CN107477809A - Air conditioner energy source management system based on Adaboost - Google Patents
Air conditioner energy source management system based on Adaboost Download PDFInfo
- Publication number
- CN107477809A CN107477809A CN201710854622.4A CN201710854622A CN107477809A CN 107477809 A CN107477809 A CN 107477809A CN 201710854622 A CN201710854622 A CN 201710854622A CN 107477809 A CN107477809 A CN 107477809A
- Authority
- CN
- China
- Prior art keywords
- air
- adaboost
- sample
- module
- long
- 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
Links
- 238000004378 air conditioning Methods 0.000 claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 21
- 238000005265 energy consumption Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000000465 moulding Methods 0.000 claims 1
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000005057 refrigeration Methods 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The present invention relates to technical field of energy management, discloses a kind of air conditioner energy source management system based on Adaboost, solves the problems, such as energy waste caused by empty machine operation under air-conditioning unmanned state.The present invention includes：Video acquisition module, for gathering interior space video data；Human detection module, the human body in video image is detected, and the number of indoor human body is obtained using Adaboost graders；Energy consumption judge module, for judging whether to need to adjust air-conditioner temperature according to current time, temperature, number or carrying out switching on and shutting down, and analysis result is sent to long-range monitoring modular；Airconditioning control module, air-conditioning is controlled according to the instruction of long-range monitoring modular；Long-range monitoring modular, for monitoring whether air-conditioning runs well, sent and instructed to airconditioning control module according to energy consumption judge module analysis result.The present invention is applied to air conditioner energy source management.
Description
Technical field
The present invention relates to technical field of energy management, the air conditioner energy source management system more particularly to based on Adaboost.
Background technology
Air-conditioning is current all kinds of buildings widest refrigeration plant employed in, at home, handles official business, be several among Workplace
Indoor temperature is adjusted using all kinds of air-conditionings, air-conditioning is also one of most electric equipment of power consumption sum.By pair
The statistical analysis of air-conditioner power consumption, air-conditioner power consumption is mainly in June to September refrigeration power consumption.Simultaneously in southern some areas air-conditioning 11
The moon to January, heating power consumption reached another peak value.As can be seen here, the main services object of air-conditioning is the refrigeration of people's daily life
With heating, Adaboost Human Detections be by image judge residing in scene whether with the presence of human body and specific people
Number, Human Detection is applied among air conditioner energy source management, can judge whether have under current operating environment with auxiliary air conditioner
People, realize the automatic timely open and close of air-conditioning, the timely closing of the indoor air-conditioning under the conditions of nobody of principal security.Meanwhile with reference to room
Outer temperature, it is possible to achieve whether air-conditioning automatic decision Current Temperatures are reasonable, so as to which operation power be adjusted, realize that energy-conservation subtracts
Row, reduce the unnecessary waste of electricity.
The content of the invention
The technical problem to be solved in the present invention is：A kind of air conditioner energy source management system based on Adaboost is provided, solved
Energy waste problem caused by empty machine operation under air-conditioning unmanned state.
To solve the above problems, the technical solution adopted by the present invention is：Air conditioner energy source management system based on Adaboost,
Including video acquisition module, human detection module, energy consumption judge module, airconditioning control module and long-range monitoring modular；
The video acquisition module is used to gather interior space video data；
The human detection module is used to detect the human body in video image, and is obtained using Adaboost graders
Take the number of indoor human body；
The energy consumption judge module be used for according to current time, temperature, number judge whether to need to adjust air-conditioner temperature or
Switching on and shutting down are carried out, and analysis result is sent to long-range monitoring modular；
The long-range monitoring modular is used to monitor whether air-conditioning runs well, according to energy consumption judge module analysis result to sky
Control module is adjusted to send instruction；
The airconditioning control module is used to be controlled air-conditioning according to the instruction of long-range monitoring modular.
Further, the training step of Adaboost graders includes in the human detection module：
A. training sample is given, and weights initialisation is done to sample；
B. giving needs the number T of loop iteration, completes iteration each time, includes the step of each iteration：
B1 sample weights normalize so that each round iteration weight all obeys probability distribution；
B2. the feature of each sample is corresponded to, trains a Weak Classifier；
B3. the relative minimum grader of each sample classification error is selected as optimal Weak Classifier；
B4. judge whether to reach given iterations T, if then entering step c, otherwise, update sample weights, and return
Return step b1；
C. the optimal Weak Classifier obtained by each iteration is combined, generates strong classifier.
Further, the training sample includes positive sample and negative sample.
The beneficial effects of the invention are as follows：The present invention can by detect the number in indoor place control air-conditioning open automatically,
Shutdown, while operation of air conditioner temperature can also be adjusted according to occupancy and outdoor temperature, reach energy-saving and emission-reduction, save the energy
Purpose.
