CN105204490A - Intelligent diagnosis system and method for standby power consumption based on integration characteristic selection and classification - Google Patents
Intelligent diagnosis system and method for standby power consumption based on integration characteristic selection and classification Download PDFInfo
- Publication number
- CN105204490A CN105204490A CN201510475741.XA CN201510475741A CN105204490A CN 105204490 A CN105204490 A CN 105204490A CN 201510475741 A CN201510475741 A CN 201510475741A CN 105204490 A CN105204490 A CN 105204490A
- Authority
- CN
- China
- Prior art keywords
- power consumption
- electrical appliance
- household electrical
- temperature
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides an intelligent diagnosis system and method for the standby power consumption based on integration characteristic selection and classification. A host selects characteristic parameters from collected signals of a household electric appliance, a support vector machine (SVM) is used to screen the characteristic parameters to obtain an optimal characteristic subset and a trained SVM classifier, whether the household electrical appliance is in a standby state is determined according to an integration characteristic selection and classification algorithm, and if the household electrical appliance is in the standby state, a terminal node controls a switching control module to switch off the household electrical appliance. Thus, the standby power consumption is reduced, and electric energy is saved.
Description
Technical field
The present invention relates to household electrical appliance power consumption diagnostic techniques field, be specifically related to a kind of stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification and diagnostic method thereof.
Background technology
Along with the popularization of intelligent grid and ladder, time-of-use tariffs, various intelligent electric meter arises at the historic moment, people's saving consciousness is also more and more stronger, also wish to carry out intelligent management to household electrical appliance and can be real-time the holding state of understanding household electrical appliance, then turn off the household electrical appliance being in holding state automatically.Intelligent power saving system can help people to realize this hope.But the maximum drawback of traditional smart machine increases and decreases equipment exactly all needs rewiring, overlapping investment and affect attractive in appearance; On the other hand, the extensibility of system and movability are also poor, and installation and maintenance cost is high.
Summary of the invention
The application is by providing a kind of stand-by power consumption intelligent diagnostics system based on Ensemble feature selection classification and diagnostic method thereof, poor to solve Intelligent power saving system extensibility and mobility in prior art, installation and the higher technical matters of maintenance cost.
For solving the problems of the technologies described above, the application is achieved by the following technical solutions:
A kind of stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification, comprise host computer, the terminal node that telegon and each household electrical appliance place are arranged, information acquisition module, gauge tap, wherein, described information acquisition module comprises temperature sensor and electric energy acquisition chip, in order to gather the temperature of household electrical appliance, voltage and current information, by described terminal node, the information collected is transferred to described host computer by described telegon, described host computer carries out analysis to the information collected and judges, and send steering order by described telegon to described terminal node, described terminal node controls described gauge tap, thus control the closedown of household electrical appliance, described host computer place is provided with Temperature Humidity Sensor in order to gather indoor temperature and humidity.
As preferred technical scheme, described host computer adopts ARM9TQ2440 host computer, described telegon adopts System on Chip/SoC CC2430, described terminal node is ZigBee circuit board, described gauge tap module adopts SL-C electromagnetic type relay, described temperature sensor adopts DS18B20, and described electric energy acquisition chip adopts ADE7755, and described Temperature Humidity Sensor adopts DHT21.
Wherein, host computer selects the ARM microcontroller ARM9TQ2440 of 32, and its frequency of operation can reach hundreds of MHz.Be integrated with many interior peripheral hardwares, and have multiple communication interface, volume is little, power consumption and cost low, reliability is high, is particularly suitable as embedded host computer.System generally adopts Flash as program storage, adopts SDRAM as Installed System Memory.The embedded OS such as VxWorks, WinCE, Linux can be adopted.More complete ICP/IP protocol can embedded based on ARM platform, realize stronger Web service function.And the integrated multiple interfaces parts of energy, can complete the function of much complex in system.For the expansion of the follow-up function of home gateway provides possibility.
