CN105785187A - Electric appliance type determination method for students' dormitory - Google Patents

Abstract

The present invention provides an electric appliance type determination method for a students' dormitory. An electric appliance identification device consisting of an information acquisition module, an information processing module and a communication module is employed to realize the electric appliance type determination method for the students' dormitory. The electric appliance type determination method is abundant in feature information through adoption of the starting current features, the fundamental wave voltage current phase difference and the load current frequency spectrum features of an electric appliance, and is combined in the features of two classifiers to perform comprehensive identification and high in identification accuracy through adoption of a combination classifier consisting of a support vector classifier and a Bayes classifier to perform identification classification. The fundamental wave voltage and current phase difference, starting current feature and load current frequency spectrum feature obtaining methods are simple and reliable. The electric appliance identification device may be used at collective public places requiring electricity load management such as a students' dormitory and the like, and may be also used at the occasions requiring electricity device management for determination and statistics of electricity load types.

Description

A kind of students' dormitory electrical appliance type judgement method

Technical field

The present invention relates to a kind of equipment identification and sorting technique, especially relate to a kind of students' dormitory electrical appliance type judgement method.

Background technology

At present, the electrical equipment character of main flow or appliance type recognition methods include the electrical appliance recognition based on bearing power coefficient of colligation algorithm, the electrical appliance recognition based on electromagnetic induction, the electrical appliance recognition based on neural network algorithm, electrical appliance recognition etc. based on cyclic dispersion mapping algorithm.Various methods all can be to a certain degree the identification realizing electrical equipment character, but owing to characteristic properties is single, means of identification is single, it is common to there is generalization ability not and can not the problem of entirely accurate identification.

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 students' dormitory electrical appliance type judgement method being capable of efficient identification.Described students' dormitory electrical appliance type judgement method by include information acquisition module, message processing module, communication module electrical equipment identification device realize.

Described information acquisition module is for gathering the load current of electrical equipment and converting current digital signal to；Described current digital signal is sent to message processing module；Described message processing module, according to the current digital signal of input, adopts 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 fundamental voltage current and phase difference of the starting current feature of electrical equipment, the load current spectrum signature of electrical equipment and electrical equipment；Described assembled classifier includes support vector machine 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；The core of described message processing module is DSP, or is ARM, or is single-chip microcomputer, or is FPGA.

Described A/D converter can adopt the A/D converter that the core of message processing module includes.

Described information acquisition module, message processing module, communication module all or part of function be integrated on a piece of SoC.

Described communication module also receives the related work instruction of host computer；Communication mode between described communication module and host computer includes 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 obtains by the following method:

Step one, obtain electrical equipment steady state current signals, and be converted into correspondence steady-state current digital signal；

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 current spectrum signature, n=1,3 ..., M；Described M represents that the most high reps of harmonic wave and M are be more than or equal to 3.

In described assembled classifier, support vector machine 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, the recognition result that appliance type recognition result is assembled classifier of Main classification device；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 in 2 kinds of the output of Main classification device or two or more appliance type recognition result, the appliance type that in the output of subsidiary classification device, probability is the highest is as the appliance type recognition result of assembled classifier；When Main classification device fails to realize appliance type identification, and the recognition result of Main classification device fails the appliance type providing identification time, 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 obtained by the following method 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 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, computational load current effective value preserving in units of power frequency period；Calculate the meansigma methods of the load current virtual value of nearest N number of power frequency period；The load current virtual value of each power frequency period within nearest N number of power frequency period is compared with the meansigma methods of the load current virtual value of this N number of power frequency period, when fluctuating margin is respectively less than the relative error range E of setting, judge that electrical equipment enters steady statue, turn to step 3；The span of described N 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 steady-state current；Electrical equipment is started Startup time to time as the start-up course time between nearest N number of power frequency period initial time；Calculate after electrical equipment starts to start the ratio between meansigma methods and the electric appliance load steady-state current of the electric appliance load current effective value within L power frequency period, using this ratio startup current rush as electrical equipment；Calculate the ratio between meansigma methods and the electric appliance load steady-state current of the electric appliance load current effective value within the start-up course time of electrical equipment, using this ratio startup average current as electrical equipment；What calculate electrical equipment starts average current and the product between the start-up course time, using this product starting current momentum as electrical equipment；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 obtains by the following method:

Step 1., enter after steady statue until electrical equipment, synchronizes to obtain the steady state voltage signal of electrical equipment, steady state current signals, and 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, using the fundamental voltage current and phase difference as electrical equipment of the phase contrast between fundamental voltage signal and fundamental current signal.

