CN103116098A - Household appliance operating state identification method based on cross correlation coefficient - Google Patents
Household appliance operating state identification method based on cross correlation coefficient Download PDFInfo
- Publication number
- CN103116098A CN103116098A CN2013100289248A CN201310028924A CN103116098A CN 103116098 A CN103116098 A CN 103116098A CN 2013100289248 A CN2013100289248 A CN 2013100289248A CN 201310028924 A CN201310028924 A CN 201310028924A CN 103116098 A CN103116098 A CN 103116098A
- Authority
- CN
- China
- Prior art keywords
- signal
- electrical appliance
- household electrical
- correlation coefficient
- method based
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to a household appliance operating state identification method based on a cross correlation coefficient. The identification method includes acquiring momentary currents or momentary power signals by the aid of intelligent electric meters installed at the entrance of a house to detect signal variation; based on periodicity as a unit, when signal variation exceeds a curtained threshold in a moment K, extracting signal waveforms of total seven periodicities of K-5, K-3, K, K+2, K+4, k+6 and K+8, and calculating waveform similarity between every two periodic signals in a time sequence; judging whether to start or stop the household appliances indoors by judging differences of six waveform similarity values and according to differentials of steady-state signals before and after K. The algorithm is simple and the judgment is accurate.
Description
Technical field
The present invention relates to a kind of household electrical appliance running rate recognizing method, particularly a kind of recognition methods based on cross-correlation coefficient.
Background technology
Along with the continuous increase of global resources environmental pressure, building more safe, reliable, environmentally friendly, economic intelligent grid becomes the common objective of global power industry.In generating, transmission of electricity, distribution, this chain of electricity consumption, a little less than electrical network and terminal user's interactive relative thin, affected overall performance and the efficient of electric system at present.Increasing researchers recognize that also intelligent electric meter is the basis of intelligent grid, has become the focus of research in recent years.
Want to realize veritably intelligent grid and user's interaction, make the user participate in veritably in electricity market, for operation and the asset management of system brings enormous benefits, should provide detailed consumer power consumption parameter for intelligent grid, make the user more clearly understand the average energy consumption of every kind of consumer, determine the undesired energy consumption of consumer, make the user feel to benefit from intelligent electric meter.
George .W. professor Hart of the Objective Concept Massachusetts Institute Technology of non-intrusion type load monitoring (Non-intrusive Load Monitoring, NILM) was brought in the electricity consumption condition monitoring of residential customer household electrical appliance first in nineteen eighty-two.The method only needs to install monitoring equipment on the house lead in main line, sampling user total voltage current signal, and recycling load identification algorithm extracts the power information of single household electrical appliance.
In recent years, Many researchers are studied for NILM, mainly concentrate on signal analysis and load and identify two aspects.Wherein, the load characteristic signal mainly comprises the harmonic wave of signal (instantaneous power or momentary current), transient-wave, and the energy consumption mode, and the ratio of constant power load model and constant-impedance load etc.; The load identification algorithm mainly concentrates on artificial neural network.More typical correlative study has:
1) research group of the Steven of Massachusetts Institute of Technology (MIT) Leeb proposes the discrimination method based on load switching transient state process information.The method can be according to starting the different load of transient current identification, and the method is estimated the information such as meritorious, idle and harmonic power of load by design simulation spectral envelope line analyzer, and develop the algorithm of transient state detection and load classification.
2) extract load current envelope in load switching transient state process based on the Kalman filtering algorithm.
3) at first the characteristic parameter of household electrical appliance is carried out the analysis and research of both macro and micro aspect, extract the more characteristic parameters of the household electrical appliance such as current waveform, meritorious, idle, harmonic content, instantaneous admittance.And proposition household electrical appliance start and stop state event detects and the load decomposition identification algorithm.
In sum, after being the collection momentary signal about the NILM research tendency at present, utilize discrimination method with many signal decomposition, thus the running status of judgement electrical equipment.But the identification algorithm theoretical principle that these researchs are adopted is all comparatively complicated, and operand is larger.