Telegon have employed the CC2430 System on Chip/SoC of Hua Nuo, and CC2430 System on Chip/SoC is the SOC of integrated ZigBee technology, 8051MCU process core, in integrated level and cost and research and development difficulty, all possesses suitable advantage.The features such as ZigBee has closely, low-power consumption, low rate, transmitted in both directions, a kind of relevant networking based on the development of IEEE802.15.4 wireless standard, safety and application software aspect radio network technique, mainly be suitable for carrying the business that data traffic is little, message transmission rate is low, can embed in various equipment, the monitoring to various important places such as family, industry and medical science can be realized.ZigBee-network forms primarily of telegon, router and terminal node.ZigBee support starlike type, netted and tree tufted network topology structure.Can have at most 65535 nodes in each ZigBee-network, distribution is responsible for by the network coordinator (NetworkCoordinator) of ZigBee in each address of node.In addition, the transmission range of each node is between 30-100m, and the distance of transmission can also be extended by using power amplifier and multi-hop reticulate texture.
Each terminal node is a little ZigBee circuit board, when host computer judges the household appliance signal collected, after showing that household electrical appliance are in holding state, whether host computer is energized by the closed control socket that reaches of terminal node control SL-C electromagnetic type relay, turn off the household electrical appliance being in holding state, thus decrease stand-by power consumption, saves energy.
Based on a diagnostic method for the stand-by power consumption intelligent diagnosis system of Ensemble feature selection classification, comprise the following steps:
S1: the collection of household appliance signal;
S2: the transmission of household appliance signal;
S3: according to the power P of the household appliance signal computist electrical appliance collected;
S4: the voltage characteristic V extracting household appliance signal
i(i=1,2 ..., m), current characteristic I
q(q=1,2 ..., n), temperature profile T
p(p=1,2 ..., s) and indoor temperature feature T1
r(r=1,2 ..., l) with Humidity Features S1
t(t=1,2, z), wherein the value of voltage characteristic number i is the natural number of 1 to m, and the value of current characteristic number q is the natural number of 1 to n, and the value of household electrical appliance temperature profile number p is the natural number of 1 to s, the value of indoor temperature Characteristic Number r is the natural number of 1 to l, and the value of indoor humidity Characteristic Number t is the natural number of 1 to z;
S5: based on Support vector regression algorithm, set up inverse model, carries out Feature Selection by inverting accuracy, to obtain optimal feature subset F
final(1,2 ... k) and inverting obtain closest to power P corresponding power P ', the number final value of optimal feature subset is the natural number of 1 to k;
S6: by power P ' with voltage characteristic V
i(i=1,2 ..., m), current characteristic I
q(q=1,2 ..., n), temperature profile T
p(p=1,2 ..., t) and indoor temperature feature T1
r(r=1,2 ..., l) with Humidity Features S1
t(t=1,2 ..., z) merge, form total feature set F to be selected
j(j=1,2 ..., h), the number j value of feature set to be selected is the natural number of 1 to h;
S7: based on support vector machine classifier and total feature set F to be selected
j(j=1,2 ..., h) carry out feature selecting and classification;
S8: obtain optimal feature subset F
final(final=1,2 ..., support vector machine classifier SVM_final k) and after training;
S9: build the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification;
S10: judge whether household electrical appliance are in holding state, if so, then enter step S11, otherwise step S3 is returned in redirect;
S11: described host computer controls gauge tap module by described wireless transport module, closes the household electrical appliance being in holding state.
By optimizing signal characteristic to be selected and support vector machine classifier parameter simultaneously, the precision of signal characteristic selection and acquisition and household electrical appliance energy consumption relational expression can be improved.Adopt high-precision packaged type feature selection mode, interpretational criteria is the pattern classification accuracy rate of sorter.Using the energy consumption of household electrical appliance as criteria for classification, thus the relational expression obtaining signal characteristic and household electrical appliance energy consumption is converted into pattern classification problem.
Further, Link-like Agent Genetic Algorithm is adopted to search for optimal feature subset F in step S8
final(final=1,2 ..., k), population quantity is selected to be greater than mrna length, and adaptive crossover mutation is:
In formula, p
c1and p
c2be two individualities to be intersected, initialization p
c1=0.9, p
c2=0.6, f
avgfor the average fitness often for population, f
maxfor the maximum adaptation degree often for population, f' is fitness value larger in two individualities to be intersected, and interlace operation adopts the single-point bracketing method of adaptive crossover mutation;
Genetic mutation adopts adaptive mutation probability equally:
In formula, p
m1, p
m2be respectively the mutation probability of individual 1 and individual 2, initialization p
m1=0.1, p
m2=0.006, f
avgfor the average fitness often for population, f
maxfor the maximum adaptation degree often for population, f waits the individual fitness value that makes a variation, and mutation operation adopts the scale-of-two alternative method of self-adaptive mutation.
