Active sensing laser protection composite material and design method thereof

Abstract

The invention discloses an active sensing laser protection composite material and a design method thereof, and belongs to the technical field of composite materials, the composite material is a woven reinforced resin matrix composite material, the structural form comprises but is not limited to orthogonal three-direction, 2.5 D and fine weaving puncture, a temperature sensor array is embedded in the composite material, and a ceramic tube array is arranged in the composite material. The composite material is connected with a single chip microcomputer through a cooling medium storage pump, the single chip microcomputer is connected with the ceramic tube array, and the flow of a cooling medium in the ceramic tube array is adjusted in real time through the control algorithm; according to the active sensing laser protection composite material and the design method thereof, the temperature field of the composite material is sensed by embedding the platinum resistor temperature sensor array, and the laser irradiation position, the energy density and the temperature field change are inversed in real time in combination with a physical information neural network algorithm, so that the cooling flow is intelligently adjusted, and the working efficiency is improved. And efficient laser protection is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of composite materials, and in particular to an active sensing laser protection composite material and a design method thereof. Background Art

[0002] With the continuous development of laser technology, laser weapons, as a new type of high-energy weapon, have been widely used in military, aerospace and other fields. Laser weapons can accurately hit targets with high-power laser beams, but they are prone to cause damage to equipment or personnel during application, especially high-temperature damage to surface materials. Traditional laser protection technology mainly relies on the thermophysical properties of materials, such as absorption, reflection and heat dissipation characteristics. However, these methods often have certain limitations, such as the inability to dynamically adjust when the laser intensity changes, or the inability to respond to rapidly changing heat loads in a timely manner, making it difficult to provide continuous and effective protection.

[0003] In recent years, composite materials have been widely used in aerospace, military equipment and protection fields due to their excellent mechanical properties and thermal stability. However, under the condition of high laser radiation intensity, the thermal management ability of composite materials themselves is still limited, especially under the condition of rapid thermal loading and transient heat flux density changes, traditional passive thermal management methods are difficult to meet the protection requirements. Therefore, how to achieve more precise heat flow control in composite materials has become an important issue to improve laser protection capabilities. Summary of the invention

[0004] The purpose of the present invention is to provide an active sensing laser protection composite material and a design method thereof, which senses the temperature field of the composite material by embedding a platinum resistance temperature sensor array, and combines a physical information neural network algorithm to invert the laser irradiation position, energy density and temperature field changes in real time, thereby intelligently adjusting the cooling flow and providing efficient laser protection.

[0005] To achieve the above objectives, the present invention provides an active sensing laser protection composite material, which is a woven reinforced resin-based composite material, and the structural forms include but are not limited to orthogonal three-way, 2.5D and fine-woven puncture. The composite material has an embedded temperature sensor array and a built-in ceramic tube array, and the composite material is connected to a single-chip microcomputer through a cooling medium storage pump.

[0006] Preferably, the temperature sensor array is a platinum resistor array, which is located inside the composite material. The platinum resistor array is located about 5 mm away from the surface inside the composite material. The platinum resistor sensor can sense temperature changes by measuring changes in resistance and feed back real-time temperature data to the control system to accurately monitor temperature changes on the surface of the composite material.

[0007] Preferably, the ceramic tube array is a silicon carbide high temperature resistant ceramic tube array, and the ceramic tube material includes high temperature resistant and high strength materials such as silicon carbide and alumina. The ceramic tube array realizes the cooling function through the conduction of liquid or gas cooling medium, and the cooling medium includes but is not limited to water, carbon dioxide, helium, nitrogen, etc.

[0008] Preferably, a preset laser protection control strategy is stored in the single chip microcomputer, and a control algorithm runs in real time in the single chip microcomputer.

[0009] Preferably, the ceramic tube array is connected to the single-chip microcomputer through the cooling medium storage pump, and the single-chip microcomputer adjusts the flow rate of the cooling medium in real time through the control algorithm, and transports it to the surface of the composite material through the ceramic tube array to ensure that the surface temperature of the material is maintained within a safe range, avoiding material damage or performance degradation due to overheating.

[0010] Preferably, the training process of the control algorithm comprises the following steps:

[0011] S1, data preparation, input the temperature sensor array position, actual temperature data and geometric characteristics of the composite material, define the training data set and test data set;

[0012] S2, create a physical information neural network (PINN) model;

[0013] S3. Define a physical information loss function based on the heat conduction equation;

[0014] S4, defining a sensor loss function, calculating the error between the temperature output by the network and the actual temperature data of the temperature sensor array;

[0015] S5. Define a sweating amount function to calculate the sweating amount, calculate the local temperature rise and laser heat flux according to the temperature field predicted by the physical information neural network model; calculate the required sweating amount according to the temperature increment and heat flux density;

[0016] S6, adjusting the flow rate of the cooling medium in the ceramic tube array according to the sweating amount, inputting the calculated sweating amount into the ceramic tube array, controlling the flow rate of the cooling medium, adjusting the sweating amount according to the real-time temperature, and ensuring that the surface temperature is within a safe range;

[0017] S7, perform training and optimization, use gradient descent method (such as Adam optimizer) to optimize physical information loss and sensor loss, minimize the loss, use back propagation, and update the weights of the neural network;

[0018] S8. After the training is completed, the trained model is used to predict the new temperature field and calculate the corresponding sweating amount, and the predicted temperature distribution and recommended sweating amount are output.

[0019] Preferably, the formula of the physical information loss function in step S3 is as follows:

[0020]

[0021] in, is the physical information error term, is the data error term, λ PDE and λ data is a hyperparameter that trades off the importance of the two error terms.

[0022] Preferably, the formula of the sensor loss function in step S4 is as follows:

[0023]

[0024] Where N is the number of temperature sensors, T pred,i is the temperature at the i-th temperature sensor location predicted by the model, T sensor,i is the actual temperature measured by the i-th temperature sensor.

[0025] Preferably, the formula of the sweat volume function in step S6 is as follows:

[0026] Sweat volume = f (temperature increment, heat flux density);

[0027] A design method for an active sensing laser protection composite material comprises the following steps:

[0028] Step 1: Select a braided reinforced resin-based composite material, the structural forms of which include orthogonal three-dimensional, 2.5D and fine-weave puncture. This composite material structure can effectively improve mechanical strength and thermal stability, and is suitable for thermal protection requirements in high-intensity laser environments;

[0029] Step 2: embed a platinum resistance array temperature sensor in the composite material. The temperature sensor array is located inside the composite material at a distance of 5 mm from the surface, and senses the temperature through resistance changes.

[0030] Step 3: Using the temperature points sensed by the temperature sensor array and combining it with the self-written control algorithm based on physical information neural network, the temperature field, laser strike position and laser energy density are inverted in real time;

[0031] Step 4, writing the trained control algorithm into the single chip microcomputer, and controlling the sweating amount of the ceramic tube array in the composite material in real time through the single chip microcomputer;

[0032] Step 5: Achieve sweat cooling through a silicon carbide ceramic tube array; select a suitable cooling medium;

[0033] Step 6: Use the control algorithm to adjust the cooling effect according to the actual situation and control the amount of sweating to achieve laser protection.

[0034] Therefore, the present invention adopts the above-mentioned active sensing laser protection composite material and the design method thereof, which has the following beneficial effects:

[0035] (1) By embedding platinum array temperature sensors in the composite material to sense the temperature field under the action of laser in real time, and combining the physical information neural network algorithm to invert the laser heat flux density and transient temperature distribution, the changes of laser radiation can be monitored in real time;

[0036] (2) Through the active sweating cooling method of the ceramic tube array built into the composite material, the sweating flow of the ceramic tube array is intelligently adjusted according to the algorithm, thereby effectively improving the thermal management capability of the composite material and realizing active protection under continuous laser irradiation;

[0037] (3) Not only does it have significant advantages in improving the thermal protection performance of composite materials, but its intelligent control method can also adjust the cooling strategy in real time according to the actual laser radiation conditions, ensuring continuous and effective protection in complex and dynamic laser environments, and has broad application prospects.

[0038] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The present invention is a flow chart of a design method of an active sensing laser protection composite material. DETAILED DESCRIPTION

[0040] The following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Example

[0042] like Figure 1 As shown, an active sensing laser protection composite material and a design method thereof include the following steps:

[0043] Step 1. Select a woven reinforced resin-based composite material. The structural forms include orthogonal three-way, 2.5D and fine-woven puncture. This composite material structure can effectively improve the mechanical strength and thermal stability, and is suitable for thermal protection requirements in high-intensity laser environments. The composite material has a built-in ceramic tube array and is connected to a single-chip microcomputer through a cooling medium storage pump.

[0044] Step 2: Embed a platinum resistance array temperature sensor in the composite material. The temperature sensor array is located inside the composite material at 5 mm from the surface. The temperature is sensed by resistance changes. The platinum resistance sensor can sense temperature changes by measuring resistance changes and feed back real-time temperature data to the control system to accurately monitor temperature changes on the surface of the composite material.

[0045] Through precise temperature sensing and distribution, the temperature sensor array can cover different areas of the composite material to monitor the temperature changes in the laser irradiation area in real time and provide accurate data support for subsequent cooling control.

[0046] Step 3: Use the temperature points sensed by the temperature sensor array and combine it with the independently written control algorithm based on physical information neural network to invert the temperature field, laser strike position and laser energy density in real time.

[0047] The control algorithm can calculate the thermal effect of the laser and the spatial distribution of the material temperature based on the laser irradiation conditions and the thermal response of the material, providing a decision-making basis for cooling control. The control algorithm improves the accuracy and efficiency of laser protection by continuously obtaining data feedback from the sensor array.

[0048] The training process of the control algorithm includes the following steps:

[0049] S1. Data preparation: input the temperature sensor array position, actual temperature data and geometric characteristics of the composite material, and define the training data set and test data set.

[0050] S2. Create a physical information neural network (PINN) model, which consists of multiple fully connected layers. The activation function of each fully connected layer uses the tanh activation function. The number of layers and neurons in each layer are hyperparameters. The input of the network (position x) is defined. The input x passes through multiple fully connected layers in sequence through forward propagation to the output layer. The output layer outputs temperature T, and there is no activation function.

[0051] S3. Define a physical information loss function based on the heat conduction equation;

[0052] The heat conduction equation satisfies the following formula:

[0053]

[0054] Among them, T pred is the temperature predicted by the model, t is the time, x is the position coordinate, and α is the thermal diffusion coefficient.

[0055] The formula for the physical information error term is as follows:

[0056]

[0057] The formula for the data error term is as follows:

[0058]

[0059] Among them, T sensor The temperature actually measured by the temperature sensor.

[0060] The formula of the physical information loss function is as follows:

[0061]

[0062] Among them, λ PDE and λ data is a hyperparameter that trades off the importance of the two error terms.

[0063] S4. Define the sensor loss function and calculate the error between the temperature output by the network and the actual temperature data of the temperature sensor array.

[0064] The formula for the sensor loss function is as follows:

[0065]

[0066] Where N is the number of temperature sensors, T pred,i is the temperature at the i-th temperature sensor location predicted by the model, T sensor,i is the actual temperature measured by the i-th temperature sensor.

[0067] S5. Define the sweating amount function to calculate the sweating amount, calculate the local temperature rise and laser heat flux based on the temperature field predicted by the physical information neural network model; calculate the required sweating amount based on the temperature increment and heat flux density.

[0068] Temperature increment T increase =T pred -T threshold , T threshold is the temperature threshold.

[0069] The formula of the sweating amount function is sweating amount = f (temperature increment, heat flux density).

[0070] In this embodiment, it is assumed that the heat flux is proportional to the absolute value of the temperature, and the heat flux is defined as: H = |T pred |, In practical applications, the heat flux density will depend on more complex physical models.

[0071] Therefore, in this embodiment, the formula of the sweat volume function is as follows:

[0072] Sweat volume = 0.1*T increase *H, while limiting the amount of sweating to between 0 and 1.

[0073] S6. Adjust the flow rate of the cooling medium in the ceramic tube array according to the sweating amount, input the calculated sweating amount into the ceramic tube array, control the flow rate of the cooling medium, adjust the sweating amount according to the real-time temperature, and ensure that the surface temperature is within a safe range.

[0074] S7, training and optimization, using the gradient descent method to optimize the physical information loss and sensor loss, and minimize the loss. In this embodiment, the Adam optimizer is used to use back propagation to update the weights of the neural network;

[0075] S8. After the training is completed, the trained model is used to predict the new temperature field and calculate the corresponding sweating amount, and the predicted temperature distribution and recommended sweating amount are output.

[0076] Step 4: Write the trained control algorithm into the single chip microcomputer, and use the single chip microcomputer to control the sweating amount of the ceramic tube array in the composite material in real time.

[0077] The control algorithm runs in real time in the single-chip microcomputer. The single-chip microcomputer stores the preset laser protection control strategy and adjusts the control parameters according to the real-time data to control the amount of sweating. The single-chip microcomputer is connected to the ceramic tube array in the composite material through the cooling medium storage pump. The control algorithm adjusts the flow of the cooling medium in real time and transports it to the surface of the composite material through the ceramic tube array to ensure that the surface temperature of the material is maintained within a safe range to avoid material damage or performance degradation due to overheating.

[0078] Step 5: Achieve sweat cooling through a silicon carbide ceramic tube array; select a suitable cooling medium.

[0079] Ceramic tube materials include high temperature resistant and high strength materials such as silicon carbide and alumina, which can operate stably in high temperature environments and maintain good thermal conductivity and thermal resistance. Ceramic tube arrays have good heat resistance and mechanical strength and can be used in high power laser protection processes.

[0080] The ceramic tube array achieves cooling through the conduction of liquid or gas cooling media. The cooling media include but are not limited to water, carbon dioxide, helium, nitrogen, etc. The choice of cooling media is adjusted according to different laser environments, composite material types and protection requirements, thereby effectively reducing the surface temperature of the material.

[0081] Step 6: Use the control algorithm to adjust the cooling effect according to the actual situation and control the amount of sweating to achieve laser protection.

[0082] Therefore, the present invention adopts the above-mentioned active sensing laser protection composite material and its design method, which not only has significant advantages in improving the thermal protection performance of the composite material, but also its intelligent control method can adjust the cooling strategy in real time according to the actual laser radiation situation, ensuring continuous and effective protection effect in complex and dynamic laser environments, and has broad application prospects.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. An active sensing laser protection composite material, characterized by: The composite material is a woven reinforced resin-based composite material, and the structural forms include orthogonal three-dimensional, 2.5D and fine-woven puncture. The composite material has an embedded temperature sensor array and a built-in ceramic tube array. The composite material is connected to a single-chip microcomputer via a cooling medium storage pump.

2. The active sensing laser protection composite material according to claim 1, characterized in that: The temperature sensor array is a platinum resistor array, and the platinum resistor array is arranged inside the composite material at a position 5 mm away from the surface thereof.

3. The active sensing laser protection composite material according to claim 1, characterized in that: The ceramic tube array is a silicon carbide high temperature resistant ceramic tube array, and the ceramic tube array realizes cooling function through conduction of liquid or gas cooling medium.

4. The active sensing laser protection composite material according to claim 1, characterized in that: The single chip microcomputer stores a preset laser protection control strategy, and the single chip microcomputer runs a control algorithm in real time.

5. The active sensing laser protection composite material according to claim 4, characterized in that: The ceramic tube array is connected to the single chip microcomputer via the cooling medium storage pump. The single chip microcomputer adjusts the flow rate of the cooling medium in real time through the control algorithm and transports the cooling medium to the surface of the composite material through the ceramic tube array.

6. The active sensing laser protection composite material according to claim 4, characterized in that: The training process of the control algorithm includes the following steps: S1, data preparation, input the temperature sensor array position, actual temperature data and geometric characteristics of the composite material, define the training data set and test data set; S2, create a physical information neural network model; S3. Define a physical information loss function based on the heat conduction equation; S4, defining a sensor loss function, calculating the error between the temperature output by the network and the actual temperature data of the temperature sensor array; S5. Define a sweating amount function to calculate the sweating amount, calculate the local temperature rise and laser heat flux according to the temperature field predicted by the physical information neural network model; calculate the required sweating amount according to the temperature increment and heat flux density; S6, adjusting the flow rate of the cooling medium in the ceramic tube array according to the sweating amount, inputting the calculated sweating amount into the ceramic tube array, controlling the flow rate of the cooling medium, adjusting the sweating amount according to the real-time temperature, and ensuring that the surface temperature is within a safe range; S7, perform training and optimization, use the gradient descent method to optimize the physical information loss and sensor loss, minimize the loss, use back propagation, and update the weights of the neural network; S8. After the training is completed, the trained model is used to predict the new temperature field and calculate the corresponding sweating amount, and the predicted temperature distribution and recommended sweating amount are output.

7. The active sensing laser protection composite material according to claim 6, characterized in that: The formula of the physical information loss function of step S3 is as follows: in, is the physical information error term, is the data error term, λ PDE and λ data is a hyperparameter that trades off the importance of the two error terms.

8. The active sensing laser protection composite material according to claim 6, characterized in that: The formula of the sensor loss function of step S4 is as follows: Where N is the number of temperature sensors, T pred,i is the temperature at the i-th temperature sensor location predicted by the model, T sensor,i is the actual temperature measured by the i-th temperature sensor.

9. The active sensing laser protection composite material according to claim 6, characterized in that: The formula of the sweat volume function in step S6 is as follows: Sweat volume = f (temperature increment, heat flux density).

10. A design method for an active sensing laser protection composite material according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1, selecting a braided reinforced resin-based composite material, the structural forms of which include orthogonal three-dimensional, 2.5D and fine braid puncture; Step 2: embed a platinum resistance array temperature sensor in the composite material. The temperature sensor array is located inside the composite material at a distance of 5 mm from the surface, and senses the temperature through resistance changes. Step 3: Using the temperature points sensed by the temperature sensor array and combining it with the self-written control algorithm based on physical information neural network, the temperature field, laser strike position and laser energy density are inverted in real time; Step 4, writing the trained control algorithm into the single chip microcomputer, and controlling the sweating amount of the ceramic tube array in the composite material in real time through the single chip microcomputer; Step 5: Achieve sweat cooling through a silicon carbide ceramic tube array; select a suitable cooling medium; Step 6: Use the control algorithm to adjust the cooling effect according to the actual situation and control the amount of sweating to achieve laser protection.

Images