Air conditioning load control method and system, readable storage medium and air conditioning unit

Abstract

The invention provides an air conditioner load control method and system, a readable storage medium and an air conditioning unit. The air conditioner load control method comprises the steps that a fresh air enthalpy value and a return air enthalpy value are calculated according to obtained fresh air information and return air information; the fresh air volume and the return air volume are calculated according to the obtained fresh air valve opening, the obtained return air valve opening and the obtained air supply volume, the fresh air load is calculated based on the fresh air volume and the fresh air enthalpy value, and the return air load is calculated based on the return air volume and the return air enthalpy value; an air supply enthalpy difference is predicted according to the neural network model, a predicted air supply enthalpy value is obtained according to the air supply enthalpy difference and the air return enthalpy value, an air supply load is calculated according to the air supply enthalpy value and the air supply amount, and an air load is calculated according to the fresh air load, the air return load and the air supply load; calculating water flow according to the air load and the inlet and outlet water temperature difference, and adjusting the opening of a cold water valve according to the water flow to control the opening of a refrigeration section and a reheating section of the air conditioner. The problems that in the passive adjusting process, load fluctuation is large, and precision is difficult to stabilize are solved, and system energy consumption is reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of air conditioning load control, and in particular, relates to an air conditioning load control method, system, readable storage medium and air conditioning unit. Background Art

[0002] Countries and regions need to take a series of measures, including promoting the use of clean energy, improving energy efficiency, and developing low-carbon transportation, to meet the challenges of global climate change. These efforts are aimed at reducing greenhouse gas emissions, protecting the earth's ecological environment, and achieving the goal of sustainable development.

[0003] Among the energy consumption of buildings, more than half of it is consumed by central air conditioning. Especially in the cooling season, central air conditioning plays the main function of indoor cooling and dehumidification. Usually, in order to ensure the comfort of the room, after cooling and dehumidifying, the air needs to be heated to achieve the ideal air supply temperature.

[0004] In the field of medical purification, the use of combined air handling units is relatively common. Usually, a certain amount of fresh air needs to be added in purification occasions to maintain the positive pressure of the room, and at the same time, the demand for fresh air by the room personnel or equipment must be met. Usually, the typical indoor unit functional sections include fresh air return air mixing section, filtration section, surface cooling section, heating section, humidification section, air supply section, etc. Under normal working conditions, the air conditioning process to achieve constant temperature and humidity in the room is: after the air sent to the room absorbs the residual heat and humidity in the room, part of it is discharged to the outside, and the other part is mixed with fresh air, cooled and dehumidified to the machine dew point by the indoor heat exchanger, and then heated to the air supply state point through the reheat section. The above adjustment process is a return air plus reheating adjustment.

[0005] Usually in the adjustment process, due to the variable and unstable characteristics of fresh air, such as different time periods of the day, different weather conditions such as rainy or sunny days, and different seasons of the year, it has a certain degree of variability and unpredictability. On rainy days, the humidity content of fresh air is relatively high, resulting in a large fresh air load. The unit surface cooling section must bear a large fresh air humidity load. In extreme weather, it even exceeds the design operating conditions, resulting in failure to meet the target requirements. At the same time, a large fresh air load also means more energy consumption. The variable operating conditions will also make it difficult to stabilize the control system, resulting in fluctuations in the operating conditions of the room, which is not conducive to the control of the room's temperature and humidity requirements. Summary of the invention

[0006] In view of this, the present application aims to propose an air conditioning load control method, system, readable storage medium and air conditioning unit to solve the problem of large load fluctuations and high energy consumption caused by passive adjustment of traditional air conditioners.

[0007] To achieve the above purpose, the technical solution of this application is implemented as follows: In a first aspect, the present application provides an air conditioning load control method, comprising: Calculate the fresh air enthalpy value and the return air enthalpy value according to the acquired fresh air information and return air information; Obtaining the fresh air valve opening, return air valve opening and supply air volume of the air conditioner, calculating the fresh air volume and return air volume at the current moment according to the fresh air valve opening, return air valve opening and supply air volume, and calculating the fresh air load based on the fresh air volume and the fresh air enthalpy value, and calculating the return air load based on the return air volume and the return air enthalpy value; Predicting and outputting a supply air enthalpy difference according to a pre-built neural network model, and obtaining a predicted supply air enthalpy value according to the supply air enthalpy difference and the return air enthalpy value, calculating the supply air load according to the supply air enthalpy value and the supply air volume, and calculating the air load to be processed according to the fresh air load, the return air load and the supply air load; The water flow rate is calculated according to the air load to be processed and the inlet and outlet water temperature difference, and the cold water valve opening is adjusted according to the water flow rate to control the opening of the air conditioning refrigeration section and the reheating section.

[0008] In the second aspect, based on the same inventive concept, the present application also provides an air conditioning load control system, including: A first calculation module is configured to calculate a fresh air enthalpy value and a return air enthalpy value according to the acquired fresh air information and return air information; a second calculation module, configured to obtain the opening of the fresh air valve, the opening of the return air valve and the supply air volume of the air conditioner, calculate the fresh air volume and the return air volume at this time according to the opening of the fresh air valve, the opening of the return air valve and the supply air volume, calculate the fresh air load based on the fresh air volume and the fresh air enthalpy value, and calculate the return air load based on the return air volume and the return air enthalpy value; a third calculation module, configured to predict and output a supply air enthalpy difference according to a pre-built neural network model, obtain a predicted supply air enthalpy value according to the supply air enthalpy difference and the return air enthalpy value, calculate the supply air load according to the supply air enthalpy value and the supply air volume, and calculate the air load to be processed according to the fresh air load, the return air load and the supply air load; The control module is configured to calculate the water flow rate according to the air load to be processed and the inlet and outlet water temperature difference, and adjust the opening of the cold water valve according to the water flow rate to control the opening of the air conditioning refrigeration section and the reheating section.

[0009] In a third aspect, based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0010] In a fourth aspect, based on the same inventive concept, the present application also provides an air conditioning unit, comprising: The air conditioning load control system as described in the second aspect; and / or; A readable storage medium as described in the third aspect.

[0011] Compared with the prior art, the air conditioning load control method, system, readable storage medium and air conditioning unit described in the present application have the following beneficial effects: The air conditioning load control method, system, readable storage medium and air conditioning unit described in the present application can realize active energy regulation, thereby avoiding the problems of large load fluctuations and difficulty in stabilizing accuracy during passive regulation. At the same time, it can also avoid the problem of increased energy consumption caused by repeated fluctuations of the system during passive regulation. This method is more accurate in energy output, can ensure that the air supply conditions match the demand conditions, the air conditioning runs more smoothly, and the system energy consumption is lower. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 This is a functional structure diagram of the air conditioning unit described in the embodiment of the present application; Figure 2 This is a flow chart of an air conditioning load control method described in an embodiment of the present application; Figure 3 This is a schematic diagram of the structure of an air conditioning load control system described in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0014] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0015] like Figure 1 As shown, the opening of the return air valve is , which can control the opening according to the return air valve actuator, and can also provide feedback on the current opening according to the actuator. The opening of the fresh air valve is , which can control the opening according to the fresh air valve actuator, and can also provide feedback on the current opening according to the actuator. Usually, the air valve opening in the air conditioning control system can directly reflect the air volume, but in actual use, the air valve opening also directly affects the system resistance, which ultimately leads to the unclear relationship between the air volume and the air valve opening angle. Therefore, it often relies more on experience and less on theoretical formulas.

[0016] According to the design requirements of general air conditioners, the air supply operating point of the air conditioner needs to deviate from the target operating point of the room. This is due to the existence of air supply temperature difference. For example, in summer, there are people or equipment in the clean room that dissipate heat, and there is radiation heat dissipation from the outdoor environment through windows or walls. This part of the load must be borne by the air supply, so there must be a supply air temperature difference. For example, in spring and autumn, the radiation heat dissipation from the outdoor environment will be significantly reduced, so the required supply air temperature difference will be reduced. Since the unit cannot predict how large the supply air temperature difference should be set, this value is constant in general air conditioning systems. This also results in the supply air temperature difference not being able to change flexibly according to the working conditions, which in turn results in the air conditioning load being able to be passively calculated based on the difference between the room working conditions and the set working conditions, and it is impossible to achieve active energy output control.

[0017] The air conditioning load control method described in the present application needs to rely on the return air volume sensor located in the return air duct to monitor the return air volume in real time. Through machine learning, the return air valve opening and the return air volume are continuously learned and compared, and error feedback is performed to ensure that there is an accurate correspondence between the return air valve opening and the return air volume. It can also self-learn and correct as the system resistance of the unit changes, thereby realizing active energy regulation, thereby avoiding problems such as large load fluctuations and difficulty in stabilizing accuracy during the passive regulation process, and at the same time avoiding the problem of increased energy consumption caused by repeated system fluctuations during the passive regulation process.

[0018] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0019] See also Figure 2 As shown, this embodiment provides an air conditioning load control method, which specifically includes the following steps: Step S101, calculating the fresh air enthalpy value and the return air enthalpy value according to the acquired fresh air information and return air information.

[0020] Specifically, in this embodiment, the air handling unit generally includes a mixing section, a filtering section, a surface cooling section, a heating section, a humidification section, a blower section, a medium-efficiency section, an air supply section, etc. The method requires the installation of analog air valves at the return air inlet and the fresh air inlet of the air-conditioning unit to calculate and adjust the return air volume and the fresh air volume.

[0021] The fresh air enthalpy value is calculated based on the fresh air temperature and fresh air humidity, which represents the working conditions of the outdoor environment at the time of sampling; the return air enthalpy value is calculated based on the return air temperature and return air humidity, which represents the actual air working conditions of the clean room at the time of sampling. This calculation process can be calculated using the current industry-common humid air calculation model CoolProp.

[0022] Due to the fresh air temperature Fresh air humidity Pre-intervention is required according to the local real-time weather conditions, such as pre-adjusting the fresh air valve (volume) according to the temperature and humidity change curves at different time periods of the day. Therefore, this embodiment takes the fresh air load as the target and pre-adjusts the fresh air volume by predicting the fresh air enthalpy value of the next time period, thereby avoiding system instability caused by sudden fluctuations in the fresh air working conditions.

[0023] Step S102, obtain the fresh air valve opening, return air valve opening and supply air volume of the air conditioner, calculate the fresh air volume and return air volume at the current moment according to the fresh air valve opening, return air valve opening and supply air volume, calculate the fresh air load based on the fresh air volume and fresh air enthalpy value, and calculate the return air load based on the return air volume and return air enthalpy value.

[0024] Specifically, in this embodiment, the fresh air volume and the return air volume at this time are calculated based on the fresh air valve opening, the return air valve opening and the supply air volume, and the fresh air load is calculated based on the fresh air volume and the fresh air enthalpy value, and the return air load is calculated based on the return air volume and the return air enthalpy value. The calculation formula is as follows: In the formula, Indicates the opening of the fresh air valve. Indicates the opening of the return air valve. Indicates the air supply volume. Indicates the fresh air volume, Indicates the return air volume. represents the fresh air enthalpy value, represents the return air enthalpy value, Indicates the fresh air load, Indicates return air load.

[0025] Step S103, predict and output the supply air enthalpy difference according to the pre-built neural network model, and obtain the predicted supply air enthalpy value according to the supply air enthalpy difference and the return air enthalpy value, calculate the supply air load according to the supply air enthalpy value and the supply air volume, and calculate the air load to be processed according to the fresh air load, return air load and supply air load.

[0026] Specifically, in this embodiment, the air supply enthalpy difference is predicted according to the pre-built neural network model, and then the predicted air supply enthalpy value is obtained. The air supply load is calculated according to the air supply enthalpy value and the air supply volume. The air load to be processed (i.e., air heat exchange amount) is calculated according to the fresh air load, the return air load and the air supply load. The specific calculation formula is as follows: In the formula, represents the supply air enthalpy difference, represents the supply air enthalpy value, Indicates the air supply load, Indicates air load.

[0027] In this step, this embodiment adopts an active load calculation method, which can perform load budgeting at the initial stage of load change, avoiding the lag of passive regulation. Furthermore, since the setting of the air supply enthalpy difference needs to be dynamically adjusted with changes in environmental conditions or seasons, in the present application method, the preset air supply enthalpy difference needs to be trained by BP neural network learning, using historical operating data, historical weather data and current data, and then derive a continuously evolving and improving model, thereby realizing a control strategy with different air supply enthalpy differences as the target under different working conditions.

[0028] Step S104: Calculate the water flow rate according to the air load to be processed and the inlet and outlet water temperature difference, and adjust the opening of the cold water valve according to the water flow rate to control the opening of the air conditioning refrigeration section and the reheating section.

[0029] Specifically, in this embodiment, the water flow rate is calculated according to the air load to be processed and the inlet and outlet water temperature difference, and the cold water valve opening is adjusted according to the water flow rate (the water valve opening is adjusted according to the inlet and outlet water temperature sensors of the inlet and outlet water pipelines of the refrigeration section, and the accurate output of the refrigeration capacity is achieved through water flow control) to control the predicted air supply load, and then control the opening of the refrigeration section and the reheating section of the air conditioner until the target temperature and humidity of the room are met; The water flow calculation formula is as follows: ; In the formula, is the specific heat capacity of water, Indicates the inlet and outlet water temperature difference, Indicates water flow.

[0030] It should be noted that, in this embodiment, according to the temperature that the room is expected to reach and humidity Calculate the target enthalpy of the room The calculation process can be calculated using the current industry-wide wet air calculation model CoolProp. The enthalpy value It represents the required air enthalpy of the room.

[0031] The method described in this embodiment uses a data model to predict the supply air temperature difference of the air-conditioning unit. The supply air temperature difference in different seasons, different times of the day, and even different numbers of people in the room can be estimated, and the calculated data can be used as the input parameter of energy control, thereby realizing active energy regulation, thereby avoiding the problems of large load fluctuations and difficulty in stabilizing accuracy in the passive regulation process, and at the same time, it can also avoid the problem of increased energy consumption caused by repeated fluctuations of the system in the passive regulation process.

[0032] In some implementations, constructing a neural network model specifically includes the following steps: Step S201, collect the set target temperature and target humidity, and collect the historical data of fresh air temperature, fresh air humidity, return air temperature, return air humidity, inlet water temperature, outlet water temperature and water valve opening, and construct a training data set.

[0033] Specifically, in this embodiment, by setting the target temperature and the target humidity, and collecting historical data such as the supply air temperature and humidity, fresh air temperature and humidity, return air temperature and humidity, inlet water temperature and outlet water temperature, and water valve opening for training, the standard calculation model does not require the specification of complex rules and has good adaptability to unknown working conditions.

[0034] Step S202: Use the training set data as independent variables and the supply air enthalpy difference data as dependent variables to train the VGG convolutional neural network model.

[0035] Step S203: input the independent variable data into the trained VGG convolutional neural network model, output the supply air enthalpy difference data, calculate the loss between the output supply air enthalpy difference data and the actual supply air enthalpy difference data, and use the back propagation optimization algorithm to update the network parameters, and calculate the minimized loss, and continuously train and iterate to update the network parameters.

[0036] Specifically, in this embodiment, the input data is calculated through a network structure such as a convolution layer and a pooling layer, and the predicted air supply enthalpy difference is output in the last layer.

[0037] The predicted air supply enthalpy difference is compared with the actual air supply enthalpy difference to calculate the loss, including L1 loss. The L1 loss function calculates the absolute value of the difference between the predicted air supply enthalpy difference and the actual air supply enthalpy difference, and then calculates the average. The calculation formula is as follows: L1 loss represents the mean absolute error between the predicted supply air enthalpy difference and the actual supply air enthalpy difference; The predicted air supply enthalpy difference is compared with the actual air supply enthalpy difference to calculate the loss, including the L2 loss. The L2 loss function calculates the square of the difference between the predicted air supply enthalpy difference and the actual air supply enthalpy difference, and then takes the average. The calculation formula is as follows: The L2 loss represents the mean square error between the predicted supply air enthalpy difference and the actual supply air enthalpy difference; Both loss functions can reflect the degree of difference between the predicted results and the true results, but L2 loss will emphasize large errors more, while L1 loss will tend to balance all errors.

[0038] By driving the network through the loss function, it can continuously learn to reduce the prediction error, thereby achieving better reconstruction effects and improving the accuracy of predicting the air supply enthalpy difference. By learning direct mapping, the iterative calculation steps are omitted. The iterative results can also be optimized by combining the iterative algorithm with the network learning residual mapping. Through end-to-end deep learning, the detection efficiency is improved.

[0039] At the same time, the back-propagation rule is used to calculate the contribution of each parameter to the loss, and the parameters are updated according to the Adam optimization algorithm to reduce the loss.

[0040] Step S204: input the real-time data into the trained VGG convolutional neural network model, and use the output air supply enthalpy difference as the target air supply enthalpy difference for energy regulation.

[0041] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0042] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present application further provides an air conditioning load control system.

[0043] like Figure 3 As shown, the air conditioning load control system comprises: The first calculation module 11 is configured to calculate the fresh air enthalpy value and the return air enthalpy value according to the acquired fresh air information and return air information; The second calculation module 12 is configured to obtain the opening of the fresh air valve, the opening of the return air valve and the supply air volume of the air conditioner, calculate the fresh air volume and the return air volume at this time according to the opening of the fresh air valve, the opening of the return air valve and the supply air volume, calculate the fresh air load based on the fresh air volume and the fresh air enthalpy value, and calculate the return air load based on the return air volume and the return air enthalpy value; The third calculation module 13 is configured to predict and output the supply air enthalpy difference according to the pre-built neural network model, and obtain the predicted supply air enthalpy value according to the supply air enthalpy difference and the return air enthalpy value, calculate the supply air load according to the supply air enthalpy value and the supply air volume, and calculate the air load to be processed according to the fresh air load, the return air load and the supply air load; The control module 14 is configured to calculate the water flow rate according to the air load to be processed and the inlet and outlet water temperature difference, and adjust the opening of the cold water valve according to the water flow rate to control the opening of the air conditioning refrigeration section and the reheating section.

[0044] For the convenience of description, the above system is described by dividing the functions into various modules. Of course, when implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0045] The system of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0046] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in any of the above embodiments.

[0047] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0048] The computer instructions stored in the storage medium of the above embodiments are used to enable the computer to execute the method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0049] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0050] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power / ground connections to the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device may be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application are to be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0051] Although the present application has been described in conjunction with specific embodiments of the present application, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the discussed embodiments.

[0052] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an air conditioning unit, including the air conditioning load control system proposed in the above-mentioned embodiments of the present application, and / or the readable storage medium proposed in the above-mentioned embodiments of the present application. Therefore, it has all the beneficial technical effects of the air conditioning load control system proposed in the above-mentioned embodiments of the present application and / or the readable storage medium proposed in the above-mentioned embodiments of the present application, and no further elaboration is made here.

[0053] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. An air conditioning load control method, characterized in that: include: Calculate the fresh air enthalpy value and the return air enthalpy value according to the acquired fresh air information and return air information; Obtaining the fresh air valve opening, return air valve opening and supply air volume of the air conditioner, calculating the fresh air volume and return air volume at the current moment according to the fresh air valve opening, return air valve opening and supply air volume, and calculating the fresh air load based on the fresh air volume and the fresh air enthalpy value, and calculating the return air load based on the return air volume and the return air enthalpy value; Predicting and outputting a supply air enthalpy difference according to a pre-built neural network model, and obtaining a predicted supply air enthalpy value according to the supply air enthalpy difference and the return air enthalpy value, calculating the supply air load according to the supply air enthalpy value and the supply air volume, and calculating the air load to be processed according to the fresh air load, the return air load and the supply air load; The water flow rate is calculated according to the air load to be processed and the inlet and outlet water temperature difference, and the cold water valve opening is adjusted according to the water flow rate to control the opening of the air conditioning refrigeration section and the reheating section.

2. The method according to claim 1, characterized in that The step of calculating the fresh air enthalpy value and the return air enthalpy value according to the acquired fresh air information and return air information includes: The fresh air temperature, fresh air humidity, return air temperature and return air humidity at the current moment are obtained, and the fresh air enthalpy value is calculated according to the fresh air temperature and the fresh air humidity, and the return air enthalpy value is calculated according to the return air temperature and the return air humidity.

