CN117366805A - Method and device for controlling temperatures of multiple points by utilizing mechanical learning and air conditioner - Google Patents

Method and device for controlling temperatures of multiple points by utilizing mechanical learning and air conditioner Download PDF

Info

Publication number
CN117366805A
CN117366805A CN202311229326.7A CN202311229326A CN117366805A CN 117366805 A CN117366805 A CN 117366805A CN 202311229326 A CN202311229326 A CN 202311229326A CN 117366805 A CN117366805 A CN 117366805A
Authority
CN
China
Prior art keywords
value
temperature
target
output value
data
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
Application number
CN202311229326.7A
Other languages
Chinese (zh)
Inventor
青野正弘
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aux Air Conditioning Co Ltd
Ningbo Aux Electric Co Ltd
Original Assignee
Aux Air Conditioning Co Ltd
Ningbo Aux Electric Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Aux Air Conditioning Co Ltd, Ningbo Aux Electric Co Ltd filed Critical Aux Air Conditioning Co Ltd
Priority to CN202311229326.7A priority Critical patent/CN117366805A/en
Publication of CN117366805A publication Critical patent/CN117366805A/en
Pending legal-status Critical Current

Links

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
    • F24F11/62—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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
    • Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention provides a method and a device for controlling temperature of multiple points by utilizing mechanical learning and an air conditioner, wherein the method comprises the following steps: updating the evaluation value of the first target combination data according to the temperature output value and the first actual temperature output value of the first target combination data; calculating an average value of parameter control values of the first target combination data and the second target combination data, and obtaining a second actual temperature output value in a stable running state; and determining newly added combined data according to the average value and the second actual temperature output value. According to the embodiment of the invention, the evaluation value of the existing combined data is updated based on the actually measured temperature value, and new combined data is continuously generated, so that the combined data gradually accords with the installation environment by continuous updating, the air conditioner can gradually adapt to the installation environment without installing an expensive sensor, and the temperature around the accurate user is adjusted according to the requirement of the user.

