Air conditioner control method and device, air conditioner and storage medium

Abstract

The invention discloses a control method and device of an air conditioner, the air conditioner and a storage medium. The invention relates to the technical field of air conditioners, and the method comprises the steps that position information of indoor personnel is obtained, and the position information is input into a constructed first neural network forward prediction model to obtain partition information; according to the partition information, reverse optimization is carried out through a genetic algorithm to obtain internal control parameters of the air conditioner; according to the internal control parameters, obtaining partition temperatures and human body PMV values through a constructed second neural network forward prediction model; and according to the partition temperature and the human body PMV value, reverse optimization is conducted through the genetic algorithm, and operation control parameters of the air conditioner are obtained. The energy use efficiency and comfort of the air conditioner are improved.

Description

Technical Field

[0001] The present invention relates to the field of air conditioning technology, and in particular to a control method, device, air conditioner and storage medium for an air conditioner. Background Technology

[0002] As people's living standards continue to improve, their requirements for indoor environmental comfort are also increasing. Air conditioners can not only be used for indoor cooling and heating, but also improve indoor air quality, thus enhancing indoor environmental comfort.

[0003] However, existing air conditioners generally use a whole-house air supply method, which can easily lead to wasted cooling capacity in unoccupied areas, resulting in reduced energy efficiency. While air conditioners that supply air to areas where people are located can quickly improve local thermal comfort around people, they can also create an uncomfortable draft in low-temperature environments, affecting the comfort of people indoors. Summary of the Invention

[0004] This invention provides a control method, device, air conditioner, and storage medium for an air conditioner, aiming to solve the problems of low energy efficiency and low comfort in existing air conditioners.

[0005] In a first aspect, embodiments of the present invention provide a control method for an air conditioner, comprising:

[0006] The location information of people indoors is obtained, and the location information is input into the constructed first neural network positive prediction model to obtain zoning information;

[0007] Based on the partition information, the internal control parameters of the air conditioner are obtained by reverse optimization using a genetic algorithm.

[0008] Based on the internal control parameters, the zone temperature and human PMV value are obtained through a constructed second neural network positive prediction model;

[0009] The operating control parameters of the air conditioner are obtained by reverse optimization using the genetic algorithm based on the zone temperature and the human body PMV value.

[0010] Secondly, embodiments of the present invention also provide a control device for an air conditioner, comprising:

[0011] The input unit acquires the location information of people indoors and inputs the location information into the constructed first neural network positive prediction model to obtain zoning information;

[0012] The first reverse optimization unit is used to obtain the internal control parameters of the air conditioner by performing reverse optimization through a genetic algorithm based on the partition information.

[0013] The determining unit is used to obtain the zone temperature and human PMV value based on the internal control parameters through a constructed second neural network positive prediction model;

[0014] The second reverse optimization unit obtains the operating control parameters of the air conditioner by performing reverse optimization using the genetic algorithm based on the zone temperature and the human body PMV value.

[0015] Thirdly, embodiments of the present invention also provide an air conditioner including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0016] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the above-described method.

[0017] This invention provides a control method, device, air conditioner, and storage medium for an air conditioner. The method includes: acquiring the location information of occupants indoors and inputting the location information into a constructed first neural network forward prediction model to obtain zoning information; obtaining internal control parameters of the air conditioner through reverse optimization using a genetic algorithm based on the zoning information; obtaining zoning temperature and human PMV value using a constructed second neural network forward prediction model based on the internal control parameters; and obtaining the operating control parameters of the air conditioner through reverse optimization using the genetic algorithm based on the zoning temperature and the human PMV value. The technical solution of this invention first obtains the internal control parameters of the air conditioner based on the location information of indoor occupants using a first neural network forward prediction model and a genetic algorithm; then, based on the internal control parameters of the air conditioner, it obtains the zone temperature and human PMV value using a second neural network forward prediction model; finally, based on the zone temperature and human PMV value, it obtains the operating control parameters of the air conditioner using a genetic algorithm to control the operation of the air conditioner, realizing an air supply mode that supplies air to occupied areas and does not supply air to unoccupied areas, effectively avoiding the waste of cooling capacity in unoccupied areas and improving the energy efficiency of the air conditioner; and because the zone temperature and human PMV value of the indoor occupants are considered when determining the operating control parameters of the air conditioner, the comfort of the air conditioner can be effectively improved. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1This is a flowchart illustrating a control method for an air conditioner according to an embodiment of the present invention.

[0020] Figure 2 A schematic diagram illustrating the construction of a first neural network positive prediction model according to an embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of a sub-process of a control method for an air conditioner provided in an embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of another sub-process of a control method for an air conditioner provided in an embodiment of the present invention;

[0023] Figure 5 This is a schematic diagram illustrating the construction of a second neural network positive prediction model according to an embodiment of the present invention;

[0024] Figure 6 This is a schematic diagram of another sub-process of a control method for an air conditioner provided in an embodiment of the present invention;

[0025] Figure 7 A flowchart illustrating a control method for an air conditioner according to another embodiment of the present invention;

[0026] Figure 8 A simplified flowchart of a control method for an air conditioner provided in an embodiment of the present invention;

[0027] Figure 9 A schematic block diagram of a control device for an air conditioner provided in an embodiment of the present invention;

[0028] Figure 10 This is a schematic block diagram of an air conditioner provided in an embodiment of the present invention. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0031] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0032] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0033] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0034] Please see Figure 1 , Figure 1 This is a flowchart illustrating a control method for an air conditioner according to an embodiment of the present invention. The control method for the air conditioner will be described in detail below. Figure 1 As shown, the method includes the following steps S110-S140.

[0035] S110. Obtain the location information of people indoors, and input the location information into the constructed first neural network positive prediction model to obtain zoning information.

[0036] In this embodiment of the invention, the location information of indoor personnel is detected in real time by millimeter-wave radar. The location information includes the coordinates and orientation of the indoor personnel relative to the air conditioner. This location information is input as a key dynamic parameter to the first neural network positive prediction model that has been trained. The model is built on a multilayer perceptron architecture. Its input layer contains two types of parameters: the first type of parameter is a fixed room parameter, which includes the room area and the air conditioner installation position. The room area refers to the length and width of the room, and the air conditioner installation position includes installation in the center of the short side and installation on the side of the long side. The second type of parameter is the dynamic control parameter, which includes the sweep blade angle, the air guide plate angle, and the indoor fan speed. The sweep blade angle includes three types: left, center, and right. For a single-air guide plate air conditioner, the air guide plate angle refers to the angle of the large air guide plate; for a double-air guide plate air conditioner, the air guide plate angle is the angle of both the large and small air guide plates. The indoor fan speed refers to a range of values. For example, if there are three speed ranges, then M1∈(n1,n2), M2∈(n3,n4), and M3∈(n5,n6), where the values ​​of n1 to n6 depend on the specific air conditioner model. These parameters, combined with the newly added indoor occupant location information, constitute the input vector. The first neural network forward prediction model outputs zoning information at the output layer through a nonlinear mapping relationship. The zoning information includes the number of zoning zones and the zoning number of the people in the room. The number of zoning zones is obtained by predicting the air-supplying zoning layout of the room under the current air conditioner operation state based on the combination of input layer parameters (e.g., dividing the room into 3 zones: left / middle / right, or front / back 2 zones). The zoning number of the people in the room (room_i) is determined by combining the location information of the people in the room (e.g., the people in the room are located in zone room_2).

[0037] Furthermore, in this embodiment of the invention, the neural network model is trained using a first dataset that meets the selected criteria, and the hyperparameters are automatically optimized using Keras-Tuner and Bayesian optimization to complete the model training. Specifically, the step of training the neural network model using the first dataset that meets the criteria to obtain the first neural network positive prediction model includes: constructing the first dataset that meets the criteria and dividing the first dataset into a training dataset and a validation dataset; defining the structure of the neural network model using Keras-Tuner and setting the hyperparameters of the neural network model to the search space of Bayesian optimization; training the neural network model using the training dataset and evaluating its performance on the validation dataset to determine the optimal hyperparameter combination through a probabilistic model; configuring the neural network model using the optimal hyperparameter combination and training the configured neural network model on the first dataset to obtain the first neural network positive prediction model. It's important to note that Keras-Tuner is an automated tool for optimizing the hyperparameters of neural networks (such as the number of hidden layers, neurons, and learning rate). It offers various search strategies, including RandomSearch, Bayesian Optimization, Hyperband (resource-based efficient search), and SklearnSearch (ensemble search). Keras-Tuner supports Bayesian optimization, which uses a probabilistic model to predict hyperparameter performance and efficiently search for the optimal combination, reducing manual trial and error. This significantly improves model training efficiency and accuracy. Please refer to [link to relevant documentation]. Figure 2 , Figure 2 This is a schematic diagram illustrating the construction of a first neural network positive prediction model provided in an embodiment of the present invention.

[0038] Furthermore, in this embodiment of the invention, the selection of the first dataset must meet certain conditions: First, rooms of different sizes are selected and partitioned, and each partition is labeled room_i. The air sweeping blade angle, air guide plate angle, and indoor fan speed of the air conditioner are adjusted to achieve multiple combinations of internal control parameters for the air conditioner. When the air conditioner operates at a specific parameter combination (including the air sweeping blade angle, air guide plate angle, and indoor fan speed range), the wind speed room_Vi at a height h (h = 1.2~1.6m) of each partition needs to be measured at multiple points. If the average wind speed Vi of any measured partition at that height section is ≥3m / s, it is determined that the current parameter combination can achieve effective air supply to that partition, and the complete set of operating data will be included in the first dataset. The entire process of storing the first dataset can be carried out simultaneously through experiments or simulations. To facilitate understanding, let's illustrate with an example: For a room with area A, the air conditioner is installed on the short wall, dividing the room into three zones: room_1, room_2, and room_3. When the air sweeper blades are pointing to the left, the angle of the large air guide plate is N2, the angle of the small air guide plate is N1, and the internal fan speed is within the range of (n1, n2), the air velocity V1 in zone room_1 is ≥ 3 m / s. This parameter combination, for example: (A, installed in the center of the short side, air sweeping to the left, N2 / N1, (n1, n2), V1, three zones (left, center, and right), is a valid set of training data and is included in the first dataset.

[0039] S120. Based on the partition information, the internal control parameters of the air conditioner are obtained by reverse optimization using a genetic algorithm.

[0040] In embodiments of the present invention, such as Figure 3As shown, step S120 may include steps S121-S122: S121, obtaining first constraints, wherein the first constraints include the room area and the installation location of the air conditioner; S122, obtaining the internal control parameters of the air conditioner by reverse optimization using the genetic algorithm based on the first constraints and the partition information. Specifically, fixed room parameters are obtained as the first constraints: room area and air conditioner installation location. The fixed room parameters, as immutable physical boundaries, together with the dynamically input partition information, constitute the input information for reverse optimization of the genetic algorithm. At this stage, the genetic algorithm starts the optimization engine and iteratively filters parameter combinations within a preset search space by simulating biological evolution mechanisms (selection, crossover, mutation). Its core objective is to reverse-solve the internal control parameters of the air conditioner, wherein the internal control parameters include the sweep blade angle, the guide vane angle, and the internal fan speed range, while strictly satisfying the zoned air supply effectiveness constraints (e.g., the wind speed in the zone where indoor occupants are located ≥3m / s) and energy-saving comfort indicators. During the optimization process, the algorithm prioritizes evaluating the impact of parameter combinations on the reachability of zoned air supply (e.g., ensuring that the airflow intensity of the room_i zone meets the standard), and dynamically adjusts the weights to balance cooling efficiency and the need for protection against direct airflow to people (e.g., limiting the angle of the air guide vanes at low temperatures). The final output internal control parameters are fed back to the air conditioner's control system in real time, driving the hardware to execute directional air supply, achieving the core closed-loop control of energy saving in unoccupied areas and comfort in occupied areas.

[0041] S130. Based on the internal control parameters, the zone temperature and human PMV value are obtained through the constructed second neural network positive prediction model.

[0042] In this embodiment of the invention, PMV (Predicted Mean Vote) is a comprehensive evaluation index for human thermal comfort, also known as the predicted average thermal sensation voting index. It is an index used to assess human thermal comfort, and a value between (-0.5, 0.5) indicates that the human body is in a state of thermal comfort. Figure 4As shown, step S130 may include steps S131-S132: S131, obtaining the environmental parameters, human body parameters, and external control parameters of the air conditioner at the current moment, wherein the environmental parameters include outdoor temperature and indoor temperature, the human body parameters include human metabolic rate, and the external control parameters include outdoor fan speed, compressor frequency, and valve opening; S132, inputting the internal control parameters, the environmental parameters, the human body parameters, and the external control parameters into the constructed second neural network positive prediction model to obtain the current zone temperature and the human body PMV value. It should be noted that indoor and outdoor temperatures are collected through indoor and outdoor temperature monitoring devices. Indoor temperature is obtained through multi-zone indoor temperature monitoring devices. Human metabolic rate is collected through infrared monitoring devices; for example, it is approximately 1.0 MET when sitting and approximately 2.0 MET when walking. This parameter directly affects the human body's sensitivity to the thermal environment. The outdoor fan speed, compressor frequency, and valve opening together constitute the main control variables of air conditioning power consumption. Internal control parameters, environmental parameters, human body parameters, and external control parameters are integrated into a multi-dimensional feature vector, which is input into the constructed second neural network positive prediction model. This model, through a deep nonlinear mapping relationship, simultaneously outputs zone temperature, human body PMV value, and air conditioning power. It should also be noted that a PMV meter, power monitoring device, and thermocouple temperature measuring device need to be installed in the room. The PMV meter is used to monitor human body PMV values ​​in real time, ensuring that the value is within the comfortable range of (-0.5, 0.5). The power monitoring device collects the power of the air conditioner. The thermocouple temperature measuring device collects the indoor temperature in different zones.

[0043] Further, in this embodiment of the invention, the step of training a neural network model using a qualified second dataset to obtain a second neural network positive prediction model includes: constructing a qualified second dataset and dividing it into a training dataset and a validation dataset; defining the structure of the neural network model using Keras-Tuner and setting the hyperparameters of the neural network model to a Bayesian optimization search space; training the neural network model using the training dataset and evaluating its performance on the validation dataset to determine the optimal hyperparameter combination through a probabilistic model; configuring the neural network model using the optimal hyperparameter combination and training the configured neural network model on the second dataset to obtain the second neural network positive prediction model. It should be noted that the collection process of the second dataset is relatively simple; data collection is completed by monitoring the data throughout the entire process. It should also be noted that... (See also...) Figure 5 , Figure 5 This is a schematic diagram illustrating the construction of a second neural network positive prediction model provided in an embodiment of the present invention.

[0044] S140. Based on the zone temperature and the human body PMV value, the operating control parameters of the air conditioner are obtained by reverse optimization using the genetic algorithm.

[0045] In embodiments of the present invention, such as Figure 6 As shown, step S140 may include steps S141-S143: S141, obtaining a set temperature and calculating the sum of the set temperature and the preset temperature value to obtain a partition temperature threshold; S142, if the partition temperature at the current moment is not less than the partition temperature threshold, then according to the obtained second constraint, the genetic algorithm is used to perform reverse optimization to obtain the operating control parameters of the air conditioner at the next moment, wherein the second constraint includes the indoor fan speed, partition temperature, and power of the air conditioner at the next moment; S143, if the partition temperature at the current moment is less than the partition temperature threshold, then according to the human body PMV value at the current moment and the obtained third constraint, the genetic algorithm is used to perform reverse optimization to obtain the operating control parameters of the air conditioner at the next moment. It should be noted that, in this embodiment, the third constraint includes the indoor fan speed at the next moment, the power of the air conditioner, and the human body PMV value. The human body PMV value at the next moment is determined based on the human body PMV value at the current moment. Specifically, if the human body PMV value at the current moment is greater than a preset PMV value, the human body PMV value at the next moment is the current human body PMV value minus the preset PMV reduction value; if the human body PMV value at the current moment is not greater than the preset PMV value, the human body PMV value at the next moment is within the preset PMV range. It should also be noted that, in this embodiment, the operating control parameters include the indoor fan speed, the outdoor fan speed, the compressor frequency, and the valve opening degree.

[0046] For ease of understanding, the implementation process of steps S141-S143 is explained in detail below: Assume that based on the current outdoor ambient temperature T_out(t), indoor ambient temperature T_in(t), human metabolic rate M, indoor fan speed Mi(t), outdoor fan speed R_out(t), compressor frequency P(t), and valve opening K(t), the current room zone temperature room_Ti(t) and human PMV value PMV(t) are predicted by the second neural network forward prediction model. Then, it is determined whether the current zone temperature room_Ti(t) is greater than or equal to the zone temperature threshold, where the zone temperature threshold is the set temperature T. 设定+5℃. If the zone temperature is greater than or equal to the zone temperature threshold, it indicates that the area where the personnel are located is a high-temperature environment. The zone temperature is set as the control object. Through reverse optimization using a genetic algorithm, the outdoor control parameters of the air conditioner at the next moment (t+1) that satisfy the following second constraints are obtained: ① Indoor fan speed Mi(t+1)∈[n1,n2]; ② Room zone temperature room_Ti(t+1)=room_Ti(t)-0.1℃; ③ The power of the air conditioner W(t+1) takes the minimum value. If the zone temperature is lower than the zone temperature threshold, it indicates that the area where the person is located is in a low-temperature environment. Further lowering the temperature may cause discomfort from the airflow. In this case, the PMV value of the human body is taken as the control object. The third constraint condition for the genetic algorithm to solve in reverse is: ① The internal fan speed Mi(t+1)∈[n1,n2]; ② When PMV(t)≥0.5, PMV(t+1)=PMV(t)-0.1; when PMV(t)<0.5, PMV(t+1)∈(-0.5,+0.5); ③ The power W(t+1) of the air conditioner takes the minimum value. Understandably, the internal fan speed Mi(t+1), external fan speed Rout(t+1), compressor speed P(t+1), and valve opening K(t+1) obtained at time (t+1) through reverse optimization are fed back to the control system for cyclic control.

[0047] Figure 7 A flowchart illustrating a control method for an air conditioner according to another embodiment of the present invention is shown below. Figure 7 As shown, in this embodiment, the method includes steps S110-S180. That is, in this embodiment, after step S140 in the above embodiment, the method further includes steps S150-S180.

[0048] S150. If no end-of-run instruction is received, then execute the step of obtaining the location information of people indoors;

[0049] S160. Detect whether the location information has changed;

[0050] S170. If the location information has not changed, then execute the step of obtaining the zone temperature and human PMV value based on the internal control parameters through the constructed second neural network positive prediction model.

[0051] S180. If the location information changes, then the step of inputting the location information into the first neural network positive prediction model to obtain the partition information is executed.

[0052] In this embodiment, if no end-of-operation command is received, the location information of indoor occupants is reacquired via millimeter-wave radar, and it is determined whether this location has changed compared to the previous cycle. If the location of the occupants has not changed, the current internal control parameters are maintained. Based on the internal control parameters combined with real-time collected indoor and outdoor environmental data, human metabolic rate, and external control parameters, the second neural network forward prediction model is invoked to calculate and output the temperature of the current occupant's zone and the human PMV value, which are used for subsequent comfort assessment and energy-saving control. If a change in the occupant's location is detected, the new location information is immediately input into the first neural network forward prediction model to re-predict and determine the zone information corresponding to the occupant's new location. This triggers a genetic algorithm to perform reverse optimization again to solve for new internal control parameters, which in turn determine the air conditioner's operating control parameters, ensuring that occupants receive comfortable airflow in any location. Please refer to [link to relevant documentation]. Figure 8 , Figure 8 A simplified flowchart of an air conditioner control method provided in an embodiment of the present invention.

[0053] In summary, the air conditioner control method in this embodiment achieves a room air supply mode of zoned air supply in occupied areas and no air supply in unoccupied areas through forward prediction of the first neural network forward prediction model and the second neural network forward prediction model and inverse solution of the genetic algorithm. This can effectively avoid the waste of cooling capacity in unoccupied areas. At the same time, it enables directional air supply for rapid cooling in occupied rooms under high temperature conditions and ensures that the PMV value of the human body is in the thermal comfort range under low temperature conditions.

[0054] Figure 9 This is a schematic block diagram of a control device 200 for an air conditioner provided in an embodiment of the present invention. Figure 9 As shown, corresponding to the above-described air conditioner control method, the present invention also provides an air conditioner control device 200. This air conditioner control device 200 includes a unit for executing the above-described air conditioner control method, and the device can be configured in an air conditioner. Specifically, please refer to... Figure 9 The control device 200 of the air conditioner includes an input acquisition unit 201, a first reverse optimization unit 202, a determination unit 203, and a second reverse optimization unit 204. Detailed descriptions of each functional module are as follows:

[0055] The input unit 201 acquires the location information of people indoors and inputs the location information into the constructed first neural network positive prediction model to obtain zoning information;

[0056] The first reverse optimization unit 202 is used to obtain the internal control parameters of the air conditioner by performing reverse optimization through a genetic algorithm based on the partition information.