The invention has the beneficial effects as follows: adopting the starting current feature of electrical equipment, the load current spectrum signature of electrical equipment and the fundamental voltage current and phase difference of electrical equipment as the identification feature of described students' dormitory electrical appliance type judgement method, characteristic information enriches simultaneously；Adopting the assembled classifier including support vector machine classifier and Bayes classifier to be identified classification, the feature taking into account support vector machine classifier and Bayes classifier comprehensively identifies, generalization ability is high with recognition accuracy；The starting current characteristic-acquisition method including starting current rush, startup average current, starting current momentum provided, and load current spectrum signature acquisition methods is simple, reliable.

Accompanying drawing explanation

Fig. 1 is the structural representation of electrical equipment identification device embodiment in 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 students' dormitory electrical appliance type judgement method 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 electrical equipment identification device embodiment in the present invention, including information acquisition module 101, message processing module 102, communication module 103.

Information acquisition module 102 is for gathering the load voltage of electrical equipment, load current and converting load voltage, load current to voltage digital signal, current digital signal, and voltage digital signal, current digital signal are sent to message processing module 102.Information acquisition module includes the ingredients such as voltage sensor, current sensor, preamplifier, wave filter, A/D converter, is respectively completed load voltage, the sensing of load current signal, amplification, filtering and analog-digital conversion function.When load current range is bigger, the preamplifier with programmable function can be selected, or before A/D converter, it is further added by an independent programmable amplifier, the load current that scope is bigger is carried out Discrete control amplify, input is made to be maintained at rational interval to the voltage signal range of A/D converter, 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 of input, current digital signal, adopts the assembled classifier including support vector machine classifier and Bayes classifier to realize appliance type identification.The input feature vector of assembled classifier includes the fundamental voltage current and phase difference of the starting current feature of electrical equipment, the load current spectrum signature of electrical equipment and electrical equipment.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, the A/D converter in information acquisition module 101 can adopt 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 mode between communication module 102 and host computer includes communication and wire communication mode, the communication that can adopt includes the modes such as ZigBee, bluetooth, WiFi, 433MHz number biography, it is possible to the wire communication mode of employing includes the modes such as 485 buses, CAN, the Internet, power carrier.Communication module 103 can also receive the related work instruction of host computer, completes the task specified.Host computer can be the server of administration section, it is also possible to be various work stations, or various mobile terminal.

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 install.

Different electric equipments has different starting current features.It is illustrated in figure 2 the start-up course current waveform of electric filament lamp desk lamp.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 manufactures typically by resistant to elevated temperatures tungsten, but the resistance of tungsten varies with temperature greatly, with R_tRepresent the tungsten filament resistance when t DEG C, 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 operation is 2000 DEG C, the filament of the electric filament lamp of " 220V100W " resistance when 2000 DEG C of normal operation 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

Namely electric filament lamp exceedes 9 times of its rated current at the immediate current starting energising, and maximum starting current occurs at Startup time.Along with the rising of electric filament lamp tungsten filament temperature, the load current of electric filament lamp exponentially reduces, subsequently into steady statue.

If electrical equipment steady-state current virtual value is I_W, and define within a relative error range set of electric current virtual value entrance electrical equipment steady-state current virtual value and stablize within this relative error range, then electrical equipment enters steady statue.Relative error range can set that to be 10%, it is also possible to is set as the value between the 2%-20% such as 2%, 5%, 15%, 20%.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_W10% range of error time, 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 virtual value.

