AI-based central air conditioning system regulation and control method, equipment, medium and product

Abstract

The invention discloses an AI-based central air conditioning system regulation and control method, equipment, a medium and a product. The method comprises the steps that real-time environment parameters matched with the central air conditioning system are obtained in real time, and current operation parameters of linkage control equipment in the central air conditioning system are obtained; inputting the real-time environment parameters and the current operation parameters into a pre-constructed AI computing power large model, and performing real-time calculation through linkage calculation among a plurality of functional sub-models in the AI computing power large model to obtain target regulation and control parameters corresponding to linkage control equipment; and parameter adjustment is conducted on the matched linkage control equipment according to all the target regulation and control parameters, so that the central air conditioning system is controlled to achieve energy-saving work on the premise that the work requirement is met. According to the technical scheme provided by the embodiment of the invention, an accurate AI calculation power large model is innovatively established for the central air-conditioning system, so that efficient output, transmission, distribution and heat exchange of energy among linkage control equipment in the central air-conditioning system are realized, and energy conservation of the system is realized.

Description

Technical Field

[0001] The present invention relates to the field of air conditioning control, and in particular to a central air conditioning system control method, equipment, medium and product based on AI (Artificial Intelligence). Background Art

[0002] In the central air-conditioning system, there are five groups of equipment, including the refrigeration main unit, chilled water delivery loop, cooling water delivery loop, cooling tower heat dissipation loop and terminal heat exchange equipment. These devices work together to provide a comfortable and efficient heating and cooling environment for the building.

[0003] The operation of a central air conditioning system is influenced by numerous parameters, including the outdoor environment, cooling tower heat exchange, cooling water delivery, heat exchange on the condensing side of the main unit, chilled water delivery, heat exchange at the terminal, terminal environmental parameters, and terminal usage habits. These parameters, coupled with each other, collectively determine the operating efficiency and energy consumption of the central air conditioning system.

[0004] During the development of this invention, the inventors discovered that conventional central air conditioning control systems primarily focus on simple control and adjustment of the operating parameters of various devices, often overlooking the impact of inter-device coupling. Furthermore, parameters such as indoor load characteristics, user habits, and outdoor weather conditions are crucial for the energy-efficient operation of central air conditioning, but conventional control systems struggle to respond promptly to these changes. Summary of the Invention

[0005] The embodiments of the present invention provide an AI-based central air-conditioning system control method, equipment, medium and product to achieve efficient energy output, distribution and heat exchange between various devices in the central air-conditioning system, thereby achieving the goal of energy saving in the central air-conditioning system.

[0006] According to one aspect of an embodiment of the present invention, a method for controlling a central air-conditioning system based on AI is provided, the method comprising:

[0007] Obtain real-time environmental parameters that match the central air-conditioning system, and obtain the current operating parameters of each linkage control device in the central air-conditioning system;

[0008] Input the real-time environmental parameters and current operating parameters into the pre-built AI computing power model. Through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time.

[0009] Adjust the parameters of the matching linkage control equipment according to the target control parameters to control the central air-conditioning system to achieve energy saving while meeting the working requirements.

[0010] According to another aspect of an embodiment of the present invention, there is provided an AI-based central air conditioning system control device, comprising:

[0011] The parameter acquisition module is used to obtain the real-time environmental parameters that match the central air-conditioning system and the current operating parameters of each linkage control device in the central air-conditioning system;

[0012] The control parameter calculation module is used to input real-time environmental parameters and current operating parameters into the pre-built AI computing power model. Through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time;

[0013] The parameter adjustment module is used to adjust the parameters of the matching linkage control equipment according to each target control parameter, so as to control the central air-conditioning system to achieve energy saving while meeting the working requirements.

[0014] According to another aspect of an embodiment of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the AI-based central air-conditioning system control method described in any embodiment of the present invention.

[0018] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the AI-based central air-conditioning system control method described in any embodiment of the present invention when executed.

[0019] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the steps of the AI-based central air-conditioning system control method as described in any embodiment of the present invention.

[0020] The technical solution of the embodiment of the present invention obtains real-time environmental parameters that match the central air-conditioning system in real time, and obtains the current operating parameters of each linkage control device in the central air-conditioning system; inputs the real-time environmental parameters and each current operating parameter into a pre-built AI computing power big model, and through the linkage calculation between multiple functional sub-models in the AI ​​computing power big model, obtains the target control parameters corresponding to each linkage control device in real time; the technical means of adjusting the parameters of the matching linkage control devices according to each target control parameter, innovatively establishes an accurate AI computing power big model for the central air-conditioning system, so that the energy is efficiently output, distributed and exchanged between the linkage control devices in the central air-conditioning system, which can control the central air-conditioning system to achieve the goal of energy saving while meeting work requirements, and can perform more intelligent and personalized control of the central air-conditioning system to improve the operating efficiency of the entire central air-conditioning system.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a flow chart of an AI-based central air-conditioning system control method provided according to an embodiment of the present invention;

[0024] Figure 2 is a flow chart of another AI-based central air-conditioning system control method provided according to an embodiment of the present invention;

[0025] Figure 3 1 is a schematic structural diagram of an AI-based central air-conditioning system control device provided according to an embodiment of the present invention;

[0026] Figure 4 2 is a schematic diagram of the structure of an electronic device that implements the AI-based central air-conditioning system control method of an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Figure 1 A flowchart of an AI-based central air-conditioning system control method provided in an embodiment of the present invention. This embodiment is applicable to situations where the operating parameters of each linkage control device in the central air-conditioning system are adjusted in real time based on the AI ​​computing power large model and real-time environmental parameters. The method can be executed by an AI-based central air-conditioning system control device, which can be implemented in the form of hardware and / or software and can generally be configured in an electronic device with data processing capabilities. The electronic device can be a terminal or a server and is used in conjunction with the central air-conditioning system.

[0030] Correspondingly, such as Figure 1 As shown, the method may include:

[0031] S110 , obtaining real-time environmental parameters that match the central air-conditioning system, and obtaining current operating parameters of each linkage control device in the central air-conditioning system.

[0032] A central air conditioning system is a centralized air conditioning system that provides air conditioning services to one or more areas through one or more central units. This system typically includes refrigeration equipment, air handling equipment, air delivery equipment, and control systems, and is designed to provide a comfortable indoor environment for a large building or multiple smaller buildings.

[0033] In a central air-conditioning system, there are multiple hardware devices, and there is a certain linkage control relationship between two or more hardware devices. Based on this, the hardware devices with the linkage control relationship are called linkage control devices in the central air-conditioning system.

[0034] In this embodiment, the above-mentioned linkage control devices may include: a refrigeration host, a chilled water delivery loop, a cooling water delivery loop, a cooling tower, a central air-conditioning terminal, and an air handling device.

[0035] The cooling unit, also known as a chiller, is the core component of a central air conditioning system, responsible for generating cooling. Depending on the structural information of the building the central air conditioning system is designed for, multiple cooling units can be installed within the system. These units are typically housed in a refrigeration room.

[0036] The chilled water delivery loop, consisting of a chilled water pump and chilled water pipes, is responsible for delivering the cooling capacity generated by the refrigeration unit to each terminal device (i.e., the central air-conditioning terminal). The chilled water pump can be understood as the power device that drives the chilled water circulation. A central air-conditioning system generally includes multiple chilled water pumps and multiple sets of adjustable valves.

[0037] The cooling water supply loop, consisting of a cooling water pump and cooling water piping, is responsible for transferring heat generated by the refrigeration unit to the cooling tower for dissipation. The cooling water pump can be understood as the device that drives the cooling water circulation. A central air conditioning system typically includes multiple cooling water pumps.

[0038] Cooling towers are used to dissipate heat from cooling water into the atmosphere, thereby enabling the recycling of cooling water. A central air conditioning system generally includes multiple cooling towers.

[0039] Central air conditioning terminals, such as fan coil units or air conditioning units, are responsible for transferring the cooling energy of chilled water to indoor air to regulate the indoor temperature.

[0040] Air handling equipment, such as a fresh air unit, is used to filter, heat, cool, humidify or dehumidify the air entering the room to ensure the quality of the indoor air.

[0041] In an optional implementation of this embodiment, the real-time environmental parameters may include: outdoor temperature and humidity values, outdoor wind speed values, and regional temperature and humidity values ​​of each air duct area in the building controlled by the central air-conditioning system.

[0042] As mentioned above, a central air-conditioning system can generally be configured in a building, and the central air-conditioning system is used to control the building. The central air-conditioning system includes multiple central air-conditioning terminals (typically, fan coil units). Each central air-conditioning terminal is used to regulate the temperature and humidity in the air duct area where it is located, so that the air duct area can achieve dynamic balance at the expected temperature and humidity values ​​pre-set by the user. For example, a building can include multiple rooms, and a central air-conditioning terminal can be independently set in each room. The room where each central air-conditioning terminal is set is the air duct area regulated by the central air-conditioning terminal. Accordingly, by collecting the temperature and humidity in each air duct area, the regional temperature and humidity values ​​corresponding to each air duct area can be obtained. The corresponding equipment operating status and temperature and humidity change trend of each area are the load characteristics of the area.

[0043] The current operating parameters of each linkage control device in the central air-conditioning system include: the current number of cooling towers started and stopped, the current operating frequency of the fans in each currently started cooling tower, the current number of cooling water pumps started and stopped, the current operating frequency of each currently started cooling water pump, the current number of refrigeration hosts started and stopped in the refrigeration room, and the current chilled water outlet temperature of the currently started refrigeration host.

[0044] The number of cooling towers currently on and off can be understood as the number of cooling towers currently on and off, among all cooling towers in the central air conditioning system. Each cooling tower contains a cooling tower fan mounted on its top. This fan accelerates heat exchange between the cooling water and air through forced ventilation, reducing the temperature of the cooling water returning to the refrigeration unit. Accordingly, the current operating frequency of the fans in each currently on cooling tower refers to the current operating frequency of each cooling tower fan that is currently on.

[0045] The number of cooling water pumps currently started and stopped can be understood as the number of cooling water pumps currently started and stopped among all cooling water pumps in the central air conditioning system. The cooling water pump's current operating frequency refers to the power supply frequency driving the cooling water pump's motor, measured in Hertz (Hz), which directly affects the pump's speed and flow rate.

[0046] The current number of cooling units started and stopped in the cooling room can be understood as the number of cooling units currently started and stopped among all cooling units in the central air conditioning system. The current chilled water outlet temperature of the cooling units refers to the current chilled water temperature at the evaporator outlet of the chiller. This parameter directly affects the cooling performance and energy efficiency of the air conditioning system.

[0047] S120. Input the real-time environmental parameters and the current operating parameters into the pre-built AI computing power model. Through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time.

[0048] In this embodiment, a large AI computing power model is pre-trained, and multiple interconnected functional sub-models are integrated into the large AI computing power model. Through the linkage calculation of these functional sub-models, the target control parameters that make the operating state of each linkage control device reach the optimal or local optimal state can be calculated. Among them, the optimal or local optimal operating state of the linkage control device can be understood as one or more parameters such as the cooling efficiency of the cooling tower water pump, the host performance coefficient of the refrigeration host, or the chilled water delivery efficiency of the chilled water pump reaching the optimal state.

[0049] In an optional implementation of this embodiment, the functional sub-models in the AI ​​computing power model may include: a load model, a refrigeration room model, and a cooling water system model;

[0050] Accordingly, through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time, including:

[0051] S1201: Input the regional temperature and humidity values ​​of each air duct area into a pre-trained load model to obtain the estimated regional cooling load value of each air duct area in the target future period predicted by the load model.

[0052] The target future period can be understood as the time period for which advance control is required. Specifically, each day can be divided into time periods according to preset time units, for example, by hour. Furthermore, when the difference between the current system time and the start time of the next period is less than or equal to a preset time length, the estimated regional cooling load value for the next hour (i.e., the target future period) can be determined using the load model prediction.

[0053] In a specific example, when the current system time reaches 2:50 p.m. on each day (or each working day), it is determined to use the load model to predict the estimated regional cooling load value of each duct area in the target future time period from 3:00 p.m. to 4:00 p.m. on that day.

[0054] In this embodiment, the zone cooling load can be understood as the total amount of heat that needs to be removed by the air conditioning system per unit time to maintain a specific duct area within the target temperature and humidity range. The estimated zone cooling load can be understood as the estimated zone cooling load output by the load model.

[0055] Optionally, the load model can be trained by constructing training samples using historical temperature and humidity values ​​collected from the supply and return air ducts of multiple central air conditioning terminals within a building over multiple historical time periods. Different central air conditioning terminals are used to control different air duct areas within the building.

[0056] S1202. Calculate the estimated total cooling load of the building controlled by the central air-conditioning system during the target future period based on the estimated cooling load of each area.

[0057] In this embodiment, after predicting the estimated regional cooling load value of each air duct area in the building in the target future time period through the load model, the estimated overall cooling load value of the building controlled by the central air-conditioning system in the target future time period can be calculated by accumulating and summing the estimated regional cooling load values.

[0058] S1203. Input the estimated total cooling load, the current start-up and stop number of the refrigeration hosts in the refrigeration room, and the current chilled water outlet temperature of the currently started refrigeration hosts into the pre-trained refrigeration room model, and obtain the target start-up number of the refrigeration hosts in the refrigeration room and the target chilled water outlet temperature of the target started refrigeration hosts as target control parameters.

[0059] In this embodiment, a refrigeration room model can be pre-trained. The refrigeration room model aims to maximize the host performance coefficient of the refrigeration host. The model is used to take the estimated total cooling load in the target future time period, the current start-up and stop number of refrigeration hosts in the refrigeration room, and the current chilled water outlet temperature of the currently started refrigeration host as model inputs, and predict the target start-up number of refrigeration hosts in the refrigeration room and the target chilled water outlet temperature of the target started refrigeration hosts when the estimated total cooling load in the target future time period reaches the optimal value.

[0060] Among them, the host performance coefficient is an important indicator to measure the energy utilization efficiency of the refrigeration host. It refers to the ratio of cooling capacity to cooling power consumption under certain working conditions.

[0061] S1204. Input the outdoor temperature and humidity values, outdoor wind speed values, the current number of cooling towers started and stopped, the current operating frequency of the fans in each currently started cooling tower, the current number of cooling water pumps started and stopped, the current operating frequency of each currently started cooling water pump, the target number of refrigeration hosts started in the refrigeration room, and the target chilled water outlet temperature of the target started refrigeration hosts into the pre-trained cooling water system model.

[0062] Similarly, the cooling water system model aims to maximize the chilled water delivery efficiency and is used to take the outdoor temperature and humidity values, the outdoor wind speed values, the current number of cooling towers started and stopped, the current operating frequency of the fans in each currently started cooling tower, the current number of cooling water pumps started and stopped, the current operating frequency of each currently started cooling water pump, the target start-up number of refrigeration hosts in the refrigeration room and the target chilled water outlet temperature of the target started refrigeration hosts as model inputs, and predict the target number of cooling towers started and stopped, the target operating frequency of the fans in each cooling tower started, the target number of cooling water pumps started and stopped and the target operating frequency of each cooling water pump started as target control parameters output by the cooling water system model.

[0063] S1205. Obtain the target number of cooling towers started and stopped, the target operating frequency of the fans in each cooling tower started, the target number of cooling water pumps started and stopped, and the target operating frequency of each cooling water pump started, output by the cooling water system model as target control parameters.

[0064] In this embodiment, when predicting the estimated value of the overall cooling load in the building during the target future time period, the pre-trained refrigeration room model and cooling water system model can be combined to predict the various target control parameters required for the target future time period under the optimal energy-saving effect.

[0065] S130. Adjust parameters of the matching linkage control devices according to the target control parameters to control the central air-conditioning system to achieve energy saving while meeting work requirements.

[0066] The technical solution of the embodiment of the present invention obtains real-time environmental parameters that match the central air-conditioning system in real time, and obtains the current operating parameters of each linkage control device in the central air-conditioning system; inputs the real-time environmental parameters and each current operating parameter into a pre-built AI computing power big model, and through the linkage calculation between multiple functional sub-models in the AI ​​computing power big model, obtains the target control parameters corresponding to each linkage control device in real time; the technical means of adjusting the parameters of the matching linkage control devices according to each target control parameter, innovatively establishes an accurate AI computing power big model for the central air-conditioning system, so that the energy is efficiently output, distributed and exchanged between the linkage control devices in the central air-conditioning system, which can control the central air-conditioning system to achieve the goal of energy saving while meeting work requirements, and can perform more intelligent and personalized control of the central air-conditioning system to improve the operating efficiency of the entire central air-conditioning system.

[0067] Based on the above embodiments, before inputting the regional temperature and humidity values ​​of each air duct area into the pre-trained load model, the following steps may be further included:

[0068] S1301. The temperature and humidity sensors installed in the return air duct of each central air-conditioning terminal of the central air-conditioning system are used to collect the historical temperature and humidity values ​​of the return air duct of each central air-conditioning terminal in different historical periods.

[0069] S1302. The temperature sensors provided in the air supply ducts of each central air-conditioning terminal are used to collect historical temperature values ​​of the air supply ducts of each central air-conditioning terminal in different historical periods.

[0070] S1303. Calculate the supply and return air enthalpy difference of each central air conditioning terminal in different historical periods based on the historical temperature and humidity values ​​of each return air channel and the historical temperature value of each supply air channel.

[0071] In this embodiment, the ambient temperature and humidity conditions in different seasons in the same building have a greater impact on the actual temperature and humidity control strategy of the central air-conditioning system. Therefore, it is possible to consider using "one year" as the statistical dimension and counting every hour of every day of each year as the smallest unit of the historical period.

[0072] Furthermore, multiple sets of historical temperature and humidity values ​​for the return air ducts and the historical temperature values ​​for each supply air duct at the same day and hour in different years can be statistically calculated to obtain the supply and return air enthalpy difference for a set hour on a set date in the year. For example, for the historical period of 3:00-4:00 pm on June 21st from 2022 to 2025, multiple sets of historical temperature and humidity values ​​for each return air duct and the historical temperature values ​​for each supply air duct can be obtained for each duct area in the building. Based on these multiple sets of data, multiple supply and return air enthalpy differences can be calculated for each duct area in the building from 3:00-4:00 pm on June 21st.

[0073] The supply-return air enthalpy difference is a core parameter in air conditioning system energy analysis, reflecting the total sensible and latent heat energy consumption during air handling. The supply-return air enthalpy difference can be calculated by taking the difference between the return air enthalpy and the supply air enthalpy.

[0074] In a specific example, the saturated water vapor pressure of the supply air duct and the saturated water vapor pressure of the return air duct can be calculated using a set of historical temperature values ​​of the return air duct and the historical temperature values ​​of the supply air duct. Then, based on the saturated water vapor pressure of the supply air duct and the preset humidity empirical value, the actual water vapor pressure of the supply air duct is calculated, and the actual water vapor pressure of the return air duct is calculated by combining the saturated water vapor pressure of the return air duct and the measured historical humidity value of the return air duct. Furthermore, the humidity content of the supply air duct is calculated based on the actual water vapor pressure of the supply air duct, and the humidity content of the return air duct is calculated based on the actual water vapor pressure of the return air duct. Then, the supply air enthalpy value and the return air enthalpy value are calculated based on the humidity content of the supply air duct and the humidity content of the return air duct, respectively. Finally, based on the supply air enthalpy value and the return air enthalpy value, a supply and return air enthalpy difference is calculated.

[0075] As mentioned above, the return air enthalpy difference at each time point in each historical period can be determined based on the maximum value, minimum value, mean value, variance and other parameters of the return air enthalpy difference calculated for each historical period.

[0076] S1304. By performing an integration operation on the enthalpy differences of the supply and return air, the cooling consumption value of each central air-conditioning terminal in different historical periods is obtained.

[0077] In this embodiment, after obtaining the enthalpy difference of the supply and return air at each time point in each historical period, the cooling consumption value of each central air-conditioning terminal in different historical periods can be obtained through a simple integral operation.

[0078] Typically, the enthalpy differences of the supply and return air at each time point in each historical period are accumulated and summed to obtain the cooling consumption value in each historical period.

[0079] It needs to be emphasized again that the solution of the embodiment of the present invention can efficiently and accurately calculate the cooling consumption value by collecting conventional temperature and humidity data in combination with simple integral calculations, without stopping water supply and installing new metering devices in the central air-conditioning terminal, thereby effectively saving implementation costs.

[0080] S1305. Based on the cooling consumption value of each central air-conditioning terminal in different historical periods, and the control relationship between the central air-conditioning terminal and each air duct area in the building controlled by the central air-conditioning system, obtain the historical cooling load value actually required by each air duct area in different historical periods.

[0081] In this embodiment, since different central air-conditioning terminals are used to regulate different air duct areas in the building, after obtaining the cooling consumption value of each central air-conditioning terminal in different historical periods, the required cooling consumption value of each air duct area in different historical periods can be obtained.

[0082] In an alternative implementation of this embodiment, historical cooling load values ​​corresponding to various cooling consumption values ​​can be calculated based on preset empirical parameters such as cooling energy efficiency ratio, distribution system efficiency, and auxiliary energy consumption. In other words, the historical cooling load values ​​actually required for each duct area during different historical periods can be obtained.

[0083] S1306. Based on the historical cooling load values ​​actually required by each duct area in different historical periods, multiple training samples are constructed, and each training sample is used to train a preset machine learning model to obtain the load model.

[0084] Through the above settings, the estimated regional cooling load of each duct area in the central air-conditioning system in the target future time period can be determined in advance according to the predicted value of the terminal load of the central air-conditioning system. Based on the estimated cooling load of each area, the estimated overall cooling load of the building controlled by the central air-conditioning system in the target future time period can be accurately estimated. Combined with the estimated overall cooling load, the target control parameters of each linkage control device in the central air-conditioning system can be estimated in advance, and each linkage control device can be adjusted in advance. While improving the air-conditioning experience of indoor personnel, the energy consumption of the central air-conditioning system can be effectively reduced.

[0085] On the basis of the above-mentioned embodiments, the electronic device for implementing the AI-based central air-conditioning system control method provided by the embodiment of the present invention includes data acquisition and communication functions. Through the communication interface with the power equipment control cabinet of the water pump, fan, etc. in the central air-conditioning system, the communication interface with the refrigeration host, the communication interface with the terminal network temperature controller, the communication interface with the third-party building control system network, etc., various types of real-time data can be collected. Then, by reading the instantaneous parameters such as temperature, humidity, pressure, flow and energy for total amount and variable analysis, AI algorithms are introduced for optimization calculations to optimize the operating parameters of the refrigeration host, chilled water pump, cooling water pump, cooling tower and air-conditioning terminal, thereby achieving system energy saving.

[0086] Among them, all collected data are classified according to the corresponding relationship of building space, and the time of all collected data is recorded in the form of timestamp.

[0087] Specifically, the communication interface with the power equipment control cabinets for water pumps, fans, and other components includes a cooling system consisting of a cooling water pump control cabinet and a cooling tower fan control cabinet; and a chilled water distribution system consisting of a chilled water pump control cabinet. By reading and processing the operating parameters of the smart meter and inverter in the variable frequency electric control cabinet, data collection and analysis of the central air conditioning water system distribution equipment is achieved. The power equipment control cabinet communication interface also includes communication access with the control cabinets for the fresh air unit and air conditioning unit. By collecting the operating parameters of the fresh air unit and air conditioning unit, data collection and analysis of the central air conditioning system distribution equipment is achieved. Furthermore, the communication interface with the refrigeration host reads the refrigeration host's operating status, load rate, condenser, and evaporator operating parameters, providing a data basis for evaluating the refrigeration host's efficiency curve and optimizing operating parameters.

[0088] The communication interface with the terminal networked thermostat can read the operating parameters of the networked thermostat, collect and analyze the terminal load and operating status of the central air-conditioning, and obtain the correspondence between the air-conditioning operating status and the ambient temperature in different time periods. By analyzing the data, the total demand and change pattern of the terminal load can be obtained; the networked communication interface with the third-party building control system connects the traditional building control system, analyzes the operating status of the air-conditioning and HVAC equipment in the operating building, and records the collected data in a spatial correspondence, providing a basis for establishing a central air-conditioning equipment operation model.

[0089] Furthermore, the technical solutions of each embodiment of the present invention can also automatically analyze the communication protocol of the access data, such as modbus, BACnet or Profibus, and can match the data table with the analog quantity relationship. Furthermore, the operating status and data changes can be analyzed to automatically match the monitoring points and logical relationships corresponding to the data.

[0090] At the same time, when collecting real-time environmental parameters, the technical solutions of the various embodiments of the present invention can collect outdoor sunlight parameters, indoor black globe temperature and other information in addition to outdoor temperature and humidity values ​​and indoor temperature and humidity values. The outdoor temperature and humidity values ​​and outdoor sunlight parameters can be used to establish an outdoor climate and time model, and the indoor temperature and humidity values ​​and indoor black globe temperature can be used to establish an indoor heat load model. The indoor building enclosure heat transfer model can be analyzed with the outdoor climate and time model. Based on the above-established models, the overall cooling load estimate of the building controlled by the central air-conditioning system in the target future period can be more accurately estimated. Based on the above-mentioned overall cooling load estimate, the target control parameters corresponding to each linkage control device can be more accurately calculated.

[0091] Building on the technologies in the aforementioned embodiments, intelligent matching between space and equipment operating parameters can be achieved, and presented in the form of an energy flow diagram, allowing users to more intuitively observe the real-time control process of the central air conditioning system. Finally, the various functional submodules included in the AI ​​computing power model can be iterated or upgraded in real time.

[0092] Figure 2 This is a flowchart of another AI-based central air conditioning system control method provided by an embodiment of the present invention. This embodiment is optimized based on the above embodiments. In this embodiment, the parameter type of "current operating parameters of each linked control device" is specifically expanded, and the operation of "real-time calculation of target control parameters corresponding to each linked control device through linked calculations between multiple functional sub-models in the AI ​​computing power model" is further refined accordingly.

[0093] Correspondingly, such as Figure 2 As shown, the method may include:

[0094] S210: Acquire real-time environmental parameters that match the central air-conditioning system, and acquire current operating parameters of each linkage control device in the central air-conditioning system.

[0095] In this embodiment, the current operating parameters of each linkage control device in the central air-conditioning system may also include: the current number of started and stopped chilled water pumps, the current operating frequency of each currently started chilled water pump, the current wind speed and current air volume of each central air-conditioning terminal fan in the central air-conditioning system, and the current control parameters of the networked temperature control system of each central air-conditioning terminal.

[0096] Correspondingly, the functional sub-models in the AI ​​computing power model also include: chilled water delivery system model and air conditioning terminal load model.

[0097] The number of chilled water pumps currently started and stopped can be understood as the number of chilled water pumps currently started and stopped among all chilled water pumps in the central air conditioning system. The chilled water pump's current operating frequency refers to the power supply frequency driving the chilled water pump motor, measured in Hertz (Hz), which directly affects the pump's speed and flow rate.

[0098] The central air-conditioning terminal fan is installed at the end of the central air-conditioning system. Its main function is to transport the air treated by the chiller to each room to meet the temperature requirements of different rooms.

[0099] The networked temperature control system at the central air conditioning terminal, also generally referred to as an intelligent temperature controller, is used to collect ambient temperature data in real time and send instructions to the network to adjust the control parameters of each control component in the central air conditioning terminal (such as the opening of the electric water valve or the fan speed, etc.). Among them, the networked temperature control system monitors the indoor temperature in real time through a built-in temperature sensor and compares the monitored temperature data with the temperature set by the user. When the indoor temperature is higher than the set temperature, the networked temperature control system will send a signal to the various control components in the central air conditioning terminal to increase the cooling capacity; when the indoor temperature is lower than the set temperature, it will control the various control components in the central air conditioning terminal to reduce the cooling capacity or stop cooling to maintain the indoor temperature within the set range.

[0100] In this embodiment, the chilled water delivery system model refers to a pre-trained machine learning model used to predict the target number of chilled water pump starts and stops, as well as the target operating frequency of each chilled water pump during target activation. This chilled water delivery system model aims to maximize chilled water delivery efficiency. Furthermore, the air conditioning terminal load model refers to a pre-trained machine learning model used to predict the target wind speed and target air volume of the central air conditioning terminal fans installed in each air duct area of ​​the central air conditioning system, as well as the target control parameters of the networked temperature control system of each central air conditioning terminal.

[0101] Furthermore, the current operating parameters of each linkage control device in the central air-conditioning system may also include: the current wind speed and current air volume of the fan in each fresh air unit in the central air-conditioning system; accordingly, the functional sub-model in the AI ​​computing power model may also include: a fresh air load model.

[0102] Among them, the fresh air load model refers to a pre-trained machine learning model used to predict the target wind speed and target air volume of the fans in each fresh air unit.

[0103] S220 : Inputting the regional temperature and humidity values ​​of each air duct area into a pre-trained load model to obtain an estimated regional cooling load value of each air duct area in a target future period predicted by the load model.

[0104] S230. Calculate an estimated total cooling load of the building controlled by the central air-conditioning system during a target future period based on the estimated cooling load of each area.

[0105] S240. Input the estimated total cooling load, the current start-stop number of refrigeration hosts in the refrigeration room, and the current chilled water outlet temperature of the currently started refrigeration host into the pre-trained refrigeration room model, and obtain the target start-up number of refrigeration hosts in the refrigeration room and the target chilled water outlet temperature of the target started refrigeration hosts as target control parameters.

[0106] S250. Input the outdoor temperature and humidity values, outdoor wind speed values, the current number of cooling towers started and stopped, the current operating frequency of the fans in each currently started cooling tower, the current number of cooling water pumps started and stopped, the current operating frequency of each currently started cooling water pump, the target number of refrigeration hosts started in the refrigeration room, and the target chilled water outlet temperature of the target started refrigeration hosts into the pre-trained cooling water system model.

[0107] S260. Obtain the target number of cooling towers started and stopped, the target operating frequency of the fans in each cooling tower started, the target number of cooling water pumps started and stopped, and the target operating frequency of each cooling water pump started, output by the cooling water system model as target control parameters.

[0108] S270. Input the estimated value of the overall cooling load, the current number of chilled water pumps started and stopped, and the current operating frequency of each currently started chilled water pump into the pre-trained chilled water delivery system model, and obtain the target number of chilled water pumps started and stopped and the target operating frequency of each chilled water pump started as target control parameters.

[0109] S280. Input the estimated regional cooling load of each air duct area in the target future period, the current wind speed and current air volume of each central air-conditioning terminal fan, and the current control parameters of the networked temperature control system of each central air-conditioning terminal into the pre-trained air-conditioning terminal load model, and obtain the target wind speed and target air volume of each central air-conditioning terminal fan, as well as the target control parameters of the networked temperature control system of each central air-conditioning terminal as target control parameters.

[0110] S290. Input the estimated value of the overall cooling load and the current wind speed and current air volume of the fans in each fresh air unit in the central air-conditioning system into a pre-trained fresh air load model, and obtain the target wind speed and target air volume of the fans in each fresh air unit as target control parameters.

[0111] S2100. Adjust parameters of the matching linkage control devices according to each target control parameter to control the central air-conditioning system to achieve energy saving while meeting work requirements.

[0112] The technical solution of the embodiment of the present invention collects and analyzes various parameters that affect the operation of the central air-conditioning system and information such as the operating status of the equipment. Through machine learning and deep learning, the terminal load can be accurately analyzed, and then an accurate AI computing power model can be established for the central air-conditioning system to achieve efficient energy output, distribution and heat exchange between various devices in the system, thereby achieving system energy saving.

[0113] At the same time, the AI ​​computing power model of the central air conditioning system also provides more data support for load analysis and forecasting of the central air conditioning system. Through AI analysis of the system, it can better implement on-demand cooling supply methods that conform to user habits, effectively improve the water balance of the air conditioning chilled water system, and while improving cooling efficiency, it also provides a basis for the efficient and stable operation of the host. Furthermore, through AI analysis of the central air conditioning system, it can also achieve efficient utilization of cold storage systems and residual cooling utilization strategies, providing data support for technologies such as load allocation and virtual power plant applications.

[0114] Figure 3 The following is a schematic diagram of the structure of an AI-based central air conditioning system control device provided by an embodiment of the present invention. Figure 3 As shown, the device includes: a parameter acquisition module 310, a control parameter calculation module 320 and a parameter adjustment module 330, wherein:

[0115] The parameter acquisition module 310 is used to acquire real-time environmental parameters that match the central air-conditioning system and to acquire current operating parameters of each linkage control device in the central air-conditioning system.

[0116] The control parameter calculation module 320 is used to input the real-time environmental parameters and the current operating parameters into the pre-built AI computing power model, and through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time.

[0117] The parameter adjustment module 330 is used to adjust the parameters of the matching linkage control devices according to each target control parameter, so as to control the central air-conditioning system to achieve energy saving while meeting the working requirements.

[0118] The technical solution of the embodiment of the present invention obtains real-time environmental parameters that match the central air-conditioning system in real time, and obtains the current operating parameters of each linkage control device in the central air-conditioning system; inputs the real-time environmental parameters and each current operating parameter into a pre-built AI computing power big model, and through the linkage calculation between multiple functional sub-models in the AI ​​computing power big model, obtains the target control parameters corresponding to each linkage control device in real time; the technical means of adjusting the parameters of the matching linkage control devices according to each target control parameter, innovatively establishes an accurate AI computing power big model for the central air-conditioning system, so that the energy is efficiently output, distributed and exchanged between the linkage control devices in the central air-conditioning system, which can control the central air-conditioning system to achieve the goal of energy saving while meeting work requirements, and can perform more intelligent and personalized control of the central air-conditioning system to improve the operating efficiency of the entire central air-conditioning system.

[0119] Based on the above embodiments, the real-time environmental parameters may include: outdoor temperature and humidity values, outdoor wind speed values, and regional temperature and humidity values ​​of each air duct area in the building controlled by the central air conditioning system;

[0120] The current operating parameters of each linkage control device in the central air-conditioning system may include: the current number of cooling towers started and stopped, the current operating frequency of the fans in each currently started cooling tower, the current number of cooling water pumps started and stopped, the current operating frequency of each currently started cooling water pump, the current number of refrigeration hosts started and stopped in the refrigeration room, and the current chilled water outlet temperature of the currently started refrigeration host.

[0121] Based on the above embodiments, the functional sub-models in the AI ​​computing power model may include: load model, refrigeration room model, and cooling water system model;

[0122] Accordingly, the control parameter calculation module 320 may be specifically used to:

[0123] Input the regional temperature and humidity values ​​of each duct area into the pre-trained load model to obtain the estimated regional cooling load value of each duct area in the target future period predicted by the load model;

[0124] Calculate the estimated total cooling load of the buildings controlled by the central air-conditioning system during the target future period based on the estimated cooling load of each area;

[0125] The estimated total cooling load, the current number of cooling units started and stopped in the cooling room, and the current chilled water outlet temperature of the currently started cooling units are input into the pre-trained cooling room model. The target number of cooling units started in the cooling room and the target chilled water outlet temperature of the cooling units started are obtained as target control parameters.

[0126] The outdoor temperature and humidity values, outdoor wind speed values, the current number of cooling towers started and stopped, the current operating frequency of the fans in each currently started cooling tower, the current number of cooling water pumps started and stopped, the current operating frequency of each currently started cooling water pump, the target number of refrigeration units started in the refrigeration room, and the target chilled water outlet temperature of the target started refrigeration units are input into the pre-trained cooling water system model.

[0127] The target number of cooling towers started and stopped, the target operating frequency of the fans in each cooling tower started at the target, the target number of cooling water pumps started and stopped, and the target operating frequency of each cooling water pump started at the target are obtained as target control parameters output by the cooling water system model.

[0128] Based on the above embodiments, a load model building module may also be included, which is used to:

[0129] Before inputting the regional temperature and humidity values ​​of each air duct area into the pre-trained load model, the temperature and humidity sensors installed in the return air duct of each central air-conditioning terminal in the central air-conditioning system are used to collect the historical temperature and humidity values ​​of the return air duct of each central air-conditioning terminal in different historical periods;

[0130] The temperature sensor set in each air supply duct of the central air conditioning terminal is used to collect the historical temperature values ​​of the air supply duct of each central air conditioning terminal in different historical periods;

[0131] Based on the historical temperature and humidity values ​​of each return air channel and the historical temperature values ​​of each supply air channel, the enthalpy difference of the supply and return air of each central air conditioning terminal in different historical periods is calculated;

[0132] By integrating the enthalpy differences of the supply and return air, the cooling consumption values ​​of the central air-conditioning terminals in different historical periods are obtained;

[0133] Based on the cooling consumption values ​​of each central air-conditioning terminal in different historical periods, and the control relationship between the central air-conditioning terminal and each air duct area in the building controlled by the central air-conditioning system, the historical cooling load values ​​actually required by each air duct area in different historical periods are obtained;

[0134] According to the historical cooling load values ​​actually required by each duct area in different historical periods, multiple training samples are constructed, and each training sample is used to train a preset machine learning model to obtain the load model.

[0135] Based on the above embodiments, the current operating parameters of each linkage control device in the central air-conditioning system can also include: the current number of started and stopped chilled water pumps, the current operating frequency of each currently started chilled water pump, the current wind speed and current air volume of each central air-conditioning terminal fan in the central air-conditioning system, and the current control parameters of the networked temperature control system of each central air-conditioning terminal.

[0136] Based on the above embodiments, the functional sub-models in the AI ​​computing power model may further include: a chilled water delivery system model and an air conditioning terminal load model;

[0137] Accordingly, the control parameter calculation module 320 may be further configured to:

[0138] The estimated total cooling load, the current number of chilled water pumps started and stopped, and the current operating frequency of each chilled water pump currently started are input into a pre-trained chilled water delivery system model. The target number of chilled water pumps started and stopped and the target operating frequency of each chilled water pump currently started are obtained as target control parameters.

[0139] The estimated regional cooling load of each air duct area in the target future period, the current wind speed and current air volume of each central air-conditioning terminal fan, and the current control parameters of the networked temperature control system of each central air-conditioning terminal are respectively input into the pre-trained air-conditioning terminal load model, and the target wind speed and target air volume of each central air-conditioning terminal fan and the target control parameters of the networked temperature control system of each central air-conditioning terminal are obtained as target control parameters.

[0140] Based on the above embodiments, the current operating parameters of each linkage control device in the central air-conditioning system may further include: the current wind speed and current air volume of the fan in each fresh air unit in the central air-conditioning system; the functional sub-model in the AI ​​computing power model also includes: a fresh air load model;

[0141] Accordingly, the control parameter calculation module 320 may be further configured to:

[0142] The estimated total cooling load and the current wind speed and current air volume of the fans in each fresh air unit in the central air-conditioning system are input into the pre-trained fresh air load model, and the target wind speed and target air volume of the fans in each fresh air unit are obtained as target control parameters.

[0143] The AI-based central air-conditioning system control device provided in an embodiment of the present invention can execute the AI-based central air-conditioning system control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0144] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0145] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0146] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0147] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0148] The processor 11 can be various general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, for example, executing the AI-based central air conditioning system control method as described in any of the embodiments of the present invention.

[0149] In some embodiments, the AI-based central air-conditioning system control method as described in any one of the embodiments of the present invention may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the AI-based central air-conditioning system control method as described in any one of the embodiments of the present invention described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the AI-based central air-conditioning system control method as described in any one of the embodiments of the present invention by any other appropriate means (for example, by means of firmware). That is:

[0150] Obtain real-time environmental parameters that match the central air-conditioning system, and obtain the current operating parameters of each linkage control device in the central air-conditioning system;

[0151] Input the real-time environmental parameters and current operating parameters into the pre-built AI computing power model. Through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time.

[0152] Adjust the parameters of the matching linkage control equipment according to the target control parameters to control the central air-conditioning system to achieve energy saving while meeting the working requirements.

[0153] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0154] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0155] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0156] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0157] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0158] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0159] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0160] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A central air conditioning system control method based on AI, characterized in that: include: Obtain real-time environmental parameters that match the central air-conditioning system, and obtain the current operating parameters of each linkage control device in the central air-conditioning system; Input the real-time environmental parameters and current operating parameters into the pre-built AI computing power model. Through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time. Adjust the parameters of the matching linkage control equipment according to the target control parameters to control the central air-conditioning system to achieve energy saving while meeting the working requirements.

2. The method according to claim 1, characterized in that Real-time environmental parameters include: outdoor temperature and humidity values, outdoor wind speed values, and regional temperature and humidity values ​​of each air duct area in the building controlled by the central air conditioning system; The current operating parameters of each linkage control device in the central air-conditioning system include: the current number of cooling towers started and stopped, the current operating frequency of the fans in each currently started cooling tower, the current number of cooling water pumps started and stopped, the current operating frequency of each currently started cooling water pump, the current number of refrigeration hosts started and stopped in the refrigeration room, and the current chilled water outlet temperature of the currently started refrigeration host.

3. The method according to claim 2, characterized in that The functional sub-models in the AI ​​computing power model include: load model, refrigeration room model, and cooling water system model; Through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time, including: Input the regional temperature and humidity values ​​of each duct area into the pre-trained load model to obtain the estimated regional cooling load value of each duct area in the target future period predicted by the load model; Calculate the estimated total cooling load of the buildings controlled by the central air-conditioning system during the target future period based on the estimated cooling load of each area; The estimated total cooling load, the current number of cooling units started and stopped in the cooling room, and the current chilled water outlet temperature of the currently started cooling units are input into the pre-trained cooling room model. The target number of cooling units started in the cooling room and the target chilled water outlet temperature of the cooling units started are obtained as target control parameters. The outdoor temperature and humidity values, outdoor wind speed values, the current number of cooling towers started and stopped, the current operating frequency of the fans in each currently started cooling tower, the current number of cooling water pumps started and stopped, the current operating frequency of each currently started cooling water pump, the target number of refrigeration units started in the refrigeration room, and the target chilled water outlet temperature of the target started refrigeration units are input into the pre-trained cooling water system model. The target number of cooling towers started and stopped, the target operating frequency of the fans in each cooling tower started at the target, the target number of cooling water pumps started and stopped, and the target operating frequency of each cooling water pump started at the target are obtained as target control parameters output by the cooling water system model.

4. The method according to claim 3, characterized in that Before inputting the regional temperature and humidity values ​​of each duct area into the pre-trained load model, the following steps are also included: The temperature and humidity sensors installed in the return air duct of each central air-conditioning terminal in the central air-conditioning system collect the historical temperature and humidity values ​​of the return air duct of each central air-conditioning terminal in different historical periods; The temperature sensor set in each air supply duct of the central air conditioning terminal is used to collect the historical temperature values ​​of the air supply duct of each central air conditioning terminal in different historical periods; Based on the historical temperature and humidity values ​​of each return air channel and the historical temperature values ​​of each supply air channel, the enthalpy difference of the supply and return air of each central air conditioning terminal in different historical periods is calculated; By integrating the enthalpy differences of the supply and return air, the cooling consumption values ​​of the central air-conditioning terminals in different historical periods are obtained; Based on the cooling consumption values ​​of each central air-conditioning terminal in different historical periods, and the control relationship between the central air-conditioning terminal and each air duct area in the building controlled by the central air-conditioning system, the historical cooling load values ​​actually required by each air duct area in different historical periods are obtained; According to the historical cooling load values ​​actually required by each duct area in different historical periods, multiple training samples are constructed, and each training sample is used to train a preset machine learning model to obtain the load model.

5. The method according to claim 3, characterized in that The current operating parameters of each linkage control device in the central air-conditioning system also include: the current number of started and stopped chilled water pumps, the current operating frequency of each currently started chilled water pump, the current wind speed and current air volume of each central air-conditioning terminal fan in the central air-conditioning system, and the current control parameters of the networked temperature control system of each central air-conditioning terminal.

6. The method according to claim 5, characterized in that The functional sub-models in the AI ​​computing power model also include: chilled water delivery system model and air conditioning terminal load model; Through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time, including: The estimated total cooling load, the current number of chilled water pumps started and stopped, and the current operating frequency of each chilled water pump currently started are input into a pre-trained chilled water delivery system model. The target number of chilled water pumps started and stopped and the target operating frequency of each chilled water pump currently started are obtained as target control parameters. The estimated regional cooling load of each air duct area in the target future period, the current wind speed and current air volume of each central air-conditioning terminal fan, and the current control parameters of the networked temperature control system of each central air-conditioning terminal are respectively input into the pre-trained air-conditioning terminal load model, and the target wind speed and target air volume of each central air-conditioning terminal fan and the target control parameters of the networked temperature control system of each central air-conditioning terminal are obtained as target control parameters.

7. The method according to claim 3, characterized in that The current operating parameters of each linkage control device in the central air-conditioning system also include: the current wind speed and current air volume of the fan in each fresh air unit in the central air-conditioning system; the functional sub-model in the AI ​​computing power large model also includes: fresh air load model; Through the linkage calculation between multiple functional sub-models in the AI ​​computing power model, the target control parameters corresponding to each linkage control device are calculated in real time, including: The estimated total cooling load and the current wind speed and current air volume of the fans in each fresh air unit in the central air-conditioning system are input into the pre-trained fresh air load model, and the target wind speed and target air volume of the fans in each fresh air unit are obtained as target control parameters.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the AI-based central air-conditioning system control method described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the AI-based central air-conditioning system control method according to any one of claims 1 to 7 when executed.

10. A computer program product, characterized in that The computer program product includes a computer program, which, when executed by a processor, implements the AI-based central air-conditioning system control method according to any one of claims 1 to 7.

Images