Summary of the invention
Purpose of the present invention just is to provide the household electrical appliance running rate recognizing method based on the mutual relationship number that a kind of identification algorithm is simple, operand is little, and it can effectively judge input or the excision of household electrical appliance for the little characteristics of household electrical appliance quantity.
The objective of the invention is to realize by such technical scheme, it comprises the following steps:
1) read momentary current or instantaneous power signal;
2) signal that reads according to step 1), the positive and negative envelope of generation signal;
3) monitoring step 2) the positive and negative envelope that generates, and judge whether signal has significant change, and if marked change occurs, change step 4) over to, if marked change do not occur, continue to monitor;
4) extract and the signal waveform in totally 7 cycles to occur before and after marked change time point k;
5) calculation procedure 4) in the wave-form similarity S of 7 periodic signals
t
6) determining step 5) in 6 wave-form similarity S calculating
tWhether difference is remarkable, if significant difference changes step 7) over to, if difference does not significantly change step 1) over to;
7) judge whether the current amplitude of signal steady-state process is poor remarkable before and after k constantly, if significantly explanation has new household electrical appliance to drop into or excision, do not cause if significantly do not illustrate by the outside noise signal.
The generation method of positive and negative envelope further, step 2) is:
Take out momentary current i (t) or the maximum of points F(k in instantaneous power p (t) per cycle) and F1(k) consist of positive and negative envelope, wherein F(k) be positive envelope, F1(k) for bearing envelope.
Further, judge in step 3) signal whether the method for marked change be:
F(k is calculated in the variation of monitoring envelope)-F(k-1) and F1(k)-F1(k-1);
The condition of signal generation marked change is:
F(k)-F(k-1)>I
0Or P
0, perhaps F1(k)-F1(k-1)<-I
0Or-P
0
F(k)-F(k-1)<-I
0Or-P
0, perhaps F1(k)-F1(k-1)>I
0Or P
0
Wherein, I
0Be the active power value without the consumer of the active power numerical value minimum of starting impulse, P
0Be the steady-state current amplitude without the consumer of the active power numerical value minimum of starting impulse.
Further, before and after in step 4), marked change time point k appears in extraction, totally 7 cycles are respectively: k, k-3, k-5, k+2, k+4, k+6 and k+8.
Further, the described wave-form similarity of step 5)
S t Computing method be:
According to time sequencing, calculate the wave-form similarity in every adjacent two cycles in 7 cycles
Wherein,
aWith
bRepresentative is the signal waveform in continuous 2 cycles in time;
Wherein,
iWith
jRepresent sampled point,
nRepresent total sampling number of per cycle,
With
Represent the mean value of the amplitude of n sampled point, that is:
Further, judge wave-form similarity in step 6)
S t Whether significant method is difference:
If
S r =(
S tmax
S tmin
)/
S tmax
If
S r <x
1, judge significant difference; If
S r >x
1, judge that difference is not remarkable, x
1Be preset value.
Further, judge in step 7) before and after k is constantly poor whether significant method is the current amplitude of signal steady-state process:
Get k front and back steady-state signal constantly, electric current I or power P are calculated their difference in magnitude, if I (k+)-I (k-)〉I
0Or P (k+)-P (k-)〉P
0, perhaps I (k+)-I (k-)<-I
0Or P (k+)-P (k-)<-P
0, be determined with new household electrical appliance and drop into or excise; If I (k+)-I (k-)<I
0Or P (k+)-P (k-)<P
0, perhaps I (k+)-I (k-) 〉-I
0Or P (k+)-P (k-) 〉-P
0, show that k causes for the outside noise signal constantly;
Wherein, k+ represents the stable state after moment k, and k-represents the front stable state of k constantly, I
0Be the active power value without the consumer of the active power numerical value minimum of starting impulse, P
0Be the steady-state current amplitude without the consumer of the active power numerical value minimum of starting impulse.
Owing to having adopted technique scheme, the present invention has advantages of as follows:
the intelligent electric meter that utilization of the present invention is arranged on family's house lead in place obtains momentary current or instantaneous power signal, the change in detection signal amount, when the variable quantity of this signal is carved k at a time, take periodicity as unit, surpass certain threshold value, extract k 5, k 3, k, k+2, k+4, k+6, k+8 is the signal waveform in totally 7 cycles, and calculate the wave-form similarity of periodic signal in twos according to time sequencing, by judging the difference of these 6 wave-form similarity numerical value, and by the difference of steady-state signal before and after k, judge that indoor whether household electrical appliance start or stop, algorithm is simple, accuracy of judgement.