Brief description of the drawings
Fig. 1 is the flow chart that embodiment carries out air conditioner energy source management.
Fig. 2 is Adaboost classifier training flow charts.
Embodiment
Embodiment provides a kind of air conditioner energy source management system based on Adaboost, including video acquisition module, people's physical examination
Survey module, energy consumption judge module, airconditioning control module and long-range monitoring modular；Wherein：
The video acquisition module is used to gather interior space video data；
The human detection module is used to detect the human body in video image, and is obtained using Adaboost graders
Take the number of indoor human body；
The energy consumption judge module be used for according to current time, temperature, number judge whether to need to adjust air-conditioner temperature or
Switching on and shutting down are carried out, and analysis result is sent to long-range monitoring modular；
The long-range monitoring modular is attached for air conditioner energy source management system terminal with platform, and just whether monitoring air-conditioning
Often operating, sent and instructed to airconditioning control module according to energy consumption judge module analysis result；
The airconditioning control module is used to be controlled air-conditioning according to the instruction of long-range monitoring modular.
Embodiment need to obtain the Adaboost graders for human testing, such as Fig. 2 before air conditioner energy source management is carried out
Shown, the training step of the Adaboost graders is as follows：
1. given training sample (x1,y1),(x2,y2),...(xn,yn), yi∈ { -1 ,+1 }, wherein, yi=+1 represents positive sample
This, yi=-1 represents negative sample, and n representative samples are total,
2 pairs of samples are weights initialisation, weight W=w1=1/n；
3. the given number T for needing loop iteration, iteration each time is completed, include the step of each iteration：
(1) sample weights normalize,So that each round iteration weight all obeys probability distribution；
(2) corresponds to the feature of each sample, trains a Weak Classifier, and the error of the grader is：
(3) the relative minimum grader of each sample classification error of selections is as optimal Weak Classifier,
(4) judges whether to reach the number T of given iteration, if so, then entering step 4, otherwise according to formula wt+1=
wT, iexp(-αtyiht(xi)) renewal sample weights, and return to step (1), wherein, αt=ln ((1- εt)/εt)。
4. the optimal Weak Classifier obtained by each iteration is combined, strong classifier is generated, is judged whether rationally,
If rationally, the grader of completion is trained to can be utilized for human testing.
After having above-mentioned grader, our cans start air conditioner energy source management, idiographic flow as shown in figure 1, including
Step：
A. video acquisition module collection interior space video data；
B. human detection module detects to the human body in video image, and obtains interior using Adaboost graders
The number of human body；
C. energy consumption judge module judges whether to need to adjust air-conditioner temperature or opened according to current time, temperature, number
Shutdown, if desired, then send analysis result to long-range monitoring modular, into step D；If need not, return to step A, lead to
Cross video acquisition module and resurvey interior space video data；
D. whether long-range monitoring modular monitoring air-conditioning runs well, if normally, can be analyzed and tied according to energy consumption judge module
Fruit sends to airconditioning control module and instructed；
E. airconditioning control module is controlled according to the instruction of long-range monitoring modular to air-conditioning.
The general principle of the present invention and main feature are the foregoing described, the description of specification simply illustrates the original of the present invention
Reason, without departing from the spirit and scope of the present invention, various changes and modifications of the present invention are possible, these changes and improvements
It all fall within the protetion scope of the claimed invention.
Claims (3)
1. the air conditioner energy source management system based on Adaboost, it is characterised in that including video acquisition module, human testing mould
Block, energy consumption judge module, airconditioning control module and long-range monitoring modular；
The video acquisition module is used to gather interior space video data；
The human detection module is used to detect the human body in video image, and obtains room using Adaboost graders
The number of interior human body；
The energy consumption judge module is used to judge whether to need to adjust air-conditioner temperature or progress according to current time, temperature, number
Switching on and shutting down, and analysis result is sent to long-range monitoring modular；
The long-range monitoring modular is used to monitor whether air-conditioning runs well, according to energy consumption judge module analysis result to air-conditioning control
Molding block sends instruction；
The airconditioning control module is used to be controlled air-conditioning according to the instruction of long-range monitoring modular.
2. the air conditioner energy source management system based on Adaboost as claimed in claim 1, it is characterised in that the Adaboost
The training step of grader includes：
A. training sample is given, and weights initialisation is done to sample；
B. giving needs the number T of loop iteration, completes iteration each time, includes the step of each iteration：
B1 sample weights normalize so that each round iteration weight all obeys probability distribution；
B2. the feature of each sample is corresponded to, trains a Weak Classifier；
B3. the relative minimum grader of each sample classification error is selected as optimal Weak Classifier；
B4. judge whether to reach given iterations T, if then entering step c, otherwise, update sample weights, and return to step
Rapid b1；
C. the optimal Weak Classifier obtained by each iteration is combined, generates strong classifier.
3. the air conditioner energy source management system based on Adaboost as claimed in claim 2, it is characterised in that the training sample
Including positive sample and negative sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710854622.4A CN107477809A (en) | 2017-09-20 | 2017-09-20 | Air conditioner energy source management system based on Adaboost |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710854622.4A CN107477809A (en) | 2017-09-20 | 2017-09-20 | Air conditioner energy source management system based on Adaboost |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107477809A true CN107477809A (en) | 2017-12-15 |
Family
ID=60586123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710854622.4A Pending CN107477809A (en) | 2017-09-20 | 2017-09-20 | Air conditioner energy source management system based on Adaboost |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107477809A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108361921A (en) * | 2018-02-07 | 2018-08-03 | 宁夏翔羚科技有限公司 | Air conditioning control method and device |
| CN115164351A (en) * | 2022-07-13 | 2022-10-11 | 上海豫汉智能科技有限公司 | Intelligent building control system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005768A (en) * | 2015-07-06 | 2015-10-28 | 河海大学 | Dynamic percentage sample cutting AdaBoost human face detection algorithm |
| CN105069396A (en) * | 2015-07-06 | 2015-11-18 | 河海大学 | Dynamic percentage characteristic cutting AdaBoost face detection algorithm |
| CN106529787A (en) * | 2016-11-02 | 2017-03-22 | 南京国电南自轨道交通工程有限公司 | Subway energy management system based on face detection technology |
-
2017
- 2017-09-20 CN CN201710854622.4A patent/CN107477809A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005768A (en) * | 2015-07-06 | 2015-10-28 | 河海大学 | Dynamic percentage sample cutting AdaBoost human face detection algorithm |
| CN105069396A (en) * | 2015-07-06 | 2015-11-18 | 河海大学 | Dynamic percentage characteristic cutting AdaBoost face detection algorithm |
| CN106529787A (en) * | 2016-11-02 | 2017-03-22 | 南京国电南自轨道交通工程有限公司 | Subway energy management system based on face detection technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108361921A (en) * | 2018-02-07 | 2018-08-03 | 宁夏翔羚科技有限公司 | Air conditioning control method and device |
| CN115164351A (en) * | 2022-07-13 | 2022-10-11 | 上海豫汉智能科技有限公司 | Intelligent building control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106461254A (en) | Air conditioning and ventilation system | |
| Wang et al. | An occupant-centric control strategy for indoor thermal comfort, air quality and energy management | |
| CN108873729A (en) | Artificial intelligence domestic environment management system based on big data | |
| CN106123221A (en) | Variable air volume control in air conditioner equipment based on video monitoring system and device | |
| CN118070664B (en) | Building energy consumption intelligent simulation method based on Internet of things and BIM | |
| CN111443609A (en) | Laboratory environment self-adaptive adjusting method based on Internet of things | |
| CN112114604A (en) | Method for regulating and controlling growth climate suitable for livestock groups in livestock breeding house | |
| CN107702290A (en) | Control method and device of air conditioner and terminal | |
| CN208859789U (en) | A kind of indoor environment intelligent control system based on study user behavior | |
| CN107477809A (en) | Air conditioner energy source management system based on Adaboost | |
| CN106979582A (en) | Air conditioning control method and system based on positional information | |
| CN115272675A (en) | Energy management system and method based on multi-sensor information fusion | |
| CN110286602A (en) | Intelligent home control method, control equipment and system based on knowledge graph | |
| CN104266312B (en) | Air conditioner and control method and system thereof | |
| CN117329665B (en) | Air conditioner indoor linkage control method and system based on intelligent AI algorithm | |
| CN115540114A (en) | Indoor environment optimized lifting heating and ventilation control system and method | |
| CN110864435A (en) | Linkage household appliance system capable of sharing human body information and environmental information | |
| CN208312636U (en) | Central air-conditioning monitoring system | |
| CN118669920A (en) | Intelligent air conditioner control and contextual model adjustment system | |
| CN114135991A (en) | Temperature preset control and equipment early warning method for subway station public area | |
| CN205783335U (en) | Air conditioning equipment and fan coil pipe | |
| CN118111071A (en) | Energy-saving control system and method for communication base station machine room | |
| CN105953367A (en) | Intelligent building air conditioner control system | |
| CN211903225U (en) | Intelligent household appliance system working in combination | |
| CN117805519A (en) | An automotive electrical component simulation test system, method, device and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171215 |