Select to start current rush I_G, start average current I_D, starting current momentum Q_IStarting current feature as electrical equipment；Start current rush I_G, start average current I_DIt is per unit value.It is specifically defined and is: start current rush I_GRear T is started for appliance starting₂Electric appliance load current average within time and electric appliance load steady-state current I_WRatio；Start average current I_DFor appliance starting time T_SWithin electric appliance load current average and electric appliance load steady-state current I_WRatio；Starting current momentum Q_IFor starting average current I_DWith start-up course time T_SProduct, dimension is ms.Electric appliance load electric current, electric appliance load steady-state current are virtual value.T₂Span be 20-100ms, or 1-5 power frequency period；Such as, T₂Value 40ms, i.e. 2 power frequency periods.Start current rush I_GReflection is the electric current impulse size in the short time after electric appliance load starts.In the start-up course of part electrical equipment, as the actual start-up course time T having electrical equipment_SLess than the T set₂Time, make the start-up course time T of electrical equipment_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_IWhat reflect 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(in the moment of setting, electric current is I₂) between the steady-state current I of current average and electric filament lamp of electric filament lamp_WRatio.Start average current I_DFor T₀(electric filament lamp Startup time) is to T_SThe steady-state current I of the current average of electric filament lamp and electric filament lamp between (electric filament lamp start-up course end time)_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 generally adopt the lectrothermal alloy wire such as nickel chromium triangle, ferrum-chromium-aluminum, and its common feature is that resistance temperature correction factor is little, and resistance value is stable.The nichrome wire being Cr20Ni80 for the trade mark, its resistance correction factor when 1000 DEG C is 1.014, namely 1000 DEG C time relative to 20 DEG C time, the nichrome wire resistance that the trade mark is Cr20Ni80 only increases by 1.4%.The actual start-up course time T of the resistive loads such as the resistive loads such as resistance furnace enter steady statue when energising starts, resistance furnace_S=0, therefore, make the actual start-up course time T of the resistive loads such as resistance furnace_S=T₂；Such as, T is worked as₂When being set as 40ms, then start-up course time T now_SAlso it is 40ms.Due to resistive load T₀Moment electric current I₀、T₂Moment electric current I₂Steady-state current I with resistive load_WEqual, 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.Monophase machine class load had both had inductive load characteristic, had again counter electromotive force load characteristic.Startup time, due to the effect of inductance, the starting current I of Startup time₀It is 0；Rise rapidly with after current, before counter electromotive force of motor does not set up, reach current peak I_M；Hereafter, motor speed increases, and motor load electric current progressively reduces, until entering steady statue.In Fig. 4, the startup current rush I of monophase machine class load_GFor T₀(monophase machine class load Startup time, electric current is I₀) to T₂(in the moment of setting, electric current is I₂) between current average and the steady-state current I of monophase machine class load_WRatio.Start average current I_DFor T₀(monophase machine class load Startup time) is to T_SThe current average of monophase machine class load and steady-state current I between (monophase machine class load start-up course end time)_WRatio.Starting current momentum Q_IAverage current I is started for monophase machine class load_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 very big surge current in startup moment, and its peak value can reach steady-state current virtual value I_WSeveral times to tens times, the time is 1 to 2 power frequency period.Owing to the startup time of computer and Switching Power Supply class load is short, its start-up course time T_SIt is likely to be less than the T of setting₂；As its start-up course time T_SLess than the T set₂Time, make T_SEqual to T₂.In Fig. 5, the startup current rush I of computer and Switching Power Supply class load_GFor T₀(computer and Switching Power Supply class load Startup time, electric current is I₀) to T₂(in the moment of setting, electric current is I₂) between the current average of computer and Switching Power Supply class load and steady-state current I_WRatio.Start average current I_DFor T₀(computer and Switching Power Supply class load Startup time) is to T_SThe current average of computer and Switching Power Supply class load and steady-state current I between (computer and Switching Power Supply class load start-up course end time)_WRatio.Starting current momentum Q_IAverage current I is started for computer and Switching Power Supply class load_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 only small (being in holding state), namely message processing module 102 starts load current is carried out continuous sampling；When the load current value virtual value that obtains of sampling starts more than 0 or starts the standby current more than electrical equipment, namely judging that electrical equipment has been started up, recording this moment is T₀.The load current value before and after appliance starting is distinguished, when special hour of ε value with a less non-negative threshold ε, for instance, during ε value 1mA, described identification device is left out ideal case, and namely thinking standby is also the starting state of electrical equipment；During but standby current more than electrical equipment less when ε value, for instance, during ε value 20mA, the holding state of electrical equipment can be thought inactive state by described identification device, but simultaneously also can the little especially electrical equipment of Partial Power cause Lou identification.