Further, in step S9, the kernel function of support vector machine is radial basis function, adopt five rank check additions, training convergence criterion is square error, sample of signal is divided into A, B, C, D tetra-groups, wherein A group sample is used for Training Support Vector Machines sorter, B group sample is used to guide Link-like Agent Genetic Algorithm and carries out search optimal feature subset, and C group sample is for carrying out parametric inversion, and D group sample is used for carrying out performance test.
Adopt leaving-one method to test A group sample and B group sample, export the support vector machine classifier parameter that the sample of signal characteristic sum after selecting trains simultaneously; The eigenwert of sample will be normalized before feature selecting classification.
Employing stays ten methods that C group sample is divided into training sample and test sample book at random, by this distribution, obtain many group training samples and test sample book, based on acquired training sample and support vector machine classifier parameter, carry out parametric regression to support vector machine, input vector is signal characteristic value, output vector is the standard value of household electrical appliance power consumption, square error stops after meeting the demands, thus the matrix that gets parms, that is: the relational expression of signal characteristic value and household electrical appliance power consumption; The eigenwert of sample is not normalized before parametric inversion.
The power consumption of household electrical appliance in section sometime can be calculated by the relational expression of signal characteristic value and household electrical appliance power consumption, D group sample be tested, obtains mean value and the standard deviation of household electrical appliance energy distribution and numeral.
As the preferred technical scheme of one, the voltage characteristic extracted in step S4 comprises the unevenness of voltage's distribiuting, average voltage, voltage mean square deviation, voltage entropy, current characteristic comprises the unevenness of distribution of current, electric current is average, electric current mean square deviation, electric current entropy, temperature profile comprises the unevenness of Temperature Distribution, temperature-averaging, temperature mean square deviation, thermal entropy, indoor temperature feature comprises the unevenness of indoor temperature distribution, indoor temperature is average, indoor temperature variance, indoor temperature entropy, indoor humidity feature comprises the unevenness of indoor humidity distribution, indoor humidity is average, indoor humidity variance, indoor humidity entropy.
Compared with prior art, the technical scheme that the application provides, the technique effect had or advantage are: system controllability and measurability is high, and extensibility is good, and reduce the energy consumption of system, are easy to apply.
Accompanying drawing explanation
Fig. 1 is stand-by power consumption intelligent diagnosis system structured flowchart of the present invention;
Fig. 2 is the process flow diagram of stand-by power consumption intelligent diagnosing method of the present invention.
Embodiment
The embodiment of the present application is by providing a kind of stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification and diagnostic method thereof, poor to solve Intelligent power saving system extensibility and mobility in prior art, install and technical matters that maintenance cost is higher.
In order to better understand technique scheme, below in conjunction with Figure of description and concrete embodiment, technique scheme is described in detail.
Embodiment
A kind of stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification, as shown in Figure 1, comprise host computer, the terminal node that telegon and each household electrical appliance place are arranged, information acquisition module, gauge tap, wherein, described information acquisition module comprises temperature sensor and electric energy acquisition chip, in order to gather the temperature of household electrical appliance, voltage and current information, by described terminal node, the information collected is transferred to described host computer by described telegon, described host computer carries out analysis to the information collected and judges, and send steering order by described telegon to described terminal node, described terminal node controls described gauge tap, thus control the closedown of household electrical appliance, described host computer place is provided with Temperature Humidity Sensor in order to gather indoor temperature and humidity.
As preferred technical scheme, described host computer adopts ARM9TQ2440 host computer, described telegon adopts System on Chip/SoC CC2430, described terminal node is ZigBee circuit board, described gauge tap module adopts SL-C electromagnetic type relay, described temperature sensor adopts DS18B20, and described electric energy acquisition chip adopts ADE7755, and described Temperature Humidity Sensor adopts DHT21.
