A feedforward refrigeration system for controlling refrigeration capacity of different building units

Abstract

The application provides a feedforward refrigeration system for controlling refrigeration capacity of different building units, which comprises an evaporator, a condenser, a compressor, an expansion valve, a water distributor and a water collector, the condenser, the expansion valve, the evaporator and the compressor are sequentially connected to form a refrigeration cycle, water in the water collector enters the water distributor after heat release in the evaporator, the water distributor is provided with multiple water distribution pipes, the water distribution pipes are connected to heat exchangers of different building units, heat exchange is carried out between the heat exchangers and air entering the heat exchangers to form low-temperature air, then the low-temperature air is transported to the building units to carry out refrigeration, and the water after heat exchange enters the water collector, valves are arranged on the water distribution pipes and used for controlling water quantity entering different building units. The refrigeration system adjusts refrigeration capacity by adjusting refrigeration water flow, the control valves on the water distribution pipes control the refrigeration water flow, the percentage of output predicted load in total load of the air conditioning system is obtained according to predicted load calculation, the percentage of valve opening degree is determined, and the valve opening degree is adjusted according to the percentage.

Description

Technical Field

[0001] This invention relates to the field of refrigeration technology, and more specifically to a compression refrigeration air supply system. Background Technology

[0002] Large buildings, especially large public buildings, generally suffer from high energy consumption and low energy efficiency. Especially during the cooling season, due to the unpredictability and fluctuation of the building's cooling load, air conditioning units often operate in a traditional fixed mode, resulting in a large amount of energy waste.

[0003] The current distribution of cooling capacity in central air conditioning systems, i.e., the cooling capacity during cooling mode, is generally adjusted based on the temperature controllers located at the air conditioning terminals. However, this adjustment method suffers from low precision and is prone to resource waste.

[0004] Existing technologies also provide cooling capacity allocation techniques. For example, CN104566785A discloses a method that uses devices such as a cloud server, mobile communication terminal, indoor temperature data acquisition device, outdoor temperature data acquisition device, and display with display control receiving module to enable central air conditioning to perform comprehensive adjustment and analysis based on user needs and the user's indoor and outdoor temperature and humidity, so as to save air conditioning resources to the maximum extent while meeting user needs. CN114264045A discloses a control module used to adjust the operating parameters of the central air conditioning system according to the results of data processing and comparison by the data module to achieve optimal energy efficiency; the monitoring module is used to monitor the changes in the energy efficiency of the central air conditioning system and the standard model, and to issue an alarm message when the actual energy efficiency changes deviate from the standard model. CN101158495A provides a fully enclosed compressor refrigeration system capable of two-stage cooling capacity regulation. It includes a compressor, condenser, expansion valve, and evaporator, connected by piping to form a sealed system. It also includes a hot gas bypass circuit, which consists of a solenoid valve and a throttling element connected in series. The inlet of the solenoid valve is connected to the high-pressure discharge pipe of the compressor, and the outlet of the throttling element is connected to the piping between the expansion valve and the evaporator. A temperature sensor is installed at the refrigerant outlet of the evaporator. The control signal output terminal of this temperature sensor is connected to the control signal input terminal of the solenoid valve.

[0005] The existing cooling capacity distribution technologies described above suffer from problems such as complex structures and inaccurate control. Therefore, there is an urgent need for a refrigeration system capable of comprehensively adjusting cooling capacity to maximize energy savings while meeting user needs. Summary of the Invention

[0006] The purpose of this invention is to provide a refrigeration system that comprehensively regulates cooling capacity in order to maximize energy saving while meeting user needs.

[0007] To achieve the above objectives, the technical solution of the present invention is as follows:

[0008] A feedforward refrigeration system for controlling the cooling capacity of different building units includes an evaporator, a condenser, a compressor, an expansion valve, a water distributor, and a water collector. The condenser, expansion valve, evaporator, and compressor are connected in sequence to form a refrigeration cycle. Water in the water collector enters the water distributor after releasing heat in the evaporator. The water distributor is equipped with multiple water distribution pipes, which are connected to heat exchangers in different building units. In the heat exchangers, water exchanges heat with the air entering the heat exchangers to form low-temperature air, which is then delivered to the building units for cooling. The water after heat exchange enters the water collector. Valves are installed on the water distribution pipes to control the amount of water entering different building units.

[0009] As an improvement, the valve is connected to the control system, which automatically controls the valve opening based on the cooling capacity required by the building unit.

[0010] As an improvement, when the cooling capacity required by a building unit increases, the opening degree of the automatic control valve increases; when the cooling capacity required by a building unit decreases, the opening degree of the automatic control valve decreases; and when the cooling capacity required by a building unit increases, the opening degree of the automatic control valve increases.

[0011] As an improvement, the return air duct is arranged perpendicularly to the fresh air duct. A mixing component is installed in the return air duct, and the mixing component is located upstream of the connection between the fresh air duct and the return air duct. The mixing component is a blade structure, which includes multiple blades. The extension direction of the gap between adjacent blades is parallel to the central axis of the fresh air duct. A fresh air mixing device is installed in the fresh air duct. The fresh air mixing device is a blade structure, located upstream of the connection between the fresh air ducts. The blade structure has multiple blades, and the extension direction of the flow channel between adjacent blades is parallel to the central axis of the return air duct.

[0012] As an improvement, the spacing between the return air channels formed by adjacent blades of the homogenizing component is different. As the distance from the fresh air duct increases, the spacing between the return air channels formed by adjacent blades becomes smaller and smaller.

[0013] As an improvement, the spacing of the return air duct can be set by adjusting the size of the blades.

[0014] As an improvement, the width of the same blade increases as it gets further away from the fresh air duct, thereby reducing the spacing between adjacent blades.

[0015] As an improvement, the cooling capacity required by the building unit is determined based on a historical cooling load correction model.

[0016] As an improvement, the load model of the historical cooling load calculation model has three main branches: building load branch, heat source load branch, and fresh air load branch.

[0017] A method for controlling a refrigeration system includes the following steps:

[0018] The first step is to collect historical data;

[0019] The second step is to establish a historical cooling load calculation model;

[0020] The third step is to build a training model.

[0021] Compared with the prior art, the present invention has the following advantages:

[0022] 1. This refrigeration system regulates the cooling capacity by adjusting the flow rate of the chilled water. The control valve on the water distribution pipe controls the flow rate of the chilled water. Based on the predicted load, the percentage of the output predicted load to the total load of the air conditioning system is calculated, the valve opening percentage is determined, and the valve opening is adjusted accordingly.

[0023] 2. This invention uses a method based on historical cooling load data to predict cooling capacity. The historical data includes cooling load information under different operating conditions in the past, such as the impact of different seasons, weather conditions, and indoor occupancy density on cooling demand. By integrating this data, the patterns and rules of load changes can be identified, avoiding the problem of traditional prediction methods relying too much on meteorological and time variables. This makes data acquisition more convenient and faster, while reducing the need for physical models and improving the universality and accuracy of load prediction. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of the overall structure of the refrigeration system of the present invention.

[0025] Figure 2 This is a schematic diagram of the mixed return air and fresh air structure of the present invention.

[0026] Figure 3 This is a schematic diagram of the cooling capacity prediction module of the refrigeration system of the present invention. Detailed Implementation

[0027] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0028] Unless otherwise specified, in this article, " / " represents division, and "×" and "*" represent multiplication.

[0029] Figure 1A feedforward refrigeration system for controlling the cooling capacity of different building units is demonstrated. The system includes an evaporator 1, a condenser 2, a compressor 3, an expansion valve 4, a water distributor 5, and a water collector 6. The evaporator 1, condenser 2, compressor 3, and expansion valve 4 are connected sequentially to form a refrigeration cycle system. Water in the water collector 6 enters the evaporator 3, exchanges heat with the refrigerant in the evaporator 1, and then releases heat before entering the water distributor 5. The water distributor 5 is equipped with multiple water distribution pipes 7, which connect to heat exchangers 8 of different building units 9. Water in the water distributor 5 enters the heat exchangers 8 through the water distribution pipes 7, exchanges heat with the air entering the heat exchangers 8, forming low-temperature air. This low-temperature air is then delivered to the building units 9 for cooling. The water after heat exchange in the heat exchangers 8 enters the water collector, thus forming a water circulation system. Valves are installed on the water distribution pipes 7 to control the amount of water entering different building units 9.

[0030] This invention controls the cooling capacity of different units by setting valves on the water distribution pipe. The cooling capacity is controlled by a single control valve that regulates the flow of cold water, resulting in a simple and reliable control structure.

[0031] As an improvement, the valve is connected to the control system, which automatically controls the valve opening based on the cooling capacity required by the building unit. This intelligent control of the valve opening achieves smart control.

[0032] As an improvement, when the cooling capacity required by a building unit increases, the opening degree of the automatic control valve increases; when the cooling capacity required by a building unit decreases, the opening degree of the automatic control valve decreases; and when the cooling capacity required by a building unit increases, the opening degree of the automatic control valve increases. Through the above intelligent control, accurate regulation of cooling capacity is achieved.

[0033] As an improvement, the air entering the heat exchanger consists of 50-80% return air and 20-50% fresh air, which are mixed before entering the heat exchanger. Because the return air is cooler than the outdoor fresh air, the cooling capacity of the return air can be fully utilized and energy saved by returning the exhaust air from the building units to the heat exchanger.

[0034] Figure 2 A schematic diagram of the ductwork for mixing return air and fresh air is shown. (For example...) Figure 2 As shown, the return air duct 10 is arranged perpendicularly to the fresh air duct 11. A mixing component 12 is provided in the return air duct 10. The mixing component 12 is located upstream of the connection between the fresh air duct and the return air duct. The mixing component 12 is a blade structure, which includes multiple blades. The extension direction of the gap between adjacent blades is parallel to the central axis of the fresh air duct.

[0035] A fresh air mixing device 13 is installed in the fresh air duct 11. The fresh air mixing device 13 has a blade structure and is located upstream of the connection point of the fresh air duct 11. The blade structure has multiple blades, and the extension direction of the flow channel between adjacent blades is parallel to the central axis of the return air duct. Through the above arrangement, the gaps between the distribution components of the return air duct and the fresh air duct are parallel to each other, which can reduce the impact and noise during fluid mixing.

[0036] As an improvement, the return air layer containing the return air distribution component and the fresh air layer containing the fresh air distribution component are staggered. This staggered arrangement ensures that during mixing, the fresh air flowing from the fresh air distribution component enters precisely between the two staggered return air layers, while the return air flowing from the return air distribution layer enters precisely between the adjacent fresh air layers. This staggered arrangement of the return air layer and the fresh air layer results in a more uniform distribution, and also reduces noise and impact.

[0037] The spacing between the return air channels formed by adjacent blades of the homogenizing component 12 is different. As the distance from the fresh air duct increases, the spacing between the return air channels formed by adjacent blades becomes smaller and smaller.

[0038] Near the fresh air outlet, the fresh air flow is at its maximum, resulting in the best mixing of fresh and return air. However, this leads to uneven mixing overall. As the distance from the outlet increases, the amount of fresh air decreases, and the mixing deteriorates, resulting in poor overall mixing performance. This invention addresses this by improving the blade spacing, causing the return air flow to decrease gradually along the direction of the fresh air entering the return air duct, thus achieving balanced mixing throughout the entire area and improving overall mixing uniformity.

[0039] As an improvement, the spacing of the return air duct can be set by adjusting the size of the blades. For example, the wider the blade is, the further away it is from the fresh air duct, and the spacing between adjacent blades can be reduced by increasing the width.

[0040] Based on existing air conditioners, this invention creatively proposes a mixed regulation system for fresh air and return air, which includes two opposing regulating devices at the upstream and downstream ends to achieve dual control and dual flow equalization, resulting in a significant equalization effect between return air and fresh air and high economic benefits.

[0041] Preferably, the spacing between adjacent blades forming the return airflow channel increases with increasing distance from the fresh air duct. This variation in spacing improves the mixing ratio and achieves better overall uniformity.

[0042] Preferred, such as Figure 2As shown, the return air duct is equipped with a return air flow equalization device 14, which is located downstream of the connection between the fresh air duct and the return air duct. The flow equalization device 14 has a multi-blade structure. As an improvement, the flow channel spacing between adjacent blades farther away from the fresh air duct is larger. With this arrangement, the mixed air flows as far away from the fresh air duct as possible, thereby improving the situation where the mixed air is concentrated near the fresh air duct after mixing, and making the mixed air evenly distributed throughout the return air duct.

[0043] As an improvement, the spacing between adjacent blades of the return air equalization device 14 increases progressively with distance from the fresh air duct. This configuration further enhances the even distribution of mixed air throughout the return air duct.

[0044] As an improvement, the flow equalization device 14 channels and the mixing component 12 channels are arranged perpendicularly to each other. Because the two sets of regulating devices are perpendicular to each other, the flow can be diffused in all four directions, both horizontally and vertically, resulting in a higher degree of homogenization.

[0045] This invention includes two devices, upstream and downstream, that enable dual control and dual flow equalization, resulting in a significant effect on the equalization of return and fresh air ratios. Furthermore, the flow equalization device ensures uniform distribution throughout the entire duct. The cooperation of these two devices achieves flow control, uniform proportional distribution, and uniform fuel distribution throughout the entire duct.

[0046] Preferably, multiple mixing devices 14 are provided, and the gaps between adjacent blades in the mixing devices become smaller and smaller along the flow direction of the fluid in the return air duct. By varying the amplitude, it is possible to further ensure uniform flow distribution while maintaining low flow resistance.

[0047] This application also discloses a refrigeration system for cooling capacity control based on cooling load prediction using a historical cooling load correction model.

[0048] Existing methods for predicting cooling load still have some shortcomings: When calculating building cooling load, the main considerations are fresh air cooling load, occupant cooling load, building envelope cooling load, and internal heat source cooling load. The main influencing factors of these cooling loads include the physical properties of the building envelope, outdoor temperature and humidity, and indoor heat sources. When calculating real-time building cooling load, since building physical properties do not change over time, we can only consider changes in outdoor temperature and humidity and changes in indoor heat sources. For office buildings, the main indoor heat source—occupants—exhibits certain regularities: the number of people, their dwell time, and their activity types all cycle weekly; similarly, outdoor temperature and humidity also exhibit certain regularities, cycling annually. Based on the cyclical nature of these important influencing factors, historical cooling loads are of great reference value for cooling load prediction.

[0049] One of the objectives of this invention is to provide a method for predicting building cooling load based on a historical cooling load correction model.

[0050] The first step is to collect historical data. Define the air-conditioning period and collect relevant information during that period, including historical data on personnel, weather, and building characteristics. The personnel module mainly collects data on the number of people and their activity types; the building module mainly collects data on building structure, interior and exterior wall area, building material properties, building location, and window / door leakage rates; the weather module mainly collects data on outdoor temperature and humidity, solar irradiance, and wind direction.

[0051] The second step is to establish a historical cooling load calculation model. The load model has three main branches: building load branch, heat source load branch, and fresh air load branch.

[0052] The main calculation formulas for the cooling load branch of a building are as follows:

[0053] Q = KF·(t) wq -t n )k a k ρ

[0054] Where: Q—hourly cooling load of the exterior wall or roof, W;

[0055] F – Area of ​​the exterior wall or roof, in meters 2 ;

[0056] K – Heat transfer coefficient of exterior walls or roof, W / (m²) 2 ·℃)

[0057] t wq — Hourly cooling load calculation temperature of exterior walls or roof, in °C;

[0058] t n —Indoor calculated temperature, °C;

[0059] k a —This is a correction value for the heat transfer coefficient of the outer surface;

[0060] k ρ — This is a correction for the absorption coefficient.

[0061] Extract the interior and exterior wall areas from the building characteristics module, determine the heat transfer coefficient of the exterior wall or roof based on the building's physical properties, and combine the outdoor temperature data from the meteorological conditions module as the hourly cooling load calculation temperature for the exterior wall or roof. The indoor calculation temperature is a constant value, thus accurately outputting the historical value of this part of the cooling load.

[0062]

[0063] In the formula: —Hourly cooling load of unsteady-state heat transfer through exterior windows, W

[0064] K – Heat transfer coefficient of the exterior window, W / (m²) 2 ·K);

[0065] F – External window heat transfer area, m² 2 ;

[0066] t wlc — Hourly cooling load calculation temperature for exterior windows, in °C;

[0067] t n —Design temperature for air-conditioned areas in summer, °C.

[0068] C a —Effective area coefficient;

[0069] C s —The shading coefficient of the window glass;

[0070] C i —The shading coefficient of the window shading system;

[0071] C LQ —Cooling load coefficient of window glass;

[0072] D jmax —Maximum solar radiation heat gain factor at each latitude zone during summer, W / m 2 .

[0073] The exterior window area is determined by extracting data from the building characteristics module and combining it with the building property parameters from the building characteristics mode. The heat transfer coefficient of the exterior window is then determined. Finally, the outdoor temperature data from the meteorological conditions module is used as the calculation temperature for the hourly cooling load of the exterior window. The design temperature of the air-conditioned area is a constant value, and the hourly cooling load of the exterior window under unsteady-state heat transfer is calculated. The hourly cooling load of the exterior window under unsteady-state heat transfer is then summed with the cooling load of the exterior wall to output the partial cooling load of the building.

[0074] The main calculation formulas for heat source load branches are:

[0075] Q r =Q S ·C CLrt +Q q

[0076] Q s =n·Φ·Q rt

[0077] Q q =n·Φ·q

[0078] Q r —Cooling load caused by heat dissipation from the human body, W;

[0079] Q S ·C CLrt —Sensible heat load, W;

[0080] C CLrt —Human body sensible heat dissipation cooling load coefficient;

[0081] Q q —Latent heat cooling load, W;

[0082] Φ—Clustering coefficient, taken as 0.93;

[0083] Q rt —Human body heat dissipation, W;

[0084] n—Number of people in the air-conditioned room;

[0085] q – the latent heat emitted by each person, W.

[0086] The sensible heat dissipation cooling load coefficient and cluster coefficient in the variable input parameters are determined by national standards and specifications. The number of people in the air-conditioned room and the latent heat dissipation per person are determined by the personnel history module, the personnel activity type, and the latent heat dissipation of different activity types of personnel by querying the air conditioning design specifications. Finally, the total personnel load is calculated by the heat source load branch.

[0087] The main calculation formulas for the fresh air load branch are:

[0088]

[0089] ρ w —Density at dry-bulb temperature for calculating outdoor air conditioning in summer;

[0090] L – Fresh air volume, m 3 / h;

[0091] t w —Outdoor air conditioning calculation dry bulb temperature, °C;

[0092] t n —Indoor calculated temperature, °C;

[0093] The fresh air density and outdoor dry-bulb temperature are obtained from meteorological modes. To ensure that the indoor air quality reaches a high standard, the fresh air volume is generally taken as 20%-50% of the total supply air volume, preferably more than 40%. The indoor calculation temperature is selected according to national standards, and the fresh air load is finally obtained.

[0094] The total building load is obtained by summing all the branch loads, and a database of cooling loads and corresponding hours is established. To ensure the reliability of the predicted load, the database should contain at least five years of historical data. Since the annual variation patterns are generally similar, the historical data should be coded and entered in annual units.

[0095] The third step is to establish a training model. First, the historical information of the time-varying cold load and the number of hours in the feature extraction network are used as samples input into the neural network system. The predicted load output value 'a' is calculated using the following formula.

[0096]

[0097] Where, x i The input variable is the historical real-time cooling load, w0 is the bias term, and w i It assigns weights to each input variable, with the weights w initialized randomly. i and bias b i The output variable is the predicted future cooling load. Five hidden neurons are set, and the number of iterations is 60,000. Sample data is input into the network and processed... After computation, the input is fed into the hidden layer. The function f is a non-linear activation function applied on the sum of products, used to introduce non-linearity into the sum of the inputs and their corresponding weights. Stronger non-linearity can be achieved by using multiple hidden layers. Setting f to the sigmoid function, after activation, the final output is the predicted value through weight allocation and bias summation. The mean squared error (MSE) between the output value and the sample value is calculated. y i1 y1 is the predicted load obtained after calculation, and y2 is the cooling load in the sample. Substituting the predicted load and the sample load into the above formula, the error is finally obtained. Multiple errors are added together, and through continuous iteration, the minimum value of the error is found according to the negative gradient direction. This determines the final weight and bias of the model. The prediction model is repeatedly trained through training set data to obtain the optimal model structure and parameter combination, thus obtaining the final cooling load prediction result.

[0098] The refrigeration system includes a cooling water circulation system and a chilled water circulation system, which together form a water circulation system. The water circulation system is equipped with two screw chiller units, one in operation and one on standby, along with two chilled water pumps, two cooling water pumps, and two cooling towers. Chilled water is cooled by cooling water in the chiller units and then enters a manifold, where it exchanges heat with the air in the combined air conditioning units. After being heated, it is pressurized by the chilled water pumps and returned to the chiller units, completing the chilled water circulation. Cooling water, after acquiring heat from the chilled water in the chiller units, enters the cooling towers, is cooled, and then pressurized by the cooling water pumps before returning to the chiller units, completing the cooling water circulation. The air circulation system uses an all-air system. Chilled water is transported to the corresponding floors of the building via the water system and then enters the air conditioning units on those floors for heat exchange. The air is collected, mixed, and then exchanged with the chilled water for cooling. A single-pass return air dew point supply method is used to determine the supply air state point. Once the supply air state is reached, it is distributed to the relevant rooms through air ducts and diffusers.

[0099] This refrigeration system regulates its cooling capacity by adjusting the chilled water flow rate through valves on the distribution pipe. These valves are controlled over continuous time intervals of equal length. Based on the predicted load, the percentage of the predicted output load relative to the total load of the air conditioning system is calculated, and the valve opening is adjusted accordingly. An improved approach is to determine the valve opening percentage over several time intervals, which should correspond to the predicted output load time intervals. The adjustment threshold is between 60% and 100%, meaning the chilled water flow rate regulating valve opening is between a minimum opening of 60% and a maximum opening of 100%. For example, the preset first range can be 60-80%, and the preset first adjustment threshold is 80% of the maximum opening of the regulating valve. If the predicted load rate is lower than 60%, the regulating valve is adjusted within the preset first range. When the predicted load rate is greater than 60%, the regulating valve should be adjusted between the second preset threshold, which is 80-100%. The chilled water outlet temperature is directly controlled by the chiller unit. The chiller unit should include a temperature sensor and an electronic valve. The chilled water outlet temperature is controlled in continuous time intervals of the same length. The load percentage is determined by the predicted load, the most suitable outlet temperature is matched, and the electronic valve is opened after the temperature is monitored by the temperature sensor and the adjustment requirements are met.

[0100] While the present invention has been disclosed above with reference to preferred embodiments, it is not limited thereto. Any person skilled in the art can make various modifications and alterations without departing from the spirit and scope of the invention; therefore, the scope of protection of the present invention should be determined by the scope defined in the claims.

Claims

1. A feedforward refrigeration system for controlling the cooling capacity of different building units, comprising an evaporator, a condenser, a compressor, an expansion valve, a water distributor, and a water collector, wherein the condenser, expansion valve, evaporator, and compressor are sequentially connected to form a refrigeration cycle; water in the water collector enters the water distributor after releasing heat in the evaporator; the water distributor is equipped with multiple water distribution pipes, which connect to heat exchangers of different building units, where heat exchange occurs between the water and air entering the heat exchangers to form low-temperature air, which is then delivered to the building units for cooling; the water after heat exchange enters the water collector; valves are installed on the water distribution pipes to control the amount of water entering different building units; the system includes a return air duct for return air and a fresh air duct for fresh air; the air entering the heat exchangers comprises 50-80% return air and 100% fresh air. 20-50% of the fresh air, return air, and fresh air are mixed before entering the heat exchanger; the return air duct is perpendicular to the fresh air duct, and a homogenizing component is installed in the return air duct, located upstream of the connection point between the fresh air duct and the return air duct; the homogenizing component is a blade structure, comprising multiple blades, with the extension direction of the gap between adjacent blades parallel to the central axis of the fresh air duct; a fresh air mixing device is installed in the fresh air duct, also a blade structure, located upstream of the connection point, with multiple blades, and the extension direction of the flow channel between adjacent blades parallel to the central axis of the return air duct; the spacing of the return air flow channels formed by adjacent blades of the homogenizing component varies, decreasing with increasing distance from the fresh air duct.

2. The refrigeration system as described in claim 1, characterized in that, The valve is connected to the control system, which automatically controls the valve opening based on the cooling capacity required by the building unit.

3. The refrigeration system as described in claim 2, characterized in that, When the cooling capacity required by a building unit increases, the opening degree of the automatic control valve increases; when the cooling capacity required by a building unit decreases, the opening degree of the automatic control valve decreases.

4. The refrigeration system as described in claim 1, characterized in that, The spacing of the return air duct can be set by adjusting the size of the blades.

5. The refrigeration system as described in claim 4, characterized in that, The wider the blade is, the further away it is from the fresh air duct, thus reducing the spacing between adjacent blades.

6. The refrigeration system as described in claim 2, characterized in that, The required cooling capacity for a building unit is determined based on a historical cooling load correction model.

7. The refrigeration system as described in claim 6, characterized in that, The load model of the historical cooling load calculation model has three main branches: building load branch, heat source load branch, and fresh air load branch.

8. A control method for a refrigeration system as described in any one of claims 1-7, comprising the following steps: The first step is to collect historical data; The second step is to establish a historical cooling load calculation model; The third step is to build a training model.

Images