A temperature intelligent control method and system

Abstract

The application discloses a kind of temperature intelligent control method and system, belong to temperature control technical field, its method specifically includes: the relevant data of target area is collected in real time;According to the relevant data of the target area, construct four-field coupling dynamic prediction model, predict the temperature of target area, the four-field coupling dynamic prediction model is based on four-field coupling model and the relevant data of target area collected in real time construction, and the four-field coupling model is based on the variable model of foundation field and is obtained by simultaneous coupling;According to the predicted temperature of target area, determine cooling water pipe flow control strategy;Cooling is carried out to target area until target temperature is reached;The application significantly improves the temperature monitoring precision, prediction accuracy and control intelligent level of mass concrete structure in construction process, effectively reduces crack risk, improves construction quality and safety guarantee ability.

Description

Technical Field

[0001] This invention belongs to the field of temperature control technology, specifically a temperature intelligent control method and system. Background Technology

[0002] In water conservancy infrastructure construction, large-volume concrete structures (thickness greater than 1 meter) are widely used in key load-bearing components such as dam bodies, gate piers, and foundations. However, during the hydration and hardening process of concrete, a large amount of hydration heat accumulates inside the structure, causing the temperature in the core area to rise rapidly, forming a large internal and external temperature difference and temperature gradient. This can easily induce temperature cracks and strength degradation, affecting the safety and durability of the project.

[0003] The following types of temperature control technologies are commonly used in engineering practice: distributed fiber optic sensors for temperature monitoring, PID controllers for regulating cooling water valves or flow rates, and the installation of cooling water pipe networks inside concrete to control the cooling rate through circulating cold water.

[0004] The shortcomings of existing temperature control technology are: the error is large in the deep part of the structure, and the error rate of traditional temperature field prediction models is generally large, resulting in large errors in subsequent temperature regulation. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention proposes a method and system for intelligent temperature control.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A temperature intelligent control method includes:

[0008] Real-time collection of relevant data from the target area;

[0009] Based on the relevant data of the target area, a four-field coupled dynamic prediction model is constructed to predict the temperature of the target area;

[0010] Determine the cooling water pipe flow control strategy based on the predicted temperature of the target area;

[0011] Cool the target area until the target temperature is reached.

[0012] Specifically, the step of constructing a four-field coupled dynamic prediction model based on relevant data of the target region includes:

[0013] A basic field variable model is established based on historical data of the target area;

[0014] By simultaneously coupling the equations of the fundamental field variables, a four-field coupled model is obtained;

[0015] Based on the four-field coupling model and real-time acquired target area data, a four-field coupling dynamic prediction model is constructed to predict the temperature of the target area.

[0016] Specifically, based on historical data of the target area, a basic field variable model is established, including: a hydrothermal model, a temperature field model, a stress field model, and a humidity field model.

[0017] Specifically, the simultaneous coupling of the fundamental field variable equations yields a four-field coupled model, including:

[0018] Set the temperature field as the main control variable;

[0019] The target region is divided into three-dimensional voxel elements or finite element nodes, and a state vector containing four variables is established at each node.

[0020] At each node, construct the coupling path between the four variables and determine the influence weight of each coupling path;

[0021] At each time step and at each node, state updates are performed based on the state of the previous time step and the influence weights.

[0022] The node states are combined into a four-field coupling model, where the state vector of each node is a time-series state vector, and each dimension of the four-field coupling model represents the spatial location, time point, and four variables.

[0023] Specifically, the step of constructing coupling paths between the four variables at each node and determining the influence weight of each coupling path includes:

[0024] Analyze the physical interaction paths between each variable and construct a coupling path dominated by the temperature field;

[0025] Identify the types of influencing factors between variable pairs in the coupling path;

[0026] Construct a coupling path mapping matrix, in which rows represent the affected variables and columns represent the variables exerting the influence.

[0027] Based on the coupling path mapping matrix, each coupling path is assigned an initial influence weight, which is then dynamically adjusted according to the temporal state changes of the variables.

[0028] Specifically, the step of performing state updates based on the state and influence weights of the previous time step at each time step and at each node includes:

[0029] Extract the state vector of each node from the previous time step;

[0030] Based on the constructed coupling path and its influence weights, the state vector of each node is updated;

[0031] The updated state vector is passed to the next time step for iterative evolution.

[0032] Specifically, the construction of a four-field coupled dynamic prediction model to predict the temperature of the target region includes:

[0033] Combining real-time relevant data of the target area, the four-field coupling model outputs time series data of four variables;

[0034] Construct a multimodal sequence neural network model, set a loss function, and train the constructed multimodal sequence neural network model;

[0035] The time series data of four variables are input into a trained multimodal sequence neural network, which outputs the predicted temperature of the target region.

[0036] Specifically, determining the cooling water pipe flow control strategy based on the predicted temperature of the target area includes:

[0037] Average all predicted temperatures within the target area and construct a temperature trend curve;

[0038] Risk levels of target areas are classified based on temperature trend curves;

[0039] Based on reinforcement learning, the current state of the target region is input, and the optimal flow rate of the cooling water pipe is output.

[0040] Based on the optimal flow rate, a PLC control signal is generated to adjust the actual flow rate of the cooling water pipe.

[0041] A temperature intelligent control system for implementing the aforementioned temperature intelligent control method includes: a data acquisition module, a prediction module, a flow control module, and a cooling module;

[0042] The data acquisition module is used to collect relevant data of the target area in real time;

[0043] The prediction module is used to construct a four-field coupled dynamic prediction model based on relevant data of the target area to predict the temperature of the target area.

[0044] The flow control module is used to determine the cooling water pipe flow control strategy based on the predicted temperature of the target area.

[0045] The cooling module is used to cool the target area until the target temperature is reached.

[0046] Specifically, the prediction module includes: a coupling unit and a prediction unit;

[0047] The coupling unit is used to establish a basic field variable model and perform simultaneous coupling of the basic field variable equations to obtain a four-field coupling model.

[0048] The prediction unit constructs a four-field coupled dynamic prediction model based on the four-field coupling model and real-time collected target area related data to predict the temperature of the target area.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] 1. This invention proposes a temperature intelligent control method and system. By integrating multimodal sensing, a four-field coupled dynamic prediction model, and reinforcement learning control, it significantly improves the temperature monitoring accuracy, prediction accuracy, and control intelligence level of large-volume concrete structures during construction. It achieves dynamic optimization and adjustment of cooling flow, breaks through the bottleneck of temperature control rate for ultra-thick structures, effectively reduces the risk of cracking, and improves construction quality and safety assurance capabilities. Attached Figure Description

[0051] Figure 1 A flowchart of a temperature intelligent control method provided by the present invention;

[0052] Figure 2 A schematic diagram of the four-field coupling model provided by this invention;

[0053] Figure 3 This invention provides an architecture diagram of a temperature intelligent control system. Detailed Implementation

[0054] The present application will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present application, but do not limit the present application in any way. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application. These all fall within the protection scope of the present application.

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] It should be noted that, unless there is a conflict, the various features in the embodiments of this application can be combined with each other, all of which are within the protection scope of this application. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. In addition, the terms "first," "second," and "third" used in this application do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0057] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items.

[0058] Example 1

[0059] Please see Figures 1-2 The present invention provides an embodiment of a temperature intelligent control method applied to the interior of concrete in hydraulic engineering projects, comprising the following specific steps:

[0060] Step S1: Collect relevant data of the target area in real time. The target area is the concrete surface and interior of the hydraulic engineering project. The relevant data of the target area includes temperature, stress, humidity and auxiliary information.

[0061] In this embodiment, the target area includes, but is not limited to: key sections inside concrete construction bodies (such as dam bodies, gate piers, and foundation pads); areas on the surface that are prone to water loss or heat; areas where cooling water pipes are arranged; areas where temperature stress is concentrated; and locations where temperature differences or crack risks are known or predicted to exist.

[0062] The auxiliary information includes: ambient temperature and humidity, cooling water flow rate, boundary conditions, etc.

[0063] Step S2: Construct a four-field coupled dynamic prediction model based on the relevant data of the target region.

[0064] The specific steps of step S2 are as follows:

[0065] Step S201: Establish a basic field variable model based on historical data of the target area.

[0066] In this embodiment, the basic field variable model includes a hydration heat field, a temperature field, a stress field, and a humidity field. The hydration heat field is established by a heat source function model with the hydration reaction rate as the core. The temperature field is based on the conduction equation of unsteady heat and introduces anisotropic thermal conductivity. The stress field adopts a nonlinear viscoelastic-plastic constitutive relation and couples the temperature-induced thermal expansion and contraction stress. The humidity field adopts a vapor migration-capillary diffusion joint model to reflect the conversion process of free water and adsorbed water.

[0067] Step S202: Combine the equations of the basic field variables to obtain a four-field coupled model.

[0068] like Figure 2 As shown, the specific steps of step S202 are as follows:

[0069] Step S2021: Set the temperature field as the main control variable.

[0070] In this embodiment, temperature is chosen as the core driving variable because: the release of heat of hydration directly affects the temperature rise; temperature changes cause the material to expand and contract, thereby generating stress; and temperature changes affect the evaporation and migration of moisture, thus affecting the humidity field. Therefore, temperature is chosen as the main axis, and its changes drive the linkage response of the other three fields.

[0071] Step S2022: Divide the target region into three-dimensional voxel elements or finite element nodes, and establish a state vector containing four variables at each node.

[0072] In this embodiment, a three-dimensional voxel is a pixel block or cubic mesh unit in three-dimensional space, similar to a two-dimensional image composed of many pixels. A three-dimensional structure can be divided into many tiny cubes, which are voxels. Each voxel is used to represent a set of states in the space, such as temperature and moisture. In engineering modeling, complex structures (such as concrete dams) are usually divided into many small units, and the corner points of each unit are called finite element nodes.

[0073] Specifically, concrete is a large-volume, heterogeneous material with highly uneven distribution of internal temperature, humidity, and stress. After dividing the overall structure into small regions, a state vector containing four variables is established on each division unit. Essentially, this is to model each region separately, reflecting the differences in the structure's behavior at different locations.

[0074] The four variables in the state vector include: hydration heat release rate, nodal temperature, nodal stress state, and nodal humidity.

[0075] Step S2023: Construct the coupling path between the four variables at each node and determine the influence weight of each coupling path.

[0076] The specific steps of step S2023 are as follows:

[0077] Step S20231: Analyze the physical interaction paths between each variable and construct a coupling path dominated by the temperature field.

[0078] In this embodiment, the coupling path refers to the path of how one variable affects another variable; in this application, it refers to how the temperature variable affects the other three variables.

[0079] Specifically, in this step, temperature is first identified as the dominant variable. In the entire four-field coupling model, temperature change is the primary driving force behind changes in other variables. Through physical mechanism analysis, the following coupling paths are constructed: Temperature → Hydration heat release: Increased temperature accelerates the hydration reaction rate of cement, leading to increased heat; Temperature → Humidity migration: Increased temperature promotes internal moisture evaporation and migration, reducing local humidity; Temperature → Stress evolution: Temperature changes cause thermal expansion and contraction of materials, resulting in internal stress under boundary conditions; Hydration heat → Temperature: The release of hydration heat itself further increases local temperature; Humidity → Hydration heat: Cement hydration depends on available water; decreased humidity will, in turn, slow down the release of hydration heat; Stress → Changes in structural thermal conductivity: Microcracks form in high-stress areas, altering thermal conductivity.

[0080] Step S20232: Identify the types of influencing factors between variable pairs in the coupling path.

[0081] Specifically, the variable pairs in each coupling path are analyzed, and their influence mechanism types are identified, such as: accelerating influence: such as increased temperature accelerating the release of heat of hydration; inhibiting influence: such as decreased humidity slowing down the release of heat of hydration; threshold-triggered influence: such as stress exceeding a certain critical value affecting the heat conduction path; feedback influence: such as the release of heat of hydration, which in turn increases the temperature, forming positive feedback; and asymmetric influence: such as temperature having a significant impact on humidity, but humidity having a weaker impact on temperature. This classification is not only used for qualitative description but will also be represented as a dynamic weighting factor in the subsequent influence weight calculation.

[0082] Step S20233: Construct a coupling path mapping matrix, in which rows represent the affected variables and columns represent the variables that exert the influence.

[0083] Specifically, based on the variable paths and influencing factor identification in the previous step, a coupling path mapping matrix is ​​constructed. The rows of this matrix represent the influenced variables, the columns represent the variables that exert the influence, and the matrix elements are path type labels or initial weight percentages. A simplified coupling path mapping matrix is ​​shown in Table 1.

[0084] Table 1

[0085]

[0086] Step S20234: Based on the coupling path mapping matrix, assign initial influence weights to each coupling path and dynamically adjust them according to the temporal state changes of the variables.

[0087] In this embodiment, an initial influence weight is first assigned to each pair of variable paths based on empirical values, literature parameters, or prior models. Then, dynamic adjustments are made. The specific adjustment logic is as follows: read the current state of the four variables of each node; determine the rate of change of the variables, such as the rate of temperature increase or the rate of humidity decrease; adjust the system according to the current state and the trend of change by calling a set of preset adjustment rules; after all path weights are output, update the state of the four-field coupling model of the node.

[0088] The adjustment rule base includes, for example: if the temperature rises rapidly, its weight on hydration heat and humidity is increased; if the humidity drops below a certain critical value, its support weight on hydration heat is automatically suppressed; if the accumulated stress approaches the warning value, its feedback adjustment factor on the temperature control path is activated.

[0089] Step S2024: At each time step and at each node, perform a state update based on the state of the previous time step and the influence weight.

[0090] The specific steps of step S2024 are as follows:

[0091] Step S20241: Extract the state vector of each node from the previous time step.

[0092] In this embodiment, the data at the current time t is processed in chronological order. For each node in the three-dimensional mesh, its state vector recorded at the previous time point t-1 is read, including the current hydration heat release rate, the current node temperature, the current node stress state, and the current node humidity.

[0093] Step S20242: Update the state vector of each node based on the constructed coupling path and its influence weights.

[0094] In this embodiment, temperature is the master variable, and its current value and rate of change affect the other three variables. Using coupling paths and influence weights, the value of each variable at time t is iteratively calculated, and the state vector at time t is updated based on the calculated value.

[0095] Step S20243: Pass the updated state vector to the next time step and perform iterative evolution.

[0096] Specifically, the latest state vector of each node at the current time is stored in the state buffer and used as the input for the next time step t+1, and this process is repeated cyclically.

[0097] The benefits of this approach are as follows: explicit updates are performed on the state vector of each node at each time step. By introducing variable coupling paths and weighting mechanisms, dynamic linkage between temperature, heat of hydration, humidity, and stress is achieved. This approach possesses temporal continuity, state evolution, and predictive adaptability, thus providing a basis for subsequent flow regulation and risk warning. In practical engineering, this state update mechanism can significantly improve the response speed and prediction accuracy of the temperature control system.

[0098] Step S2025: Combine the node states into a four-field coupling model, wherein the state vector of each node is a time series state vector, and each dimension of the four-field coupling model represents the spatial location, time point, and four variables.

[0099] like Figure 2 As shown, in Figure 2 In the diagram, the X, Y, and Z axes represent spatial dimensions, indicating the three-dimensional division of the concrete structure. Figure 2 The points in the diagram represent each voxel or finite element node in the concrete structure. The → symbol below represents the time axis, which describes the continuous evolution of the state vector of each node over time. The variable dimensions (H, T, S, M) are: each node records four basic field variables at each moment, forming a state vector V(t) = [H, T, S, M], where H represents the hydration heat release rate, T represents the node temperature, S represents the node stress state, and M represents the node humidity.

[0100] The advantages of this approach are as follows: by setting temperature as the master variable and constructing a coupled state system of hydration heat, humidity, and stress variables, high-precision dynamic prediction and modeling of multiphysics fields are achieved through spatial node partitioning, temporal state evolution, and variable path weight linkage. The proposed four-field coupled model has engineering applicability and can support the intelligent, precise, and automated development direction of concrete temperature control in water conservancy projects. It solves the technical problems of traditional temperature control models such as inability to dynamically adapt, coupling failure, and response delay.

[0101] Step S203: Based on the four-field coupling model and the real-time collected target area related data, construct a four-field coupling dynamic prediction model to predict the temperature of the target area.

[0102] The specific steps of step S203 are as follows:

[0103] Step S2031: Combining real-time relevant data of the target area, the four-field coupling model outputs time series data of four variables.

[0104] Step S2032: Construct a multimodal sequence neural network model, set a loss function, and train the constructed multimodal sequence neural network model.

[0105] In this embodiment, the network structure design includes: input, four modal channels of four time series as network input; main structure, adopting a neural network structure based on time series modeling, such as GRU, LSTM or Transformer; modal fusion, fusing the sequence features of the four variables through attention mechanism or multi-channel gating unit; output, the temperature prediction value of the target node in the future several time steps.

[0106] The loss function used is the mean squared error (MSE) loss function, which evaluates the difference between the predicted temperature and the actual temperature.

[0107] Training of the multimodal sequence neural network model: Historical measurement data is used as the training set; samples are organized using a sliding window method to improve the model's ability to identify short-term trends; multiple rounds of iterative training are performed to optimize weight parameters, complete model fitting, and obtain a well-trained multimodal sequence neural network model.

[0108] Step S2033: Input the time series data of the four variables into the trained multimodal sequence neural network and output the predicted temperature of the target region.

[0109] Step S3: Determine the cooling water pipe flow control strategy based on the real-time predicted temperature data.

[0110] The specific steps of step S3 are as follows:

[0111] Step S301: Average all predicted temperatures within the target area and construct a temperature trend curve;

[0112] In this step, the predicted temperature values ​​of all spatial nodes in the target area are extracted from the obtained temperature prediction results. The temperature values ​​of all voxels or finite element nodes are weighted and averaged, taking into account location, material differences, or structural importance, to obtain the average temperature value of the target area at each prediction time point. The average temperature values ​​are arranged in chronological order to form a temperature trend curve. The curve is smoothed using methods such as spline interpolation or local weighted regression to suppress high-frequency noise. This trend curve will be used to evaluate the rate of temperature rise, peak temperature, etc.

[0113] Step S302: Classify the risk level of the target area based on the temperature trend curve.

[0114] In this embodiment, the thermal risk level of the target area is classified according to key indicators in the trend curve. The main rules include, but are not limited to: maximum temperature threshold: if the predicted temperature is >75°C, it is judged as high risk; heating rate threshold: if the average heating rate is >0.7°C / h, it is judged as medium to high risk; temperature gradient change rate: if the internal and surface temperature difference is >20°C, it is judged as extremely high risk; multi-point peak synchronicity: if multiple points simultaneously enter the rapid heating zone, the level is increased.

[0115] Based on the above conditions, the target area is divided into four levels: Level I (low risk): normal maintenance; Level II (medium risk): mild cooling; Level III (high risk): active forced cooling; Level IV (extremely high risk): multi-point scheduling and joint control, key tracking.

[0116] Step S303: Based on reinforcement learning, input the current state of the target region and output the optimal flow rate of the cooling water pipe.

[0117] In this embodiment, a cooling strategy model based on Q-Learning or deep reinforcement learning algorithms is adopted. The state is defined as follows: current temperature prediction trend; current risk level; cooling water flow rate at the previous time step; and auxiliary information such as local temperature difference and stress distribution. The action is defined as: controlling the flow rate adjustment of each or each group of cooling water pipes. The action space includes increasing flow rate, decreasing flow rate, or keeping it constant, or setting precision control in a continuous action space. The reward function is designed with the following objectives: the predicted temperature is controlled within a safe range, cooling energy consumption is minimized, and stress growth is gradual. If the temperature enters the safe range, a positive reward is given; if there is accelerated temperature rise or excessive energy consumption, a penalty is given. The strategy is executed by the trained reinforcement learning model, which outputs the optimal cooling flow rate solution based on the current state. The strategy is automatically updated within each prediction cycle, supporting adaptive dynamic adjustment.

[0118] Step S304: Generate a PLC control signal based on the optimal flow rate to adjust the actual flow rate of the cooling water pipe.

[0119] In this embodiment, the flow regulation of the cooling water pipe relies on data interaction and control command transmission between the programmable logic controller (PLC) and the temperature control prediction platform. First, the cooling strategy is converted into a standard PLC control command set, including target flow, speed adjustment, valve opening and closing actions, etc. Through the edge computing platform, the commands are sent to the control valve of each section of the cooling water pipe in real time. The control valve realizes the prediction-driven intelligent temperature control of the internal temperature of the large-volume concrete structure and adjusts the water flow according to the command.

[0120] The PLC adopts industrial standard communication interfaces, including: Modbus TCP / IP, Ethernet interface for configuration software; RS485 for accessing edge data acquisition gateways; and OPC UA protocol for data interface with cloud or control platforms. These communication interfaces ensure data exchange with flow meters, actuators, and predictive systems, and support bidirectional control signal interaction.

[0121] The benefits of this step are: it enables predictive intelligent temperature control of the internal temperature of large-volume concrete structures, and transforms flow control from experience-based adjustment to model-based decision management, resulting in higher cooling efficiency and lower energy consumption.

[0122] Step S4: Cool the target area until the target temperature is reached.

[0123] Example 2

[0124] Please see Figure 3 Another embodiment of the present invention provides: a cybersecurity compliance assessment system, comprising: a data acquisition module, a prediction module, a flow control module, and a cooling module;

[0125] The data acquisition module is used to collect relevant data of the target area in real time;

[0126] The prediction module is used to construct a four-field coupled dynamic prediction model based on relevant data of the target area to predict the temperature of the target area.

[0127] The flow control module is used to determine the cooling water pipe flow control strategy based on the predicted temperature of the target area.

[0128] The cooling module is used to cool the target area until the target temperature is reached.

[0129] The prediction module includes: a coupling unit and a prediction unit;

[0130] The coupling unit is used to establish a basic field variable model and perform simultaneous coupling of the basic field variable equations to obtain a four-field coupling model.

[0131] The prediction unit constructs a four-field coupled dynamic prediction model based on the four-field coupling model and real-time collected target area related data to predict the temperature of the target area.

[0132] In addition, the parts of the technical solutions provided in the embodiments of this application that are consistent with the implementation principles of the corresponding technical solutions in the prior art have not been described in detail, so as to avoid excessive elaboration.

[0133] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the invention. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A temperature intelligent control method, characterized in that, The method comprises the following steps: collecting real-time data of a target region; constructing a four-field coupling dynamic prediction model based on the real-time data of the target region to predict the temperature of the target region, wherein the four-field coupling dynamic prediction model is constructed based on a four-field coupling model and the real-time data of the target region, and the four-field coupling model is obtained by simultaneously coupling a basic field variable model; determining a cooling water pipe flow control strategy according to the predicted temperature of the target region; cooling the target region until the target region reaches a target temperature; constructing a four-field coupling dynamic prediction model based on the real-time data of the target region, comprising: establishing a basic field variable model based on historical data of the target region; simultaneously coupling the basic field variable equations to obtain a four-field coupling model; constructing a four-field coupling dynamic prediction model based on the four-field coupling model and the real-time data of the target region to predict the temperature of the target region; the establishing a basic field variable model based on historical data of the target region comprises a water-heat conversion model, a temperature field model, a stress field model, and a humidity field model; the simultaneously coupling the basic field variable equations to obtain a four-field coupling model comprises: setting the temperature field as a main control variable; dividing the target region into three-dimensional voxel units or finite element nodes, and establishing a state vector containing hydration heat, temperature, stress, and humidity at each node; constructing coupling paths between the four variables at each node and determining the influence weights of the coupling paths; in each time step and at each node, performing state updating according to the state of the previous time step and the influence weights; combining the node states into a four-field coupling model, wherein the state vector of each node is a time series state vector, and each dimension of the four-field coupling model represents a spatial position, a time point, and the four variables; the constructing coupling paths between the four variables at each node and determining the influence weights of the coupling paths comprises: analyzing the physical action paths between each variable to construct a coupling path dominated by the temperature field; identifying the influence factor types between the variable pairs in the coupling path; constructing a coupling path mapping matrix, wherein the rows represent the affected variables and the columns represent the variables that exert influence, assigning initial influence weights to each coupling path based on the coupling path mapping matrix, and dynamically adjusting the influence weights according to the time series state changes of the variables.

2. The temperature intelligent control method of claim 1, wherein, the in each time step and at each node, performing state updating according to the state of the previous time step and the influence weights comprises: extracting the state vector of each node from the previous time step; updating the state vector of each node based on the constructed coupling paths and their influence weights; passing the updated state vector to the next time step for iterative evolution.

3. The temperature intelligent control method of claim 2, wherein, the constructing a four-field coupling dynamic prediction model to predict the temperature of the target region comprises: combining the real-time data of the target region, and the four-field coupling model outputs time series data of the four variables; constructing a multi-modal sequence neural network model, setting a loss function, and training the constructed multi-modal sequence neural network model; The time series data of four variables is input into the trained multi-modal sequence neural network, and the predicted temperature of the target area is output.

4. The temperature intelligent control method of claim 3, wherein, The cooling water pipe flow control strategy is determined according to the predicted temperature of the target area, including: Average all predicted temperatures in the target area and construct a temperature trend curve; Divide the target area into risk levels based on the temperature trend curve; Based on reinforcement learning, input the current state of the target area, and output the optimal flow of the cooling water pipe; Generate a PLC control signal according to the optimal flow to adjust the actual flow of the cooling water pipe.

5. A temperature intelligent control system for implementing the temperature intelligent control method of any one of claims 1-4, characterized in that, It includes: Data acquisition module, prediction module, flow control module and cooling module; The data acquisition module is used to collect real-time data of the target area; The prediction module is used to construct a four-field coupled dynamic prediction model according to the relevant data of the target area to predict the temperature of the target area; The flow control module is used to determine the cooling water pipe flow control strategy according to the predicted temperature of the target area; The cooling module is used to cool the target area until the target temperature is reached; The prediction module includes a coupling unit and a prediction unit; The coupling unit is used to establish a basic field variable model, and the basic field variable equation set is coupled to obtain a four-field coupled model; The prediction unit constructs a four-field coupled dynamic prediction model based on the four-field coupled model and the real-time collected target area related data to predict the temperature of the target area.

Images