Other advantages of the present invention, target and feature will be set forth to a certain extent in the following description, and to a certain extent, based on being apparent to those skilled in the art to investigating hereinafter, perhaps can be instructed from the practice of the present invention.Target of the present invention and other advantages can realize and obtain by following instructions and claims.
Description of drawings
Description of drawings of the present invention is as follows.
Fig. 1 is algorithm flow chart of the present invention;
Fig. 2 is the oscillogram of embodiment.
Embodiment
The invention will be further described below in conjunction with drawings and Examples.
Correct time point as shown in table 1, that 1. numbering changes to the use-pattern that has 10. recorded household electrical appliance within a period of time.
The details of use that table 1 household electrical appliance drop into and excise
Numbering | Time (second) | Periodicity | The household |
① | 12 | 46th | Notebook computer Open |
② | 45 | 20th | Without (change of notebook running status) |
③ | 94 | 6th | Electricity-saving lamp Open |
④ | 118 | 15th | Without (change of notebook running status) |
⑤ | 153 | 35th | Without (change of notebook running status) |
⑥ | 188 | 39th | Without (change of notebook running status) |
⑦ | 192 | 1st | Notebook computer Close |
⑧ | 225 | 48th | Electricity-saving lamp Close |
⑨ | 280 | 43rd | Electricity-saving lamp Open |
⑩ | 294 | 29th | Electricity-saving lamp Close |
According to algorithm of the present invention, calculate the electric current similarity result of calculation of experiment current waveform and the part curent change significant point thereof of 5 minutes, and represent with oscillogram, as shown in Figure 2.
When having household electrical appliance switching event to occur, 6 electric current similarity numerical value change are obvious.For example be numbered the moment 1., it is 0.45A that this moment current envelope curve changes F (k) F (k 1), wave-form similarity
S t Calculated value is followed successively by 0.790,0.467, and 0.280,0.739,0.959 and 0.990.For analyzing the significance degree of electric current similarity difference, use ratio
S r =(
S tmax
S tmin
)/
S tmax
Analyze, wherein
S tmax
With
S tmin
This is respectively maximal value and the minimum value of six numerical value.For 1. constantly, this ratio is (0.990-0.280)/0.990=72%.3., 7., 8., 9. and 10. this ratio in the moment is respectively 30%, 39%, 56%, 86% and 51%.
And when not having household electrical appliance switching event to occur, 6 electric current similarity numerical value change are so unobvious.For example, the moment, F (k) F (k 1) 6. was 1.08A, wave-form similarity
S t Be 0.964,0.837,0.823,0.999,0.998 and 0.999, ratio
S r =(
S tmax
S tmin
)/
S tmax
=17.6%.2., 4. and 5. this ratio in the moment is much smaller, is respectively 1%, 1.6% and 1%.Fact proved, be 2., 4., 5. and 6. the different conditions of notebook computer, constantly is 6. that notebook computer begins to carry out " shutdown " order, so its
S r =(
S tmax
S tmin
)/
S tmax
=17.6% ratio is bigger.However, still less than there being household electrical appliance switching event that this ratio constantly occurs.
So work as wave-form similarity
S r <x
1The time, enter next link and continue to determine whether that new household electrical appliance drop into/excision; When
S r X
1The time, x
1Be preset value, judge without new household electrical appliance and drop into/excision.
