Methods, devices and systems for regulating temperature and humidity

Abstract

This application discloses a method, apparatus, and system for regulating temperature and humidity. The method includes: acquiring a first temperature and a first humidity in a target space; determining a first difference between the first temperature and a preset temperature, and determining a second difference between the first humidity and a preset humidity; determining a target neural network model from multiple neural network models based on conditions satisfied by the first and second differences, wherein the target neural network model is used to determine the operating parameters of the air conditioning equipment used to adjust the first temperature and / or the first humidity; using the target neural network model to determine the operating parameters, and adjusting the air conditioning equipment according to the operating parameters to regulate the temperature and humidity in the target space. This application solves the technical problem in related technologies where temperature and humidity cannot be controlled according to different scenarios, resulting in poor temperature and humidity regulation effects in computer room environments.

Description

Technical Field

[0001] This application relates to the field of temperature and humidity control, and more specifically, to a method, apparatus, and system for regulating temperature and humidity. Background Technology

[0002] To achieve temperature and humidity control in computer rooms, direct expansion air conditioning systems, such as general-purpose air conditioners and dedicated computer room air conditioners, are commonly used. General-purpose air conditioners typically consist of a single-cycle refrigeration system comprising a compressor, condenser, expansion valve, and evaporator. They increase humidity by raising the temperature or decrease humidity by lowering the room temperature to remove water molecules from the air. For normal refrigeration cycles, since temperature and humidity control are coupled, while the temperature can generally be kept within the required range, achieving the required humidity is difficult. Adjusting the humidity in the computer room also causes changes in the room temperature. Therefore, related technologies cannot achieve temperature and humidity control in communication computer rooms based on different scenarios.

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

[0004] This application provides a method, apparatus, and system for regulating temperature and humidity, which at least solves the technical problem in the related art that the temperature and humidity cannot be controlled according to different scenarios, resulting in poor regulation effect of temperature and humidity in the computer room environment.

[0005] According to one aspect of the embodiments of this application, a method for regulating temperature and humidity is provided, comprising: acquiring a first temperature and a first humidity in a target space; determining a first difference between the first temperature and a preset temperature, and determining a second difference between the first humidity and a preset humidity; determining a target neural network model from a plurality of neural network models based on conditions satisfied by the first difference and the second difference, wherein the target neural network model is used to determine the operating parameters of an air conditioning device used to adjust the first temperature and / or the first humidity; using the target neural network model to determine the operating parameters, and adjusting the air conditioning device according to the operating parameters to regulate the temperature and humidity in the target space.

[0006] Optionally, based on the conditions satisfied by the first difference and the second difference, a target neural network model is determined from multiple neural network models, including: when the first difference is greater than a temperature threshold and the second difference is less than or equal to a humidity threshold, determining the operating parameters of the air conditioning equipment through a first neural network model in the target neural network model, wherein the operating parameters include the compressor frequency and the opening degree of the expansion valve corresponding to the low-temperature branch of the air conditioning equipment, and the weight corresponding to the compressor frequency in the first neural network model is greater than the weight corresponding to the expansion valve opening; when the first difference is less than or equal to the temperature threshold and the second difference is greater than the humidity threshold, determining the operating parameters of the air conditioning equipment through a second neural network model in the target neural network model, wherein the weight corresponding to the compressor frequency in the second neural network model is less than the weight corresponding to the expansion valve opening; when the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, comparing the first difference and the second difference; when the first difference is greater than the second difference, determining the operating parameters of the air conditioning equipment through the first neural network model; when the first difference is less than the second difference, determining the operating parameters of the air conditioning equipment through the second neural network model.

[0007] Optionally, the operating parameters of the air conditioning equipment are determined through the first neural network model in the target neural network model, including: Step 1: Inputting the first temperature and the preset temperature into the trained first neural network model to obtain the first compressor frequency and the first expansion valve opening, wherein the first expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: Determining the second temperature of the target space under the first compressor frequency and the first expansion valve opening; Step 3: When the second temperature is greater than the temperature threshold, inputting the second temperature as the first temperature into the first neural network model, repeating the above steps 1 to 2 until the second temperature is less than or equal to the temperature threshold, and using the compressor frequency and expansion valve opening corresponding to the second temperature being less than or equal to the temperature threshold as the first target compressor frequency and the first target expansion valve opening output by the first neural network model.

[0008] Optionally, the operating parameters of the air conditioning equipment are determined through the second neural network model in the target neural network model, including: Step 1: Inputting the first humidity and the preset humidity into the trained second neural network model to obtain the second compressor frequency and the second expansion valve opening, wherein the second expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: Determining the second humidity of the target space under the second compressor frequency and the second expansion valve opening; Step 3: When the second humidity is greater than the humidity threshold, inputting the second humidity as the first humidity into the second neural network model, repeating the above steps 1 to 2 until the second humidity is less than or equal to the humidity threshold, and using the compressor frequency and expansion valve opening corresponding to the second humidity being less than or equal to the humidity threshold as the second target compressor frequency and the second target expansion valve opening output by the second neural network model.

[0009] Optionally, if the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, the method further includes: determining the operating parameters of the air conditioning equipment through a third neural network model in the target neural network model; determining the operating parameters of the air conditioning equipment through a third neural network model in the target neural network model includes: Step 1: inputting the first temperature, the first humidity, and the preset temperature and preset humidity into the trained third neural network model to obtain the third compressor frequency and the third expansion valve opening, wherein the third expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: determining the second temperature and the second humidity of the target space under the third compressor frequency and the third expansion valve opening; Step 3: if the second temperature is greater than the temperature threshold or the second humidity is greater than the humidity threshold, inputting the second temperature and the second humidity as the first temperature and the first humidity into the third neural network model, and repeating the above steps 1 to 2 until the second temperature is less than or equal to the temperature threshold and the second humidity is less than or equal to the humidity threshold, and using the compressor frequency and expansion valve opening corresponding to the second temperature being less than or equal to the temperature threshold and the second humidity being less than or equal to the humidity threshold as the third target compressor frequency and the third target expansion valve opening output by the third neural network model.

[0010] Optionally, the third neural network model is trained as follows: A training dataset is obtained to train the initial neural network model, including initial temperature, initial humidity, target temperature, target humidity, and the target compressor frequency and target expansion valve opening of the air conditioning unit at the target temperature and target humidity; the data in the training dataset is processed by the initial neural network model to obtain the predicted compressor frequency and predicted expansion valve opening; the predicted compressor frequency and the target compressor frequency are compared, and the predicted expansion valve opening and the target expansion valve opening are compared to obtain the comparison results; the model parameters in the initial neural network model are adjusted based on the comparison results to obtain the third neural network model.

[0011] Optionally, the input to the target neural network model may also include environmental parameters of the target space.

[0012] According to another aspect of the embodiments of this application, a temperature and humidity regulating device is also provided, comprising: an acquisition module for acquiring a first temperature and a first humidity in a target space; a first determination module for determining a first difference between the first temperature and a preset temperature, and a second difference between the first humidity and a preset humidity; a second determination module for determining a target neural network model from multiple neural network models based on conditions satisfied by the first difference and the second difference, wherein the target neural network model is used to determine the operating parameters of an air conditioning device used to adjust the first temperature and / or the first humidity; and an adjustment module for using the target neural network model to determine the operating parameters and adjusting the air conditioning device based on the operating parameters to regulate the temperature and humidity in the target space.