Wherein, host computer selects the ARM microcontroller ARM9TQ2440 of 32, and its frequency of operation can reach hundreds of MHz.Be integrated with many interior peripheral hardwares, and have multiple communication interface, volume is little, power consumption and cost low, reliability is high, is particularly suitable as embedded host computer.System generally adopts Flash as program storage, adopts SDRAM as Installed System Memory.The embedded OS such as VxWorks, WinCE, Linux can be adopted.More complete ICP/IP protocol can embedded based on ARM platform, realize stronger Web service function.And the integrated multiple interfaces parts of energy, can complete the function of much complex in system.For the expansion of the follow-up function of home gateway provides possibility.
Telegon have employed the CC2430 System on Chip/SoC of Hua Nuo, and CC2430 System on Chip/SoC is the SOC of integrated ZigBee technology, 8051MCU process core, in integrated level and cost and research and development difficulty, all possesses suitable advantage.The features such as ZigBee has closely, low-power consumption, low rate, transmitted in both directions, a kind of relevant networking based on the development of IEEE802.15.4 wireless standard, safety and application software aspect radio network technique, mainly be suitable for carrying the business that data traffic is little, message transmission rate is low, can embed in various equipment, the monitoring to various important places such as family, industry and medical science can be realized.ZigBee-network forms primarily of telegon, router and terminal node.ZigBee support starlike type, netted and tree tufted network topology structure.Can have at most 65535 nodes in each ZigBee-network, distribution is responsible for by the network coordinator (NetworkCoordinator) of ZigBee in each address of node.In addition, the transmission range of each node is between 30-100m, and the distance of transmission can also be extended by using power amplifier and multi-hop reticulate texture.
Each terminal node is a little ZigBee circuit board, when host computer judges the household appliance signal collected, after showing that household electrical appliance are in holding state, whether host computer is energized by the closed control socket that reaches of terminal node control SL-C electromagnetic type relay, turn off the household electrical appliance being in holding state, thus decrease stand-by power consumption, saves energy.
Based on a diagnostic method for the stand-by power consumption intelligent diagnosis system of Ensemble feature selection classification, as shown in Figure 2, comprise the following steps:
S1: the collection of household appliance signal;
S2: the transmission of household appliance signal;
S3: according to the power P of the household appliance signal computist electrical appliance collected;
S4: the voltage characteristic V extracting household appliance signal
i(i=1,2 ..., m), current characteristic I
q(q=1,2 ..., n), temperature profile T
p(p=1,2 ..., s) and indoor temperature feature T1
r(r=1,2 ..., l) with Humidity Features S1
t(t=1,2, z), wherein the value of voltage characteristic number i is the natural number of 1 to m, and the value of current characteristic number q is the natural number of 1 to n, and the value of household electrical appliance temperature profile number p is the natural number of 1 to s, the value of indoor temperature Characteristic Number r is the natural number of 1 to l, and the value of indoor humidity Characteristic Number t is the natural number of 1 to z;
S5: based on Support vector regression algorithm, set up inverse model, carries out Feature Selection by inverting accuracy, to obtain optimal feature subset F
final(1,2 ... k) and inverting obtain closest to power P corresponding power P ', the number final value of optimal feature subset is the natural number of 1 to k;
S6: by power P ' with voltage characteristic V
i(i=1,2 ..., m), current characteristic I
q(q=1,2 ..., n), temperature profile T
p(p=1,2 ..., t) and indoor temperature feature T1
r(r=1,2 ..., l) with Humidity Features S1
t(t=1,2 ..., z) merge, form total feature set F to be selected
j(j=1,2 ..., h), the number j value of feature set to be selected is the natural number of 1 to h;
S7: based on support vector machine classifier and total feature set F to be selected
j(j=1,2 ..., h) carry out feature selecting and classification;
S8: obtain optimal feature subset F
final(final=1,2 ..., support vector machine classifier SVM_final k) and after training;
S9: build the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification;
S10: judge whether household electrical appliance are in holding state, if so, then enter step S11, otherwise step S3 is returned in redirect;
S11: described host computer controls gauge tap module by described wireless transport module, closes the household electrical appliance being in holding state.
By optimizing signal characteristic to be selected and support vector machine classifier parameter simultaneously, the precision of signal characteristic selection and acquisition and household electrical appliance energy consumption relational expression can be improved.Adopt high-precision packaged type feature selection mode, interpretational criteria is the pattern classification accuracy rate of sorter.Using the energy consumption of household electrical appliance as criteria for classification, thus the relational expression obtaining signal characteristic and household electrical appliance energy consumption is converted into pattern classification problem.
