CN108594040A - A kind of students' dormitory electrical appliance genre classification methods - Google Patents

A kind of students' dormitory electrical appliance genre classification methods Download PDF

Info

Publication number
CN108594040A
CN108594040A CN201810338493.8A CN201810338493A CN108594040A CN 108594040 A CN108594040 A CN 108594040A CN 201810338493 A CN201810338493 A CN 201810338493A CN 108594040 A CN108594040 A CN 108594040A
Authority
CN
China
Prior art keywords
current
appliance
electric appliance
load
classifier
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810338493.8A
Other languages
Chinese (zh)
Inventor
周维龙
凌云
孔玲爽
曾红兵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University of Technology
Original Assignee
Hunan University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hunan University of Technology filed Critical Hunan University of Technology
Priority to CN201810338493.8A priority Critical patent/CN108594040A/en
Priority to CN201610218359.5A priority patent/CN105785187B/en
Publication of CN108594040A publication Critical patent/CN108594040A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R19/00Arrangements for measuring currents or voltages or for indicating presence or sign thereof
    • G01R19/25Arrangements for measuring currents or voltages or for indicating presence or sign thereof using digital measurement techniques

Abstract

A kind of students' dormitory electrical appliance genre classification methods, the characteristics of classification is identified, two kinds of graders are taken into account using the assembled classifier including support vector machine classifier and Bayes classifier, carry out comprehensive identification, and recognition accuracy is high;Identification feature of the fundamental voltage current and phase difference and load current spectrum signature of the starting current feature, electric appliance that use electric appliance simultaneously as appliance type, characteristic information are abundant;Fundamental voltage current and phase difference, starting current feature, the load current spectrum signature acquisition methods of offer are simple, reliable.The appliance type sorting technique can be used in some collective public places for needing to carry out power load management such as collective of students dormitory, can be used for other occasions for needing to carry out electrical equipment management for needing to carry out power load type with statistics.

Description

A kind of students' dormitory electrical appliance genre classification methods
Present patent application is divisional application, and application No. is 201610218359.5, the applying date is in April, 2016 for original bill 8 days, a kind of entitled students' dormitory electrical appliance type judgement method.
Technical field
The present invention relates to a kind of identification of electrical equipment and sorting techniques, more particularly, to a kind of students' dormitory electrical appliance type Sorting technique.
Background technology
Currently, the electric appliance property of mainstream or appliance type recognition methods include based on bearing power coefficient of colligation algorithm Electrical appliance recognition, the electrical appliance recognition based on neural network algorithm, is based on week at the electrical appliance recognition based on electromagnetic induction The electrical appliance recognition etc. of phase property discrete transform algorithm.Various methods can be the knowledge for realizing electric appliance property to a certain degree Not, but since characteristic properties are single, means of identification is single, and generally existing generalization ability is inadequate and is unable to asking for entirely accurate identification Topic.
Invention content
It is an object of the present invention to for the defect of present prior art, a kind of can realize efficient identification is provided Raw accommodation electricity usage device genre classification methods.It includes support vector cassification that the students' dormitory electrical appliance genre classification methods, which use, The assembled classifier of device and Bayes classifier carries out appliance type identification;The input feature vector of the assembled classifier includes electric appliance Starting current feature, the load current spectrum signature of electric appliance and the fundamental voltage current and phase difference of electric appliance.
In the assembled classifier, support vector machine classifier is main grader, and Bayes classifier is auxiliary grader. The assembled classifier, which carries out appliance type, which knows method for distinguishing, is:When Main classification device successfully realizes appliance type identification, main point The appliance type recognition result of class device is the recognition result of assembled classifier;It is identified when Main classification device fails realization appliance type, And the recognition result of Main classification device is 2 kinds of 2 kinds or two or more electricity that either two or more appliance type exports Main classification device In device type identification result, the highest appliance type of probability is known as the appliance type of assembled classifier in the output of subsidiary classification device Other result;It is identified when Main classification device fails realization appliance type, and fails to provide the electricity of identification in the recognition result of Main classification device When device type, the highest appliance type of probability identifies knot as the appliance type of assembled classifier during subsidiary classification device is exported Fruit.
The load current spectrum signature is prepared by the following:
Step 1: obtaining the steady state current signals of electric appliance, and it is converted into corresponding steady-state current digital signal;
Step 2: carrying out Fourier transform to steady-state current digital signal, load current spectral characteristic is obtained;
Step 3: using the odd harmonic signal relative magnitude that overtone order in load current spectral characteristic is n times as negative Carry current spectrum feature, wherein n=1,3 ..., M;The M indicates harmonic wave highest number and M is more than or equal to 3.The harmonic wave letter Number relative magnitude is the ratio of harmonic signal amplitude and electric appliance load steady-state current virtual value.
The fundamental voltage current and phase difference of the electric appliance is prepared by the following:
Step 1., after electric appliance enters stable state, synchronous steady state voltage signal, the steady state current signals for obtaining electric appliance, And it is converted into corresponding steady state voltage digital signal, steady-state current digital signal;
2., to steady state voltage digital signal, steady-state current digital signal step carries out digital filtering respectively, extract fundamental wave Voltage signal, fundamental current signal;
Step 3., analysis calculate the phase difference between fundamental voltage signal and fundamental current signal, by fundamental voltage signal Fundamental voltage current and phase difference of the phase difference as electric appliance between fundamental current signal.
The judgement after electric appliance enters stable state, according to each power frequency period within nearest N number of power frequency period Load current virtual value carry out, specific method is:Continuous sampling is carried out to the load current of electric appliance, is single with power frequency period Position computational load current effective value simultaneously preserves;Calculate the average value of the load current virtual value of N number of power frequency period recently;When nearest The load current virtual value of each power frequency period within N number of power frequency period and the load current virtual value of N number of power frequency period Average value compare, fluctuating range be respectively less than set relative error range E when, judgement electric appliance enter stable state.The N Value range be 50-500, the value range of E is 2%-20%.
The starting current feature includes starting current rush, starting average current, starting current momentum, by with lower section Method obtains:
Before step 1, appliance starting, starts the load current continuous sampling to electric appliance and load current size is sentenced It is disconnected;When load current virtual value is more than ε, judgement electric appliance starts to start and turns to step 2;The ε is the numerical value more than 0;
After step 2, electric appliance to be determined enter stable state, step 3 is turned to;
It is step 3, electric using the average value of the load current virtual value within nearest N number of power frequency period as electric appliance load stable state Stream;Electric appliance is started into Startup time to the time between nearest N number of power frequency period initial time as the start-up course time;It calculates Electric appliance start after starting the average value of the electric appliance load current effective value within L power frequency period and electric appliance load steady-state current it Between ratio, using the ratio as the startup current rush of electric appliance;Calculate the electric appliance load within the start-up course time of electric appliance Ratio between the average value and electric appliance load steady-state current of current effective value, using the ratio as the average electricity of the startup of electric appliance Stream;The startup average current for calculating electric appliance and the product between the start-up course time, using the product as the starting current of electric appliance Momentum;The value range of the L is 1-5.
The input feature vector of the assembled classifier further includes electric appliance load steady-state current.
The students' dormitory electrical appliance genre classification methods are by including information acquisition module, message processing module, communication mould The device of block is realized.Described information acquisition module is used to acquire the load current information of electric appliance and load voltage information and send to letter Cease processing module;Described information processing module carries out appliance type identification according to the information of input;The communication module is for sending out Send the appliance type recognition result of message processing module to host computer.
Described information acquisition module includes current sensor, preamplifier, filter, A/D converter;At described information The core for managing module is DSP, is either that ARM is either microcontroller or is FPGA.
The A/D converter that the core of message processing module includes may be used in the A/D converter.
Described information acquisition module, message processing module, communication module all or part of function be integrated in a piece of SoC In (System on Chip, system on chip).
The communication module also receives the related work instruction of host computer;Communication between the communication module and host computer Mode includes communication and wired communication mode;The communication include ZigBee, bluetooth, WiFi, 433MHz numbers pass mode;The wired communication mode includes 485 buses, CAN bus, internet, power carrier mode.
The beneficial effects of the invention are as follows:Using the assembled classifier for including support vector machine classifier and Bayes classifier The characteristics of classification is identified, takes into account support vector machine classifier and Bayes classifier carries out comprehensive identification, generalization ability with Recognition accuracy is high;Simultaneously using starting current feature, the load current spectrum signature of electric appliance and the fundamental wave of electric appliance of electric appliance Identification feature of the voltage current phase difference as the students' dormitory electrical appliance genre classification methods, characteristic information are abundant;It provides Including starting current rush, start average current, the starting current characteristic-acquisition method including starting current momentum, and it is negative It is simple, reliable to carry current spectrum characteristic-acquisition method.
Description of the drawings
Fig. 1 is the device embodiment structural schematic diagram for realizing students' dormitory electrical appliance genre classification methods;
Fig. 2 is the start-up course current waveform of incandescent 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 that Switching Power Supply class loads;
Fig. 6 is students' dormitory electrical appliance genre classification methods flow chart.
Specific implementation mode
Below in conjunction with attached drawing, the invention will be further described.
Fig. 1 is to realize that the device embodiment structural schematic diagram of students' dormitory electrical appliance genre classification methods, including information are adopted Collect module 101, message processing module 102, communication module 103.
Information acquisition module 102 is used to acquire the load voltage of electric appliance, load current and turns load voltage, load current Change 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 compositions such as voltage sensor, current sensor, preamplifier, filter, A/D converter portion Point, it is respectively completed load voltage, the sensing of load current signal, amplification, filtering and analog-digital conversion function.Work as load current range When larger, the preamplifier with programmable function can be selected, or is further added by an independent journey before A/D converter Amplifier is controlled, the load current larger to range carries out Discrete control amplification, make the voltage signal range for being input to A/D converter It is maintained at rational section, ensures conversion accuracy.Filter avoids spectral aliasing for filtering out high fdrequency component.
Voltage digital signal, current digital signal of the message processing module 102 according to input, using including support vector machines The assembled classifier of grader and Bayes classifier realizes appliance type identification.The input feature vector of assembled classifier includes electric appliance Starting current feature, the load current spectrum signature of electric appliance and the fundamental voltage current and phase difference of electric appliance.Message processing module 102 core is DSP, ARM, microcontroller, or is FPGA.When include in the core of message processing module A/D converter and When the A/D converter is met the requirements, the core of message processing module 102 may be used in the A/D converter in information acquisition module 101 The A/D converter for including in the heart.
Communication module 103 is sent to host computer for realizing the communication between host computer, by Classification and Identification result.Communication Communication mode between module 102 and host computer includes communication and wired communication mode, the channel radio that may be used Letter mode includes the modes such as ZigBee, bluetooth, WiFi, 433MHz number biography, and the wired communication mode that may be used includes 485 total The modes such as line, CAN bus, internet, power carrier.Communication module 103 can also receive the related work instruction of host computer, complete At specified task.Host computer can be the server of administrative department, can also be various work stations or various shiftings Dynamic terminal.
Information acquisition module 101, message processing module 102, communication module 103 all or part of function can integrate On a piece of SoC, reduces device volume, facilitate installation.
Different electrical equipments has different starting current features.It is illustrated in figure 2 the start-up course of incandescent lamp desk lamp Current waveform.Incandescent lamp is that filament electrified regulation to incandescent state is sent out the electric light source of visible light using heat radiation.Incandescent lamp Filament usually manufactured with heat safe tungsten, but the resistance of tungsten varies with temperature greatly, with RtIndicate tungsten filament at t DEG C Resistance, with R0Indicate resistance of the tungsten filament at 0 DEG C, then the two has following relationships
Rt=R0(1+0.0045t)
For example, set the temperature of the filament (tungsten filament) of incandescent lamp in normal work as 2000 DEG C, one " 220V 100W's " The resistance when filament of incandescent lamp is worked normally at 2000 DEG C is
Its 0 DEG C resistance in no power is
Its 20 DEG C resistance in no power is
R20=R0(1+0.0045t)=52.8 Ω
I.e. incandescent lamp is in 9 times of the immediate current for starting energization more than its rated current, and maximum starting current is happened at Startup time.With the raising of incandescent lamp tungsten filament temperature, the load current of incandescent lamp exponentially reduces, subsequently into steady Determine state.
If electric appliance steady-state current virtual value is IW, and define electric current virtual value and enter electric appliance steady-state current virtual value Within the relative error range of one setting and stablize within this relative error range, then electric appliance enters stable state.Phase 10% can be set as to error range, the value that can also be set as between the 2%-20% such as 2%, 5%, 15%, 20%.Fig. 2 In, the relative error range that sets is 10%, when the load current of incandescent lamp is exponentially reduced to its IW10% miss When poor range, T at the time of as in Fig. 2S, start-up course terminates.The start-up course time of incandescent lamp is TS。IWFor virtual value.
Selection starts current rush IG, start average current ID, starting current momentum QIStarting current as electric appliance is special Sign;Start current rush IG, start average current IDIt is per unit value.Being specifically defined is:Start current rush IGFor appliance starting T after beginning2Electric appliance load current average within time and electric appliance load steady-state current IWRatio;Start average current ID For appliance starting time TSWithin electric appliance load current average and electric appliance load steady-state current IWRatio;Starting current rushes Measure QITo start average current IDWith start-up course time TSProduct, dimension ms.Electric appliance load electric current, electric appliance load stable state Electric current is virtual value.T2Value range be 20-100ms or 1-5 power frequency period;For example, T2Value 40ms, i.e., 2 A power frequency period.Start current rush IGWhat is reflected is the electric current impulse size after electric appliance load starts in the short time.In part In the start-up course of electric appliance, as the practical start-up course time T for having electric applianceSLess than the T of setting2When, when enabling the start-up course of electric appliance Between TSEqual to T2.Start average current IDWhat is reflected is the electric current entirety size in electric appliance load start-up course.Starting current momentum QIWhat is reflected is the integral strength that electric appliance load starts.
In Fig. 2, the startup current rush I of incandescent lampGFor T0(incandescent lamp Startup time, electric current I0) to T2(setting when It carves, electric current I2) between the current average of incandescent lamp and the steady-state current I of incandescent lampWRatio.Start average current IDFor T0(incandescent lamp Startup time) is to TSThe current average of incandescent lamp and incandescent lamp between (incandescent lamp start-up course end time) Steady-state current IWRatio.Starting current momentum QIStart average current I for incandescent lampDWith start-up course time TSProduct.
