Self-powered energy-storage temperature-adjusting concrete wall and management and control method and manufacturing method thereof

Abstract

The invention relates to a self-powered energy-storage temperature-adjusting concrete wall and a management and control method and a manufacturing method thereof, and solves the problem that in the prior art, application of a phase-change material and a thermoelectric material is mostly independently designed, collaborative optimization of the phase-change material and the thermoelectric material cannot be achieved, and consequently the utilization efficiency of solar energy is low. A plurality of through pipelines are arranged inside; the thermoelectric phase change material is poured into the pipeline of the hollow frame, the thermoelectric phase change material is ionic thermoelectric phase change hydrogel, and the thermoelectric phase change material comprises at least two gel components with different phase change temperatures so as to form temperature gradient regulation and control; the thermoelectric function structure comprises N-type thermoelectric materials and P-type thermoelectric materials which are arranged on the outer surface of the hollow frame or form a hollow frame body, and the N-type thermoelectric materials and the P-type thermoelectric materials are alternately arranged and are connected in series through electrodes to form a closed thermoelectric loop. The system has the following effects that efficient utilization of solar energy is achieved, energy storage, temperature adjustment and self-power supply functions are integrated, and the energy-saving effect of a building is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of building energy conservation, and in particular to a self-powered energy storage and temperature-regulating concrete wall and a control method and a manufacturing method thereof. Background Art

[0002] In the field of building energy conservation, with the pursuit of sustainable development and low-carbon architecture, the development of building materials that efficiently utilize solar energy and possess energy storage and temperature regulation capabilities has become a research hotspot. Building energy consumption accounts for a large proportion of total energy consumption in society. As a clean and renewable energy source, the efficient use of solar energy is crucial for reducing building energy consumption. However, the intermittent and unstable nature of solar energy limits its continued application in buildings. Therefore, how to efficiently utilize solar energy and convert it into a storable and usable form of energy is one of the key challenges in current building energy conservation technology.

[0003] Currently, energy-saving technologies for building envelope structures primarily focus on the application of thermal insulation materials. In recent years, phase change materials (PCMs) have been increasingly used in wall components due to their ability to absorb and release latent heat within the phase change temperature range. By absorbing and releasing latent heat, PCMs can effectively regulate temperature fluctuations within buildings, improving thermal stability and comfort. Furthermore, thermoelectric materials (TEMs) are also being gradually incorporated into building materials. They utilize the Seebeck effect to directly convert temperature differences into electricity, providing auxiliary power support for buildings.

[0004] The inventors discovered the following deficiencies in the aforementioned related technologies: Conventional thermoelectric materials in existing technologies suffer from low thermoelectric efficiency and unstable power generation, making them incapable of meeting the continuous energy supply requirements of building operations. Furthermore, conventional phase-change materials are prone to leakage during packaging and use, and their thermal conductivity is low, limiting their practical application in buildings. Furthermore, existing technologies often employ phase-change materials and thermoelectric materials independently, failing to achieve synergistic optimization between the two, resulting in low solar energy utilization efficiency. Summary of the Invention

[0005] In order to achieve efficient utilization of solar energy, integration of energy storage and temperature regulation and self-power supply functions, and significantly improve the energy-saving effect of buildings, the present application provides a self-powered energy storage and temperature regulation concrete wall and its control method and manufacturing method.

[0006] In a first aspect, the present application provides a self-powered energy storage temperature-regulating concrete wall, which adopts the following technical solution:

[0007] A self-powered energy storage and temperature-regulating concrete wall, comprising:

[0008] The hollow frame is formed by 3D printing and has several through-channels inside;

[0009] Thermoelectric phase change material is poured into the pipe of the hollow frame. The thermoelectric phase change material is an ionic thermoelectric phase change hydrogel and contains at least two gel components with different phase change temperatures to form a temperature gradient control;

[0010] The thermoelectric functional structure includes an N-type thermoelectric material and a P-type thermoelectric material provided on the outer surface of the hollow frame or constituting the hollow frame body, wherein the N-type thermoelectric material and the P-type thermoelectric material are alternately arranged and connected in series through electrodes to form a closed thermoelectric circuit;

[0011] The opposing cement boards include a high-temperature board located outdoors and a low-temperature board located indoors. The high-temperature board and the low-temperature board are fixed to both sides of the hollow frame, and an electrode area is reserved on the surface of the board, and the electrode area is connected to the external terminal through a conductive material.

[0012] The insulating cement layer is poured on the hollow frame, the thermoelectric phase change hydrogel poured inside it, and the outside of the cement board to solidify the entire structure into one.

[0013] By adopting this technical solution, the wall utilizes a 3D-printed hollow frame and thermoelectric phase-change hydrogel, combined with a thermoelectric functional structure and an insulating cement layer, to achieve self-powered electricity and heat storage and temperature control. It efficiently utilizes the temperature difference between indoors and outdoors to generate electricity, while the phase-change material stores energy and regulates temperature, improving building energy efficiency. Its structural integration and stability are strong, and it has promising application prospects.

[0014] In a second aspect, the present application provides a control method, which adopts the following technical solutions:

[0015] A control method, applied to a self-powered energy storage temperature-controlled concrete wall, comprising:

[0016] The wall control system is activated to collect multi-source operating data along a preset monitoring path through a preset sensor matrix. The multi-source operating data includes the real-time temperature difference between the high-temperature plate and the low-temperature plate, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel.

[0017] Collect historical climate data of the area where the wall is located, perform standardized preprocessing on the historical climate data and multi-source operational data, and construct a spatiotemporal feature dataset;

[0018] The spatiotemporal feature dataset is input into a pre-built temperature difference prediction model to output the temperature difference prediction trend for a preset period of time in the future. Based on this trend, the graded heat release timing parameters of the thermoelectric phase change hydrogel are initially configured.

[0019] During the wall operation process, pre-processed multi-source operation data is obtained in real time to determine whether the temperature difference is lower than the preset control threshold;

[0020] If yes, the heat release control instruction is triggered to start the heat release of the corresponding components of the thermoelectric phase change hydrogel according to the preset priority, and the heat release rate of each component is corrected in real time through the dynamic adjustment algorithm to stabilize the temperature difference in the preset effective range;

[0021] If not, maintain the current heat release timing parameters and continue to monitor changes in multi-source operating data.

[0022] By employing this technical solution, the control method uses a sensor matrix to collect real-time wall operating data, combines it with historical climate data to predict temperature differences, and dynamically regulates the heat release of the thermoelectric phase-change hydrogel to ensure a stable wall temperature difference. This method improves the wall's temperature control accuracy and energy efficiency, enhances the system's intelligence and adaptability, and provides a highly effective solution for building energy conservation. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a method for manufacturing a self-powered energy storage and temperature-regulating concrete wall according to an embodiment of the present application.

[0024] Figure 2 It is a schematic diagram of an empty frame in an embodiment of the present application.

[0025] Figure 3 This is a schematic diagram of an embodiment of the present application in which a high-temperature panel and a low-temperature panel are installed on both sides of a hollow frame.

[0026] Figure 4 This is a schematic diagram of the series connection of N-type thermoelectric material and P-type thermoelectric material in the embodiment of the present application.

[0027] Figure 5 This is a schematic diagram of filling two gel materials with different phase transition temperatures in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The present application is further described in detail below with reference to the accompanying drawings.

[0029] Reference Figure 1 , is a method for manufacturing a self-powered energy storage temperature-regulating concrete wall disclosed in this application, comprising:

[0030] Step S1: forming a hollow frame by 3D printing, wherein the hollow frame has a plurality of through pipes inside.

[0031] Among them, 3D printing: a technology that creates three-dimensional objects by stacking materials layer by layer. Hollow frame: a frame structure with a cavity inside, used to fill materials. For details, please refer to Figure 2 Through-channel: A continuous channel inside the frame used for pouring phase change material.

[0032] 3D Printer: Choose an industrial-grade 3D printer suitable for printing high-temperature plastics or thermoelectric functional materials, such as an FDM or SLA printer. Printing materials: High-temperature plastics (such as PLA, PC) or thermoelectric composite materials (such as doped Bi2Te3).

[0033] The necessary steps are as follows: 1. Design the hollow frame model: Use CAD software to design a 3D model of the hollow frame, which should include several through-hole pipes. Pipe design should consider the fluidity and filling efficiency of the phase change material. Example: Design a cubic hollow frame with several parallel through-hole pipes. 2. Prepare a 3D printer and materials: Select an appropriate 3D printer and printing material based on the design model. For high-temperature resistant plastics, use an FDM printer and PLA material; for thermoelectric functional materials, use an industrial-grade 3D printer capable of printing composite materials. Example: Use an FDM printer, PLA material, and set the printing temperature to 210°C. 3. 3D Print the Hollow Frame: Import the designed 3D model into the 3D printer's slicing software and set printing parameters such as layer height and infill density. Start the 3D printer and begin printing the hollow frame. During printing, ensure that the material is evenly distributed and that the pipes remain hollow. Example: Set the layer height to 0.2mm, the infill density to 10%, and the printing speed to 60mm / s. 4. Post-processing: After printing is complete, perform post-processing on the hollow frame, such as removing support structures and cleaning residues inside the pipes to ensure smooth flow inside the pipes. Example: Use tweezers to remove support structures and use compressed air to clean residues inside the pipes.

[0034] Step S2, forming a thermoelectric functional structure: if the hollow frame material is a non-thermoelectric functional material, a coating containing N-type thermoelectric material and P-type thermoelectric material is provided on the outer surface of the hollow frame, so that the two materials are alternately arranged and connected in series through electrodes to form a closed thermoelectric loop; if the hollow frame material is a thermoelectric functional material, a hollow frame body containing N-type thermoelectric material and P-type thermoelectric material is directly formed by 3D printing, so that the two materials are alternately distributed inside the frame and connected in series through electrodes to form a closed thermoelectric loop.

[0035] Among them, the thermoelectric functional structure: a structure that uses the Seebeck effect to convert temperature difference into electrical energy, which is composed of N-type and P-type thermoelectric materials arranged alternately and connected in series through electrodes to form a closed loop. Figure 4 N-type thermoelectric material: A material with a negative Seebeck coefficient, where electrons are the charge carriers. P-type thermoelectric material: A material with a positive Seebeck coefficient, where holes are the charge carriers. Electrode series connection: Multiple thermoelectric units are connected via electrodes to form a closed circuit to increase the output voltage. Electrode material: Copper foil or silver glue is typically used to connect the thermoelectric materials and draw current.

[0036] The necessary procedures are described as follows:

[0037] 1. Select the thermoelectric material: If the hollow frame is made of a non-thermoelectric material (which can be a high-temperature plastic), spray a thermoelectric coating on the outer surface of the frame. If the hollow frame is made of a thermoelectric material, directly 3D print the hollow frame body containing N-type and P-type thermoelectric materials. For example, select commercially available Bi2Te3 (P-type) and Sb2Te3 (N-type) thermoelectric materials.

[0038] 2. Form the thermoelectric structure as follows: Spray the thermoelectric material coating: Use an electrostatic spray process to alternately spray N-type and P-type thermoelectric materials onto the outer surface of the hollow frame. The coating thickness is 30-80μm, ensuring a natural connection at the frame pipes and connection nodes to form a continuous thermoelectric path. For example, spray P-type Bi2Te3 and N-type Sb2Te3 materials onto the outer surface of the hollow frame, with a coating thickness of 50μm.

[0039] 3. 3D-Printed Thermoelectric Material Frame: 3D printing is used to directly print N-type and P-type thermoelectric materials into a hollow frame body, with a pre-set path for alternating distribution of the two materials. Example: 3D printing is used to directly form a hollow frame containing N-type and P-type thermoelectric materials to form an integrated thermocouple array.

[0040] 4. Electrode connection: Reserve electrode areas on both sides of the hollow frame and use copper foil or silver glue to lead the electrode areas to external terminals. Example: Reserve a 20mm x 30mm electrode area on the surface of the high-temperature plate and low-temperature plate. Use 100μm thick copper foil for welding or silver glue to connect thin copper wires and lead them to external terminals.

[0041] Step S3: pouring ionic thermoelectric phase-change hydrogel into the pipe of the hollow frame, where the hydrogel contains at least two gel components with different phase-change temperatures.

[0042] Among them, ionic thermoelectric phase-change hydrogels: a material that combines thermoelectric properties with phase-change energy storage functions, can absorb or release latent heat within a specific temperature range and possesses ionic conductivity, allowing it to participate in the thermoelectric conversion process. Ionic thermoelectric phase-change hydrogels: can be prepared through chemical synthesis methods or purchased from specialized material suppliers. For example, phase-change hydrogel materials containing ionically conductive components, such as poly (N-isopropylacrylamide) (PNIPAM)-based hydrogels, can be used.

[0043] Phase transition temperature: The temperature at which a material changes from solid to liquid or vice versa, absorbing or releasing a significant amount of latent heat. Infusion: Liquid material is injected into the hollow frame's pipes, filling the pipes and forming a continuous phase-change energy storage layer. Infusion primarily utilizes standard infusion equipment, such as syringe pumps or pressure infusion devices, to ensure uniform filling of the pipes.

[0044] The necessary procedures are described as follows:

[0045] 1. Prepare ionic thermoelectric phase change hydrogel: According to the design requirements, select or prepare ionic thermoelectric phase change hydrogel components containing at least two different phase transition temperatures. These components can absorb and release latent heat in different temperature ranges to form a temperature gradient control. See the filling diagram of two ionic thermoelectric phase change hydrogels with different phase transition temperatures for reference. Figure 5 Example: Select a hydrogel with a phase transition temperature of 35°C and a hydrogel with a phase transition temperature of 45°C to cope with the temperature difference between day and night.

[0046] 2. Hydrogel Infusion: Inject the prepared ionic thermoelectric phase change hydrogel into the hollow frame's tubes using an infusion device. Ensure the hydrogel is evenly distributed during the infusion process, avoiding bubbles and voids. Example: Use a syringe pump to slowly inject the hydrogel into the tubes at a rate of 10 ml / min to ensure uniform filling.

[0047] 3. Curing and Inspection: After pouring, allow the hydrogel to cure naturally or accelerate the curing process by heating. After curing, inspect the hydrogel filling within the pipe to ensure there are no leaks or unfilled areas. Example: Allow the poured frame to cure naturally at room temperature for 24 hours, or heat at 60°C for 2 hours. Afterward, inspect the hydrogel filling within the pipe.

[0048] In step S4, a high-temperature panel located outdoors and a low-temperature panel located indoors are fixed on both sides of the hollow frame, electrode areas are reserved on the surfaces of the high-temperature panel and the low-temperature panel, and the electrode areas are led out to external terminals through conductive materials.

[0049] Among them, high temperature board: located on the outdoor side, used to absorb solar heat and convert it into thermal energy. Low temperature board: located on the indoor side, used to maintain a lower temperature and form a temperature difference with the high temperature board. The settings of high temperature board and low temperature board can refer to Figure 3 Electrode area: The area used to connect to external circuits and draw out electrical energy, usually reserved on the surface of the cement board.

[0050] Cement board: Prefabricated cement board made of white cement or sulfoaluminate cement provides good thermal insulation and structural stability. Electrode material: Copper foil or silver glue is usually used to connect the thermoelectric material and draw out the current.

[0051] The necessary procedures are described as follows:

[0052] 1. Prepare cement boards: Prefabricate high-temperature and low-temperature boards according to design requirements. The high-temperature boards should have good light and heat absorption properties, while the low-temperature boards should have good thermal insulation properties. Example: Use white cement to prefabricate high-temperature and low-temperature boards with dimensions of 300mm × 300mm × 20mm.

[0053] 2. Fix the cement board: Fix the high-temperature and low-temperature panels to either side of the hollow frame. This can be done by adhesive or mechanical fastening, ensuring a tight fit between the cement board and the frame. Example: Use high-resistivity insulating cement to bond the high-temperature and low-temperature panels to either side of the hollow frame.

[0054] 3. Reserved Electrode Area: Reserve an electrode area on the surface of the high-temperature and low-temperature panels, typically 20mm x 30mm. The electrode area is used to connect the thermoelectric material and draw current. Example: Reserve a 20mm x 30mm electrode area on the surface of the high-temperature and low-temperature panels for subsequent welding or silver glue connection of the electrodes.

[0055] 4. Electrode Connection: Use copper foil or silver glue to connect the electrode area to the external terminal. Ensure the electrode connection is secure to avoid poor contact. Example: Use 100μm thick copper foil to solder or silver glue to connect a thin copper wire to the electrode area and lead it to the external terminal.

[0056] Step S5: Insulating cement is poured onto the hollow frame, the thermoelectric phase change hydrogel poured inside the hollow frame, and the outsides of the high-temperature plate and the low-temperature plate, and solidified to form a complete wall.

[0057] Insulating cement: A high-resistivity cement material used to prevent electrical leakage and provide structural stability. This material can be purchased from building material suppliers or prepared on demand. Foamed concrete or other high-resistivity cement materials are typically used.

[0058] Casting: The process of pouring a liquid material (such as cement) into a mold or structure and allowing it to solidify and take shape. Casting equipment: Standard casting tools such as mixers and casting molds are used.

[0059] The necessary procedures are described as follows:

[0060] 1. Prepare insulating cement: Select or prepare insulating cement with high resistivity according to design requirements. Ensure its resistivity is ≥10 8 Ω·cm to prevent current leakage. Example: Foam concrete is selected as insulating cement, and its resistivity is ≥10 8 Ω·cm.

[0061] 2. Pour the insulating cement: Pour the insulating cement evenly around the hollow frame, thermoelectric phase change hydrogel, and cement board. Ensure the cement is evenly filled during pouring to avoid air bubbles and voids. Example: After mixing the foam concrete evenly in a mixer, slowly pour it around the outside of the hollow frame, ensuring that the cement completely covers the frame, hydrogel, and cement board.

[0062] 3. Curing and Inspection: After pouring, allow the insulating cement to cure naturally or accelerate the curing process by heating. After curing, inspect the overall structure of the wall to ensure there are no cracks or unfilled areas. Example: Allow the poured wall to cure naturally at room temperature for 24 hours, or heat at 60°C for 2 hours, then inspect the overall structure of the wall.

[0063] The present application also provides a self-powered energy storage and temperature-regulating concrete wall manufactured by the above-mentioned manufacturing method, including a hollow frame, a thermoelectric phase change material, a thermoelectric functional structure, oppositely arranged cement boards and an insulating cement layer.

[0064] The hollow frame is formed by 3D printing and has several through-channels inside. These channels are filled with thermoelectric phase-change material, an ionic thermoelectric phase-change hydrogel containing at least two gel components with different phase-change temperatures to create a temperature gradient.

[0065] There are two implementation methods for the thermoelectric functional structure.

[0066] One embodiment is as follows: the thermoelectric functional structure is a thermoelectric material coating provided on the outer surface of the hollow frame, the thermoelectric material coating includes N-type thermoelectric material and P-type thermoelectric material, the thermoelectric material coating is formed by electrostatic spraying, has a thickness of 30-80 μm, and is naturally connected at the frame pipes and connection nodes to form a continuous thermoelectric path.

[0067] Another embodiment is as follows: the thermoelectric functional structure is composed of N-type thermoelectric material and P-type thermoelectric material constituting the hollow frame body, and a path in which the N-type thermoelectric material and the P-type thermoelectric material are alternately distributed is preset inside the hollow frame to form an integrated thermocouple array.

[0068] The opposing cement boards include a high-temperature board fixedly connected to one side of the hollow frame and located on the outdoor side, and a low-temperature board fixedly connected to the other side of the hollow frame and located on the indoor side. Electrode areas are reserved on the surfaces of the high-temperature board and the low-temperature board, and the electrode areas are led to external wiring terminals through conductive materials.

[0069] An insulating cement layer is poured on the hollow frame, the thermoelectric phase change hydrogel poured inside, and the outside of the cement board, and the insulating cement layer solidifies the entire structure into one.

[0070] The present application also provides a method for controlling a self-powered energy storage and temperature-regulating concrete wall, which is applied to a self-powered energy storage and temperature-regulating concrete wall, comprising:

[0071] Step S100: Start the wall control system and collect multi-source operation data along the preset monitoring path through the preset sensor matrix. The multi-source operation data includes the real-time temperature difference between the high-temperature plate and the low-temperature plate, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel.

[0072] Among them, the wall management and control system is an integrated intelligent system used to monitor and control the operating status of self-powered energy storage and temperature-controlled concrete walls in real time.

[0073] Sensor Matrix: A set of sensors distributed at different locations on the wall to collect operational data. Sensor Matrix: Uses multiple sensors, such as temperature sensors, voltage sensors, current sensors, etc., installed at key locations on the wall.

[0074] Multi-source operational data: includes the real-time temperature difference between the high-temperature and low-temperature panels, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel. Real-time temperature difference: The temperature difference between the high-temperature and low-temperature panels is a key parameter for thermoelectric conversion. Output electrical parameters: The voltage, current, and other electrical parameters output by the thermoelectric functional structure are used to evaluate thermoelectric conversion efficiency. Phase change state data: The phase change temperature, latent heat, and other data of the thermoelectric phase change hydrogel are used to evaluate the energy storage and release states of the phase change material.

[0075] The necessary procedures are described as follows:

[0076] 1. Start the wall control system: Turn on the power of the wall control system and start the data acquisition and processing modules. Example: Start the wall control system based on the embedded system and ensure that all modules are operating normally.

[0077] 2. Sensor Matrix Initialization: Check the connection status of the sensor matrix to ensure that all sensors are functioning properly. Example: Initialize the sensor matrix using temperature sensors (such as thermocouples) and electrical sensors (such as voltmeters and ammeters).

[0078] 3. Data Collection: Using pre-set monitoring paths, collect the real-time temperature difference between the high-temperature and low-temperature plates, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel. For example, collect the temperature difference between the high-temperature and low-temperature plates, use a voltmeter and ammeter to collect the output voltage and current of the thermoelectric functional structure, and use a temperature sensor to collect the phase change temperature of the phase change material.

[0079] 4. Data Transmission: The collected multi-source operating data is transmitted to the wall control system through the data acquisition system. Example: Using a wireless sensor network to transmit the collected data to the wall control system ensures the real-time and accuracy of the data.

[0080] 5. Data storage and preprocessing: The collected data is stored in the database of the wall control system and subjected to preliminary preprocessing, such as filtering and denoising. Example: Use a low-pass filter to filter the collected temperature difference data to remove high-frequency noise.

[0081] Step S200 , collecting historical climate data of the area where the wall is located, performing standardized preprocessing on the historical climate data and multi-source operation data, and constructing a spatiotemporal feature dataset.

[0082] Among them, historical climate data refers to meteorological data of the area where the wall is located over a period of time in the past, including information such as temperature, humidity, wind speed, and sunshine. Multi-source operation data refers to operation data collected from the wall sensor matrix, including the real-time temperature difference between the high-temperature plate and the low-temperature plate, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel. Standardization preprocessing refers to normalizing the data to make it have a unified scale to facilitate subsequent analysis and modeling. Spatiotemporal feature dataset refers to a dataset containing temporal and spatial information, which is used to build models and predictions.

[0083] The necessary procedures are described as follows:

[0084] 1. Collect historical climate data: Obtain historical climate data for the wall's area from a weather station or online weather data platform, including information such as temperature, humidity, wind speed, and sunshine. This data will provide environmental context for the wall's operation. For example, obtain the past five years of weather data from the National Meteorological Data Center, including daily maximum and minimum temperatures, humidity, wind speed, and sunshine duration.

[0085] 2. Data Standardization Preprocessing: Historical climate data and multi-source operational data are standardized to a uniform scale. This step typically uses the Min-Max normalization method to scale the data range to the [0, 1] range. This method eliminates dimensional differences between different data sources, facilitating subsequent analysis. For example, suppose the historical temperature data range is [10, 35] and the real-time temperature difference data range is [5, 20]. After Min-Max normalization, the data range is changed to [0, 1]. Specifically, the normalized value of each data point is equal to the difference between the point and the minimum value divided by the data range.

[0086] 3. Construct a spatiotemporal feature dataset: Integrate standardized historical climate data and multi-source operational data into a spatiotemporal feature dataset. This dataset contains not only temporal information (such as date and hour) but also spatial information (such as different wall locations). This helps subsequent models capture temporal and spatial variations. For example, construct a dataset where temporal features include date and hour, and spatial features include different wall locations (such as high-temperature panels and low-temperature panels). Feature data includes historical temperature, real-time temperature difference, thermoelectric output voltage, phase change material state, and more.

[0087] 4. Dataset Storage and Management: Store the constructed spatiotemporal feature dataset in a database to facilitate subsequent model training and prediction. This step can use a relational database (such as SQLite) or a non-relational database (such as MongoDB).

[0088] In step S300, the spatiotemporal feature dataset is input into a pre-built temperature difference prediction model, the temperature difference prediction trend for a preset time period in the future is output, and the graded heat release timing parameters of the thermoelectric phase change hydrogel are initially configured based on the trend.

[0089] The temperature difference prediction model, built based on historical and real-time data, is used to predict future temperature difference trends. The graded heat release timing parameters are pre-set based on the predicted temperature difference trends to optimize thermal energy management.

[0090] The necessary procedures are described as follows:

[0091] 1. Input the spatiotemporal feature dataset: The spatiotemporal feature dataset constructed in step S200 is input into the pre-built temperature difference prediction model. This data, including historical climate data and multi-source operational data, serves as model input. For example, the input dataset includes information such as temperature, humidity, wind speed, sunshine, and real-time wall temperature difference, voltage, and current for the past week.

[0092] 2. Model Prediction: The temperature difference prediction model outputs a predicted temperature difference trend for a preset time period (e.g., the next 24 hours) based on the input spatiotemporal feature dataset. This model can be a statistical linear regression model or a more complex neural network model. For example, the model predicts that the wall temperature difference will gradually decrease from 10°C to 5°C over the next 24 hours, then rise back to 8°C at night.

[0093] 3. Initially configure the graded heat release timing parameters: Based on the predicted temperature difference trend, the graded heat release timing parameters of the thermoelectric phase change hydrogel are initially configured. These parameters determine the heat release rate of the phase change material at different time periods to optimize thermal energy management and improve thermoelectric conversion efficiency. For example, according to the prediction, when the temperature difference is large during the day, the phase change material releases heat at a slower rate; when the temperature difference is small at night, the phase change material releases heat at a faster rate to maintain a stable temperature difference in the wall.

[0094] In step S400, during the operation of the wall, pre-processed multi-source operation data is obtained in real time to determine whether the temperature difference is lower than a preset control threshold. If yes, step S500 is executed; if not, step S600 is executed.

[0095] Multi-source operational data: This refers to operational data collected from the wall's sensor matrix, including the real-time temperature difference between the high- and low-temperature panels, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel. Preset control threshold: This is a pre-set temperature difference threshold used to determine whether the wall requires thermal energy control. Real-time acquisition: This refers to the continuous collection and processing of data during wall operation to monitor the wall's operating status in real time.

[0096] The necessary procedures are described as follows:

[0097] 1. Real-time Data Acquisition: During wall operation, the wall control system acquires pre-processed multi-source operational data in real time. This data includes the real-time temperature difference between the high-temperature and low-temperature panels, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel. For example, the wall control system collects the temperature difference between the high-temperature and low-temperature panels once a minute and the output voltage and current data of the thermoelectric functional structure once a second.

[0098] 2. Temperature Difference Determination: Based on the preset control threshold, determine whether the real-time temperature difference is below the threshold. The preset control threshold is set based on the wall design requirements and operational objectives, and is typically determined by historical data and experimental results. For example, if the preset control threshold is 5°C, the control mechanism is triggered when the real-time temperature difference is below 5°C.

[0099] 3. Execute the corresponding steps: If the real-time temperature difference is lower than the preset control threshold, execute step S500 to trigger the heat release control instruction. If the real-time temperature difference is not lower than the preset control threshold, execute step S600 to maintain the current heat release timing parameters. For example: If the real-time temperature difference is 4°C, which is lower than the preset control threshold of 5°C, the heat release control instruction is triggered and execute step S500. If the real-time temperature difference is 6°C, which is not lower than the preset control threshold of 5°C, the current heat release timing parameters are maintained and execute step S600.

[0100] Step S500, triggering the heat release control instruction, starting the corresponding components of the thermoelectric phase change hydrogel to release heat according to the preset priority, and correcting the heat release rate of each component in real time through the dynamic adjustment algorithm to stabilize the temperature difference in the preset effective range.

[0101] Among them, the heat release control instruction: When the temperature difference falls below the preset control threshold, the instruction is triggered to start the heat release process of the thermoelectric phase change hydrogel. The preset priority: The priority order set according to the wall design requirements and operational objectives is used to determine which thermoelectric phase change hydrogel components release heat first. The dynamic adjustment algorithm: An algorithm that adjusts the heat release rate of the thermoelectric phase change hydrogel in real time to maintain a stable temperature difference in the wall. The preset effective range: A pre-set temperature difference target range used to ensure the wall's thermoelectric conversion efficiency and thermal energy management.

[0102] The necessary procedures are described as follows:

[0103] 1. Triggering a heat release control command: When the real-time temperature difference falls below the preset control threshold, the wall control system triggers a heat release control command, initiating the heat release process of the thermoelectric phase change hydrogel. Example: If the real-time temperature difference is 4°C, which is 5°C below the preset control threshold, the wall control system triggers a heat release control command.

[0104] 2. Activate heat release according to preset priority: Heat release is activated for the corresponding components of the thermoelectric phase change hydrogel according to the preset priority. Priority is typically set based on the phase change temperature and thermoelectric properties of the phase change material. For example, if the preset priority is to activate heat release for components with lower phase change temperatures before those with higher phase change temperatures, for example, if components have phase change temperatures of 30°C and 40°C, the component with 30°C will be activated first.

[0105] 3. Dynamically Adjust Heat Release Rate: A dynamic adjustment algorithm is used to adjust the heat release rate of each component in real time to maintain the wall's temperature differential within a preset effective range. The algorithm dynamically adjusts the heat release rate based on the real-time temperature differential and the preset target range. For example, based on a real-time temperature differential of 4°C and the preset effective range of [5°C, 10°C], the dynamic adjustment algorithm adjusts the heat release rate of a component with a phase change temperature of 30°C to 2°C per hour to maintain a stable temperature differential.

[0106] Among them, the dynamic adjustment algorithm uses a simple proportional-integral-differential (PID) controller to dynamically adjust the heat release rate of the thermoelectric phase change hydrogel according to the difference between the real-time temperature difference and the preset effective range.

[0107] Example: Assuming the real-time temperature difference is 4°C, which is 5°C lower than the lower limit of the preset effective range [5°C, 10°C], the PID controller calculates the heat release rate that needs to be increased and adjusts the heat release rate of the component with a phase change temperature of 30°C to 2°C per hour to maintain a stable temperature difference.

[0108] Step S600: maintaining the current heat release timing parameters and continuously monitoring the changes in multi-source operating data.

[0109] The heat release timing parameters refer to the time series parameters of the thermoelectric phase change hydrogel's heat release, which are used to control the heat release rate of the phase change material over different time periods. Multi-source operational data refers to operational data collected from the wall sensor matrix, including the real-time temperature difference between the high-temperature and low-temperature panels, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel.

[0110] The necessary procedures are described as follows:

[0111] 1. Maintain current heat release timing parameters: When the real-time temperature difference is no less than the preset control threshold, the current heat release timing parameters of the thermoelectric phase change hydrogel are maintained unchanged. These parameters are determined based on the previously used temperature difference prediction model and dynamic adjustment algorithm. For example, the current heat release timing parameters are set to release heat at a rate of 1°C per hour for a component with a phase change temperature of 30°C during the day and 2°C per hour for a component with a phase change temperature of 40°C at night. When the real-time temperature difference is 6°C, which is 5°C higher than the preset control threshold, the current heat release timing parameters are maintained unchanged.

[0112] 2. Continuously monitor changes in multi-source operational data: The wall control system continuously collects multi-source operational data in real time, including the real-time temperature difference between the high-temperature and low-temperature panels, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel. For example, the wall control system collects the temperature difference data between the high-temperature and low-temperature panels once a minute and the output voltage and current data of the thermoelectric functional structure once a second to continuously monitor the wall's operating status.

[0113] 3. Dynamic Adjustment Preparation: Even if the current temperature difference is within the preset effective range, the wall control system must be prepared to dynamically adjust based on new data. This includes continuous monitoring of the temperature difference and dynamic correction of heat release timing parameters. For example, if the temperature difference begins to decrease and approaches the preset control threshold, the wall control system will be prepared to trigger the heat release control command and adjust the heat release rate to maintain a stable temperature difference.

[0114] Based on this trend, the initial configuration of the graded heat release timing parameters of the thermoelectric phase change hydrogel includes:

[0115] Step S301 : matching a preset thermoelectric phase change hydrogel temperature gradient combination according to the climate type of the area where the wall is located, where the thermoelectric phase change hydrogel temperature gradient combination includes at least two gel components with different phase change temperatures.

[0116] Climate type refers to the climatic characteristics of the region where the wall is located, such as tropical, temperate, or frigid. Different climate types have different temperature variations. Thermoelectric phase-change hydrogel temperature gradient combination refers to a combination of at least two gel components with different phase transition temperatures, designed to accommodate varying temperature variations. Thermoelectric phase-change hydrogel temperature gradient combination is preset based on the wall's design requirements and operational objectives, typically determined based on experimental data and theoretical calculations.

[0117] Phase transition temperature: refers to the temperature point at which a material changes from solid to liquid or from liquid to solid, at which point the material absorbs or releases a large amount of latent heat.

[0118] The necessary procedures are described as follows:

[0119] 1. Determine the climate type: Based on the wall's geographic location and meteorological data, determine the area's climate type. This step can be accomplished by consulting meteorological data or using GIS tools. For example, the wall is located between 30° and 60° north latitude, with an average annual temperature between 0°C and 30°C, and exhibits distinct seasonal variations. Therefore, the climate type is matched to a temperate zone. Using GIS tools, you can precisely determine the wall's geographic location and climate characteristics, ensuring accurate matching.

[0120] 2. Matching a preset thermoelectric phase change hydrogel temperature gradient combination: Based on the determined climate type, select a preset thermoelectric phase change hydrogel temperature gradient combination. This preset combination typically contains at least two gel components with different phase transition temperatures to accommodate varying temperature variations. For example, for a temperate climate, select thermoelectric phase change hydrogel components with phase transition temperatures of 25°C and 35°C. The 25°C component is used to cope with high summer temperatures, while the 35°C component is used to cope with low winter temperatures. This combination effectively manages temperature variations in the wall across different seasons, ensuring optimized thermoelectric conversion efficiency and thermal energy management.

[0121] The specific matching process can use a simple rules engine to match the wall's location and meteorological data to a preset climate type. Rules can be based on characteristics such as location, average temperature, and seasonal variations. For example, if the wall is located between 30° and 60° north latitude and the annual average temperature is between 0°C and 30°C, it matches the temperate climate type. Based on this, a thermoelectric phase change hydrogel component with phase transition temperatures of 25°C and 35°C is selected to adapt to the temperature changes required by different seasons.

[0122] Step S302 : extracting cooling features based on the temperature difference prediction trend, including the cooling start stage, the cooling rate change stage and the low temperature stabilization stage.

[0123] Among them, the temperature difference prediction trend: the temperature difference change trend between the high-temperature panel and the low-temperature panel of the wall within the preset future period output by the temperature difference prediction model. Cooling characteristics: the key features extracted from the temperature difference prediction trend, including the cooling start stage, the cooling rate change stage and the low-temperature stabilization stage, which are used to describe the dynamic process of temperature difference change. Cooling start stage: the time point when the temperature difference begins to decrease and the initial temperature difference value. Cooling rate change stage: the time period when the temperature difference decrease rate changes, which may include acceleration or deceleration stages. Low-temperature stabilization stage: the time period when the temperature difference reaches a low level and remains relatively stable.

[0124] The necessary procedures are described as follows:

[0125] 1. Obtain temperature difference forecast trends: Obtain temperature difference trends within a preset future time period from the temperature difference forecast model. This trend is typically presented as time series data. For example, the temperature difference forecast model output indicates that the wall temperature difference will gradually decrease from 10°C to 5°C over the next 24 hours, then rise back to 8°C at night.

[0126] 2. Identify the start of the temperature drop: Identify the time point when the temperature difference begins to decrease and the initial temperature difference value. This can be achieved by detecting the first drop point in the temperature difference time series. Example: From the temperature difference forecast trend, identify the start of the temperature drop at the third hour, with an initial temperature difference of 10°C.

[0127] 3. Extracting Cooling Rate Change Phases: Identify time periods where the temperature difference rate of decrease changes, which may include acceleration or deceleration phases. This can be achieved by calculating the time derivative of the temperature difference rate of change. Example: From the temperature difference forecast trend, identify that the cooling rate begins to accelerate at the 6th hour, increasing from 0.5°C per hour to 1°C per hour, and begins to decelerate at the 12th hour, dropping to 0.5°C per hour.

[0128] 4. Identify the low-temperature stable phase: Identify periods of time when the temperature difference reaches a low level and remains relatively stable. This can be achieved by detecting periods of time when the rate of change of the temperature difference is close to zero. Example: From the temperature difference forecast trend, it can be identified that the low-temperature stable phase begins at the 18th hour, with the temperature difference stabilizing at around 5°C.

[0129] The above process can be applied to the cooling feature extraction algorithm. This algorithm uses the differential method to calculate the temperature difference rate of change and identify the cooling start point and rate change point. To identify the low-temperature stable phase, a threshold can be set. When the temperature difference rate of change falls below this threshold, the system is considered to have entered the low-temperature stable phase. For example, a temperature difference rate of change threshold of 0.1°C / hour is set. When the rate of change falls below this threshold, the system is considered to have entered the low-temperature stable phase. By calculating the first-order difference of the temperature difference time series, the cooling start point and rate change phase can be identified.

[0130] Step S303 : setting a preset start priority for the gel components in the temperature gradient combination according to different cooling characteristic stages.

[0131] Among them, the cooling characteristic stage: the key characteristic stage extracted from the temperature difference prediction trend, including the cooling start stage, the cooling rate change stage and the low-temperature stabilization stage. The temperature gradient combination: contains at least two thermoelectric phase change hydrogel components with different phase transition temperatures, which are used to adapt to different temperature change requirements. Gel component: a thermoelectric phase change hydrogel material with a specific phase transition temperature, which is used to release or absorb heat at a specific temperature. Preset startup priority: based on the cooling characteristic stage, the pre-set gel component startup order is used to optimize thermal energy management.

[0132] The necessary procedures are described as follows:

[0133] 1. Analyze cooling characteristic stages: Based on the cooling characteristic stages extracted in step S302, analyze the characteristics and requirements of each stage. This includes the cooling start stage, the cooling rate change stage, and the low-temperature stabilization stage. For example, the cooling characteristic stages extracted from the temperature difference prediction trend are as follows: Cooling start stage: At the third hour, the initial temperature difference is 10°C. Cooling rate change stage: Starting at the sixth hour, the temperature drops by 1°C per hour; starting at the 12th hour, the temperature drops by 0.5°C per hour. Low-temperature stabilization stage: Starting at the 18th hour, the temperature difference stabilizes at around 5°C.

[0134] 2. Set Preset Activation Priorities: Based on the characteristics of the cooling profile, set preset activation priorities for the gel components in the temperature gradient combination. Priorities are typically set based on the phase transition temperature and cooling rate to ensure appropriate heat release at different stages. For example, for a temperate climate, select thermoelectric phase-change hydrogel components with phase transition temperatures of 25°C and 35°C. At the start of the cooling phase (hour 3), activate the component with a phase transition temperature of 35°C to quickly respond to the decreasing temperature differential. During the cooling rate variation phase (hours 6 to 12), activate the component with a phase transition temperature of 25°C to respond to the accelerated cooling. During the low-temperature stabilization phase (hour 18), maintain the component with a phase transition temperature of 25°C to maintain a stable temperature differential. Prioritization rules can be used to set activation priorities for gel components based on the characteristics of the cooling profile. Rules can be based on phase transition temperature, cooling rate, and target temperature differential range.

[0135] 3. Verify priority settings: Use simulations or experiments to verify that the set startup priorities meet the climate characteristics and operational requirements of the wall area. For example, by simulating temperature fluctuations throughout the year, verify that the set startup priorities can provide stable thermoelectric conversion efficiency across the seasons. If the simulation results show that the temperature difference can be effectively managed during both the hot summer and cold winter periods, the priority settings are considered appropriate.

[0136] Step S304: dynamically configuring the preset heat release parameters of each component according to the predicted cooling rate.

[0137] Cooling rate: The rate at which the temperature difference changes over time, usually expressed as the temperature drop per hour.

[0138] Preset heat release parameters: The heat release rate and duration of the thermoelectric phase change hydrogel component are pre-set based on the wall design requirements and operational objectives. Dynamic configuration: Based on real-time data and prediction results, the heat release parameters of the thermoelectric phase change hydrogel component are adjusted in real time to adapt to different temperature changes.

[0139] The necessary procedures are described as follows:

[0140] 1. Obtain the predicted cooling rate: The predicted cooling rate is obtained from the cooling characteristic phases extracted in step S302. This includes rate data for the cooling start phase, the cooling rate change phase, and the low-temperature stabilization phase. Example: The predicted cooling rate is as follows: Cooling start phase (3rd hour): Initial temperature difference of 10°C, beginning to decrease. Cooling rate change phase (6th to 12th hour): Decrease by 1°C per hour, then decelerate to 0.5°C per hour. Low-temperature stabilization phase (18th hour): Temperature difference stabilizes at approximately 5°C.

[0141] 2. Dynamically configure the preset heat release parameters of each component: Based on the predicted cooling rate, the heat release parameters of the thermoelectric phase change hydrogel component are dynamically adjusted. This includes the heat release rate and duration to ensure the appropriate amount of heat is released at different stages to maintain a stable temperature difference in the wall. For example: During the initial cooling phase (hour 3), the component with a phase change temperature of 35°C is activated at a heat release rate of 2°C per hour to quickly respond to the decreasing temperature difference. During the cooling rate variation phase (hours 6 to 12), the component with a phase change temperature of 25°C is adjusted to a heat release rate of 1.5°C per hour to accommodate the accelerated cooling. During the low-temperature stabilization phase (hour 18), the component with a phase change temperature of 25°C is maintained at a heat release rate of 1°C per hour to maintain a stable temperature difference.

[0142] 3. Real-time Adjustment and Optimization: The wall control system monitors temperature differentials in real time and dynamically adjusts heat release parameters based on the difference between the actual cooling rate and the predicted value. This can be achieved using a PID controller or other intelligent algorithm to ensure that the temperature differential remains within a preset effective range. For example, if the actual cooling rate is faster than the predicted value, the wall control system can increase the heat release rate to mitigate the temperature differential drop; if the actual cooling rate is slower than the predicted value, the heat release rate can be appropriately reduced to avoid excessive heat release. Assuming the preset effective temperature differential range is [5°C, 10°C], the PID controller dynamically adjusts the heat release rate based on the difference between the actual temperature differential and the target range. If the actual temperature differential approaches the lower limit of 5°C, the controller increases the heat release rate; if the actual temperature differential approaches the upper limit of 10°C, the controller reduces the heat release rate.

[0143] Step S305 , integrating the activation priority and the heat release parameters to form an initial heat release timing benchmark adapted to the regional climate and temperature difference trend.

[0144] Based on the integrated activation priorities and heat release parameters, a benchmark for initial heat release timing is generated to match the climate and temperature variations in the area where the wall is located. This benchmark will serve as a guide for the heat release behavior of the thermoelectric phase change hydrogel component.

[0145] Example: Hours 0-3: No heat release, temperature difference maintained at 10°C. Hours 3-6: Activate a component with a phase transition temperature of 35°C, release heat at a rate of 2°C per hour, and the temperature difference drops from 10°C to 8°C.

[0146] Hours 6-12: Start the component with a phase transition temperature of 25°C, release heat at a rate of 1.5°C per hour, and reduce the temperature difference from 8°C to 6°C. Hours 12-18: Maintain the component with a phase transition temperature of 25°C, release heat at a rate of 1°C per hour, and maintain the temperature difference at 6°C. Hours 18-24: Maintain the component with a phase transition temperature of 25°C, release heat at a rate of 1°C per hour, and maintain the temperature difference at 5°C.

[0147] The dynamic adjustment algorithm is used to correct the heat release rate of each component in real time to stabilize the temperature difference within the preset effective range, including:

[0148] Step S501 , collecting dynamic control data, the dynamic control data including the real-time temperature difference between the high temperature plate and the low temperature plate, the residual latent heat of each thermoelectric phase change hydrogel component, the thermoelectric output power, and the preset graded heat release timing parameters.

[0149] Dynamic control data: Data used to monitor and adjust the wall's operating status in real time, including real-time temperature difference, residual latent heat, thermoelectric output power, and graded heat release timing parameters. Real-time temperature difference: The instantaneous temperature difference between the high-temperature and low-temperature panels. Residual latent heat: The unreleased latent heat energy of each thermoelectric phase change hydrogel component. Thermoelectric output power: The instantaneous electrical energy output generated by the wall's thermoelectric conversion.

[0150] Graded heat release timing parameters: preset time series and rate parameters for heat release of thermoelectric phase change hydrogel components.

[0151] The necessary procedures are described as follows:

[0152] 1. Collect real-time temperature difference: Use the temperature sensor in the wall control system to collect real-time temperature difference data between the high-temperature panel and the low-temperature panel. Example: Collect temperature difference data once a minute and record the current temperature difference as 8°C.

[0153] 2. Calculate the residual latent heat: Use the energy monitoring module in the wall control system to calculate the residual latent heat of each thermoelectric phase change hydrogel component. For example, the residual latent heat of the component with a phase change temperature of 25°C is calculated to be 50 J / g, and the residual latent heat of the component with a phase change temperature of 35°C is calculated to be 30 J / g.

[0154] 3. Collecting Thermoelectric Output Power: The power sensor in the wall control system collects the wall's thermoelectric output power in real time. Example: Collect the thermoelectric output power once per second and record the current output power as 0.5W.

[0155] 4. Obtaining the tiered heat release timing parameters: Obtain the tiered heat release timing parameters from the preset parameter library of the wall control system. These parameters include the activation priority and heat release rate of each component. For example, obtaining the preset tiered heat release timing parameters: the component with a phase change temperature of 25°C has a priority of 1 and a heat release rate of 1.5°C per hour; the component with a phase change temperature of 35°C has a priority of 2 and a heat release rate of 2°C per hour.

[0156] In step S502, a multi-objective optimization model is constructed based on the preset startup priority. Temperature difference stability, power generation efficiency, and material life are set as core objectives and assigned preset weights. A preset reward coefficient is given to the latent heat reserve strategy that adapts to the regional climate, and a preset penalty coefficient is applied to excessive heat release that violates the preset cooling stage.

[0157] Preset activation priority: The activation order of the thermoelectric phase-change hydrogel components is pre-set based on the climate characteristics and temperature variation patterns of the wall area. This is determined by analyzing historical climate data (such as temperature variation patterns) and experimental data for the wall area, combined with the wall design requirements, to determine the activation order of the different phase-change temperature components.

[0158] Multi-objective optimization model: A mathematical model that comprehensively considers multiple optimization objectives (such as temperature difference stability, power generation efficiency, and material lifespan). By weighing the relationships between these objectives, it finds the optimal heat release strategy. Acquisition method: Constructed based on wall operating data (such as real-time temperature difference, thermoelectric output power, and residual latent heat of the material), the model is solved using optimization algorithms (such as genetic algorithms and particle swarm optimization algorithms). Temperature difference stability: Measures the stability of the temperature difference between the high- and low-temperature panels of the wall. The goal is to maintain the temperature difference within a preset effective range (e.g., [5°C, 10°C]). Acquisition method: Temperature sensors in the wall control system collect real-time temperature difference data between the high- and low-temperature panels, calculating the rate of change of the temperature difference and stability indicators. Power generation efficiency: The efficiency of the electrical energy output generated by the wall's thermoelectric conversion. The goal is to maximize the thermoelectric output power. Acquisition method: Power sensors collect the wall's thermoelectric output power in real time and calculate the power generation efficiency based on the wall's design parameters.

[0159] Material life: The service life of key materials such as thermoelectric phase change hydrogels. The goal is to reduce material loss and extend service life by reasonably controlling the heat release process. Acquisition method: Calculate the residual latent heat of each thermoelectric phase change hydrogel component through the energy monitoring module, and evaluate the material life in combination with the material performance decay model. Reward coefficient: Bonus points are given to latent heat reserve strategies that meet the regional climate characteristics, encouraging optimization strategies to match climatic conditions. Acquisition method: Set according to the climatic characteristics of the area where the wall is located and the preset temperature difference control strategy. Penalty coefficient: Deduction points are given for excessive heat release that violates the preset cooling stage, to avoid excessive heat release causing the temperature difference to drop too quickly or damage the material performance. Acquisition method: Set according to the climatic characteristics of the area where the wall is located and the preset temperature difference control strategy.

[0160] The necessary process is as follows:

[0161] 1. Objective Function Construction: The objective function takes temperature difference stability, power generation efficiency, and material lifespan as core objectives and assigns preset weights (e.g., a weight of 0.4 for temperature difference stability, 0.3 for power generation efficiency, and 0.3 for material lifespan). Furthermore, a latent heat reserve strategy that meets regional climate characteristics is rewarded with a coefficient of 1.2, while excessive heat release is penalized with a coefficient of 0.8. Example formula: Optimization objective = 0.4 × temperature difference stability + 0.3 × power generation efficiency + 0.3 × material lifespan + 1.2 × reward − 0.8 × penalty.

[0162] 2. Data acquisition and input: 1. Real-time temperature difference: The temperature difference data between the high-temperature plate and the low-temperature plate is collected through the temperature sensor in the wall control system. 2. Residual latent heat: The residual latent heat of each thermoelectric phase change hydrogel component is calculated through the energy monitoring module. 3. Thermoelectric output power: The thermoelectric output power of the wall is collected through the power sensor. 4. Preset parameters: The graded heat release timing parameters, including the startup priority and heat release rate of each component, are obtained from the preset parameter library of the wall control system. Example: Assume that the real-time temperature difference is 8°C, the residual latent heat of the component with a phase change temperature of 25°C is 50J / g, the residual latent heat of the component with a phase change temperature of 35°C is 30J / g, and the thermoelectric output power is 0.5W.

[0163] 3. Optimization Model Solution: 1. Optimization Algorithm: A genetic algorithm was selected to solve the multi-objective optimization model. The genetic algorithm iteratively optimizes heat release parameters by simulating the process of natural selection. For example, suppose the initial heat release rate is 1.5°C / hour for the component with a phase transition temperature of 25°C and 2°C / hour for the component with a phase transition temperature of 35°C. After genetic algorithm optimization, the rate is adjusted to 1.2°C / hour for the component with a phase transition temperature of 25°C and 1.8°C / hour for the component with a phase transition temperature of 35°C, achieving a better balance between temperature difference stability, power generation efficiency, and material lifespan.

[0164] 4. Real-time Adjustment and Feedback: Dynamic Adjustment: Based on real-time data collected and the results of the optimization model, the heat release rate of each component is dynamically adjusted. For example, if the real-time temperature difference approaches the lower limit of 5°C, the heat release rate is increased; if it approaches the upper limit of 10°C, the heat release rate is reduced. Feedback Mechanism: The wall management and control system monitors the optimization results in real time, and the optimization model is corrected and adjusted based on actual operating data.

[0165] For example, during operation, it is discovered that the heat release rate of a component with a phase transition temperature of 25°C is too fast, causing the temperature difference to drop to 6°C, approaching the preset control threshold of 5°C. In this case, a penalty coefficient of 0.8 is applied, and the heat release rate of this component is dynamically adjusted to 1°C per hour to maintain a stable temperature difference.

[0166] Step S503: Generate a graded heat release dynamic adaptation strategy based on the multi-objective optimization model and dynamic control data.

[0167] The necessary procedures are described as follows:

[0168] 1. Data collection and input:

[0169] Process: Sensors in the wall control system collect real-time dynamic control data, including the real-time temperature difference between the high-temperature and low-temperature panels, the residual latent heat of each thermoelectric phase-change hydrogel component, the thermoelectric output power, and preset graded heat release timing parameters. Example: Real-time temperature difference: 8°C; Residual latent heat of the component with a phase change temperature of 25°C: 50 J / g; Residual latent heat of the component with a phase change temperature of 35°C: 30 J / g; Thermoelectric output power: 0.5 W; Preset graded heat release timing parameters: Component with a phase change temperature of 25°C has priority 1 and a heat release rate of 1.5°C per hour; Component with a phase change temperature of 35°C has priority 2 and a heat release rate of 2°C per hour.

[0170] 2. The multi-objective optimization model is solved as follows:

[0171] Process: The collected dynamic control data is input into a multi-objective optimization model, and an optimization algorithm (such as a genetic algorithm) is used to determine the optimal heat release strategy. Example: Assume the optimization model's objective function is: Optimization objective = 0.4 × temperature difference stability + 0.3 × power generation efficiency + 0.3 × material life. After genetic algorithm optimization, the heat release rate of the component with a phase transition temperature of 25°C is adjusted to 1.2°C per hour, and the heat release rate of the component with a phase transition temperature of 35°C is adjusted to 1.8°C per hour.

[0172] 3. Generate a dynamic adaptation strategy for graded heat release:

[0173] Process: Based on the optimization model results, a graded heat release dynamic adaptation strategy is generated to dynamically adjust the heat release rate and duration of each component. Example: During the initial cooling phase (hour 3), the component with a phase transition temperature of 35°C is activated at a heat release rate of 2°C per hour. During the cooling rate variation phase (hours 6 to 12), the component with a phase transition temperature of 25°C is adjusted to a heat release rate of 1.5°C per hour. During the low-temperature stabilization phase (hour 18), the component with a phase transition temperature of 25°C is maintained at a heat release rate of 1°C per hour.

[0174] In step S504, the heat release rate of each thermoelectric phase change hydrogel component is adjusted according to the graded heat release dynamic adaptation strategy through a dynamic adjustment algorithm to correct the deviation and ensure that the temperature difference is stable within a preset effective range.

[0175] The necessary steps are as follows: 1. Initialize the algorithm: Set PID parameters (e.g., P=1.0, I=0.1, D=0.05). 2. Collect data: Collect temperature difference data in real time (e.g., current temperature difference is 8°C). 3. Calculate deviation: Compare the current temperature difference with the target range (e.g., target 7.5°C) and calculate the deviation (e.g., deviation 0.5°C). 4. Adjust the heat release rate: Adjust the heat release rate based on the deviation: High temperature difference (e.g., 8°C > 7.5°C): Reduce the heat release rate. Low temperature difference (e.g., 6°C < 7.5°C): Increase the heat release rate. Example: For a component with a phase change temperature of 25°C: Adjust the heat release rate from 1.2°C per hour to 1.0°C (high temperature difference) or 1.4°C (low temperature difference).

[0176] Phase change temperature 35°C component: Adjust from 1.8°C per hour to 1.6°C (high temperature difference) or 2.0°C (low temperature difference). 5. Feedback correction: Monitor temperature difference changes and calibrate the algorithm based on actual data to ensure that the temperature difference remains stable within the preset range.

[0177] In step S505, the regulated data is fed back to the management and control system, and the comprehensive benefits are calculated using a multi-objective optimization model. When the preset standards are reached, the preset graded heat release timing parameters are updated to form a closed-loop control.

[0178] Comprehensive benefit: The overall benefit after considering multiple optimization objectives, such as temperature differential stability, power generation efficiency, and material lifespan. This benefit is calculated using a multi-objective optimization model and assigned using preset weights. Preset standard: A pre-set comprehensive benefit threshold used to determine whether to update the graded heat release timing parameters. This threshold is determined based on the wall's design requirements and operational objectives, typically through experimental data and historical operational data. Closed-loop control: This data is fed back to the control system through a real-time feedback mechanism, allowing for dynamic adjustments based on the comprehensive benefit assessment results.

[0179] In step S505, the regulated data (including temperature difference, heat release rate, thermoelectric output power, etc.) is fed back to the wall management and control system. Based on this data, the management and control system calculates the comprehensive benefit using a multi-objective optimization model. The formula for comprehensive benefit is: Comprehensive benefit = 0.4 × temperature difference stability + 0.3 × power generation efficiency + 0.3 × material life. If the calculated comprehensive benefit meets or exceeds a preset standard (for example, 0.8), the preset graded heat release timing parameters are updated. For example, the heat release rate of the component with a phase transition temperature of 25°C is adjusted from 1.2°C per hour to 1.3°C, and the heat release rate of the component with a phase transition temperature of 35°C is adjusted from 1.8°C per hour to 1.9°C. The updated parameters are reapplied to the wall management and control system for continued real-time monitoring and regulation, forming a closed-loop control system to ensure efficient and stable wall operation.

[0180] A method for controlling a self-powered energy storage temperature-regulating concrete wall further includes the following steps after initially configuring the graded heat release timing parameters of the thermoelectric phase change hydrogel based on the trend:

[0181] In step Sa00, a thermal resistance monitoring data set is formed by combining multi-source operation data with graded heat release timing parameters.

[0182] Thermal resistance monitoring data set: A data set used to monitor wall thermal resistance, formed by combining multi-source operating data and graded heat release timing parameters.

[0183] In step Sa00, the wall control system collects real-time multi-source operational data, including the real-time temperature difference between the high-temperature and low-temperature panels, thermoelectric output power, and the phase change state of the thermoelectric phase-change hydrogel. Simultaneously, it obtains graded heat release timing parameters from a preset parameter library and integrates these data with the multi-source operational data to form a thermal resistance monitoring dataset. For example, the real-time temperature difference is 8°C, the thermoelectric output power is 0.5W, the residual latent heat of the component with a phase change temperature of 25°C is 50J / g, the residual latent heat of the component with a phase change temperature of 35°C is 30J / g, the heat release rate of the component with a phase change temperature of 25°C is 1.2°C / hour, and the heat release rate of the component with a phase change temperature of 35°C is 1.8°C / hour. This data is integrated and stored in the wall control system's database, providing the foundation for the subsequent thermal-electric coupled simulation model.

[0184] In step Sb00, a thermal-electrical coupling simulation model is established based on the initial heat release timing benchmark, the thermal resistance monitoring data set is connected to calibrate the parameters, a digital twin is constructed, and heat flow and thermal resistance simulation results with preset normal thresholds are generated.

[0185] Among them, the thermal-electric coupling simulation model: a simulation model that comprehensively considers the heat transfer and electrical energy conversion processes, used to simulate the thermoelectric performance of the wall. Acquisition method: constructed based on physical equations and wall structural parameters, implemented through simulation software (such as COMSOL Multiphysics or ANSYS). Thermal resistance monitoring data set: a data set for monitoring the thermal resistance of the wall formed by combining multi-source operation data and graded heat release timing parameters. Acquisition method: integrating multi-source operation data and graded heat release timing parameters through a data acquisition system. Digital twin: a virtual digital model of the wall, reflecting the physical state and performance of the wall in real time. Acquisition method: constructed through calibration of the simulation model and real-time data. Preset normal threshold: a pre-set normal range value of heat flow and thermal resistance, used to determine whether the wall is operating normally. Acquisition method: set according to wall design requirements and historical operation data.

[0186] The necessary process is described as follows: In step Sb00, a coupled thermal-electrical simulation model is first established, based on the initial heat release time series benchmark. This model comprehensively considers the heat transfer and electrical energy conversion processes within the wall. It is constructed based on physical equations and wall structural parameters and implemented using simulation software such as COMSOL Multiphysics. Next, multi-source operational data from the thermal resistance monitoring dataset (such as real-time temperature difference, heat release rate, and thermoelectric output power) is integrated into the simulation model to calibrate model parameters and ensure model accuracy and reliability. Using the calibrated simulation model, a digital twin of the wall is constructed, reflecting its physical state and performance in real time. Finally, simulation results for heat flux and thermal resistance are generated, including preset normal thresholds, providing a basis for subsequent anomaly detection. For example, the normal thresholds for heat flux are set to [0.4, 0.6] W / m², and the normal thresholds for thermal resistance are set to [0.05, 0.15] K·m² / W. These thresholds are determined based on wall design requirements and historical operational data and are used to determine whether the wall is operating normally.

[0187] In step Sc00, the multi-source operating data in the thermal resistance monitoring data set is compared with the simulation results. If the local thermal resistance exceeds the preset normal threshold, the temperature difference deviates from the preset effective range and the mutation exceeds the preset amplitude, and the output electrical parameter deviates from the stable range, it is determined to be a thermal resistance anomaly, the abnormal location is marked in the BIM system, and an early warning is triggered.

[0188] The necessary process is described as follows: In step Sc00, the multi-source operational data in the thermal resistance monitoring dataset (such as real-time temperature difference, thermoelectric output power, and heat release rate of the phase-change hydrogel) is first compared with the simulation results generated by the thermo-electric coupling simulation model. Specific comparisons include: Local thermal resistance: Checking whether the local thermal resistance exceeds the preset normal threshold (e.g., [0.05, 0.15] K·m² / W). Temperature difference: Checking whether the temperature difference deviates from the preset effective range (e.g., [5°C, 10°C]) and whether the sudden change exceeds the preset range (e.g., ±2°C / hour). Output electrical parameters: Checking whether the output electrical parameters (such as voltage and current) deviate from the stable range (e.g., voltage fluctuation of ±0.1V, current fluctuation of ±0.2A).

[0189] If any of the above conditions are met, a thermal resistance anomaly is identified. Once an anomaly is detected, the system will mark the location of the anomaly in the BIM system, trigger an alert, and notify maintenance personnel to inspect and address the issue. For example, if the thermal resistance value of an area is 0.20K·m² / W, exceeding the upper limit of the normal threshold of 0.15K·m² / W, the system will automatically highlight the area in the BIM model and send an alert to the maintenance personnel's terminal device so that timely action can be taken.

[0190] A method for controlling a self-powered energy storage temperature-controlled concrete wall further includes steps after marking an abnormal location in a BIM system and triggering an early warning, specifically as follows:

[0191] In step Sd00 , a parameter mapping rule library is established based on the abnormal position marked in the thermal resistance abnormality warning, the magnitude of the thermal resistance exceeding the preset normal threshold, and the phase change material distribution in the corresponding area.

[0192] Thermal resistance anomaly warning: When the thermal resistance of the wall exceeds the preset normal threshold, the system triggers a warning signal. Acquisition method: Determined by comparing the multi-source operating data in the thermal resistance monitoring data set with the simulation results. Parameter mapping rule base: A rule base containing information such as the abnormal location, the thermal resistance excess amplitude and the distribution of phase change materials, used to generate temporary adjustment parameters for graded heat release. Acquisition method: Constructed based on historical data, experimental results and expert experience. Abnormal location: The specific location of the thermal resistance anomaly marked in the BIM system. Acquisition method: Determined through the early warning function in the BIM system. The amplitude of the thermal resistance exceeding the preset normal threshold: The degree to which the thermal resistance exceeds the preset normal threshold. Acquisition method: Calculated by comparing the thermal resistance monitoring data with the preset normal threshold. Phase change material distribution: The distribution of thermoelectric phase change hydrogel in the corresponding abnormal area. Acquisition method: Determined through wall design parameters and sensor data.

[0193] The necessary process is described as follows: In step Sd00, the abnormal location marked in the thermal resistance anomaly warning is first obtained from the BIM system to determine the specific location of the anomaly. Next, the extent to which the thermal resistance exceeds the preset normal threshold is calculated to assess the severity of the anomaly. Simultaneously, the distribution of the phase change material in the corresponding area is obtained to understand the specific distribution of the thermoelectric phase change hydrogel in the abnormal area. Based on this information, a parameter mapping rule library is established, containing adjustment parameter mapping rules for different abnormal situations. For example, if the abnormal location is a specific area of ​​the wall, the thermal resistance exceeds the threshold by 0.05K·m² / W, and the area is primarily distributed in a hydrogel component with a phase change temperature of 25°C, the rule library will set corresponding adjustment parameter rules for this abnormal situation, such as a heat release rate correction coefficient of 1.2 for the target component and a temporary activation priority adjustment value of 0. These rules will be used to subsequently generate temporary adjustment parameters for graded heat release to address thermal resistance anomalies.

[0194] Step Se00, based on the parameter mapping rule library, combined with the real-time temperature difference and output electrical parameters in the thermal resistance monitoring data set, generates the graded heat release temporary adjustment parameters, which include the heat release rate correction coefficient of the target component and the startup priority temporary adjustment value.

[0195] Temporary adjustment parameters for graded heat release are generated based on the current thermal resistance anomaly and real-time operating data. These parameters are used to optimize the heat release process of the thermoelectric phase change hydrogel and are obtained through a parameter mapping rule library combined with real-time data. Heat release rate correction coefficients are used to adjust the heat release rate of the target component and are calculated based on the rules in the parameter mapping rule library. Startup priority temporary adjustment values ​​are used to adjust the startup priority of the target component and are determined based on the rules in the parameter mapping rule library.

[0196] In step Se00, rules matching the current thermal resistance anomaly are first extracted from the parameter mapping rule library. These rules are based on information such as the anomaly location, the magnitude of the thermal resistance excess, and the distribution of the phase change material. Next, temporary adjustment parameters for graded heat release are generated by combining the real-time temperature difference and output electrical parameters from the thermal resistance monitoring dataset. The specific process is as follows:

[0197] Extract matching rules: Based on the anomaly location, thermal resistance excess, and phase change material distribution marked in the BIM system, corresponding rules are extracted from the parameter mapping rule library. For example, if the anomaly location is a specific area of ​​the wall, the thermal resistance excess is 0.05K·m² / W, and the area is primarily distributed with hydrogel components with a phase change temperature of 25°C, then the corresponding rule is extracted.

[0198] Combined with real-time data: Get the real-time temperature difference and output electrical parameters from the thermal resistance monitoring data set. For example, the current real-time temperature difference is 8°C and the thermoelectric output power is 0.5W.

[0199] Generate temporary adjustment parameters: Based on the extracted rules and real-time data, the heat release rate correction factor and startup priority temporary adjustment value for the target component are calculated. For example, the rule base stipulates that for the above abnormal situation, the heat release rate correction factor is 1.2 and the startup priority temporary adjustment value is 0. This means that the heat release rate of the component with a phase change temperature of 25°C should be increased by 20%, while the startup priority remains unchanged.

[0200] In step Sf00, the temporary adjustment parameters are input into the thermal-electrical coupling simulation model to simulate the heat flow recovery effect under different adjustment parameters, output the parameter adaptation score, and select the parameter with the highest score as the execution parameter.

[0201] The parameter fitness score is a quantitative indicator used to evaluate the heat flow recovery effect under different adjustment parameters. It is used to select the optimal adjustment parameters. The score is calculated by simulating the heat flow recovery effect under different adjustment parameters using a thermal-electrical coupled simulation model. The execution parameter is the temporary adjustment parameter with the highest score, which is used to actually control the thermoelectric performance of the wall. The execution parameter is obtained by selecting the parameter fitness score.

[0202] In step Sf00, the temporary adjustment parameters generated in step Se00 are input into the thermal-electrical coupling simulation model to simulate the heat flow recovery effect under different adjustment parameters. The specific process is as follows:

[0203] 1. Enter temporary adjustment parameters: Enter temporary adjustment parameters (such as the heat release rate correction factor and the startup priority temporary adjustment value) into the thermal-electrical coupling simulation model. For example, for a component with a phase change temperature of 25°C, the heat release rate correction factor is 1.2, and the startup priority temporary adjustment value is 0.

[0204] 2. Simulating Heat Flow Recovery: The simulation model simulates the heat flow recovery effect of the wall under different temporary adjustment parameters, including changes in temperature difference, thermal resistance, and thermoelectric output power. For example, simulation results show that after adjustment, the temperature difference decreases from 8°C to 7.5°C, the thermal resistance decreases from 0.20K·m² / W to 0.15K·m² / W, and the thermoelectric output power increases from 0.5W to 0.55W.

[0205] 3. Calculate parameter fitness scores: Based on the simulation results, calculate the fitness score for each adjustment parameter. Scoring metrics can include temperature difference change, thermal resistance change, thermoelectric output power change, and other factors. For example, the scoring formula might be: Fitness score = 0.4 × temperature difference change + 0.3 × thermal resistance change + 0.3 × thermoelectric output power change. Assuming a temperature difference change of 0.5°C, a thermal resistance change of 0.05K·m² / W, and a thermoelectric output power change of 0.05W, the fitness score is: Fitness score = 0.4 × 0.5 + 0.3 × 0.05 + 0.3 × 0.05 = 0.23.

[0206] 4. Select execution parameters: Compare the fitness scores of different tuning parameters and select the one with the highest score as the execution parameter. For example, if three sets of tuning parameters are simulated and their fitness scores are 0.23, 0.25, and 0.22, the one with a fitness score of 0.25 is selected as the execution parameter.

[0207] In step Sg00, a temporary heat release control instruction is generated according to the execution parameters, the corresponding thermoelectric phase change hydrogel component is started according to the adjusted start priority, and the heat release rate is adjusted according to the heat release rate correction coefficient.

[0208] Temporary Heat Release Control Instructions: These instructions are generated based on the execution parameters and are used to guide the heat release process of the thermoelectric phase-change hydrogel component of the wall. These instructions are generated and sent by the wall control system. Startup Priority: The activation order of the thermoelectric phase-change hydrogel components. These instructions are determined by the temporary start priority adjustment value in the execution parameters. Heat Release Rate Correction Factor: This factor is used to adjust the heat release rate of the target component. These instructions are determined by the heat release rate correction factor in the execution parameters.

[0209] In step Sg00, based on the execution parameters selected in step Sf00, temporary heat release control instructions are generated, and the heat release process of the thermoelectric phase change hydrogel component of the wall is controlled according to these instructions. The specific process is as follows:

[0210] Generate Control Instructions: Generates temporary heat release control instructions based on execution parameters. These instructions include the activation priority and heat release rate correction factor for the target component. For example, if the execution parameters are a heat release rate correction factor of 1.2 for a component with a phase change temperature of 25°C, the activation priority temporary adjustment value is 0; if the execution parameters are a heat release rate correction factor of 1.1 for a component with a phase change temperature of 35°C, the activation priority temporary adjustment value is 1.

[0211] Activate the corresponding components: Activate the corresponding thermoelectric phase change hydrogel components according to the adjusted activation priority. For example, according to the temporary activation priority adjustment value, the component with a phase change temperature of 25°C is activated first, followed by the component with a phase change temperature of 35°C.

[0212] Adjust the heat release rate: Adjust the heat release rate of each component based on the heat release rate correction factor. For example, if the original heat release rate of a component with a phase transition temperature of 25°C is 1.2°C per hour and the correction factor is 1.2, the adjusted heat release rate is 1.44°C per hour. If the original heat release rate of a component with a phase transition temperature of 35°C is 1.8°C per hour and the correction factor is 1.1, the adjusted heat release rate is 1.98°C per hour.

[0213] Step Sh00: During the control process, multi-source operation data is collected in real time to determine whether the temperature difference in the abnormal area returns to the preset effective range and whether the thermal resistance drops to the normal threshold.

[0214] Determine whether the temperature difference has returned to the valid range: Compare the real-time temperature difference in the abnormal area with the preset valid range (such as [5°C, 10°C]). Example: Preset valid range: [5°C, 10°C]; real-time temperature difference: 7.5°C; Judgment result: The temperature difference of 7.5°C is within the preset valid range.

[0215] Determine whether the thermal resistance has fallen within the normal threshold: Compare the real-time thermal resistance of the abnormal area with the preset normal threshold (for example, [0.05, 0.15] K·m² / W). Example: Preset normal threshold: [0.05, 0.15] K·m² / W; real-time thermal resistance: 0.12 K·m² / W; judgment result: The thermal resistance of 0.12 K·m² / W is within the preset normal threshold.

[0216] In step Si00, if all conditions are met, the current temporary adjustment parameters are maintained until the thermal resistance is stable, and then the parameters are fed back to the management and control system to update the parameter mapping rule library.

[0217] In step Sj00, if the condition is not met, the parameter mapping rule base is re-called based on the real-time data to generate the correction parameters, and the simulation adaptation and control steps are repeated until the anomaly is alleviated.

[0218] Determine again whether the abnormal situation has been alleviated: repeat step Sh00, collect multi-source operation data in real time, and determine whether the temperature difference in the abnormal area returns to the preset effective range and whether the thermal resistance drops to the normal threshold.

[0219] Step Sk00: synchronously store the exception handling process and parameter adjustment records into the fault knowledge base.

[0220] A method for controlling a self-powered energy storage temperature-controlled concrete wall further includes steps after marking an abnormal location in a BIM system and triggering an early warning, specifically as follows:

[0221] Step SA00: extract the thermal resistance characteristics of the abnormal location, the corresponding regional historical thermal resistance data and BIM spatial coordinates, integrate the regional historical climate data and the associated records of the thermal resistance monitoring data set, and form a prediction sample set with spatiotemporal labels.

[0222] The thermal resistance characteristics of the abnormal location refer to the thermal resistance characteristics of the area within the wall where the abnormal thermal resistance occurs, including the magnitude and rate of change of the thermal resistance. This characteristic is obtained by using the sensor matrix in the wall control system to monitor the heat flow distribution within the wall in real time. This is combined with the thermal resistance monitoring dataset to extract the thermal resistance characteristics of the abnormal area. The historical thermal resistance data for the corresponding area refers to the thermal resistance data recorded during historical operation of the area where the abnormal location is located. This data is used to compare and analyze the characteristics of the current thermal resistance anomaly. This characteristic is obtained by retrieving the historical thermal resistance monitoring records for that area from the wall control system's database.

[0223] Extract the thermal resistance characteristics of the abnormal location from the wall control system, including the current thermal resistance value and rate of change. Retrieve historical thermal resistance data for the area and analyze its changing trends. Obtain the spatial coordinates of the abnormal location within the BIM system to ensure accurate positioning. Retrieve historical climate data for the area where the wall is located from the meteorological database, including temperature and humidity. Integrate this data with the associated records in the thermal resistance monitoring dataset to form a prediction sample set with spatiotemporal labels.

[0224] Step SB00: call the pre-built thermal resistance trend prediction model, input the real-time sequence of continuous thermal resistance changes after abnormality of the thermal resistance monitoring data set and the thermal flow cloud map characteristics of the digital twin.

[0225] Thermal resistance trend prediction model: A mathematical model built based on historical data and real-time monitoring data is used to predict the changing trend of wall thermal resistance over a preset future time period. This model is constructed by training historical thermal resistance data using machine learning algorithms (such as time series analysis, recurrent neural networks (RNNs) or long short-term memory (LSTMs) in deep learning) to build a thermal resistance trend prediction model. Once built, the model is stored in the model library of the wall management and control system. Real-time series of continuous thermal resistance changes after an anomaly in the thermal resistance monitoring dataset: This data sequence, obtained in real time from the moment an anomaly occurs, reflects the dynamic changes in thermal resistance after the anomaly. This data is collected in real time through the sensor matrix in the wall management and control system. Starting from the moment the anomaly occurs, thermal resistance changes are continuously recorded to form a real-time series of data. Digital twin thermal flow cloud map features: This visualization feature of the wall's heat flow distribution, constructed using digital twin technology, displays the internal heat flow distribution of the wall in the form of a cloud map. This feature is generated by combining the digital twin model of the wall with real-time data from the thermal resistance monitoring dataset to generate a cloud map of the internal heat flow distribution. Cloud map features include information such as heat flux density and heat flow direction.

[0226] The necessary steps are as follows: 1. Calling the thermal resistance trend prediction model: Calling a pre-built thermal resistance trend prediction model from the wall control system's model library. This model has been trained using historical data and can predict future thermal resistance trends based on the input real-time thermal resistance data and heat flow cloud map features. 2. Input Data Preparation: Real-time Series of Continuous Thermal Resistance Changes after an Anomaly: Receive real-time thermal resistance data after an anomaly from the wall control system's sensor matrix to form a continuous series of thermal resistance changes. Digital Twin Thermal Flow Cloud Map Features: Generate a cloud map of the heat flow distribution within the wall using the digital twin model and extract key features from the cloud map, such as heat flux density and direction. 3. Data Input and Model Execution: Input the prepared data into the thermal resistance trend prediction model. The model performs calculations and analysis based on the input real-time thermal resistance change series and heat flow cloud map features, outputting a predicted thermal resistance change curve for a preset future time period. 4. Result Output: The model outputs a thermal resistance change prediction curve that demonstrates future thermal resistance trends, providing a basis for subsequent temperature difference impact assessment and risk classification.

[0227] Step SC00: Output the thermal resistance change prediction curve for the future preset period through the thermal resistance trend prediction model, generate the temperature difference impact assessment result based on the temperature difference prediction trend, and divide it into three risk levels according to the impact degree.

[0228] In step SC00, a pre-trained thermal resistance trend prediction model (such as LSTM or ARIMA) is first input with the real-time sequence of continuous thermal resistance changes after the anomaly and the characteristics of the digital twin's heat flow cloud map to generate a thermal resistance change forecast curve for a preset future time period. Next, combined with the temperature difference prediction trend (derived through linear regression or other time series models), the impact of thermal resistance changes on wall temperature differences is comprehensively evaluated, and key indicators such as the temperature difference change amplitude and rate are calculated. Finally, based on the severity of the assessment results and according to preset grading standards (such as the temperature difference change amplitude threshold), potential future thermal resistance anomalies or temperature difference deviations in the wall are classified into three risk levels: low risk, medium risk, and high risk, providing a decision-making basis for subsequent early warning and control measures.

[0229] Furthermore, considering that the thermal resistance change prediction curve, temperature difference impact assessment results, temporary adjustment parameters and other prediction-related data are available, the heat release rate of each component is corrected in real time through a dynamic adjustment algorithm to stabilize the temperature difference within the preset effective range. The specific steps are as follows:

[0230] In step A, after obtaining the prediction-related data (including the thermal resistance change prediction curve, the temperature difference impact assessment results, and the temporary adjustment parameters), the fusion data is collected. The fusion data includes the dynamic control data (real-time temperature difference, residual latent heat, and output power) and the above-mentioned prediction-related data.

[0231] Step B, based on the results of the temperature difference impact assessment, upgrade the multi-objective optimization model, set the temperature difference stability (including prediction deviation correction), power generation efficiency, and material life as core objectives and assign preset weights, set a reward coefficient for early heat release that matches the thermal resistance prediction trend, and set a penalty coefficient for delayed adjustment that does not respond to the prediction risk.

[0232] Step B: First, clarify the temperature difference impact assessment results (referring to the assessment of future temperature difference fluctuation amplitude, duration, and impact range based on the thermal resistance change prediction curve, such as "moderate risk: the temperature difference may exceed the preset range by 1.5°C within 3 hours"), and use this as a basis to upgrade the multi-objective optimization model (an algorithm model that simultaneously optimizes multiple objectives, such as the NSGA-Ⅱ algorithm).

[0233] During the upgrade, three core objectives were incorporated into the model: temperature difference stability (including prediction deviation correction, that is, comparing the deviation between the actual temperature difference and the predicted temperature difference and correcting it. For example, when the predicted temperature difference is 8°C and the actual temperature difference is 9°C, the correction amount is automatically included), power generation efficiency (thermoelectric conversion efficiency), and material life (number of times the phase change material is recycled), and preset weights were assigned (for example: 50%, 30%, 20%).

[0234] At the same time, a reward and punishment mechanism is set up: if the adjustment strategy matches the thermal resistance prediction trend in advance (for example, heat release is started before the predicted thermal resistance rises), a reward coefficient is given (for example, the strategy score is increased by 10%); if the predicted risk is not responded to (for example, the predicted temperature difference exceeds the threshold but no adjustment is made in advance), a penalty coefficient is applied (for example, the strategy score is reduced by 15%).

[0235] In step C, a dynamic adaptation strategy for graded heat release is generated based on the upgraded multi-objective optimization model and fusion data. The strategy includes conventional correction parameters (corresponding to real-time deviations) and predictive adjustment parameters (corresponding to predicted trends).

[0236] Specific process of step C: Use the upgraded multi-objective optimization model as the calculation framework and input the fusion data obtained in step A (including dynamic data such as real-time temperature difference, residual latent heat, and trend data such as thermal resistance prediction curve).

[0237] The data is run using a particle swarm optimization algorithm (example algorithm). The algorithm prioritizes matching the real-time temperature difference with the predicted trend. For example, if the real-time temperature difference is slightly higher than the preset range, and the predicted curve indicates that the temperature difference may continue to rise, the algorithm generates two types of parameters: conventional correction parameters (such as increasing the current heat release rate by 10%) and predictive adjustment parameters (such as starting a high-phase transition temperature component 20 minutes earlier).

[0238] Finally, a hierarchical heat release dynamic adaptation strategy is formed (referring to a heat release adjustment plan based on priority and scenario), which clarifies the specific adjustment methods in different situations.

[0239] Step D, using a dynamic adjustment algorithm to correct the heat release rate of each component according to the preset weighted value of the real-time temperature difference deviation and the predicted trend deviation, including starting high-priority components in advance and dynamically adjusting the heat release step size.

[0240] Step D: Invoke the dynamic adjustment algorithm (used to modify heat release parameters in real time) and first read the graded heat release dynamic adaptation strategy generated in Step C. The algorithm extracts the weighting rules in the strategy (e.g., a 60% weight for real-time temperature difference deviation and a 40% weight for predicted trend deviation) and performs a weighted calculation on the two types of deviations.

[0241] For example, if the real-time temperature difference is 2°C higher than the preset range (real-time deviation), and the temperature difference is predicted to rise another 1°C in one hour (forecast deviation), the algorithm calculates a comprehensive adjustment value based on the weights. This value modifies the heat release rate of each component: for high-priority components, their heat release program is activated earlier; for components currently releasing heat, the heat release step size is adjusted based on the calculated results (for example, increasing the heat release rate by 5% every 5 minutes), ensuring that the adjustment responds to both real-time conditions and future trends.

[0242] In step E, after the temperature difference stabilizes in the preset effective range and the prediction deviation is less than the preset threshold, the control data is fed back to the management and control system, and the graded heat release timing parameters and thermal resistance trend prediction model coefficients are simultaneously updated to form a closed loop.

[0243] The embodiments of this specific implementation method are all preferred embodiments of the present application and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A self-powered energy storage temperature regulating concrete wall, characterized in that: include: The hollow frame is formed by 3D printing and has several through-channels inside; Thermoelectric phase change material is poured into the pipe of the hollow frame. The thermoelectric phase change material is an ionic thermoelectric phase change hydrogel and contains at least two gel components with different phase change temperatures to form a temperature gradient control; The thermoelectric functional structure includes an N-type thermoelectric material and a P-type thermoelectric material provided on the outer surface of the hollow frame or constituting the hollow frame body, wherein the N-type thermoelectric material and the P-type thermoelectric material are alternately arranged and connected in series through electrodes to form a closed thermoelectric circuit; The opposing cement boards include a high-temperature board located outdoors and a low-temperature board located indoors. The high-temperature board and the low-temperature board are fixed to both sides of the hollow frame, and an electrode area is reserved on the surface of the board, and the electrode area is connected to the external terminal through a conductive material. The insulating cement layer is poured on the hollow frame, the thermoelectric phase change hydrogel poured inside it, and the outside of the cement board to solidify the entire structure into one.

2. The self-powered energy storage and temperature-regulating concrete wall according to claim 1, characterized in that: The thermoelectric functional structure is a thermoelectric material coating provided on the outer surface of the hollow frame. The thermoelectric material coating includes N-type thermoelectric material and P-type thermoelectric material. The thermoelectric material coating is formed by electrostatic spraying with a thickness of 30-80μm, and is naturally connected at the frame pipes and connection nodes to form a continuous thermoelectric path.

3. The self-powered energy storage and temperature-regulating concrete wall according to claim 1, characterized in that: The thermoelectric functional structure is composed of N-type thermoelectric material and P-type thermoelectric material that constitute the hollow frame body. The hollow frame is preset with a path where the N-type thermoelectric material and the P-type thermoelectric material are alternately distributed to form an integrated thermocouple array.

4. A method for controlling a self-powered energy storage temperature-regulating concrete wall, characterized in that: The self-powered energy storage and temperature-regulating concrete wall according to any one of claims 1 to 3 comprises: The wall control system is activated to collect multi-source operating data along a preset monitoring path through a preset sensor matrix. The multi-source operating data includes the real-time temperature difference between the high-temperature plate and the low-temperature plate, the output electrical parameters of the thermoelectric functional structure, and the phase change state data of the thermoelectric phase change hydrogel. Collect historical climate data of the area where the wall is located, perform standardized preprocessing on the historical climate data and multi-source operational data, and construct a spatiotemporal feature dataset; The spatiotemporal feature dataset is input into a pre-built temperature difference prediction model to output the temperature difference prediction trend for a preset period of time in the future. Based on this trend, the graded heat release timing parameters of the thermoelectric phase change hydrogel are initially configured. During the wall operation process, pre-processed multi-source operation data is obtained in real time to determine whether the temperature difference is lower than the preset control threshold; If yes, the heat release control instruction is triggered to start the heat release of the corresponding components of the thermoelectric phase change hydrogel according to the preset priority, and the heat release rate of each component is corrected in real time through the dynamic adjustment algorithm to stabilize the temperature difference in the preset effective range; If not, maintain the current heat release timing parameters and continue to monitor changes in multi-source operating data.

5. A method for controlling a self-powered energy storage temperature-regulating concrete wall according to claim 4, characterized in that: Based on this trend, the initial configuration of the graded heat release timing parameters of the thermoelectric phase change hydrogel includes: According to the climate type of the area where the wall is located, a preset thermoelectric phase change hydrogel temperature gradient combination is matched, and the thermoelectric phase change hydrogel temperature gradient combination includes at least two gel components with different phase change temperatures; Extract cooling characteristics based on temperature difference prediction trend, including cooling start stage, cooling rate change stage and low temperature stabilization stage; According to different cooling characteristic stages, preset starting priorities are set for the gel components in the temperature gradient combination; Dynamically configure the preset heat release parameters of each component based on the predicted cooling rate; Integrate startup priority and heat release parameters to form an initial heat release timing benchmark that adapts to regional climate and temperature difference trends.

6. A method for controlling a self-powered energy storage temperature-regulating concrete wall according to claim 5, characterized in that: The dynamic adjustment algorithm is used to correct the heat release rate of each component in real time to stabilize the temperature difference within the preset effective range, including: Collect dynamic control data, including the real-time temperature difference between the high-temperature plate and the low-temperature plate, the residual latent heat of each thermoelectric phase change hydrogel component, the thermoelectric output power, and the preset graded heat release timing parameters; A multi-objective optimization model is constructed based on the preset startup priority framework. Temperature difference stability, power generation efficiency, and material life are set as core objectives and assigned preset weights. A preset reward coefficient is assigned to latent heat reserve strategies that adapt to the regional climate, and a preset penalty coefficient is applied to excessive heat release that violates the preset cooling stage. Generate a dynamic adaptation strategy for graded heat release based on a multi-objective optimization model and dynamic control data; Through the dynamic adjustment algorithm and the graded heat release dynamic adaptation strategy, the heat release rate of each thermoelectric phase change hydrogel component is adjusted to correct the deviation and ensure that the temperature difference is stable in the preset effective range; The regulated data is fed back to the management and control system, and the comprehensive benefits are calculated using a multi-objective optimization model. When the preset standards are reached, the preset graded heat release timing parameters are updated to form a closed-loop control.

7. A method for controlling a self-powered energy storage temperature-regulating concrete wall according to claim 6, characterized in that: The step of initially configuring the graded heat release timing parameters of the thermoelectric phase change hydrogel based on the trend is further included, specifically as follows: The thermal resistance monitoring data set is formed by combining multi-source operation data with graded heat release time series parameters; A thermal-electrical coupling simulation model was established based on the initial heat release time series benchmark. The thermal resistance monitoring dataset was connected to calibrate the parameters, and a digital twin was constructed to generate heat flow and thermal resistance simulation results with preset normal thresholds. The multi-source operating data in the thermal resistance monitoring data set is compared with the simulation results. If the local thermal resistance exceeds the preset normal threshold, the temperature difference deviates from the preset effective range and the mutation exceeds the preset amplitude, or the output electrical parameter deviates from the stable range, it is determined to be a thermal resistance anomaly. The abnormal location is marked in the BIM system and an early warning is triggered.

8. A method for controlling a self-powered energy storage temperature-regulating concrete wall according to claim 7, characterized in that: It also includes the following steps after marking abnormal locations in the BIM system and triggering an alert: A parameter mapping rule library is established based on the abnormal position marked in the thermal resistance abnormality warning, the magnitude of the thermal resistance exceeding the preset normal threshold, and the distribution of phase change materials in the corresponding area; Based on the parameter mapping rule library and combined with the real-time temperature difference and output electrical parameters in the thermal resistance monitoring data set, temporary adjustment parameters for graded heat release are generated. The temporary adjustment parameters include the heat release rate correction coefficient of the target component and the temporary adjustment value of the startup priority. Input the temporary adjustment parameters into the thermal-electrical coupling simulation model, simulate the heat flow recovery effect under different adjustment parameters, output the parameter fitness score, and select the parameter with the highest score as the execution parameter; Generate a temporary heat release control instruction based on the execution parameters, start the corresponding thermoelectric phase change hydrogel component according to the adjusted start priority, and adjust the heat release rate according to the heat release rate correction coefficient; During the control process, multi-source operating data is collected in real time to determine whether the temperature difference in the abnormal area has returned to the preset effective range and whether the thermal resistance has dropped to the normal threshold; If all of them are achieved, the current temporary adjustment parameters are maintained until the thermal resistance is stable, and then the parameters are fed back to the control system to update the parameter mapping rule library; If it is not achieved, the parameter mapping rule base is re-called based on real-time data to generate corrected parameters, and the simulation adaptation and control steps are repeated until the anomaly is alleviated; The exception handling process and parameter adjustment records are simultaneously stored in the fault knowledge base.

9. A method for controlling a self-powered energy storage temperature-regulating concrete wall according to claim 7, characterized in that: It also includes the following steps after marking abnormal locations in the BIM system and triggering an alert: Extract the thermal resistance characteristics of the abnormal location, the corresponding regional historical thermal resistance data and BIM spatial coordinates, and integrate the regional historical climate data and the associated records of the thermal resistance monitoring dataset to form a prediction sample set with spatiotemporal labels; Call the pre-built thermal resistance trend prediction model, input the real-time sequence of continuous thermal resistance changes after abnormality of the thermal resistance monitoring data set and the thermal flow cloud map characteristics of the digital twin; The thermal resistance trend prediction model is used to output the thermal resistance change prediction curve for the preset period in the future. Combined with the temperature difference prediction trend, the temperature difference impact assessment result is generated, and the risk level is divided into three levels according to the degree of impact.

10. A method for manufacturing a self-powered energy storage and temperature-regulating concrete wall, characterized in that: The self-powered energy storage and temperature-regulating concrete wall according to any one of claims 1 to 3 comprises: A hollow frame is formed by 3D printing, and a plurality of through-channels are provided inside the hollow frame; Forming a thermoelectric functional structure: If the hollow frame material is a non-thermoelectric functional material, a coating comprising an N-type thermoelectric material and a P-type thermoelectric material is provided on the outer surface of the hollow frame, so that the two materials are alternately arranged and connected in series through electrodes to form a closed thermoelectric loop; if the hollow frame material is a thermoelectric functional material, a hollow frame body comprising an N-type thermoelectric material and a P-type thermoelectric material is directly formed by 3D printing, so that the two materials are alternately distributed inside the frame and connected in series through electrodes to form a closed thermoelectric loop; Infusing an ionic thermoelectric phase-change hydrogel into a pipe of the hollow frame, the hydrogel comprising at least two gel components with different phase-change temperatures; A high-temperature panel located outdoors and a low-temperature panel located indoors are fixed on both sides of the hollow frame, electrode areas are reserved on the surfaces of the high-temperature panel and the low-temperature panel, and the electrode areas are led out to external wiring terminals through conductive materials; Insulating cement is poured into the hollow frame, the thermoelectric phase change hydrogel poured inside the hollow frame, and the outside of the high-temperature plate and the low-temperature plate, and a complete wall is formed after solidification.

Images