S r <x
1The time, get k front and back steady-state current signal constantly, calculate their difference in magnitude, if I (k+)-I (k-) 0.15A or 25W, perhaps I (k+)-I (k-)<-0.15A or-25W, explanation continues to determine whether that new household electrical appliance drop into/excision; If I (k+)-I (k-)<0.15A or 25W, perhaps I (k+)-I (k-) 〉-0.15A or-25W, show that k causes for the outside noise signal constantly.Wherein, k+ represents the stable state after moment k, and k-represents the front stable state of k constantly.
the intelligent electric meter that utilization of the present invention is arranged on family's house lead in place obtains momentary current or instantaneous power signal, the change in detection signal amount, when the variable quantity of this signal is carved k at a time, take periodicity as unit, surpass certain threshold value, extract k 5, k 3, k, k+2, k+4, k+6, k+8 is the signal waveform in totally 7 cycles, and calculate the wave-form similarity of periodic signal in twos according to time sequencing, by judging the difference of these 6 wave-form similarity numerical value, and by the difference of steady-state signal before and after k, judge that indoor whether household electrical appliance start or stop, algorithm is simple, accuracy of judgement.
Explanation is at last, above embodiment is only unrestricted in order to technical scheme of the present invention to be described, although with reference to preferred embodiment, the present invention is had been described in detail, those of ordinary skill in the art is to be understood that, can modify or be equal to replacement technical scheme of the present invention, and not breaking away from aim and the scope of the technical program, it all should be encompassed in the middle of claim scope of the present invention.
Claims (7)
1. the household electrical appliance running rate recognizing method based on cross-correlation coefficient, is characterized in that, said method comprising the steps of:
1) read momentary current or instantaneous power signal;
2) signal that reads according to step 1), the positive and negative envelope of generation signal;
3) monitoring step 2) the positive and negative envelope that generates, and judge whether signal has significant change, and if marked change occurs, change step 4) over to, if marked change do not occur, continue to monitor;
4) extract and the signal waveform in totally 7 cycles to occur before and after marked change time point k;
5) calculation procedure 4) in the wave-form similarity S of 7 periodic signals
t
6) determining step 5) in 6 wave-form similarity S calculating
tWhether difference is remarkable, if significant difference changes step 7) over to, if difference does not significantly change step 1) over to;
7) judge whether the current amplitude of signal steady-state process is poor remarkable before and after k constantly, if significantly explanation has new household electrical appliance to drop into or excision, do not cause if significantly do not illustrate by the outside noise signal.
2. a kind of household electrical appliance running rate recognizing method based on cross-correlation coefficient as claimed in claim 1, is characterized in that step 2) described in the generation method of positive and negative envelope be:
Take out momentary current i (t) or the maximum of points F(k in instantaneous power p (t) per cycle) and F1(k) consist of positive and negative envelope, wherein F(k) be positive envelope, F1(k) for bearing envelope.
3. a kind of household electrical appliance running rate recognizing method based on cross-correlation coefficient as claimed in claim 2, is characterized in that, judge in step 3) signal whether the method for marked change be:
F(k is calculated in the variation of monitoring envelope)-F(k-1) and F1(k)-F1(k-1);
The condition of signal generation marked change is:
F(k)-F(k-1)>I
0Or P
0, perhaps F1(k)-F1(k-1)<-I
0Or-P
0
F(k)-F(k-1)<-I
0Or-P
0, perhaps F1(k)-F1(k-1)>I
0Or P
0
Wherein, I
0Be the active power value without the consumer of the active power numerical value minimum of starting impulse, P
0Be the steady-state current amplitude without the consumer of the active power numerical value minimum of starting impulse.
4. a kind of household electrical appliance running rate recognizing method based on cross-correlation coefficient as claimed in claim 1, it is characterized in that, before and after in step 4), marked change time point k appears in extraction, totally 7 cycles are respectively: k, k-3, k-5, k+2, k+4, k+6 and k+8.
5. a kind of household electrical appliance running rate recognizing method based on cross-correlation coefficient as claimed in claim 4, is characterized in that the described wave-form similarity of step 5)
S t Computing method be:
According to time sequencing, calculate the wave-form similarity in every adjacent two cycles in 7 cycles
Wherein,
aWith
bRepresentative is the signal waveform in continuous 2 cycles in time;
Wherein,
iWith
jRepresent sampled point,
nRepresent total sampling number of per cycle,
With
Represent the mean value of the amplitude of n sampled point, that is:
。
6. a kind of household electrical appliance running rate recognizing method based on cross-correlation coefficient as claimed in claim 5, is characterized in that, judgement wave-form similarity S in step 6)
tWhether significant method is difference:
If
S r =(
S tmax
S tmin
)/
S tmax
If
S r <x
1, judge significant difference; If
S r >x
1, judge that difference is not remarkable, x
1Be preset value.
