepared by the following:

Step 1., enter after steady statue until electric appliance load, synchronizes to obtain the steady state voltage signal of electric appliance load, steady-state current letter Number, and it is converted into corresponding steady state voltage digital signal, steady-state current digital signal；

Step 2., steady state voltage digital signal, steady-state current digital signal are carried out digital filtering respectively, extracts fundamental voltage Signal, fundamental current signal；

Step phase contrast 3., between analytical calculation fundamental voltage signal and fundamental current signal, by fundamental voltage signal and base Phase contrast between signal wave current is as the fundamental voltage current and phase difference of electrical equipment.