CN111561771A - Intelligent air conditioner temperature adjusting method - Google Patents
Intelligent air conditioner temperature adjusting method Download PDFInfo
- Publication number
- CN111561771A CN111561771A CN202010550490.8A CN202010550490A CN111561771A CN 111561771 A CN111561771 A CN 111561771A CN 202010550490 A CN202010550490 A CN 202010550490A CN 111561771 A CN111561771 A CN 111561771A
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- temperature
- thermal imaging
- human body
- user
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses an intelligent air conditioner temperature adjusting method, which can realize real-time intelligent control of air conditioner temperature by automatically acquiring human body temperature state, environmental parameters and air conditioner working temperature and constructing a user personal database by utilizing a deep learning algorithm, thereby bringing excellent experience to users; based on a large number of databases of different users, the rules of different groups of people for the preference of the air conditioner working scheme can be analyzed to form an intelligent temperature adjusting scheme with universality, so that the method is expanded and applied to users who do not use the method; by adjusting the working temperature of the air conditioner in real time, the electric energy can be saved to the greatest extent under the condition of ensuring the user experience.
Description
Technical Field
The invention relates to the technical field of air conditioners, in particular to an intelligent air conditioner temperature adjusting method.
Background
The air conditioner temperature in the current market can only be set to a certain fixed value or a fixed time length generally, and can not adjust the temperature more intelligently according to individual difference and personal preference of users. When the user got back to indoor from the open air, because the sensation is hotter, the temperature value that is most suitable comfortable to the human body this moment is lower, and after a period, this kind of temperature can let the people feel colder, needs manual regulation again this moment to set up air conditioner temperature, complex operation. During sleep at night, human body temperature can reduce, and the air conditioner can bring bad experience effect after user's body temperature reduces with same temperature work all the time, has still wasted the electric energy simultaneously.
Therefore, in order to improve user experience, reduce the operation steps of a user and save electric energy, a set of temperature intelligent control scheme is provided.
Disclosure of Invention
In view of the above, the present invention provides an intelligent air conditioner temperature adjusting method.
The purpose of the invention is realized by the following technical scheme:
an intelligent air conditioner temperature adjusting method comprises the following steps:
the method comprises the steps of obtaining a thermal imaging graph and environmental parameters of a human body in real time and obtaining the air conditioner temperature set by a user under the environmental parameters, wherein the environmental parameters comprise: ambient temperature, ambient relative humidity, current time;
separating the human body part in the thermal imaging image from the indoor background by utilizing an image recognition technology; deep learning is carried out on the human body thermal imaging image after the indoor background is separated by adopting a VGG convolutional neural network, the human body temperature state in the human body thermal imaging image is identified, and a thermal imaging image feature library of a user is formed;
constructing a user database based on the thermal imaging graph feature library and the environmental parameters;
and based on the user database, deep learning is carried out by adopting a recurrent neural network to form a temperature preference control scheme aiming at the individual user, so that the optimal working temperature of the air conditioner under the conditions of given environmental parameters and the body temperature of the human body is obtained.
And further, acquiring a human body thermal imaging image through a thermal imager.
Furthermore, user databases of a large number of users are collected and integrated, deep learning is carried out through a classification algorithm, rules of different crowds for the preference of the air conditioner working temperature are analyzed, and an intelligent temperature adjusting scheme with universality for different crowds is formed.
Further, the separating the background in the chamber from the thermal imaging image is divided into two stages: firstly, enhancing the boundary division of the thermal imaging picture, and then automatically dividing the thermal imaging picture by utilizing an image dividing technology of random weight particle swarm and K-mean clustering; through these two stages, the human body in the thermal imaging picture can be separated from the indoor background.
Further, the classification algorithm is a KNN algorithm.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
according to the invention, the human body temperature state information, the environmental parameters and the air conditioner temperature are automatically acquired, and a temperature control scheme suitable for different user preferences is constructed by utilizing a deep learning algorithm, so that the real-time intelligent control of the air conditioner temperature can be realized, and excellent experience feeling is brought to the user;
based on a large number of databases of different users, the rules of different groups of people for the preference of the air conditioner working scheme can be analyzed to form an intelligent temperature adjusting scheme with universality, so that the method is expanded and applied to users who do not use the method;
the working temperature of the air conditioner is adjusted in real time, so that the electric energy can be saved to the maximum extent under the condition of ensuring the user experience;
the infrared technology has the advantages of visual image, safety, reliability, non-contact temperature measurement, no electromagnetic interference, long detection distance and the like.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
The drawings of the present invention are described below.
FIG. 1 is a topology diagram of the present invention; FIG. 2 is a schematic view of a working scenario of the present invention; fig. 3 is a diagram of the working process of the present invention.
Detailed Description
The invention is further illustrated by the following figures and examples.
Example 1
As shown, 1 represents a user; 2 represents an air conditioner; 3 represents the wiring between the air conditioner and the control system box; 4 represents a thermal infrared imager; the control system box is represented by 5 and used for collecting data, performing deep learning and controlling the working state of the air conditioner; 6 represents an instrument box for collecting the ambient temperature and humidity, the position of the instrument box is properly selected, the position is close to the height of a user, and the distance is slightly far away from an air conditioner, so that the influence of nonuniform indoor temperature distribution caused by the refrigeration/heat of the air conditioner on the accuracy of collected data is reduced; and 7 represents a connection connecting the temperature and humidity instrument box and the control system box.
The specific scheme of this example is as follows:
the environmental temperature and the environmental relative humidity are obtained in real time through the instrument box 6, and then parameters of the environmental temperature and the environmental relative humidity are transmitted to the control system box 5 through wiring;
acquiring a thermal imaging image of a human body through the thermal imager 4, and then transmitting the thermal imaging image to the control system box 5 through wiring;
the working temperature of the air conditioner is transmitted to a control system box body 5 through a wiring 3, and the control system box body 5 is provided with a time recording system.
The control box body 5 forms an intelligent temperature control scheme for the user through deep learning, and the specific process is as follows:
the image processing of the thermal imaging photo is divided into two stages, firstly, the boundary division of the thermal imaging photo is enhanced, and secondly, the thermal imaging photo is automatically divided by utilizing the image division technology of random weight particle swarm and K-mean clustering. Through these two stages, the human body in the thermal imaging picture can be separated from the indoor background. In the air conditioner temperature intelligent control scheme provided by this embodiment, the image semantic segmentation of the photo uses a VGG convolutional neural network.
After the deep learning VGG convolutional neural network is used for processing the image, a thermal image feature library based on the user person is formed, and the obtained human body thermal image is subjected to feature matching identification through the trained thermal image feature library, so that the current temperature state of the human body can be obtained.
Constructing a user database based on the thermal imaging graph feature library and the environmental parameters;
and performing deep learning through a recurrent neural network based on the user database to form a temperature preference control scheme aiming at the individual user, so as to obtain the optimal working temperature of the air conditioner under the conditions of given environmental parameters and human body temperature.
The method is characterized in that user databases of a large number of users are collected and integrated, deep learning is carried out through a classification algorithm, rules of different groups of people for the preference of the air conditioner working temperature are analyzed, and an intelligent temperature adjusting scheme with universality is formed. In the embodiment, a KNN algorithm is selected for deep learning, and the rule of different crowds for the preference of the air conditioner working temperature is obtained.
After forming the intelligent temperature adjustment scheme for the user's individual:
and after the thermal infrared imager collects a thermal imaging image of a user, the thermal imaging image is transmitted to a control system box body below the thermal infrared imager for processing, and the control system generates the optimal working temperature information of the air conditioner at the moment according to the processed thermal imaging image information, the environment temperature and humidity information transmitted from the temperature and humidity box and the current moment and transmits the optimal working temperature information to the air conditioner for execution.
The invention needs to acquire the thermal imaging picture, not only for acquiring the body temperature of the human body, but also for comprehensively mastering the temperature state of the human body, namely the heat distribution rule of the human body. Under different body conditions, people of the same body temperature will have different heat distributions. For example, the body temperature increases with vigorous exercise and fever, which may be identical but with distinct sensations, such as cold feeling, but hot feeling after exercise. The thermal imaging images of the human body are not the same in the two situations of fever and movement, so that the images are identified through an algorithm to obtain the heat exchange information between the human body and the external environment and the heat distribution condition of the whole human body, so that the thermal state of the human body can be judged at the moment.
Only if the difference of the thermal imaging state is recognized, the current state of the human body can be accurately analyzed, so that the air conditioner works at the optimal temperature, and comfortable experience is brought to a user
In addition, along with the continuous development of smart homes, the intelligent requirements of users on home products are higher and higher, and the human body temperature state information acquired through the human body thermal image and the deep learning algorithm in the scheme can play a role in constructing a whole set of smart home system, so that information sources are provided for other smart devices needing the information, and the intelligent home system becomes an important part in the whole smart home system.
Therefore, partial links of the scheme can also become an important link of the complete intelligent home system. And along with present 5G technological continuous popularization, the computer vision technique can make the computer vision more powerful at the intelligence of edge with 5G's combination, and through the combination of end cloud, the intelligence of front end and the intelligence of rear end high in the clouds combine together promptly for the mode that this scheme finally formed the intelligent temperature regulation scheme that has the universality is simpler, various, becomes a new development trend.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered in the protection scope of the present invention.
Claims (5)
1. An intelligent air conditioner temperature adjusting method is characterized in that:
the method comprises the steps of obtaining a thermal imaging graph and environmental parameters of a human body in real time and obtaining the air conditioner temperature set by a user under the environmental parameters, wherein the environmental parameters comprise: ambient temperature, ambient relative humidity, current time;
separating the human body part in the thermal imaging image from the indoor background by utilizing an image recognition technology; deep learning is carried out on the human body thermal imaging image after the indoor background is separated by adopting a VGG convolutional neural network, the human body temperature state in the human body thermal imaging image is identified, and a thermal imaging image feature library of a user is formed;
constructing a user database based on the thermal imaging graph feature library and the environmental parameters;
and based on the user database, deep learning is carried out by adopting a recurrent neural network to form a temperature preference control scheme aiming at the individual user, so that the optimal working temperature of the air conditioner under the conditions of given environmental parameters and the body temperature of the human body is obtained.
2. The intelligent air conditioner temperature adjusting method according to claim 1, characterized in that: and acquiring a human body thermal imaging image through a thermal imager.
3. The intelligent air conditioner temperature adjusting method according to claim 1, characterized in that: the method comprises the steps of collecting and integrating user databases of a large number of users, deeply learning through a classification algorithm, analyzing rules of different groups of people about air conditioner working temperature preference, and forming an intelligent temperature adjusting scheme with universality for different groups of people.
4. The intelligent air conditioner temperature adjusting method according to claim 1, characterized in that: separating the indoor background of the thermal imaging image is divided into two stages: firstly, enhancing the boundary division of the thermal imaging picture, and then automatically dividing the thermal imaging picture by utilizing an image dividing technology of random weight particle swarm and K-mean clustering; through these two stages, the human body in the thermal imaging picture can be separated from the indoor background.
5. The intelligent air conditioner temperature adjusting method according to claim 3, characterized in that: the classification algorithm is a KNN algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010550490.8A CN111561771A (en) | 2020-06-16 | 2020-06-16 | Intelligent air conditioner temperature adjusting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010550490.8A CN111561771A (en) | 2020-06-16 | 2020-06-16 | Intelligent air conditioner temperature adjusting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111561771A true CN111561771A (en) | 2020-08-21 |
Family
ID=72068792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010550490.8A Pending CN111561771A (en) | 2020-06-16 | 2020-06-16 | Intelligent air conditioner temperature adjusting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111561771A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114110963A (en) * | 2021-11-11 | 2022-03-01 | 珠海格力电器股份有限公司 | Air conditioner with intelligent adjusting function and control method |
| CN115930384A (en) * | 2023-03-13 | 2023-04-07 | 中国海洋大学 | Intelligent air conditioner control device and control method using reinforcement learning and thermal imaging |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954016A (en) * | 2014-05-21 | 2014-07-30 | 珠海格力电器股份有限公司 | Control method and control system of air conditioner as well as air conditioner |
| CN105180380A (en) * | 2015-10-21 | 2015-12-23 | 珠海格力电器股份有限公司 | Intelligent air conditioning system |
| US20160116178A1 (en) * | 2014-10-23 | 2016-04-28 | Vivint, Inc. | Real-time temperature management |
| CN107103609A (en) * | 2017-04-17 | 2017-08-29 | 上海电力学院 | Niblack power equipment Infrared Image Segmentations based on particle group optimizing |
| JP2018109458A (en) * | 2016-12-28 | 2018-07-12 | パナソニック株式会社 | Control device for air conditioning system and air conditioning system |
| CN109140665A (en) * | 2018-08-31 | 2019-01-04 | 珠海格力电器股份有限公司 | Control the method, apparatus and air-conditioning device of air-conditioning |
| CN109767437A (en) * | 2019-01-09 | 2019-05-17 | 电子科技大学 | Thermal-induced imagery defect characteristic extracting method based on k mean value dynamic multi-objective |
| CN110513835A (en) * | 2018-05-22 | 2019-11-29 | 珠海格力电器股份有限公司 | Improve control method, device and the air-conditioning of air conditioning comfortableness |
-
2020
- 2020-06-16 CN CN202010550490.8A patent/CN111561771A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954016A (en) * | 2014-05-21 | 2014-07-30 | 珠海格力电器股份有限公司 | Control method and control system of air conditioner as well as air conditioner |
| US20160116178A1 (en) * | 2014-10-23 | 2016-04-28 | Vivint, Inc. | Real-time temperature management |
| CN105180380A (en) * | 2015-10-21 | 2015-12-23 | 珠海格力电器股份有限公司 | Intelligent air conditioning system |
| JP2018109458A (en) * | 2016-12-28 | 2018-07-12 | パナソニック株式会社 | Control device for air conditioning system and air conditioning system |
| CN107103609A (en) * | 2017-04-17 | 2017-08-29 | 上海电力学院 | Niblack power equipment Infrared Image Segmentations based on particle group optimizing |
| CN110513835A (en) * | 2018-05-22 | 2019-11-29 | 珠海格力电器股份有限公司 | Improve control method, device and the air-conditioning of air conditioning comfortableness |
| CN109140665A (en) * | 2018-08-31 | 2019-01-04 | 珠海格力电器股份有限公司 | Control the method, apparatus and air-conditioning device of air-conditioning |
| CN109767437A (en) * | 2019-01-09 | 2019-05-17 | 电子科技大学 | Thermal-induced imagery defect characteristic extracting method based on k mean value dynamic multi-objective |
Non-Patent Citations (1)
| Title |
|---|
| 张金玉等: "《红外热波检测及其图像序列处理技术》", 30 June 2015 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114110963A (en) * | 2021-11-11 | 2022-03-01 | 珠海格力电器股份有限公司 | Air conditioner with intelligent adjusting function and control method |
| CN115930384A (en) * | 2023-03-13 | 2023-04-07 | 中国海洋大学 | Intelligent air conditioner control device and control method using reinforcement learning and thermal imaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110629B (en) | Personnel information detection method and system for indoor environment control | |
| CN108921100B (en) | Face recognition method and system based on visible light image and infrared image fusion | |
| Zhang et al. | Multimodal spontaneous emotion corpus for human behavior analysis | |
| WO2020177498A1 (en) | Non-intrusive human body thermal comfort detection method and system based on posture estimation | |
| Ramanathan et al. | Face verification across age progression | |
| Wang et al. | A natural visible and infrared facial expression database for expression recognition and emotion inference | |
| Trujillo et al. | Automatic feature localization in thermal images for facial expression recognition | |
| CN100478979C (en) | Status identification method by using body information matched human face information | |
| US12000609B2 (en) | Detecting presence and estimating thermal comfort of one or more human occupants in a built space in real-time using one or more thermographic cameras and one or more RGB-D sensors | |
| CN111561771A (en) | Intelligent air conditioner temperature adjusting method | |
| Arandjelović et al. | Thermal and reflectance based personal identification methodology under variable illumination | |
| JP3697286B2 (en) | Condition monitoring device | |
| CN109886154A (en) | Most pedestrian's appearance attribute recognition methods according to collection joint training based on Inception V3 | |
| Qi et al. | Learning complex spatio-temporal configurations of body joints for online activity recognition | |
| CN115294639B (en) | Color temperature adjustable lamp strip and control method thereof | |
| CN111832697A (en) | Intelligent human body recognition energy-saving temperature regulating system | |
| CN116524586A (en) | Dance scoring algorithm based on CNN and GCN gesture estimation and similarity matching | |
| US20210232834A1 (en) | Device for identifying a clothing family index | |
| Tayal et al. | Face recognition using eigenface | |
| Li et al. | Non-invasive human thermal comfort assessment based on multiple angle/distance facial key-region temperatures recognition | |
| CN110594179B (en) | Fan and fan control method | |
| WO2023077782A1 (en) | Air conditioner control method and control apparatus, and air conditioner | |
| CN114964506A (en) | Indoor human body thermal comfort intelligent regulation and control method and system based on infrared thermal imaging | |
| Abouelenien et al. | Detecting thermal discomfort of drivers using physiological sensors and thermal imaging | |
| CN115905688A (en) | Reference information generation method based on artificial intelligence and smart home |
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: 20200821 |