A water-cooled central air conditioning automatic regulating water supply temperature control system and method

Abstract

This invention provides a control method and system for automatically adjusting the supply water temperature of a central air conditioning system. The method includes: real-time acquisition of supply water temperature, return water temperature, supply water flow rate, and indoor and outdoor temperature and humidity data from the air conditioning unit; calculation of the actual cooling capacity supplied by the unit and the total cooling capacity demand of the building terminals, wherein the total cooling capacity demand of the building terminals is calculated using a vertically layered model; reverse derivation of the predicted supply water temperature value based on the cooling capacity supply and demand balance; comparison of the predicted value with the initial set value, and automatic adjustment of the supply water temperature according to the deviation rate; and iterative optimization of the calculation parameters using a deep learning model. The system includes an air conditioning room control system, a terminal data acquisition system, and a data processing system. This invention achieves on-demand cooling, significant energy-saving effects, high indoor comfort, low management and maintenance costs, strong adaptability, good compatibility, simple installation, and low retrofit risk, making it suitable for energy-saving retrofits of central air conditioning systems in various commercial buildings.

Description

Technical Field

[0001] This invention relates to the field of energy-saving technology for chilled water central air conditioning, and in particular to a control method and system for automatically calculating the cooling demand of air conditioning terminals and controlling the temperature of chilled water supplied by the refrigeration unit in reverse. Background Technology

[0002] As an important component of large public buildings and commercial facilities, central air conditioning systems account for 30%-50% of the building's total energy consumption, and their energy efficiency level directly affects the building's overall energy consumption and operating costs.

[0003] Water-cooled central air conditioning systems are characterized by large cooling capacity, high energy efficiency, and multiple functions, and are widely used in large office buildings, shopping malls, hotels, transportation hubs, and other scenarios. However, in existing technologies, the cold source manufacturing end does not provide a corresponding cold source according to the end-user demand, and there is a common phenomenon of "overpowered power supply," that is, the cooling capacity of the refrigeration unit far exceeds the actual demand of the end users, resulting in a large amount of energy waste.

[0004] Currently, energy-saving retrofit technologies on the market are mainly divided into two categories: The first category is intelligent control systems, which centralize the operation data of the central air conditioning system in the control room for convenient viewing and management by on-site personnel. However, the energy-saving effect is limited and relies on human initiative and responsibility. The second category involves frequency conversion retrofitting of the four cycles of the central air conditioning system, which operates at low frequency according to the cooling demand of the terminal units. This results in significant energy savings, but it suffers from problems such as high retrofit costs, long cycles, and difficult construction. Furthermore, the cooling capacity of the refrigeration unit is still manually set by the water supply temperature, making it impossible to achieve automatic on-demand supply. Therefore, this invention proposes a control system and method for automatically adjusting the water supply temperature of a water-cooled central air conditioning system, in order to at least partially solve the problems that may exist in the prior art. Summary of the Invention

[0005] In view of the above problems, a control system and method for automatically adjusting the supply water temperature of a water-cooled central air conditioning system are proposed to overcome or at least partially solve these problems. Since the energy consumption of the refrigeration unit accounts for more than 50% of the total energy consumption of the central air conditioning system, the control method and system for automatically adjusting the supply water temperature of the central air conditioning system proposed in this application achieve the goals of on-demand cooling and energy saving.

[0006] In a first aspect, the present invention provides a control method for automatically adjusting the water supply temperature of a central air conditioning system, comprising the following steps:

[0007] Step S1: Data Acquisition

[0008] Real-time collection of the water supply temperature T of the air conditioning unit 供 Return water temperature T 回 Water supply flow rate M, and indoor and outdoor temperature and humidity data, including indoor temperature T. in and outdoor temperature Tout .

[0009] The indoor temperature T in The outdoor temperature T is collected by multiple terminal temperature and humidity sensors deployed in typical areas of the building. out Data is collected by outdoor temperature and humidity sensors installed in open areas of buildings.

[0010] Step S2: Cooling capacity calculation

[0011] Calculate the actual cooling capacity Q supplied by the air conditioning unit based on the collected data. 供 Total cooling capacity demand at building terminals Q 需 .

[0012] The actual cooling capacity Q supplied by the air conditioning unit 供 The calculation formula is:

[0013] Q 供 =M×c×ρ×(T 回 -T 供 );

[0014] Where c is the specific heat capacity of water, taken as 4.2 × 10⁻⁶. 3 J / (kg·℃); ρ is the density of water, taken as 1000 kg / m³ 3 M represents the water supply flow rate, in meters (m³). 3 / h; through unit conversion, 1kW = 3.6 × 10 6 J / h, Q 供 Convert the unit to kW.

[0015] Total cooling capacity demand at building terminals Q 需 The calculation method is as follows: Divide the building into m zones according to vertical spatial layers, and calculate the cooling demand Q for each zone j. j Then sum them up to get Q. 需 .

[0016] Specifically, the building is divided into m areas according to vertical spatial layers, and each area is calculated using the formula Q. j =[K j ×A j ×(T out -T in )×α j ]+(q j ×A j ); where K j Let J be the heat transfer coefficient of the building envelope in region j, expressed in W / (m²). 2 ·℃); A j The area of ​​the enclosure structure in region j is expressed in m². 2 ;T out Outdoor temperature; T inThe average indoor temperature in region j is obtained by taking the arithmetic mean of the measurements from multiple end-point temperature and humidity sensors within that region; α j q is the solar radiation correction factor for region j; j The heat load per unit area in region j is expressed in W / m². 2 .

[0017] Step S3: Temperature Prediction

[0018] Based on the principle of cooling supply and demand balance, the predicted value of water supply temperature T is derived in reverse. 预测 The calculation formula is:

[0019] T 预测 =T 回 -Q 需 / (M×c×ρ);

[0020] Step S4: Logical Judgment and Adjustment

[0021] T 预测 Compared with the initial set water supply temperature T 初 A comparison is made, and the corresponding water supply temperature adjustment strategy is implemented based on the comparison results:

[0022] If T 预测 <T 初 The system is determined to have a cooling supply that is less than the cooling demand, and the main unit maintains a temperature range of T. 初 The system runs and generates alarm messages to prompt administrators to assess whether the water supply temperature needs to be lowered.

[0023] If T 预测 =T 初 It is determined that the supplied cooling capacity equals the demanded cooling capacity, and the main unit maintains the initial operation at T.

[0024] If T 预测 >T 初 The condition is determined to be that the supplied cooling capacity exceeds the demanded cooling capacity, and the temperature deviation rate ∂ = (T) is calculated. 预测 -T 初 ) / T 初 ×100%, if ∂ ≥ preset threshold, then adjust the water supply temperature to T. 预测 If ∂ < preset threshold, the host maintains T. 初 run.

[0025] The preset threshold is preferably 5%. This threshold can be adjusted according to energy-saving needs and application scenarios. The smaller the threshold, the greater the energy saving effect. When adjusting, it is necessary to comprehensively balance the host's operating life and energy-saving benefits.

[0026] Step S5: Model Optimization

[0027] Deep learning models are used to iteratively optimize the parameters for calculating cooling demand, improving prediction accuracy. Specifically, this includes periodically extracting historical operating data, including indoor temperature changes, outdoor temperature changes, and air conditioning unit energy consumption data, and automatically correcting the solar radiation correction factor α. j and heat load per unit area q j Then, retrain the model parameters.

[0028] Step S6: Mode Switching

[0029] The method supports one-click switching between energy-saving mode and the original system mode, facilitating comparison and verification of energy-saving effects. In energy-saving mode, the system runs automatically without manual intervention.

[0030] Secondly, the present invention also provides a control system for automatically adjusting the water supply temperature of a central air conditioning system to implement the above method, comprising:

[0031] The air conditioning room control system includes a smart gateway, an air conditioning unit programmable logic controller (PLC), a touch screen HMI, and a water supply temperature sensor. 供 Return water temperature sensor T 回 And a water supply flow meter M. The touchscreen HMI communicates with the PLC via TCP / IP protocol to set the initial water supply temperature Tinitial. The water supply temperature sensor Tinitial 供 Return water temperature sensor T 回 The temperature transmitter is connected to the PLC analog input module, and the water flow meter M communicates with the PLC via the Modbus-RTU protocol. The smart gateway communicates with the PLC via the Modbus-RTU protocol and uploads the air conditioning unit's operating data to the cloud platform via a 4G or 5G network.

[0032] The terminal data acquisition system includes n terminal temperature and humidity sensors T n Outdoor temperature and humidity sensor T out And the smart gateway, where n is a positive integer greater than 0. The terminal temperature and humidity sensor T n Based on the building's area, the installation locations cover typical areas in the east, south, west, and north directions, as well as key locations in public areas such as the lobby, corridors, and restaurants. The terminal temperature and humidity sensor T... n This is a wirelessly rechargeable sensor with a built-in LoRa communication protocol and a battery life of at least one year. The smart gateway and the outdoor temperature and humidity sensor T are also mentioned. out Installed in an open area of ​​a building, the smart gateway 2 collects T data via the LoRa protocol. n and T out The data is then uploaded to the cloud platform via 4G or 5G networks.

[0033] The data processing system includes a cloud platform, operating PCs, and mobile terminals. The cloud platform deploys a building vertical mechanism model and a deep learning optimization module to execute the aforementioned control methods. The operating PCs are deployed in the building engineering management office for real-time monitoring of the system's operational status. The mobile terminals are used by administrators to remotely view operational data and receive alarm information.

[0034] Both smart gateway one and smart gateway two have built-in 4G / 5G communication modules, supporting multi-protocol conversion functions such as Modbus-RTU, TCP / IP, and LoRa, enabling bidirectional data transmission between the air conditioning unit, terminal sensors, and the cloud platform.

[0035] Thirdly, the present invention also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements a control method for automatically adjusting the water supply temperature of a water-cooled central air conditioning system.

[0036] Fourthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements a control method for automatically adjusting the water supply temperature of a water-cooled central air conditioning system.

[0037] The embodiments of the present invention have the following advantages:

[0038] By accurately calculating terminal cooling demand using a building vertical mechanism model, and dynamically adjusting the water supply temperature, the system achieves a precise match between cooling supply and demand, avoiding energy waste caused by excess cooling. Energy savings of over 20% are achieved, demonstrating significant energy conservation and consumption reduction. The system employs vertical layered calculation of cooling demand, taking into account the thermal environment differences between different floors and areas, preventing localized overcooling or overheating, ensuring uniform indoor temperature throughout the building, and improving environmental comfort. The system supports unmanned management, automatic operation and alarms, reducing manual inspection and operation workload. Management personnel can remotely monitor, improving management efficiency and enabling unmanned operation of the air conditioning room, reducing management and maintenance costs. Utilizing a Python deep learning module, the model achieves autonomous iterative optimization, continuously improving the accuracy of cooling calculation and temperature prediction, adapting to different building conditions and long-term operational changes, enhancing system stability and reliability, and demonstrating strong adaptability. This system is compatible with multiple communication protocols including Modbus-RTU, TCP / IP, LoRa, and 4G / 5G, making it adaptable to various brands and models of air conditioning units. Sensor placement can be flexibly adjusted according to building area, making it suitable for various commercial buildings and large venues, offering excellent compatibility and scalability. The entire system features lightweight deployment, a short modification cycle, convenient implementation, and no impact on the normal operation of the building's air conditioning system. The system does not require shutdown of the air conditioning system during modification, and installation is simple. The system does not modify any control logic of the original control system and is completely independent, resulting in very low modification risk. The energy-saving mode can be switched back to the original system mode with one click, facilitating verification of energy-saving effects and ensuring rapid restoration of the original system in case of system failure. The system has low hardware costs, is easy to install, and offers significant energy-saving effects. Investment costs can generally be recovered within 1-2 years, demonstrating good economic and social benefits and a short investment payback period. By significantly reducing the energy consumption of central air conditioning systems, carbon emissions are reduced. The promotion and application of this invention will drive the innovative development of central air conditioning energy-saving technologies, promote the deep application of IoT, AI, and other technologies in the field of building energy conservation, and drive the upgrading of related industries. Attached Figure Description

[0039] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating the steps of a control method for automatically adjusting the water supply temperature of a water-cooled central air conditioner, provided in some embodiments of the present invention.

[0041] Figure 2 This is a schematic diagram of the energy consumption of the air conditioning unit during the testing of a water-cooled central air conditioning system that automatically adjusts the water supply temperature, according to some embodiments of the present invention.

[0042] Figure 3 This is a schematic diagram of the electrical control structure of a control system and method for automatically adjusting the water supply temperature of a water-cooled central air conditioner, provided in some embodiments of the present invention. Detailed Implementation

[0043] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0044] Reference Figure 1 As shown, this application provides a control method for automatically adjusting the water supply temperature of a water-cooled central air conditioning system, which includes the following steps:

[0045] Step S1, Data Acquisition: Real-time acquisition of the water supply temperature T of the air conditioning unit. 供 Return water temperature T 回 Water supply flow rate M, and indoor temperature T in and outdoor temperature T out Indoor and outdoor temperature and humidity data; specifically including: setting the initial water supply temperature T via the touchscreen HMI. 初 Start the air conditioning unit and all sensors and gateway devices; the terminal temperature and humidity sensor T n Outdoor temperature and humidity sensor T out Data is collected at a frequency of 1 minute / time and uploaded to the cloud platform via the smart gateway 2; water supply temperature sensor T 供 Return water temperature sensor T 回 The water flow meter M collects data and uploads it to the cloud platform via PLC and smart gateway.

[0046] Step S2, Cooling Capacity Calculation: Calculate the actual cooling capacity Q supplied by the air conditioning unit based on the collected data. 供 Total cooling capacity demand at building terminals Q 需 This includes: based on the collected data, utilizing the actual cooling capacity Q supplied by the air conditioning unit. 供 The calculation formula for Q: 供 =M×c×ρ×(T 回 -T 供 ), to obtain the actual cooling capacity Q supplied by the air conditioning unit 供 In the formula, c is the specific heat capacity of water, taken as 4.2 × 10⁻⁶. 3 J / (kg·℃), where ρ is the density of water, taken as 1000 kg / m³. 3 M is in meters. 3 / h, convert Q to a unit. 供 Convert the unit to kW.

[0047] This also includes: dividing the building into m zones based on vertical spatial layers, and calculating each zone using the formula: Q j =[K j ×A j ×(T out -T in )×α j ]+(q j ×A j ), calculate the cooling demand Q for each region j. j According to the cooling capacity requirement Q j Summing these values ​​yields the total cooling capacity requirement Q at the building's terminals. 需 In the formula, K j Let A be the heat transfer coefficient of the building envelope in region j. j For the area of ​​the enclosure structure of region j, T out The outdoor temperature, T in Let α be the average indoor temperature of region j. j Let q be the solar radiation correction factor for region j. j Let T be the heat load per unit area in region j. The average indoor temperature T in region j is... in The indoor average temperature T is obtained by taking the arithmetic mean of the measurements from multiple end temperature and humidity sensors in the area. in Through multiple end temperature and humidity sensors T in this area n The measured values ​​are obtained by taking the arithmetic mean, that is... , where k is the sensor number in the area.

[0048] Step S3, Temperature Prediction: Based on the principle of cooling supply and demand balance and the corresponding calculation formula, the predicted value of water supply temperature T is derived in reverse. 预测 The calculation formula is as follows: Where c is the specific heat capacity of water, and ρ is the density of water;

[0049] Step S4, Logic Judgment and Adjustment: Compare the predicted water supply temperature T with the initial set water supply temperature Tinitial, and execute the corresponding water supply temperature adjustment strategy based on the comparison result; the water supply temperature adjustment strategy specifically includes:

[0050] If T 预测 <T 初 The system is determined to have a cooling supply that is less than the cooling demand, and the main unit maintains a temperature range of T. 初 The system runs and generates alarm messages to prompt administrators to assess whether the water supply temperature needs to be lowered.

[0051] If T 预测 =T 初The system is determined to have a cooling supply equal to a cooling demand, and the main unit maintains a temperature range of T. 初 run;

[0052] If T 预测 >T 初 The condition is determined to be that the supplied cooling capacity exceeds the demanded cooling capacity, and the temperature deviation rate ∂ = (T) is calculated. 预测 -T 初 ) / T 初 ×100%, if ∂ ≥ preset threshold, then adjust the water supply temperature to T. 预测 If ∂ < preset threshold, the host maintains T. 初 The preset threshold is 5%, and this threshold can be adjusted according to energy-saving needs and application scenarios. The smaller the threshold, the greater the energy saving effect. When adjusting, it is necessary to comprehensively balance the host's operating life and energy-saving benefits.

[0053] Step S5, Model Optimization: Iteratively optimize the cooling demand calculation parameters using a deep learning model to improve prediction accuracy. This includes: periodically extracting historical operating data using a deep learning model, including indoor temperature changes, outdoor temperature changes, and air conditioning unit energy consumption data, and automatically correcting the solar radiation correction coefficient α. j and heat load per unit area q j We then iterate through the training of model parameters to improve prediction accuracy.

[0054] Specifically, the cloud platform's deep learning module continuously collects system operation data and automatically extracts historical operation data monthly, including terminal temperature changes, outdoor temperature changes, and air conditioning unit energy consumption data, and automatically corrects the solar radiation correction factor α. j and heat load per unit area q j Retrain the model parameters to improve Q. 需 Calculation accuracy and T 预测 This ensures accuracy and enables adaptive upgrades to the control system.

[0055] It also includes step S6: a one-click switching function. The system supports one-click switching between energy-saving mode and the original system mode, facilitating comparison and verification of energy-saving effects. In energy-saving mode, the system operates automatically without manual intervention, achieving unmanned management of the air conditioning room.

[0056] In some embodiments of this application, such as Figure 3 As shown, a control system for automatically adjusting the water supply temperature of a central air conditioning system that implements the above method includes:

[0057] The air conditioning room control system includes a smart gateway (4), an air conditioning unit programmable logic controller (PLC) (5), a touch screen HMI (HMI) (6), and a water supply temperature sensor (T). 供 8. Return water temperature sensor T 回9 and water flow meter M7; the touch screen HMI6 is used to set the initial water supply temperature T. 初 The water supply temperature sensor T 供 Return water temperature sensor T 回 The water flow meter M7 is connected to PLC5, and PLC5 communicates with the cloud platform 3 through smart gateway 4.

[0058] The terminal data acquisition system includes n terminal temperature and humidity sensors T n 11. Outdoor temperature and humidity sensor T out 12 and smart gateway 210; the terminal temperature and humidity sensor T n 11 and outdoor temperature and humidity sensor T out 12 connects to the smart gateway 2 10 via wireless communication, and the smart gateway 2 10 communicates with the cloud platform 3;

[0059] The data processing system includes a cloud platform 3, an operating computer PC1, and a mobile terminal 2; the cloud platform 3 is equipped with a building vertical mechanism model and a deep learning optimization module, which are used to execute the above control methods.

[0060] The terminal temperature and humidity sensor T n 11 is a wireless charging sensor with built-in LoRa communication protocol and a power storage capacity of no less than 1 year; both the smart gateway 4 and smart gateway 10 have built-in 4G / 5G communication modules and support multi-protocol conversion.

[0061] As an example, a central air conditioning system for automatically adjusting the water supply temperature includes an air conditioning room control system, a terminal data acquisition system, and a data processing system; the air conditioning room control system includes an intelligent gateway, an air conditioning main unit programmable controller (PLC5), and a touch screen (HMI6) for initially setting the water supply temperature T. 初 (This serves as both the initial temperature for host startup and as T) 预测 (Lower limit temperature), water supply temperature sensor T 供 8. Return water temperature sensor T 回 9. Water supply flow meter M7; Smart gateway 4 communicates with the air conditioning unit programmable controller PLC5 via Modbus-RTU communication protocol. Smart gateway 4 transmits the air conditioning unit's operating data to the cloud platform 3 via 4G or 5G communication. Touchscreen HMI6 communicates with the air conditioning unit programmable controller PLC5 via TCP / IP protocol, allowing administrators to set the initial water supply temperature value for the unit before starting it. Water supply temperature sensor T... 供 8. Return water temperature sensor T 回9. The temperature transmitter is connected to the PLC5 analog module of the air conditioning unit programmable controller. The water supply flow meter M communicates with the PLC5 via Modbus-RTU. The vertical model of the cloud platform 3 mechanism can be obtained through formula Q. 供 The cooling capacity supplied by the main unit can be calculated using the formula: M × c × ρ × ∆T1. In the formula, c is the specific heat capacity of water, taken as 4.2 × 10³ J / (kg·℃), ρ is the density of water, taken as 1000 kg / m³, M is the supply water flow rate (in m³ / h), and ∆T1 is the return water temperature sensor temperature. 回 9 and water supply temperature sensor T 供 The temperature difference is 8. Unit conversion: 1 kW = 3.6 × 10⁶ J / h, final Q. 供 The unit is kW. The terminal data acquisition system contains n (a positive integer greater than 0) temperature and humidity sensors T n 11 and outdoor temperature and humidity sensor T out 12. The number of end sensors is determined by the building's area. For buildings smaller than 20,000 square meters, install 6 to 10 sensors. For buildings larger than 20,000 square meters, the number can be increased based on actual data collection needs. Installation locations are typical locations in the four different directions (east, south, west, and north) of the building, as well as key locations in the building's public areas (such as the lobby, corridors, and restaurants). All temperature and humidity sensors installed at the end points are wirelessly rechargeable, with a battery life exceeding one year. The Smart Gateway 2.10 can be installed in relatively open areas of the building. The Smart Gateway 2.10 collects data from the temperature and humidity sensors distributed throughout the building via the LoRa protocol. n 11. Data: Install a temperature and humidity sensor T outdoors at a distance of no more than 10km from the smart gateway 210. out 12 is used to detect changes in outdoor temperature. The smart gateway 10 transmits the collected data from the terminal temperature and humidity sensor T via 4G or 5G communication. n 11. Data is transmitted to cloud platform 3. The data processing system includes cloud platform 3, operating computer PC1, and mobile terminal 2. PC1 is best installed in the building's engineering management office for real-time monitoring and management of air conditioning operation. Mobile terminal 2 primarily facilitates management personnel to view air conditioning operation status and receive alarm signals in real time, improving management efficiency. Cloud platform 3 uses Python deep learning technology to establish a building vertical mechanism model for real-time and accurate calculation of the building's total cooling capacity. The building vertical mechanism model is a cooling load calculation model that divides the building's vertical space into layers. Its core is to calculate the cooling load layer by layer based on the thermal environment differences between different floors (e.g., strong solar radiation on the top floor, low temperature on the bottom floor, and high population density on the middle floors) and then sum them up to obtain the total cooling capacity requirement for the entire building. Using a conventional mechanism model to calculate the total indoor cooling capacity requirement of the entire building results in a large error. The vertical layered model can significantly improve the accuracy of cooling capacity calculation, according to formula Q. 需 =Q trans(Heat transfer and cooling load of building envelope) + Q internal (Indoor heat load), Q trans =K×A×ΔT2×α,Q internal =A×q, where K is the heat transfer coefficient of the building envelope (unit: °C), representing the thermal insulation performance of the building envelope (the smaller the value, the better the insulation, such as K≈0.5~1.5 for exterior walls, K≈2.0~4.0 for windows, see GB51245-2017 Unified Standard for Energy-Saving Design of Industrial Buildings for details), and A is the area of ​​the building envelope (unit: m²). 2 α is the solar radiation correction factor (refer to the standard GB 50176-2016 "Code for Thermal Design of Civil Buildings"), q is the heat load per unit area, which varies in different regions (refer to the standard GB / T 51074-2015 "Code for Urban Heating Planning"), and ΔT2 is the indoor-outdoor calculated temperature difference (unit: °C), i.e., ΔT2 = T out -T in T out For the outdoor sensor temperature, T in T represents the average temperature of all areas within the room. in =( If the building is divided into m vertical zones, where j represents each floor, the cooling requirement for each zone is... Therefore, the total cooling capacity Q required for the entire building is... 需 = After establishing a vertical mechanism model corresponding to the building on cloud platform 3, the model has the function of autonomous learning and optimization, and can obtain the end-point T in real time. n and outdoor T out Data changes can be collected at a frequency of 1 minute per instance to predict the building's required cooling capacity Q. 需 This enables intelligent cooling capacity prediction and management. The model is based on Q... 需 Inverse prediction of water supply temperature T 预测 =T 回 -Q 需 / M×c×ρ. The calculated T 预测 With T 初 In comparison, because this control method is biased towards energy saving and consumption reduction, the lower the water supply temperature, the higher the air conditioning energy consumption. If T 预测 <T 初 , indicating Q 供 需 The main unit's water supply temperature continues to follow T. 初 The system will run, but it will generate alarm information and send it to PC1 and mobile phone2, allowing administrators to determine whether the water supply temperature needs to be lowered; if T 预测 =T 初 , indicating Q 供 =Q 需 ​The main unit's water supply temperature continues to follow T. 初 Run; if T 预测 >T 初 , indicating Q 供 Q 需 Temperature deviation rate ∂ = (T 预测 -T 初 )×100% / T 初 ≥5% allows writing to T 预测 Depending on the service scenario, the write range of the deviation rate ∂ can be adjusted. The smaller the deviation rate ∂, the greater the energy saving. In actual deployment scenarios, it is necessary to balance the proportion of host lifespan and energy saving. Cloud platform 3 will T 预测 Write the value to T 初 The corresponding PLC5 address, the host will follow T 预测 When the system is running, the main unit will either reduce its load or enter standby mode. This control method can quickly adjust the chilled water supply temperature of the air conditioning system according to changes in outdoor weather without affecting indoor comfort, reducing building energy waste, achieving energy-saving and stable operation of the central air conditioning system, and enabling unmanned management of the computer room, effectively reducing management costs.

[0062] In some embodiments of this application, a control system and method for automatically adjusting the water supply temperature of a central air conditioning system are described, such as... Figure 3 As shown, the system includes an air conditioning room control system, a terminal data acquisition system, and a data processing system; the room control system includes an air conditioning unit programmable controller (PLC5), a smart gateway (4), and a touchscreen HMI6 for setting the initial water supply temperature (T). 初 Water supply flow meter M7, water supply temperature sensor T 供 8. Return water temperature sensor T 回 9. Install a smart gateway-4 control box in the air conditioning main unit room. Insert a 4G SIM card into the gateway-4 and connect the air conditioning main unit PLC5 to the gateway via a network cable. If the main unit PLC5 does not have a built-in Modbus communication port, a corresponding communication module can be added. It is also necessary to ensure that the air conditioning main unit's touchscreen HMI6 is in communication mode with the main unit. Install a flow meter (M7) and a water supply temperature sensor (T) on the main water supply pipeline. 供 8 and return water temperature sensor T 回 All 9 are connected to the PLC5 analog input module; the terminal acquisition system includes a smart gateway 210 and a terminal temperature and humidity sensor T. n 11. Outdoor temperature and humidity sensor T out12. Install n wireless temperature sensors with built-in LoRa protocol in key areas inside the building. Configure the network of n temperature sensors using a mobile APP. Install a smart gateway 210 control box in a relatively open area of ​​the building. Insert a 4G SIM card into the smart gateway 210. The data processing system includes a control computer PC1, a mobile phone 2, and a cloud platform 3. Real-time communication between PC1 and mobile phone 2 is achieved through remote software and the APP. PC1 accesses the corresponding cloud platform 3. Deploy a physical principle-based vertical mechanism white box model of air conditioning operation on the cloud platform 3. The mechanism model analyzes and processes the collected terminal temperature and humidity sensor data and air conditioning operation data, and calculates the total cooling capacity Q required by the building. 需 Reverse prediction T 供 Predicted value T 预测 Real-time judgment of T 预测 With T 初 The relationship when T 预测 >T 初 , indicating Q 供 Q 需 Cloud platform 3 will T 预测 Write the value to T 初 The host will use the corresponding PLC address according to T 预测 To achieve energy-efficient operation.

[0063] This implementation case uses a 10-story, 11,000-square-meter all-glass curtain wall hotel building as the application scenario. The building is equipped with two Midea centrifugal chiller units, model CCWE650H, with a cooling capacity of 2285kW and a rated power of 369.8kW / H. Each unit is equipped with a digital electricity meter. In daily management, the hotel adopts a one-in-one standby strategy for the units. The chilled water supply temperature of the units is set to 7℃ year-round. In addition, the air conditioning system is also equipped with two 55kW fixed-frequency chilled water pumps, two 55kW fixed-frequency cooling water pumps, and a cooling tower system. This test aims to achieve the control goal of "cooling on demand and energy saving" while ensuring that indoor comfort is not affected.

[0064] 1. Control System Deployment and Selection

[0065] The control system of this invention consists of three parts: an air conditioning room control system, a terminal data acquisition system, and a data processing system. The selection, deployment location, and parameter configuration of the hardware in each part are as follows:

[0066] (1) Hardware deployment of the air conditioning room control system: The intelligent gateway-4 control box is deployed in the air conditioning room on the first basement floor of the building. The core is used to collect host operation data and execute cloud platform 3 temperature commands. The intelligent gateway 4 is a Huawei AR502H edge computing gateway, installed on the wall next to the PLC control cabinet in the air conditioning room. It supports Modbus-RTU / TCP and 4G / 5G communication protocols; the 4G / 5G access is via the operator's IoT card, bound to the 3MQTT server address of the cloud platform; the programmable logic controller (PLC5) of the air conditioning unit is a Siemens S7-1200 (model 1214C DC / DC / DC), equipped with an analog input module SM 1231 (4-channel AI). The supply and return water temperature sensors are connected to the SM 1231 through temperature transmitters; the PLC5 communicates with the intelligent gateway 4 via the Modbus-RTU protocol and with the touch screen HMI6 via the TCP / IP protocol; the touch screen HMI6 on the air conditioning unit control cabinet is a Weintek MT8102iE (10.1-inch), where administrators set the initial supply water temperature T. 初 The temperature is 7℃. In this case, the chilled water supply temperature sensor T... 供 8. Return water temperature sensor T 回 All nine devices use PT100 platinum resistance temperature sensors with an accuracy of ±0.2℃ and a measurement range of -20~60℃. The water supply flow meter is a Xun'er SE11 electromagnetic flow meter (DN100), installed on the main chilled water supply pipeline, with an accuracy of 1.0 class, and has been connected to the PLC5 via the Modbus-RTU protocol.

[0067] (2) Hardware deployment of the terminal data acquisition system: The system is deployed on each floor of the building and outdoors. Its core function is to collect indoor and outdoor temperature and humidity data to provide a basis for the cooling capacity calculation of the cloud platform 3. The smart gateway 210 model is the WD140 LoRa gateway of the Wutong Bolian brand, which is deployed on the roof of the 10th floor of the building. The communication distance is ≤10km. It transmits data with the cloud platform 3 through a 4G SIM card and operates in the frequency band of 410~493MHz. The terminal temperature sensors used are AM102 wireless rechargeable temperature and humidity sensors from Xingzong IoT, with a one-year battery life, a measurement range of -20℃ to 60℃, a sampling accuracy of ±0.2℃, and an operating frequency band of 470~510MHz. One sensor is installed in each of the following locations: one in the east and west corners of the 4th floor (avoiding heat sources); one in each of the south and north corners of the 8th floor (avoiding heat sources); one in the lobby and one in the restaurant on the 1st floor; one in the conference room on the 10th floor; and one outside the platform on the 10th floor. A total of eight temperature sensors are installed. All sensors communicate with the smart gateway 210 via the LoRa protocol, with a sampling frequency set to 1 minute / time.

[0068] (3) Hardware and software configuration of data processing system: The cloud platform 3 server adopts Alibaba Cloud ECS cloud server (general type g7, 4 cores 8GB memory, 5Mbps bandwidth), deploys time series database InfluxDB 2.7 (to store historical running data) and MQTT message server EMQ X 5.0 (to receive sensor data); the operating computer PC1 is configured with Intel i5 processor, 8GB memory, and Windows 10 system, and deploys cloud platform 3 Web management terminal (for real-time monitoring and parameter setting); the mobile terminal 2 supports the installation of customized APP (for receiving alarm information and viewing running status); cloud platform 3 is developed with Python 3.8 and equipped with TensorFlow 2.15 deep learning framework to build building vertical mechanism model; model parameter settings: the floors are divided into 4 vertical areas (1st floor, 4th floor, 8th floor, 10th floor).

[0069] 2. Control System Software Flow and Calculation Implementation

[0070] The core of the control method of this invention is "data acquisition, cooling capacity calculation, temperature derivation, command issuance, and loop optimization". The specific process and calculation practice are as follows:

[0071] (1) System initialization and startup: The administrator sets the initial water supply temperature T through the touch screen HMI6. 初 =7℃, PLC5 will T 初 Write the water supply temperature control register, start the chiller unit and chilled water pump, the main unit runs at a water supply temperature of 7℃, and the chilled water pump and cooling water pump operate at a fixed frequency of 50Hz.

[0072] (2) Real-time data acquisition and preprocessing: The cloud platform 3 acquires PLC5 operating data in real time during host operation, including chilled water supply temperature, chilled water return temperature, and total chilled water flow rate.

[0073] Where c = 4.2 × 10 3 J / (kg·℃), ρ=1000kg / m 3 The sample was collected at 10:10 pm, M=393m. 3 / h, , ,but =1834kW.

[0074] End-point data acquisition: The smart gateway 2.10 collects data from 7 indoor T7 sensors and 1 outdoor T7 sensor via the LoRa protocol. out Sensor data is uploaded to cloud platform 3; cloud platform 3 preprocesses the data, including removing outliers (using the 3x standard deviation method to remove jump data caused by sensor malfunctions) and calculating the average indoor temperature T for each floor.in Calculate the indoor-outdoor temperature difference ΔT2=T out -T in (T) in The average indoor temperature of the entire building, T in =( ) / 8, Here j=4.

[0075] (3) Total cooling capacity demand at the terminal Q 需 Estimation (vertical mechanism model): Based on the formula The cloud platform 3 calculates the cooling demand hierarchically using a vertical mechanism model, and then aggregates the results to obtain the total cooling demand Q for the entire building. (T data was collected.) out =32℃, T1=23℃, T2-4=24℃, T5-8=25℃, T10=26℃ (for ease of calculation, the collected temperatures are accurate to the nearest whole number). For the double-glass curtain wall, K is taken as 5.5, α is the solar radiation correction factor taken as 0.3, and q is the heat load per unit area taken as 110. Calculations show Q1=124.85kW, Q2-5=479.6kW, Q6-9=486.2kW, Q10=119.9kW, Q... 需 =1210.55kW;

[0076] (4) Derive T in reverse from the required cooling capacity. 预测 With the issuance of control decisions: T 预测 =T 回 -(Q 需 ×3600) / (M×4.2×1000), simplified formula: T 预测 =T 回 -Q 需 / (1.163×M)=8.35℃, T 预测 >T 初 , indicating Q 供 Q 需 The deviation rate ∂ = 19.28%, and the cloud platform 3 transmits T through the intelligent gateway 4. 预测 =8.3℃ is automatically written to the PLC's water supply temperature setting register. Since all data of the entire air conditioning system are constantly changing during operation, the above calculation process is only a demonstration of the model algorithm at a specific point in time.

[0077] 3. Model self-learning optimization

[0078] The vertical mechanism model of Cloud Platform 3 has autonomous learning capabilities, automatically extracting historical operating data (terminal temperature changes, outdoor temperature changes) every month, and automatically correcting the solar radiation correction coefficient α. j (Adjust according to the season, using higher values ​​in summer and lower values ​​in winter), optimize the heat load q per unit area. j(Adjust according to personnel density and equipment operation status), retrain the model parameters to improve system stability and accuracy.

[0079] Case test data

[0080] After one week of stable operation following debugging, this case study began a 10-day energy-saving test. Since the energy-saving system did not change the control logic of the original control system, the energy-saving system and the original system can be switched with one click. During the verification of the energy-saving effect, the energy-saving mode was turned on every other day for 5 days and the original system was run for 5 days. The energy consumption data of the air conditioning unit was recorded for 24 hours and compared to calculate the energy saving rate. The following is the real-time data during the test.

[0081] like Figure 2 As shown, this is a continuous 10-day test of the air conditioner's 24-hour usage. The original day refers to the day the air conditioner operates in its original control system mode, and the energy-saving day refers to the day the energy-saving system is turned on. The data shows that the indoor temperature changes little regardless of the mode, indicating that indoor comfort is not affected in the energy-saving state. However, the daily energy consumption is significantly reduced in the energy-saving state. The energy saving rate = original daily energy consumption - energy-saving day energy consumption / original daily energy consumption. In this test, the energy saving rate = 36269 - 28704 / 36269 = 20.86%, showing a significant energy-saving effect.

[0082] Primitive Day Energy Saving Day Primitive Day Energy Saving Day Primitive Day date June 11 June 12 June 13 June 14 June 15 Outdoor temperature (°C) 32.6 32.4 29.8 29.5 30 Lobby temperature (°C) 22.7 23.3 22.6 23.4 22.3 Restaurant temperature (°C) 22.7 23.3 22.6 23.4 22.3 Room temperature (°C) in A418 26.5 24.8 23.2 23.7 25.8 Room temperature (°C) in B409 23.9 23.9 22.3 22.0 23.9 Room temperature (°C) in C801 23.8 23.6 22.9 23.2 23.7 Room temperature (°C) in D812 25.3 24.5 22.7 23.4 25 Temperature in the conference room (°C) 25.5 25.6 24.7 24.7 28.4 Daily electricity consumption (kW) 8170.5 6063.9 7144.5 5463.3 7009.2

[0083] Table 1.1

[0084] Energy Saving Day Primitive Day Energy Saving Day Primitive Day Energy Saving Day date June 16 June 17 June 18 June 19 June 20 Outdoor temperature (°C) 31.3 29.1 30.7 31.4 30.3 Lobby temperature (°C) 24 23.9 25 22 24 Restaurant temperature (°C) 24 23.9 25 22 24 Room temperature (°C) in A418 24.5 25.2 25.5 25.3 24.9 Room temperature (°C) in B409 24.8 22.5 22.7 23.7 24.3 Room temperature (°C) in C801 23.8 23.5 22.9 24.1 23.9 Room temperature (°C) in D812 24.2 24.9 25.2 25 24.6 Temperature in the conference room (°C) 25 24.1 25 23.7 24 Daily electricity consumption (kW) 6133.2 6161.7 5582.1 7783.2 5460.9

[0085] Table 1.2

[0086] The beneficial effects of this application include: (1) Significant energy saving and consumption reduction: By accurately calculating the terminal cooling demand through the building vertical mechanism model, the water supply temperature is dynamically adjusted to achieve accurate matching between cooling supply and demand, avoid energy waste caused by excess cooling, significantly reduce the energy consumption of the central air conditioning system, and reduce operating costs. (2) Improved indoor comfort: The cooling demand is calculated vertically and layered, taking into account the thermal environment differences of different floors and areas, avoiding local areas from being too cold or too hot, ensuring the uniformity of indoor temperature throughout the building, and improving environmental comfort. (3) Reduced management and maintenance costs: The system supports unmanned management, automatic operation and alarm, reducing the workload of manual inspection and operation, and management personnel can remotely monitor and improve management efficiency. (4) Strong adaptability: Relying on the Python deep learning module to realize the autonomous iterative optimization of the model, continuously improve the accuracy of cooling calculation and temperature prediction, adapt to different building conditions and long-term operating changes, and improve the stability and reliability of system operation. (5) Good compatibility and scalability: It is compatible with multi-protocol communication design, can be adapted to different brands and models of air conditioning units, and the sensor layout can be flexibly adjusted according to the building area, adapting to various commercial buildings, large venues and other scenarios. (6) Easy system installation: The entire system is a lightweight deployment, with a short transformation cycle, convenient implementation, no impact on the use of building air conditioning, and significant effect. (7) Low transformation risk: The system does not modify any control logic of the original control system, the transformation risk is very low, the energy-saving mode can be switched with one click, and the energy-saving effect verification is more accurate.

[0087] Some embodiments of the present invention also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method described above.

[0088] Some embodiments of the present invention also provide a computer-readable storage medium on which a computer program is stored, and which, when executed by a processor, implements the method described above.

[0089] Some embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the method described above.

[0090] As the apparatus embodiment is basically similar to the method embodiment, it is described in a relatively simple manner. For relevant details, please refer to the description of the method embodiment.

[0091] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0092] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0094] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0096] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0097] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the aforementioned element.

[0098] The above provides a detailed description of the control system and method for automatically adjusting the water supply temperature of a water-cooled central air conditioning system. Specific examples have been used to illustrate the principles and implementation methods of the invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the invention. Therefore, the content of this specification should not be construed as a limitation of the invention.

Claims

1. A control method for automatically adjusting the water supply temperature of a water-cooled central air conditioning system, characterized in that, The method includes the following steps: Step S1, Data Acquisition: Real-time acquisition of the water supply temperature T of the air conditioning unit. 供 Return water temperature T 回 Water supply flow rate M, and indoor temperature T in and outdoor temperature T out Indoor and outdoor temperature and humidity data; Step S2, Cooling Capacity Calculation: Calculate the actual cooling capacity Q supplied by the air conditioning unit based on the collected data. 供 Total cooling capacity demand at building terminals Q 需 ; Step S3, Temperature Prediction: Based on the principle of cooling supply and demand balance and the corresponding calculation formula, the predicted value of water supply temperature T is derived in reverse. 预测 The calculation formula is: T 预测 =T 回 -Q 需 / (M×c×ρ), where c is the specific heat capacity of water and ρ is the density of water; Step S4, Logical Judgment and Adjustment: T 预测 Compared with the initial set water supply temperature T 初 Compare the results and implement the corresponding water supply temperature adjustment strategy based on the comparison results; Step S5, Model Optimization: Use a deep learning model to iteratively optimize the parameters for calculating cooling demand, thereby improving prediction accuracy.

2. The method according to claim 1, characterized in that, The actual cooling capacity Q supplied by the air conditioning unit is calculated based on the collected data. 供 Total cooling capacity demand at building terminals Q 需 ,include: Based on the collected data, the actual cooling capacity Q supplied by the air conditioning unit is used. 供 The calculation formula for Q: 供 =M×c×ρ×(T 回 -T 供 ), to obtain the actual cooling capacity Q supplied by the air conditioning unit 供 In the formula, c is taken as 4.2 × 10. 3 J / (kg·℃), ρ is taken as 1000 kg / m 3 M is in meters. 3 / h, convert Q to a unit. 供 Convert the unit to kW.

3. The method according to claim 1, characterized in that, The actual cooling capacity Q supplied by the air conditioning unit is calculated based on the collected data. 供 Total cooling capacity demand at building terminals Q 需 It also includes: The building is divided into m zones based on vertical spatial layers, and the calculation formula is used for each zone: Q j =[K j ×A j ×(T out -T in )×α j ]+(q j ×A j ), calculate the cooling demand Q for each region j. j ; Based on the cooling capacity requirement Q j Summing these values ​​yields the total cooling capacity requirement Q at the building's terminals. 需 In the formula, K j Let A be the heat transfer coefficient of the building envelope in region j. j For the area of ​​the enclosure structure of region j, T out The outdoor temperature, T in Let α be the average indoor temperature of region j. j Let q be the solar radiation correction factor for region j. j Let be the heat load per unit area in region j.

4. The method according to claim 3, characterized in that, The average indoor temperature T in the area j in It is obtained by taking the arithmetic mean of the measurements from multiple end temperature and humidity sensors in the area.

5. The method according to claim 1, characterized in that, The water supply temperature regulation strategy specifically includes: If T 预测 <T 初 If the supply of cooling capacity is determined to be less than the demand for cooling capacity, the main unit will maintain the initial operation at T and at the same time generate an alarm message to prompt the management personnel to assess whether it is necessary to reduce the supply water temperature. If T 预测 =T 初 The system is determined to have a cooling supply equal to a cooling demand, and the main unit maintains a temperature range of T. 初 run; If T 预测 >T 初 The condition is determined to be that the supplied cooling capacity exceeds the demanded cooling capacity, and the temperature deviation rate ∂ = (T) is calculated. 预测 -T 初 ) / T 初 ×100%, if ∂ ≥ preset threshold, then adjust the water supply temperature to T. 预测 If ∂ < preset threshold, the host maintains T. 初 run.

6. The method according to claim 5, characterized in that, The preset threshold is 5%, and this threshold can be adjusted according to energy-saving needs and application scenarios. The smaller the threshold, the greater the energy-saving effect.

7. The method according to claim 1, characterized in that, The method of using a deep learning model to iteratively optimize the parameters for calculating cooling demand and improve prediction accuracy includes: The system uses a deep learning model to periodically extract historical operating data, including indoor temperature changes, outdoor temperature changes, and air conditioning unit energy consumption data, and automatically corrects the solar radiation correction factor α. j and heat load per unit area q j We then iterate through the training of model parameters to improve prediction accuracy.

8. The method according to claim 1, characterized in that, The real-time acquisition of the air conditioning unit's water supply temperature T 供 Return water temperature T 回 Water supply flow rate M, and indoor temperature T in and outdoor temperature T out Indoor and outdoor temperature and humidity data, including: Set the initial water supply temperature T via the touchscreen HMI 初 Start the air conditioning unit and all sensors and gateway devices; End temperature and humidity sensor T n Outdoor temperature and humidity sensor T out Data is collected at a frequency of 1 minute per instance and uploaded to the cloud platform via intelligent gateway 2. Water supply temperature sensor T 供 Return water temperature sensor T 回 The water flow meter M collects data and uploads it to the cloud platform via PLC and smart gateway.

9. A control system for automatically adjusting the water supply temperature of a central air conditioning system, implementing the method of any one of claims 1-8, characterized in that, include: The air conditioning room control system includes a smart gateway, an air conditioning unit programmable logic controller (PLC), a touch screen HMI, and a water supply temperature sensor. 供 Return water temperature sensor T 回 And the water supply flow meter M; The touchscreen HMI is used to set the initial water supply temperature T. 初 The water supply temperature sensor T 供 Return water temperature sensor T 回 The water supply flow meter M is connected to the PLC, and the PLC communicates with the cloud platform through the smart gateway. The terminal data acquisition system includes n terminal temperature and humidity sensors T n Outdoor temperature and humidity sensor T out And the smart gateway 2. The terminal temperature and humidity sensor T n Outdoor temperature and humidity sensor T out It connects to the smart gateway 2 via wireless communication, and the smart gateway 2 communicates with the cloud platform. The data processing system includes a cloud platform, an operating PC, and a mobile terminal. The cloud platform is deployed with a building vertical mechanism model and a deep learning optimization module, used to execute the control method described in any one of claims 1-8.

10. The system according to claim 9, characterized in that, The terminal temperature and humidity sensor T n It is a wireless charging sensor with built-in LoRa communication protocol and a power storage capacity of no less than 1 year; both smart gateway one and smart gateway two have built-in 4G / 5G communication modules and support multi-protocol conversion.

Images