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 logical Frequently with lectrothermal alloy wires such as nickel chromium triangle, ferrum-chromium-aluminums, common feature is that resistance temperature correction factor is small, resistance value stabilization.With board For number for the nichrome wire of Cr20Ni80, resistance correction factor at 1000 DEG C is 1.014, i.e., 1000 DEG C whens are opposite When 20 DEG C, the trade mark is that the nichrome wire resistance of Cr20Ni80 only increases by 1.4%.The resistive loads such as resistance furnace are opened in energization Enter stable state, the practical start-up course time T of the resistive loads such as resistance furnace when dynamicS=0, therefore, enable resistance furnace etc. The practical start-up course time T of resistive loadS=T2;For example, working as T2When being set as 40ms, then start-up course time at this time TSAlso it is 40ms.Due to resistive load T0Moment electric current I0、T2Moment electric current I2With the steady-state current I of resistive loadWIt is equal, Therefore, the startup current rush I of resistive loadG=1, start average current ID=1.
It is illustrated in figure 4 the start-up course current waveform of monophase machine class load.The load of monophase machine class both has inductance Property load characteristic, and have counter electromotive force load characteristic.Startup time, due to the effect of inductance, the starting current of Startup time I0It is 0;Subsequent electric current rises rapidly, before counter electromotive force of motor is not set up, reaches current peak IM;Hereafter, motor speed increases Add, motor load electric current gradually reduces, until entering stable state.In Fig. 4, the startup current rush I of monophase machine class loadG For T0(monophase machine class loads Startup time, electric current I0) to T2(at the time of setting, electric current I2) between monophase machine class it is negative The current average of load and steady-state current IWRatio.Start average current IDFor T0(monophase machine class load Startup time) extremely TSThe current average and steady-state current I that monophase machine class loads between (monophase machine class loads the start-up course end time)W's Ratio.Starting current momentum QIIt is loaded for monophase machine class and starts average current IDWith start-up course time TSProduct.
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 will produce a prodigious surge current because of the influence to capacitor charging, in startup moment, and peak value can reach surely State current effective value IWSeveral times to more than ten times, the time be 1 to 2 power frequency period.Since computer and Switching Power Supply class load The startup time it is short, start-up course time TSLikely to be less than the T of setting2;As its start-up course time TSLess than the T of setting2 When, enable TSEqual to T2.In Fig. 5, the startup current rush I of computer and the load of Switching Power Supply classGFor T0(computer and switch electricity Source class loads Startup time, electric current I0) to T2(at the time of setting, electric current I2) between computer and Switching Power Supply class load Current average and steady-state current IWRatio.Start average current IDFor T0(when computer and the load of Switching Power Supply class start Carve) to TSComputer and the electricity of Switching Power Supply class load between (computer and Switching Power Supply class load the start-up course end time) Levelling mean value and steady-state current IWRatio.Starting current momentum QIStart average current for computer and the load of Switching Power Supply class IDWith start-up course time TSProduct.
Obtaining the method for starting current feature of electric appliance is:
Before appliance starting, when load current value is 0 (being not keyed up) or very little (being in standby), message processing module 102 start to carry out continuous sampling to load current;When the load current value virtual value that sampling obtains starts to be more than 0 or opens When beginning to be more than the standby current of electric appliance, that is, judge that electric appliance has been started up, it is T to record the moment0.With a smaller non-negative threshold Value ε distinguishes the load current value before and after appliance starting, when ε values are especially small, for example, when ε value 1mA, the identification dress It sets and does not consider ideal case, that is, it is also the starting state of electric appliance to think standby;When ε values are smaller but more than electric appliance standby current When, for example, when ε value 20mA, the standby mode of electric appliance can be considered inactive state by the identification device, but also can simultaneously The especially small electric appliance of Partial Power cause leakage to identify.
Message processing module 102 carries out continuous sampling to load current, and using power frequency period as unit computational load electric current Virtual value simultaneously preserves;Continuous plus is most after electric appliance has been started up, and continuous sampling reaches N number of power frequency period, while sampling The average value I of the load current virtual value of nearly N number of power frequency periodV;Message processing module 102 to nearest N number of power frequency period within The load current virtual value of each power frequency period is compared with the average value of the load current virtual value of N number of power frequency period, When error (or fluctuation) amplitude is respectively less than the relative error range E set, judgement electric appliance enters stable state, nearest N number of work The initial time in frequency period is the finish time of start-up course, and it is T to record the moment1(as Figure 2-Figure 5).
Using the average value of the load current virtual value within nearest N number of power frequency period as electric appliance load steady-state current IW; Electric appliance is started into Startup time T0To nearest N number of power frequency period initial time T1Between time as start-up course time TS.Meter Calculate T0To the T of setting2Between (i.e. electric appliance starts after starting within 1-5 power frequency period) load current average value and stable state it is electric Flow IWRatio, using the ratio as the startup current rush I of electric applianceG.Calculate T0To TSBetween load current average value with it is steady State electric current IWRatio, using the ratio as the startup average current I of electric applianceD.Calculate the startup average current I of electric applianceDWith startup Process time TSProduct, using the product as the starting current momentum Q of electric applianceI
Due to not knowing electric appliance steady-state current virtual value I in advanceW, therefore, by N number of power frequency period, i.e. one section of duration TP Within fluctuation range be less than setting relative error range E when load current virtual value average value as electric appliance steady-state current Virtual value IW.Since the start-up course of ordinary appliances is very fast, so, TPValue range be 1-10s, typical value is 2s, accordingly Power frequency period quantity N value range be 50-500, the typical value of N is 100.The value model of the relative error range E It encloses for 2%-20%, the typical value of E is 10%.
The input feature vector of assembled classifier further includes the load current spectrum signature of electric appliance.The load current frequency spectrum of electric appliance is special Sign controls information acquisition module 101 by message processing module 102, is obtained by following steps:
Step 1: after electric appliance enters stable state, the steady state current signals of electric appliance are obtained, and are converted into corresponding Steady-state current digital signal.
Step 2: carrying out Fourier transform to steady-state current digital signal, load current spectral characteristic is obtained.To ensure Fu Vertical leaf transformation is smoothed out, and obtains the steady state current signals of electric appliance aforementioned, and be converted into corresponding steady-state current number During word signal, the accuracy and speed of A/D converter needs the requirement for meeting Fourier transform, sample frequency that can set For 10kHz or other numerical value;Message processing module 102 carries out FFT operations to collected steady-state current digital signal, 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 special in input According to 1,2 in sign vector ..., the sequence of M is arranged in order.Since load current spectral characteristic is mainly made of odd harmonic, remove Outside a small number of electrical equipments, 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 is sequentially used as load current spectrum signature, wherein n=1,3 ..., M.1 time when n=1 Harmonic wave is fundamental frequency.The harmonic signal relative magnitude is harmonic signal amplitude and electric appliance steady-state current virtual value IWRatio Value.The M indicates harmonic wave highest number, and under normal circumstances, M is more than or equal to 3.
The input feature vector of assembled classifier further includes the fundamental voltage current and phase difference of electric appliance.Fundamental voltage current and phase difference Resistive, capacitive character, inductive load can be distinguished, it can also be to general inductive load and big inductive load It distinguishes.The fundamental voltage current and phase difference of electric appliance by message processing module 102 control information acquisition module 101, by with Lower step obtains:
Step 1., after electric appliance enters stable state, synchronous steady state voltage signal, the steady state current signals for obtaining electric appliance, And it is converted into corresponding steady state voltage digital signal, steady-state current digital signal.
2., to steady state voltage digital signal, steady-state current digital signal step carries out digital filtering respectively, extract fundamental wave Voltage signal, fundamental current signal.
Step 3., analysis calculate the phase difference between fundamental voltage signal and fundamental current signal, by fundamental voltage signal Fundamental voltage current and phase difference of the phase difference as electric appliance between fundamental current signal.
Step 2. in digital filtering carried out respectively to steady state voltage digital signal, steady-state current digital signal, number filter Wave algorithm can select the digital filter algorithms such as Kalman filtering method, Wavelet Transform, Wiener Filter Method, adaptive-filtering.
In assembled classifier, support vector machine classifier is main grader, and Bayes classifier is auxiliary grader.Combination The input feature vector of grader includes starting current feature above-mentioned and load current spectrum signature, the input feature vector of assembled classifier Simultaneously as the input feature vector of support vector machine classifier and the input feature vector of Bayes classifier.
It is illustrated in figure 6 students' dormitory electrical appliance genre classification methods flow chart, method flow includes:
Step A, appliance starting is waited for;
Step B, it acquires appliance starting current data and preserves, until appliance starting process terminates;
Step C, the appliance starting current data of analysis acquisition, obtains the starting current feature of electric appliance;
Voltage when step D, acquiring electric appliance steady operation and preserves current data;
Step E, the voltage when electric appliance steady operation of analysis acquisition, current data, obtain the load current frequency spectrum of electric appliance 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, appliance type recognition result is exported.
The assembled classifier, which carries out appliance type, which knows method for distinguishing, is:When Main classification device successfully realizes that appliance type is known Not, i.e., Main classification device output recognition result be unique appliance type, i.e., in recognition result unique appliance type for be when, The appliance type that Main classification device is identified 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 be 2 kinds either have in two or more appliance type, that is, recognition result 2 kinds or Two or more appliance type is when being, in 2 kinds that Main classification device is exported or two or more appliance type recognition result, auxiliary point Appliance type recognition result of the highest appliance type of probability as assembled classifier in the output of class device;When Main classification device fails reality Existing appliance type identification, and fail to provide the appliance type of identification in the recognition result of Main classification device, i.e., do not have in recognition result Appliance type is when being, the highest appliance type of probability is known as the appliance type of assembled classifier during subsidiary classification device is exported Other result.
By taking a simple embodiment 1 as an example, method for distinguishing is known to illustrate that assembled classifier carries out appliance type.Equipped with one A assembled classifier, input feature vector areWherein, IGIt is to open Dynamic current rush;IDIt is to start average current;QIIt is starting current momentum;A1、A2、A3、A4、A5For in load current spectral characteristic 1-5 rd harmonic signal relative magnitudes,For the fundamental voltage current and phase difference of electric appliance.The output of assembled classifier is { B1, B2, B3, B4, B1、B2、B3、B4It is defeated to the recognition result of incandescent lamp, resistance furnace, hair-dryer, computer to respectively represent assembled classifier Go out, recognition result B1、B2、B3、B4Value be two-value classification marker.The input feature vector of Main classification device is alsoIts output is { F1, F2, F3, F4, F1、F2、F3、F4Generation respectively Table Main classification device exports the recognition result of incandescent lamp, resistance furnace, hair-dryer, computer, recognition result F1、F2、F3、F4Take Value is also two-value classification marker.The input feature vector of subsidiary classification device is similarly 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) it is the posterior probability for assisting grader 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 indicates that identified electric appliance belongs to white The possibility size of vehement lamp, resistance furnace, hair-dryer, computer.
In embodiment 1, B1、B2、B3、B4Classification marker and F1、F2、F3、F4Classification marker take 1,0.Classification marker When being 1, corresponding appliance type is matched with current input feature, for the recognition result of confirmation, corresponding appliance type in other words Recognition result is yes;When classification marker is 0, corresponding appliance type is mismatched with input feature vector, is failed as the identification confirmed As a result, corresponding appliance type recognition result is no in other words.
In embodiment 1, if the identification classification marker of certain Main classification device is F1F2F3F4=0100, then it is assumed that main point Class device successfully realizes that appliance type identifies, therefore, does not consider the recognition result of subsidiary classification device, directly enables B1B2B3B4=0100, That is the recognition result of assembled classifier is:Identified electric appliance is resistance furnace.
In embodiment 1, if the identification classification marker of certain Main classification device is F1F2F3F4=1010, then it is assumed that main point Class device fails to realize appliance type identification, and the recognition result of Main classification device is 2 kinds or two or more appliance type;Set this again When subsidiary classification device recognition result meet P (y1|x)<P(y3| x), then enable B1B2B3B4=0010, the i.e. identification of assembled classifier The result is that:Identified electric appliance is hair-dryer.
In embodiment 1, if the identification classification marker of certain Main classification device is F1F2F3F4=0000, then it is assumed that main point Class device fails to realize appliance type identification, and fails to provide the appliance type of identification in the recognition result of Main classification device;Set this again When subsidiary classification device recognition result meet P (y1|x)>P(y2| x) and P (y1|x)>P(y3| x) and P (y1|x)>P(y4| x), then Enable B1B2B3B4=1000, i.e. the recognition result of assembled classifier is:Identified electric appliance is incandescent lamp.
The recognition result classification marker of assembled classifier, Main classification device can also use other schemes, for example, using respectively Classification marker 1, -1 or 0,1, either -1,1 and other schemes come indicate corresponding electric appliance recognition result be yes, it is no. Assembled classifier can be identical with the classification marker scheme of Main classification device, can not also be identical.
Can also include electric appliance steady-state current virtual value I in the input feature vector of the assembled classifierW.For example, there is 2 kinds Different electric appliance, electric iron and resistance furnace need to identify, electric iron, resistance furnace are all pure resistor loads, and all has resistance temperature It is small to spend correction factor, the common feature of resistance value stabilization.Therefore, starting current feature above-mentioned and load current frequency are relied on merely Spectrum signature, the fundamental voltage current and phase difference feature of electric appliance can not distinguish them.Increase electric appliance stable state in input feature vector Current effective value IWAfterwards, electric iron power is small, electric appliance steady-state current virtual value IWIt is small;Resistance furnace power is big, and electric appliance steady-state current has Valid value IWGreatly, feature is different, and assembled classifier can carry out and complete to identify.
