A neural network optimization-based fast thermal shielding metamaterial and a design method thereof

Abstract

The application discloses a kind of fast heat shielding metamaterials based on neural network optimization and design method thereof, belong to heat shielding metamaterial structure design and preparation field.Method as follows: with heat shielding metamaterial in steady-state heat shielding capacity and transient heat shielding effect time as comprehensive optimization target, set comprehensive objective function;Establish heat shielding metamaterial model, to stratified metamaterial equivalent thermal conductivity uniform orthogonal, select several groups of simulation test samples;Based on steady-state solution, obtain Mv value under different equivalent thermal conductivity conditions;Based on transient solution, obtain tv value under different equivalent thermal conductivity conditions;Build artificial neural network model;Equivalent thermal conductivity and its corresponding Mv value and tv value under the condition are input into artificial neural network model and carried out multi-objective optimization calculation;Design and establish heat shielding metamaterial.The design method is quick, simple, and the heat shielding metamaterial obtained using the method has good heat shielding effect and can quickly reach the heat shielding state.

Description

Technical Field

[0001] This invention belongs to the field of thermal shielding metamaterial structure design and preparation, specifically involving a rapid thermal shielding metamaterial based on neural network optimization and its design method. Background Technology

[0002] Thermal metamaterials refer to materials that achieve unique thermal properties not found in real-world materials through macroscopic or microscopic structural design, such as thermal stealth, thermal shielding, thermal torsion, and thermal illusion. Traditional thermal metamaterial design is typically based on theoretical calculations or empirical design, methods that are slow and complex. Furthermore, the designed thermal metamaterials often suffer from thermal insulation or thermal abrupt singularities, significantly increasing the difficulty of practical design and fabrication.

[0003] Therefore, there is an urgent need to provide a new design method for thermal metamaterials to achieve good thermal shielding effect and enable rapid thermal shielding. Summary of the Invention

[0004] This invention aims to address the problems of complex design, long design cycle, numerous design variables, and difficult and costly subsequent processing of existing thermal shielding metamaterials. It proposes a rapid thermal shielding metamaterial and its design method based on neural network optimization.

[0005] The specific technical solution adopted in this invention is as follows:

[0006] In a first aspect, the present invention provides a method for designing rapid thermal shielding metamaterials based on neural network optimization, the specific steps of which are as follows:

[0007] S1: Taking the thermal shielding capability of the thermal shielding metamaterial under steady state and the time to achieve thermal shielding effect under transient state as the comprehensive optimization objectives, a comprehensive objective function is set; where, the thermal shielding capability under steady state is characterized by the surface integral Mv value of the absolute value of the temperature difference between each point of the shielding region under steady state and the temperature under ideal thermal shielding steady state, and the time to achieve thermal shielding effect under transient state is characterized by the time tv value of the average temperature of the shielding region rising from the initial temperature to near the ideal steady-state thermal shielding effect;

[0008] S2: Establish a thermal shielding metamaterial model including multiple concentric rings; use the equivalent thermal conductivity of each concentric ring as a variable and set the variable range; uniformly orthogonally apply the equivalent thermal conductivity of the multiple concentric rings and select several sets of simulation test examples.

[0009] S3: Input the equivalent thermal conductivity of each concentric ring in several sets of simulation test examples in step S2 into the thermal shielding metamaterial model, and obtain the Mv value under different equivalent thermal conductivity conditions based on steady-state solution, which is used to evaluate the thermal shielding effect under these conditions.

[0010] S4: Input the equivalent thermal conductivity of each concentric ring in several sets of simulation test examples in step S2 into the thermal shielding metamaterial model, and obtain the tv value under different equivalent thermal conductivity conditions based on transient solution, which is used to evaluate the speed at which the thermal shielding effect is achieved under these conditions.

[0011] S5: Building an artificial neural network model;

[0012] S6: Input the Mv value obtained in step S3 and the tv value obtained in step S4 into the artificial neural network model for multi-objective optimization calculation to obtain the equivalent thermal conductivity of each concentric ring under the optimal condition of the objective function.

[0013] S7: Based on the equivalent thermal conductivity of each concentric ring under the optimal condition of the objective function obtained in step S6, a thermal shielding metamaterial is designed and established based on the neutral inclusion principle.

[0014] As a preferred option, in step S1, the Mv value and tv value are normalized and then added together in a certain proportion to obtain the comprehensive optimization objective function.

[0015] Preferably, the thermal shielding metamaterial model described in step S1 is established using the commercial software COMSOL.

[0016] Preferably, the variable range of thermal conductivity of each concentric ring in step S2 is set to 2–394 W / (m·K).

[0017] Preferably, the heat-shielding metamaterial model consists of two concentric rings; the specific steps for establishing the two-layer heat-shielding metamaterial model are as follows:

[0018] In the COMSOL commercial software, a two-dimensional model is selected, and a solid heat transfer physical field is established. The solid heat transfer physical field is a square with a side length of 5m. From the center outwards, concentric circular curves with radii of 1m, 1.5m, and 2m are set sequentially, and are respectively denoted as the first curve, the second curve, and the third curve. The center of the circle coincides with the center of the square. The ring formed by the second curve and the third curve is denoted as the first layer of concentric rings, and the ring formed by the first curve and the second curve is denoted as the second layer of concentric rings.

[0019] The temperature on the left side of the square is set to 0K, the temperature on the right side to 100K, and the top and bottom edges are thermally insulated. The interior of the first curve is the thermal shielding region, and the thermal conductivity of the thermal shielding region is set to 394W / (m·K). The thermal conductivity of the outer region of the third curve is 75-80W / (m·K). The equivalent thermal conductivity of the first concentric ring is denoted as k1, and the equivalent thermal conductivity of the second concentric ring is denoted as k2. The model of the two thermal shielding metamaterials is meshed.

[0020] Furthermore, in step S4, in order to reduce the calculation time, the calculation stop condition is set to the average temperature of the shielded area reaching 45K, or the actual heat transfer time reaching 400 seconds.

[0021] Furthermore, step S7 is detailed as follows:

[0022] S71: Determine the proportional relationship between the two materials in each layer of concentric rings:

[0023]

[0024] l1 + l2 = 1

[0025] Where: K s Let K1 be the equivalent thermal conductivity of each concentric ring layer under the optimal condition of the objective function, K2 be the thermal conductivity of material 1 in W / (m·K), and K2 be the thermal conductivity of material 2 in W / (m·K); l1 and l2 are the proportions of material 1 and material 2 in the concentric ring layer to be solved, respectively.

[0026] S71: Based on the ratio of the two materials in each concentric ring obtained in step S71, the density and specific heat capacity of each concentric ring are obtained, thus completing the design of the thermal shielding metamaterial.

[0027] Preferably, in step S5, the artificial neural network model is built using the commercial software iSight.

[0028] Preferably, the parameters of the artificial neural network model are as follows: bias 0.2, weight 0.5, number of layers 1, number of nodes 3.

[0029] In a second aspect, the present invention provides a thermally shielding metamaterial obtained using the design method described in the first aspect.

[0030] Compared with current methods for designing and preparing thermal shielding metamaterials, this invention has the following advantages:

[0031] (1) The thermal shielding metamaterial design method provided by this invention introduces an artificial neural network model, taking the thermal shielding capability of the thermal shielding metamaterial under steady state and the time to achieve thermal shielding effect under transient state as the comprehensive optimization objective, and rapidly optimizes the equivalent thermal conductivity of concentric rings. This method can be used to design thermal shielding metamaterial structures with different numbers of concentric rings, with strong design flexibility and wide applicability.

[0032] (2) The thermal shielding metamaterial design method provided by the present invention can be simulated and designed using COMSOL commercial software. The preparation process is clear, with low requirements for the external environment and extremely low requirements for theoretical basis and experimental conditions. Attached Figure Description

[0033] Figure 1 The model of the double-layer thermally shielded metamaterial set in the commercial software COMSOL in Example 1;

[0034] Figure 2 This shows the mesh generation for the double-layer thermally shielded metamaterial model in Example 1;

[0035] Figure 3 The Mv values ​​are the 1600 sets of simulation test samples selected in Example 1.

[0036] Figure 4 The thermal field distribution diagram of the thermal shielding metamaterial obtained in Example 1 is shown.

[0037] Figure 5 The graph shows the change of Mv value over time for the thermal shielding metamaterial obtained in Example 1.

[0038] Figure 6 To determine the temperature field distribution and isotherm diagram in the steady state of the double-layer thermally shielded metamaterial model, assuming the model is a homogeneous material. Detailed Implementation

[0039] The present invention will be further described and illustrated below with reference to the accompanying drawings and specific embodiments. The technical features of each embodiment of the present invention can be combined accordingly, provided that there is no mutual conflict.

[0040] Example 1

[0041] This embodiment prepares a rapid thermal shielding metamaterial, and the specific preparation method is carried out according to the following steps:

[0042] I. Determination of Design Objectives and Objective Functions: The comprehensive optimization objectives are set based on the thermal shielding metamaterial's thermal shielding capability under steady-state conditions and the time required to achieve thermal shielding effect under transient conditions.

[0043] In this step, both thermal shielding capability and the time to achieve thermal shielding effect are selected as multi-objective optimizations. The optimization goal is to make the thermal shielding metamaterial have the best possible thermal shielding effect while having the shortest possible time to achieve steady-state thermal shielding effect.

[0044] The steady-state thermal shielding capability is characterized by the surface integral of the absolute value of the temperature difference between each point in the shielded area under steady-state conditions and the temperature under ideal thermal shielding conditions, Mv. The smaller the Mv value, the better the steady-state thermal shielding effect. The time to achieve thermal shielding effect under transient conditions is characterized by the time tv, during which the average temperature of the shielded area rises from the initial temperature to near the ideal steady-state thermal shielding effect. The smaller the tv value, the faster the thermal shielding effect can be achieved.

[0045] After normalizing the Mv and tv values, they are added together according to a certain ratio to obtain the comprehensive optimization objective function. In this embodiment, the contribution ratios of the Mv and tv values ​​are 0.7 and 0.3, respectively.

[0046] II. A model of a double-layer thermally shielded metamaterial was established based on COMSOL commercial software.

[0047] Select a two-dimensional model in COMSOL and establish the solid heat transfer physical field.

[0048] like Figure 1 As shown, the physical field of solid heat transfer is a square with a side length of 5m. Concentric circular curves with radii of 1m, 1.5m and 2m are set out from the center outwards, and are denoted as the first curve, the second curve and the third curve, respectively. The center of the circle coincides with the center of the square. The ring formed by the second curve and the third curve is denoted as the first concentric ring, and the ring formed by the first curve and the second curve is denoted as the second concentric ring.

[0049] The temperature on the left side of the square is set to 0K, the temperature on the right side is set to 100K, and the top and bottom edges are thermally insulated. The inside of the first curve is the thermal shielding region, and the thermal conductivity of the thermal shielding region is set to 394W / (m·K). The thermal conductivity of the outer region of the third curve is 75~80W / (m·K). The equivalent thermal conductivity of the first concentric ring is denoted as k1, and the equivalent thermal conductivity of the second concentric ring is denoted as k2.

[0050] Mesh the model of the two-layer thermally shielded metamaterial, such as... Figure 2 As shown.

[0051] III. Selection and sampling of variable design parameters.

[0052] The equivalent thermal conductivity k1 of the first concentric ring and the equivalent thermal conductivity k2 of the second concentric ring are used as variables, and the variable range of the variables is set.

[0053] In this embodiment, to maximize the design space, the thermal conductivity of copper and organosilicon PMDS were referenced. Copper has a thermal conductivity of 394 W / (m·K), and PDMS has a thermal conductivity of 0.15 W / (m·K). Therefore, the variable range of thermal conductivity for each concentric ring layer was selected as 2–394 W / (m·K).

[0054] The equivalent thermal conductivity of the double-layer concentric rings was uniformly orthogonal, and 1600 sets of simulation test samples were selected. The results are shown in Table 1. Figure 3 The Mv values ​​are the corresponding values ​​for 1600 sets of simulation test samples.

[0055] Table 1 Simulation test sample results

[0056] 12 392 2.872700166 131.2 12 242 3.193709477 131.2 12 382 2.892556457 131.2 12 232 3.216541778 131.2 12 372 2.912645333 131.2 12 222 3.239441966 131.2 12 362 2.932966876 131.2 12 212 3.262366713 131.2 12 352 2.953520572 131.2 12 202 3.285262223 131.2 12 342 2.974305203 131.2 12 192 3.308061451 131.2 12 332 2.995318711 131.2 12 182 3.330680411 131.2 12 322 3.016558041 131.2 12 172 3.353013242 148.4 12 312 3.038018949 131.2 12 162 3.374925468 148.4 12 302 3.059695772 131.2 12 152 3.396244698 148.2 12 292 3.081581147 131.2 2 312 0.586652901 325.2 12 282 3.103665673 131.2 2 302 0.591538602 325.2 12 272 3.125937489 131.2 2 292 0.596507124 325.2 12 262 3.148381762 131.2 2 282 0.601560508 325.2 12 252 3.170980044 131.2 ... ... ... ...

[0057] IV. Calculation of thermal shielding capability under steady state based on steady-state solver.

[0058] The equivalent thermal conductivity k1 of the first concentric ring and the equivalent thermal conductivity k2 of the second concentric ring in 1600 sets of simulation test examples were input into the thermal shielding metamaterial model. Using the steady-state solver in the COMSOL commercial software, the Mv values ​​for different equivalent thermal conductivity conditions were obtained to evaluate the thermal shielding effect under these conditions. The steady-state thermal shielding effect data are as follows: Figure 4 As shown.

[0059] V. Calculation of transient thermal equilibrium velocity based on transient solver.

[0060] The equivalent thermal conductivity k1 of the first concentric ring and the equivalent thermal conductivity k2 of the second concentric ring in the 1600 sets of simulation test samples were input into the thermal shielding metamaterial model. The transient solver in the COMSOL commercial software was used to obtain the tv value under different equivalent thermal conductivity conditions, which was used to evaluate the speed at which the thermal shielding effect was achieved under these conditions.

[0061] In transient calculations, to save computational costs, the upper limit of the actual heat transfer time is set to 400 seconds. If the shielded area has not reached thermal steady state by 400 seconds, the calculation is abandoned, and the maximum time is retained as 400 seconds. The transient calculation saves the actual heat transfer time when the shielded area reaches thermal steady state as a parameter for the rate of reaching thermal steady state.

[0062] VI. Construction of artificial neural networks based on the iSight commercial software.

[0063] The artificial neural network structure parameters are set as follows: bias 0.2, weight 0.5, number of layers 1, and number of nodes 3.

[0064] VII. Multi-objective optimization design based on artificial neural network model.

[0065] Discarding data with tv values ​​exceeding 400 seconds, input the Mv value obtained in step four and the tv value obtained in step five into the artificial neural network model for multi-objective optimization calculation to obtain the equivalent thermal conductivity of each concentric ring under the optimal condition of the objective function.

[0066] After optimization, the equivalent thermal conductivity k1 = 11.4 W / (m·K) of the first concentric ring and the equivalent thermal conductivity k2 = 392.3 W / (m·K) of the second concentric ring were obtained as preferred parameters.

[0067] 8. Based on the above optimized data, a double-layer thermal shielding metamaterial model was designed and established.

[0068] (1) Determine the proportional relationship between the two materials in each layer of concentric rings:

[0069]

[0070] l1 + l2 = 1

[0071] Where: K s Let K1 be the equivalent thermal conductivity of each concentric ring layer under the optimal condition of the objective function, K2 be the thermal conductivity of material 1 in W / (m·K), and K2 be the thermal conductivity of material 2 in W / (m·K); l1 and l2 are the proportions of material 1 and material 2 in the concentric ring layer to be solved, respectively.

[0072] Substituting the equivalent thermal conductivity k1 = 11.4 W / (m·K) of the first concentric ring and the equivalent thermal conductivity k2 = 392.3 W / (m·K) of the second concentric ring into K, respectively... s Material 1 is copper, and material 2 is PDMS. Determine the proportions of copper and PDMS in the first and second concentric rings.

[0073] (2) Based on the ratio of the two materials in each concentric ring obtained in step (1), the density and specific heat capacity of each concentric ring are calculated to obtain the thermal shielding metamaterial.

[0074] This example demonstrates the fabrication of a thermal shielding metamaterial with rapid thermal shielding capabilities. Testing showed that the thermal shielding effect of this metamaterial under steady-state conditions is as follows: Figure 4 The Mv value is 2.88. The transient Mv variation with time and the central average temperature variation with actual heat transfer time are as follows: Figure 5 As shown. Meanwhile, to more significantly compare the thermal shielding effect of this thermal shielding metamaterial, simulation calculations were performed on a homogeneous material. The steady-state thermal field distribution is shown in [the figure]. Figure 6 .

[0075] The thermal shielding metamaterial prepared in this embodiment exhibits a steady-state Mv value of 2.88, which is significantly higher than the Mv value of 13.5 for homogeneous materials, demonstrating excellent steady-state thermal shielding capabilities. Furthermore, the metamaterial reaches steady state in approximately 125 seconds transiently, achieving a rapid thermal steady-state effect. Overall, it demonstrates excellent performance and achieves the desired rapid thermal shielding effect.

[0076] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the invention. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, all technical solutions obtained through equivalent substitution or transformation fall within the protection scope of the present invention.

Claims

1. A method for designing rapid thermal shielding metamaterials based on neural network optimization, characterized in that, The specific steps are as follows: S1: Taking the thermal shielding capability of the thermal shielding metamaterial under steady state and the time to achieve thermal shielding effect under transient state as the comprehensive optimization objectives, a comprehensive objective function is set; where, the thermal shielding capability under steady state is characterized by the surface integral Mv value of the absolute value of the temperature difference between each point of the shielding region under steady state and the temperature under ideal thermal shielding steady state, and the time to achieve thermal shielding effect under transient state is characterized by the time tv value of the average temperature of the shielding region rising from the initial temperature to near the ideal steady-state thermal shielding effect; S2: Establish a thermal shielding metamaterial model including multiple concentric rings; use the equivalent thermal conductivity of each concentric ring as a variable and set the variable range; uniformly orthogonally apply the equivalent thermal conductivity of the multiple concentric rings and select several sets of simulation test examples. S3: Input the equivalent thermal conductivity of each concentric ring in several sets of simulation test examples in step S2 into the thermal shielding metamaterial model, and obtain the Mv value under different equivalent thermal conductivity conditions based on steady-state solution, which is used to evaluate the thermal shielding effect under these conditions. S4: Input the equivalent thermal conductivity of each concentric ring in several sets of simulation test examples in step S2 into the thermal shielding metamaterial model, and obtain the tv value under different equivalent thermal conductivity conditions based on transient solution, which is used to evaluate the speed at which the thermal shielding effect is achieved under this condition; S5: Building an artificial neural network model; S6: Input the Mv value obtained in step S3 and the tv value obtained in step S4 into the artificial neural network model for multi-objective optimization calculation to obtain the equivalent thermal conductivity of each concentric ring under the optimal condition of the objective function. S7: Based on the equivalent thermal conductivity of each concentric ring under the optimal condition of the objective function obtained in step S6, a thermal shielding metamaterial is designed and established based on the neutral inclusion principle.

2. The design method according to claim 1, characterized in that, In step S1, the Mv and tv values ​​are normalized and then added together in a certain proportion to obtain the comprehensive optimization objective function.

3. The design method according to claim 1, characterized in that, The thermal shielding metamaterial model described in step S1 was established using COMSOL commercial software.

4. The design method according to claim 1, characterized in that, In step S2, the variable range of thermal conductivity of each concentric ring is set to 2–394 W / (m·K).

5. The design method according to claim 1, characterized in that, The heat-shielding metamaterial model consists of two concentric rings; the specific details of establishing the two-layer heat-shielding metamaterial model are as follows: In the COMSOL commercial software, a two-dimensional model is selected, and a solid heat transfer physical field is established. The solid heat transfer physical field is a square with a side length of 5m. From the center outwards, concentric circular curves with radii of 1m, 1.5m, and 2m are set sequentially, and are respectively denoted as the first curve, the second curve, and the third curve. The center of the circle coincides with the center of the square. The ring formed by the second curve and the third curve is denoted as the first layer of concentric rings, and the ring formed by the first curve and the second curve is denoted as the second layer of concentric rings. The temperature on the left side of the square is set to 0K, the temperature on the right side to 100K, and the top and bottom edges are thermally insulated. The interior of the first curve is the thermal shielding region, and the thermal conductivity of the thermal shielding region is set to 394W / (m·K). The thermal conductivity of the outer region of the third curve is 75-80W / (m·K). The equivalent thermal conductivity of the first concentric ring is denoted as k1, and the equivalent thermal conductivity of the second concentric ring is denoted as k2. The model of the two thermal shielding metamaterials is meshed.

6. The design method according to claim 5, characterized in that, In step S4, to reduce calculation time, the calculation stop condition is set to the average temperature of the shielded area reaching 45K, or the actual heat transfer time reaching 400 seconds.

7. The design method according to claim 5, characterized in that, Step S7 is as follows: S71: Determine the proportional relationship between the two materials in each layer of concentric rings: l1+l2＝1 Where: K s Let K1 be the equivalent thermal conductivity of each concentric ring layer under the optimal condition of the objective function, K2 be the thermal conductivity of material 1 in W / (m·K), and K2 be the thermal conductivity of material 2 in W / (m·K); l1 and l2 are the proportions of material 1 and material 2 in the concentric ring layer to be solved, respectively. S71: Based on the ratio of the two materials in each concentric ring obtained in step S71, the density and specific heat capacity of each concentric ring are obtained, thus completing the design of the thermal shielding metamaterial.

8. The design method according to claim 1, characterized in that, In step S5, the artificial neural network model is built using the commercial software ISight.

9. The design method according to claim 1, characterized in that, The parameters of the artificial neural network model are as follows: bias 0.2, weight 0.5, number of layers 1, number of nodes 3.

10. A thermally shielding metamaterial obtained using the design method described in any one of claims 1 to 9.

Images