Further, Link-like Agent Genetic Algorithm is adopted to search for optimal feature subset F in step S8
final(final=1,2 ..., k), population quantity is selected to be greater than mrna length, and adaptive crossover mutation is:
In formula, p
c1and p
c2be two individualities to be intersected, initialization p
c1=0.9, p
c2=0.6, f
avgfor the average fitness often for population, f
maxfor the maximum adaptation degree often for population, f' is fitness value larger in two individualities to be intersected, and interlace operation adopts the single-point bracketing method of adaptive crossover mutation;
Genetic mutation adopts adaptive mutation probability equally:
In formula, p
m1, p
m2be respectively the mutation probability of individual 1 and individual 2, initialization p
m1=0.1, p
m2=0.006, f
avgfor the average fitness often for population, f
maxfor the maximum adaptation degree often for population, f waits the individual fitness value that makes a variation, and mutation operation adopts the scale-of-two alternative method of self-adaptive mutation.
Further, in step S9, the kernel function of support vector machine is radial basis function, adopt five rank check additions, training convergence criterion is square error, sample of signal is divided into A, B, C, D tetra-groups, wherein A group sample is used for Training Support Vector Machines sorter, B group sample is used to guide Link-like Agent Genetic Algorithm and carries out search optimal feature subset, and C group sample is for carrying out parametric inversion, and D group sample is used for carrying out performance test.
Adopt leaving-one method to test A group sample and B group sample, export the support vector machine classifier parameter that the sample of signal characteristic sum after selecting trains simultaneously; The eigenwert of sample will be normalized before feature selecting classification.
Employing stays ten methods that C group sample is divided into training sample and test sample book at random, by this distribution, obtain many group training samples and test sample book, based on acquired training sample and support vector machine classifier parameter, carry out parametric regression to support vector machine, input vector is signal characteristic value, output vector is the standard value of household electrical appliance power consumption, square error stops after meeting the demands, thus the matrix that gets parms, that is: the relational expression of signal characteristic value and household electrical appliance power consumption; The eigenwert of sample is not normalized before parametric inversion.
The power consumption of household electrical appliance in section sometime can be calculated by the relational expression of signal characteristic value and household electrical appliance power consumption, D group sample be tested, obtains mean value and the standard deviation of household electrical appliance energy distribution and numeral.
As the preferred technical scheme of one, the voltage characteristic extracted in step S4 comprises the unevenness of voltage's distribiuting, average voltage, voltage mean square deviation, voltage entropy, current characteristic comprises the unevenness of distribution of current, electric current is average, electric current mean square deviation, electric current entropy, temperature profile comprises the unevenness of Temperature Distribution, temperature-averaging, temperature mean square deviation, thermal entropy, indoor temperature feature comprises the unevenness of indoor temperature distribution, indoor temperature is average, indoor temperature variance, indoor temperature entropy, indoor humidity feature comprises the unevenness of indoor humidity distribution, indoor humidity is average, indoor humidity variance, indoor humidity entropy.
In above-described embodiment of the application, by providing a kind of stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification and diagnostic method thereof, host computer carries out characteristic parameter selection to the household appliance signal collected, support vector machine is utilized to screen characteristic parameter, obtain the support vector machine classifier after optimal feature subset and training, judge whether household electrical appliance are in holding state by this Ensemble feature selection sorting algorithm, if be in holding state, then control gauge tap module by terminal node standby household electrical appliance cut out, reach minimizing stand-by power consumption, the object of saves energy.
It should be noted that; above-mentioned explanation is not limitation of the present invention; the present invention is also not limited in above-mentioned citing, the change that those skilled in the art make in essential scope of the present invention, modification, interpolation or replacement, also should belong to protection scope of the present invention.
Claims (7)
1. the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification, it is characterized in that, comprise host computer, the terminal node that telegon and each household electrical appliance place are arranged, information acquisition module, gauge tap, wherein, described information acquisition module comprises temperature sensor and electric energy acquisition chip, in order to gather the temperature of household electrical appliance, voltage and current information, by described terminal node, the information collected is transferred to described host computer by described telegon, described host computer carries out analysis to the information collected and judges, and send steering order by described telegon to described terminal node, described terminal node controls described gauge tap, thus control the closedown of household electrical appliance, described host computer place is provided with Temperature Humidity Sensor in order to gather indoor temperature and humidity.
