TPMS heat exchanger based on intelligent response of phase change material

Abstract

The application discloses a TPMS heat exchanger based on intelligent response of phase change material, and relates to the technical field of heat exchange and heat energy management. The heat exchanger comprises a heat storage unit, a sensor group, a controller and an executing mechanism; the heat storage unit is internally provided with a phase change material packaging area which is coupled with heat transfer of a working medium flow channel and is fluidically isolated; a TPMS heat conduction framework in the packaging area is jointly defined by a periodic implicit curved surface function and a continuously changing equivalent surface threshold value, and different TPMS basic configurations can be adopted. The controller stores configuration description parameters corresponding to the actual heat storage unit, inputs time sequence data of pressure difference, flow and temperature distribution into a data driven model in combination with the parameters, so as to obtain a liquid phase rate of the phase change material and a residual latent heat storage capacity, and adjust circulating working medium flow, auxiliary cooling power or heat source power according to the liquid phase rate and the residual latent heat storage capacity. The structure forms a corresponding relationship among geometric parameters, operation state identification and closed loop heat management under different TPMS configurations.

Description

Technical Field

[0001] This invention relates to the field of heat exchange and thermal energy management technology, specifically a TPMS heat exchanger based on intelligent response of phase change materials. Background Technology

[0002] Aerospace, energy and power, and high heat flux density equipment often face transient thermal shock problems during operation. If the heat exchange system can only make lagging adjustments based on the temperature of a single point, problems such as local temperature rise and failure to switch heat dissipation strategies after the heat storage capacity is exhausted are likely to occur.

[0003] Phase change materials (PCMs) can absorb or release heat using latent heat, but their thermal conductivity is typically low. Enhancing internal heat transfer within PCMs using a continuous porous thermally conductive framework can shorten the heat transfer path. However, if the PCM is not reliably isolated from the working fluid, or if there is a lack of online identification of the liquid phase fraction and remaining latent heat storage capacity, it is difficult to simultaneously ensure sealing reliability and active thermal management.

[0004] Existing technologies have already disclosed composite structures of gradient TPMS frameworks and phase change materials generated by level set equations, such as the stepped-pore composite thermal storage material described in CN116179164A. Therefore, simply using a certain TPMS configuration, setting a porosity gradient, or filling with phase change material is insufficient to demonstrate the complete technical contribution of this application. Different TPMS configurations have different flow resistances and heat transfer responses. If the state identification model does not include the actual configuration parameters, the same set of temperature or pressure difference changes may correspond to different degrees of phase change, and the controller will also find it difficult to maintain consistent state determination logic after changing the configuration.

[0005] Therefore, it is necessary to establish the correspondence between the actual TPMS configuration, multi-source sensor data during operation and phase change state, and drive the actuator according to the liquid phase ratio or residual latent heat storage capacity under the condition of ensuring the isolation between the working fluid and the phase change material, so as to form a closed-loop thermal management device applicable to different TPMS basic configurations. Summary of the Invention

[0006] The purpose of this invention is to provide a TPMS heat exchanger based on intelligent response of phase change materials, which enables TPMS configuration description parameters to participate in phase change state identification and implements closed-loop regulation based on the identified liquid fraction or residual latent heat storage capacity.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a TPMS heat exchanger based on intelligent response of phase change materials.

[0008] The TPMS heat exchanger includes a heat storage unit, a sensor group, a controller, an actuator, and a heat exchanger shell; the TPMS refers to a three-period minimal surface, whose basic configuration is defined by an implicit surface function that is periodic in three independent directions.

[0009] The heat exchanger shell forms a working fluid flow channel; the heat storage unit includes a phase change material encapsulation area that is heat-coupled and fluid-isolated with the working fluid flow channel. The phase change material encapsulation area is provided with a TPMS thermal conductive skeleton and filled with phase change heat storage material. The TPMS thermal conductive skeleton and the phase change heat storage material together constitute a stepped hole composite heat storage structure.

[0010] The sensor array acquires inlet and outlet pressures, volumetric flow rate, inlet temperature, outlet temperature, and temperatures at multiple locations within the phase change material encapsulation zone; the inlet and outlet pressure difference and volumetric flow rate are used to obtain flow resistance parameters, and the temperature measurement point sequence is used to characterize the advancement state of the phase change front.

[0011] The controller is connected to the sensor group and the actuator, stores the configuration description parameters corresponding to the actual TPMS thermal conductive skeleton, and inputs the configuration description parameters, flow resistance parameters and temperature time series data into the data driving model to obtain the liquid phase fraction and residual latent heat storage capacity of the phase change thermal storage material, and generates an adaptive control signal accordingly.

[0012] The TPMS thermal conductive framework can adopt any continuous TPMS basic configuration defined by a periodic implicit surface function; Primitive, Gyroid, Diamond, I-WP, Neovius, and Lidinoid can all be used as basic configurations. The following Primitive is only used as a non-limiting formula example. The expression for the Primitive surface is: cosX + cosY + cosZ = C(z), where X = 2απx, Y = 2βπy, Z = 2γπz, x, y, and z represent rectangular coordinates, α, β, and γ are used to control the size of the three-period minimum surface unit, and C(z) is the isosurface threshold. The unit porosity is adjusted by the threshold-porosity calibration relationship corresponding to the selected basic configuration. The porosity changes continuously along the z-axis of the flow direction, and the corresponding isosurface threshold function expression is: C(z) = C min +(C max -C min )×[(zz min ) / (z max -z min )]. Among them, C min C is the lower limit of the isosurface threshold. max z is the upper limit of the isosurface threshold. min The minimum value of the z-axis coordinate, z max This represents the maximum value of the z-axis coordinate.

[0013] The sensor group includes a pressure sensor group, a flow sensor group, and a temperature sensor group; the volumetric flow rate can also be obtained from the calibration feedback of a circulating pump or a flow regulating valve. The flow resistance parameter is calculated based on the inlet and outlet pressure difference and the volumetric flow rate using the following formula: R f=Δp / q v , where R f Here are the flow resistance parameters, Δp is the inlet and outlet pressure difference, and q is the flow resistance parameter. v The volumetric flow rate is used; the heat transfer parameters include the inlet temperature, outlet temperature, and temperature distribution inside the heat storage material of the heat storage unit.

[0014] The data-driven model is a long short-term memory neural network trained with calibration data and / or simulation data. The model input includes configuration description parameters corresponding to the actual TPMS thermal skeleton, as well as time-series data of flow resistance parameters and temperature, where the dynamic time-series feature vector is: X t =[R f (t),T in (t),T out (t),T1(t),T2(t),...,T n (t),dR f [ / dt,dT / dt,…], where X t Let R be a time series feature vector, where t is the time index. f (t) represents the current resistance value at time t, T in (t) represents the inlet temperature at time t, T out (t) represents the outlet temperature at time t, where T1(t), T2(t), ..., T n (t) represents the temperature measurement values ​​at n different locations inside the thermal storage unit at time t, and dR f / dt is the rate of change of flow resistance, and dT / dt is the rate of change of temperature; the configuration description parameters include at least the basic configuration identifier, unit scale, isosurface threshold distribution parameters and porosity distribution parameters.

[0015] The training data for the Long Short-Term Memory (TPMS) neural network can be obtained in the following ways: For at least one basic TPMS configuration, under the conditions of initial liquid phase ratio, heat load curve, working fluid inlet flow rate, and temperature boundary, the flow resistance, temperature time series, and liquid phase ratio reference values ​​are obtained through calibration experiments or verified multiphysics simulations; the input features are normalized; the network adopts an input layer, at least one LSTM hidden layer, and a fully connected output layer, with the output being the liquid phase ratio; the mean squared error loss function is used during training, and the model accuracy is verified using an independent test set; after training, the network parameters are fixed into the controller.

[0016] The liquid phase fraction φ(t) satisfies 0 ≤ φ(t) ≤ 1; the remaining latent heat storage capacity C res (t) is calculated using the following formula: C res (t)=m p ×L f ×[1-φ(t)], where C res (t) represents the remaining latent heat storage capacity at time t, mp L represents the total mass of the phase change material. f Let φ(t) be the latent heat of phase change, and let φ(t) be the liquid phase fraction at time t.

[0017] The controller is further configured to: when the liquid phase ratio φ(t) reaches a first preset upper limit φ th or the remaining latent heat storage capacity C res (t) is lower than the second preset lower limit C th At that time, a corresponding adaptive control signal is generated; the threshold is set according to the allowable working range of the phase change material and the target reserved heat storage capacity.

[0018] The adaptive control signal is generated based on the PID control algorithm, specifically: Where u(t) is the control signal, and e(t) = φ target -φ(t) is the difference between the actual state and the desired state of the system at time t, φ target K is the target liquid fraction. p K i K d These are the PID control parameters.

[0019] The actuator includes at least one of a flow regulating valve, a circulating pump, an auxiliary cooling device, and a heat source power regulating interface; the adaptive control signal is used to regulate the flow rate of the circulating working fluid, regulate the auxiliary cooling power, output an overheat warning, and / or reduce the heat source power.

[0020] The TPMS thermal conductive frame is made of metal or ceramic material, wherein the metal material is selected from at least one of stainless steel, aluminum alloy or mold steel.

[0021] The phase change thermal storage material is a paraffin-based phase change material or an inorganic salt phase change material; a thermally conductive isolation wall is provided between the phase change material encapsulation area and the working fluid flow channel.

[0022] Compared with the prior art, the present invention has at least the following beneficial effects: 1. This invention uses the basic configuration, unit size, and porosity distribution of the TPMS thermal conductive framework as conditional parameters for phase change state identification. These parameters, along with operating state parameters such as inlet and outlet pressure difference, volumetric flow rate, and multi-point temperature, are input into the state identification model. This allows the state identification process to consider the influence of different TPMS structures on the temperature field, flow resistance, and sensing response characteristics. This reduces the risk of misjudging similar temperature or pressure difference changes as having the same liquid phase fraction due to different TPMS configurations or structural parameters, and improves the applicability of identifying the liquid phase fraction and residual latent heat storage capacity of phase change materials.

[0023] 2. This invention employs periodic implicit surface functions and spatially continuously varying isosurface thresholds to construct the TPMS heat-conducting framework. Under the conditions of unified spatial coordinates and phase continuity, by making the isosurface thresholds continuously change with spatial position, the surfaces and channels in adjacent regions within the selected basic configuration transition continuously, reducing surface misalignment, abrupt changes in pore size, local sealing, and increased local flow resistance caused by direct splicing of discrete units. For different TPMS basic configurations such as Primitive, Gyroid, Diamond, I-WP, Neovius, and Lidinoid, corresponding isosurface threshold-porosity calibration relationships are established, enabling different basic configurations to construct continuous gradient structures according to the target porosity distribution. This facilitates the selection of appropriate configurations based on heat transfer performance, flow resistance, and additive manufacturing constraints, improving the consistency and applicability of gradient structure design.

[0024] 3. This invention utilizes time-series data of inlet and outlet pressure difference, volumetric flow rate, and multi-point temperature to form dynamic state variables, and combines them with the configuration description parameters of the TPMS thermal conductive framework to identify the liquid fraction and residual latent heat storage capacity of the phase change material. The controller adjusts the flow rate of the heat exchange medium, the operating status of the auxiliary cooling device, and / or the power of the heat source according to the identification results, so that the basis for thermal management adjustment is expanded from a single instantaneous temperature to a dynamic judgment of the thermal storage state of the phase change material. This allows the corresponding thermal management strategy to be switched when the residual latent heat storage capacity reaches the preset adjustment conditions, reducing the risk of response lag or frequent switching caused by controlling based solely on a single temperature threshold. Attached Figure Description

[0025] Figure 1 This is an isometric view of a TPMS heat exchanger based on intelligent response of phase change materials according to the present invention; Figure 2 This is a top view of a TPMS heat exchanger based on intelligent response of phase change materials according to the present invention; Figure 3 This is a cross-sectional view of a TPMS heat exchanger based on intelligent response of phase change materials according to the present invention; Figure 4 This is a front view of a TPMS heat exchanger based on intelligent response of phase change materials according to the present invention; Figure 5 This is a partial schematic diagram of a TPMS heat exchanger based on intelligent response of phase change materials according to the present invention; Figure 6 This is a three-dimensional structural diagram of an example TPMS thermal skeleton using the Primitive basic configuration in this invention. Figure 7 for Figure 6 A slant view of the Primitive example configuration shown; Figure 8This is a flowchart of a data-driven model and intelligent control design method for a TPMS heat exchanger based on the intelligent response of phase change materials, according to the present invention. Explanation of reference numerals in the attached figures: 1. Thermal storage unit; 2. Inlet pipe; 3. Outlet pipe; 4. Pressure sensor group; 5. Temperature sensor group; 6. Flow sensor; 7. Controller; 8. Heat exchanger shell; 401. Inlet pressure sensor; 402. Outlet pressure sensor; 501. Inlet temperature sensor; 502. Outlet temperature sensor; 503. Internal temperature sensor array. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] Example: Figures 1 to 8 As shown, this embodiment provides a TPMS heat exchanger based on the intelligent response of phase change materials.

[0028] like Figures 1 to 4 As shown, the TPMS heat exchanger in this embodiment includes a heat storage unit 1, a sensor group and controller 7, an actuator and a heat exchanger housing 8.

[0029] A working fluid flow channel is formed within the heat exchanger shell 8, communicating with the inlet pipe 2 and the outlet pipe 3. The heat storage unit 1 includes a phase change material encapsulation area that is thermally coupled to and fluidly isolated from the working fluid flow channel. A TPMS thermally conductive skeleton is installed within the encapsulation area, which is filled with phase change heat storage material. Pressure sensor group 4 and temperature sensor group 5 transmit monitoring data to controller 7. Controller 7 also receives volumetric flow feedback from flow sensor 6 or the circulating pump and flow control valve. Controller 7 stores configuration description parameters corresponding to the actual TPMS thermally conductive skeleton and combines these parameters with sensing timing data for phase change state identification. Controller 7 is connected to the flow control valve, circulating pump, auxiliary cooling device, or heat source power regulation interface via control lines. The heat exchanger shell 8 is a load-bearing and sealing component and is not an actuator.

[0030] like Figure 5As shown, this embodiment uses a Primitive surface as the basic configuration to illustrate the correspondence between configuration parameters, gradient parameters, and sensing control, but does not imply that Primitive is the preferred or only configuration. In the horizontal direction, the structure consists of multiple Primitive units arranged in a periodic array. Other embodiments may replace the basic configuration with configurations such as Gyroid, Diamond, I-WP, Neovius, or Lidinoid. Along the fluid flow direction, the porosity of the units decreases sequentially from the inlet to the outlet. Adjacent units use the same basic configuration and the isosurface threshold changes continuously to avoid surface misalignment and abrupt changes in pore size. Figure 6 and Figure 7 As shown, the expression for the Primitive surface is cosX + cosY + cosZ = C(z), where X = 2απx, Y = 2βπy, Z = 2γπz, x, y, and z represent rectangular coordinates, α, β, and γ are used to control the size of the three-period minimum surface unit, and C(z) is the isosurface threshold. The unit porosity is adjusted by the threshold-porosity calibration relationship corresponding to the selected basic configuration. In this embodiment, the positive z-axis points from the outlet to the inlet, so that the porosity increases uniformly along the z-axis, that is, it decreases from the inlet to the outlet along the actual flow direction. Therefore, the expression for C(z) is C(z) = C min +(C max -C min )×[(zz min ) / (z max -z min )], where C min C is the lower limit of the isosurface threshold. max z is the upper limit of the isosurface threshold. min The minimum value of the z-axis coordinate, z max This represents the maximum value of the z-axis coordinate.

[0031] In this embodiment, the TPMS thermally conductive frame is made of 316L stainless steel, and the phase change thermal storage material is paraffin wax. When the high-temperature working fluid flows through the working fluid channel, heat is transferred to the paraffin wax through the thermally conductive isolation wall and the TPMS thermally conductive frame; the paraffin wax undergoes a solid-liquid phase change and stores heat in the form of latent heat. When the working fluid temperature decreases or the heat load decreases, the paraffin wax releases heat and undergoes a liquid-solid phase change. The thermally conductive isolation wall keeps the working fluid and the phase change material fluidly isolated.

[0032] The sensor group includes pressure sensor group 4 and temperature sensor group 5. For example... Figure 4 As shown, a pressure sensor array is configured with one sensor at the inlet and one at the outlet of thermal storage unit 1, namely inlet pressure sensor 401 and outlet pressure sensor 402, for measuring the pressure difference between the inlet and outlet. The flow resistance parameter R is calculated using the following formula. f =Δp / q v , where R fHere are the flow resistance parameters, Δp is the inlet and outlet pressure difference, and q is the flow resistance parameter. v This represents the volumetric flow rate. Flow resistance parameters characterize the current hydraulic conditions on the working fluid side and are input into the model along with the temperature series and configuration description parameters to distinguish the effects of flow rate changes, configuration differences, and phase transition state changes on the measurement signal. For example... Figure 5 As shown, the temperature sensor group 5 includes an inlet temperature sensor 501, an outlet temperature sensor 502, and an internal temperature sensor array 503. The inlet temperature sensor 501 measures the inlet temperature of the working fluid, the outlet temperature sensor 502 measures the outlet temperature of the working fluid, and the internal temperature sensor array 503 arranges multiple temperature probes at key locations within the three-period minimal surface to measure the internal temperature distribution of the phase change material. The temperature distribution data is used to calculate heat transfer parameters, including the inlet temperature, outlet temperature, and the internal temperature distribution of the heat storage material.

[0033] like Figure 8 As shown, the data-driven model is constructed using a long short-term memory neural network. The input layer receives configuration description parameters and time-series data sequences from sensors, where the dynamic time-series feature vector is X. t =[R f (t),T in (t),T out (t),T1(t),T2(t),...,T n (t),dR f [ / dt,dT / dt,…], where X t Let R be a time series feature vector, where t is the time index. f (t) represents the current resistance value at time t, T in (t) represents the inlet temperature at time t, T out (t) represents the outlet temperature at time t, where T1(t), T2(t), ..., T n (t) represents the temperature measurement values ​​at n different locations inside the thermal storage unit at time t, and dR f / dt represents the rate of change of flow resistance, and dT / dt represents the rate of change of temperature. The configuration description parameters include at least the basic configuration identifier, unit scale, isosurface threshold distribution parameters, and porosity distribution parameters. These configuration description parameters are concatenated at the model input as static conditional quantities and dynamic temporal characteristics. The model output is the liquid phase fraction φ(t), satisfying 0≤φ(t)≤1, and the remaining latent heat storage capacity C. res (t), C is calculated using the following formula. res (t)=m p ×L f ×[1-φ(t)], where C res (t) represents the remaining latent heat storage capacity at time t, m p L represents the total mass of the phase change material. f This is the latent heat of phase transition.

[0034] The intelligent control logic is as follows: First, sensor data is collected in real time and filtered and normalized; then, the processed data is input into a long short-term memory neural network model, which outputs the current liquid fraction φ(t) and the remaining capacity C. res (t); when φ(t) exceeds the first preset upper limit φ th or the remaining latent heat storage capacity C res (t) is lower than the second preset lower limit C th When the thermal storage margin reaches the adjustment boundary, an adaptive control signal is generated based on the decision result, specifically using a PID control algorithm. Where u(t) is the control signal, and e(t) = φ target -φ(t) is the difference between the actual state and the desired state of the system at time t, φ target K is the target liquid fraction. p K i K d These are the PID control parameters. The adaptive control signal is used to perform at least one of the following operations: adjusting the flow rate of the circulating working fluid in the system; starting or adjusting the power of the auxiliary cooling device; triggering a system overheat warning; and reducing the power output of the heat source equipment. Controller 7 records the liquid phase ratio, remaining latent heat storage capacity, and execution quantity before and after each control operation. If model parameters need to be updated, they should be updated offline using calibrated or verified data and then loaded after verification to avoid unverified online updates directly altering the safety control boundaries.

[0035] This embodiment employs metal additive manufacturing to integrally form a 316L stainless steel TPMS thermally conductive skeleton and thermally conductive isolation wall. Based on the selected basic configuration, a calibration relationship between the isosurface threshold and porosity is established, and the unit size and threshold distribution are determined within the range that meets the requirements of minimum wall thickness, minimum pore size, and powder discharge. Subsequently, molten paraffin is injected into the continuous pore region on the phase change material side under vacuum and sealed to prevent the working fluid channel from being occupied by the phase change material. Sensor mounting holes can be pre-drilled during printing or machined in post-processing. Finally, the end cap is sealed, airtightness is checked, and the sensor, controller, and actuator are assembled.

[0036] In one optional performance evaluation method, at least two basic TPMS configurations are selected, and / or TPMS thermally conductive frameworks with different unit sizes and porosity distributions are selected. For each TPMS thermally conductive framework, under the same conditions of thermal storage material type and mass, initial temperature, heat load curve, heat exchange medium inlet temperature, actuator adjustment range, sensor arrangement, and control cycle, the configuration-conditional phase change state control method and single-point temperature threshold control method of this invention are used for comparison. Evaluation indicators include liquid phase fraction estimation error, residual latent heat storage capacity estimation error, maximum temperature overshoot of the controlled object, adjustment response time, cumulative pumping energy consumption, and number of control strategy switching times. Among them, the reference values ​​of liquid phase fraction and residual latent heat storage capacity can be obtained by a calibrated enthalpy measurement method, a mass-energy balance method, or a multiphysics simulation model verified by prototype data.

[0037] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A TPMS heat exchanger based on intelligent response of phase change materials, characterized in that: The TPMS heat exchanger includes a heat storage unit (1), a sensor group, a controller (7), an actuator, and a heat exchanger housing (8). The heat exchanger shell (8) is provided with a working fluid flow channel connecting the inlet pipe (2) and the outlet pipe (3); the heat storage unit (1) has a phase change material encapsulation area that is heat-coupled and fluid-isolated with the working fluid flow channel, and the encapsulation area is provided with a TPMS thermal conductive skeleton and filled with phase change heat storage material; the TPMS thermal conductive skeleton is defined by a periodic implicit surface function and a continuously changing isosurface threshold, and adjacent TPMS periodic units are continuously connected. The two TPMS periodic units adopt a unified spatial coordinate system, periodic scale and phase reference, and the implicit function values ​​and isosurface thresholds on both sides of the common boundary are continuous, so that the TPMS surface and the channel are continuously connected at the common boundary to form adjacent units; The sensor array acquires inlet and outlet pressure difference, volumetric flow rate, inlet and outlet temperature, and temperature at multiple locations within the packaging area; The controller (7) connects the sensor group and the actuator, and stores the configuration description parameters of the TPMS thermal conductive skeleton; the controller (7) obtains the flow resistance parameters based on the inlet and outlet pressure difference and volume flow rate, and inputs the configuration description parameters, flow resistance parameters and temperature time series data into the data driving model to obtain the liquid phase fraction and residual latent heat storage capacity of the phase change thermal storage material, and generates the adaptive control signal of the actuator accordingly.

2. The TPMS heat exchanger based on intelligent response of phase change materials according to claim 1, characterized in that: The sensor group includes an inlet pressure sensor (401), an outlet pressure sensor (402), a flow sensor (6), an inlet temperature sensor (501), an outlet temperature sensor (502), and an internal temperature sensor array (503); the measuring points of the internal temperature sensor array (503) are spaced apart along the flow direction of the encapsulation area or the expected propulsion direction of the phase change front.

3. A TPMS heat exchanger based on intelligent response of phase change materials according to claim 1, characterized in that: The TPMS thermally conductive framework is defined by a periodic implicit surface function, and its basic configuration is selected from any one of Primitive, Gyroid, Diamond, I-WP, Neovius or Lidinoid. Adjacent units adopt the same basic configuration, and the isosurface threshold changes continuously according to the corresponding threshold-porosity calibration relationship to form a porosity gradient structure.

4. A TPMS heat exchanger based on intelligent response of phase change materials according to claim 1, characterized in that: The configuration description parameters include basic configuration identifier, unit scale, isosurface threshold distribution parameters, and porosity distribution parameters; the data-driven model uses the configuration description parameters as static conditional quantities and the flow resistance parameters and temperature time series data as dynamic state quantities.

5. A TPMS heat exchanger based on intelligent response of phase change materials according to claim 4, characterized in that: The data-driven model includes a long short-term memory neural network trained by calibration data and / or simulation data; the controller (7) obtains the remaining latent heat storage capacity based on its output liquid phase ratio, total mass of phase change material and latent heat of phase change.

6. A TPMS heat exchanger based on intelligent response of phase change materials according to claim 5, characterized in that: When the liquid phase fraction reaches the first preset upper limit and / or the remaining latent heat storage capacity is lower than the second preset lower limit, the controller (7) generates the adaptive control signal by means of a proportional-integral-derivative control algorithm based on the difference between the set value and the estimated value of the liquid phase fraction.

7. A TPMS heat exchanger based on intelligent response of phase change materials according to claim 1, characterized in that: The actuator includes at least one of a flow regulating valve, a circulating pump, an auxiliary cooling device, and a heat source power regulating interface, for regulating the flow rate of the circulating working fluid, the auxiliary cooling power, and / or the heat source power.

8. A TPMS heat exchanger based on intelligent response of phase change materials according to claim 1, characterized in that: The TPMS thermally conductive frame is made of metal or ceramic, and the metal is selected from at least one of stainless steel, aluminum alloy or mold steel.

9. A TPMS heat exchanger based on intelligent response of phase change materials according to claim 1, characterized in that: The phase change thermal storage material is a paraffin-based or inorganic salt phase change material; a thermally conductive isolation wall is provided between the encapsulation area and the working fluid channel.

Images