Load current is carried out continuous sampling by message processing module 102, and in units of power frequency period computational load current effective value preserving；When electrical equipment has been started up, and after continuous sampling reaches N number of power frequency period, the meansigma methods I of the load current virtual value of the nearest N number of power frequency period of Continuous plus while sampling_V；The meansigma methods of the load current virtual value of each power frequency period within nearest N number of power frequency period Yu the load current virtual value of this N number of power frequency period is compared by message processing module 102, when error (or fluctuation) amplitude is respectively less than the relative error range E of setting, judge that electrical equipment enters steady statue, the finish time that initial time is start-up course of this nearest N number of power frequency period, 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.Calculate T₀To the T set₂Between the load current meansigma methods of (i.e. electrical equipment start to start after within 1-5 power frequency period) and steady-state current I_WRatio, using this ratio startup current rush I as electrical equipment_G.Calculate T₀To T_SBetween load current meansigma methods and steady-state current I_WRatio, using this ratio startup average current I as electrical equipment_D.Calculate the startup average current I of electrical equipment_DWith start-up course time T_SProduct, using this product starting current momentum Q as electrical equipment_I。

Owing to not knowing electrical equipment steady-state current virtual value I in advance_W, therefore, by N number of power frequency period, i.e. one section of duration T_PWithin fluctuation range less than the relative error range E set time the meansigma methods of load current virtual value as electrical equipment steady-state current virtual value I_W.Owing to the start-up course of ordinary appliances is very fast, so, T_PSpan be 1-10s, typical value is 2s, and the typical value that span is 50-500, N of corresponding power frequency period quantity N is 100.The typical value that span is 2%-20%, E of described relative error range 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 controlled information acquisition module 101 by message processing module 102, is obtained by following steps:

Step one, enter after steady statue until electrical equipment, obtain the steady state current signals of electrical equipment, and be 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.For ensureing being smoothed out of Fourier transform, steady state current signals at aforementioned acquisition electrical equipment, and it is converted in the process of steady-state current digital signal of correspondence, the accuracy and speed of A/D converter needs to meet the requirement of Fourier transform, sample frequency can set that as 10kHz, or other numerical value；The steady-state current digital signal collected is carried out FFT computing by message processing module 102, calculates 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；Form assembled classifier input feature value time, nth harmonic signal relative magnitude in input feature value according to 1,2 ..., the order of M is arranged in order.Owing to load current spectral characteristic is mainly made up of odd harmonic, except minority electric equipment, even-order harmonic component is almost 0, accordingly it is also possible to using odd harmonic signal relative magnitude that overtone order in load current spectral characteristic is n time sequentially as load current spectrum signature, wherein, n=1,3 ..., M.1 subharmonic during n=1 is fundamental frequency.Described harmonic signal relative magnitude is harmonic signal amplitude and electrical equipment steady-state current virtual value I_WRatio.Described M represents the most high reps of harmonic wave, and generally, M is be 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.Resistive, capacitive character, inductive load can be made a distinction by fundamental voltage current and phase difference, it is also possible to general inductive load and big inductive load are made a distinction.The fundamental voltage current and phase difference of electrical equipment is controlled information acquisition module 101 by message processing module 102, is obtained by following steps:

Step 1., enter after steady statue until electrical equipment, synchronizes to obtain the steady state voltage signal of electrical equipment, steady state current signals, and 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 fundamental voltage signal, fundamental current signal.

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

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

In assembled classifier, support vector machine classifier is Main classification device, and Bayes classifier is subsidiary classification device.The input feature vector of assembled classifier includes aforesaid starting current feature and load current spectrum signature, the input feature vector of the input feature vector of the assembled classifier input feature vector simultaneously as support vector machine classifier and Bayes classifier.

Being illustrated in figure 6 students' dormitory electrical appliance type judgement method flow chart, method flow includes:

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 spectrum signature of electrical equipment, fundamental voltage current and phase difference；

Step F, using starting current feature, load current spectrum signature, fundamental voltage current and phase difference as the input feature vector of assembled classifier；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: when Main classification device successfully realizes appliance type identification, namely the recognition result of Main classification device output is unique appliance type, namely when in recognition result, unique appliance type is for being, using the appliance type of the Main classification device identification appliance type recognition result as assembled classifier；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, when namely recognition result having 2 kinds or two or more appliance type for being, by in 2 kinds of the output of Main classification device or two or more appliance type recognition result, the appliance type that in the output of subsidiary classification device, probability is the highest is as the appliance type recognition result of assembled classifier；When Main classification device fails to realize appliance type identification, and the recognition result of Main classification device fails to provide the appliance type of identification, when namely not having appliance type for being in recognition result, in being exported by subsidiary classification device, the highest appliance type of probability is as the appliance type recognition result of assembled classifier.

For a simple embodiment 1, illustrate that assembled classifier carries out appliance type and knows method for distinguishing.Being provided with an assembled classifier, its input feature vector is x={I_G, I_D, Q_I, A₁, A₂, A₃, A₄, A₅,, wherein, I_GIt is start current rush；I_DIt is start average current；Q_IIt it is starting current momentum；A₁、A₂、A₃、A₄、A₅For the 1-5 rd harmonic signal relative magnitude in load current spectral characteristic,Fundamental voltage current and phase difference for electrical equipment.The output of assembled classifier is { B₁, B₂, B₃, B₄, B₁、B₂、B₃、B₄Represent the assembled classifier recognition result to electric filament lamp, resistance furnace, hair-dryer, computer respectively to export, recognition result B₁、B₂、B₃、B₄Value be two-value key words sorting.The input feature vector of Main classification device is also x={I_G, I_D, Q_I, A₁, A₂, A₃, A₄, A₅,, its output is { F₁, F₂, F₃, F₄, F₁、F₂、F₃、F₄Represent the Main classification device recognition result to electric filament lamp, resistance furnace, hair-dryer, computer respectively to export, recognition result F₁、F₂、F₃、F₄Value be also two-value key words sorting.The input feature vector of subsidiary classification device is similarly x={I_G, I_D, Q_I, 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) for the posterior probability of subsidiary classification device output, 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 the electrical equipment identified belongs to the probability size of electric filament lamp, resistance furnace, hair-dryer, 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, and for the recognition result confirmed, corresponding appliance type recognition result is yes in other words；When key words sorting is 0, corresponding appliance type does not mate with input feature vector, fails to become the recognition result of confirmation, and corresponding appliance type recognition result is no in other words.

In embodiment 1, if the discriminator of certain Main classification device is labeled as F₁F₂F₃F₄=0100, then it is assumed that Main classification device successfully realizes appliance type identification, therefore, it is left out the recognition result of subsidiary classification device, directly makes B₁B₂B₃B₄=0100, namely the recognition result of assembled classifier is: identified electrical equipment is resistance furnace.

In embodiment 1, if the discriminator of certain Main classification device is labeled as 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；The recognition result setting now subsidiary classification device again meets P (y₁|x)<P(y₃| x), then make B₁B₂B₃B₄=0010, namely the recognition result of assembled classifier is: identified electrical equipment is hair-dryer.

In embodiment 1, if the discriminator of certain Main classification device is labeled as F₁F₂F₃F₄=0000, then it is assumed that Main classification device fails to realize appliance type identification, and fails to provide the appliance type of identification in the recognition result of Main classification device；The recognition result setting now subsidiary classification device again 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, namely the recognition result of assembled classifier is: identified electrical equipment is electric filament lamp.

Assembled classifier, Main classification device recognition result key words sorting can also adopt other scheme, for instance, respectively with 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 electrical equipment steady-state current virtual value I_W.Such as, having electrical equipment 2 kinds different, electric cautery and resistance furnace to need to identify, electric cautery, resistance furnace are all pure resistor loads, and it is little all to have resistance temperature correction factor, the common feature that resistance value is stable.Therefore, they cannot be made a distinction by the simple fundamental voltage current and phase difference feature relying on aforesaid starting current feature and load current spectrum signature, electrical equipment.Input feature vector increases electrical equipment steady-state current virtual value I_WAfter, electric cautery power is little, electrical equipment steady-state current virtual value I_WLittle；Resistance furnace power is big, electrical equipment steady-state current virtual value I_WGreatly, feature is different, and assembled classifier can carry out and complete identifying.

Subsidiary classification device is Bayes classifier.The one among three kinds of Bayes classifiers such as NBC grader (Naive Bayes Classifier), TAN grader (crown pruning), BAN grader (Bayes classifier of enhancing) can be selected as subsidiary classification device.

Embodiment 2 selects NBC grader as subsidiary classification device.The definition of Naive Bayes Classification is 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 each characteristic attribute is conditional sampling in naive Bayesian, so having:

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

In embodiment 2, the input feature vector of assembled classifier is { I_G, I_D, Q_I, A₁, A₃,, wherein, I_GIt is start current rush；I_DIt is start average current；Q_IIt it is starting current momentum；A₁、A₃For 1 in load current spectral characteristic, 3 odd harmonic signal relative magnitude；For the fundamental voltage current and phase difference of electrical equipment, unit is degree, and when fundamental voltage is ahead of fundamental current,Require that the electrical equipment classification identified is electric filament lamp, resistance furnace, electric fan, computer, hair-dryer.Make the characteristic attribute combination x={a of Naive Bayes Classifier₁,a₂,a₃,a₄,a₅,a₆In element and assembled classifier input feature vector set in element { I according to the order of sequence_G, I_D, Q_I, A₁, A₃,One_to_one corresponding；The output category set C={y of Naive Bayes Classifier₁,y₂,y₃,y₄,y₅Then respectively with electrical equipment classification electric filament lamp, resistance furnace, electric fan, computer, hair-dryer 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 method taked is:

a₁: { a₁<3.5,3.5≤a₁≤7,a₁>7}；

a₂: { a₂<1.2,1.2≤a₂≤1.8,a₂>1.8}；

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<-5,-5≤a₆≤12,a₆>12}。

2, every electric appliances type is all gathered many group samples as training sample, calculate the ratio that every electric appliances type sample occupies in all appliance type samples simultaneously, namely calculate P (y respectively₁)、P(y₂)、P(y₃)、P(y₄)、P(y₅).When every electric appliances all gathers identical sample size, for instance, every electric appliances all gathers the sample more than 100 groups, and wherein every electric appliances randomly chooses 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 the conditional probability of each characteristic attribute lower of all categories and estimates, namely distinguishes statistical computation

P(a₁<3.5|y₁)、P(3.5≤a₁≤7|y₁)、P(a₁>7|y₁)；

P(a₁<3.5|y₂)、P(3.5≤a₁≤7|y₂)、P(a₁>7|y₂)；

…；

P(a₁<3.5|y₅)、P(3.5≤a₁≤7|y₅)、P(a₁>7|y₅)；

P(a₂<1.2|y₁)、P(1.2≤a₂≤1.8|y₁)、P(a₂>1.8|y₁)；

P(a₂<1.2|y₂)、P(1.2≤a₂≤1.8|y₂)、P(a₂>1.8|y₂)；

…；

P(a₂<1.2|y₅)、P(1.2≤a₂≤1.8|y₅)、P(a₂>1.8|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<-5|y₁)、P(-5≤a₆≤12|y₁)、P(a₆≥12|y₁)；

P(a₆<-5|y₂)、P(-5≤a₆≤12|y₂)、P(a₆≥12|y₂)；

…；

P(a₆<-5|y₅)、P(-5≤a₆≤12|y₅)、P(a₆≥12|y₅)。

Through above-mentioned step 1, step 2, step 3, NBC classifier training completes.Wherein, characteristic attribute is carried out segmentation and divides by manually determining by step 1, and when each input feature vector is carried out disperse segmentaly, the quantity of segmentation is 2 sections or more than 2 sections, for instance, in embodiment 2, feature a₁-a₆All it is divided into 3 sections.Each feature is specifically divided into how many sections, and the result after test test sample can be adjusted by the selection of fragmentation threshold according to the Bayes classifier after training.Step 2, step 3 have been calculated by message processing module 102 or computer.

The method that in the present invention, employing Bayes classifier carries out classifying is:

1, using the input feature vector of the assembled classifier input feature vector as Bayes classifier.In example 2, by the input feature vector set { I of assembled classifier_G, I_D, Q_I, A₁, A₃,As the input feature vector x of Bayes classifier, and have x={a₁,a₂,a₃,a₄,a₅,a₆}。

2, the conditional probability of each characteristic attribute of all categories lower obtained according to training is estimated, determines the segmentation place of each input feature vector attribute respectively and determines its probability P (a to every electric appliances classification₁|y₁)～P (a_m|y_n), wherein, electrical equipment category set is C={y₁,y₂,…,y_n}.In embodiment 2, electrical equipment category set C={y₁,y₂,y₃,y₄,y₅The corresponding electrical equipment classification represented is electric filament lamp, resistance furnace, electric fan, computer, hair-dryer, it is determined that P (a₁|y₁)～P (a₆|y₅) method be adopt the conditional probability of each characteristic attribute obtained in training NBC grader process to estimate.

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, making P (x)=1 substitute actual P (x) value, 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

$P\left(y_1\right|x)=P\left(x\right|y_1)P\left(y_1\right)=P\left(y_1\right)\underset{j=1}{\overset{6}{\&Pi;}}P\left(a_j\right|y_1);$

$P\left(y_2\right|x)=P\left(x\right|y_2)P\left(y_2\right)=P\left(y_2\right)\underset{j=1}{\overset{6}{\&Pi;}}P\left(a_j\right|y_2);$

$P\left(y_3\right|x)=P\left(x\right|y_3)P\left(y_3\right)=P\left(y_3\right)\underset{j=1}{\overset{6}{\&Pi;}}P\left(a_j\right|y_3);$

$P\left(y_4\right|x)=P\left(x\right|y_4)P\left(y_4\right)=P\left(y_4\right)\underset{j=1}{\overset{6}{\&Pi;}}P\left(a_j\right|y_4);$

$P\left(y_5\right|x)=P\left(x\right|y_5)P\left(y_5\right)=P\left(y_5\right)\underset{j=1}{\overset{6}{\&Pi;}}P\left(a_j\right|y_5).$

Adopt test sample that the Bayes classifier trained is tested, decide whether to adjust the discretization method to input feature vector (namely adjusting number of fragments and threshold value), re-training Bayes classifier according to test result.

Main classification device is support vector machine classifier, or is called SVM classifier.SVM classifier is particularly suitable for solving two-value classification situation, therefore, Main classification device adopts multiple two class output SVM classifier compositions, each two class output SVM classifier correspondence identification one appliance type, such as, embodiment 1 can adopt 4 two class output SVM classifier identify electric filament lamp, resistance furnace, hair-dryer, computer respectively, embodiment 2 can adopt 5 two class output SVM classifier identify electric filament lamp, resistance furnace, electric fan, computer, hair-dryer respectively.When Main classification device selects multiple two class output SVM classifier to collectively constitute, the input feature vector of all two class output SVM classifier is the input feature vector of Main classification device.

When training each two class output SVM classifier, every electric appliances type all being gathered and organizes sample more, randomly draw partly as training sample, remaining is as test sample.Sample collection adopts the method for the starting current feature of aforesaid acquisition electrical equipment and obtains the load current spectrum signature of electrical equipment and the method for the fundamental voltage current and phase difference feature of acquisition electrical equipment.All of training sample is all as the training sample of each two class output SVM classifier.Such as, in example 2, respectively electric filament lamp, resistance furnace, electric fan, computer, hair-dryer even load can all be gathered more than 100 groups of samples, randomly draw wherein 100 groups every kind, totally 500 groups sample composition training samples, remaining sample composition test sample；Certainly, the sample size of certain load or all load collections does not reach 100 groups of samples, and SVM classifier also is able to obtain good classifying quality.

Two class output SVM classifier selected by Main classification device select radially base RBF kernel function, and adopt particle cluster algorithm (PSO) that the punishment parameter C and nuclear parameter Y of each two class output SVM classifier are in optimized selection.