[0013] According to another aspect of the embodiments of this application, a temperature and humidity regulation system is also provided, comprising: an air conditioning device and a controller, wherein the controller is configured to acquire a first temperature and a first humidity in a target space; determine a first difference between the first temperature and a preset temperature, and determine a second difference between the first humidity and a preset humidity; determine a target neural network model from multiple neural network models based on conditions satisfied by the first difference and the second difference, wherein the target neural network model is configured to determine the operating parameters of the air conditioning device used to adjust the first temperature and / or the first humidity; determine the operating parameters using the target neural network model, and adjust the air conditioning device according to the operating parameters to regulate the temperature and humidity in the target space; the air conditioning device includes at least a compressor, a condenser, a first electronic expansion valve, a second electronic expansion valve, a first plate heat exchanger, and a second plate heat exchanger, wherein the first suction port of the compressor, the first plate heat exchanger, and the first electronic expansion valve constitute a first branch, the first branch being used to regulate the temperature of the air conditioning device, and the second suction port of the compressor, the second plate heat exchanger, and the second electronic expansion valve constitute a second branch, the second branch being used to regulate the humidity of the air conditioning device.

[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-mentioned temperature and humidity adjustment method by running the computer program.

[0015] In this embodiment, a first temperature and a first humidity in the target space are obtained; a first difference between the first temperature and a preset temperature are determined, and a second difference between the first humidity and a preset humidity are determined; based on the conditions satisfied by the first and second differences, a target neural network model is determined from multiple neural network models, wherein the target neural network model is used to determine the operating parameters of the air conditioning equipment used to adjust the first temperature and / or the first humidity; the operating parameters are determined using the target neural network model, and the air conditioning equipment is adjusted according to the operating parameters to regulate the temperature and humidity in the target space, thereby achieving the purpose of regulating the temperature and humidity in the target space by adjusting the operating parameters of the air conditioning equipment. This achieves the technical effect of accurately controlling the operating parameters of the air conditioning equipment according to the target neural network model, and solves the technical problem in related technologies that the temperature and humidity cannot be controlled according to different scenarios, resulting in poor temperature and humidity regulation effect in the computer room environment. 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 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 a method for regulating temperature and humidity according to an embodiment of this application.

[0018] Figure 2 This is a flowchart of a method for adjusting temperature and humidity according to an embodiment of this application;

[0019] Figure 3a This is a structural schematic diagram of an air conditioning device according to an embodiment of this application;

[0020] Figure 3b This is a diagram showing the distribution of cooling capacity between the high and low temperature sides when the compressor frequency f = 40Hz (EEV1 opening degree is 80%), according to an embodiment of this application.

[0021] Figure 3c This is a diagram showing the distribution of cooling capacity between the high and low temperature sides when the compressor frequency f = 50Hz (EEV1 opening degree is 80%), according to an embodiment of this application.

[0022] Figure 3d This is a high and low temperature side cooling capacity distribution diagram according to an embodiment of this application when the compressor frequency f = 55Hz (EEV1 opening degree is 80%).

[0023] Figure 3e This is a schematic diagram of the structure of a first neural network model according to an embodiment of this application;

[0024] Figure 4 This is a structural diagram of a temperature and humidity regulating device according to an embodiment of this application;

[0025] Figure 5 This is a structural diagram of a temperature and humidity control system according to an embodiment of this application. Detailed Implementation

[0026] 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.

[0027] 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.

[0028] First, some nouns or terms that appear in the explanation of the embodiments of this application shall be interpreted as follows:

[0029] A condenser is a component of a refrigeration system, a type of heat exchanger that converts gas or vapor into liquid, rapidly transferring heat from the tubes to the surrounding air. The condenser's operation is exothermic, hence its relatively high temperature.

[0030] The Drier Filter is primarily used for filtering impurities.

[0031] Sight glass: The liquid moisture indicator provides users with an accurate method to determine the quality and moisture content of the refrigerant in the system. The wide-angle sight glass allows visual inspection of the refrigerant, making it easy to see bubbles or flashes of vapor, indicating whether the refrigerant dosage is appropriate and requires refilling. The indicator element, located at the center of the sight glass, is highly sensitive to moisture and gradually changes color as the moisture content in the system changes.

[0032] Gate valve: The closing principle of a gate valve is to rely on the pressure of the valve stem to make the valve disc sealing surface and the valve seat sealing surface fit tightly together, thus preventing the flow of media.

[0033] Electronic expansion valve: An electronic expansion valve is a throttling element that allows the refrigerant flow into a refrigeration unit to be throttled according to a preset program.

[0034] Plate heat exchangers are high-efficiency heat exchangers composed of a series of corrugated metal plates stacked together. Thin rectangular channels are formed between the plates, allowing heat exchange to occur. Plate heat exchangers are ideal for liquid-liquid and liquid-vapor heat exchange. They feature high heat exchange efficiency, low heat loss, compact and lightweight structure, small footprint, wide application, and long service life.

[0035] R410a is a new type of environmentally friendly refrigerant that does not damage the ozone layer. Its working pressure is about 1.6 times that of ordinary R22 air conditioners, and it has high cooling (heating) efficiency.

[0036] The equipment in communication equipment rooms consists of numerous microelectronic and precision mechanical components, which are susceptible to temperature and humidity fluctuations. Temperature has a significant impact on the electronic components and recording media of computer room equipment. For semiconductor components, the reliability decreases by approximately 25% for every 10°C increase in room temperature within the specified range; for recording media, excessively high or low temperatures can lead to data loss or access failures. Humidity also has a significant impact on computer equipment. When the relative humidity is high, water vapor forms a film on the surface of electronic components or dielectric materials, easily causing conductive paths between components; when the relative humidity is too low, high electrostatic voltage is easily generated. Currently, whether it is an important communication equipment room of Class A, B, or C, or a smaller equipment room for access networks or wireless systems, there are specific requirements for the temperature and humidity of the equipment room environment.

[0037] In related technologies, to achieve temperature and humidity control in computer rooms, ordinary air conditioners and dedicated computer room air conditioners are commonly used. Dedicated computer room air conditioners typically consist of two single-cycle cooling systems, which are selectively activated and deactivated based on the room's cooling capacity. For humidity control in computer rooms, besides utilizing the inherently ineffective cooling cycle system, methods such as humidification tanks and infrared humidification are currently used. However, these humidification methods pose serious safety hazards, and most computer rooms have now discontinued these air conditioning humidification measures. Furthermore, achieving the required humidity levels while adjusting the temperature is difficult. Therefore, for simultaneous temperature and humidity control in communication computer rooms, neither ordinary nor dedicated air conditioners currently available in computer rooms achieve satisfactory results.

[0038] To address the aforementioned problems, embodiments of this application provide a method for adjusting temperature and humidity, which can be implemented in... Figure 1 The following describes the computer terminal shown.

[0039] The temperature and humidity adjustment method provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a method of temperature and humidity regulation 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] pass Figure 1 The processor in the system executes the following temperature and humidity regulation method: acquiring a first temperature and a first humidity in the target space; determining a first difference between the first temperature and a preset temperature, and determining a second difference between the first humidity and a preset humidity; determining a target neural network model from multiple neural network models based on the conditions satisfied by the first and second differences, wherein the target neural network model is used to determine the operating parameters of the air conditioning equipment used to adjust the first temperature and / or the first humidity; using the target neural network model to determine the operating parameters, and adjusting the air conditioning equipment according to the operating parameters to regulate the temperature and humidity in the target space.

[0041] In the above operating environment, this application provides an embodiment of a method for adjusting temperature and humidity. 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. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0042] Figure 2This is a flowchart of a temperature and humidity adjustment method according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0043] Step S202: Obtain the first temperature and first humidity in the target space.

[0044] In step S202 above, the first temperature and the first humidity are the actual temperature and actual humidity collected for the first time in the target space, respectively.

[0045] Step S204: Determine the first difference between the first temperature and the preset temperature, and determine the second difference between the first humidity and the preset humidity.

[0046] Step S206: Based on the conditions satisfied by the first difference and the second difference, a target neural network model is determined from multiple neural network models, wherein the target neural network model is used to determine the operating parameters of the air conditioning equipment used to adjust the first temperature and / or the first humidity.

[0047] Step S208: The target neural network model is used to determine the operating parameters, and the air conditioning equipment is adjusted according to the operating parameters to regulate the temperature and humidity in the target space.

[0048] In step S206 above, the operating parameters of the air conditioning equipment may include, for example, the compressor frequency (or compressor speed) and the opening degree of the expansion valve in the low-temperature branch of the air conditioning equipment. The selection of compressor frequency and the opening degree of the expansion valve in the low-temperature branch of the air conditioning equipment as operating parameters is explained below:

[0049] Figure 3a This is a structural schematic diagram of an air conditioning device according to an embodiment of this application. Figure 3a In the diagram, 1-compressor first suction port, 2-compressor second suction port, 3-compressor, 4-compressor discharge port, 5-copper pipe, 6-condenser, 7-drier filter, 8-sight glass, 9-first shut-off valve, 10-second shut-off valve, 11-first electronic expansion valve, 12-second electronic expansion valve, 13-first ball valve, 14-second ball valve, 15-high temperature chilled water, 16-first plate heat exchanger, 17-low temperature chilled water, 18-second plate heat exchanger.

[0050] In the above Figure 3a In this context, the electronic expansion valve for the loop corresponding to the refrigerant flowing through the first plate heat exchanger is defined as EEV1, and the electronic expansion valve for the loop corresponding to the refrigerant flowing through the second plate heat exchanger is defined as EEV2.

[0051] The principle of the above-mentioned air conditioning equipment is as follows:

[0052] During normal cooling operation of the air conditioning system, refrigerant R410a exits from the compressor discharge port, passes through the condenser, dryer filter, and sight glass, and then enters two electronic expansion valves for throttling and pressure reduction. It then splits into two paths, each entering a plate heat exchanger. Finally, the R410a gas from both loops returns to the compressor, forming the entire refrigeration cycle. The electronic expansion valve corresponding to the loop where the refrigerant flows through the high-temperature plate heat exchanger is defined as EEV1, and the electronic expansion valve corresponding to the loop where it flows through the low-temperature plate heat exchanger is defined as EEV2. The EEV1 branch is defined as the high-temperature branch, and the EEV2 branch as the low-temperature branch. The refrigerant exchanges heat with the coolant water in the plate heat exchangers. The low-temperature side plate heat exchanger outputs low-temperature chilled water for the humidity control terminal of the air conditioning system; the high-temperature side plate heat exchanger outputs high-temperature chilled water for the temperature control terminal. The two branches output two different evaporation temperatures, and the plate heat exchangers output chilled water at two different temperatures to meet the cooling load required for temperature control and the wet load required for humidity control. Among them, the high-temperature branch outputs chilled water at a higher temperature for use in the control terminal of the computer room temperature, while the low-temperature branch outputs chilled water at a lower temperature for use in the control terminal of the computer room humidity.

[0053] Compressor frequency adjustment affects both the high-temperature and low-temperature circuits simultaneously. When EEV1 and EEV2 are at the same opening degree, as the compressor frequency increases, the discharge volume increases, leading to a faster refrigerant flow rate. This results in lower suction pressures on both the low-temperature and high-temperature sides of the compressor, causing a decrease in the evaporation temperature on both sides. Since the suction temperatures on the low-temperature and high-temperature sides of the compressor are constant, the superheat in both loops gradually increases. As the compressor frequency increases, the refrigerant compression ratio per unit time increases, and the compressor discharge volume increases, leading to an increasing cooling capacity in both loops, including the total cooling capacity. However, based on actual experimental results, the impact of compressor frequency adjustment on refrigerant flow differs between the high-temperature and low-temperature circuits, with a greater impact on the high-temperature loop and a smaller impact on the low-temperature loop. This can be achieved through… Figures 3b to 3d Some of the experimental data in the text illustrate, specifically, Figure 3b This is a diagram showing the distribution of cooling capacity between the high and low temperature sides when the compressor frequency f = 40Hz (EEV1 opening degree is 80%). Figure 3c This is a diagram showing the distribution of cooling capacity between the high and low temperature sides when the compressor frequency f = 50Hz (EEV1 opening degree is 80%). Figure 3d This is a diagram showing the distribution of cooling capacity between the high and low temperature sides when the compressor frequency f = 55Hz (EEV1 opening degree is 80%).

[0054] Based on the above principles and relevant experimental data, it is known that adjusting the compressor frequency has different effects on the refrigerant flow in the high-temperature and low-temperature loops, with a greater impact on the high-temperature loop and a smaller impact on the low-temperature loop. Therefore, in this embodiment, the temperature difference of the high-temperature chilled water is controlled by the compressor frequency, and the temperature difference of the low-temperature chilled water is controlled by the EEV2 opening. That is, the output of the high-temperature branch is controlled by the compressor frequency, thereby controlling the temperature in the machine room; the output of the low-temperature branch is controlled by the EEV2 opening, thereby controlling the humidity in the machine room. Therefore, the compressor frequency and the opening of the expansion valve in the low-temperature branch of the air conditioning equipment are used as operating parameters of the air conditioning equipment. The operating parameters are determined by the target neural network model, and the air conditioning equipment is adjusted according to the obtained operating parameters, thereby regulating the temperature and humidity in the target space.

[0055] In step S206 of the above-mentioned temperature and humidity adjustment method, a target neural network model is determined from multiple neural network models based on the conditions satisfied by the first difference and the second difference. Specifically, this includes the following steps: When the first difference is greater than a temperature threshold and the second difference is less than or equal to a humidity threshold, the operating parameters of the air conditioning equipment are determined using the first neural network model in the target neural network model. The operating parameters include the compressor frequency and the opening degree of the expansion valve corresponding to the low-temperature branch of the air conditioning equipment. In the first neural network model, the weight corresponding to the compressor frequency is greater than the weight corresponding to the expansion valve opening. When the first difference is less than or equal to the temperature threshold and the second difference is greater than the humidity threshold, the operating parameters of the air conditioning equipment are determined using the second neural network model in the target neural network model. In the second neural network model, the weight corresponding to the compressor frequency is less than the weight corresponding to the expansion valve opening. When the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, the first difference and the second difference are compared. When the first difference is greater than the second difference, the operating parameters of the air conditioning equipment are determined using the first neural network model. When the first difference is less than the second difference, the operating parameters of the air conditioning equipment are determined using the second neural network model.

[0056] In this application embodiment, temperature and humidity control can be implemented for different scenarios. For example, in this application embodiment, the following scenarios may be included:

[0057] Scenario 1: Temperature Control

[0058] In this temperature control scenario, the humidity in the target space meets the corresponding preset humidity condition. Specifically, the first difference between the first temperature in the target space and the preset temperature is greater than a temperature threshold, and the second difference between the first humidity in the target space and the preset humidity is less than or equal to a humidity threshold. In this case, only the temperature in the target space needs adjustment, without needing to adjust the humidity or making excessive adjustments. Therefore, it is necessary to select a first neural network model from multiple neural network models to determine the operating parameters of the air conditioning equipment (including compressor frequency and the opening of the expansion valve in the low-temperature branch), and then adjust the temperature and humidity of the target space based on the operating parameters obtained from the first neural network model.

[0059] It should be noted that since this scenario is a temperature control scenario, that is, more temperature adjustment is needed and less humidity adjustment is needed. Since the temperature is greatly affected by the compressor frequency, the first neural network model with a weight corresponding to the compressor frequency is selected to be greater than the weight corresponding to the expansion valve opening in the low temperature branch to determine the operating parameters of the air conditioning equipment.

[0060] Scenario 2: Humidity Control

[0061] In this humidity control scenario, the temperature in the target space meets the corresponding preset temperature condition. Specifically, the first difference between the first temperature in the target space and the preset temperature is less than or equal to a temperature threshold, and the second difference between the first humidity in the target space and the preset humidity is greater than a humidity threshold. In this case, only the humidity in the target space needs adjustment, without adjusting the temperature or making excessive adjustments to the temperature. Therefore, a second neural network model needs to be selected from multiple neural network models to determine the operating parameters of the air conditioning equipment. Then, the temperature and humidity in the target space are adjusted based on the operating parameters obtained from the second neural network model.

[0062] It should be noted that since this scenario is a humidity control scenario, which requires more humidity adjustment and less temperature adjustment, and the humidity is greatly affected by the opening of the expansion valve in the low-temperature branch, the second neural network model corresponding to the compressor frequency is selected with a smaller weight than the weight corresponding to the opening of the expansion valve in the low-temperature branch to determine the operating parameters of the air conditioning equipment.

[0063] Scenario 3: Combined temperature and humidity control

[0064] In this scenario of combined temperature and humidity control, it indicates that neither the temperature nor humidity in the target space meets the corresponding preset temperature and humidity conditions. Specifically, the first difference between the first temperature and the preset temperature in the target space is greater than a temperature threshold, and the second difference between the first humidity and the preset humidity in the target space is greater than a humidity threshold. In this case, the temperature and humidity in the target space need to be adjusted. In an optional embodiment, the neural network model to be used can be determined based on the magnitude of the difference between temperature and humidity. Specifically, by comparing the magnitude of the first and second differences, if the first difference is greater than the second difference, it indicates that the temperature adjustment is more significant than the humidity adjustment. In this case, the first neural network model can be used to determine the operating parameters of the air conditioning equipment, thereby controlling the temperature and humidity of the target space. If the first difference is less than the second difference, it indicates that the humidity adjustment is more significant than the temperature adjustment. In this case, the second neural network model can be used to determine the operating parameters of the air conditioning equipment, thereby adjusting the temperature and humidity of the target space.

[0065] In the above steps, the operating parameters of the air conditioning equipment are determined by the first neural network model in the target neural network model, specifically including the following steps: Step 1: Input the first temperature and the preset temperature into the trained first neural network model to obtain the first compressor frequency and the first expansion valve opening, wherein the first expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: Determine the second temperature of the target space under the first compressor frequency and the first expansion valve opening; Step 3: When the second temperature is greater than the temperature threshold, input the second temperature as the first temperature into the first neural network model, and repeat the above steps 1 to 2 until the second temperature is less than or equal to the temperature threshold, and use the compressor frequency and expansion valve opening corresponding to the second temperature being less than or equal to the temperature threshold as the first target compressor frequency and the first target expansion valve opening output by the first neural network model.

[0066] In this embodiment, the dataset used during the training of the first neural network model can be data where the humidity meets the preset humidity requirement, but the temperature does not meet the corresponding preset temperature requirement. Only by training the neural network model with such a dataset can the first neural network model be applied to the temperature control and regulation in scenario one.

[0067] Specifically, in the process of controlling the temperature in scenario one, the target room can be, for example, a server room. First, the first difference between the collected first temperature of the target room and the preset temperature is determined. If the first difference is small, i.e., the first difference is less than or equal to the temperature threshold, no temperature adjustment is performed. If the difference is large, i.e., the first difference is greater than the temperature threshold, the collected first temperature and the preset temperature to which the first temperature needs to be adjusted need to be input into a pre-trained first neural network model. Based on the compressor frequency and EEV2 opening (i.e., the opening of the expansion valve corresponding to the low-temperature branch in the air conditioning equipment) output by the first neural network model, the actual compressor frequency and EEV2 opening are adjusted, and the process returns to the step of collecting the second temperature of the target space under the adjusted compressor frequency and EEV2 opening and determining the difference between the second temperature and the preset temperature. If the difference between the second temperature and the preset temperature is greater than the temperature threshold, further adjustment is required. At this time, the second temperature is used as the first temperature and input into the first neural network model. The above steps are repeated until the difference between the second temperature and the preset temperature is less than or equal to the temperature threshold, and the first target compressor frequency and the first target expansion valve opening are output. It should be noted that since the low-temperature branch also bears part of the indoor cooling load, the output of the first neural network model in this application also includes the EEV2 opening degree, and the weight of the EEV2 opening degree in the first neural network model is much smaller than the weight of the compressor frequency.

[0068] In some optional embodiments of this application, the structural schematic diagram of the first neural network model is as follows: Figure 3e As shown, in Figure 3e In this model, the first neural network mainly consists of an input layer, an output layer, and multiple hidden layers. Each hidden layer contains h neurons. Let x represent a training input, and y = y(x) represent the corresponding expected output. To find the weights and biases in the first neural network model such that its output y(x) fits all training inputs x, a cost function is defined:

[0069]

[0070] In the above formula, w represents the set of weights in the first neural network model, b is all the biases in the first neural network model, n is the number of training input data, a represents the true output, and the summation is performed on the total training input x. The symbol |||| refers to the magnitude of the vector. Furthermore, the cost function C(w,b) is quite small, i.e., C(w,b)≈0, more precisely, when y(x) is close to the output a for all training inputs x. Therefore, if suitable weights and biases can be found such that C(w,b)≈0, it will work well. Here, the gradient descent algorithm is used to train the first neural network model to find the weights w and biases b that minimize the cost function.

[0071] When training the first neural network model, multiple sets of data can be pre-configured based on actual adjustment experience. Each set of data includes: actual temperature, preset temperature, compressor frequency, and EEV2 opening degree. The preset temperature can be used as a standard value, and the first neural network model can be trained using the actual temperature, compressor frequency, and EEV2 opening degree as input and output, respectively. It should be noted that the model parameters in the first neural network model can be different for different standard values ​​(i.e., different temperature thresholds; different computer rooms can indicate different temperature thresholds according to actual conditions). The various parameters in the first neural network model are determined through the training process, and the first neural network model is obtained after training.

[0072] In the above steps, the operating parameters of the air conditioning equipment are determined by the second neural network model in the target neural network model, specifically including the following steps: Step 1: Input the first humidity and the preset humidity into the trained second neural network model to obtain the second compressor frequency and the second expansion valve opening, wherein the second expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: Determine the second humidity of the target space under the second compressor frequency and the second expansion valve opening; Step 3: When the second humidity is greater than the humidity threshold, input the second humidity as the first humidity into the second neural network model, and repeat the above steps 1 to 2 until the second humidity is less than or equal to the humidity threshold, and use the compressor frequency and expansion valve opening corresponding to the second humidity being less than or equal to the humidity threshold as the second target compressor frequency and the second target expansion valve opening output by the second neural network model.

[0073] In this embodiment, the dataset used during the training of the second neural network model can be data where the temperature meets the preset temperature requirement, but the humidity does not meet the corresponding preset humidity requirement. Only by training the neural network model with such a dataset can the resulting second neural network model be applicable to the control and adjustment of humidity in scenario two.

[0074] Specifically, in the humidity control process of Scenario 2, the second difference between the first humidity of the target room and the preset humidity is first determined. If the second difference is small, i.e., less than or equal to the humidity threshold, no humidity adjustment is performed. If the difference is large, i.e., greater than the humidity threshold, the first humidity and the preset humidity to which the first humidity needs to be adjusted are input into the pre-trained second neural network model. The actual compressor frequency and EEV2 opening (i.e., the opening of the expansion valve corresponding to the low-temperature branch in the air conditioning equipment) output by the second neural network model are adjusted, and the process returns to the steps of collecting the second humidity of the target space under the adjusted compressor frequency and EEV2 opening and determining the difference between the second humidity and the preset humidity. If the difference between the second humidity and the preset humidity is greater than the humidity threshold, further adjustment is required. At this time, the second humidity is used as the first humidity and input into the second neural network model. The above steps are repeated until the difference between the second humidity and the preset humidity is less than or equal to the humidity threshold, and the second target compressor frequency and the second target expansion valve opening are output. It should be noted that, consistent with the temperature control scenario described above, since the high-temperature branch also bears a portion of the indoor humidity load, the output of the second neural network model in this embodiment also includes the compressor frequency, and the weight of the compressor frequency in the second neural network model is much smaller than the weight of the EEV2 opening degree.

[0075] In some optional embodiments of this application, the creation of the second neural network model, the selection of model parameters, and the pre-training process can be referred to the process of executing the first neural network model in Scenario 1, and will not be repeated here. That is, when training the second neural network model, each set of values ​​used in the training includes: actual humidity, preset humidity, compressor frequency, and EEV2 opening degree. Similarly, the preset humidity can be used as a standard value, and the second neural network model can be trained using the actual humidity, compressor frequency, and EEV2 opening degree as input and output, respectively.

[0076] In the above steps, when the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, the method further includes the following steps: determining the operating parameters of the air conditioning equipment through the third neural network model in the target neural network model; determining the operating parameters of the air conditioning equipment through the third neural network model in the target neural network model includes: Step 1: inputting the first temperature, the first humidity, and the preset temperature and preset humidity into the trained third neural network model to obtain the third compressor frequency and the third expansion valve opening, wherein the third expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: determining the second temperature and the second humidity of the target space under the third compressor frequency and the third expansion valve opening; Step 3: when the second temperature is greater than the temperature threshold or the second humidity is greater than the humidity threshold, inputting the second temperature and the second humidity as the first temperature and the first humidity into the third neural network model, and repeating the above steps 1 to 2 until the second temperature is less than or equal to the temperature threshold and the second humidity is less than or equal to the humidity threshold, and using the compressor frequency and expansion valve opening corresponding to the second temperature being less than or equal to the temperature threshold and the second humidity being less than or equal to the humidity threshold as the third target compressor frequency and the third target expansion valve opening output by the third neural network model.

[0077] In the above steps, the third neural network model is trained as follows: A training dataset is obtained to train the initial neural network model. This dataset includes initial temperature, initial humidity, target temperature, target humidity, and the target compressor frequency and target expansion valve opening of the air conditioning unit at the target temperature and target humidity. The initial neural network model processes the data in the training dataset to obtain the predicted compressor frequency and predicted expansion valve opening. The predicted compressor frequency and the target compressor frequency are compared, as are the predicted expansion valve opening and the target expansion valve opening, to obtain the comparison results. Based on the comparison results, the model parameters in the initial neural network model are adjusted to obtain the third neural network model.

[0078] In an optional embodiment of this application, during the process of controlling temperature and humidity in scenario three, temperature and humidity control can also be achieved in another way. Specifically, firstly, the first difference between the first temperature of the target room and the preset temperature, and the second difference between the first humidity of the target room and the preset humidity are determined. If both the first difference and the second difference are small, that is, the first difference is less than or equal to the temperature threshold and the second difference is less than or equal to the humidity threshold, then no temperature and humidity adjustment is performed. If the difference is large, i.e., the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, then the collected first temperature, first humidity, and the preset temperature and preset humidity to which the first temperature and humidity need to be adjusted need to be input into the pre-trained third neural network model. Based on the compressor frequency and EEV2 opening (i.e., the opening of the expansion valve corresponding to the low-temperature branch in the air conditioning equipment) output by the third neural network model, the actual compressor frequency and EEV2 opening are adjusted, and the process returns to collect the second temperature and second humidity of the target space under the adjusted compressor frequency and EEV2 opening, as well as the steps of judging the difference between the second temperature and the preset temperature and the second humidity and the preset humidity. If the difference between the second temperature and the preset temperature is greater than the temperature threshold, or the difference between the second humidity and the preset humidity is greater than the humidity threshold, then further adjustment is needed. At this time, the second temperature and the second humidity are input into the third neural network model as the first temperature and the first humidity, respectively, and the above steps are repeated until the difference between the second temperature and the preset temperature is less than the temperature threshold and the difference between the second humidity and the preset humidity is less than the humidity threshold.

[0079] In another optional embodiment, temperature and humidity can also be controlled in the following way: Specifically, in scenario three above, the first temperature and first humidity of the target space can be input into the first neural network model and the second neural network model respectively, thereby obtaining the fourth target compressor frequency and the fourth target expansion valve opening (i.e., the expansion valve opening corresponding to the low-temperature branch of the air conditioning unit) output by the first neural network model, and the fifth target compressor frequency and the fifth target expansion valve opening (i.e., the expansion valve opening corresponding to the low-temperature branch of the air conditioning unit) output by the second neural network model. By setting the weights of the fourth target compressor frequency and the fifth target compressor frequency, the fourth target compressor frequency can be controlled. The total compressor frequency to be adjusted is obtained by weighted summation of the four target compressor frequencies and the fifth target compressor frequency. The total expansion valve opening to be adjusted is obtained by weighted summation of the four target expansion valve openings and the fifth target expansion valve openings, based on the weighted summation of the four target expansion valve openings and the fifth target expansion valve openings. Then, it is determined whether the difference between the second temperature and the preset temperature under the total compressor frequency and the total expansion valve opening is less than or equal to the temperature threshold, and whether the difference between the second humidity and the preset humidity is less than or equal to the humidity threshold. If either of them is not satisfied, the adjustment is repeated until both temperature and humidity meet the corresponding preset temperature and preset humidity requirements.

[0080] In the above steps, since external environmental factors also affect the temperature and humidity of the target space, the input of the neural network model can be changed according to the actual ambient temperature, ambient air pressure and some other environmental parameters each day. That is, the input of the target neural network model also includes the environmental parameters of the target space.

[0081] In another alternative embodiment, the superheat and condensing pressure can be adjusted when determining the output of the target neural network model. Optionally, the condensing pressure can be controlled by the frequency of the condenser fan, and the superheat can be controlled by the opening degree of EEV1.

[0082] The temperature and humidity regulation method provided in this application embodiment is based on the idea of ​​controlling the temperature and humidity of the computer room separately. It uses a single air conditioner to regulate both temperature and humidity, enabling control of the computer room's temperature and humidity under different scenarios. Furthermore, when the air conditioner's processor (or an external processing platform) performs temperature and humidity control, a pre-trained neural network model is used to accurately determine the air conditioner's output.

[0083] The temperature and humidity regulation method provided in this application has the following advantages: (1) The entire refrigeration system is driven by a single compressor, forming two refrigeration branches. The system is stable, compact, and occupies a small area. At the same time, two different temperatures of chilled water are output through a plate heat exchanger. The high and low temperature chilled water are used for ambient air temperature and humidity treatment, respectively. (2) Different neural network models are set for different branches. The actual collected data is used as the input of the model. The temperature and humidity are controlled in real time according to the output of the model, and the indoor temperature and humidity are accurately controlled. (3) While realizing the temperature and humidity control of the communication equipment room, the evaporation temperature of the refrigeration cycle system is increased, and the energy-saving operation of the system is realized. (4) No additional humidity treatment device is required, which avoids the safety hazards of the equipment room such as circuit temperature rise and fire caused by the long-term operation of the humidity treatment circuit. For humidification methods such as humidification tanks and electrode humidification, personnel need to regularly go to the equipment room to check the humidification circuit to prevent the water circuit from being blocked and the equipment from burning dry. This application does not have the situation of equipment burning dry and heating up. Frequent on-site inspection of the air conditioning equipment is not required, which greatly reduces the maintenance workload of maintenance personnel.

[0084] Figure 4 This is a structural diagram of a temperature and humidity regulating device according to an embodiment of this application, as shown below. Figure 4 As shown, the device includes:

[0085] The acquisition module 32 is used to acquire the first temperature and the first humidity in the target space;

[0086] The first determining module 34 is used to determine a first difference between a first temperature and a preset temperature, and to determine a second difference between a first humidity and a preset humidity;

[0087] The second determining module 36 is used to determine a target neural network model from multiple neural network models based on the conditions satisfied by the first difference and the second difference, wherein the target neural network model is used to determine the operating parameters of the air conditioning equipment used to adjust the first temperature and / or the first humidity;

[0088] The adjustment module 38 is used to determine the operating parameters using a target neural network model and adjust the air conditioning equipment according to the operating parameters to regulate the temperature and humidity in the target space.

[0089] In the second determining module of the aforementioned temperature and humidity regulating device, a target neural network model is determined from multiple neural network models based on the conditions satisfied by the first difference and the second difference. Specifically, this includes the following process: When the first difference is greater than a temperature threshold and the second difference is less than or equal to a humidity threshold, the operating parameters of the air conditioning equipment are determined using the first neural network model in the target neural network model. These operating parameters include the compressor frequency and the opening degree of the expansion valve corresponding to the low-temperature branch of the air conditioning equipment. In the first neural network model, the weight corresponding to the compressor frequency is greater than the weight corresponding to the expansion valve opening. When the first difference is less than or equal to the temperature threshold and the second difference is greater than the humidity threshold, the operating parameters of the air conditioning equipment are determined using the second neural network model in the target neural network model. In the second neural network model, the weight corresponding to the compressor frequency is less than the weight corresponding to the expansion valve opening. When the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, the first difference and the second difference are compared. When the first difference is greater than the second difference, the operating parameters of the air conditioning equipment are determined using the first neural network model. When the first difference is less than the second difference, the operating parameters of the air conditioning equipment are determined using the second neural network model.

[0090] In the second determining module of the aforementioned temperature and humidity regulating device, the operating parameters of the air conditioning equipment are determined by the first neural network model in the target neural network model. Specifically, the process includes the following steps: Step 1: Input the first temperature and the preset temperature into the trained first neural network model to obtain the first compressor frequency and the first expansion valve opening, wherein the first expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: Determine the second temperature of the target space under the first compressor frequency and the first expansion valve opening; Step 3: When the second temperature is greater than the temperature threshold, input the second temperature as the first temperature into the first neural network model, and repeat the above steps 1 to 2 until the second temperature is less than or equal to the temperature threshold, and use the compressor frequency and expansion valve opening corresponding to the second temperature being less than or equal to the temperature threshold as the first target compressor frequency and the first target expansion valve opening output by the first neural network model.

[0091] In the second determining module of the aforementioned temperature and humidity regulating device, the operating parameters of the air conditioning equipment are determined by the second neural network model in the target neural network model. Specifically, the process includes the following steps: Step 1: Input the first humidity and the preset humidity into the trained second neural network model to obtain the second compressor frequency and the second expansion valve opening, wherein the second expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: Determine the second humidity of the target space under the second compressor frequency and the second expansion valve opening; Step 3: When the second humidity is greater than the humidity threshold, input the second humidity as the first humidity into the second neural network model, and repeat the above steps 1 to 2 until the second humidity is less than or equal to the humidity threshold, and use the compressor frequency and expansion valve opening corresponding to the second humidity being less than or equal to the humidity threshold as the second target compressor frequency and the second target expansion valve opening output by the second neural network model.

[0092] In the second determining module of the aforementioned temperature and humidity regulating device, when the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, the second determining module is further used to determine the operating parameters of the air conditioning equipment through the third neural network model in the target neural network model; determining the operating parameters of the air conditioning equipment through the third neural network model in the target neural network model specifically includes the following process: Step 1: Input the first temperature, the first humidity, and the preset temperature and preset humidity into the trained third neural network model to obtain the third compressor frequency and the third expansion valve opening, wherein the third expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: Determine the second temperature and second humidity of the target space under the third compressor frequency and the third expansion valve opening; Step 3: When the second temperature is greater than the temperature threshold or the second humidity is greater than the humidity threshold, input the second temperature and the second humidity as the first temperature and the first humidity into the third neural network model, and repeat the above steps 1 to 2 until the second temperature is less than or equal to the temperature threshold and the second humidity is less than or equal to the humidity threshold. Then, use the compressor frequency and expansion valve opening corresponding to the second temperature being less than or equal to the temperature threshold and the second humidity being less than or equal to the humidity threshold as the third target compressor frequency and the third target expansion valve opening output by the third neural network model.

[0093] In the aforementioned temperature and humidity control device, the third neural network model is trained as follows: A training dataset is obtained to train the initial neural network model. This dataset includes initial temperature, initial humidity, target temperature, target humidity, and the target compressor frequency and target expansion valve opening of the air conditioning unit at the target temperature and target humidity. The initial neural network model processes the data in the training dataset to obtain the predicted compressor frequency and predicted expansion valve opening. The predicted compressor frequency and the target compressor frequency are compared, as are the predicted expansion valve opening and the target expansion valve opening, to obtain a comparison result. Based on the comparison result, the model parameters in the initial neural network model are adjusted to obtain the third neural network model.

[0094] In the aforementioned temperature and humidity control device, the input to the target neural network model also includes environmental parameters of the target space.

[0095] It should be noted that, Figure 4 The temperature and humidity regulating device shown is used to perform... Figure 2 The temperature and humidity adjustment method shown above also applies to this temperature and humidity adjustment device, and will not be repeated here.

[0096] Figure 5 This is a structural diagram of a temperature and humidity control system according to an embodiment of this application, as shown below. Figure 5 As shown, the temperature and humidity regulation system 40 includes: an air conditioning unit 42 and a controller 44, wherein the controller is used to acquire a first temperature and a first humidity in the target space; determine a first difference between the first temperature and a preset temperature, and determine a second difference between the first humidity and a preset humidity; determine a target neural network model from multiple neural network models based on the conditions satisfied by the first difference and the second difference, wherein the target neural network model is used to determine the operating parameters of the air conditioning unit used to adjust the first temperature and / or the first humidity; determine the operating parameters using the target neural network model, and adjust the air conditioning unit according to the operating parameters to regulate the temperature and humidity in the target space; the air conditioning unit includes at least a compressor, a condenser, a first electronic expansion valve, a second electronic expansion valve, a first plate heat exchanger, and a second plate heat exchanger, wherein the first suction port of the compressor, the first plate heat exchanger, and the first electronic expansion valve constitute a first branch, which is used to regulate the temperature of the air conditioning unit, and the second suction port of the compressor, the second plate heat exchanger, and the second electronic expansion valve constitute a second branch, which is used to regulate the humidity of the air conditioning unit.

[0097] In the temperature and humidity control system described above, the controller and the air conditioning equipment can be independent, or the controller can be built into the air conditioning equipment.

[0098] It should be noted that, Figure 5The temperature and humidity control system shown is used to perform... Figure 2 The temperature and humidity adjustment methods shown above also apply to this temperature and humidity adjustment system, and will not be repeated here.

[0099] This application 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 temperature and a first humidity in a target space; determining a first difference between the first temperature and a preset temperature, and determining a second difference between the first humidity and a preset humidity; determining a target neural network model from multiple neural network models based on conditions satisfied by the first difference and the second difference, wherein the target neural network model is used to determine the operating parameters of an air conditioning device used to adjust the first temperature and / or the first humidity; using the target neural network model to determine the operating parameters, and adjusting the air conditioning device based on the operating parameters to regulate the temperature and humidity in the target space.

[0100] It should be noted that the aforementioned electronic equipment is used to perform Figure 2 The temperature and humidity adjustment methods shown above also apply to this electronic device, and will not be repeated here.

[0101] 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 temperature and humidity regulation method by running the computer program: acquiring a first temperature and a first humidity in a target space; determining a first difference between the first temperature and a preset temperature, and determining a second difference between the first humidity and a preset humidity; determining a target neural network model from multiple neural network models based on conditions satisfied by the first and second differences, wherein the target neural network model is used to determine the operating parameters of the air conditioning equipment used to adjust the first temperature and / or the first humidity; using the target neural network model to determine the operating parameters, and adjusting the air conditioning equipment according to the operating parameters to regulate the temperature and humidity in the target space.

[0102] It should be noted that the aforementioned non-volatile storage media is used for execution. Figure 2 The temperature and humidity adjustment methods shown above also apply to this non-volatile storage medium, and will not be repeated here.

[0103] 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. A method of temperature and humidity conditioning, characterized in that, The method comprises: obtaining a first temperature and a first humidity in a target space; determining a first difference between the first temperature and a preset temperature, and a second difference between the first humidity and a preset humidity; determining a target neural network model from a plurality of neural network models according to a condition met by the first difference and the second difference, wherein the target neural network model is used to determine an operating parameter of an air conditioning device used to adjust the first temperature and / or the first humidity; determining the operating parameter by using the target neural network model, and adjusting the air conditioning device according to the operating parameter to adjust the temperature and humidity in the target space; determining a target neural network model from a plurality of neural network models according to a condition met by the first difference and the second difference, comprising: in a case where the first difference is greater than a temperature threshold and the second difference is less than or equal to a humidity threshold, determining the operating parameter of the air conditioning device by a first neural network model in the target neural network model, wherein the operating parameter comprises a compressor frequency and an expansion valve opening degree corresponding to a low-temperature branch of the air conditioning device, and a weight corresponding to the compressor frequency in the first neural network model is greater than a weight corresponding to the expansion valve opening degree; in a case where the first difference is less than or equal to the temperature threshold and the second difference is greater than the humidity threshold, determining the operating parameter of the air conditioning device by a second neural network model in the target neural network model, wherein a weight corresponding to the compressor frequency in the second neural network model is less than a weight corresponding to the expansion valve opening degree; in a case where the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, comparing the first difference and the second difference; in a case where the first difference is greater than the second difference, determining the operating parameter of the air conditioning device by the first neural network model; in a case where the first difference is less than the second difference, determining the operating parameter of the air conditioning device by the second neural network model; The air conditioning device comprises at least a compressor, a condenser, a first electronic expansion valve, a second electronic expansion valve, a first plate heat exchanger and a second plate heat exchanger, a first suction port of the compressor, the first plate heat exchanger and the first electronic expansion valve constitute a high-temperature branch, the high-temperature branch is used to adjust the temperature of the air conditioning device, a second suction port of the compressor, the second plate heat exchanger and the second electronic expansion valve constitute a low-temperature branch, and the low-temperature branch is used to adjust the humidity of the air conditioning device.

2. The method of claim 1, wherein, Determining the operating parameter of the air conditioning device by the first neural network model in the target neural network model comprises: Step 1: inputting the first temperature and the preset temperature into the trained first neural network model to obtain a first compressor frequency and a first expansion valve opening degree, wherein the first expansion valve opening degree is the expansion valve opening degree corresponding to the low-temperature branch in the air conditioning device; Step 2: determining a second temperature of the target space under the first compressor frequency and the first expansion valve opening degree; Step 3: In the case that the second temperature is greater than the temperature threshold, input the second temperature as the first temperature into the first neural network model, repeat steps 1-2 until the second temperature is less than or equal to the temperature threshold, and the compressor frequency and expansion valve opening corresponding to the second temperature less than or equal to the temperature threshold are taken as the first target compressor frequency and the first target expansion valve opening output by the first neural network model.