Subsidiary classification device is Bayes classifier.It can select NBC graders (Naive Bayes Classifier), TAN classification Three kinds of Bayes classifiers such as device (crown pruning), BAN graders (Bayes classifier of enhancing) it In it is a kind of be used as subsidiary classification device.
Embodiment 2 selects NBC graders as subsidiary classification device.Naive Bayes Classification is defined as follows:
(1) x={ a are set1, a2..., amIt is an item to be sorted, and the characteristic attribute that each a is x;
(2) category set C={ y are had1, y2..., yn};
(3) P (y are calculated1| x), P (y2| x) ..., P (yn|x);
(4) if P (yk| k)=max { P (y1| x), P (y2| x) ..., P (yn| x) }, then x ∈ yk
Calculate the (3) walk in the specific method of each conditional probability be:
1. it is training sample set to find the item collection cooperation to be sorted classified known to one;
2. statistics obtain it is of all categories under each characteristic attribute conditional probability estimation;
P(a1|y1), P (a2|y1) ..., P (am|y1);
P(a1|y2), P (a2|y2) ..., P (am|y2);
…;
P(a1|yn), P (a2|yn) ..., P (am|yn)。
3. according to Bayes' theorem, have:
Because denominator for all categories be constant, as long as therefore we molecule is maximized;Again because in simplicity Each characteristic attribute is conditional sampling in Bayes, so having:
In embodiment 2, the input feature vector of assembled classifier isWherein, IGIt is to open Dynamic current rush;IDIt is to start average current;QIIt is starting current momentum;A1、A3For 1,3 time in load current spectral characteristic Odd harmonic signal relative magnitude;For the fundamental voltage current and phase difference of electric appliance, unit is degree, and fundamental voltage is ahead of base When wave electric current,It is required that the electric appliance classification of identification is incandescent lamp, resistance furnace, electric fan, computer, hair-dryer.Enable simple shellfish The characteristic attribute combination x={ a of this grader of leaf1, a2, a3, a4, a5, a6In element and assembled classifier input feature vector collection Element in conjunction is sequentiallyIt corresponds;The output category set of Naive Bayes Classifier C={ y1, y2, y3, y4, y5Then corresponded respectively with electric appliance classification incandescent lamp, resistance furnace, electric fan, computer, hair-dryer.
The process of training NBC graders includes:
1, segmentation division is carried out to characteristic attribute, carries out sliding-model control.In embodiment 2, the characteristic attribute taken is discrete Change method 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, multigroup sample is acquired as training sample to every electric appliances type, while calculates and exists per electric appliances type sample The ratio occupied in all appliance type samples, that is, calculate separately P (y1)、P(y2)、P(y3)、P(y4)、P(y5).When every class electricity When device acquires identical sample size, for example, the sample more than 100 groups is acquired per electric appliances, wherein random per electric appliances Select 100 groups of samples as training sample, other are then used as test sample, and total training sample is 500 groups, and is had
P(y1)=P (y2)=P (y3)=P (y4)=P (y5)=0.2.
3, the frequency (ratio) of each characteristic attribute segmentation under each class condition of training sample is calculated, statistics obtains all kinds of The conditional probability estimation of each characteristic attribute under other, i.e., statistics calculates respectively
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(a2< 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> 009 | 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)。
By above-mentioned step 1, step 2, step 3, NBC classifier trainings are completed.Wherein, step 1 to characteristic attribute into Row segmentation is divided by manually determining, when carrying out disperse segmentaly to each input feature vector, the quantity of segmentation is 2 sections or 2 sections More than, for example, in embodiment 2, feature a1-a6All it is divided into 3 sections.Each feature is specifically divided into how many sections, the selection of fragmentation threshold Result after being tested test sample according to the Bayes classifier after training is adjusted.Step 2, step 3 are by information The either computer of processing module 102, which calculates, to be completed.
It is using the method that Bayes classifier is classified in the present invention:
1, using the input feature vector of assembled classifier as the input feature vector of Bayes classifier.In example 2, it will combine The input feature vector set of graderAs the input feature vector x of Bayes classifier, and there is x ={ a1, a2, a3, a4, a5, a6}。
2, according to training obtain it is of all categories under each characteristic attribute conditional probability estimate, respectively determine each input feature vector Where the segmentation of attribute and determine its probability P (a to every electric appliances classification1|y1)~P (am|yn), wherein electric appliance category set For C={ y1, y2..., yn}.In embodiment 2, electric appliance category set C={ y1, y2, y3, y4, y5The corresponding electric appliance classification represented is Incandescent lamp, resistance furnace, electric fan, computer, hair-dryer determine P (a1|y1)~P (a6|y5) method be using training NBC point The conditional probability estimation of each characteristic attribute obtained during class device.
3, according to formula
Calculate the other posterior probability of each electric type.Because denominator P (x) is constant for all electric appliance classifications, P (x) is enabled =1 substitutes actual P (x) value, and the mutual size not influenced between each electric appliance classification posterior probability compares, has at this time
In embodiment 2, have
Trained Bayes classifier is tested using test sample, adjustment pair is decided whether according to test result The discretization method (adjusting number of fragments and threshold value) of input feature vector, re -training Bayes classifier.
Main classification device is support vector machine classifier, or is SVM classifier.SVM classifier is particularly suitable for solving two-value Classification situation, therefore, Main classification device is using multiple two classes output SVM classifier composition, each two classes output SVM classifier correspondence A kind of appliance type is identified, for example, 4 two classes output SVM classifiers may be used in embodiment 1 identifies incandescent lamp, electricity respectively Stove, hair-dryer, computer are hindered, 5 two classes output SVM classifiers may be used in embodiment 2 and identify incandescent lamp, resistance respectively Stove, electric fan, computer, hair-dryer.When Main classification device selects multiple two classes output SVM classifiers to collectively constitute, all two classes The input feature vector of output SVM classifier is the input feature vector of Main classification device.
When each two class of training exports SVM classifier, multigroup sample is acquired to every electric appliances type, randomly selects part work For training sample, remaining is as test sample.The method that sample collection uses the starting current feature above-mentioned for obtaining electric appliance With the load current spectrum signature for obtaining electric appliance and the method for the fundamental voltage current and phase difference feature for obtaining electric appliance.All Training sample exports the training sample of SVM classifier as each two class.For example, in example 2, it can be respectively to white heat The loads such as lamp, resistance furnace, electric fan, computer, hair-dryer acquire more than 100 groups samples, randomly select wherein each 100 Group, totally 500 groups of samples form training sample, and remaining sample forms test sample;Certainly, certain load or all loads are adopted 100 groups of samples are not achieved in the sample size of collection, and SVM classifier can also obtain preferable classifying quality.
The radial base RBF kernel functions of two classes output SVM classifier selection selected by Main classification device, and use particle cluster algorithm (PSO) the punishment parameter C and nuclear parameter Y that SVM classifier is exported to each two class are in optimized selection.
Each two classes output SVM classifier only needs to be performed a kind of Classification and Identification of appliance type, the training of SVM classifier It is relatively easy.Main classification device is made of multiple two classes output SVM classifier, between each two classes output SVM classifier independently of each other, Therefore, when a certain characteristic attribute being identified, the recognition result that Main classification device is possible to output is unique appliance type, or Person's recognition result is 2 kinds and either two or more appliance type or fails to provide the appliance type of Classification and Identification result.

Claims (9)

1. a kind of students' dormitory electrical appliance genre classification methods, which is characterized in that it includes support vector machine classifier and shellfish to use The assembled classifier of this grader of leaf carries out appliance type identification;The input feature vector of the assembled classifier includes the startup of electric appliance The fundamental voltage current and phase difference of current characteristic, the load current spectrum signature of electric appliance and electric appliance.
2. electrical appliance genre classification methods in students' dormitory as described in claim 1, which is characterized in that the assembled classifier In, support vector machine classifier is main grader, and Bayes classifier is auxiliary grader.
3. electrical appliance genre classification methods in students' dormitory as claimed in claim 2, which is characterized in that the assembled classifier into Row appliance type knows method for distinguishing:When Main classification device successfully realizes appliance type identification, the appliance type of Main classification device is known Other result is the recognition result of assembled classifier;When Main classification device fails to realize appliance type identification, and the identification of Main classification device As a result it is 2 kinds of 2 kinds or two or more appliance type recognition result that either two or more appliance type exports Main classification device In, appliance type recognition result of the highest appliance type of probability as assembled classifier in the output of subsidiary classification device;When main point Class device fails to realize appliance type identification, and when failing to provide the appliance type of identification in the recognition result of Main classification device, will be auxiliary Appliance type recognition result of the highest appliance type of probability as assembled classifier in helping grader to export.
4. electrical appliance genre classification methods in students' dormitory as claimed in any one of claims 1-3, which is characterized in that described negative Current spectrum feature is carried to be prepared by the following:
Step 1: obtaining the steady state current signals of electric appliance, and it is converted into corresponding steady-state current digital signal;
Step 2: carrying out Fourier transform to steady-state current digital signal, load current spectral characteristic is obtained;
Step 3: using the odd harmonic signal relative magnitude that overtone order in load current spectral characteristic is n times as load electricity Flow spectrum signature, wherein n=1,3 ..., M;The M indicates harmonic wave highest number and M is more than or equal to 3.
5. electrical appliance genre classification methods in students' dormitory as claimed in claim 4, which is characterized in that the harmonic signal is opposite Amplitude is the ratio of harmonic signal amplitude and electric appliance load steady-state current virtual value.
6. electrical appliance genre classification methods in students' dormitory as claimed in any one of claims 1-3, which is characterized in that described to open Streaming current feature includes starting current rush, starting average current, starting current momentum.
7. electrical appliance genre classification methods in students' dormitory as claimed in any one of claims 1-3, which is characterized in that the electricity The fundamental voltage current and phase difference of device is prepared by the following:
Step 1., after electric appliance enters stable state, synchronous steady state voltage signal, steady state current signals for obtaining electric appliance, and will It is converted to corresponding steady state voltage digital signal, steady-state current digital signal;
2., to steady state voltage digital signal, steady-state current digital signal step carries out digital filtering respectively, extract fundamental voltage Signal, fundamental current signal;
Step 3., analysis calculate the phase difference between fundamental voltage signal and fundamental current signal, by fundamental voltage signal and base Fundamental voltage current and phase difference of the phase difference as electric appliance between signal wave current.
8. electrical appliance genre classification methods in students' dormitory as claimed in claim 7, which is characterized in that described to wait for that electric appliance enters surely Determine the judgement after state, is carried out according to the load current virtual value of each power frequency period within nearest N number of power frequency period;Institute The value range for stating N is 50-500.
9. electrical appliance genre classification methods in students' dormitory as claimed in claim 8, which is characterized in that the load current of electric appliance Continuous sampling is carried out, as unit computational load current effective value and is preserved using power frequency period;Calculate the negative of nearest N number of power frequency period Carry the average value of current effective value;The load current virtual value and the N of each power frequency period within nearest N number of power frequency period The average value of the load current virtual value of a power frequency period compares, when fluctuating range is respectively less than the relative error range E set, Judgement electric appliance enters stable state;The value range of the E is 2%-20%.
CN201810338493.8A 2016-04-08 2016-04-08 A kind of students' dormitory electrical appliance genre classification methods Pending CN108594040A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201810338493.8A CN108594040A (en) 2016-04-08 2016-04-08 A kind of students' dormitory electrical appliance genre classification methods
CN201610218359.5A CN105785187B (en) 2016-04-08 2016-04-08 A kind of students' dormitory electrical appliance type judgement method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810338493.8A CN108594040A (en) 2016-04-08 2016-04-08 A kind of students' dormitory electrical appliance genre classification methods

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201610218359.5A Division CN105785187B (en) 2016-04-08 2016-04-08 A kind of students' dormitory electrical appliance type judgement method

Publications (1)

Publication Number Publication Date
CN108594040A true CN108594040A (en) 2018-09-28

Family

ID=56395135

Family Applications (2)

Application Number Title Priority Date Filing Date
CN201810338493.8A Pending CN108594040A (en) 2016-04-08 2016-04-08 A kind of students' dormitory electrical appliance genre classification methods
CN201610218359.5A Active CN105785187B (en) 2016-04-08 2016-04-08 A kind of students' dormitory electrical appliance type judgement method

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN201610218359.5A Active CN105785187B (en) 2016-04-08 2016-04-08 A kind of students' dormitory electrical appliance type judgement method

Country Status (1)

Country Link
CN (2) CN108594040A (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909101B (en) * 2017-01-13 2019-04-23 中国海洋大学 A kind of non-intrusion type household electrical appliance sorter and method
CN107525986A (en) * 2017-07-22 2017-12-29 华映科技(集团)股份有限公司 Free-standing electrical equipment type automatic identification method
CN107271824A (en) * 2017-07-22 2017-10-20 华映科技(集团)股份有限公司 Single-line type electrical equipment type automatic identification method
CN107525984A (en) * 2017-07-22 2017-12-29 华映科技(集团)股份有限公司 Device type automatic identification method based on plant capacity
CN107525985A (en) * 2017-07-22 2017-12-29 华映科技(集团)股份有限公司 Device type automatic identification method based on device current ID

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001351104A (en) * 2000-06-06 2001-12-21 Matsushita Electric Ind Co Ltd Method/device for pattern recognition and method/device for pattern collation
CN102279326B (en) * 2011-04-22 2014-03-12 华中科技大学 Electrical appliance recognition method and household user carbon emission metering system applying same
TWI443346B (en) * 2012-09-14 2014-07-01 Chunghwa Telecom Co Ltd Electrical appliance identification system and method
CN104090176A (en) * 2014-06-09 2014-10-08 深圳市宏电技术股份有限公司 Intelligent household appliance recognition method based on power consumption characteristic curve

Also Published As

Publication number Publication date
CN105785187A (en) 2016-07-20
CN105785187B (en) 2018-06-15

Similar Documents

Publication Publication Date Title
CN104819576B (en) The leaving water temperature control method and water-heater system of water heater
Berges et al. User-centered nonintrusive electricity load monitoring for residential buildings
CN103544663B (en) The recommendation method of network open class, system and mobile terminal
CN103673008B (en) A kind of intelligent range hood and the control method of this range hood
US8539259B2 (en) Method and apparatus for indicating power level over a communication interface
Dong et al. An event window based load monitoring technique for smart meters
US8843334B2 (en) Utility metering
EP3053299B1 (en) Detection and classification scheme for power over ethernet system
US8311754B2 (en) Power monitoring and analysis system for identifying and tracking individual electrical devices
EP1842324B1 (en) Detecting legacy powered device in power over ethernet system
CN102279326B (en) Electrical appliance recognition method and household user carbon emission metering system applying same
US8463452B2 (en) Apparatus using time-based electrical characteristics to identify an electrical appliance
AU2002350112B8 (en) Systems, methods, and software for classifying documents
CN104809163A (en) Method of recommending clothing matching of user based on mobile terminal and mobile terminal
TWI440862B (en) Electrical detection method and system based on user feedback information
CN104199822A (en) Method and system for identifying demand classification corresponding to searching
CN104214804B (en) Electromagnetic heating device and cookware detecting method thereof
DE112011103159T5 (en) Energy consumption detection based on a voltage drop
US20100287489A1 (en) Power Monitoring and Analysis System for Identifying Individual Electrical Devices
CN105187630A (en) Mobile terminal music saving method and system based on emotion recognition
CN105184304B (en) Image identification device and characteristic quantity data register method to image identification device
CN105910232A (en) Air conditioner control method, system and air conditioner based on neighboring air conditioner setting learning
CN104076224B (en) A kind of test method of power information collecting device reliability demonstration
Matthews et al. Automatically disaggregating the total electrical load in residential buildings: a profile of the required solution
CN105242600A (en) Personalized intelligent water closet control system, control method thereof, and intelligent water closet

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination