Air conditioner control method and device and electronic equipment

Abstract

The application discloses an air conditioner control method, device and electronic equipment. The method comprises the following steps: acquiring a first dry-bulb temperature and a first wet-bulb temperature of an evaporator inlet of an air conditioner at a first time, and an operating parameter of the air conditioner at the first time; determining a sensible cooling capacity and a latent cooling capacity of the air conditioner at a second time according to the first dry-bulb temperature, the first wet-bulb temperature and the operating parameter of the air conditioner at the first time; performing operation on the sensible cooling capacity and the latent cooling capacity at the second time by using a first transfer function and a second transfer function, so as to obtain a second dry-bulb temperature and a second wet-bulb temperature of the air conditioner at the second time; and determining the operating parameter of the air conditioner at the second time according to the second dry-bulb temperature and the second wet-bulb temperature. The application solves the technical problem of insufficient adjustment accuracy when the operating parameter of the air conditioner is adjusted in the related art due to the fact that the dry-bulb temperature and the wet-bulb temperature of the air conditioner cannot be calculated separately in the related art.

Description

Technical Field

[0001] This application relates to the field of air conditioning technology, and more specifically, to an air conditioning control method, device, and electronic device. Background Technology

[0002] The sensible and latent cooling capacities of a direct expansion air conditioner are affected by factors such as fan speed, compressor speed, evaporator inlet dry-bulb temperature, and evaporator inlet wet-bulb temperature. Traditional methods for determining air conditioner operating parameters based on dry-bulb and wet-bulb temperatures cannot calculate these temperatures separately, resulting in insufficient precision in adjusting the operating parameters of the air conditioner in related technologies.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides an air conditioning control method, device, and electronic device to at least solve the technical problem of insufficient adjustment accuracy when adjusting the operating parameters of an air conditioner due to the inability to calculate the dry-bulb temperature and wet-bulb temperature of the air conditioner separately in related technologies.

[0005] According to one aspect of the embodiments of this application, an air conditioning control method is provided, comprising: acquiring a first dry-bulb temperature and a first wet-bulb temperature at the evaporator inlet of an air conditioner at a first moment, and the operating parameters of the air conditioner at the first moment; determining the sensible cooling capacity and latent cooling capacity of the air conditioner at a second moment based on the first dry-bulb temperature, the first wet-bulb temperature, and the operating parameters of the air conditioner at the first moment, wherein the second moment is after the first moment; calculating the sensible cooling capacity at the second moment using a first transfer function to obtain the second dry-bulb temperature of the air conditioner at the second moment, and calculating the sensible cooling capacity and latent cooling capacity at the second moment using a second transfer function to obtain the second wet-bulb temperature of the air conditioner at the second moment, wherein the first transfer function is used to represent the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature; and determining the operating parameters of the air conditioner at the second moment based on the second dry-bulb temperature and the second wet-bulb temperature.

[0006] Optionally, the first transfer function and the second transfer function are determined by: determining the spatial volume of the target space where the air conditioner is located; collecting the first environmental parameters of the target space at a preset frequency, and collecting the output parameters of the air conditioner; and determining the first transfer function and the second transfer function based on the spatial volume, the first environmental parameters, and the output parameters.

[0007] Optionally, the operating parameters include the air conditioner's fan speed and compressor speed. The operating parameters of the air conditioner at a second moment are determined based on the second dry-bulb temperature and the second wet-bulb temperature, including: when the second dry-bulb temperature equals the first preset dry-bulb temperature and the second wet-bulb temperature equals the first preset wet-bulb temperature, determining that the air conditioner's fan speed and compressor speed at the second moment are equal to the air conditioner's fan speed and compressor speed at the first moment; when the second dry-bulb temperature is not equal to the first preset dry-bulb temperature, or the second wet-bulb temperature is not equal to the first preset wet-bulb temperature, adjusting the air conditioner's fan speed and compressor speed until the second dry-bulb temperature equals the first preset dry-bulb temperature and the second wet-bulb temperature equals the first preset wet-bulb temperature, and determining the fan speed and compressor speed at the time when the second dry-bulb temperature equals the first preset dry-bulb temperature and the second wet-bulb temperature equals the first preset wet-bulb temperature as the air conditioner's fan speed and compressor speed at the second moment.

[0008] Optionally, adjusting the air conditioner's fan speed and compressor speed until the second dry-bulb temperature equals the first preset dry-bulb temperature and the second wet-bulb temperature equals the first preset wet-bulb temperature includes the following steps: First, adjusting the air conditioner's fan speed and compressor speed; Second, determining the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment based on the adjusted fan speed and compressor speed, as well as the first dry-bulb temperature and the first wet-bulb temperature; Third, determining the second dry-bulb temperature corresponding to the adjusted fan speed and compressor speed based on the first transfer function and the sensible cooling capacity at the second moment, and determining the second wet-bulb temperature corresponding to the adjusted fan speed and compressor speed based on the second transfer function; Fourth, if the second dry-bulb temperature corresponding to the adjusted fan speed and compressor speed equals the first preset dry-bulb temperature and the second wet-bulb temperature corresponding to the adjusted fan speed and compressor speed equals the first preset wet-bulb temperature, determining the adjusted fan speed and compressor speed as the fan speed and compressor speed at the second moment; otherwise, skipping to the first step.

[0009] Optionally, the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment are determined based on the first dry-bulb temperature, the first wet-bulb temperature and the operating parameters of the air conditioner at the first moment, including: processing the first dry-bulb temperature and the first wet-bulb temperature through a target prediction model to obtain the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment, wherein the target prediction model is a reinforcement learning model.

[0010] Optionally, the target prediction model is trained as follows: The initial operating parameters of the air conditioner and the training dataset are determined. The training data in the training dataset includes multiple sets of dry-bulb and wet-bulb temperatures at different times, as well as the standard latent cooling capacity and standard sensible cooling capacity corresponding to the dry-bulb and wet-bulb temperatures at each time point. The standard latent cooling capacity and standard sensible cooling capacity are the latent cooling capacity and sensible cooling capacity when the dry-bulb and wet-bulb temperatures in the target space where the air conditioner is located are adjusted to the second preset dry-bulb temperature and the second preset wet-bulb temperature. The initial operating parameters and the training data in the training dataset are processed by the model to be trained to obtain the predicted latent cooling capacity and the predicted sensible cooling capacity. The predicted latent cooling capacity and the standard latent cooling capacity are compared, as are the predicted sensible cooling capacity and the standard sensible cooling capacity, to obtain the comparison results. The model parameters of the model to be trained are adjusted based on the comparison results to obtain the target prediction model.

[0011] Optionally, the model parameters of the model to be trained can be adjusted based on the comparison results, including: adjusting the model parameters of the model to be trained when the comparison results show that the predicted latent cooling amount is not equal to the standard latent cooling amount, or the predicted sensible cooling amount is not equal to the standard sensible cooling amount; and determining the processing time required for the model to be trained to output the predicted latent cooling amount and the predicted sensible cooling amount when the comparison results show that the predicted latent cooling amount is equal to the standard latent cooling amount and the predicted sensible cooling amount is equal to the standard sensible cooling amount, and adjusting the model parameters of the model to be trained when the processing time is not less than a preset time.

[0012] According to another aspect of the embodiments of this application, an air conditioning control device is also provided, comprising: an acquisition module, configured to acquire a first dry-bulb temperature and a first wet-bulb temperature at the evaporator inlet of the air conditioner at a first moment, and the operating parameters of the air conditioner at the first moment; a first determination module, configured to determine the sensible cooling capacity and latent cooling capacity of the air conditioner at a second moment based on the first dry-bulb temperature, the first wet-bulb temperature and the operating parameters of the air conditioner at the first moment, wherein the second moment is after the first moment; a calculation module, configured to calculate the sensible cooling capacity at the second moment using a first transfer function to obtain the second dry-bulb temperature of the air conditioner at the second moment, and to calculate the sensible cooling capacity and latent cooling capacity at the second moment using a second transfer function to obtain the second wet-bulb temperature of the air conditioner at the second moment, wherein the first transfer function is used to represent the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature; and a second determination module, configured to determine the operating parameters of the air conditioner at the second moment based on the second dry-bulb temperature and the second wet-bulb temperature.

[0013] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory for storing program instructions; and a processor connected to the memory for executing program instructions to perform the following functions: acquiring a first dry-bulb temperature and a first wet-bulb temperature at the evaporator inlet of an air conditioner at a first moment, and the operating parameters of the air conditioner at the first moment; determining the sensible cooling capacity and latent cooling capacity of the air conditioner at a second moment based on the first dry-bulb temperature, the first wet-bulb temperature, and the operating parameters of the air conditioner at the first moment, wherein the second moment is after the first moment; calculating the sensible cooling capacity at the second moment using a first transfer function to obtain the second dry-bulb temperature of the air conditioner at the second moment, and calculating the sensible cooling capacity and latent cooling capacity at the second moment using a second transfer function to obtain the second wet-bulb temperature of the air conditioner at the second moment, wherein the first transfer function is used to represent the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature; and determining the operating parameters of the air conditioner at the second moment based on the second dry-bulb temperature and the second wet-bulb temperature.

[0014] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored computer program, wherein the device containing the non-volatile storage medium executes the above-described air conditioning control method by running the computer program.

[0015] In this embodiment, the first dry-bulb temperature and the first wet-bulb temperature at the evaporator inlet of the air conditioner at a first moment, as well as the operating parameters of the air conditioner at the first moment, are obtained. Based on the first dry-bulb temperature, the first wet-bulb temperature, and the operating parameters of the air conditioner at the first moment, the sensible cooling capacity and latent cooling capacity of the air conditioner at a second moment are determined, wherein the second moment is after the first moment. A first transfer function is used to calculate the sensible cooling capacity at the second moment to obtain the second dry-bulb temperature of the air conditioner at the second moment, and a second transfer function is used to calculate the sensible cooling capacity and latent cooling capacity at the second moment to obtain the second wet-bulb temperature of the air conditioner at the second moment. The first transfer function is used to represent the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature. Based on the second dry-bulb temperature and the second wet-bulb temperature, the operating parameters of the air conditioner at the second moment are determined, thereby achieving the purpose of separately determining the dry-bulb temperature and the wet-bulb temperature of the air conditioner. This achieves the technical effect of improving the control accuracy of the operating parameters of the air conditioner, and solves the technical problem of insufficient adjustment accuracy when adjusting the operating parameters of the air conditioner in related technologies due to the inability to separately calculate the dry-bulb temperature and the wet-bulb temperature of the air conditioner. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing an air conditioning control method according to an embodiment of this application;

[0018] Figure 2 This is a flowchart illustrating an air conditioning control method according to an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of a first transfer function according to an embodiment of this application;

[0020] Figure 4 This is a schematic diagram of a second transfer function according to an embodiment of this application;

[0021] Figure 5 This is a schematic diagram of the architecture of a target prediction model according to an embodiment of this application;

[0022] Figure 6 This is a schematic flowchart of an air conditioning control process according to an embodiment of this application;

[0023] Figure 7 This is a schematic diagram of the training process of a prediction program according to an embodiment of this application;

[0024] Figure 8 This is a schematic diagram of an initial stage dry bulb temperature change curve according to an embodiment of this application;

[0025] Figure 9 This is a schematic diagram of an initial stage wet-bulb temperature change curve according to an embodiment of this application;

[0026] Figure 10 This is a schematic diagram of a dry-bulb temperature change curve during a continuous operation phase according to an embodiment of this application;

[0027] Figure 11 This is a schematic diagram of a wet-bulb temperature change curve during continuous operation according to an embodiment of this application;

[0028] Figure 12 This is a schematic diagram of the structure of an air conditioning control device according to an embodiment of this application. Detailed Implementation

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

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] First, some nouns or terms that appear in the explanation of the embodiments of this application shall be interpreted as follows:

[0032] Sensible cooling capacity: Sensible cooling capacity, also known as sensible heat, refers to the amount of heat absorbed or released by an object during the process of absorbing or releasing heat, which only increases or decreases the kinetic energy of the object's molecules, even if the temperature of the substance rises or falls, without any change in the state of the substance.

[0033] Latent cooling capacity: This refers to the amount of cooling capacity caused by the condensation of moisture in the air due to low temperature. Because a phase change occurs, i.e. from gaseous to liquid, this portion of cooling capacity is called latent cooling capacity.

[0034] Enthalpy: The enthalpy of air refers to the total energy of a given mass of air under specific conditions. It includes the internal energy of the air and the contribution of pressure-volume work. The internal energy of air is the sum of the kinetic and potential energy of air molecules, and is related to temperature. Pressure-volume work refers to the work done when the air undergoes a volume change, and is related to both pressure and volume changes. In common engineering applications, the enthalpy of air is often used to calculate the energy changes during the heating or cooling of air. Knowing the initial and final states of air temperature, pressure, and humidity, the enthalpy of air can be determined by consulting tables or using calculation software.

[0035] Reinforcement learning involves an agent and an execution environment. The agent continuously learns and optimizes its policy through interaction and feedback with the execution environment. Specifically, the agent observes and obtains the state of the execution environment, and based on a certain policy, determines the action to be taken in response to the current state. This action acts on the execution environment, changing its state and generating feedback to the agent, known as a reward. The agent uses the reward score to determine whether the previous action was correct and whether the policy needs adjustment, thus updating its policy accordingly. By repeatedly observing the state, determining actions, and receiving feedback, the agent can continuously update its policy, with the ultimate goal of learning a policy that maximizes the accumulated reward score. This is the typical reinforcement learning process. If the agent uses deep learning algorithms, including neural networks, during the learning and policy adjustment process, such a system is called a deep reinforcement learning system.

[0036] With societal development, cleanrooms, specialized laboratories, high-end hotels, and other locations are increasingly demanding constant temperature and humidity conditions. For direct expansion air conditioners, the sensible and latent cooling capacities are affected by factors such as fan speed, compressor speed, evaporator inlet dry-bulb temperature, and evaporator inlet wet-bulb temperature. In related technologies, to control the air conditioning parameters of direct expansion air conditioners and maintain constant temperature and humidity conditions, an air conditioning model is typically established to predict the dry-bulb and wet-bulb temperatures. However, building such a model involves considering numerous variables, making it difficult to construct. Conversely, considering only the primary variables leads to a loss of model accuracy. Furthermore, since dry-bulb and wet-bulb temperatures are two interdependent variables, this method cannot achieve independent control of either temperature.