3. The method according to claim 1, characterized in that The fresh air volume and return air volume at this time are calculated according to the fresh air valve opening, return air valve opening and supply air volume. The specific calculation formula is as follows: ； ； The fresh air load is calculated based on the fresh air volume and the fresh air enthalpy value, and the return air load is calculated based on the return air volume and the return air enthalpy value, and the calculation formula is as follows; ； ； In the formula, Indicates the opening of the fresh air valve. Indicates the opening of the return air valve. Indicates the air supply volume. Indicates the fresh air volume, Indicates the return air volume. represents the fresh air enthalpy value, represents the return air enthalpy value, Indicates the fresh air load, Indicates return air load.

4. The method according to claim 3, characterized in that: Taking the fresh air load as a target, the fresh air volume is pre-adjusted by predicting the fresh air enthalpy value of the next time period.

5. The method according to claim 3, characterized in that: The predicted supply air enthalpy value is obtained according to the supply air enthalpy difference and the return air enthalpy value, and the supply air load is calculated according to the supply air enthalpy value and the supply air volume. The specific calculation formula is as follows: ； ； The air load to be processed is calculated based on the fresh air load, return air load and supply air load, and the calculation formula is as follows: ； In the formula, represents the supply air enthalpy difference, represents the supply air enthalpy value, Indicates the air supply load, Indicates air load.

6. The method according to claim 5, characterized in that The water flow is calculated according to the air load to be processed and the inlet and outlet water temperature difference, and the opening of the cold water valve is adjusted according to the water flow, including: The water flow rate is calculated according to the air load to be processed and the inlet and outlet water temperature difference, and the cold water valve opening is adjusted according to the water flow rate to control the predicted air supply load, thereby controlling the opening of the air conditioning cooling section and the reheating section until the target temperature and humidity of the room are met; The water flow calculation formula is as follows: ； In the formula, is the specific heat capacity of water, Indicates the inlet and outlet water temperature difference, Indicates water flow.

7. The method according to claim 1, characterized in that: Collect the set target temperature and target humidity, and collect the historical data of fresh air temperature, fresh air humidity, return air temperature, return air humidity, inlet water temperature, outlet water temperature and water valve opening, and build a training data set; The training set data is used as an independent variable and the air supply enthalpy difference data is used as a dependent variable to train a VGG convolutional neural network model; Input the independent variable data into the trained VGG convolutional neural network model, output the supply air enthalpy difference data, calculate the loss between the output supply air enthalpy difference data and the actual supply air enthalpy difference data, and use the back propagation optimization algorithm to update the network parameters and calculate the minimum loss, and continuously train and iterate to update the network parameters; The real-time data is input into the trained VGG convolutional neural network model, and the output air supply enthalpy difference is used as the target air supply enthalpy difference for energy regulation.

8. An air conditioning load control system, characterized in that: include: A first calculation module is configured to calculate a fresh air enthalpy value and a return air enthalpy value according to the acquired fresh air information and return air information; a second calculation module, configured to obtain the opening of the fresh air valve, the opening of the return air valve and the supply air volume of the air conditioner, calculate the fresh air volume and the return air volume at this time according to the opening of the fresh air valve, the opening of the return air valve and the supply air volume, calculate the fresh air load based on the fresh air volume and the fresh air enthalpy value, and calculate the return air load based on the return air volume and the return air enthalpy value; a third calculation module, configured to predict and output a supply air enthalpy difference according to a pre-built neural network model, obtain a predicted supply air enthalpy value according to the supply air enthalpy difference and the return air enthalpy value, calculate the supply air load according to the supply air enthalpy value and the supply air volume, and calculate the air load to be processed according to the fresh air load, the return air load and the supply air load; The control module is configured to calculate the water flow rate according to the air load to be processed and the inlet and outlet water temperature difference, and adjust the opening of the cold water valve according to the water flow rate to control the opening of the air conditioning refrigeration section and the reheating section.

9. A non-transitory computer-readable storage medium, characterized in that: in, The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

10. An air conditioning unit, characterized in that: include: The air conditioning load control system according to claim 8; and / or; The readable storage medium as claimed in claim 9.

Images