3. The method of claim 1, wherein, Determining the operating parameters of the air conditioning equipment through a second neural network model in the target neural network model, comprising: Step 1: input the first humidity and the preset humidity into the trained second neural network model to obtain a second compressor frequency and a second expansion valve opening, wherein the second expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: determine the second humidity of the target space under the second compressor frequency and the second expansion valve opening; Step 3: In the case that the second humidity is greater than the humidity threshold, input the second humidity as the first humidity into the second neural network model, repeat steps 1-2 until the second humidity is less than or equal to the humidity threshold, and the compressor frequency and expansion valve opening corresponding to the second humidity less than or equal to the humidity threshold are taken as the second target compressor frequency and the second target expansion valve opening output by the second neural network model.

4. The method of claim 1, wherein, In the case that the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, the method further comprises: Determining the operating parameters of the air conditioning equipment through a third neural network model in the target neural network model; Determining the operating parameters of the air conditioning equipment through a third neural network model in the target neural network model, comprising: Step 1: input the first temperature, the first humidity, the preset temperature, and the preset humidity into the trained third neural network model to obtain a third compressor frequency and a third expansion valve opening, wherein the third expansion valve opening is the expansion valve opening corresponding to the low-temperature branch in the air conditioning equipment; Step 2: determine the second temperature and the second humidity of the target space under the third compressor frequency and the third expansion valve opening; Step 3: In the case that the second temperature is greater than the temperature threshold, or the second humidity is greater than the humidity threshold, input the second temperature and the second humidity as the first temperature and the first humidity into the third neural network model, repeat steps 1-2 until the second temperature is less than or equal to the temperature threshold, and the second humidity is less than or equal to the humidity threshold, and the compressor frequency and expansion valve opening corresponding to the second temperature less than or equal to the temperature threshold and the second humidity less than or equal to the humidity threshold are taken as the third target compressor frequency and the third target expansion valve opening output by the third neural network model.

5. The method of claim 4, wherein, The third neural network model is trained by the following method: obtain a training data set required for training an initial neural network model, wherein the training data set includes an initial temperature, an initial humidity, a target temperature, a target humidity, and a target compressor frequency and a target expansion valve opening degree corresponding to the air conditioning equipment under the target temperature and the target humidity; process data in the training data set through the initial neural network model to obtain a predicted compressor frequency and a predicted expansion valve opening degree; compare the predicted compressor frequency with the target compressor frequency and compare the predicted expansion valve opening degree with the target expansion valve opening degree to obtain a comparison result; adjust model parameters in the initial neural network model according to the comparison result to obtain the third neural network model.

6. The method of claim 1, wherein, The input of the target neural network model further includes environmental parameters of the target space.

7. A temperature and humidity adjusting device, characterized by comprising: comprise: an obtaining module configured to obtain a first temperature and a first humidity in a target space; a first determining module configured to determine a first difference value of the first temperature and a preset temperature, and determine a second difference value of the first humidity and a preset humidity; The second determining module is configured to determine a target neural network model from a plurality of neural network models according to a condition satisfied by the first difference value and the second difference value, wherein the target neural network model is used to determine an operation parameter of an air conditioning device used to adjust the first temperature and / or the first humidity; in a case where the first difference value is greater than a temperature threshold value and the second difference value is less than or equal to a humidity threshold value, the operation parameter of the air conditioning device is determined by a first neural network model in the target neural network model, wherein the operation parameter includes a compressor frequency and an opening degree of an expansion valve corresponding to a low-temperature branch of the air conditioning device, and a weight corresponding to the compressor frequency in the first neural network model is greater than a weight corresponding to the opening degree of the expansion valve; in a case where the first difference value is less than or equal to the temperature threshold value and the second difference value is greater than the humidity threshold value, the operation parameter of the air conditioning device is determined by a second neural network model in the target neural network model, wherein a weight corresponding to the compressor frequency in the second neural network model is less than a weight corresponding to the opening degree of the expansion valve; in a case where the first difference value is greater than the temperature threshold value and the second difference value is greater than the humidity threshold value, the first difference value and the second difference value are compared; in a case where the first difference value is greater than the second difference value, the operation parameter of the air conditioning device is determined by the first neural network model; in a case where the first difference value is less than the second difference value, the operation parameter of the air conditioning device is determined by the second neural network model; the air conditioning device at least includes a compressor, a condenser, a first electronic expansion valve, a second electronic expansion valve, a first plate heat exchanger and a second plate heat exchanger, a first suction port of the compressor, the first plate heat exchanger and the first electronic expansion valve constitute a high-temperature branch, the high-temperature branch is used to adjust a temperature of the air conditioning device, a second suction port of the compressor, the second plate heat exchanger and the second electronic expansion valve constitute a low-temperature branch, and the low-temperature branch is used to adjust a humidity of the air conditioning device; The adjusting module is configured to determine the operation parameter by using the target neural network model, and adjust the air conditioning device according to the operation parameter, so as to adjust the temperature and the humidity in the target space.

8. A temperature and humidity conditioning system, characterized by, Comprise: An air conditioning device and a controller, wherein The controller is configured to acquire a first temperature and a first humidity in a target space, determine a first difference between the first temperature and a preset temperature, and determine a second difference between the first humidity and a preset humidity; determine a target neural network model from a plurality of neural network models according to a condition satisfied by the first difference and the second difference, wherein the target neural network model is used to determine an operating parameter of an air conditioning device used to adjust the first temperature and / or the first humidity; determine the operating parameter by using the target neural network model, and adjust the air conditioning device according to the operating parameter to adjust the temperature and humidity in the target space; and determine the target neural network model from the plurality of neural network models according to the condition satisfied by the first difference and the second difference, including: in a case where the first difference is greater than a temperature threshold and the second difference is less than or equal to a humidity threshold, determining the operating parameter of the air conditioning device by using a first neural network model in the target neural network model, wherein the operating parameter includes a compressor frequency and an opening degree of an expansion valve corresponding to a low-temperature branch of the air conditioning device, and a weight corresponding to the compressor frequency in the first neural network model is greater than a weight corresponding to the opening degree of the expansion valve; in a case where the first difference is less than or equal to the temperature threshold and the second difference is greater than the humidity threshold, determining the operating parameter of the air conditioning device by using a second neural network model in the target neural network model, wherein a weight corresponding to the compressor frequency in the second neural network model is less than a weight corresponding to the opening degree of the expansion valve; and in a case where the first difference is greater than the temperature threshold and the second difference is greater than the humidity threshold, comparing the first difference and the second difference; in a case where the first difference is greater than the second difference, determining the operating parameter of the air conditioning device by using the first neural network model; and in a case where the first difference is less than the second difference, determining the operating parameter of the air conditioning device by using the second neural network model. The air conditioning device includes at least a compressor, a condenser, a first electronic expansion valve, a second electronic expansion valve, a first plate heat exchanger, and a second plate heat exchanger, a first suction port of the compressor, the first plate heat exchanger, and the first electronic expansion valve constitute a high-temperature branch, the high-temperature branch is used to adjust the temperature of the air conditioning device, a second suction port of the compressor, the second plate heat exchanger, and the second electronic expansion valve constitute a low-temperature branch, and the low-temperature branch is used to adjust the humidity of the air conditioning device.

9. A non-volatile storage medium, comprising: The non-volatile storage medium includes a stored computer program, wherein a device in which the non-volatile storage medium is located executes the temperature and humidity adjustment method in any one of claims 1 to 6 by running the computer program.

Images