[0037] To achieve separate regulation of dry-bulb and wet-bulb temperatures, related technologies also control the airflow and temperature at the air conditioner inlet, and comprehensively consider the specific heat capacity and density of indoor air, thereby adjusting the dry-bulb and wet-bulb temperatures output by the air conditioner to achieve separate control of the dry-bulb and wet-bulb temperatures. However, this method is only based on theoretical calculations and does not take into account the mutual interference between dry-bulb and wet-bulb temperatures in actual scenarios, resulting in insufficient accuracy after regulation.

[0038] To address this problem, this application provides an air conditioning control method, which can operate in... Figure 1 The computer terminal shown is described in detail below.

[0039] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1A hardware structure block diagram of a computer terminal for implementing an air conditioning control method is shown. Figure 1 As shown, the computer terminal 100 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data (including program instructions and data storage devices), and a transmission module 106 for communication functions (capable of wired and / or wireless network connections). In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, the computer terminal 100 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0040] The aforementioned computer terminal can be a device in the air conditioner to be adjusted, or a third-party device that operates independently of the air conditioner. For the former, considering the cost and the complexity of hardware implementation, it can be implemented using the existing memory or controller in the air conditioner. For the latter, it can be a remote control device adapted to the air conditioner, or a mobile terminal or other device that supports the control of the air conditioner (for example, an APP for controlling the air conditioner is installed on the mobile terminal).

[0041] In addition, when using the aforementioned computer terminal to control the air conditioner, considering hardware costs, one processor can be used to execute all control processes. Alternatively, from the perspective of operational efficiency, the control process for the air conditioner can be divided according to function, and different functions can be assigned to different processors for execution. For example, in the embodiments of this application, the main design idea is to first use the temperature and humidity transfer function to determine the dry and wet bulb temperatures of the air conditioner at the next moment, then use a reinforcement learning model to predict the sensible and latent cooling capacity at the next moment, and finally adjust the operating parameters of the air conditioner based on parameters such as the sensible and latent cooling capacity at the next moment and the sensible and latent cooling capacity at the current moment. In this case, the calculation function of the temperature and humidity transfer function and the prediction function of the reinforcement learning model can be assigned to different processors to run, so as to improve operational efficiency.

[0042] In the above operating environment, this application provides an embodiment of an air conditioning control method. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0043] Figure 2 This is a flowchart of an air conditioning control method according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0044] Step S202: Obtain the first dry-bulb temperature and the first wet-bulb temperature at the evaporator inlet of the air conditioner at the first moment, as well as the operating parameters of the air conditioner at the first moment;

[0045] Step S204: Determine the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment based on the first dry-bulb temperature, the first wet-bulb temperature and the operating parameters of the air conditioner at the first moment, wherein the second moment is after the first moment;

[0046] Step S206: The sensible cooling capacity at the second moment is calculated using the first transfer function to obtain the second dry-bulb temperature of the air conditioner at the second moment; and the sensible cooling capacity and latent cooling capacity at the second moment are calculated using the second transfer function to obtain the second wet-bulb temperature of the air conditioner at the second moment. The first transfer function is used to represent the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature.

[0047] Step S208: Determine the operating parameters of the air conditioner at the second moment based on the second dry-bulb temperature and the second wet-bulb temperature.

[0048] In steps S202 to S208 above, based on the idea of ​​controlling the dry-bulb temperature and wet-bulb temperature of the room (as described in the target space below) separately, and combined with the influence of the sensible cooling capacity and latent cooling capacity output by the air conditioner (or air conditioning system) on the indoor dry-bulb temperature and wet-bulb temperature, a feedforward neural network model is constructed. According to the actual situation of the indoor air conditioner and the target dry-bulb temperature and target wet-bulb temperature, various operating parameters of the air conditioning system are adjusted. For example, the fan speed and compressor speed of the air conditioning system are adjusted to counteract the mutual influence of the dry-bulb temperature and wet-bulb temperature, so as to achieve separate control of the dry-bulb temperature and wet-bulb temperature.

[0049] Specifically, this embodiment of the application obtains the first dry-bulb temperature and the first wet-bulb temperature at the evaporator inlet of the air conditioner at a first moment, as well as the operating parameters of the air conditioner at the first moment; determines the sensible cooling capacity and latent cooling capacity of the air conditioner at a second moment based on the first dry-bulb temperature, the first wet-bulb temperature, and the operating parameters of the air conditioner at the first moment, wherein the second moment is after the first moment; calculates the sensible cooling capacity at the second moment using a first transfer function to obtain the second dry-bulb temperature of the air conditioner at the second moment, and calculates the sensible cooling capacity and latent cooling capacity at the second moment using a second transfer function to obtain the second wet-bulb temperature of the air conditioner at the second moment, wherein the first transfer function is used to represent the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature; determines the operating parameters of the air conditioner at the second moment based on the second dry-bulb temperature and the second wet-bulb temperature, thereby achieving the purpose of separately determining the dry-bulb temperature and the wet-bulb temperature of the air conditioner, thus realizing the technical effect of improving the control accuracy of the operating parameters of the air conditioner, and solving the technical problem of insufficient adjustment accuracy when adjusting the operating parameters of the air conditioner due to the inability to separately calculate the dry-bulb temperature and the wet-bulb temperature of the air conditioner in related technologies. The steps described above are explained in detail below.

[0050] In the above air conditioning control method, the first transfer function and the second transfer function are determined by: determining the spatial volume of the target space where the air conditioner is located; collecting the first environmental parameters of the target space at a preset frequency, and collecting the output parameters of the air conditioner; and determining the first transfer function and the second transfer function based on the spatial volume, the first environmental parameters, and the output parameters.

[0051] In this embodiment of the application, according to the principle of energy balance, the rate of change of sensible heat in the target space (e.g., the target room) due to the change in dry-bulb temperature is equal to the sensible heat generated in the target space per unit time minus the sensible heat eliminated per unit time. The sensible heat balance equation is shown in the following formula (1):

[0052]

[0053] In the above formula (1), t n,d The dry-bulb temperature of the air in the target space (i.e., t as described below) d ), in °C; t s,d The unit is the dry-bulb temperature of the air supply air of the air conditioner, in °C; L is the air volume of the air conditioner, in m³ / s. 3 / s;Q S ρ represents the sensible heat (or sensible cold) of the target space, in kW; ρ represents the air density of the target space, in kg / m³. 3 V represents the spatial volume of the target space, in meters. 3 C pτ represents the specific heat capacity of air in the target space, expressed in kJ / ℃·kg, where τ is the temperature.

[0054] By further analyzing the above formula (1), considering the sensible cooling (or sensible heating) Q output by the air conditioner... S The dry bulb temperature t in the target space d The response has a certain delay, therefore, formula (1) can be transformed to obtain the following: Figure 3 As shown, with sensible heat Q S The general expression for the first transfer function G1(s), which serves as the excitation and the dry-bulb temperature in the target space as the response, should be noted. It should be understood that the dry-bulb temperature of the target space can be interpreted as the dry-bulb temperature output by the air conditioner to the target space, i.e., the dry-bulb temperature at the evaporator inlet of the air conditioner. The general expression for the first transfer function G1(s) is shown in the following formula (2):

[0055]

[0056] In the above formula (2), K1 represents the gain, with units of ℃ / kW. In an optional embodiment, K1 can be determined by the parameters in formula (1), for example, by the spatial volume V of the target space, the first environmental parameters (including air density ρ, air specific heat capacity C) p The output parameters of the air conditioner (including the air volume L) are determined, τ1 is the time lag coefficient in seconds, and T1 is the time constant in seconds. Therefore, the corresponding dry-bulb temperature can be obtained based on the sensible cooling capacity.

[0057] When determining the second transfer function, according to the law of energy balance, the total heat accumulated in the target space per unit time is equal to the total heat flowing into the target space per unit time minus the total heat flowing out of the target space per unit time. The total heat balance calculation formula is shown in formula (3) below:

[0058]

[0059] In the above formula (3), i is the enthalpy of air, in kJ / kg; n Let i be the energy content per unit mass of air at the wet-bulb temperature in the target space (i.e., i as described below). s Q represents the energy content per unit mass of air at the wet-bulb temperature of the air supply air in an air conditioner. l This represents the latent heat (or latent cold) of the target space, expressed in kW. Other parameters can be found in the explanation of the parameters in the first transfer function above, and will not be repeated here.

[0060] Similar to the transfer model of the first transfer function corresponding to the dry-bulb temperature mentioned above, the above formula (3) can be transformed to obtain the following: Figure 4 As shown, the sensible cooling capacity QS and latent cooling capacity Q l As an excitation, the general expression for the second transfer function G2(s) of the response, which takes the enthalpy value in the target space as the response, is shown in the following formula (4):

[0061]

[0062] Wherein, K2 represents the gain, with units of ℃ / kW. In an optional embodiment, K2 can be determined by the parameters in formula (3), for example, by the spatial volume V of the target space, the first environmental parameters (including air density ρ, and the energy content i of a unit mass of air at the wet-bulb temperature in the target space). n Energy content per unit mass of air at the wet-bulb temperature of the air supply air in an air conditioner (i) s The output parameters of the air conditioner (including the air volume L) are determined, τ2 is the time lag coefficient in seconds, and T2 is the time constant in seconds. Therefore, the corresponding indoor enthalpy value can be obtained based on the sensible cooling capacity and the latent cooling capacity.

[0063] Within the range of air conditioning, under a certain atmospheric pressure, the wet-bulb temperature t w It can be approximated as a single-valued function of enthalpy i, that is, t w =f(i). The wet-bulb temperature and enthalpy values ​​at multiple state points are queried, and the following empirical formula (5) is obtained through fitting:

[0064] t w =-0.0023i 2 +0.5512i-4.1674 (5)

[0065] Through the above formulas (3)-(5), it can be seen that the wet-bulb temperature of the target space is affected by the total heat (latent heat + sensible heat), and the change of enthalpy of the state point in the target space can be obtained by the change of the total heat in the time domain. Then, based on the enthalpy, the wet-bulb temperature of the state point in the target space can be calculated by the above empirical formula (5).

[0066] In the above-mentioned air conditioning control method, the operating parameters include the fan speed and compressor speed of the air conditioner. The operating parameters of the air conditioner at the second moment are determined based on the second dry-bulb temperature and the second wet-bulb temperature, specifically including the following steps: when the second dry-bulb temperature is equal to the first preset dry-bulb temperature and the second wet-bulb temperature is equal to the first preset wet-bulb temperature, the fan speed and compressor speed of the air conditioner at the second moment are determined to be equal to the fan speed and compressor speed of the air conditioner at the first moment; when the second dry-bulb temperature is not equal to the first preset dry-bulb temperature, or the second wet-bulb temperature is not equal to the first preset wet-bulb temperature, the fan speed and compressor speed of the air conditioner are adjusted until the second dry-bulb temperature is equal to the first preset dry-bulb temperature and the second wet-bulb temperature is equal to the first preset wet-bulb temperature, and the fan speed and compressor speed when the second dry-bulb temperature is equal to the first preset dry-bulb temperature and the second wet-bulb temperature are equal to the first preset wet-bulb temperature are determined as the fan speed and compressor speed of the air conditioner at the second moment.

[0067] In this embodiment, the second dry-bulb temperature and the second wet-bulb temperature are the dry-bulb temperature and wet-bulb temperature corresponding to when the air conditioner is adjusted to a preset temperature. The dry-bulb temperature and wet-bulb temperature corresponding to the preset temperature are also the aforementioned first preset dry-bulb temperature and first preset wet-bulb temperature. For example, if the dry-bulb temperature of the air conditioner needs to be adjusted to 25°C and the wet-bulb temperature needs to be adjusted to 15°C, then 25°C is the aforementioned first preset dry-bulb temperature and 15°C is the aforementioned first preset wet-bulb temperature. When the second dry-bulb temperature and the second wet-bulb temperature of the air conditioner at the second moment are equal to the aforementioned first preset dry-bulb temperature and first preset wet-bulb temperature, that is, when the air conditioner is adjusted to the desired dry-bulb temperature and wet-bulb temperature, the fan speed and compressor speed of the air conditioner at the previous moment (i.e., the aforementioned first moment) are determined as the fan speed and compressor speed of the air conditioner at the second moment. If the air conditioner fails to reach the first preset dry-bulb temperature and the first preset wet-bulb temperature, the fan speed and compressor speed of the air conditioner need to be adjusted until the dry-bulb temperature of the air conditioner reaches the first preset dry-bulb temperature and the wet-bulb temperature reaches the first preset wet-bulb temperature. The fan speed and compressor speed at which the first preset dry-bulb temperature and the first preset wet-bulb temperature are met are then determined as the operating parameters of the air conditioner at the second moment.

[0068] In the above air conditioning control method, the step of adjusting the air conditioner's fan speed and compressor speed until the second dry-bulb temperature equals the first preset dry-bulb temperature and the second wet-bulb temperature equals the first preset wet-bulb temperature includes: First, adjusting the air conditioner's fan speed and compressor speed; Second, determining the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment based on the adjusted fan speed and compressor speed, as well as the first dry-bulb temperature and the first wet-bulb temperature; Third, determining the second dry-bulb temperature corresponding to the adjusted fan speed and compressor speed based on the first transfer function and the sensible cooling capacity at the second moment, and determining the second wet-bulb temperature corresponding to the adjusted fan speed and compressor speed based on the second transfer function; Fourth, if the second dry-bulb temperature corresponding to the adjusted fan speed and compressor speed equals the first preset dry-bulb temperature and the second wet-bulb temperature corresponding to the adjusted fan speed and compressor speed equals the first preset wet-bulb temperature, determining the adjusted fan speed and compressor speed as the fan speed and compressor speed at the second moment; otherwise, jumping back to the first step.

[0069] In this embodiment, during the above process, the target prediction model (referring to the ANN model in this embodiment) obtains the air conditioner's fan speed, compressor speed (or adjusted air conditioner fan speed and compressor speed), first dry-bulb temperature, and first wet-bulb temperature, and outputs the sensible cooling capacity and latent cooling capacity of the air conditioner. The sensible cooling capacity and latent cooling capacity are the same as the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment. The sensible cooling capacity output by the target prediction model is input into the first transfer function to obtain the second dry-bulb temperature. The sensible cooling capacity and latent cooling capacity output by the target prediction model are input into the second transfer function to obtain the second wet-bulb temperature. It is determined whether the second dry-bulb temperature obtained by the first transfer function meets the first preset dry-bulb temperature, and whether the second wet-bulb temperature obtained by the second transfer function meets the second preset wet-bulb temperature. If the corresponding first preset dry-bulb temperature and first preset wet-bulb temperature are met, the operating parameters of the air conditioner at this time are determined to be the air conditioner's fan speed and compressor speed (or adjusted air conditioner fan speed and compressor speed) obtained above. Otherwise, continue adjusting the air conditioner's operating parameters until the air conditioner is adjusted to the first preset dry-bulb temperature and the first preset wet-bulb temperature through the above steps.

[0070] In the above air conditioning control method, the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment are determined based on the first dry-bulb temperature, the first wet-bulb temperature and the operating parameters of the air conditioner at the first moment. This includes: processing the first dry-bulb temperature and the first wet-bulb temperature through a target prediction model to obtain the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment. The target prediction model is a reinforcement learning model.

[0071] In the above steps, the target prediction model is trained as follows: The initial operating parameters and training dataset of the air conditioner are determined. The training data in the training dataset includes multiple sets of dry-bulb and wet-bulb temperatures at different times, as well as the standard latent cooling capacity and standard sensible cooling capacity corresponding to the dry-bulb and wet-bulb temperatures at each time point. The standard latent cooling capacity and standard sensible cooling capacity are the latent cooling capacity and sensible cooling capacity when the dry-bulb and wet-bulb temperatures in the target space where the air conditioner is located are adjusted to the second preset dry-bulb temperature and the second preset wet-bulb temperature. The initial operating parameters and training data in the training dataset are processed by the model to be trained to obtain the predicted latent cooling capacity and predicted sensible cooling capacity. The predicted latent cooling capacity and standard latent cooling capacity are compared, as are the predicted sensible cooling capacity and standard sensible cooling capacity, to obtain the comparison results. Based on the comparison results, the model parameters of the model to be trained are adjusted to obtain the target prediction model.

[0072] In the above steps, the model parameters of the model to be trained are adjusted according to the comparison results, including: adjusting the model parameters of the model to be trained when the comparison result is that the predicted latent cooling amount is not equal to the standard latent cooling amount, or the predicted sensible cooling amount is not equal to the standard sensible cooling amount; and determining the processing time required for the model to be trained to output the predicted latent cooling amount and the predicted sensible cooling amount when the comparison result is that the predicted latent cooling amount is equal to the standard latent cooling amount and the predicted sensible cooling amount is equal to the standard sensible cooling amount, and adjusting the model parameters of the model to be trained when the processing time is not less than the preset time.

[0073] In the embodiments of this application, the target prediction model described above can be any reinforcement learning model, such as an ANN model. In some embodiments of this application, the architecture of the target prediction model is as follows: Figure 5 As shown, it includes multiple convolutional layers. Additionally, from... Figure 5 As can be seen from the data, the input to this model is the operating parameters of the air conditioner (including fan speed C and compressor speed F), based on the dry-bulb temperature t at the evaporator inlet of the air conditioner. d and wet-bulb temperature t w The output is the sensible cooling capacity Q required by the air conditioning system to adjust the dry-bulb and wet-bulb temperatures in the target space to the target values. s and latent cooling capacity Q l .

[0074] As an alternative implementation, 80% of the data in the dataset can be selected as training data, and the remaining 20% ​​of the data can be used as detection data to train the ANN model.

[0075] In this embodiment, under different air conditions at the evaporator inlet, in order to adjust the dry-bulb and wet-bulb temperatures in the target space to preset dry-bulb and wet-bulb temperatures (i.e., the aforementioned first preset dry-bulb temperature or first preset wet-bulb temperature), the sensible and latent cooling capacities output by the combination of the air conditioner's fan speed and compressor speed are also different, as shown in Table 1 below. Table 1 shows the dry-bulb and wet-bulb temperatures corresponding to the air conditioner evaporator inlet air condition acquisition points, and Table 2 shows the combination of the air conditioner's fan speed and compressor speed. Data with the same serial number are corresponding data.

[0076] Table 1

[0077]

[0078] Table 2

[0079]

[0080] In summary, the air conditioning control method provided in this application embodiment is as follows: Figure 6 As shown, the first dry-bulb temperature t at the evaporator inlet of the air conditioner at the first moment is obtained. d (t) and the first wet-bulb temperature t w (t), and the operating parameters of the air conditioner at the first moment, including fan speed C(t) and compressor speed F(t); using the target prediction model (i.e. Figure 6 The ANN model in the model determines the sensible cooling capacity Q of the air conditioner at the second time step based on the first dry-bulb temperature, the first wet-bulb temperature, and the operating parameters of the air conditioner at the first time step. s ′(t) and latent cooling Q l ′(t), where the second moment is after the first moment; it should be noted that the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment are used to calculate the dry-bulb temperature and wet-bulb temperature of the air conditioner at the second moment. In an optional embodiment, since the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment are determined by the operating parameters at the first moment, as well as the first dry-bulb temperature and the first wet-bulb temperature at the first moment, the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment can also be referred to as the sensible cooling capacity and latent cooling capacity of the air conditioner at the first moment.

[0081] The sensible cooling capacity at the second time moment is calculated using the first transfer function G1(s), and the second dry-bulb temperature t of the air conditioner at the second time moment is obtained. d (t+1), and the sensible and latent cooling at the second time step (i.e., Q′) using the second transfer function G2(s). total (t)=Q′ s (t)+Q l The calculation is performed using ′(t) to obtain the second wet-bulb temperature t of the air conditioner at the second time point. w(t+1), where the first transfer function represents the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function represents the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature; the operating parameters of the air conditioner at the second moment are determined based on the second dry-bulb temperature and the second wet-bulb temperature, and the above steps are repeated until the air conditioner is adjusted to the first preset dry-bulb temperature and the first preset wet-bulb temperature, thereby achieving the purpose of separately determining the dry-bulb temperature and wet-bulb temperature of the air conditioner, thus realizing the technical effect of improving the control accuracy of the operating parameters of the air conditioner, and thus solving the technical problem of insufficient adjustment accuracy when adjusting the operating parameters of the air conditioner due to the inability to separately calculate the dry-bulb temperature and wet-bulb temperature of the air conditioner in related technologies.

[0082] In this embodiment of the application, during the training of the target prediction model, three module files written using an object-oriented approach are required: AC_env.py, RL_brain.py, and interface.py. Here, AC_env.py represents the air conditioning interaction program, RL_brain.py represents the agent decision-making program, and interface.py represents the interface display program.

[0083] As an optional implementation, the main function of the aforementioned air conditioning interaction program is to provide feedback on environmental monitoring parameters and reward values, and to create an `envs()` class based on these parameters and reward values. Specifically, the air conditioning interaction program first receives the air conditioner's status and actions from the previous moment (i.e., the first moment mentioned above), sums them to calculate the status for the next moment (i.e., the second moment mentioned above); secondly, it calls the target prediction model (which can be saved as an h5 file) to predict the sensible and latent cooling output of the air conditioner for the next moment; finally, it transmits the prediction results to the transfer function module in Simlink (including the first and second transfer functions) via the User Datagram Protocol (UDP) to calculate the dry-bulb and wet-bulb temperatures. The module returns the dry-bulb and wet-bulb temperatures and the reward value.

[0084] For example, a class named `envs()` can be created to represent an environment. Initialization operations are performed in the `__init__()` function of this environment class, such as defining the action space, initial state, dry-bulb and wet-bulb temperatures, and identifying the target space model. Then, in the `reset` function, a reset operation is performed to restore the environment to its initial state and return this initial state. In the `step` function, the agent's decision action and the current state are received as input. Based on the agent's decision action and the current state, the state for the next moment is calculated. The room model is used to predict the temperature for the next moment, and the reward value is calculated based on the difference between the predicted temperature and the target temperature, and this reward value is returned.

[0085] The above process describes the initialization of an environment class and the basic flow of the `step` function, used to simulate the environment and calculate reward values. Specific implementation details need to be adjusted and implemented according to the specific problem and environment.

[0086] RL_brain.py, as the agent decision-making program, primarily constructs a decision-making system by adding and retrieving rows from the q-table, and selects control actions based on the q-value corresponding to the current state. The q-table is a QLearningTable() class created within the module, used to implement decision rules based on the Q-learning algorithm. Specifically, it may include the following parts:

[0087] 1. `__init__(self,…)`: Initializes an instance of the `QLearningTable` class. This method first allocates memory for a `q` table to store the Q-values ​​of state-action pairs. It also initializes algorithm parameters, specifically the learning rate, reward decay coefficient, and greedy coefficient.

[0088] 2. `choose_action(self,…)`: Selects a control action based on the current state. This method takes the current state as input and selects a control action according to a decision rule. The specific implementation of the decision rule can be based on a relevant model established according to the actual environmental conditions. For example, first, a transfer function model of the indoor dry-bulb and wet-bulb temperatures can be established based on the actual indoor conditions. Then, based on a pre-established sensible and latent cooling capacity prediction model, the sensible and latent cooling capacity that the air conditioner needs to output to achieve the target dry-bulb and wet-bulb temperatures can be determined. The selected control action will be the return value of the method.

[0089] 3. `learn(self,…)`: Learns based on the current state and the selected control action. This method takes the current state and the selected control action as input and learns according to the decision rule. The specific learning algorithm can be based on the Q-learning algorithm, updating the corresponding Q-values ​​in the Q-table based on the current state and the control action. The return value of the method can be the new control action obtained after learning.

[0090] 4. check_state_exist(self,…): Checks if the current state point exists in q_table. This method takes the current state as input and checks if the state point already exists in q_table. If it does not exist, it adds the state point to q_table.

[0091] The above process implements a QLearningTable class, providing methods for selecting control actions and learning, which includes a q-table to store the Q-values ​​of state-action pairs. Specific decision rules and learning algorithms need to be implemented and adjusted according to the actual situation.

[0092] `interface.py` is the visualization interface module. It uses Tkinter to generate a dynamic interface that displays changes in control components during training, allowing for parameter adjustment and the discovery of local optima. The visualization interface generation process involves, for example, calling the parent class `Tk`'s initialization method in the initialization method to create a dynamic graph of the air conditioner's fan and compressor speeds, and then creating the control interface based on this graph. Next, in the `step` method, the current state value is received, and the points on the dynamic graph are updated accordingly. In the `reset` method, the environment is reset to its initial state. Finally, in the `render` method, the environment is updated and rendered, thus generating the visualization interface.

[0093] By using the above programs, including AC_env.py, RL_brain.py, and interface.py, the target prediction model can be trained. The corresponding training process is as follows: Figure 7 As shown, the specific steps include the following:

[0094] The first step is to set the q table to null and set the fan starting speed of the direct expansion air conditioner to 50% of the maximum speed and the compressor starting speed to 50% of the maximum speed. The initial state s is {50,50}.

[0095] The second step is to pass the current state to the agent, make the agent decision, call the choose_action() function in the RL_brain.py module, use the decision control as the state increment of the current time, and obtain the state of the next time step;

[0096] The third step is to pass the state of the next moment into the air-conditioned room model (such as the target space model mentioned above), call the AC_env.py module to get the temperature of the next moment, and calculate the reward value. For example, use the reward function to calculate the reward value.

[0097] The fourth step is to call the learning() function of the RL_brain.py module, pass the current state, state increment, next state, and reward value to the agent, and update the q table;

[0098] Fifth step: Determine if the temperature at the next moment is the set temperature. If yes, proceed to the sixth step. If no, record the state at the next moment as the state at the current moment and repeat the trial and error process.

[0099] Step 6: Determine if the temperature tracking time has converged. If yes, the training ends; otherwise, return the current state to the initial state and repeat the next loop. It should be noted that the temperature tracking time in this step can be, for example, the time it takes for the program to derive the operating parameters of the air conditioner corresponding to the preset dry-bulb and wet-bulb temperatures. Convergence refers to the temperature within the temperature tracking time meeting the preset conditions (e.g., the set temperature) and remaining in a stable state (e.g., unchanged), or the temperature within a preset number of consecutive temperature tracking times meeting the preset conditions and remaining in a stable state.

[0100] After training, save the q-table as a CSV file for later use. Since the air conditioner setting temperature and the q-table training termination condition correspond one-to-one, the path to save the q-table needs to include a temperature identification marker, such as '… / aim_temp(24,20).csv'.

[0101] In this embodiment of the application, the simulation operation mode specifically includes the following steps:

[0102] The first step is to determine the q table and the current status of the air conditioner. At this point, the q table is a saved CSV file.

[0103] The second step is to pass the current state to the agent, call the choose_action() function in the RL_brain.py module, use the decision control as the state increment of the current time step, and obtain the state of the next time step.

[0104] The third step is to pass the next moment's state into the target space model, call the AC_env.py module to obtain the temperature at the next moment, and use the reward function to calculate the reward value.

[0105] The fourth step is to call the learning() function of the RL_brain.py module, pass the current state, state increment, next state, and reward value to the agent, update the q table, and then jump to the second step.

[0106] As can be seen from the above steps, this operating mode will be continuously executed in a loop to ensure that the dry-bulb temperature and wet-bulb temperature in the target space are always maintained at a stable value.

[0107] To further demonstrate how the air conditioning control method provided in this application can regulate the dry-bulb and wet-bulb temperatures in a target space in practical application scenarios, the following simulation experiments are provided in some embodiments of this application:

[0108] Specifically, the initial temperature settings in the target space for the simulation experiment were a dry-bulb temperature of 25℃ and a wet-bulb temperature of 15℃. The experimental simulation scenario involved changing the set dry-bulb and wet-bulb temperatures to 20.8℃ and 10.1℃ respectively, and maintaining them at the set temperatures (t). d =20.8℃,t w =10.1℃).

[0109] The changes in dry bulb temperature in the initial stage are as follows: Figure 8 As shown, the wet-bulb temperature changes as follows: Figure 9 As shown, the temperature adjustment process ends when the temperature falls within ±3% of the set value. The system adapts to changes in the set dry-bulb temperature in approximately 176 seconds, and to changes in the set wet-bulb temperature in approximately 3256 seconds. It can be seen that after adopting the air conditioning control method provided in this application, both dry-bulb and wet-bulb temperatures converge rapidly in the initial stage of adjustment. The agent's experience learning makes the adjustment process rapid and without overshoot.

[0110] Because in the experiment, the dry-bulb temperature difference term |t in the excitation signal d -t d_set The coefficient of | is 2, and the wet-bulb temperature difference term |t w -t w_set The coefficient of | is 1, indicating that the variable controlled by the reward term with a larger coefficient converges faster. Further analysis of the dry-bulb and wet-bulb temperature simulation curves reveals that the control variable corresponding to the reward term with a smaller coefficient fluctuates less frequently. Given that in daily use, air conditioners prioritize cooling speed over dehumidification, the cooling speed can be increased by appropriately amplifying the dry-bulb temperature difference term.

[0111] Figure 10 This describes the dry-bulb temperature variation under long-term control using the air conditioning control method provided in this application. Figure 11This describes the wet-bulb temperature variation under long-term control using the air conditioning control method provided in this application. It can be seen that the wet-bulb temperature fluctuates over a larger range, resulting in a smoother curve and a lower fluctuation frequency; the dry-bulb temperature fluctuates over a smaller range, with more drastic temperature changes and a higher fluctuation frequency. During a test period of 40,000 s, the maximum dynamic deviation of the dry-bulb temperature was 6.7%, and the maximum dynamic deviation of the wet-bulb temperature was 21.9%. Furthermore, due to the dry-bulb temperature difference term |t in the reward signal... d -t d_set The coefficient of | is 2, and the wet-bulb temperature difference term |t w -t w_set The coefficient of | is 1. This shows that the variable controlled by the reward item with the larger coefficient is more likely to remain stable within a smaller range around the set value, with a higher frequency of fluctuation.

[0112] Figure 12 This is a structural diagram of an air conditioning control device according to an embodiment of this application, such as... Figure 12 As shown, the device includes:

[0113] The acquisition module 32 is used to acquire the first dry-bulb temperature and the first wet-bulb temperature at the evaporator inlet of the air conditioner at the first moment, as well as the operating parameters of the air conditioner at the first moment.

[0114] The first determining module 34 is used to determine the sensible cooling capacity and latent cooling capacity of the air conditioner at the second moment based on the first dry-bulb temperature, the first wet-bulb temperature and the operating parameters of the air conditioner at the first moment, wherein the second moment is after the first moment;

[0115] The calculation module 36 is used to calculate the sensible cooling capacity at the second moment using a first transfer function to obtain the second dry-bulb temperature of the air conditioner at the second moment, and to calculate the sensible cooling capacity and latent cooling capacity at the second moment using a second transfer function to obtain the second wet-bulb temperature of the air conditioner at the second moment. The first transfer function is used to represent the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature.

[0116] The second determining module 38 is used to determine the operating parameters of the air conditioner at the second moment based on the second dry-bulb temperature and the second wet-bulb temperature.

[0117] Figure 12 The air conditioning control device shown is used to perform Figure 2 The air conditioning control method shown above is also applicable to this air conditioning control device, and will not be repeated here.

[0118] It should be noted that each module in the above-mentioned air conditioning control device can be a program module (for example, a set of program instructions to implement a certain function) or a hardware module. For the latter, it can be manifested in the following forms, but is not limited to these: each of the above modules is manifested as a processor, or the functions of each of the above modules are implemented by a processor.

[0119] This application embodiment also provides an electronic device, including: a memory for storing program instructions; and a processor connected to the memory for executing program instructions to perform the following functions: acquiring a first dry-bulb temperature and a first wet-bulb temperature at the evaporator inlet of an air conditioner at a first moment, and the operating parameters of the air conditioner at the first moment; determining the sensible cooling capacity and latent cooling capacity of the air conditioner at a second moment based on the first dry-bulb temperature, the first wet-bulb temperature, and the operating parameters of the air conditioner at the first moment, wherein the second moment is after the first moment; calculating the sensible cooling capacity at the second moment using a first transfer function to obtain the second dry-bulb temperature of the air conditioner at the second moment, and calculating the sensible cooling capacity and latent cooling capacity at the second moment using a second transfer function to obtain the second wet-bulb temperature of the air conditioner at the second moment, wherein the first transfer function represents the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function represents the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature; and determining the operating parameters of the air conditioner at the second moment based on the second dry-bulb temperature and the second wet-bulb temperature.

[0120] It should be noted that the aforementioned electronic equipment is used to perform Figure 2 The air conditioning control method shown above is also applicable to this electronic device, and will not be repeated here.

[0121] This application embodiment also provides a non-volatile storage medium, which includes a stored computer program. The device containing the non-volatile storage medium executes the following air conditioning control method by running the computer program: acquiring the first dry-bulb temperature and the first wet-bulb temperature at the evaporator inlet of the air conditioner at a first moment, and the operating parameters of the air conditioner at the first moment; determining the sensible cooling capacity and latent cooling capacity of the air conditioner at a second moment based on the first dry-bulb temperature, the first wet-bulb temperature, and the operating parameters of the air conditioner at the first moment, wherein the second moment is after the first moment; calculating the sensible cooling capacity at the second moment using a first transfer function to obtain the second dry-bulb temperature of the air conditioner at the second moment, and calculating the sensible cooling capacity and latent cooling capacity at the second moment using a second transfer function to obtain the second wet-bulb temperature of the air conditioner at the second moment, wherein the first transfer function represents the functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function represents the functional relationship between the sensible cooling capacity and the latent cooling capacity of the air conditioner and the wet-bulb temperature; and determining the operating parameters of the air conditioner at the second moment based on the second dry-bulb temperature and the second wet-bulb temperature.

[0122] It should be noted that the aforementioned non-volatile storage media is used for execution. Figure 2 The air conditioning control method shown above is also applicable to this non-volatile storage medium, and will not be repeated here.

[0123] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An air conditioner control method characterized by comprising: The method comprises: acquiring a first dry-bulb temperature and a first wet-bulb temperature of an evaporator inlet of an air conditioner at a first time, and an operating parameter of the air conditioner at the first time; determining sensible cooling capacity and latent cooling capacity of the air conditioner at a second time according to the first dry-bulb temperature, the first wet-bulb temperature and the operating parameter of the air conditioner at the first time, wherein the second time is after the first time; performing operation on the sensible cooling capacity at the second time by using a first transfer function to obtain a second dry-bulb temperature of the air conditioner at the second time, and performing operation on the sensible cooling capacity and the latent cooling capacity at the second time by using a second transfer function to obtain a second wet-bulb temperature of the air conditioner at the second time, wherein the first transfer function is used to represent a functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent a functional relationship between the sensible cooling capacity and the latent cooling capacity and the wet-bulb temperature of the air conditioner; determining the operating parameter of the air conditioner at the second time according to the second dry-bulb temperature and the second wet-bulb temperature.

2. The air conditioner control method according to claim 1, characterized by, The first transfer function and the second transfer function are determined by: determining a space volume of a target space in which the air conditioner is located; acquiring a first environmental parameter of the target space and an output parameter of the air conditioner at a preset frequency; determining the first transfer function and the second transfer function according to the space volume, the first environmental parameter and the output parameter.

3. The air conditioner control method according to claim 1, characterized by, The operating parameter comprises a fan rotating speed and a compressor rotating speed of the air conditioner, and the determination of the operating parameter of the air conditioner at the second time according to the second dry-bulb temperature and the second wet-bulb temperature comprises: in a case where the second dry-bulb temperature is equal to a first preset dry-bulb temperature and the second wet-bulb temperature is equal to a first preset wet-bulb temperature, determining that the fan rotating speed and the compressor rotating speed of the air conditioner at the second time are equal to the fan rotating speed and the compressor rotating speed of the air conditioner at the first time; in a case where the second dry-bulb temperature is not equal to the first preset dry-bulb temperature or the second wet-bulb temperature is not equal to the first preset wet-bulb temperature, adjusting the fan rotating speed and the compressor rotating speed of the air conditioner until the second dry-bulb temperature is equal to the first preset dry-bulb temperature and the second wet-bulb temperature is equal to the first preset wet-bulb temperature, and determining the fan rotating speed and the compressor rotating speed at the time when the second dry-bulb temperature is equal to the first preset dry-bulb temperature and the second wet-bulb temperature is equal to the first preset wet-bulb temperature as the fan rotating speed and the compressor rotating speed of the air conditioner at the second time.

4. The air conditioner control method according to claim 3, characterized by, The step of adjusting the fan rotating speed and the compressor rotating speed of the air conditioner until the second dry-bulb temperature is equal to the first preset dry-bulb temperature and the second wet-bulb temperature is equal to the first preset wet-bulb temperature comprises: a first step of adjusting the fan rotating speed and the compressor rotating speed of the air conditioner; a second step of determining the sensible cooling capacity and the latent cooling capacity of the air conditioner at the second time according to the adjusted fan rotating speed and the compressor rotating speed of the air conditioner, and the first dry-bulb temperature and the first wet-bulb temperature. In the third step, a second dry-bulb temperature corresponding to the adjusted fan rotating speed and the adjusted compressor rotating speed of the air conditioner is determined according to the sensible heat release and the second time point and according to the second transfer function, and a second wet-bulb temperature corresponding to the adjusted fan rotating speed and the adjusted compressor rotating speed of the air conditioner is determined according to the sensible heat release and the latent heat release at the second time point and according to the second transfer function; In the fourth step, if the second dry-bulb temperature corresponding to the adjusted fan rotating speed and the adjusted compressor rotating speed of the air conditioner is equal to the first preset dry-bulb temperature, and the second wet-bulb temperature corresponding to the adjusted fan rotating speed and the adjusted compressor rotating speed of the air conditioner is equal to the first preset wet-bulb temperature, it is determined that the adjusted fan rotating speed and the adjusted compressor rotating speed of the air conditioner are the fan rotating speed and the compressor rotating speed at the second time point, otherwise, the first step is jumped to.

5. The air conditioner control method according to claim 1, characterized by, The second time point sensible heat release and the second time point latent heat release are determined according to the first dry-bulb temperature, the first wet-bulb temperature and the working parameters of the air conditioner at the first time point, including: The first dry-bulb temperature and the first wet-bulb temperature are processed by a target prediction model, so as to obtain the second time point sensible heat release and the second time point latent heat release, wherein the model type of the target prediction model is a reinforcement learning model.

6. The air conditioner control method according to claim 5, characterized by, The target prediction model is obtained by training in the following way: An initial working parameter of the air conditioner and a training data set are determined, wherein the training data in the training data set includes a plurality of groups of dry-bulb temperature and wet-bulb temperature at different time points, and standard latent heat release and standard sensible heat release corresponding to the dry-bulb temperature and the wet-bulb temperature at each time point, wherein the standard latent heat release and the standard sensible heat release are the latent heat release and the sensible heat release when the dry-bulb temperature and the wet-bulb temperature in a target space where the air conditioner is located are adjusted to a second preset dry-bulb temperature and a second preset wet-bulb temperature; The initial working parameter and the training data in the training data set are processed by a to-be-trained model to obtain a predicted latent heat release and a predicted sensible heat release; The predicted latent heat release is compared with the standard latent heat release, and the predicted sensible heat release is compared with the standard sensible heat release to obtain a comparison result, and the model parameters of the to-be-trained model are adjusted according to the comparison result to obtain the target prediction model.

7. The air conditioner control method according to claim 6, characterized by, The model parameters of the to-be-trained model are adjusted according to the comparison result, including: In the case that the comparison result is that the predicted latent heat release is not equal to the standard latent heat release, or the predicted sensible heat release is not equal to the standard sensible heat release, the model parameters of the to-be-trained model are adjusted; In the case that the comparison result is that the predicted latent heat release is equal to the standard latent heat release, and the predicted sensible heat release is equal to the standard sensible heat release, a processing time length required for the to-be-trained model to output the predicted latent heat release and the predicted sensible heat release is determined, and in the case that the processing time length is not less than a preset time length, the model parameters of the to-be-trained model are adjusted.

8. An air conditioner control device characterized by comprising: including: An acquisition module is configured to acquire a first dry-bulb temperature and a first wet-bulb temperature of an evaporator inlet of an air conditioner at a first time point, and working parameters of the air conditioner at the first time point; The first determining module is configured to determine the sensible cooling capacity and the latent cooling capacity of the air conditioner at a second time according to the first dry-bulb temperature, the first wet-bulb temperature and the working parameter of the air conditioner at the first time, wherein the second time is after the first time. The operation module is configured to obtain the second dry-bulb temperature of the air conditioner at the second time by operating the sensible cooling capacity at the second time by using a first transfer function, and obtain the second wet-bulb temperature of the air conditioner at the second time by operating the sensible cooling capacity and the latent cooling capacity at the second time by using a second transfer function, wherein the first transfer function is used to represent a functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent a functional relationship between the sensible cooling capacity, the latent cooling capacity and the wet-bulb temperature of the air conditioner. The second determining module is configured to determine the working parameter of the air conditioner at the second time according to the second dry-bulb temperature and the second wet-bulb temperature.

9. An electronic device, comprising: The memory is configured to store program instructions. The processor is connected with the memory and is configured to execute the program instructions to realize the following functions: obtaining the first dry-bulb temperature and the first wet-bulb temperature of the evaporator inlet of the air conditioner at a first time, and the working parameter of the air conditioner at the first time; determining the sensible cooling capacity and the latent cooling capacity of the air conditioner at a second time according to the first dry-bulb temperature, the first wet-bulb temperature and the working parameter of the air conditioner at the first time, wherein the second time is after the first time; obtaining the second dry-bulb temperature of the air conditioner at the second time by operating the sensible cooling capacity at the second time by using a first transfer function, and obtaining the second wet-bulb temperature of the air conditioner at the second time by operating the sensible cooling capacity and the latent cooling capacity at the second time by using a second transfer function, wherein the first transfer function is used to represent a functional relationship between the sensible cooling capacity and the dry-bulb temperature of the air conditioner, and the second transfer function is used to represent a functional relationship between the sensible cooling capacity, the latent cooling capacity and the wet-bulb temperature of the air conditioner; and determining the working parameter of the air conditioner at the second time according to the second dry-bulb temperature and the second wet-bulb temperature. The non-volatile storage medium comprises a stored computer program, wherein a device where the non-volatile storage medium is located executes the air conditioner control method in any one of claims 1 to 7 by running the computer program.

10. A non-volatile storage medium, comprising: ​

Images