Description

Method and device for controlling temperatures of multiple points by utilizing mechanical learning and air conditioner
Technical Field
The invention relates to the technical field of automatic shutdown control of air conditioners, in particular to a method and a device for controlling temperatures at multiple points by utilizing mechanical learning and an air conditioner.
Background
In recent years, in order to improve user comfort, some air conditioners have developed a technique for acquiring a temperature around the user by a thermal camera and performing temperature adjustment. However, in the application scenario of the commercial multi-split air conditioner, a plurality of internal machines may be installed in a wide space in a connected manner, and it is difficult to adjust the temperature around the user due to interaction between the internal machines. Also in this environment, there may be a plurality of users in one space, and thus, it is necessary to adjust the temperatures of a plurality of locations.
At present, a method for simulating a fluid and controlling the temperature through a simulation technology exists. However, the space without the obstacle is preset in the fluid simulation, and the conditions such as the ceiling height and the like are assumed, so that the obtained data are quite possibly not matched with the actual installation conditions. In addition, there is a method of recognizing the installation environment through the high-performance camera and then performing fluid simulation, but the price of the computing equipment for simulation is relatively high, and the cost of the high-performance camera is inevitably increased greatly.
Disclosure of Invention
To solve the above problems, an embodiment of the present invention provides a method for performing temperature control on multiple points by using machine learning, the method including: acquiring a target temperature value of at least one position, and determining first target combination data in a plurality of combination data according to the target temperature value; each piece of combined data comprises a parameter control value, a temperature output value and an evaluation value, and the first target combined data is combined data with the smallest difference between the temperature output value and the target temperature value in each piece of combined data; controlling the operation of the air conditioner according to the parameter control value of the first target combination data, and acquiring a first actual temperature output value in a stable operation state; updating the evaluation value of the first target combination data according to the temperature output value of the first target combination data and the first actual temperature output value; determining second target combination data in a plurality of combination data according to the target temperature value, wherein the second target combination data is combination data with small difference between a temperature output value and the target temperature value in each combination data; calculating an average value of parameter control values of the first target combination data and the second target combination data, and controlling the operation of the air conditioner according to the average value to obtain a second actual temperature output value in a stable operation state; determining newly added combined data according to the average value and the second actual temperature output value; and the parameter control value of the newly added combined data is the average value, the temperature output value is the second actual temperature output value, and the evaluation value is the initial evaluation value.
The method for controlling the temperatures by utilizing the mechanical learning, which is provided by the embodiment of the invention, has a plurality of combination data consisting of control values, multi-point room temperature data and evaluation values, when the indoor temperature of any position is regulated, the data with the output value closest to the set temperature is selected from the combination data to be used as the control parameter of the air conditioner to operate, the evaluation value of the existing combination data is updated based on the actually measured temperature value, and new combination data is continuously generated, so that the combination data is continuously updated to gradually conform to the installation environment, the air conditioner can gradually adapt to the installation environment without installing expensive sensors, and the temperature around the accurate user can be regulated according to the requirement of the user.
Optionally, the method further comprises: and if the number of the plurality of combined data is larger than a preset threshold value, deleting the combined data with the lowest evaluation value.
According to the embodiment of the invention, the mode of discarding the combined data can be continuously optimized, and the method can continuously learn and adapt to the installation environment.
Optionally, the method further comprises: if the temperature adjustment value of any one or more positions input by a user is received, determining third target combination data in the combination data according to the temperature adjustment value; the third target combination data is combination data with the smallest difference between the temperature output value and the temperature regulation value in the combination data; and controlling the operation of the air conditioner according to the parameter control value of the third target combination data.
In the embodiment of the invention, enough combined data is obtained based on the mechanical learning mode, or the learning times reach the preset conditions, and the like, and the operation of the air conditioner can be controlled based on the combined data.
Optionally, the method further comprises: and if the number of the plurality of combined data is larger than the preset threshold value and the combined data with the lowest evaluation value is a plurality of combined data, deleting the combined data with the earliest date in the combined data with the lowest evaluation value.
In the embodiment of the invention, under the condition that a plurality of combined data with the lowest evaluation value exists, the combined data with the earliest generation date can be deleted, so that the combined data which is generated more recently is reserved, and the current installation environment is more met.
Optionally, each of the combination data includes a temperature output value that is a temperature output value of a plurality of locations; the difference between the temperature output value and the target temperature value is the sum of the difference between the temperature value of each position of the target temperature value and the temperature output value of the corresponding position; or, the difference between the temperature adjustment value and the target temperature value is the sum of the difference between the temperature value of each position of the temperature adjustment value and the temperature output value of the corresponding position.
According to the embodiment of the invention, a user can adjust one position or a plurality of positions, and the air conditioner can accurately control the temperatures of the plurality of positions.
Optionally, the calculation formula of the evaluation value G is as follows:
wherein, ts_i is the target temperature value of the temperature test point Ti, tm_i is the temperature output value of the temperature test point Ti, and n is the number of the temperature test points.
The embodiment of the invention provides a calculation formula of the evaluation value G, which can evaluate the applicability of the combined data, thereby selecting proper combined data.
Optionally, the calculation formula for updating the evaluation value is as follows:
where z_after is an evaluation value after update, z_before is an evaluation value before update, tm "_i is an actual temperature output value of the temperature test point Ti, and α is an evaluation threshold.
The embodiment of the invention provides a feasible way for updating the evaluation value, and can update the evaluation value of the combined data.
Optionally, each combination data further includes an outdoor temperature output value and an outdoor illumination output value, and the calculation formula for updating the evaluation value is as follows:
wherein tout_m is the actual outdoor temperature, tout is the outdoor temperature output value, hm is the actual illumination quantity, H is the outdoor illumination quantity output value, F1, F2, gi are all weighting coefficients, ts_i is the target temperature value of the temperature test point Ti, tm_i is the temperature output value of the temperature test point Ti, and n is the number of the temperature test points.
The embodiment of the invention provides a feasible way for updating the evaluation value, and can update the evaluation value of the combined data.
The embodiment of the invention provides a device for controlling temperature of multiple points by utilizing mechanical learning, which comprises the following components: the first acquisition module is used for acquiring a target temperature value of at least one position and determining first target combined data in a plurality of combined data according to the target temperature value; each piece of combined data comprises a parameter control value, a temperature output value and an evaluation value, and the first target combined data is combined data with the smallest difference between the temperature output value and the target temperature value in each piece of combined data; the first operation module is used for controlling the operation of the air conditioner according to the parameter control value of the first target combination data and obtaining a first actual temperature output value in a stable operation state; the evaluation module is used for updating the evaluation value of the first target combination data according to the temperature output value of the first target combination data and the first actual temperature output value; the second acquisition module is used for determining second target combined data in a plurality of combined data according to the target temperature value, wherein the second target combined data are combined data with small difference between a temperature output value and the target temperature value in the combined data; the second running module is used for calculating the average value of the parameter control values of the first target combination data and the second target combination data, controlling the running of the air conditioner according to the average value and obtaining a second actual temperature output value in a stable running state; the new adding module is used for determining new added combined data according to the average value and the second actual temperature output value; and the parameter control value of the newly added combined data is the average value, the temperature output value is the second actual temperature output value, and the evaluation value is the initial evaluation value.
The embodiment of the invention provides a multi-split air conditioner, which comprises the device for controlling the temperature of multiple points by utilizing mechanical learning and a plurality of temperature measurers; the temperature measurer is used for measuring actual temperature output values of all the positions respectively.
Embodiments of the present invention provide a computer readable storage medium storing a computer program which, when read and executed by a processor, implements the above-described method.
The device for controlling the temperature of the multiple points by using the mechanical learning and the multi-split air conditioner can achieve the same technical effect as the method for controlling the temperature of the multiple points by using the mechanical learning.
Drawings
FIG. 1 is a schematic flow chart of a method for performing temperature control on multiple points by using mechanical learning according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a two-dimensional horizontal plane model of an assumed installation scene in an embodiment of the invention;
FIG. 3 is a schematic flow chart of a method for temperature control of multiple points using machine learning in an embodiment of the invention;
fig. 4 is a schematic structural diagram of an apparatus for performing temperature control on multiple points by using mechanical learning according to an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
The method for controlling the temperatures of the multiple points by utilizing the mechanical learning provided by the embodiment of the invention can control the temperatures of the multiple points by utilizing the mechanical learning.
In order to facilitate understanding of the scheme in this embodiment, the basic principle thereof will be exemplified below. Fig. 1 is a schematic flow chart of a basic principle of a method for performing temperature control on multiple points by using mechanical learning in an embodiment of the invention.
Let the control value be X, the output value be Y, and the evaluation value be Z, the following is defined for the relevant combinations:
theoretical correlation of control value and output value y=2 x X 2
Measured correlation of control value and output value y=2 x X 2 +3
The above correlation formula is merely an example for convenience of explanation.
(1) Acquiring initial combined data
The initial combination data were set to be (1) to (4) (the initial evaluation values were set to be 10)
①(X＝1,Y＝2,Z＝10)、②(X＝3,Y＝18,Z＝10)、③(X＝5,Y＝50,Z＝10)、④(X＝8,Y＝128,Z＝10)
(2) Selecting combined data that approximates user requirements
And selecting the combination data with the output value most conforming to the user requirement value in the initial combination data. For example, if the user demand value=30, the combination of the output value and the demand value closest to each other is (2) (x=3, y=18, and z=10).
(3) Measuring actual output value after running and waiting for stabilization of air conditioner
The air conditioner operates according to the control value in the selected combination (2), and calculates the value in the steady state as the actual output value. For example, if the control value x=3, the actual output value Y' =21.
(4) Updating evaluation value of combined data
The reliability (accuracy) of the selected combination data (2) is evaluated based on the actual output value, and the evaluation value of the combination data (2) is updated. Updating the formula of the evaluation value: z_after=z_before- |y-Y' |+α, where α is an evaluation threshold (e.g., α=5). In the above example, (2) (x=3, y=18, z=10) has the following evaluation values: z=10- |18-21|+5=12
(5) A new control value is generated.
The average of the control values in the combination closest to the demand value and the combination closest to the second is calculated, and a new control value is generated. The closest combination (2) (x=3, y=18, z=12), the second closest combination (3) (x=5, y=50, z=10), the new control value x= (3+5)/2=4.
(6) Actually measured output value and new combined data are obtained
The operation is performed according to the control value obtained in (5), the value in the steady operation state is calculated as the actual output value, and the calculated value is stored as a new combination of the control value and the output value. For example, the new control value x=4, the measured output value y=35, the new combination (5) (x=4, y=35, z=10).
(7) Combined data with low discard evaluation
When the above-mentioned combined data exceeds a certain quantity, the data with lowest evaluation value in the combined data are automatically abandoned. When the evaluation values of the plurality of combination data are the same, the data having a lower number (or a relatively earlier date) is discarded. To take the above examples, (1) (x=1, y=2, z=10), (2) (x=3, y=18, z=12), (3) (x=5, y=50, z=10), (4) (x=8, y=128, z=10), (5) (x=4, y=35, z=10), the combination of (1) (x=1, y=2, z=10) needs to be discarded.
(8) Repeating the steps (2) - (7), thereby optimizing the output value, gradually approaching the output value to the required value, and continuously learning to adapt to the installation environment by continuously discarding the combination with low evaluation value and generating a new combination.
Take the case that the commercial multi-split air conditioner can control the temperature of a plurality of positions as an example. Fig. 2 is a schematic view of a two-dimensional horizontal plane model assuming an installation scene, showing a plurality of internal machines A, B, C, D in a room defined by walls w, and measurement and setting positions T1 to T9 of temperatures.
The control value and the output value are defined as shown in table 1.
TABLE 1
The initial combination data of the control value and the output value may be measured by preliminary experiments, calculated by simulation, calculated from the installed operation data, or the like. In addition, the user demand value is set temperature, and if the temperature test point cannot be set as shown in fig. 2, the intake air temperature of the internal machine may be taken as the output value.
Regarding how to select the combination data, the data may be evaluated according to the suitability (accuracy) evaluation formula G shown below, and a combination in which the G value is the smallest may be selected. If there is only one temperature measuring point, the difference is directly calculated, and if there are a plurality of temperature measuring points, the absolute value of the difference is calculated and then summed.
Wherein, ts_i is the set temperature of the temperature test point Ti.
As shown below, the control value in the selected combination data is used to obtain the actual operating output value, and the evaluation value of the combination data is updated according to the difference between the output value of the selected combination and the actual output value. Combination of two or more kinds of materialsThe updated evaluation values are as follows
Wherein Tm "_i is the measured temperature of the temperature test point Ti, and alpha is the evaluation threshold.
Then, a new control value is generated, an output value is obtained, new combination data is added, and when the combination data exceeds a predetermined amount (for example, 1000 sets of combination data), data having a low evaluation value is discarded.
Fig. 3 shows a schematic flow chart of a method for temperature control of multiple points using machine learning in an embodiment of the invention, the method comprising the steps of:
s302, acquiring a target temperature value of at least one position, and determining first target combination data in a plurality of combination data according to the target temperature value.
Wherein, each combination data includes a parameter control value, a temperature output value and an evaluation value. The first target combination data is combination data with the smallest difference between the temperature output value and the target temperature value in the combination data. It should be noted that, the temperature output value in the above-mentioned combined data may be temperature output values of a plurality of positions; if the target temperature values of the plurality of positions are obtained, the difference value between the target temperature value and the temperature output value corresponding to each position can be calculated, then the absolute values of all the difference values are summed, and then the combined data with the smallest sum value is used as the first target combined data.
Specifically, the parameter control values may include an evaporation temperature, an inner fan rotation speed, and the like.
Taking a multi-connected air conditioner with a plurality of internal machines as an example, a plurality of combination data comprising control values, multi-point room temperature data and evaluation values are preset, and when the indoor temperature at any one position is regulated, the combination data with the output value closest to the regulation target temperature is selected from the combination data as a control parameter.
S304, controlling the operation of the air conditioner according to the parameter control value of the first target combination data, and obtaining a first actual temperature output value in a stable operation state.
And after the air conditioner runs for a preset time period to reach a stable state according to the parameter control value of the first target combination data, obtaining the measured temperature value of each position.
S306, updating the evaluation value of the first target combination data according to the temperature output value and the first actual temperature output value of the first target combination data.
After the actual temperature output value actually measured is obtained, the degree of coincidence between the combined data and the current space to be used may be evaluated based on the difference between the actual temperature output value and the temperature output value in the combined data.
Illustratively, the evaluation value G is calculated as follows:
wherein, ts_i is the target temperature value of the temperature test point Ti, tm_i is the temperature output value of the temperature test point Ti, and n is the number of the temperature test points.
Illustratively, the calculation formula for updating the evaluation value G is as follows:
where z_after is an evaluation value after update, z_before is an evaluation value before update, tm "_i is an actual temperature output value of the temperature test point Ti, and α is an evaluation threshold.
S308, determining second target combination data in the plurality of combination data according to the target temperature value. The second target combination data is combination data in which the difference between the temperature output value and the target temperature value is small.
And generating a new control value based on the average number of the control values in the first target combination data closest to the target temperature value and the second target combination data closest to the target temperature value, and further obtaining corresponding combination data.
S310, calculating an average value of parameter control values of the first target combination data and the second target combination data, and controlling the air conditioner to operate according to the average value to obtain a second actual temperature output value in a stable operation state.
S312, determining newly added combination data according to the average value and the second actual temperature output value. The parameter control value of the newly added combination data is the average value, the temperature output value is the second actual temperature output value, and the evaluation value is the initial evaluation value.
And generating new combined data by the updated first target combined data and the updated second target combined data, wherein the parameter control value of the new combined data is the average value of the parameter control values of the first target combined data and the second target combined data, and the temperature output value is the measured output value obtained by running based on the average value, so that the combined data more accurately describes the current use space, thereby realizing continuous learning adaptation environment.
The method for controlling the temperatures by utilizing the mechanical learning, which is provided by the embodiment of the invention, has a plurality of combination data consisting of control values, multi-point room temperature data and evaluation values, when the indoor temperature of any position is regulated, the data with the output value closest to the set temperature is selected from the combination data to be used as the control parameter of the air conditioner to operate, the evaluation value of the existing combination data is updated based on the actually measured temperature value, and new combination data is continuously generated, so that the combination data is continuously updated to gradually conform to the installation environment, the air conditioner can gradually adapt to the installation environment without installing expensive sensors, and the temperature around the accurate user can be regulated according to the requirement of the user.
In addition to the generation of new combined data, it is also necessary to consider the limitation of the total number, and in the case where the number of combined data exceeds a certain amount, combined data having a low evaluation value may be discarded. Based on this, the above method may further include: and if the number of the plurality of combined data is larger than a preset threshold value, deleting the combined data with the lowest evaluation value. Through the mode of discarding the combined data, the method can be continuously optimized, and the method can continuously learn and adapt to the installation environment.
Further, the method may further include: and if the number of the plurality of combined data is greater than the preset threshold value and the combined data with the lowest evaluation value is a plurality of combined data, deleting the combined data with the earliest generation date in the combined data with the lowest evaluation value. Under the condition that a plurality of combination data with the lowest evaluation value exist, the combination data with the earliest generation date can be deleted, so that the combination data which are generated more recently can be reserved, and the current installation environment can be met more.
And after enough combined data is obtained based on the mechanical learning mode or the learning times reach preset conditions, the operation of the air conditioner can be controlled based on the combined data. Based on this, the above method may further include: if the temperature adjustment value of any one or more positions input by the user is received, determining third target combination data in the combination data according to the temperature adjustment value; the third target combination data is the combination data with the smallest difference between the temperature output value and the temperature regulation value in the combination data; and then, controlling the operation of the air conditioner according to the parameter control value of the third target combination data.
The air conditioner is controlled to operate based on the combined data obtained in the mode, so that the peripheral temperature of a user can be regulated more accurately, and the use experience is improved.
Optionally, each of the above-mentioned combination data includes a temperature output value that is a temperature output value of a plurality of positions; the difference between the temperature output value and the target temperature value is the sum of the difference between the temperature value of each position of the target temperature value and the temperature output value of the corresponding position; or, the difference between the temperature adjustment value and the target temperature value is the sum of the difference between the temperature value of each position of the temperature adjustment value and the temperature output value of the corresponding position. Wherein summing the differences is summing the absolute values of the differences. The user can adjust one position or a plurality of positions, and the air conditioner can accurately control the temperature of a plurality of positions.
Further, since the indoor temperature is influenced by the outdoor air temperature, the solar radiation amount, and the like, this temperature influence is also reflected in the output value. Alternatively, the combination of the control value and the output value is shown in table 2. However, the outdoor temperature and the illumination quantity influence the indoor temperature through the heat conduction of the outer wall, so that the change of the time periods such as wind blowing, cloudy days and the like is ignored, and the average value in a period (such as one hour) is adopted.
TABLE 2
The applicability evaluation formula G has a weight coefficient, and an evaluation value (fitting value) of the outdoor temperature and the insolation amount is set to be larger than a difference between the same and the set temperatures of the respective positions (in order to limit the outdoor thermometer illumination amount to a similar condition).
Based on this, each of the above-mentioned combination data further includes an outdoor temperature output value and an outdoor illumination output value, and the calculation formula of the update evaluation value G is as follows:
wherein tout_m is the actual outdoor temperature, tout is the outdoor temperature output value, hm is the actual illumination quantity, H is the outdoor illumination quantity output value, F1, F2, gi are all weighting coefficients, ts_i is the target temperature value of the temperature test point Ti, tm_i is the temperature output value of the temperature test point Ti, and n is the number of the temperature test points.
Outdoor temperature and insolation can be measured by sensors installed on the equipment, and meteorological data can be obtained through a network. In addition, the combined data can be stored in the cloud.
Since the internal units are far from the user and only the intake temperature of each internal unit is used, when the measurement is too rough because no other temperature measurement point is provided, a temperature measuring instrument that can be installed near the user can be used. The temperature measurer can also input the set temperature of the position and can send data to the internal machine in a wired or wireless mode.
The multi-connected air conditioner connected with a plurality of internal machines is provided with a plurality of data consisting of control values and multi-point room temperature data, and when the indoor temperature of any one position is regulated, the data with the output value closest to the set temperature is selected from the combined data to serve as a control parameter.
And evaluating the consistency (precision) of the combined data in the project, discarding the data with lower evaluation, and retaining new data, so that the data gradually accords with the installation environment regardless of updating.
The embodiment of the invention provides a multi-split air conditioner, which comprises the device for controlling the temperature of multiple points by utilizing mechanical learning and a plurality of temperature measurers; the temperature measurer is used for measuring actual temperature output values of all the positions respectively.
The multi-split air conditioner comprises a temperature measurer which can acquire temperature data of any position and communicate with the air conditioner, and temperature setting of the position can be input into the temperature measurer.
Fig. 4 is a schematic structural diagram of an apparatus for performing temperature control on multiple points by using mechanical learning, in an embodiment of the present invention, where the apparatus includes:
a first obtaining module 401, configured to obtain a target temperature value of at least one location, and determine first target combined data in a plurality of combined data according to the target temperature value; each piece of combined data comprises a parameter control value, a temperature output value and an evaluation value, and the first target combined data is combined data with the smallest difference between the temperature output value and the target temperature value in each piece of combined data;
a first operation module 402, configured to control the operation of the air conditioner according to the parameter control value of the first target combination data, and obtain a first actual temperature output value in a steady operation state;
an evaluation module 403, configured to update an evaluation value of the first target combination data according to a temperature output value of the first target combination data and the first actual temperature output value;
a second obtaining module 404, configured to determine second target combined data in the plurality of combined data according to the target temperature value, where the second target combined data is combined data with a small difference between a temperature output value and the target temperature value in each of the combined data;
a second operation module 405, configured to calculate an average value of parameter control values of the first target combination data and the second target combination data, and control the operation of the air conditioner according to the average value, so as to obtain a second actual temperature output value in a stable operation state;
a new adding module 406, configured to determine new combined data according to the average value and the second actual temperature output value; and the parameter control value of the newly added combined data is the average value, the temperature output value is the second actual temperature output value, and the evaluation value is the initial evaluation value.
The device for controlling the temperatures by utilizing the mechanical learning provided by the embodiment of the invention is provided with a plurality of combination data consisting of control values, multi-point room temperature data and evaluation values, when the indoor temperature of any position is regulated, the data with the output value closest to the set temperature is selected from the combination data to be used as the control parameter of the air conditioner to operate, the evaluation value of the existing combination data is updated based on the actually measured temperature value, and new combination data is continuously generated, so that the combination data is continuously updated to gradually conform to the installation environment, the air conditioner can gradually adapt to the installation environment without installing expensive sensors, and the temperature around the accurate user can be regulated according to the requirement of the user.
As a possible way, the method further comprises: and if the number of the plurality of combined data is larger than a preset threshold value, deleting the combined data with the lowest evaluation value.
As a possible way, the method further comprises: if the temperature adjustment value of any one or more positions input by a user is received, determining third target combination data in the combination data according to the temperature adjustment value; the third target combination data is combination data with the smallest difference between the temperature output value and the temperature regulation value in the combination data; and controlling the operation of the air conditioner according to the parameter control value of the third target combination data.
As a possible way, the method further comprises: and if the number of the plurality of combined data is larger than the preset threshold value and the combined data with the lowest evaluation value is a plurality of combined data, deleting the combined data with the earliest date in the combined data with the lowest evaluation value.
As a possible way, each of the combination data includes a temperature output value of a plurality of positions; the difference between the temperature output value and the target temperature value is the sum of the difference between the temperature value of each position of the target temperature value and the temperature output value of the corresponding position; or, the difference between the temperature adjustment value and the target temperature value is the sum of the difference between the temperature value of each position of the temperature adjustment value and the temperature output value of the corresponding position.
As a possible way, the calculation formula of the evaluation value G is as follows:
wherein, ts_i is the target temperature value of the temperature test point Ti, tm_i is the temperature output value of the temperature test point Ti, and n is the number of the temperature test points.
As a possible way, the calculation formula for updating the evaluation value G is as follows:
where z_after is an evaluation value after update, z_before is an evaluation value before update, tm "_i is an actual temperature output value of the temperature test point Ti, and α is an evaluation threshold.
As a possible way, each combination data further includes an outdoor temperature output value and an outdoor illumination output value, and the calculation formula for updating the evaluation value G is as follows:
wherein tout_m is the actual outdoor temperature, tout is the outdoor temperature output value, hm is the actual illumination quantity, H is the outdoor illumination quantity output value, F1, F2, gi are all weighting coefficients, ts_i is the target temperature value of the temperature test point Ti, tm_i is the temperature output value of the temperature test point Ti, and n is the number of the temperature test points.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program, and when the computer program is read and run by a processor, the method provided by the embodiment is realized, the same technical effect can be achieved, and the repetition is avoided, so that the description is omitted. Wherein the computer readable storage medium is selected from Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.
Of course, it will be appreciated by those skilled in the art that implementing all or part of the above-described methods in the embodiments may be implemented by a computer level to instruct a control device, where the program may be stored in a computer readable storage medium, and the program may include the above-described methods in the embodiments when executed, where the storage medium may be a memory, a magnetic disk, an optical disk, or the like.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention should be assessed accordingly to that of the appended claims.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention should be assessed accordingly to that of the appended claims.

Claims (11)

1. A method for temperature control of multiple points using machine learning, the method comprising:
acquiring a target temperature value of at least one position, and determining first target combination data in a plurality of combination data according to the target temperature value; each piece of combined data comprises a parameter control value, a temperature output value and an evaluation value, and the first target combined data is combined data with the smallest difference between the temperature output value and the target temperature value in each piece of combined data;
controlling the operation of the air conditioner according to the parameter control value of the first target combination data, and acquiring a first actual temperature output value in a stable operation state;
updating the evaluation value of the first target combination data according to the temperature output value of the first target combination data and the first actual temperature output value;
determining second target combination data in a plurality of combination data according to the target temperature value, wherein the second target combination data is combination data with small difference between a temperature output value and the target temperature value in each combination data;
calculating an average value of parameter control values of the first target combination data and the second target combination data, and controlling the operation of the air conditioner according to the average value to obtain a second actual temperature output value in a stable operation state;
determining newly added combined data according to the average value and the second actual temperature output value; and the parameter control value of the newly added combined data is the average value, the temperature output value is the second actual temperature output value, and the evaluation value is the initial evaluation value.
2. The method of claim 1, wherein the method further comprises:
and if the number of the plurality of combined data is larger than a preset threshold value, deleting the combined data with the lowest evaluation value.
3. The method of claim 2, wherein the method further comprises:
if the temperature adjustment value of any one or more positions input by a user is received, determining third target combination data in the combination data according to the temperature adjustment value; the third target combination data is combination data with the smallest difference between the temperature output value and the temperature regulation value in the combination data;
and controlling the operation of the air conditioner according to the parameter control value of the third target combination data.
4. The method of claim 2, wherein the method further comprises:
and if the number of the plurality of combined data is larger than the preset threshold value and the combined data with the lowest evaluation value is a plurality of combined data, deleting the combined data with the earliest date in the combined data with the lowest evaluation value.
5. A method according to claim 3, wherein each of said combined data includes a temperature output value for a plurality of locations;
the difference between the temperature output value and the target temperature value is the sum of the difference between the temperature value of each position of the target temperature value and the temperature output value of the corresponding position; or,
the difference between the temperature adjustment value and the target temperature value is the sum of the difference between the temperature value of each position of the temperature adjustment value and the temperature output value of the corresponding position.
6. The method according to any one of claims 1 to 5, wherein the evaluation value G is calculated as follows:
wherein, ts_i is the target temperature value of the temperature test point Ti, tm_i is the temperature output value of the temperature test point Ti, and n is the number of the temperature test points.
7. The method of claim 6, wherein the calculation formula for updating the evaluation value is as follows:
where z_after is an evaluation value after update, z_before is an evaluation value before update, tm "_i is an actual temperature output value of the temperature test point Ti, and α is an evaluation threshold.
8. The method of any one of claims 1-5, wherein each of the combination data further includes an outdoor temperature output value and an outdoor light output value, and the calculation formula for updating the evaluation value G is as follows:
wherein tout_m is the actual outdoor temperature, tout is the outdoor temperature output value, hm is the actual illumination quantity, H is the outdoor illumination quantity output value, F1, F2, gi are all weighting coefficients, ts_i is the target temperature value of the temperature test point Ti, tm_i is the temperature output value of the temperature test point Ti, and n is the number of the temperature test points.
9. An apparatus for temperature control of multiple points using machine learning, the apparatus comprising:
the first acquisition module is used for acquiring a target temperature value of at least one position and determining first target combined data in a plurality of combined data according to the target temperature value; each piece of combined data comprises a parameter control value, a temperature output value and an evaluation value, and the first target combined data is combined data with the smallest difference between the temperature output value and the target temperature value in each piece of combined data;
the first operation module is used for controlling the operation of the air conditioner according to the parameter control value of the first target combination data and obtaining a first actual temperature output value in a stable operation state;
the evaluation module is used for updating the evaluation value of the first target combination data according to the temperature output value of the first target combination data and the first actual temperature output value;
the second acquisition module is used for determining second target combined data in a plurality of combined data according to the target temperature value, wherein the second target combined data are combined data with small difference between a temperature output value and the target temperature value in the combined data;
the second running module is used for calculating the average value of the parameter control values of the first target combination data and the second target combination data, controlling the running of the air conditioner according to the average value and obtaining a second actual temperature output value in a stable running state;
the new adding module is used for determining new added combined data according to the average value and the second actual temperature output value; and the parameter control value of the newly added combined data is the average value, the temperature output value is the second actual temperature output value, and the evaluation value is the initial evaluation value.
10. A multi-split air conditioner, comprising the device for controlling temperature at multiple points by using mechanical learning and a plurality of temperature measuring devices according to claim 9;
the temperature measurer is used for measuring actual temperature output values of all the positions respectively.
11. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when read and run by a processor, implements the method according to any of claims 1-7.
CN202311229326.7A 2023-09-21 2023-09-21 Method and device for controlling temperatures of multiple points by utilizing mechanical learning and air conditioner Pending CN117366805A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311229326.7A CN117366805A (en) 2023-09-21 2023-09-21 Method and device for controlling temperatures of multiple points by utilizing mechanical learning and air conditioner

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311229326.7A CN117366805A (en) 2023-09-21 2023-09-21 Method and device for controlling temperatures of multiple points by utilizing mechanical learning and air conditioner

Publications (1)

Publication Number Publication Date
CN117366805A true CN117366805A (en) 2024-01-09

Family

ID=89401291

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311229326.7A Pending CN117366805A (en) 2023-09-21 2023-09-21 Method and device for controlling temperatures of multiple points by utilizing mechanical learning and air conditioner

Country Status (1)

Country Link
CN (1) CN117366805A (en)

Similar Documents

Publication Publication Date Title
CN110986306B (en) Method, device and equipment for adjusting room temperature based on machine learning and storage medium
JP5572799B2 (en) Air conditioning system controller
US6134511A (en) Method and apparatus for improving building energy simulations
KR20190120564A (en) Air conditioner or heat pump energy performance test apparatus and test method which can simulate time variable outdoor climate condition and indoor sensible/latent building load
KR102194002B1 (en) energy operation management system by using optimized physical learning model and machine learning methods
JP2022160989A (en) System and method for calibrating model of thermal dynamics
CN114237057A (en) Dynamic modeling method, system, equipment and medium for intelligent building electricity analysis
CN108302732A (en) Air conditioning control method and air conditioner
WO2012011401A1 (en) Output control device
TWI524293B (en) Environment control method and system thereof
CN112668224B (en) Method and system for determining optimal installation position of air-conditioning room temperature sensor
CN117366805A (en) Method and device for controlling temperatures of multiple points by utilizing mechanical learning and air conditioner
JP2001082782A (en) Airconditioning controller
CN110726216B (en) Air conditioner, control method, device and system thereof, storage medium and processor
WO2021111617A1 (en) Air-conditioning control device
KR20210077342A (en) Method and apparatus for simulating air conditioner
CN109543235B (en) Distributed electric heating load modeling system constructed based on parameter library and modeling method thereof
US20230332793A1 (en) Air conditioning control device
JP2015090232A (en) Air conditioning system, and program
CN113435031A (en) Parameter identification method and system for first-order ETP model of house to which air conditioner belongs
Basalaev et al. Enhancing room thermal comfort conditions modeling in buildings through schedule-based indicator functions for possible variable thermal perturbation inputs
Papas et al. ADREAM: Energy Consumption Optimisation through Dynamic Energetic Simulations for an Intelligent Management of Energy
CN110645687A (en) Sensor, controller, electronic device, air conditioner
JP7264359B1 (en) Heat loss coefficient estimation system, heat loss coefficient estimation method, and program
KR20230036989A (en) Method And Apparatus for Generating Thermal Simulator of Building

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