[0057] The determining unit 203 is used to obtain the zone temperature and human PMV value based on the internal control parameters through a constructed second neural network positive prediction model;

[0058] The second reverse optimization unit 204 obtains the operating control parameters of the air conditioner by performing reverse optimization through the genetic algorithm based on the zone temperature and the human body PMV value.

[0059] In some embodiments, such as this one, the first reverse optimization unit 202 is specifically used for:

[0060] Obtain the first constraint, wherein the first constraint includes the room area and the installation location of the air conditioner;

[0061] The internal control parameters of the air conditioner are obtained by reverse optimization using the genetic algorithm based on the first constraint and the partition information.

[0062] In some embodiments, such as this one, the determining unit 203 is specifically used for:

[0063] The system acquires environmental parameters, human body parameters, and external control parameters of the air conditioner at the current moment. The environmental parameters include outdoor temperature and indoor temperature, the human body parameters include human metabolic rate, and the external control parameters include outdoor fan speed, compressor frequency, and valve opening.

[0064] The second neural network positive prediction model is constructed by inputting the internal control parameters, the environmental parameters, the human body parameters, and the external control parameters to obtain the current zone temperature and the human body PMV value.

[0065] In some embodiments, such as this one, the second reverse optimization unit 204 is specifically used for:

[0066] Obtain the set temperature and calculate the sum of the set temperature and the preset temperature value to obtain the zone temperature threshold;

[0067] If the current zone temperature is not less than the zone temperature threshold, then the operating control parameters of the air conditioner at the next moment are obtained by reverse optimization through the genetic algorithm based on the obtained second constraint. The second constraint includes the indoor fan speed, zone temperature and power of the air conditioner at the next moment.

[0068] If the zone temperature at the current moment is less than the zone temperature threshold, then the operating control parameters of the air conditioner at the next moment are obtained by reverse optimization through the genetic algorithm based on the human body PMV value at the current moment and the obtained third constraint condition. The third constraint condition includes the indoor fan speed, the power of the air conditioner and the human body PMV value at the next moment. The human body PMV value at the next moment is determined based on the human body PMV value at the current moment.

[0069] In some embodiments, such as this one, the control device 200 of the air conditioner further includes:

[0070] The first execution unit is configured to execute the step of obtaining the location information of indoor personnel if no end-of-run instruction is received.

[0071] A detection unit is used to detect whether the location information has changed;

[0072] The second execution unit is used to execute the step of obtaining the partition temperature and human PMV value based on the internal control parameters through the constructed second neural network positive prediction model if the location information has not changed.

[0073] The third execution unit is used to execute the step of inputting the location information into the first neural network positive prediction model to obtain partition information if the location information changes.

[0074] The control device for the aforementioned air conditioner can be implemented as a computer program, which can, for example... Figure 10 The air conditioner shown is running.

[0075] Please see Figure 10 , Figure 10 This is a schematic block diagram of an air conditioner provided in an embodiment of the present invention. The air conditioner 300 is a device that can improve energy efficiency and comfort.

[0076] See Figure 10 The air conditioner 300 includes a processor 302, a memory, and a network interface 305 connected via a system bus 301. The memory may include a non-volatile storage medium 303 and internal memory 304.

[0077] The non-volatile storage medium 303 may store an operating system 3031 and a computer program 3032. When the computer program 3032 is executed, it causes the processor 302 to execute a control method for an air conditioner.

[0078] The processor 302 is used to provide computing and control capabilities to support the operation of the entire air conditioner 300.

[0079] The internal memory 304 provides an environment for the operation of the computer program 3032 in the non-volatile storage medium 303. When the computer program 3032 is executed by the processor 302, the processor 302 can execute a control method for an air conditioner.

[0080] This network interface 305 is used for network communication with other devices. Those skilled in the art will understand that... Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the air conditioner 300 to which the present invention is applied. A specific air conditioner 300 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0081] The processor 302 is used to run a computer program 3032 stored in a memory to implement any embodiment of the control method for the air conditioner described above.

[0082] It should be understood that, in this embodiment of the invention, the processor 302 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0083] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0084] Therefore, the present invention also provides a storage medium. This storage medium may be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to perform any embodiment of the control method for the air conditioner described above.

[0085] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0086] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0087] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0088] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0089] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an air conditioner to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0090] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0091] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0092] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A control method for an air conditioner, characterized in that, include: The location information of people indoors is obtained, and the location information is input into the constructed first neural network positive prediction model to obtain zoning information; Based on the partition information, the internal control parameters of the air conditioner are obtained by reverse optimization using a genetic algorithm. Based on the internal control parameters, the zone temperature and human PMV value are obtained through a constructed second neural network positive prediction model; The operating control parameters of the air conditioner are obtained by reverse optimization using the genetic algorithm based on the zone temperature and the human body PMV value, so as to control the operation of the air conditioner.

2. The method according to claim 1, characterized in that, The steps of training a neural network model using a first dataset / second dataset that meets the conditions to obtain a first neural network positive prediction model / second neural network positive prediction model include: Construct the first dataset / second dataset that meets the conditions, and divide the first dataset / second dataset into a training dataset and a validation dataset; The structure of the neural network model is defined using Keras-Tuner, and the hyperparameters of the neural network model are set to the Bayesian optimization search space; The neural network model is trained using the training dataset and its performance is evaluated on the validation dataset to determine the optimal combination of hyperparameters using a probabilistic model. The neural network model is configured using the optimal hyperparameter combination, and the configured neural network model is trained on the first dataset / second dataset to obtain the first neural network positive prediction model / second neural network positive prediction model.

3. The method according to claim 1, characterized in that, The step of obtaining the internal control parameters of the air conditioner by reverse optimization using a genetic algorithm based on the partition information includes: Obtain the first constraint, wherein the first constraint includes the room area and the installation location of the air conditioner; The internal control parameters of the air conditioner are obtained by reverse optimization using the genetic algorithm based on the first constraint and the partition information.

4. The method according to claim 1, characterized in that, The step of obtaining the zone temperature and human PMV value based on the internal control parameters through a constructed second neural network positive prediction model includes: The system acquires environmental parameters, human body parameters, and external control parameters of the air conditioner at the current moment. The environmental parameters include outdoor temperature and indoor temperature, the human body parameters include human metabolic rate, and the external control parameters include outdoor fan speed, compressor frequency, and valve opening. The second neural network positive prediction model is constructed by inputting the internal control parameters, the environmental parameters, the human body parameters, and the external control parameters to obtain the current zone temperature and the human body PMV value.

5. The method according to claim 4, characterized in that, The step of obtaining the operating control parameters of the air conditioner by reverse optimization using the genetic algorithm based on the zone temperature and the human body PMV value includes: Obtain the set temperature and calculate the sum of the set temperature and the preset temperature value to obtain the zone temperature threshold; If the current zone temperature is not less than the zone temperature threshold, then the operating control parameters of the air conditioner at the next moment are obtained by reverse optimization through the genetic algorithm based on the obtained second constraint. The second constraint includes the indoor fan speed, zone temperature and power of the air conditioner at the next moment. If the zone temperature at the current moment is less than the zone temperature threshold, then the operating control parameters of the air conditioner at the next moment are obtained by reverse optimization through the genetic algorithm based on the human body PMV value at the current moment and the obtained third constraint condition.

6. The method according to claim 5, characterized in that, The third constraint includes the indoor fan speed at the next moment, the power of the air conditioner, and the human body PMV value, wherein the human body PMV value at the next moment is determined based on the human body PMV value at the current moment.

7. The method according to claim 5, characterized in that, The method further includes: If no end-of-run command is received, then proceed with the step of obtaining the location information of people indoors; Detect whether the location information has changed; If the location information has not changed, then the step of obtaining the zone temperature and human PMV value based on the internal control parameters through the constructed second neural network positive prediction model is executed; If the location information changes, the step of inputting the location information into the first neural network positive prediction model to obtain the partition information is executed.

8. A control device for an air conditioner, characterized in that, include: The input unit acquires the location information of people indoors and inputs the location information into the constructed first neural network positive prediction model to obtain zoning information; The first reverse optimization unit is used to obtain the internal control parameters of the air conditioner by performing reverse optimization through a genetic algorithm based on the partition information. The determining unit is used to obtain the zone temperature and human PMV value based on the internal control parameters through a constructed second neural network positive prediction model; The second reverse optimization unit obtains the operating control parameters of the air conditioner by performing reverse optimization using the genetic algorithm based on the zone temperature and the human body PMV value.

9. An air conditioner, characterized in that, The air conditioner includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the method as described in any one of claims 1-7.

Images