7. a kind of household electrical appliance running rate recognizing method based on cross-correlation coefficient as claimed in claim 6, is characterized in that, judges in step 7) that before and after k is constantly, whether significantly the poor method of the current amplitude of signal steady-state process is:
Get k front and back steady-state signal constantly, electric current I or power P are calculated their difference in magnitude, if I (k+)-I (k-)〉I
0Or P (k+)-P (k-)〉P
0, perhaps I (k+)-I (k-)<-I
0Or P (k+)-P (k-)<-P
0, be determined with new household electrical appliance and drop into or excise; If I (k+)-I (k-)<I
0Or P (k+)-P (k-)<P
0, perhaps I (k+)-I (k-) 〉-I
0Or P (k+)-P (k-) 〉-P
0, show that k causes for the outside noise signal constantly;
Wherein, k+ represents the stable state after moment k, and k-represents the front stable state of k constantly, I
0Be the active power value without the consumer of the active power numerical value minimum of starting impulse, P
0Be the steady-state current amplitude without the consumer of the active power numerical value minimum of starting impulse.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310028924.8A CN103116098B (en) | 2013-01-25 | 2013-01-25 | Household appliance operating state identification method based on cross correlation coefficient |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310028924.8A CN103116098B (en) | 2013-01-25 | 2013-01-25 | Household appliance operating state identification method based on cross correlation coefficient |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103116098A true CN103116098A (en) | 2013-05-22 |
CN103116098B CN103116098B (en) | 2014-11-19 |
Family
ID=48414524
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310028924.8A Active CN103116098B (en) | 2013-01-25 | 2013-01-25 | Household appliance operating state identification method based on cross correlation coefficient |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103116098B (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104597813A (en) * | 2014-12-23 | 2015-05-06 | 李凤兰 | Intelligent socket capable of automatically identifying electric appliance running state |
CN105974220A (en) * | 2016-04-25 | 2016-09-28 | 东莞市联洲知识产权运营管理有限公司 | Residential community power load identification system |
CN106093630A (en) * | 2016-06-02 | 2016-11-09 | 华北电力大学 | A kind of non-intrusion type household electrical appliance discrimination method |
CN106771593A (en) * | 2016-11-28 | 2017-05-31 | 国网江苏省电力公司苏州供电公司 | Non-intrusion type electromagnetic oven based on mixing criterion starts discrimination method |
CN106909974A (en) * | 2015-12-22 | 2017-06-30 | 中国电信股份有限公司 | Method, data-analyzing machine and system for analyzing multiple terminals state |
CN107065587A (en) * | 2017-05-27 | 2017-08-18 | 环球智达科技(北京)有限公司 | Control device |
CN107085935A (en) * | 2017-05-27 | 2017-08-22 | 环球智达科技(北京)有限公司 | closing control method |
CN107123255A (en) * | 2017-05-27 | 2017-09-01 | 环球智达科技(北京)有限公司 | Method for controlling opening and closing |
CN107123256A (en) * | 2017-05-27 | 2017-09-01 | 环球智达科技(北京)有限公司 | Detect judgment means |
CN107171435A (en) * | 2017-03-20 | 2017-09-15 | 国网浙江义乌市供电公司 | Power distribution network monitors energy conserving system |
CN107170226A (en) * | 2017-05-27 | 2017-09-15 | 环球智达科技(北京)有限公司 | The detection determination methods of closing control |
CN107230341A (en) * | 2017-05-27 | 2017-10-03 | 环球智达科技(北京)有限公司 | Open the detection determination methods of control |
CN109738723A (en) * | 2018-12-29 | 2019-05-10 | 重庆邮电大学 | A kind of electric energy meter three-phase automatic identification method |
CN110197220A (en) * | 2019-05-27 | 2019-09-03 | 湖南工业大学 | A kind of electrical load starting operation recognition methods |
CN112379178A (en) * | 2020-10-28 | 2021-02-19 | 国网安徽省电力有限公司合肥供电公司 | Method, system and storage medium for judging similarity of two waveforms with time delay |
CN115006824A (en) * | 2022-06-30 | 2022-09-06 | 歌尔科技有限公司 | Rowing machine action counting method, device, medium and intelligent wearable device |
CN115407157A (en) * | 2022-10-31 | 2022-11-29 | 南昌工程学院 | Complex multi-state electrical appliance load event distinguishing method and device |
CN115542825A (en) * | 2022-11-24 | 2022-12-30 | 北京北投智慧城市科技有限公司 | Intelligent building equipment monitoring and early warning system and method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050184852A1 (en) * | 2004-02-25 | 2005-08-25 | Lg Electronics Inc | Home network system and control method for the same |
EP2355025A1 (en) * | 2010-02-01 | 2011-08-10 | Electricité de France | Method for assessing a device or a building intended for being connected to a power mains and associated application for a mobile terminal |
CN102455374A (en) * | 2010-10-19 | 2012-05-16 | 西安扩力机电科技有限公司 | Simplified electric fee meter used by household appliance |
KR101172602B1 (en) * | 2010-08-24 | 2012-08-08 | 강릉원주대학교산학협력단 | Method, system and computer-readable recording medium for administrating electric power per appliance |
-
2013
- 2013-01-25 CN CN201310028924.8A patent/CN103116098B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050184852A1 (en) * | 2004-02-25 | 2005-08-25 | Lg Electronics Inc | Home network system and control method for the same |
EP2355025A1 (en) * | 2010-02-01 | 2011-08-10 | Electricité de France | Method for assessing a device or a building intended for being connected to a power mains and associated application for a mobile terminal |
KR101172602B1 (en) * | 2010-08-24 | 2012-08-08 | 강릉원주대학교산학협력단 | Method, system and computer-readable recording medium for administrating electric power per appliance |
CN102455374A (en) * | 2010-10-19 | 2012-05-16 | 西安扩力机电科技有限公司 | Simplified electric fee meter used by household appliance |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104597813B (en) * | 2014-12-23 | 2017-11-03 | 高峰 | A kind of smart jack of automatic identification electric operation state |
CN104597813A (en) * | 2014-12-23 | 2015-05-06 | 李凤兰 | Intelligent socket capable of automatically identifying electric appliance running state |
CN106909974A (en) * | 2015-12-22 | 2017-06-30 | 中国电信股份有限公司 | Method, data-analyzing machine and system for analyzing multiple terminals state |
CN106909974B (en) * | 2015-12-22 | 2020-11-03 | 中国电信股份有限公司 | Method, data analyzer and system for analyzing multi-terminal state |
CN105974220A (en) * | 2016-04-25 | 2016-09-28 | 东莞市联洲知识产权运营管理有限公司 | Residential community power load identification system |
CN105974220B (en) * | 2016-04-25 | 2018-11-20 | 江苏德克玛电气有限公司 | A kind of residential area power load identifying system |
CN106093630A (en) * | 2016-06-02 | 2016-11-09 | 华北电力大学 | A kind of non-intrusion type household electrical appliance discrimination method |
CN106093630B (en) * | 2016-06-02 | 2019-01-15 | 华北电力大学 | A kind of non-intrusion type household electrical appliance discrimination method |
CN106771593A (en) * | 2016-11-28 | 2017-05-31 | 国网江苏省电力公司苏州供电公司 | Non-intrusion type electromagnetic oven based on mixing criterion starts discrimination method |
CN107171435A (en) * | 2017-03-20 | 2017-09-15 | 国网浙江义乌市供电公司 | Power distribution network monitors energy conserving system |
CN107085935A (en) * | 2017-05-27 | 2017-08-22 | 环球智达科技(北京)有限公司 | closing control method |
CN107065587A (en) * | 2017-05-27 | 2017-08-18 | 环球智达科技(北京)有限公司 | Control device |
CN107170226A (en) * | 2017-05-27 | 2017-09-15 | 环球智达科技(北京)有限公司 | The detection determination methods of closing control |
CN107123256A (en) * | 2017-05-27 | 2017-09-01 | 环球智达科技(北京)有限公司 | Detect judgment means |
CN107123255A (en) * | 2017-05-27 | 2017-09-01 | 环球智达科技(北京)有限公司 | Method for controlling opening and closing |
CN107230341A (en) * | 2017-05-27 | 2017-10-03 | 环球智达科技(北京)有限公司 | Open the detection determination methods of control |
CN109738723A (en) * | 2018-12-29 | 2019-05-10 | 重庆邮电大学 | A kind of electric energy meter three-phase automatic identification method |
CN110197220A (en) * | 2019-05-27 | 2019-09-03 | 湖南工业大学 | A kind of electrical load starting operation recognition methods |
CN112379178A (en) * | 2020-10-28 | 2021-02-19 | 国网安徽省电力有限公司合肥供电公司 | Method, system and storage medium for judging similarity of two waveforms with time delay |
CN115006824A (en) * | 2022-06-30 | 2022-09-06 | 歌尔科技有限公司 | Rowing machine action counting method, device, medium and intelligent wearable device |
CN115006824B (en) * | 2022-06-30 | 2023-12-26 | 歌尔科技有限公司 | Rowing machine motion counting method, device, medium and intelligent wearable equipment |
CN115407157A (en) * | 2022-10-31 | 2022-11-29 | 南昌工程学院 | Complex multi-state electrical appliance load event distinguishing method and device |
CN115542825A (en) * | 2022-11-24 | 2022-12-30 | 北京北投智慧城市科技有限公司 | Intelligent building equipment monitoring and early warning system and method |
CN115542825B (en) * | 2022-11-24 | 2023-03-14 | 北京北投智慧城市科技有限公司 | Intelligent building equipment monitoring and early warning system and method |
Also Published As
Publication number | Publication date |
---|---|
CN103116098B (en) | 2014-11-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103116098B (en) | Household appliance operating state identification method based on cross correlation coefficient | |
CN108021736B (en) | Load switching action monitoring method based on sliding window residual error model | |
CN105972761B (en) | A kind of non-intrusion type air conditioner load monitoring method | |
CN103217603A (en) | Recognition method of on-line monitoring of power consumption of non-intrusive household appliances | |
CN105823948A (en) | Non-invasive resident load identification method | |
CN106646026A (en) | Non-intrusive household appliance load identification method | |
CN110956220A (en) | Non-invasive household appliance load identification method | |
CN111564842B (en) | Method for statistical estimation of medium-and-long-term energy consumption in non-invasive electric load monitoring | |
Yu et al. | Nonintrusive appliance load monitoring for smart homes: Recent advances and future issues | |
CN105372541A (en) | Household appliance intelligent set total detection system based on pattern recognition and working method thereof | |
CN112505511A (en) | Non-invasive low-voltage fault arc detection and positioning method and system | |
CN111242391A (en) | Machine learning model training method and system for power load identification | |
CN111722028A (en) | Load identification method based on high-frequency data | |
CN111382789A (en) | Power load identification method and system based on machine learning | |
Himeur et al. | Efficient multi-descriptor fusion for non-intrusive appliance recognition | |
Girmay et al. | Simple event detection and disaggregation approach for residential energy estimation | |
Gong et al. | A svm optimized by particle swarm optimization approach to load disaggregation in non-intrusive load monitoring in smart homes | |
CN107767037B (en) | User electricity utilization composition analysis method | |
CN105676028B (en) | A kind of resident load electricity consumption recognition methods based on template matches filtering | |
Bergés et al. | Leveraging data from environmental sensors to enhance electrical load disaggregation algorithms | |
Fang et al. | An event detection approach based on improved CUSUM algorithm and kalman filter | |
Chen et al. | Non-intrusive load monitoring based on feature extraction of change-point and xgboost classifier | |
Cannas et al. | NILM techniques applied to a real-time monitoring system of the electricity consumption | |
Guohua et al. | Research on non-intrusive load monitoring based on random forest algorithm | |
Cannas et al. | Real-time monitoring system of the electricity consumption in a household using NILM techniques |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |