CN113719974A - Air conditioner wind direction intelligent control method and system based on flow field information prediction - Google Patents
Air conditioner wind direction intelligent control method and system based on flow field information prediction Download PDFInfo
- Publication number
- CN113719974A CN113719974A CN202110910614.3A CN202110910614A CN113719974A CN 113719974 A CN113719974 A CN 113719974A CN 202110910614 A CN202110910614 A CN 202110910614A CN 113719974 A CN113719974 A CN 113719974A
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- flow field
- air supply
- field information
- air
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005057 refrigeration Methods 0.000 claims abstract description 29
- 238000013135 deep learning Methods 0.000 claims abstract description 26
- 230000004044 response Effects 0.000 claims abstract description 23
- 238000010586 diagram Methods 0.000 claims abstract description 20
- 239000013598 vector Substances 0.000 claims description 11
- 238000004088 simulation Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000012805 post-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 6
- 238000005211 surface analysis Methods 0.000 description 5
- 238000009434 installation Methods 0.000 description 3
- 238000001816 cooling Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007636 ensemble learning method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004441 surface measurement Methods 0.000 description 1
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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/56—Remote control
- F24F11/58—Remote control using Internet communication
-
- 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
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
- F24F11/79—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling the direction of the supplied air
-
- 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
- F24F11/88—Electrical aspects, e.g. circuits
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/20—Humidity
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
- F24F2120/12—Position of occupants
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2130/00—Control inputs relating to environmental factors not covered by group F24F2110/00
- F24F2130/10—Weather information or forecasts
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
An air conditioner wind direction intelligent control method and system based on flow field information prediction are disclosed, wherein the control method comprises the following steps: establishing a flow field information prediction model through deep learning; collecting space structure parameters, current environment data, air conditioner position and air supply related data, uploading the data to a flow field information prediction model, and predicting flow field information of the air conditioner after the air conditioner is started by combining local meteorological data, wherein the flow field comprises a temperature field and an air speed field; drawing an air conditioner operation time response surface graph with a horizontal air supply angle and a vertical air supply angle as a coordinate axis abscissa and an ordinate respectively according to predicted flow field information after the air conditioner is started, so that a target refrigeration area reaches a comfortable temperature; and determining an air supply angle with the minimum air supply time of the air conditioner when the target refrigeration area reaches the comfortable temperature under the condition of comfortable air speed in the air conditioner operation time response surface diagram, and forming an air supply control scheme of the air conditioner for control by taking the air supply angle as the optimal air supply angle. The intelligent air supply system can intelligently improve the intelligence and the comfort of air supply.
Description
Technical Field
The invention belongs to the field of air conditioner control, and particularly relates to an air conditioner wind direction intelligent control method and system based on flow field information prediction.
Background
The air supply direction of the traditional air conditioner is selected by a user through remote control, if the air supply of the air conditioner directly blows to the user, the user feels uncomfortable, and too much deviation of the air direction from the user also causes too low cooling speed of the position where the user is located, so that the comfort level of the user is reduced.
The existing air conditioner direct blowing prevention technology comprises the following steps: the air conditioner comprises a dense air hole technology, a sectional air hole technology, a rotary softening air flow technology and the like, but the existing technologies generally have the problems that the air supply distance is not enough, the user feels that the refrigeration effect is poor and the like.
Disclosure of Invention
The present invention aims to solve the above problems in the prior art, and provide an intelligent control method and system for air direction of an air conditioner based on flow field information prediction, which can enable the air conditioner to operate in an optimal air supply direction, and improve intelligence and comfort of air supply.
In order to achieve the purpose, the invention has the following technical scheme:
an air conditioner wind direction intelligent control method based on flow field information prediction comprises the following steps:
establishing a flow field information prediction model through deep learning;
collecting space structure parameters, current environment data, air conditioner position and air supply related data, uploading the data to a flow field information prediction model, and predicting flow field information of the air conditioner after the air conditioner is started by combining local meteorological data, wherein the flow field comprises a temperature field and an air speed field;
drawing an air conditioner operation time response surface graph with a horizontal air supply angle and a vertical air supply angle as a coordinate axis abscissa and an ordinate respectively according to predicted flow field information after the air conditioner is started, so that a target refrigeration area reaches a comfortable temperature;
and determining an air supply angle with the minimum air supply time of the air conditioner when the target refrigeration area reaches the comfortable temperature under the condition of comfortable air speed in the air conditioner operation time response surface diagram, and forming an air supply control scheme of the air conditioner for control by taking the air supply angle as the optimal air supply angle.
As a preferred scheme of the present invention, the flow field information prediction model is established by deep learning, CFD simulation is performed on spatial structure parameters, current environmental data, air conditioner position and air supply related data, spatial grids are formed into a plurality of regions from a CFD simulation result, an average temperature and an average wind speed of each region, which change with time, are obtained, and the average temperature and the average wind speed are used as a deep learning training data set to train and obtain the flow field information prediction model.
As a preferable aspect of the present invention, the space structure parameters include a length, a width, and a height of the space, the current environment data includes current temperature and humidity data in the space, and the air supply related data includes an air conditioner model, an air direction of the air supply, and a temperature of the air supply.
As a preferred solution of the present invention, the specific training process of deep learning includes the following steps:
inputting the space structure parameters, the current environment data, the air conditioner position and the air supply related data into a full-connection neural network layer after regularization processing to obtain characteristic vectors;
on one hand, the feature vector is input into a convolutional neural network, and the convolutional neural network is divided into the following three parts: the 1D convolution network transforms the input feature vector into 1D high-dimensional features through 1D convolution operation; the 2D deconvolution network expands the 1D high-dimensional features into high-resolution 2D features through 2D deconvolution, and then the 2D high-dimensional features are compressed through 2D convolution operation by the 2D convolution network; finally, the 3D deconvolution network converts the 2D high-dimensional features into output discrete features through 3D deconvolution;
on the other hand, the feature vector is input into a regression model, and an analytic expression obtained by learning the regression model is used as a continuous feature;
converting the priori theoretical knowledge into the priori knowledge constraint characteristics through an embedded method;
and fusing the obtained discrete features, continuous features and priori knowledge constraint features by an integrated learning method to obtain a final output prediction tensor, namely a gridding prediction result, and obtaining a predicted flow field information result by data post-processing.
As a preferred scheme of the present invention, the target refrigeration area is collected by manual input by a user or by arranging a camera in the space.
As a preferred scheme of the invention, when the target refrigeration area is manually input by a user, the information uploading frequency is 1 to 3 hours, and when the target refrigeration area is collected by arranging a camera in the space, the updated information is uploaded in real time when the target refrigeration area is changed.
As a preferred scheme of the present invention, the camera uploads the collected information to the cloud computing center through the wireless WiFi, or the user manually inputs the information through the remote control terminal and uploads the input information to the cloud computing center through the wireless WiFi, and the cloud computing center is connected to the weather monitoring server.
As a preferable scheme of the invention, the comfortable wind speed is set by a user or is 0.3m/s which is a common value of engineering.
As a preferable scheme of the invention, the air conditioner operation time response surface graph is obtained by plotting the nonlinear fitting of data.
The invention also provides an air conditioner wind direction intelligent control system based on flow field information prediction, which comprises:
the prediction model establishing module is used for establishing a flow field information prediction model through deep learning;
the flow field information prediction module is used for collecting space structure parameters, current environment data, air conditioner position and air supply related data, uploading the data to the flow field information prediction model, and predicting the flow field information of the air conditioner after being started by combining local meteorological data, wherein the flow field comprises a temperature field and an air speed field;
the drawing module is used for drawing an air conditioner operation time response surface diagram which takes a horizontal air supply angle and a vertical air supply angle as a coordinate axis abscissa and an ordinate respectively according to the predicted flow field information after the air conditioner is started so as to enable a target refrigeration area to reach comfortable temperature;
and the control scheme generation module is used for determining an air supply angle with the minimum air supply time of the air conditioner when the target refrigeration area reaches the comfortable temperature under the condition of comfortable air speed in the air conditioner operation time response surface diagram, and forming an air supply control scheme of the air conditioner for control by taking the air supply angle as an optimal air supply angle.
Compared with the prior art, the invention has the following beneficial effects: the method has the advantages that the air supply control scheme with the highest comfort level for the user is directly provided by deep learning and response surface analysis methods without setting the air supply direction of the air conditioner by the user, so that the dual requirements of refrigeration and comfort level of the user can be met, and a new way is provided for the energy-saving and efficiency-increasing intelligent control of the air conditioner.
Drawings
Fig. 1 is a schematic view illustrating an information interaction process between a user side and a cloud server side according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a combination of a user side and a cloud server side device according to an embodiment of the present invention;
FIG. 3 is a result diagram of a CFD simulation temperature field during operation of a room air conditioner according to an embodiment of the present invention;
FIG. 4 is a CFD simulation wind velocity field result diagram during operation of a room air conditioner according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a flow field information prediction model established by deep learning according to an embodiment of the present invention;
FIG. 6 is a graph of the predicted temperature field of a room at different times for different height sections according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of determining an optimal wind direction according to a response surface analysis method according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Referring to fig. 1, an implementation of the air conditioner wind direction intelligent control method based on flow field information prediction mainly comprises a user side and a cloud service side. Referring to fig. 2, the cloud server device includes a weather monitoring server, a cloud computing center, and a deep learning cluster; the user end equipment comprises a household air conditioner, an intelligent camera, a user remote control and the like, wherein the intelligent camera is not required.
The functions of the various parts are as follows:
(1) the cloud server side:
processing data uploaded by a user side, giving an intelligent wind direction control scheme and transmitting the intelligent wind direction control scheme to the user side;
(1.1) weather monitoring server:
the system is in butt joint with a weather bureau server and receives weather conditions and air temperature and humidity data of each region;
(1.2) cloud computing center: data transmission of a cloud server side is planned overall, and the cloud server side directly interacts with a user side;
(2) a user side:
collecting required data, uploading the data to a cloud server, and receiving an intelligent wind direction control scheme sent by the cloud server;
(2.1) a household air conditioner:
the household equipment is internally provided with the WIFI module, can be connected with the Internet and directly interacts with a cloud computing center of a cloud server;
(2.2) intelligent camera:
the video acquisition equipment can monitor the positions of personnel in a room in real time and can interact with local data of the household air conditioner;
(2.3) remote control by a user:
the user can control the operation of the air conditioner through a remote controller or a mobile phone APP, and can input required data in the APP.
The invention relates to an air conditioner wind direction intelligent control method based on flow field information prediction, which comprises the following steps:
s1, establishing a flow field information prediction model through deep learning;
s2, collecting space structure parameters, current environment data, air conditioner position and air supply related data, uploading the data to a flow field information prediction model, and predicting flow field information of the air conditioner after being started by combining local meteorological data, wherein the flow field comprises a temperature field and an air speed field;
the space structure parameters comprise the length, the width and the height of a space, the current environment data comprise the current temperature and humidity data in the space, and the related air supply data comprise the air conditioner model, the air direction of air supply and the temperature of air supply
S3, drawing an air conditioner operation time response surface diagram with a horizontal air supply angle and a vertical air supply angle as a coordinate axis abscissa and an ordinate respectively according to predicted flow field information after the air conditioner is started, so that a target refrigeration area reaches a comfortable temperature;
and S4, determining the air supply angle with the minimum air supply time of the air conditioner when the target refrigeration area reaches the comfortable temperature under the condition of comfortable wind speed in the air conditioner operation time response surface diagram, and forming an air supply control scheme of the air conditioner for control by taking the air supply angle as the optimal air supply angle.
The cloud server establishes a room flow field information prediction model through a deep learning method, wherein first-stage data of the deep learning is from CFD simulation of a room temperature field of an air conditioner, and the first-stage data comprises the following input information: the length, the width, the high-level structural parameters of the room space, the installation position of the air conditioner, the air supply direction and the air supply temperature of the air conditioner, the initial temperature of the room and the like; and CFD simulation result information as follows: the room is gridded into several zones, each zone having an average temperature and an average wind speed that vary over time. By using the information as a training data set for deep learning, the trained model can accurately and quickly predict the corresponding CFD simulation result information under a certain input condition. The data of the second stage of deep learning is derived from experimental data of a room temperature field of the air conditioner, a plurality of temperature and wind speed measuring points are arranged in the room, and a prediction model is corrected through the experimental test data to obtain a prediction effect with higher accuracy. Fig. 3 and 4 show the simulation results of the room air temperature field and the wind speed field, respectively, by applying the CFD technology.
The following specifically describes a process of establishing a flow field information prediction model through deep learning.
As shown in fig. 5, the deep learning method uses a convolutional neural network and a regression model to predict flow field information based on a feature fusion idea. First, known data relating to the room shape and size, the air conditioner installation position, the average initial temperature, the local air physical properties, and the like are input to the fully-connected neural network layer after data regularization. Inputting the obtained feature vector into a convolutional neural network, wherein the convolutional neural network is divided into 3 parts: the 1D convolution network transforms the input feature vector into 1D high-dimensional features through 1D convolution operation; the 2D deconvolution network expands the 1D high-dimensional features into high-resolution 2D features through 2D deconvolution, and then the 2D high-dimensional features are compressed through 2D convolution operation by the 2D convolution network; and finally, the 3D deconvolution network converts the 2D high-dimensional features into output discrete features, namely 4D tensor: length x width x height x time channel, the length, width and height dimensions of which are determined by the room dimensions. The feature vectors obtained from the fully connected layer are also input to the regression model, and the analytic expression obtained by learning the regression model is used as the continuous feature. In addition, prior theoretical knowledge such as a continuous equation and the like is converted into prior knowledge constraint characteristics through an embedded method so as to eliminate partial ill-conditioned results obtained by a machine learning method. Finally, the discrete features, the continuous features and the priori knowledge constraint features are fused by an ensemble learning method to obtain a final output prediction tensor (gridding prediction result), and a predicted flow field information result can be obtained by data post-processing (such as a linear interpolation method) and a predicted temperature field result is shown in fig. 6.
When a user uses the air conditioner applying the method, the APP is required to fill in the information of the length, the width, the height and other structural parameters of the room space, the installation position information of the air conditioner, the type information of the air conditioner, the comfortable wind speed and the target refrigeration area information at a user side, wherein the information refers to the frequent position of the user in the room, such as a sofa, a chair or a bed, and if the room is provided with an intelligent camera, the information can be acquired by the intelligent camera in the room in real time. In addition, the air conditioner can obtain the temperature and humidity data in the current room in real time.
The built-in WIFI link module of air conditioner and storage space, the cloud server side is uploaded through the air conditioner to the information that user side APP collected, if do not be equipped with intelligent camera in the room, information upload frequency is once for 1 to 3 hours, if the target refrigeration is regional by intelligent camera collection, then updates the upload information when user's position changes. The cloud computing center receives the data uploaded by the user side and firstly predicts the air outlet temperature of the air conditioner by combining with local meteorological data, the temperature is obtained by summarizing and fitting correlation of experimental test data, and the accuracy is high. And predicting flow field information of different air supply directions including temperature field and wind speed field information after the air conditioner is started in the room in the deep learning cluster by using the data as input data. Therefore, the deep learning cluster can quickly obtain the running time of reducing the average temperature of the target refrigeration area to the temperature set by the user under the condition of any air supply direction of the air conditioner, and judge whether the air speed of the area exceeds the comfortable air speed set by the user.
The cloud computing center performs data interaction with the deep learning cluster to obtain a multi-dimensional data set for air supply direction-operation time-air speed comfort judgment, and then determines an optimal control scheme of the air supply direction of the air conditioner through a response surface analysis method. Fig. 7 is a response surface diagram of the air conditioner operation time when the horizontal air supply angle and the vertical air supply angle are horizontal and vertical coordinate axes and the target refrigeration area reaches a comfortable temperature, and the response surface diagram is obtained by drawing data through nonlinear fitting by a cloud computing center. The diagram has an uncomfortable wind speed area, the wind speed range is set by a user terminal, or the common engineering value is 0.3m/s, and the wind direction larger than the wind speed range is eliminated by the system. Outside this area, the air supply direction that minimizes the air conditioner operation time when the target cooling area reaches the user-set temperature is determined as the optimal air supply direction. Under the air supply direction, the air conditioner can simultaneously meet the dual requirements of the fastest refrigeration and comfortable air speed of a user.
And the cloud server transmits the optimal air supply control scheme to the air conditioner at the user side, and the air conditioner is started after being started. After the air conditioner at the user side obtains the optimal air supply angle scheme, the air conditioner does not need to interact with the cloud server side until a new control scheme is received. And the cloud server side rapidly completes the processes of prediction, response surface analysis and determination of the optimal wind direction scheme after receiving the uploaded information of the air conditioner at the user side and sends the information to the air conditioner at the user side.
The invention also provides an air conditioner wind direction intelligent control system based on flow field information prediction, which comprises:
the prediction model establishing module is used for establishing a flow field information prediction model through deep learning;
the flow field information prediction module is used for collecting space structure parameters, current environment data, air conditioner position and air supply related data, uploading the data to the flow field information prediction model, and predicting the flow field information of the air conditioner after being started by combining local meteorological data, wherein the flow field comprises a temperature field and an air speed field;
the drawing module is used for drawing an air conditioner operation time response surface diagram which takes a horizontal air supply angle and a vertical air supply angle as a coordinate axis abscissa and an ordinate respectively according to the predicted flow field information after the air conditioner is started so as to enable a target refrigeration area to reach comfortable temperature;
and the control scheme generation module is used for determining an air supply angle with the minimum air supply time of the air conditioner when the target refrigeration area reaches the comfortable temperature under the condition of comfortable air speed in the air conditioner operation time response surface diagram, and forming an air supply control scheme of the air conditioner for control by taking the air supply angle as an optimal air supply angle.
According to the intelligent control method for the wind direction of the air conditioner, the wind direction of the air supply of the air conditioner does not need to be set by a user, but a wind direction control scheme with the highest comfort level of the user is obtained through calculation by a deep learning and response surface analysis method.
While the invention has been described in further detail with reference to specific preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An air conditioner wind direction intelligent control method based on flow field information prediction is characterized by comprising the following steps:
establishing a flow field information prediction model through deep learning;
collecting space structure parameters, current environment data, air conditioner position and air supply related data, uploading the data to a flow field information prediction model, and predicting flow field information of the air conditioner after the air conditioner is started by combining local meteorological data, wherein the flow field comprises a temperature field and an air speed field;
drawing an air conditioner operation time response surface graph with a horizontal air supply angle and a vertical air supply angle as a coordinate axis abscissa and an ordinate respectively according to predicted flow field information after the air conditioner is started, so that a target refrigeration area reaches a comfortable temperature;
and determining an air supply angle with the minimum air supply time of the air conditioner when the target refrigeration area reaches the comfortable temperature under the condition of comfortable air speed in the air conditioner operation time response surface diagram, and forming an air supply control scheme of the air conditioner for control by taking the air supply angle as the optimal air supply angle.
2. The air conditioner wind direction intelligent control method based on flow field information prediction as claimed in claim 1, wherein the flow field information prediction model is built through deep learning to perform CFD simulation by using spatial structure parameters, current environment data and air conditioner position and air supply related data, space grids are formed into a plurality of regions from CFD simulation results, the average temperature and the average wind speed of each region changing along with time are obtained and used as a deep learning training data set, and the flow field information prediction model is obtained through training.
3. The intelligent control method for air conditioner wind direction based on flow field information prediction according to claim 1 or 2, characterized in that the spatial structure parameters comprise length, width and height of a space, the current environmental data comprise current temperature and humidity data in the space, and the air supply related data comprise air conditioner model, air direction of air supply and temperature of air supply.
4. The air conditioner wind direction intelligent control method based on flow field information prediction as claimed in claim 3, wherein the specific training process of deep learning comprises the following steps:
inputting the space structure parameters, the current environment data, the air conditioner position and the air supply related data into a full-connection neural network layer after regularization processing to obtain characteristic vectors;
on one hand, the feature vector is input into a convolutional neural network, and the convolutional neural network is divided into the following three parts: the 1D convolution network transforms the input feature vector into 1D high-dimensional features through 1D convolution operation; the 2D deconvolution network expands the 1D high-dimensional features into high-resolution 2D features through 2D deconvolution, and then the 2D high-dimensional features are compressed through 2D convolution operation by the 2D convolution network; finally, the 3D deconvolution network converts the 2D high-dimensional features into output discrete features through 3D deconvolution;
on the other hand, the feature vector is input into a regression model, and an analytic expression obtained by learning the regression model is used as a continuous feature;
converting the priori theoretical knowledge into the priori knowledge constraint characteristics through an embedded method;
and fusing the obtained discrete features, continuous features and priori knowledge constraint features by an integrated learning method to obtain a final output prediction tensor, namely a gridding prediction result, and obtaining a predicted flow field information result by data post-processing.
5. The air conditioner wind direction intelligent control method based on flow field information prediction according to claim 1, characterized in that: the target refrigeration area is manually input by a user or collected by arranging a camera in the space.
6. The intelligent control method for the air conditioner wind direction based on the flow field information prediction as claimed in claim 5, wherein: when the target refrigeration area is manually input by a user, the information uploading frequency is 1 to 3 hours, and when the target refrigeration area is collected by arranging a camera in a space, the updated information is uploaded in real time when the target refrigeration area is changed.
7. The intelligent control method for the air conditioner wind direction based on the flow field information prediction as claimed in claim 5, wherein: the camera uploads the collected information to the cloud computing center through wireless WiFi, or a user manually inputs the information through a remote control terminal and uploads the input information to the cloud computing center through wireless WiFi, and the cloud computing center is connected with a meteorological monitoring server.
8. The air conditioner wind direction intelligent control method based on flow field information prediction according to claim 1, characterized in that: the comfortable wind speed is set by a user or is 0.3m/s which is a common engineering value.
9. The air conditioner wind direction intelligent control method based on flow field information prediction according to claim 1, characterized in that: the air conditioner operation time response surface diagram is obtained by drawing through data nonlinear fitting.
10. The utility model provides an air conditioner wind direction intelligence control system based on flow field information prediction which characterized in that includes:
the prediction model establishing module is used for establishing a flow field information prediction model through deep learning;
the flow field information prediction module is used for collecting space structure parameters, current environment data, air conditioner position and air supply related data, uploading the data to the flow field information prediction model, and predicting the flow field information of the air conditioner after being started by combining local meteorological data, wherein the flow field comprises a temperature field and an air speed field;
the drawing module is used for drawing an air conditioner operation time response surface diagram which takes a horizontal air supply angle and a vertical air supply angle as a coordinate axis abscissa and an ordinate respectively according to the predicted flow field information after the air conditioner is started so as to enable a target refrigeration area to reach comfortable temperature;
and the control scheme generation module is used for determining an air supply angle with the minimum air supply time of the air conditioner when the target refrigeration area reaches the comfortable temperature under the condition of comfortable air speed in the air conditioner operation time response surface diagram, and forming an air supply control scheme of the air conditioner for control by taking the air supply angle as an optimal air supply angle.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110910614.3A CN113719974A (en) | 2021-08-09 | 2021-08-09 | Air conditioner wind direction intelligent control method and system based on flow field information prediction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110910614.3A CN113719974A (en) | 2021-08-09 | 2021-08-09 | Air conditioner wind direction intelligent control method and system based on flow field information prediction |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113719974A true CN113719974A (en) | 2021-11-30 |
Family
ID=78675294
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110910614.3A Pending CN113719974A (en) | 2021-08-09 | 2021-08-09 | Air conditioner wind direction intelligent control method and system based on flow field information prediction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113719974A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116026007A (en) * | 2022-12-21 | 2023-04-28 | 珠海格力电器股份有限公司 | Temperature adjusting method and device, storage medium and electronic equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455676A (en) * | 2013-09-04 | 2013-12-18 | 重庆建工住宅建设有限公司 | Method for simulating indoor thermal environment by fluid mechanics |
CN104374048A (en) * | 2014-10-29 | 2015-02-25 | 广东美的制冷设备有限公司 | Control method for air supply angle of air-conditioner and control system |
CN110910503A (en) * | 2019-10-15 | 2020-03-24 | 珠海格力电器股份有限公司 | Simulation method and device for air conditioning environment |
CN111238001A (en) * | 2020-02-25 | 2020-06-05 | 珠海格力电器股份有限公司 | Control method and device for air supply of air conditioner, storage medium and processor |
CN111428586A (en) * | 2020-03-09 | 2020-07-17 | 同济大学 | Three-dimensional human body posture estimation method based on feature fusion and sample enhancement |
CN111932511A (en) * | 2020-08-04 | 2020-11-13 | 南京工业大学 | Electronic component quality detection method and system based on deep learning |
-
2021
- 2021-08-09 CN CN202110910614.3A patent/CN113719974A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455676A (en) * | 2013-09-04 | 2013-12-18 | 重庆建工住宅建设有限公司 | Method for simulating indoor thermal environment by fluid mechanics |
CN104374048A (en) * | 2014-10-29 | 2015-02-25 | 广东美的制冷设备有限公司 | Control method for air supply angle of air-conditioner and control system |
CN110910503A (en) * | 2019-10-15 | 2020-03-24 | 珠海格力电器股份有限公司 | Simulation method and device for air conditioning environment |
CN111238001A (en) * | 2020-02-25 | 2020-06-05 | 珠海格力电器股份有限公司 | Control method and device for air supply of air conditioner, storage medium and processor |
CN111428586A (en) * | 2020-03-09 | 2020-07-17 | 同济大学 | Three-dimensional human body posture estimation method based on feature fusion and sample enhancement |
CN111932511A (en) * | 2020-08-04 | 2020-11-13 | 南京工业大学 | Electronic component quality detection method and system based on deep learning |
Non-Patent Citations (1)
Title |
---|
张继刚: "壁挂式空调房间内流场温度场特性与人体热舒适的研究", 《工程科技Ⅱ辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116026007A (en) * | 2022-12-21 | 2023-04-28 | 珠海格力电器股份有限公司 | Temperature adjusting method and device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110856134B (en) | Large-scale wireless sensor network data collection method based on unmanned aerial vehicle | |
CN103940049B (en) | Air-conditioner set control method, apparatus and system | |
CN211503153U (en) | Indoor air quality cooperative monitoring and regulation system based on multiple targets | |
CN101737907B (en) | Method for intelligently controlling indoor environment based on thermal imaging technology | |
CN104267626B (en) | A kind of household appliance control method and system | |
CN108413588B (en) | Personalized air conditioner control system and method based on thermal imaging and BP neural network | |
CN103398451A (en) | Multi-dimensional indoor environment controlling method and system based on learning of user behaviors | |
CN105509225B (en) | A kind of method, apparatus and system for adjusting the apparatus of air conditioning | |
CN102779228A (en) | Method and system for online prediction on cooling load of central air conditioner in marketplace buildings | |
CN110598906A (en) | Method and system for controlling energy consumption of superstores in real time based on deep reinforcement learning | |
CN115220351B (en) | Intelligent energy-saving optimization control method for building air conditioning system based on cloud side end | |
CN113418286B (en) | Self-adaptive thermal sensing robot and air conditioner temperature adjusting method | |
CN103389710A (en) | Internet of Things environment control method and device based on context-aware | |
CN113719974A (en) | Air conditioner wind direction intelligent control method and system based on flow field information prediction | |
CN115774899B (en) | BIM modeling-based visual air conditioner management method and system | |
CN113110057A (en) | Heating power station energy-saving control method based on artificial intelligence and intelligent decision system | |
CN112577159A (en) | Air conditioner energy-saving intelligent control method and device based on human body thermal comfort | |
CN113535233B (en) | Artificial intelligence system for heating and ventilation cloud edge cooperation | |
CN115047821A (en) | Intelligent monitoring system for live pig breeding environment and evaluation method thereof | |
CN107390521B (en) | Method for calculating optimal indoor temperature measuring point of air conditioning system and test platform | |
CN116225102B (en) | Mobile energy storage communication temperature rise automatic monitoring system and device | |
CN110726216B (en) | Air conditioner, control method, device and system thereof, storage medium and processor | |
CN107965883A (en) | Cloud computing system and method, multi-gang air-conditioner management system and method | |
CN106152394A (en) | Data center's entirety energy consuming solution and system | |
CN112378052A (en) | Indoor comfort degree adjusting method, device and system, computer equipment 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: 20211130 |