Each two class output SVM classifier only need to be performed the identification of a kind of appliance type, and the training of SVM classifier is relatively easy.Main classification device is made up of multiple two class output SVM classifier, each two classes export between SVM classifier separate, therefore, when a certain characteristic 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 fails to provide the appliance type of identification.

Claims (10)

1. a students' dormitory electrical appliance type judgement method, 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 converting current digital signal to；Described current digital signal is sent to message processing module；

Described message processing module, according to the current digital signal of input, adopts 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 fundamental voltage current and phase difference of the starting current feature of electrical equipment, the load current spectrum signature of electrical equipment and electrical equipment；

Described assembled classifier includes support vector machine classifier and Bayes classifier；

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

2. students' dormitory as claimed in claim 1 electrical appliance type judgement method, it is characterised in that described information acquisition module includes current 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 is FPGA.

3. students' dormitory as claimed in claim 2 electrical appliance type judgement method, it is characterised in that described A/D converter adopts the A/D converter that the core of message processing module includes.

4. students' dormitory as claimed in claim 1 electrical appliance type judgement method, it is characterised in that described communication module also receives the related work instruction of host computer；Communication mode between described communication module and host computer includes 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.

5. the students' dormitory electrical appliance type judgement method as according to any one of claim 1-4, it is characterised in that in described assembled classifier, support vector machine classifier is Main classification device, and Bayes classifier is subsidiary classification device.

6. students' dormitory as claimed in claim 5 electrical appliance type judgement method, it is characterized in that, described assembled classifier carries out appliance type knowledge method for distinguishing: when Main classification device successfully realizes appliance type identification, the recognition result that appliance type recognition result is assembled classifier of Main classification device；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 in 2 kinds of the output of Main classification device or two or more appliance type recognition result, the appliance type that in the output of subsidiary classification device, probability is the highest is as the appliance type recognition result of assembled classifier；When Main classification device fails to realize appliance type identification, and the recognition result of Main classification device fails the appliance type providing identification time, 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.

7. students' dormitory as claimed in claim 5 electrical appliance type judgement method, it is characterised in that described load current spectrum signature obtains by the following method:

Step one, obtain electrical equipment steady state current signals, and be converted into correspondence steady-state current digital signal；

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 current spectrum signature, wherein, n=1,3 ..., M；Described M represents that the most high reps of harmonic wave and M are be more than or equal to 3.

8. students' dormitory as claimed in claim 5 electrical appliance type judgement method, it is characterised in that described starting current feature is obtained by the following method 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 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, computational load current effective value preserving in units of power frequency period；Calculate the meansigma methods of the load current virtual value of nearest N number of power frequency period；The load current virtual value of each power frequency period within nearest N number of power frequency period is compared with the meansigma methods of the load current virtual value of this N number of power frequency period, when fluctuating margin is respectively less than the relative error range E of setting, judge that electrical equipment enters steady statue, turn to step 3；The span of described N 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 steady-state current；Electrical equipment is started Startup time to time as the start-up course time between nearest N number of power frequency period initial time；Calculate after electrical equipment starts to start the ratio between meansigma methods and the electric appliance load steady-state current of the electric appliance load current effective value within L power frequency period, using this ratio startup current rush as electrical equipment；Calculate the ratio between meansigma methods and the electric appliance load steady-state current of the electric appliance load current effective value within the start-up course time of electrical equipment, using this ratio startup average current as electrical equipment；What calculate electrical equipment starts average current and the product between the start-up course time, using this product starting current momentum as electrical equipment；The span of described L is 1-5.

9. students' dormitory as claimed in claim 8 electrical appliance type judgement method, it is characterised in that the input feature vector of described assembled classifier also includes electric appliance load steady-state current.

10. students' dormitory as claimed in claim 5 electrical appliance type judgement method, it is characterised in that the fundamental voltage current and phase difference of described electrical equipment obtains by the following method:

Step 1., enter after steady statue until electrical equipment, synchronizes to obtain the steady state voltage signal of electrical equipment, steady state current signals, and 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, using the fundamental voltage current and phase difference as electrical equipment of the phase contrast between fundamental voltage signal and fundamental current signal.