Building radiation air conditioning system regulation method and system based on internet of things

Abstract

This application discloses a method and system for controlling a building radiant air conditioning system based on the Internet of Things (IoT). After acquiring at least one panel temperature data and auxiliary temperature data within a preset radiant area, this application reconstructs the temperature field of the preset radiant area based on the at least one panel temperature data and auxiliary temperature data. The condensation risk level of the preset radiant area is determined based on the reconstructed temperature field. When the condensation risk level is lower than a preset risk level, in response to the triggering of a preset control event, a target prediction model is determined based on the type of the preset control event. Using the target prediction model, a set of target control parameters for the preset radiant area is predicted based on the condensation risk level and the reconstructed temperature field. The radiant air conditioning system corresponding to the preset radiant area is then controlled based on the set of target control parameters. Therefore, the accuracy and safety of condensation prevention judgment in the radiant air conditioning system can be improved.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and specifically to a method and system for controlling building radiant air conditioning systems based on the Internet of Things. Background Technology

[0002] In recent years, with the rapid development of Internet technology, the deep integration of the Internet of Things (IoT) and building heating, ventilation, and air conditioning (HVAC) systems has become an important development direction in the field of smart buildings. In some scenarios where radiant terminals (such as capillary networks, ceiling / floor radiant panels) are coupled with independent fresh air systems and remote monitoring and automated adjustment are achieved through IoT architecture, in order to minimize building energy consumption while ensuring indoor thermal comfort and avoiding the risk of condensation on radiant surfaces.

[0003] In the research and practice of current technologies, the IoT control schemes for radiant air conditioning generally suffer from the following defects: the surface temperature distribution of the radiant panel is not uniform. Under the influence of factors such as hydraulic imbalance and local cold bridging effects, the temperature of locally cold clusters may have already fallen below the dew point temperature, but the temperature at a single point or on average still appears safe, leading to missed condensation detection. Therefore, radiant air conditioning systems frequently experience missed detection of local condensation in actual operation, posing a significant safety hazard related to condensation. Summary of the Invention

[0004] This application provides a method and system for controlling a building radiant air conditioning system based on the Internet of Things, which can improve the accuracy and safety of condensation prevention judgment in the radiant air conditioning system.

[0005] A method for controlling a building radiant air conditioning system based on the Internet of Things, comprising: Acquire at least one plate surface temperature data and auxiliary temperature data within a preset radiation area. The plate surface temperature data indicates the temperature distribution information of the radiation plate surface within the preset radiation area, and the auxiliary temperature data is used to help characterize the temperature distribution information of the preset radiation area. Based on the at least one plate surface temperature data and auxiliary temperature data, the temperature field of the preset radiation area is reconstructed, and the condensation risk level of the preset radiation area is determined according to the reconstructed temperature field. When the condensation risk level is lower than the preset risk level, in response to the triggering of a preset control event, a target prediction model is determined based on the type of the preset control event; Using a target prediction model, the target control parameter set for the preset radiation area is obtained based on the condensation risk level and the reconstructed temperature field. The radiant air conditioning system corresponding to the preset radiation area is regulated based on the target control parameter set.

[0006] Accordingly, embodiments of this application provide an IoT-based building radiant air conditioning system control system, comprising: The acquisition unit is used to acquire at least one plate surface temperature data and auxiliary temperature data within a preset radiation area. The plate surface temperature data indicates the temperature distribution information of the surface of the radiation plate within the preset radiation area, and the auxiliary temperature data is used to help characterize the temperature distribution information of the preset radiation area. The reconstruction unit is used to reconstruct the temperature field of the preset radiation area based on the at least one plate surface temperature data and auxiliary temperature data, and to determine the condensation risk level of the preset radiation area based on the reconstructed temperature field. The determining unit is used to determine a target prediction model based on the type of the triggered preset control event when the condensation risk level is lower than the preset risk level. The prediction unit is used to predict the set of target control parameters for the preset radiation area based on the condensation risk level and the reconstructed temperature field using a target prediction model. The control unit is used to control the radiant air conditioning system corresponding to the preset radiation area based on the target control parameter set.

[0007] In some embodiments, the reconstruction unit may specifically be used to fuse the at least one plate surface temperature data with the supply and return water temperature data, the cold bridge point temperature data of the enclosure structure, and the inner pipe wall temperature data to obtain fused temperature data; divide the preset radiation area into a preset number of temperature grids based on the size of the preset radiation area; map the fused temperature data onto the preset number of temperature grids using a preset interpolation algorithm to obtain the reconstructed temperature field corresponding to the preset radiation area; and determine the condensation risk level of the preset radiation area based on the reconstructed temperature field.

[0008] In some embodiments, the reconstruction unit may be specifically used to obtain the target dew point temperature value corresponding to the preset radiation area, the target dew point temperature value indicating the critical temperature value at which condensation occurs in the preset radiation area; calculate the difference between the temperature value corresponding to each temperature grid in the reconstructed temperature field and the target dew point temperature value respectively to obtain the condensation margin corresponding to each temperature grid; and determine the condensation risk level of the preset radiation area based on the condensation margin corresponding to each temperature grid.

[0009] In some embodiments, the determining unit may be specifically used to determine the target prediction model as a disturbance prediction model when the type of the preset control event is a disturbance control event, wherein the disturbance prediction model uses temperature change trend prediction as the prediction target; when the type of the preset control event is a condensation risk control event, the target prediction model is a condensation risk prediction model, wherein the condensation risk prediction model uses condensation margin change trend prediction as the prediction target; and when the type of the preset control event is an optimization control event, the target prediction model is an optimization prediction model, wherein the optimization prediction model uses energy efficiency prediction as the prediction target.

[0010] In some embodiments, the prediction unit may specifically be used to determine the rate of temperature change during the disturbance control event based on the temperature change data of the preset radiation area during a historical period; take the reconstructed temperature field at the current moment as the initial value of the temperature distribution and the condensation risk level at the current moment as a constraint; use the disturbance prediction model to predict the temperature change trend within a preset period based on the rate of temperature change, the initial value of the temperature distribution, and the constraint, and obtain the predicted temperature distribution value at each prediction moment within the preset period; determine the compensation control value at each prediction moment within the preset period based on the deviation between the predicted temperature distribution value at each prediction moment within the preset period and the target temperature value corresponding to the preset radiation area; and use the disturbance prediction model to generate a set of target control parameters for the preset radiation area based on the compensation control value.

[0011] In some embodiments, the prediction unit may specifically be used to select a target condensation margin from the condensation margins corresponding to at least one temperature grid in the reconstructed temperature field; using the condensation risk prediction model, based on the target condensation margin, condensation risk level, and reconstructed temperature field, predict the condensation margin change trend within a preset time period to obtain the predicted condensation margin value at each prediction time within the preset time period; determine the compensation control value at each prediction time within the preset time period based on the comparison result between the predicted condensation margin value and the margin threshold at each prediction time within the preset time period; and use the condensation risk prediction model to generate a target control parameter set for the preset radiation area based on the compensation control value.

[0012] In some embodiments, the prediction unit may specifically be used to determine the load change trend and energy consumption change trend of the preset radiation area within a preset time period based on historical control data of the preset radiation area; using the optimized prediction model, based on the load change trend, the energy consumption change trend, the condensation risk level, and the reconstructed temperature field, to perform energy efficiency optimization within the preset time period, obtaining the energy efficiency prediction value at each prediction time within the preset time period; determining the compensation control value at each prediction time within the preset time period based on the energy efficiency prediction value at each prediction time within the preset time period; and using the optimized prediction model, generating a target control parameter set for the preset radiation area based on the compensation control value.

[0013] In some embodiments, the control unit can be specifically used to: extract water supply temperature envelope data from local storage when a network connection interruption is detected between the edge gateway corresponding to the preset radiation area and the cloud server; correct the target control parameter set based on the water supply temperature envelope data; and control the radiant air conditioning system corresponding to the preset radiation area based on the corrected target control parameter set; when a network connection between the edge gateway and the cloud server is detected to be restored, send the valve position status and cumulative operating data during the network outage to the cloud server; and receive feedback information returned by the cloud server, so as to correct the target control parameter set based on the feedback information and control the radiant air conditioning system corresponding to the preset radiation area based on the corrected target control parameter set.

[0014] In some embodiments, the control unit may specifically be used to obtain the state feedback value of the actuator in the building radiant air conditioning system corresponding to the preset radiation area; calculate the residual between the state feedback value and the corresponding command value in the target control parameter set; when the residual exceeds a preset residual threshold in multiple consecutive control cycles, mark the preset radiation area as a hydraulic imbalance state and determine the compensation coefficient corresponding to the preset radiation area; use the compensation coefficient to correct the target control parameter set, and control the radiant air conditioning system corresponding to the preset radiation area based on the corrected target control parameter set.

[0015] In some embodiments, the control unit may be specifically used to execute an anti-condensation control strategy when the condensation risk level is higher than or equal to a preset risk level; the execution of the anti-condensation control strategy includes: reducing or closing the cold water supply valve of the preset radiation area to reduce the flow rate of cold water entering the preset radiation area, so as to allow the surface temperature of the radiant panel in the preset radiation area to rise; and / or, turning on or increasing the fresh air dehumidification of the preset radiation area to reduce the indoor dew point temperature of the preset radiation area; and / or, adjusting the mixing ratio of return air and fresh air in the preset radiation area to reduce the dew point temperature of the adhesive layer in the preset radiation area.

[0016] Furthermore, this application also provides an electronic device, including a processor and a memory, wherein the memory stores an application program, and the processor is used to run the application program in the memory to execute the IoT-based building radiant air conditioning system control method provided in this application.

[0017] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to execute steps in any of the IoT-based building radiant air conditioning system control methods provided in embodiments of this application.

[0018] Furthermore, this application also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the steps in the IoT-based building radiant air conditioning system control method provided in this application.

[0019] This embodiment of the application, after acquiring at least one panel surface temperature data and auxiliary temperature data within a preset radiation area, can reconstruct the temperature field of the preset radiation area based on the at least one panel surface temperature data and auxiliary temperature data. The condensation risk level of the preset radiation area is then determined based on the reconstructed temperature field. When the condensation risk level is lower than the preset risk level, in response to the triggering of a preset control event, a target prediction model is determined based on the type of the preset control event. Using the target prediction model, a set of target control parameters for the preset radiation area is predicted based on the condensation risk level and the reconstructed temperature field. The radiant air conditioning system corresponding to the preset radiation area is then controlled based on the set of target control parameters. Since this scheme can reconstruct the temperature field corresponding to the preset radiation area based on at least one panel surface temperature data and auxiliary temperature data, it comprehensively reflects the temperature distribution at various locations on the surface of the radiant panel, avoiding reliance on single-point temperature or average temperature for condensation prevention judgment. Furthermore, the condensation risk level is determined based on the difference between the temperature value and the dew point temperature value at each location in the reconstructed temperature field. When the condensation risk level is lower than the preset risk level, control parameters are predicted in response to the triggering of the preset control event. The radiant air conditioning system is then controlled based on the predicted set of target control parameters. Therefore, it can improve the accuracy and safety of condensation prevention judgment in radiant air conditioning systems. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments 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.

[0021] Figure 1 This is a schematic diagram of a scenario for the control method of a building radiant air conditioning system based on the Internet of Things provided in the embodiments of this application; Figure 2 This is a schematic flowchart of the control method for a building radiant air conditioning system based on the Internet of Things provided in the embodiments of this application; Figure 3 This is a schematic diagram of the specific process of step 102 of the IoT-based building radiant air conditioning system control method provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the IoT-based building radiant air conditioning system control system provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] This application provides a method and related equipment for controlling a building radiant air conditioning system based on the Internet of Things (IoT). The related equipment may include an IoT-based building radiant air conditioning system control system, electronic equipment, computer program products, and computer-readable storage media. The IoT-based building radiant air conditioning system control system can be integrated into the electronic equipment, which may be a server or a terminal, etc.

[0024] The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0025] For example, see Figure 1 Taking the integration of an IoT-based building radiant air conditioning system control system into an electronic device as an example, the electronic device can acquire at least one panel temperature data and auxiliary temperature data within a preset radiation area. Based on the at least one panel temperature data and auxiliary temperature data, the temperature field of the preset radiation area is reconstructed, and the condensation risk level of the preset radiation area is determined according to the reconstructed temperature field. When the condensation risk level is lower than the preset risk level, in response to the triggering of a preset control event, a target prediction model is determined based on the type of the preset control event. Using the target prediction model, the target control parameter set of the preset radiation area is predicted based on the condensation risk level and the reconstructed temperature field. The radiant air conditioning system corresponding to the preset radiation area is controlled based on the target control parameter set.

[0026] It is understood that, in the specific embodiments of this application, the object's surface temperature data, auxiliary temperature data and other related data are involved. When the following embodiments of this application are applied to specific products or technologies, permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0027] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0028] This embodiment will be described from the perspective of an IoT-based building radiant air conditioning system control system. Specifically, the IoT-based building radiant air conditioning system control system can be integrated into an electronic device, which can be a server or a terminal, etc. The terminal can include tablet computers, laptops, personal computers (PCs), wearable devices, virtual reality devices, or other smart devices that can perform IoT-based building radiant air conditioning system control.

[0029] like Figure 2 As shown, Figure 2 This is a schematic diagram of an optional process for controlling a building radiant air conditioning system based on the Internet of Things (IoT) provided in this embodiment. This IoT-based control method can be executed by a server or a terminal alone, or it can be executed by a terminal in conjunction with a server. The specific process of this IoT-based control method is as follows: 101. Obtain at least one plate surface temperature data and auxiliary temperature data within the preset radiation area.

[0030] The IoT-based building radiant air conditioning system control method of this application embodiment can be applied to the edge gateway in the control system. The control system may include multiple edge gateways, a cloud server, and a building radiant air conditioning system. The edge gateways are communicatively connected to both the cloud server and the building radiant air conditioning system.

[0031] Specifically, the control system architecture can adopt a distributed architecture of cloud and multiple edge gateways. In this architecture, the cloud server can be deployed in a remote data center or public cloud platform, responsible for cross-building model aggregation, slow variable tuning (such as the generation and distribution of the next day's water supply temperature envelope), OTA model (Over-The-Air) distribution, and device shadow management; the edge gateways can be deployed in the building's floor electrical rooms or heat exchange stations. Each edge gateway communicates with the cloud server via wired or wireless networks, and simultaneously communicates with sensors and actuators in its area via fieldbus (such as Modbus, BACnet, KNX) or wireless protocols (such as Zigbee, LoRa, Wi-Fi). A building can include at least one edge gateway, the specific number of which depends on the building's size, number of floors, and number of devices. For multi-story buildings, one edge gateway is typically deployed per floor or every 2-3 floors; for single-story large-space buildings (such as shopping malls and stadiums), multiple edge gateways can be deployed by area; for small buildings, only one edge gateway can be deployed for the entire building. Each edge gateway manages at least one preset radiation area.

[0032] A pre-defined radiant zone can be understood as the smallest independent control unit within a building where a radiant air conditioning system is deployed. This is a spatial area with its own water supply line, independent valve control, and independent sensor configuration, capable of independently regulating cooling / heating. Pre-defined radiant zones can include, but are not limited to: a single room (such as an office, meeting room, or executive office); a localized area within a large space (such as east, west, south, or north zones defined by orientation, or open office areas, reception areas, or rest areas defined by function); or a specific functional area (such as an archive or equipment room). The physical boundaries of each pre-defined radiant zone are typically related to the building's spatial division, function, or orientation. The principle for their division is that areas within the same zone have similar heat load characteristics, similar usage times, and can be independently controlled through the same water supply branch. Each pre-defined radiant zone is equipped with an independent sensor group (including panel temperature sensors, temperature and humidity sensors, and personnel sensors) and independent actuators (including mixing valves and electric heating valves). For example, taking a 6-story office building as an example, each floor has a building area of ​​about 2,000 square meters. It is divided into 4 preset radiation areas according to the four directions of east, south, west and north. The entire building contains a total of 24 preset radiation areas. Each area on each floor is independently managed by the edge gateway of the floor.

[0033] A building radiant air conditioning system can include a radiant terminal subsystem, a fresh air dehumidification subsystem, a heat source / cooling source subsystem, and a control subsystem. The radiant terminal subsystem includes radiant panels (ceiling, floor, or wall radiant panels) laid within a pre-defined radiant area, water supply pipes, and return water pipes. Cooling / heating coils are embedded within the radiant panels, allowing chilled or hot water to flow through the coils and exchange heat with the indoor environment via the radiant panel surface. The fresh air dehumidification subsystem includes a fresh air unit, a dehumidification section, and supply air ducts, designed to independently handle the indoor humidity load and prevent condensation on the radiant panel surface. The heat source / cooling source subsystem includes heat pump units, chillers, or boilers, providing chilled or hot water to the radiant terminals. The control subsystem includes sensor arrays, edge gateways, actuators, and a cloud platform.

[0034] The building radiant air conditioning system may also include field devices, i.e., actuators, that receive control commands sent by the edge gateway and convert them into physical actions. The actuators in this application may include at least one of the following: (1) Mixing three-way valve: Installed on the water supply pipeline of each preset radiant area, used to regulate the water supply temperature entering the area. The mixing three-way valve changes the water supply temperature entering the radiant plate by adjusting the mixing ratio of cold water (from the cold source) and return water (from the return water pipe of the radiant plate). Increasing the valve opening increases the proportion of cold water and decreases the water supply temperature; decreasing the valve opening increases the proportion of return water and increases the water supply temperature. The adjustment accuracy of the mixing three-way valve is usually 1%, and its opening command is issued by the edge gateway through analog signals (such as 4-20mA or 0-10V).

[0035] (2) Zoned electric heating valve: A switch-type valve installed on the water supply branch of each preset radiation zone to control the flow of cold water in that zone. The electric heating valve has only two states: open and closed. It is controlled by the edge gateway through a switch signal and is used to cut off the cold water supply to that zone in extreme cases (such as forced shutdown of cooling after hard constraint triggering).

[0036] (3) Fresh air handling unit frequency converter: connected to the motor of the fresh air handling unit, used to adjust the air supply frequency of the fresh air handling unit, thereby changing the fresh air dehumidification and air supply volume of the preset radiation area. The frequency converter receives frequency commands (such as 0-50Hz) issued by the edge gateway. When the frequency increases, the dehumidification capacity increases and the indoor dew point temperature decreases, which helps to suppress the risk of condensation.

[0037] (4) Heat pump frequency converter: connected to the heat source unit (such as heat pump compressor), used to adjust the outlet water temperature setpoint or operating frequency of the heat source unit, thereby changing the water supply temperature level of the entire system. The edge gateway can fine-tune the heat pump outlet water temperature setpoint within a preset range (usually ±0.5℃) as a supplement to the zone valve regulation.

[0038] The panel surface temperature data can be understood as the temperature distribution information of the radiant panel surface within a preset radiation area, reflecting the temperature status at various points on the radiant panel surface. The panel surface temperature data can be obtained by collecting data from a multi-point patch temperature sensor array deployed on the radiant panel surface, with at least four sensors per panel, evenly distributed at the four corners and the center of the radiant panel surface. For example, taking the ceiling radiant panel of an office as an example, one PT100 patch temperature sensor is deployed at each of the four corners and the center of the radiant panel, for a total of five measuring points. The edge gateway collects the temperature data of each measuring point at a frequency of 5Hz, which is used as the panel surface temperature data of the radiant panel.

[0039] Auxiliary temperature data can be understood as information used to help characterize the temperature distribution within a preset radiation area. This includes temperature data at locations other than the surface temperature of the radiant panel, or the temperature of the medium itself, providing additional thermal information for temperature field reconstruction. Auxiliary temperature data may include at least one of the following: supply and return water temperature data within the preset radiation area, temperature data at cold bridge points in the building envelope, and temperature data of the inner pipe wall.

[0040] The supply and return water temperature data can be understood as the temperature values ​​of the circulating water in the supply and return water mains of the preset radiation area, which are collected by temperature sensors installed on the supply and return water mains. The difference between the supply and return water temperatures can reflect the current cooling load; the larger the temperature difference, the heavier the current load in the area.

[0041] Temperature data at cold bridge points in the building envelope can be understood as the temperature values ​​of the inner surfaces of cold bridge locations within the building envelope, collected by surface-mount temperature sensors installed at each cold bridge location. Cold bridge locations refer to areas in the building envelope where thermal resistance is significantly reduced due to differences in material thermal conductivity or structural discontinuities, such as the upper edge of window frames, the sides of beams, and the inner corners of exterior walls. Because the inner surface temperature of these locations is often lower than that of the surrounding building envelope and radiant panels under radiant cooling conditions, they are typically the preferred locations for condensation.

[0042] The inner pipe wall temperature data can be understood as the temperature value of the outer wall of the water supply or return pipe inside the preset radiation area, which is collected by the patch temperature sensor installed on the outer wall of the pipe inside the radiation plate.

[0043] 102. Based on at least one plate surface temperature data and auxiliary temperature data, reconstruct the temperature field of the preset radiation area, and determine the condensation risk level of the preset radiation area according to the reconstructed temperature field.

[0044] The reconstructed temperature field can be understood as a two-dimensional temperature dataset used to characterize the complete temperature distribution on the surface of the radiating plate within a preset radiation region. The reconstructed temperature field can include the temperature value corresponding to each temperature grid within the preset radiation region.

[0045] The condensation risk level characterizes the degree of risk of condensation occurring in a predefined radiation area. Condensation risk levels can include safe, low-risk, medium-risk, and high-risk levels.

[0046] This includes reconstructing the temperature field of a preset radiation area based on at least one plate surface temperature data and auxiliary temperature data, and determining the condensation risk level of the preset radiation area based on the reconstructed temperature field, such as... Figure 3 For details, please refer to steps S21-S24 below: S21. At least one plate surface temperature data is fused with supply and return water temperature data, building envelope cold bridge point temperature data, and inner pipe wall temperature data to obtain fused temperature data.

[0047] The fused temperature data can be understood as the temperature data obtained by integrating temperature data from different sensors according to their respective weights or priorities.

[0048] The fusion method can be as follows: Panel temperature data can be used as the main data for temperature field reconstruction; supply and return water temperature data can be used as boundary constraint data (providing the current load state boundary of the preset radiation area); cold bridge point temperature data can be used as independent constraint data (marking the location of the influence of local cold points in the building envelope on the temperature field distribution); and inner pipe wall temperature data can be used as leading prediction data (providing a reference for the trend of panel temperature changes). After labeling each of the above data according to its data type, they are combined into the fused temperature data.

[0049] It should be noted that the supply and return water temperature data, the cold bridge point temperature data of the building envelope, and the inner pipe wall temperature data are optional auxiliary temperature data; that is, one or more of them can be used in actual integration. Furthermore, in the above integration method, the plate surface temperature data is the only main data directly involved in subsequent interpolation calculations, while the supply and return water temperature data, cold bridge point temperature data, and inner pipe wall temperature data are auxiliary reference data, not directly involved in interpolation calculations, but used to help judge the rationality of the interpolation results and the temperature change trend.

[0050] S22. Based on the size of the preset radiation area, divide the preset radiation area into a preset number of temperature grids.

[0051] The preset size of the radiation region can be understood as the length and width (or area) of the radiation plate. The preset number can be understood as the number of grid divisions pre-set according to the size of the radiation plate and the required temperature field resolution, usually divided into several equal parts along both the length and width directions, so that the physical area corresponding to each temperature grid is approximately equal. The temperature grid can be understood as discretizing the surface of the radiation plate into several regular small regions, each of which serves as an independent temperature calculation unit.

[0052] Specifically, the method of dividing the preset radiation area into a preset number of temperature grids can be as follows: the radiation plate can be divided into M equal parts along its length and N equal parts along its width, forming M×N temperature grids, where M and N are both positive integers.

[0053] It should be noted that a higher number of meshes results in higher resolution of the temperature field, but also increases the computational load; conversely, a lower number of meshes results in higher computational efficiency but lower resolution. Those skilled in the art can flexibly set the values ​​of M and N according to actual accuracy requirements and / or the computing resources of the edge gateway.

[0054] S23. Using a preset interpolation algorithm, the fused temperature data is mapped onto a preset number of temperature grids to obtain the reconstructed temperature field corresponding to the preset radiation region.

[0055] The preset interpolation algorithm can be used as a numerical calculation method to extrapolate discrete sensor measurement point temperature values ​​to all temperature grids. The preset interpolation algorithm may include at least one of the following: inverse distance weighted interpolation (IDW), bilinear interpolation, kriging interpolation, or radial basis function interpolation.

[0056] The method employs a preset interpolation algorithm to map the fused temperature data onto a preset number of temperature grids, obtaining the reconstructed temperature field corresponding to a preset radiation region. Specifically, taking the inverse distance weighted interpolation method as an example, for the center point of each temperature grid, the temperature value of that grid point is calculated based on its distance from the measurement points of each temperature sensor. Assume the surface of the radiating plate has a total of... The temperature sensor measuring point, the first The locations of the measuring points are ( , The temperature value is ( =1,2,..., For the center point of any temperature grid Its temperature value The calculation formulas (1) and (2) can be as follows: in, It can characterize the center point of the temperature grid. The interpolated temperature value at that point is the temperature value of that grid point in the reconstructed temperature field. It can characterize the first The measured temperature values ​​at each temperature sensor measuring point. It can characterize the first Each temperature sensor measuring point is relative to the center point of the grid. The weighting coefficients, It can characterize the grid center point To the The Euclidean distance between the temperature sensor measuring points It can represent the power exponent and is used to control the degree to which distance affects the weight. The larger the value, the higher the weight of the nearby measurement point. It is usually taken as... =2.

[0057] It should be noted that the closer a measuring point is to the center of the grid, the greater its weight in the interpolation calculation; the farther away a measuring point is, the smaller its weight. By iterating through the center points of all temperature grids using the above formula, the temperature value of each grid point can be calculated, thus obtaining a continuous two-dimensional temperature field covering the entire surface of the radiant plate.

[0058] Among them, the supply and return water temperature data in the auxiliary temperature data are used to provide the current load state boundary of the preset radiation area. When the supply and return water temperature difference is large, it indicates that the load in the area is heavy and the overall temperature field is low. The range of interpolation results should be based on the supply and return water temperatures as the boundary reference. The cold bridge point temperature data in the auxiliary temperature data are used to mark the location of the cold bridge in the enclosure structure and its influence on the temperature field distribution. In the area near the cold bridge point, the temperature of the cold bridge point should be considered as a local correction in the interpolation calculation. The inner pipe wall temperature data is used as a leading prediction signal for the temperature change of the plate surface to help judge the temperature change trend.

[0059] S24. Determine the condensation risk level of the preset radiation area based on the reconstructed temperature field.

[0060] The method for determining the condensation risk level of a preset radiation area based on the reconstructed temperature field can be as follows: obtain the target dew point temperature value corresponding to the preset radiation area; then, calculate the difference between the temperature value corresponding to each temperature grid in the reconstructed temperature field and the target dew point temperature value to obtain the condensation margin corresponding to each temperature grid; then, determine the condensation risk level of the preset radiation area based on the condensation margin corresponding to each temperature grid.

[0061] The target dew point temperature indicates the critical temperature at which condensation occurs in a preset radiation area; that is, when the surface temperature of the radiation panel is below this value, condensation may occur on the surface. The condensation margin characterizes the remaining safe space between the current temperature value at the corresponding temperature grid location and the critical condensation condition. A larger condensation margin value indicates a safer location, while a smaller condensation margin value (closer to zero or negative) indicates that the location is closer to or has already reached the condensation condition.

[0062] The method for obtaining the target dew point temperature value corresponding to the preset radiation area can specifically include: collecting the air temperature and relative humidity of each node by deploying multiple temperature and humidity nodes within the preset radiation area; calculating the dew point temperature value corresponding to each node based on the air temperature and relative humidity of each node; and taking the highest dew point temperature value among all nodes as the target dew point temperature value of the preset radiation area. For example, the temperature and humidity nodes can be SHT35 temperature and humidity sensors (accuracy ±1.5%RH), with one set deployed every 15m², and the edge gateway collecting the air temperature and relative humidity data of each node at a frequency of 1Hz.

[0063] Optionally, in some embodiments, after obtaining the target dew point temperature value, the difference between the temperature value corresponding to each temperature grid in the reconstructed temperature field and the target dew point temperature value can be calculated to obtain the condensation margin corresponding to each temperature grid. The specific calculation method may include: for any temperature grid in the reconstructed temperature field, the condensation margin of the grid point can be obtained by subtracting the target dew point temperature value from the temperature value of its center point. The specific calculation formula (3) can be as follows: (Formula 3) in, It can characterize the first Line number Column temperature grid center point Condensation margin at the location. It can characterize the first Line number Column temperature grid center point The temperature value at that location (from the reconstructed temperature field). It can characterize the target dew point temperature value of the preset radiation area.

[0064] Optionally, in some embodiments, after calculating the condensation margin corresponding to each temperature grid, the condensation risk level of the preset radiation area can be determined based on the condensation margin corresponding to each temperature grid. The specific determination method may include: calculating the local condensation entropy of the preset radiation area based on the condensation margin of all temperature grids in the reconstructed temperature field (an index used to comprehensively quantify the distribution of condensation risk on the surface of the radiation plate, which simultaneously considers the size of the condensation margin of each grid point and the area weight represented by each grid point; even if only a few grid points have low condensation margins, if the area corresponding to these grid points is large, the condensation entropy will also increase significantly), so as to accurately reflect the actual severity of the condensation risk, and then determine the condensation risk level of the preset radiation area based on the local condensation entropy of the preset radiation area. The specific calculation formula (4) can be as follows: in, It can characterize the local condensation entropy and be used to quantify the degree of condensation risk distribution on the surface of the radiation plate in a preset radiation area. It can characterize the first Line number The area weighting coefficient of the temperature grid is positively correlated with the proportion of the physical area represented by the temperature grid to the total area of ​​the radiant plate. The larger the area of ​​the grid, the higher the weight. The sum of the weighting coefficients of all grids is 1. It can characterize the sigmoid activation function. It can characterize the steepness coefficient. It can characterize the first Line number Column temperature grid center point Condensation margin at the location. This can represent a condensation margin threshold, used to determine whether a grid point is in a safe state. A grid point is considered safe when its condensation margin is greater than this value, and considered to have a condensation risk when its condensation margin is less than this value. For example, The value can be 1.5℃.

[0065] For each temperature grid, the difference between its condensation margin and margin threshold is first calculated. This difference is then nonlinearly transformed using a sigmoid activation function and a steepness coefficient, and its logarithm is taken. This logarithm is then multiplied by the area weight coefficient of that grid. Finally, the results for all grids are negative and summed. When the condensation margin of a grid is much lower than the margin threshold, the σ value approaches 0, becomes negative after taking the logarithm, and becomes positive and relatively large after taking the negative, indicating that the grid contributes a high risk. When the condensation margin of all grids is much higher than the margin threshold, the σ value of each grid approaches 1, the Σ term approaches 0, and E_cond approaches 0, indicating extremely low risk. The larger the value of the local condensation entropy E_cond, the higher the condensation risk on the surface of the radiant plate.

[0066] Secondly, based on the value of the local condensation entropy E_cond, the condensation risk level of the preset radiation area is determined, for example: If E_cond is greater than the first preset entropy threshold (e.g., 0.5), the condensation risk level of the preset radiation area is determined to be high risk (i.e., condensation warning state), and the edge gateway immediately executes the anti-condensation control strategy. If E_cond is between the second preset entropy threshold (e.g., 0.2) and the first preset entropy threshold (0.5), then the condensation risk level is determined to be medium risk. If E_cond is between the third preset entropy threshold (e.g., 0.1) and the second preset entropy threshold (0.2), then the condensation risk level is determined to be low risk. If E_cond is less than or equal to the third preset entropy threshold (e.g., 0.1), the condensation risk level is determined to be safe.

[0067] In addition, it is necessary to determine individually whether the temperature of each cold bridge point is lower than the sum of the target dew point temperature and the safety threshold (e.g., 1.0℃): if any cold bridge point meets this condition, the condensation risk level is directly determined to be high risk level, and the anti-condensation control strategy is enforced, without relying on the judgment result of the above-mentioned local condensation entropy.

[0068] 103. When the condensation risk level is lower than the preset risk level, in response to the triggering of the preset control event, the target prediction model is determined based on the type of the preset control event.

[0069] The preset risk level can be understood as a risk level threshold used to determine whether a preset radiation area needs to enter the conventional control mode. In this application, the preset risk level can be a high-risk level, meaning that when the condensation risk level is lower than the high-risk level, the control system can operate according to the conventional control logic; when the condensation risk level is higher than or equal to the high-risk level, the control system needs to implement an anti-condensation control strategy.

[0070] Among them, preset control events can be understood as external disturbance signals or internal state change signals that trigger the edge gateway to perform control quantity calculations. The types of preset control events can be understood as classifications of preset control events according to their physical causes and control objectives, which can include disturbance control events, condensation risk control events, and optimization control events.

[0071] The target prediction model can be understood as a mathematical model selected by the edge gateway based on the type of currently triggered event, used to predict future state changes in a preset radiation area and generate a set of control parameters. The target prediction model can include a disturbance prediction model, a condensation risk prediction model, and an optimization prediction model.

[0072] Specifically, the method of determining the target prediction model based on the type of the preset control event in response to the triggering of the preset control event may include: (1) When the type of the preset control event is a disturbance control event, the target prediction model is determined to be the disturbance prediction model.

[0073] Among them, the disturbance prediction model can be used to predict the temperature change trend when external disturbances (such as people entering and exiting, or doors and windows opening and closing) occur. The disturbance prediction model takes the prediction of temperature change trend as its prediction target. That is, the core output of the model is the predicted temperature distribution value at each time within a preset period in the future, so as to quickly respond to the impact of disturbances on the indoor thermal environment.

[0074] It should be noted that disturbance control events can include, but are not limited to, external disturbances that can cause sudden changes in the indoor thermal environment, such as: doors and windows in the preset radiation zone changing from closed to open, or the number of people occupying the preset radiation zone changing from zero to non-zero or undergoing a preset magnitude change. The characteristic of disturbance control events is that the indoor heat load changes abruptly after the event occurs, and the system needs to respond quickly to bring the temperature back to the set value. Therefore, the prediction target of the disturbance prediction model is the temperature change trend, that is, determining the required compensation control amount by predicting future temperature trends.

[0075] (2) When the type of the preset control event is the condensation risk control event, the target prediction model is determined to be the condensation risk prediction model.

[0076] Among them, the condensation risk prediction model can be used to predict the evolution trend of condensation risk when the condensation margin is rapidly declining. The condensation risk prediction model takes the prediction of the condensation margin change trend as the prediction objective. That is, the core output of the model is the predicted value of the condensation margin at each time within a preset period in the future, with safety as the highest priority objective.

[0077] It should be noted that condensation risk control events may include, but are not limited to, events that indicate a rapid increase in condensation risk, such as the rate of decrease of the minimum condensation margin in a preset radiation area within a preset time window (e.g., 60 seconds) exceeding a preset rate threshold (e.g., 0.3℃ / min). The characteristic of condensation risk control events is that the condensation margin is rapidly narrowing, and the system needs to prioritize safety to prevent condensation from occurring. Therefore, the prediction objective of the condensation risk prediction model is the trend of condensation margin change; that is, by predicting the future change of the condensation margin at the most dangerous grid point, the required compensation control amount is determined to ensure that the condensation margin does not fall below the safety threshold.

[0078] (3) When the type of the preset control event is the optimization control event, the target prediction model is determined to be the optimization prediction model.

[0079] The optimized prediction model can be understood as a model used to predict comprehensive energy efficiency when cloud data is updated or system status changes. The optimized prediction model takes energy efficiency prediction as its prediction objective. That is, the core output of the model is the comprehensive energy efficiency prediction value at each time within a preset future period, with energy saving as the optimization objective.

[0080] It should be noted that optimization and control events can include, but are not limited to, events that trigger global system optimization, such as the arrival of the next day's water supply temperature envelope data from the cloud or changes in the hash value of the OTA model file. The characteristic of optimization and control events is that the system obtains new global information (such as next day's weather forecast or an updated load forecasting model), requiring a redesign of the control strategy to improve energy efficiency. Therefore, the prediction objective of the optimization forecasting model is comprehensive energy efficiency, that is, to determine the optimal combination of control parameters for energy efficiency within a preset future time period through optimization.

[0081] Optionally, in some embodiments, when the condensation risk level is higher than or equal to a preset risk level, an anti-condensation control strategy is implemented. The anti-condensation control strategy includes: reducing or closing the cold water supply valve of the preset radiation area to decrease the flow rate of cold water entering the preset radiation area, so that the surface temperature of the radiant panel in the preset radiation area rises; and / or, turning on or increasing the fresh air dehumidification of the preset radiation area to lower the indoor dew point temperature of the preset radiation area; and / or, adjusting the mixing ratio of return air and fresh air in the preset radiation area to lower the dew point temperature of the adhesive layer in the preset radiation area.

[0082] Understandably, the core objective of anti-condensation control strategies is to rapidly eliminate condensation risk through physical means when the condensation risk level reaches or exceeds the high-risk level, ensuring that the surface temperature of the radiant panel is higher than the dew point temperature. The three anti-condensation control strategies mentioned above have different priorities: adjusting the cold water valve is the most direct and fastest way to raise the panel temperature, suitable for scenarios where the condensation risk increases dramatically; fresh air dehumidification and adjusting the mixing ratio of return air and fresh air are mainly aimed at situations where the indoor dew point temperature is too high, suitable for scenarios where the indoor moisture load suddenly increases; in practical applications, a single strategy can be selected based on the specific degree of condensation risk, or multiple strategies can be executed simultaneously to enhance the anti-condensation effect. For example, when the condensation risk level has just reached the preset risk level (e.g., high-risk level), only the strategy of reducing the cold water supply valve can be implemented; when the condensation risk level is much higher than the preset risk level, both the strategy of reducing the cold water supply valve and the strategy of starting fresh air dehumidification can be implemented simultaneously. Furthermore, if the condensation risk level remains higher than the preset risk level, one or more combinations of the above anti-condensation control strategies can be executed cyclically at preset time intervals until the condensation risk level falls below the preset risk level. It should be noted that the execution priority and combination of the above-mentioned anti-condensation control strategies can be adjusted and configured according to factors such as the equipment configuration of the preset radiation area and the specific value of the condensation risk level. This application embodiment does not limit this.

[0083] 104. Using a target prediction model, a set of target control parameters for the preset radiation area is obtained based on the condensation risk level and the reconstructed temperature field prediction.

[0084] The target control parameter set can be used to instruct the edge gateway to issue specific control commands to the actuators, so that the actuators in the radiant air conditioning system corresponding to the preset radiation area can perform physical actions according to the predicted control parameters. The target control parameter set can include at least one of the following: mixing valve opening command, fresh air frequency adjustment command, and supply water temperature set correction value. For example, taking the ceiling radiant panel of an office as an example, the target control parameter set can include two control commands: "mixing valve opening 47%" and "fresh air frequency 35Hz".

[0085] Among them, there are several ways to use a target prediction model to obtain the set of target control parameters for a preset radiation area based on the condensation risk level and the reconstructed temperature field prediction. These methods can be as follows: (1) When the target prediction model is a disturbance prediction model, the temperature change rate during the disturbance control event can be determined based on the temperature change data of the disturbance control event in the preset radiation area during the historical period. Then, the reconstructed temperature field at the current moment is used as the initial value of the temperature distribution, and the condensation risk level at the current moment is used as the constraint condition. Then, the disturbance prediction model is used to predict the temperature change trend in the preset period based on the temperature change rate, the initial value of the temperature distribution and the constraint condition, and the predicted value of the temperature distribution at each prediction moment in the preset period is obtained. Then, based on the deviation between the predicted value of the temperature distribution at each prediction moment in the preset period and the target temperature value corresponding to the preset radiation area, the compensation control value at each prediction moment in the preset period is determined. Then, the disturbance prediction model is used to generate the target control parameter set of the preset radiation area based on the compensation control value.

[0086] The historical disturbance control events can be understood as records of historical events of the same type as the current disturbance control event that occurred in the preset radiation area over a past period. For example, if the current event is a personnel entry event, then the historical disturbance control events are similar personnel entry events that occurred in the past. Temperature change data can be understood as a historical data sequence of temperature changes over time at various measuring points on the surface of the radiant panel, recorded by the edge gateway during the occurrence of historical disturbance control events. The rate of temperature change can be understood as the amount of change in the surface temperature of the radiant panel per unit time during the disturbance control event, used to characterize the intensity of the impact of the current disturbance on the indoor thermal environment.

[0087] The initial temperature distribution can be understood as the reconstructed temperature field at the current moment, i.e., the temperature distribution of each temperature grid on the surface of the radiant plate at the current moment, serving as the starting state for the prediction model calculation. The constraints can be understood as the safety restrictions imposed on the prediction results of the perturbation prediction model, i.e., the condensation risk level at the current moment determines the upper limit of the adjustment range of each control parameter during the prediction process; the higher the risk level, the smaller the allowable adjustment range.

[0088] The preset time period can be understood as the length of time the perturbation prediction model makes predictions, i.e., a prediction time window extending into the future from the current moment (e.g., 6 prediction moments, each 10 minutes apart). The temperature change trend can be understood as the direction of the surface temperature of the radiant plate over time within the preset time period, such as a continuous decrease, a continuous increase, or a tendency to stabilize. The prediction moment can be understood as each discretized time point within the preset time period, and the interval between two adjacent prediction moments can be the same (e.g., 10-minute intervals). The predicted temperature distribution value can be understood as the set of predicted temperature values ​​for each temperature grid in the reconstructed temperature field at a certain prediction moment.

[0089] The target temperature value can be understood as the desired indoor temperature setting for the preset radiation area, which is usually set by the user through a temperature control panel or mobile terminal (e.g., 25℃ in summer). The compensation control value can be understood as the amount of control that needs to be applied to make the predicted temperature distribution value approach the target temperature value. For example, to eliminate the 3℃ deviation between the current temperature and the target temperature, the opening of the mixing valve needs to be increased by a certain percentage.

[0090] Specifically, the method of determining the temperature change rate during a disturbance control event based on temperature change data of a preset radiation area during a historical period may include: extracting temperature change data of the preset radiation area when similar disturbance control events occur during a historical period from the local storage of the edge gateway; performing statistical processing on the extracted temperature change data; and calculating the average temperature change rate within a preset time window after the event occurs as the current temperature change rate.

[0091] Optionally, in some embodiments, after determining the temperature change rate during the disturbance control event, the reconstructed temperature field at the current moment can be used as the initial value of the temperature distribution, and the condensation risk level at the current moment can be used as a constraint. A disturbance prediction model is then used to predict the temperature change trend within a preset time period based on the temperature change rate, the initial value of the temperature distribution, and the constraint, thus obtaining the predicted temperature distribution value for each prediction moment within the preset time period. Specifically, the prediction method may include: the disturbance prediction model starts with the initial temperature distribution value at the current moment, uses the temperature change rate as the driving force for state transition, and recursively calculates the change in the surface temperature of the radiant plate moment by moment within the preset time period. During the recursion, the condensation risk level at the current moment serves as a constraint to limit the prediction results. When the condensation risk level is high, the predicted temperature change amplitude will be suppressed to prevent over-regulation from further increasing the condensation risk. That is, for each prediction moment within the preset time period, the model calculates the temperature value of each temperature grid at that moment based on the temperature distribution, temperature change rate, and constraint boundary corresponding to the condensation risk level of the previous moment. By recursively calculating moment by moment, the predicted temperature distribution value for each prediction moment within the preset time period can be obtained.

[0092] For example, the disturbance prediction model can specifically be a lightweight model predictive control (MPC) model, and its objective function can be calculated as shown in formula (5): Formula (5) in, It can characterize the objective function value and is used to evaluate the overall performance of a control sequence. The smaller the value, the better the control effect. It can represent the number of time steps in the prediction time domain, that is, the number of time steps the model uses to predict the future. It can represent the step number in the prediction time domain. =1,2,...,H. It can represent the current moment. It can characterize the first The expected indoor temperature value at each predicted time. It can characterize the target temperature setting value corresponding to the preset radiation area. This can characterize the condensation penalty weight, which is used to control the importance of condensation risk in the objective function. A higher value indicates that the system prioritizes preventing condensation. It increases with the number of people occupying the space. It can characterize the margin threshold (e.g., 1.5℃). It can represent the minimum condensation margin in all temperature grids at the current moment. It can characterize the penalty coefficient for changes in control quantity, and is used to suppress drastic changes in control quantity between adjacent control cycles, thereby avoiding frequent actuator actions. It can characterize control quantities, including mixing valve opening, fresh air frequency, and water supply temperature setting correction values. It can characterize the first The change in control quantity at each prediction time is the difference between the control quantity at the current time and the control quantity at the previous time.

[0093] Understandably, the objective function consists of three terms: the first term is a temperature deviation penalty term, which penalizes situations where the indoor temperature deviates from the target temperature; the larger the deviation, the larger the value of this term. The second term is a condensation penalty term, which penalizes situations where the condensation margin is lower than the margin threshold; when the minimum condensation margin is lower than the margin threshold, this term produces a positive value, and the larger the deviation from the threshold, the larger the penalty value. The third term is a control quantity change penalty term, which penalizes large fluctuations in the control quantity between adjacent control cycles; the larger the value of this term, the more drastic the change in the control quantity, which will lead to frequent actuator operation, increasing energy consumption and equipment wear.

[0094] The optimization objective of the disturbance prediction model is to solve for the objective function while satisfying preset constraints (such as water supply temperature envelope constraints, condensation hard constraints, etc.). The control quantity sequence is minimized, and the control quantity at the current moment is extracted from the solved control quantity sequence as the target control parameter set for the preset radiation area. It should be noted that the above... and The specific value can be calibrated and adjusted according to actual engineering needs. The value of increases with the number of occupants, which can be understood as follows: when the number of occupants increases, the indoor heat load increases, and the system needs stronger cooling capacity. However, stronger cooling capacity may bring a higher risk of condensation. Therefore, it is necessary to increase the condensation penalty weight to balance comfort and safety. For example, The value can be 50 (baseline value). It can take the value 0.1.

[0095] Optionally, in some embodiments, after obtaining the predicted temperature distribution value at each predicted moment within a preset time period, the compensation control value for each predicted moment within the preset time period can be determined based on the deviation between the predicted temperature distribution value at each predicted moment and the target temperature value corresponding to the preset radiation area. Specifically, the determination method may include: taking the average or weighted average of the predicted temperature distribution values ​​at each predicted moment to obtain the expected indoor temperature at that predicted moment; calculating the difference between the expected indoor temperature and the target temperature value; and determining the compensation control amount required to pull the expected temperature at that predicted moment back to the target temperature based on the magnitude and direction of the difference.

[0096] Optionally, in some embodiments, after determining the compensation control value at each predicted moment within a preset time period, a disturbance prediction model can be used to generate a target control parameter set for a preset radiation area based on the compensation control value. Specifically, this generation can include: converting the compensation control value at each predicted moment within the preset time period into a corresponding mixing valve opening command according to a preset mapping relationship (such as a linear mapping or PID mapping between temperature deviation and valve opening); using the mixing valve opening command corresponding to the current moment as the mixing valve opening command in the target control parameter set, and outputting it to the actuator for execution. If the compensation control value is less than a preset dead zone threshold (e.g., the valve opening change is less than 1.5%), the current valve position is maintained and no update command is sent.

[0097] (2) When the target prediction model is the condensation risk prediction model, the target condensation margin can be selected from the condensation margin corresponding to at least one temperature grid in the reconstructed temperature field. Then, the condensation risk prediction model is used to predict the condensation margin change trend in the preset time period based on the target condensation margin, condensation risk level, and reconstructed temperature field, so as to obtain the condensation margin prediction value at each prediction time in the preset time period. Then, based on the comparison result between the condensation margin prediction value at each prediction time in the preset time period and the margin threshold, the compensation control value at each prediction time in the preset time period is determined. Then, the condensation risk prediction model is used to generate the target control parameter set of the preset radiation area based on the compensation control value.

[0098] The target condensation margin can be understood as the key condensation margin value selected from the condensation margins corresponding to all temperature grids in the reconstructed temperature field, used for tracking by the condensation risk prediction model. This value is usually the minimum among all condensation margins, corresponding to the location on the radiant panel surface closest to the danger of condensation. The condensation margin change trend can be understood as the evolution of the condensation margin value at each prediction time within a preset period, such as a continuous decrease (indicating an increased condensation risk), a continuous increase (indicating a reduced condensation risk), or a tendency to stabilize. The predicted condensation margin value can be understood as the estimated condensation margin value at the target location on the radiant panel surface (i.e., the grid point corresponding to the target condensation margin) calculated by the condensation risk prediction model at a certain prediction time. The margin threshold can be understood as a preset safety boundary value used to determine whether the condensation risk is acceptable. When the predicted condensation margin value is lower than this threshold, it indicates that there is a condensation risk at that prediction time.

[0099] The method of selecting the target dew point from the dew point margins corresponding to at least one temperature grid in the reconstructed temperature field can specifically include: calculating the dew point margin corresponding to each temperature grid in the reconstructed temperature field (i.e., the difference between the temperature value of the grid point and the target dew point temperature value); finding the dew point margin with the smallest value among all grid points, taking the temperature grid point corresponding to the smallest dew point margin as the most dangerous grid point on the surface of the radiant plate, and taking the smallest dew point margin as the target dew point margin.

[0100] Optionally, in some embodiments, after the target condensation margin is obtained, a condensation risk prediction model can be used to predict the condensation margin change trend within a preset time period based on the target condensation margin, condensation risk level, and reconstructed temperature field, so as to obtain the predicted condensation margin value at each prediction time within the preset time period. Specifically, the prediction method may include: the condensation risk prediction model takes the temperature grid point corresponding to the target condensation margin as the tracking object, uses the current condensation margin value of the temperature grid point as the prediction starting point, and uses the condensation risk level at the current time as the constraint boundary, and extrapolates the change trajectory of the condensation margin of the temperature grid point moment by moment within the preset time period. During the moment-by-moment extrapolation process, the condensation risk prediction model calculates the predicted condensation margin value of the temperature grid point at the next moment based on the current condensation margin value of the temperature grid point, the temperature gradient information of the area near the temperature grid point, and the historical condensation margin change rate of the temperature grid point.

[0101] For example, for the temperature grid point corresponding to the target condensation margin, the condensation margin at the next prediction time can be calculated using the condensation risk prediction model by the following formula (6): Formula (6) in, It can characterize the condensation margin at the next predicted time. It can characterize the condensation margin value of the target grid point at the current moment (i.e., the minimum condensation margin among all grid points). It can characterize the rate of change of the condensation allowance of the target grid point at the current moment. It is determined based on the historical condensation allowance change data of the grid point, and the unit is ℃ / min. It can characterize the prediction time step, that is, the time interval between two adjacent prediction times. This can represent the condensation risk adjustment coefficient, which is positively correlated with the current condensation risk level. The higher the condensation risk level, the higher the condensation risk level. The higher the value, the more the system tends to actively increase the plate temperature to suppress condensation.

[0102] It is understandable that in the calculation formula (6), the predicted value of the condensation margin of the target grid point at the next prediction time is composed of three parts superimposed. The first part is the current condensation margin value, which serves as the starting benchmark for prediction. The second part is the change amount extrapolated based on the historical rate of change, reflecting the magnitude of the change in condensation margin as the current trend continues. The third part is an active adjustment term based on the current condensation risk level. When the condensation risk increases, this term is positive and increases, causing the predicted condensation margin to tend to rise, thereby triggering the system to take anti-condensation measures in advance. By recursively applying the calculation formula (6) time by time, the predicted value of the condensation margin of the temperature grid point at each prediction time within the preset time period can be obtained, and thus the predicted value of the condensation margin at each prediction time within the preset time period can be obtained.

[0103] Optionally, in some embodiments, after obtaining the predicted condensation margin value for each predicted moment within a preset time period, the compensation control value for each predicted moment within the preset time period can be determined based on the comparison between the predicted condensation margin value and the margin threshold. Specifically, the determination method may include: for each predicted moment, comparing the predicted condensation margin value for that moment with the margin threshold; if the predicted condensation margin value is lower than the margin threshold, a positive compensation control value is determined based on the difference between the predicted condensation margin value and the margin threshold (indicating a need to reduce cooling capacity to increase panel temperature); if the predicted condensation margin value is higher than the margin threshold and the difference is large (i.e., sufficient safety margin), no compensation control value may be applied or a negative compensation control value may be applied (indicating that cooling capacity can be appropriately increased); if the predicted condensation margin value is equal to or slightly higher than the margin threshold, the compensation control value may be zero or the current adjustment range may remain unchanged.

[0104] Optionally, in some embodiments, after obtaining the compensation control value for each predicted moment within a preset time period, a condensation risk prediction model can be used to generate a target control parameter set for a preset radiation area based on the compensation control value. Specifically, this generation can include: converting the compensation control value for each predicted moment within the preset time period into corresponding control commands according to a preset mapping relationship (such as the mapping relationship between condensation margin deviation and valve opening), including mixing valve opening commands and / or fresh air frequency adjustment commands; selecting the command corresponding to the current moment from the converted control commands as the target control parameter set, and outputting it to the actuator for execution. For example, when the predicted condensation margin value is lower than the margin threshold, this mapping relationship can convert the condensation margin deviation into a mixing valve closing amount; the larger the deviation, the greater the valve closing amount, allowing the surface temperature of the radiant panel to rise back to a safe range as quickly as possible.

[0105] (3) When the target prediction model is the optimized prediction model, the load change trend and energy consumption change trend of the preset radiation area are determined according to the historical control data of the preset radiation area within the preset time period. Then, the optimized prediction model is used to optimize energy efficiency within the preset time period based on the load change trend, energy consumption change trend, condensation risk level and reconstructed temperature field, and obtain the energy efficiency prediction value at each prediction time within the preset time period. Then, the compensation control value at each prediction time within the preset time period is determined according to the energy efficiency prediction value at each prediction time within the preset time period. Then, the optimized prediction model is used to generate the target control parameter set of the preset radiation area based on the compensation control value.

[0106] Historical control data can be understood as the operational data of the preset radiation area recorded by the edge gateway during its historical operation. This data may include, but is not limited to: historical load data (such as supply and return water temperature difference, cooling capacity), historical energy consumption data (such as heat pump unit power consumption, fresh air unit power consumption), historical environmental data (such as indoor and outdoor temperature and humidity), and corresponding control parameters (such as valve opening degree, supply water temperature setpoint). Load change trend can be understood as the trend of cooling and heating load in the preset radiation area over a preset period. For example, a continuous increase in load indicates that the area requires more cooling capacity. Energy consumption change trend can be understood as the trend of energy consumption in the preset radiation area over a preset period. For example, a continuous increase in energy consumption indicates that the system energy efficiency may be decreasing. Predicted energy efficiency value can be understood as the comprehensive energy efficiency index value (such as system energy efficiency ratio EER or comprehensive part load performance coefficient IPLV) expected to be achieved at a certain prediction time based on the current state and candidate control strategies, used to evaluate the energy-saving effect of the control strategy.

[0107] Specifically, determining the load change trend and energy consumption change trend of the preset radiation area within a preset time period based on historical control data of the preset radiation area can include: extracting historical control data of the preset radiation area during the same historical time period (e.g., the same time period in the past 7 days) from the local storage of the edge gateway; performing statistical analysis and trend fitting on the extracted historical control data to obtain the load change curve and energy consumption change curve of the preset radiation area within the preset time period; and using the load change curve and energy consumption change curve as the load change trend and energy consumption change trend within the preset time period.

[0108] Optionally, in some embodiments, after obtaining the load change trend and energy consumption change trend, an optimized prediction model can be used. Based on the load change trend, energy consumption change trend, condensation risk level, and reconstructed temperature field, energy efficiency optimization is performed within a preset time period to obtain the predicted energy efficiency value for each prediction moment within the preset time period. The energy efficiency optimization method may specifically include: the optimized prediction model uses the load change trend and energy consumption change trend as prediction benchmarks, the condensation risk level as a safety constraint boundary, and the reconstructed temperature field as the current temperature distribution benchmark, and traverses or iteratively searches the set of candidate control parameters within the preset time period. For each set of candidate control parameters (including but not limited to candidate values ​​for mixing valve opening, fresh air frequency, and water supply temperature setting correction), the model predicts the load response and energy consumption response at each prediction moment within the preset time period under the action of these parameters, and calculates the comprehensive energy efficiency index value corresponding to each prediction moment. The model selects a set of parameters from all candidate control parameter sets that optimizes the comprehensive energy efficiency index (i.e., achieves the highest energy efficiency), and records the energy efficiency values ​​corresponding to this set of parameters at each prediction moment as the predicted energy efficiency value for each prediction moment within the preset time period.

[0109] For example, the energy efficiency optimization process of the prediction model can be implemented based on the model predictive control (MPC) framework, and its objective function can be calculated as shown in formula (7): in, Energy consumption penalty weights can be used to characterize the importance of energy consumption in the objective function. A higher value indicates that the system is more inclined to prioritize energy conservation. It can characterize the first The predicted energy consumption value at each prediction time. It can characterize the penalty coefficient for changes in control quantity, and is used to suppress drastic changes in control quantity between adjacent control cycles.

[0110] Understandably, the objective function consists of three terms: the first is a temperature deviation penalty term, used to penalize situations where the indoor temperature deviates from the target temperature; the second is an energy consumption penalty term, used to penalize situations where the predicted energy consumption value is too high, with a larger value for this term indicating higher predicted energy consumption; and the third is a control variable change penalty term, used to suppress large fluctuations in the control variable. The optimization objective of the prediction model is: under the premise of satisfying preset constraints (including safety constraints corresponding to condensation risk levels, water supply temperature envelope constraints, etc.), to solve for the objective function... The control input sequence that is minimized is the control strategy with optimal energy efficiency. It should be noted that the above... and The specific value can be calibrated and adjusted according to actual engineering needs. When the system is operating under partial load conditions, it can be appropriately increased. To strengthen the optimization orientation of prioritizing energy conservation. For example, It can take values ​​between 0.2 and 2.0. It can take values ​​between 0.05 and 0.2.

[0111] Optionally, in some embodiments, after obtaining the energy efficiency prediction value for each prediction moment within a preset time period, the compensation control value for each prediction moment within the preset time period can be determined based on the energy efficiency prediction value for each prediction moment within the preset time period. An optimized prediction model is then used to generate a target control parameter set for a preset radiation area based on the compensation control value. Specifically, the determination method may include: for each prediction moment, comparing the candidate control parameter corresponding to the optimal energy efficiency prediction value with the current actual control parameter, and calculating the difference between the two as the compensation control value for that prediction moment; then, converting the compensation control value corresponding to the current moment into a corresponding control instruction according to a preset mapping relationship, including at least one of a mixing valve opening instruction, a fresh air frequency adjustment instruction, and a water supply temperature setting correction value, and outputting the converted control instruction as the target control parameter set to the actuator for execution.

[0112] 105. Adjust the radiant air conditioning system corresponding to the preset radiation area based on the target control parameter set.

[0113] One method for regulating the radiant air conditioning system corresponding to a preset radiation area based on a set of target control parameters is as follows: For example, the edge gateway can send each control command (such as the mixing valve opening command, the fresh air frequency adjustment command, and the water supply temperature set correction value) in the set of target control parameters to the corresponding actuators (such as the mixing three-way valve, the fresh air unit frequency converter, and the heat pump frequency converter). The actuators perform corresponding physical actions (such as adjusting the valve opening, adjusting the fan frequency, and adjusting the water supply temperature set value) according to the received commands, thereby realizing the regulation of the operating status of the radiant air conditioning system in the preset radiation area.

[0114] In this application, since the control of the radiant air conditioning system involves data interaction between the cloud and the edge gateway, and network communication is unstable, it is necessary to ensure the reliable operation of the system under abnormal network conditions. Specifically, this can include the following two scenarios: (1) When the network connection between the edge gateway and the cloud server corresponding to the preset radiation area is interrupted, the water supply temperature envelope data can be extracted from the local storage, and the target control parameter set can be corrected based on the water supply temperature envelope data. The radiant air conditioning system corresponding to the preset radiation area can be controlled based on the corrected target control parameter set.

[0115] It should be noted that the water supply temperature envelope data is data received by the edge gateway from the cloud server and stored locally before the network outage. This data includes the upper and lower limits of the water supply temperature for the preset radiation area at various times within a preset future time period. During the network outage, the edge gateway no longer relies on real-time commands from the cloud server. Instead, it independently uses the latest locally stored water supply temperature envelope data as the control constraint boundary, combined with the indoor relative humidity estimated by the local Kalman filter, to continue executing local model predictive control. When the network connection is restored, the edge gateway sends a status synchronization message to the cloud server. The cloud server compares the last valve position status recorded by the edge gateway during the network outage with the expected status of the device's shadow. When the comparison deviation exceeds a preset deviation threshold, it returns a correction command to the edge gateway. The edge gateway then corrects the target control parameter set based on the correction command and continues to control the radiant air conditioning system based on the corrected target control parameter set.

[0116] (2) When the network connection between the edge gateway and the cloud server is restored, the valve position status and cumulative operating data during the network outage are sent to the cloud server, and feedback information returned by the cloud server is received. The target control parameter set is corrected based on the feedback information, and the radiant air conditioning system corresponding to the preset radiation area is controlled based on the corrected target control parameter set.

[0117] It should be noted that the feedback information is a correction instruction generated by the cloud server after comparing the valve position status and cumulative operating data sent by the edge gateway during the network outage with the expected status of the device shadow stored on the cloud server. The feedback information may include: the type of correction instruction (e.g., valve position correction instruction, water temperature correction instruction), the correction amount (e.g., valve position deviation value), and the execution timestamp. The edge gateway corrects each control parameter in the target control parameter set according to the correction amount in the feedback information, ensuring that the corrected control parameters in the target control parameter set are consistent with the expected status of the device shadow in the cloud. This ensures idempotent alignment of the device status after network recovery and avoids repetitive actions or system oscillations caused by inconsistent status.

[0118] Optionally, in some embodiments, an actuator residual correction step may also be included. The specific correction method may include: obtaining the state feedback value of the actuator in the building radiant air conditioning system corresponding to the preset radiation area; then, calculating the residual between the state feedback value and the corresponding command value in the target control parameter set; then, when the residual exceeds the preset residual threshold in multiple consecutive control cycles, marking the preset radiation area as a hydraulic imbalance state and determining the compensation coefficient corresponding to the preset radiation area; then, using the compensation coefficient to correct the target control parameter set, and controlling the radiant air conditioning system corresponding to the preset radiation area based on the corrected target control parameter set.

[0119] It should be noted that the status feedback value refers to the actual status signal transmitted back to the edge gateway after the actuator completes the control command action. Examples include the actual valve opening value transmitted by a mixing three-way valve and the actual operating frequency value transmitted by the inverter of a fresh air handling unit. The status feedback value reflects whether the actuator has accurately executed the control action according to the command value. The residual is the difference between the actuator's status feedback value and the command value issued by the edge gateway, used to quantify the actual execution deviation of the actuator.

[0120] When an actuator experiences mechanical jamming, wear, or hydraulic imbalance, the residual between the status feedback value and the command value will increase significantly. If the residual exceeds the preset residual threshold for multiple consecutive control cycles, it means that the actuator has a persistent execution deviation, rather than a single accidental error. Therefore, the preset radiation area is marked as a hydraulic imbalance state to trigger the subsequent compensation and correction mechanism.

[0121] The compensation coefficient is a multiplicative adjustment factor determined based on the residual magnitude. It is used to correct the control commands issued to the actuator in subsequent control cycles, so that the actual state of the actuator approaches the command value. For example, when the actual opening degree of the mixing valve is consistently lower than the commanded opening degree, the compensation coefficient is greater than 1, which is used to proportionally increase the subsequent commanded opening degree to compensate for the execution deviation.

[0122] By introducing an actuator residual correction step, actual execution deviations caused by factors such as hydraulic imbalance, actuator aging, or installation deviations can be compensated, enabling the edge gateway to sense and adaptively adjust actuator commands, ensuring accurate execution of control commands, and improving the system's control precision and robustness.

[0123] As can be seen from the above, after obtaining at least one plate surface temperature data and auxiliary temperature data within a preset radiation area, the embodiments of this application can reconstruct the temperature field of the preset radiation area based on at least one plate surface temperature data and auxiliary temperature data, and determine the condensation risk level of the preset radiation area according to the reconstructed temperature field. When the condensation risk level is lower than the preset risk level, in response to the triggering of a preset control event, a target prediction model is determined based on the type of the preset control event, and the target prediction model is used to predict the target control parameter set of the preset radiation area based on the condensation risk level and the reconstructed temperature field, so as to control the radiant air conditioning system corresponding to the preset radiation area based on the target control parameter set. This scheme can reconstruct the temperature field corresponding to the preset radiation area based on at least one panel temperature data and auxiliary temperature data, thereby comprehensively reflecting the temperature distribution at various locations on the surface of the radiant panel. This avoids relying on single-point temperature or average temperature for condensation prevention judgment and effectively identifies early condensation risks caused by local cold clusters and cold bridges in the building envelope. Furthermore, it determines the condensation risk level based on the difference between the temperature value and the dew point temperature value at each location in the reconstructed temperature field. When the condensation risk level is lower than the preset risk level, it predicts control parameters in response to the triggering of a preset control event and controls the radiant air conditioning system based on the predicted target control parameter set. Therefore, the accuracy and safety of condensation prevention judgment in radiant air conditioning systems can be improved. Simultaneously, the event-triggered control mechanism avoids the waste of computing power and response lag caused by fixed-period polling, improving the utilization efficiency of edge computing power. Under abnormal network conditions, the edge gateway retrieves the water supply temperature envelope data from local storage to continue executing local predictive control, avoiding the risk of condensation runaway due to lost valve commands and improving system reliability. Actuator residual correction compensates for hydraulic imbalance and execution deviation, improving control accuracy. Idempotent alignment of states after network recovery is achieved through network outage state synchronization and device shadowing mechanisms, ensuring stable system operation.

[0124] To better implement the above methods, this application also provides an Internet of Things (IoT) based building radiant air conditioning system control system. This IoT-based building radiant air conditioning system control system can be integrated into electronic devices, such as servers or terminals. The terminal may include tablet computers, laptops, and / or personal computers.

[0125] For example, such as Figure 4 As shown, the IoT-based building radiant air conditioning system control system may include an acquisition unit 301, a reconstruction unit 302, a determination unit 303, a prediction unit 304, and a control unit 305, as follows: (1) Obtain unit 301; The acquisition unit 301 is used to acquire at least one plate surface temperature data and auxiliary temperature data within a preset radiation area. The plate surface temperature data indicates the temperature distribution information of the radiation plate surface within the preset radiation area, and the auxiliary temperature data is used to help characterize the temperature distribution information of the preset radiation area.

[0126] (2) Reconstruction unit 302; The reconstruction unit 302 is used to reconstruct the temperature field of the preset radiation area based on the at least one plate surface temperature data and auxiliary temperature data, and to determine the condensation risk level of the preset radiation area based on the reconstructed temperature field.

[0127] (3) Determine unit 303; The determining unit 303 is used to determine a target prediction model based on the type of the triggered preset control event when the condensation risk level is lower than the preset risk level.

[0128] (4) Prediction unit 304; The prediction unit 304 is used to use a target prediction model to predict the set of target control parameters for the preset radiation area based on the condensation risk level and the reconstructed temperature field.

[0129] (5) Control unit 305; The control unit 305 is used to control the radiant air conditioning system corresponding to the preset radiation area based on the target control parameter set.

[0130] It should be noted that the control system may also include multiple edge gateways, cloud servers, and building radiant air conditioning systems. For details, please refer to step 101 in Embodiment 1.

[0131] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0132] This application also provides an electronic device, such as... Figure 5 As shown, it illustrates a structural schematic diagram of the electronic device involved in the embodiments of this application, specifically: The electronic device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 5 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 401 is the control center of the electronic device, connecting various parts of the device via various interfaces and lines. It executes software programs and / or modules stored in the memory 402, and calls data stored in the memory 402, to perform various functions and process data. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0133] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0134] The electronic device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0135] The electronic device may also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0136] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application programs stored in the memory 402 to realize various functions. It will be understood by those skilled in the art that all or part of the steps in the various methods of the above embodiments can be implemented by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by the processor.

[0137] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps in any of the IoT-based building radiant air conditioning system control methods provided in embodiments of this application.

[0138] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0139] The computer-readable storage medium may include: read-only memory (ROM), disk or optical disk, etc.

[0140] Since the instructions stored in the computer-readable storage medium can execute the steps in any of the IoT-based building radiant air conditioning system control methods provided in the embodiments of this application, the beneficial effects that any of the IoT-based building radiant air conditioning system control methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0141] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the methods provided in the various alternative implementations of the IoT-based building radiant air conditioning system control described above.

[0142] The foregoing describes in detail a method and related equipment for controlling a building radiant air conditioning system based on the Internet of Things (IoT) provided in the embodiments of this application. The related equipment may include an IoT-based building radiant air conditioning system control system, electronic devices, computer program products, and computer-readable storage media. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for controlling a building radiant air conditioning system based on the Internet of Things, characterized in that, include: Acquire at least one plate surface temperature data and auxiliary temperature data within a preset radiation area. The plate surface temperature data indicates the temperature distribution information of the radiation plate surface within the preset radiation area, and the auxiliary temperature data is used to help characterize the temperature distribution information of the preset radiation area. Based on the at least one plate surface temperature data and auxiliary temperature data, the temperature field of the preset radiation area is reconstructed, and the condensation risk level of the preset radiation area is determined according to the reconstructed temperature field. The auxiliary temperature data includes supply and return water temperature data, cold bridge point temperature data of the building envelope, and inner pipe wall temperature data within the preset radiation area, including: The temperature data of at least one plate surface is fused with the temperature data of the supply and return water, the temperature data of the cold bridge point of the enclosure structure, and the temperature data of the inner pipe wall to obtain the fused temperature data. Based on the size of the preset radiation region, the preset radiation region is divided into a preset number of temperature grids; A preset interpolation algorithm is used to map the fused temperature data onto a preset number of temperature grids to obtain the reconstructed temperature field corresponding to the preset radiation region. Specifically, when mapping the fused temperature data to the preset number of temperature grids, the plate surface temperature data in the fused temperature data is used as the main data for mapping. The supply and return water temperature data in the fused temperature data are used to provide the current load state boundary of the preset radiation region. The range of the interpolation result corresponding to the preset interpolation algorithm is referenced to the supply and return water temperatures. The cold bridge point temperature data in the fused temperature data is used to mark the location of the cold bridge in the enclosure structure that affects the temperature field distribution. The inner pipe wall temperature data in the fused temperature data is used as a leading prediction signal for plate surface temperature changes to assist in judging the temperature change trend. Determining the condensation risk level of the preset radiation area based on the reconstructed temperature field includes: obtaining the target dew point temperature value corresponding to the preset radiation area, wherein the target dew point temperature value indicates the critical temperature value at which condensation occurs in the preset radiation area; calculating the difference between the temperature value corresponding to each temperature grid in the reconstructed temperature field and the target dew point temperature value to obtain the condensation margin corresponding to each temperature grid; and determining the condensation risk level of the preset radiation area based on the condensation margin corresponding to each temperature grid. When the condensation risk level is lower than the preset risk level, in response to the triggering of a preset control event, a target prediction model is determined based on the type of the preset control event, including: when the type of the preset control event is a disturbance control event, the target prediction model is determined to be a disturbance prediction model, wherein the disturbance prediction model takes temperature change trend prediction as the prediction target; Using the target prediction model, a set of target control parameters for the preset radiation area is predicted based on the condensation risk level and the reconstructed temperature field. This includes: determining the temperature change rate during a disturbance control event based on temperature change data of the preset radiation area during historical periods; using the reconstructed temperature field at the current moment as the initial value of the temperature distribution and the condensation risk level at the current moment as a constraint; using the disturbance prediction model, predicting the temperature change trend within a preset period based on the temperature change rate, the initial value of the temperature distribution, and the constraint, obtaining a predicted temperature distribution value at each prediction moment within the preset period; determining a compensation control value at each prediction moment within the preset period based on the deviation between the predicted temperature distribution value at each prediction moment and the target temperature value corresponding to the preset radiation area; and generating the set of target control parameters for the preset radiation area based on the compensation control value using the disturbance prediction model. The radiant air conditioning system corresponding to the preset radiation area is regulated based on the target control parameter set; The method further includes: When the condensation risk level is higher than or equal to the preset risk level, the anti-condensation control strategy is executed. The implementation of the anti-condensation control strategy includes: Adjust or close the cold water supply valve of the preset radiation area to reduce the flow rate of cold water entering the preset radiation area, so that the surface temperature of the radiation plate in the preset radiation area can rise again; And / or, turn on or increase the fresh air dehumidification in the preset radiation area to reduce the indoor dew point temperature in the preset radiation area; And / or, adjust the mixing ratio of return air and fresh air in the preset radiation area to reduce the dew point temperature of the adhesive layer in the preset radiation area.

2. The method for controlling a building radiant air conditioning system based on the Internet of Things according to claim 1, characterized in that, The step of determining a target prediction model based on the type of the preset control event in response to the triggering of a preset control event includes: When the type of the preset control event is a condensation risk control event, the target prediction model is determined to be a condensation risk prediction model, and the condensation risk prediction model takes the prediction of the condensation margin change trend as the prediction target. The step of using the target prediction model to obtain the target control parameter set for the preset radiation area based on the condensation risk level and the reconstructed temperature field prediction includes: The target condensation margin is selected from the condensation margins corresponding to at least one temperature grid in the reconstructed temperature field. Using the aforementioned condensation risk prediction model, based on the target condensation margin, condensation risk level, and reconstructed temperature field, the trend of condensation margin change within a preset time period is predicted to obtain the predicted value of condensation margin at each prediction time within the preset time period. Based on the comparison between the predicted condensation margin value and the margin threshold at each predicted moment within the preset time period, the compensation control value at each predicted moment within the preset time period is determined. Using the aforementioned condensation risk prediction model, a set of target control parameters for the preset radiation area is generated based on the compensation control value.

3. The method for controlling a building radiant air conditioning system based on the Internet of Things according to claim 1, characterized in that, The step of determining a target prediction model based on the type of the preset control event in response to the triggering of a preset control event includes: When the type of the preset control event is an optimized control event, the target prediction model is determined to be an optimized prediction model, and the optimized prediction model takes energy efficiency prediction as the prediction target. The step of using the target prediction model to obtain the target control parameter set for the preset radiation area based on the condensation risk level and the reconstructed temperature field prediction includes: Based on the historical control data of the preset radiation area, determine the load change trend and energy consumption change trend of the preset radiation area within a preset time period; Using the optimized prediction model, based on the load change trend, the energy consumption change trend, the condensation risk level, and the reconstructed temperature field, energy efficiency optimization is performed within a preset time period to obtain the predicted energy efficiency value at each prediction time within the preset time period. Based on the energy efficiency prediction value at each prediction time within the preset time period, determine the compensation control value at each prediction time within the preset time period. Using the optimized prediction model, a set of target control parameters for the preset radiation area is generated based on the compensation control value.

4. The method for controlling a building radiant air conditioning system based on the Internet of Things according to any one of claims 1-3, characterized in that, The method further includes: When the network connection between the edge gateway and the cloud server corresponding to the preset radiation area is interrupted, the water supply temperature envelope data is extracted from the local storage, and the target control parameter set is corrected based on the water supply temperature envelope data. The radiant air conditioning system corresponding to the preset radiation area is then controlled based on the corrected target control parameter set. When the network connection between the edge gateway and the cloud server is restored, the valve position status and cumulative operating data during the network outage are sent to the cloud server, and feedback information returned by the cloud server is received. The target control parameter set is corrected based on the feedback information, and the radiant air conditioning system corresponding to the preset radiation area is controlled based on the corrected target control parameter set.

5. The method for controlling a building radiant air conditioning system based on the Internet of Things according to any one of claims 1-3, characterized in that, The method further includes: Obtain the status feedback value of the actuator in the building radiant air conditioning system corresponding to the preset radiation area; Calculate the residual between the state feedback value and the corresponding command value in the target control parameter set; When the residual exceeds a preset residual threshold within multiple consecutive control cycles, the preset radiation area is marked as a hydraulic imbalance state, and the compensation coefficient corresponding to the preset radiation area is determined. The target control parameter set is corrected using the compensation coefficient, and the radiant air conditioning system corresponding to the preset radiation area is controlled based on the corrected target control parameter set.

6. A building radiant air conditioning system control system based on the Internet of Things, characterized in that, The method for controlling a building radiant air conditioning system based on the Internet of Things as described in any one of claims 1-5 includes: The acquisition unit is used to acquire at least one plate surface temperature data and auxiliary temperature data within a preset radiation area. The plate surface temperature data indicates the temperature distribution information of the surface of the radiation plate within the preset radiation area, and the auxiliary temperature data is used to help characterize the temperature distribution information of the preset radiation area. The reconstruction unit is used to reconstruct the temperature field of the preset radiation area based on the at least one plate surface temperature data and auxiliary temperature data, and to determine the condensation risk level of the preset radiation area according to the reconstructed temperature field. The auxiliary temperature data includes the supply and return water temperature data, the cold bridge point temperature data of the building envelope, and the inner pipe wall temperature data within the preset radiation area. The reconstruction unit is specifically used to fuse the at least one plate surface temperature data with the supply and return water temperature data, the cold bridge point temperature data of the enclosure structure, and the inner pipe wall temperature data to obtain fused temperature data; based on the size of the preset radiation area, the preset radiation area is divided into a preset number of temperature grids; a preset interpolation algorithm is used to map the fused temperature data onto the preset number of temperature grids to obtain the reconstructed temperature field corresponding to the preset radiation area; wherein, when mapping the fused temperature data onto the preset number of temperature grids, the plate surface temperature data in the fused temperature data is used as the main data for mapping, the supply and return water temperature data in the fused temperature data is used to provide the current load state boundary of the preset radiation area, and the interpolation result corresponding to the preset interpolation algorithm is... The range of values ​​for the result is referenced to the supply and return water temperatures. The cold bridge point temperature data in the fused temperature data is used to mark the location of the cold bridge in the enclosure structure that affects the temperature field distribution. The inner pipe wall temperature data in the fused temperature data is used as a leading prediction signal for the surface temperature change to help determine the temperature change trend. The condensation risk level of the preset radiation area is determined based on the reconstructed temperature field, including: obtaining the target dew point temperature value corresponding to the preset radiation area, where the target dew point temperature value indicates the critical temperature value at which condensation occurs in the preset radiation area; calculating the difference between the temperature value corresponding to each temperature grid in the reconstructed temperature field and the target dew point temperature value to obtain the condensation margin corresponding to each temperature grid; and determining the condensation risk level of the preset radiation area based on the condensation margin corresponding to each temperature grid. The determining unit is used to determine a target prediction model based on the type of the triggered preset control event when the condensation risk level is lower than the preset risk level, in response to the triggering of the preset control event, including: when the type of the preset control event is a disturbance control event, determining the target prediction model as a disturbance prediction model, wherein the disturbance prediction model takes temperature change trend prediction as the prediction target; The prediction unit is used to predict a set of target control parameters for the preset radiation area based on the condensation risk level and the reconstructed temperature field using the target prediction model. This includes: determining the temperature change rate during a disturbance control event based on temperature change data of the preset radiation area during historical periods; using the reconstructed temperature field at the current moment as the initial value of the temperature distribution and the condensation risk level at the current moment as a constraint; using the disturbance prediction model to predict the temperature change trend within a preset period based on the temperature change rate, the initial value of the temperature distribution, and the constraint, obtaining a predicted temperature distribution value for each prediction moment within the preset period; determining a compensation control value for each prediction moment within the preset period based on the deviation between the predicted temperature distribution value at each prediction moment and the target temperature value corresponding to the preset radiation area; and generating the set of target control parameters for the preset radiation area based on the compensation control value using the disturbance prediction model. The control unit is used to control the radiant air conditioning system corresponding to the preset radiation area based on the target control parameter set; The control unit is further configured to execute an anti-condensation control strategy when the condensation risk level is higher than or equal to a preset risk level. The execution of the anti-condensation control strategy includes: reducing or closing the cold water supply valve of the preset radiation area to decrease the flow rate of cold water entering the preset radiation area, thereby causing the surface temperature of the radiant panel within the preset radiation area to rise; and / or, turning on or increasing the fresh air dehumidification of the preset radiation area to lower the indoor dew point temperature of the preset radiation area; and / or, adjusting the mixing ratio of return air and fresh air in the preset radiation area to lower the dew point temperature of the adhesive layer in the preset radiation area.

Images