2. the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification according to claim 1, it is characterized in that, described host computer adopts ARM9TQ2440 host computer, described telegon adopts System on Chip/SoC CC2430, described terminal node is ZigBee circuit board, and described gauge tap module adopts SL-C electromagnetic type relay, and described temperature sensor adopts DS18B20, described electric energy acquisition chip adopts ADE7755, and described Temperature Humidity Sensor adopts DHT21.
3., as claimed in claim 1 based on the diagnostic method of the stand-by power consumption intelligent diagnosis system of Ensemble feature selection classification, it is characterized in that, comprise the following steps:
S1: the collection of household appliance signal;
S2: the transmission of household appliance signal;
S3: according to the power P of the household appliance signal computist electrical appliance collected;
S4: the voltage characteristic V extracting household appliance signal
i(i=1,2 ..., m), current characteristic I
q(q=1,2 ..., n), temperature profile T
p(p=1,2 ..., s) and indoor temperature feature T1
r(r=1,2 ..., l) with Humidity Features S1
t(t=1,2, z), wherein the value of voltage characteristic number i is the natural number of 1 to m, and the value of current characteristic number q is the natural number of 1 to n, and the value of household electrical appliance temperature profile number p is the natural number of 1 to s, the value of indoor temperature Characteristic Number r is the natural number of 1 to l, and the value of indoor humidity Characteristic Number t is the natural number of 1 to z;
S5: based on Support vector regression algorithm, set up inverse model, carries out Feature Selection by inverting accuracy, to obtain optimal feature subset F
final(1,2 ... k) and inverting obtain closest to power P corresponding power P ', wherein the number final value of optimal feature subset is the natural number of 1 to k;
S6: by power P ' with voltage characteristic V
i(i=1,2 ..., m), current characteristic I
q(q=1,2 ..., n), temperature profile T
p(p=1,2 ..., t) and indoor temperature feature T1
r(r=1,2 ..., l) with Humidity Features S1
t(t=1,2 ..., z) merge, form total feature set F to be selected
j(j=1,2 ..., h), wherein the number j value of feature set to be selected is the natural number of 1 to h;
S7: based on support vector machine classifier and total feature set F to be selected
j(j=1,2 ..., h) carry out feature selecting and classification;
S8: obtain optimal feature subset F
final(final=1,2 ..., support vector machine classifier SVM_final k) and after training;
S9: build the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification;
S10: judge whether household electrical appliance are in holding state, if so, then enter step S11, otherwise step S3 is returned in redirect;
S11: described host computer controls gauge tap module by described wireless transport module, closes the household electrical appliance being in holding state.
4. the diagnostic method of the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification according to claim 3, is characterized in that, adopts Link-like Agent Genetic Algorithm to search for optimal feature subset F in step S8
final(final=1,2 ..., k), population quantity is selected to be greater than mrna length, and adaptive crossover mutation is:
In formula, p
c1and p
c2be two individualities to be intersected, initialization p
c1=0.9, p
c2=0.6, f
avgfor the average fitness often for population, f
maxfor the maximum adaptation degree often for population, f' is fitness value larger in two individualities to be intersected, and interlace operation adopts the single-point bracketing method of adaptive crossover mutation;
Genetic mutation adopts adaptive mutation probability equally:
In formula, p
m1, p
m2be respectively the mutation probability of individual 1 and individual 2, initialization p
m1=0.1, p
m2=0.006, f
avgfor the average fitness often for population, f
maxfor the maximum adaptation degree often for population, f waits the individual fitness value that makes a variation, and mutation operation adopts the scale-of-two alternative method of self-adaptive mutation.
5. the diagnostic method of the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification according to claim 3, it is characterized in that, in step S9, the kernel function of support vector machine is radial basis function, adopt five rank check additions, training convergence criterion is square error, sample of signal is divided into A, B, C, D tetra-groups, wherein A group sample is used for Training Support Vector Machines sorter, B group sample is used to guide Link-like Agent Genetic Algorithm and carries out search optimal feature subset, C group sample is for carrying out parametric inversion, and D group sample is used for carrying out performance test.
6. the diagnostic method of the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification according to claim 5, is characterized in that,
Adopt leaving-one method to test A group sample and B group sample, export the support vector machine classifier parameter that the sample of signal characteristic sum after selecting trains simultaneously;
Employing stays ten methods that C group sample is divided into training sample and test sample book at random, by this distribution, obtain many group training samples and test sample book, based on acquired training sample and support vector machine classifier parameter, carry out parametric regression to support vector machine, input vector is signal characteristic value, output vector is the standard value of household electrical appliance power consumption, square error stops after meeting the demands, thus the matrix that gets parms, that is: the relational expression of signal characteristic value and household electrical appliance power consumption;
The power consumption of household electrical appliance in section sometime can be calculated by the relational expression of signal characteristic value and household electrical appliance power consumption, D group sample be tested, obtains mean value and the standard deviation of household electrical appliance energy distribution and numeral.
7. the diagnostic method of the stand-by power consumption intelligent diagnosis system based on Ensemble feature selection classification according to claim 3, it is characterized in that, the voltage characteristic extracted in step S4 comprises the unevenness of voltage's distribiuting, average voltage, voltage mean square deviation, voltage entropy, current characteristic comprises the unevenness of distribution of current, electric current is average, electric current mean square deviation, electric current entropy, temperature profile comprises the unevenness of Temperature Distribution, temperature-averaging, temperature mean square deviation, thermal entropy, indoor temperature feature comprises the unevenness of indoor temperature distribution, indoor temperature is average, indoor temperature variance, indoor temperature entropy, indoor humidity feature comprises the unevenness of indoor humidity distribution, indoor humidity is average, indoor humidity variance, indoor humidity entropy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510475741.XA CN105204490B (en) | 2015-08-06 | 2015-08-06 | The diagnostic method for the stand-by power consumption intelligent diagnosis system classified based on Ensemble feature selection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510475741.XA CN105204490B (en) | 2015-08-06 | 2015-08-06 | The diagnostic method for the stand-by power consumption intelligent diagnosis system classified based on Ensemble feature selection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105204490A true CN105204490A (en) | 2015-12-30 |
| CN105204490B CN105204490B (en) | 2017-10-20 |
Family
ID=54952231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510475741.XA Expired - Fee Related CN105204490B (en) | 2015-08-06 | 2015-08-06 | The diagnostic method for the stand-by power consumption intelligent diagnosis system classified based on Ensemble feature selection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105204490B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105719006A (en) * | 2016-01-18 | 2016-06-29 | 合肥工业大学 | Cause-and-effect structure learning method based on flow characteristics |
| WO2018023709A1 (en) * | 2016-08-05 | 2018-02-08 | 黄新勇 | Method and system for monitoring and prompting energy consumption in broadcast network |
| CN114066071A (en) * | 2021-11-19 | 2022-02-18 | 厦门大学 | Power parameter optimization method based on energy consumption, terminal equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4380243A (en) * | 1980-01-16 | 1983-04-19 | Braley Charles A | Overflow control system |
| WO1995010875A1 (en) * | 1993-10-12 | 1995-04-20 | Fischer, Helmut | Power supply for standby circuits of electrical devices |
| CN1987697A (en) * | 2006-12-22 | 2007-06-27 | 浙江大学 | Fault diagnostic system and method for under industrial producing process small sample condition |
| CN101873009A (en) * | 2010-07-12 | 2010-10-27 | 浙江昱能光伏科技集成有限公司 | Home intelligent power monitoring system |
| CN102307126A (en) * | 2011-08-15 | 2012-01-04 | 武汉安通科技产业发展有限公司 | Multi-network accessed multifunctional digital home intelligent terminal and control method thereof |
| CN103135464A (en) * | 2013-01-23 | 2013-06-05 | 山东建筑大学 | Electricity saving control system and method of standby electric equipment |
| CN103365269A (en) * | 2013-06-28 | 2013-10-23 | 南京邮电大学 | Wireless sensor network-based intelligent household electrical appliance multimode remote monitoring system and method |
| CN103760862A (en) * | 2014-01-17 | 2014-04-30 | 东莞维锐光电科技有限公司 | Smart home management method and smart home management system |
-
2015
- 2015-08-06 CN CN201510475741.XA patent/CN105204490B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4380243A (en) * | 1980-01-16 | 1983-04-19 | Braley Charles A | Overflow control system |
| WO1995010875A1 (en) * | 1993-10-12 | 1995-04-20 | Fischer, Helmut | Power supply for standby circuits of electrical devices |
| CN1987697A (en) * | 2006-12-22 | 2007-06-27 | 浙江大学 | Fault diagnostic system and method for under industrial producing process small sample condition |
| CN101873009A (en) * | 2010-07-12 | 2010-10-27 | 浙江昱能光伏科技集成有限公司 | Home intelligent power monitoring system |
| CN102307126A (en) * | 2011-08-15 | 2012-01-04 | 武汉安通科技产业发展有限公司 | Multi-network accessed multifunctional digital home intelligent terminal and control method thereof |
| CN103135464A (en) * | 2013-01-23 | 2013-06-05 | 山东建筑大学 | Electricity saving control system and method of standby electric equipment |
| CN103365269A (en) * | 2013-06-28 | 2013-10-23 | 南京邮电大学 | Wireless sensor network-based intelligent household electrical appliance multimode remote monitoring system and method |
| CN103760862A (en) * | 2014-01-17 | 2014-04-30 | 东莞维锐光电科技有限公司 | Smart home management method and smart home management system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105719006A (en) * | 2016-01-18 | 2016-06-29 | 合肥工业大学 | Cause-and-effect structure learning method based on flow characteristics |
| WO2018023709A1 (en) * | 2016-08-05 | 2018-02-08 | 黄新勇 | Method and system for monitoring and prompting energy consumption in broadcast network |
| CN114066071A (en) * | 2021-11-19 | 2022-02-18 | 厦门大学 | Power parameter optimization method based on energy consumption, terminal equipment and storage medium |
| CN114066071B (en) * | 2021-11-19 | 2024-09-13 | 厦门大学 | Power parameter optimization method based on energy consumption, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105204490B (en) | 2017-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109066990B (en) | Centralized scheduling-based platform area power grid terminal disturbance topological structure identification method | |
| Xia et al. | A real-time monitoring system based on ZigBee and 4G communications for photovoltaic generation | |
| Zhao et al. | Development of an energy monitoring system for large public buildings | |
| Wu et al. | Sewage information monitoring system based on wireless sensor | |
| CN103124105A (en) | Wireless intelligent sensor network system for monitoring states of intelligent substation devices | |
| CN104835018B (en) | The reliability estimation method and device of medium voltage distribution network rack | |
| CN107909788A (en) | A kind of wireless kilowatt meter reading-out system based on LoRa | |
| CN105046924A (en) | Intelligent farmland irrigation control system based on Internet of Things and operation method of intelligent farmland irrigation control system | |
| CN201955886U (en) | Agricultural environment information collection system based on wireless sensor network | |
| CN204559607U (en) | A kind of things-internet gateway | |
| CN106208393B (en) | A kind of distribution network automated monitoring method and system | |
| CN112804318B (en) | Ammeter region identification method | |
| CN105204490A (en) | Intelligent diagnosis system and method for standby power consumption based on integration characteristic selection and classification | |
| CN116828412A (en) | New energy automobile fills and trades electric box and becomes rack wireless communication system | |
| CN112804292B (en) | Ammeter distribution area identification method | |
| Cao et al. | Automatic meter reading system based on wireless mesh networks and SOPC technology | |
| CN104009469B (en) | A kind of low-voltage distribution network platform district network topology isopleth map collecting method | |
| CN108649578A (en) | The grid structure adjustment of high, middle pressure city net and networking mode optimization method and device | |
| CN104135523B (en) | A kind of intelligent RFID aquatic products forecasting shelf life device of embedded Web Service | |
| CN207819947U (en) | A kind of intelligence community house management system | |
| CN114069608B (en) | Voltage-based distributed type platform area identification method | |
| CN203376857U (en) | Remote meter reading system based on wireless sensor network | |
| CN109756029A (en) | A kind of monitoring system for solar energy power generating | |
| CN206378727U (en) | Sewage monitoring system based on Internet of Things | |
| CN205506995U (en) | Overhead line monitoring and fault indication device based on from networking model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171020 Termination date: 20180806 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |