Detector moving laser irradiation damage assessment method and system

Abstract

The invention belongs to the technical field of photoelectricity, and relates to a detector moving laser irradiation damage assessment method and system. The evaluation method comprises the following steps: determining mobile laser parameters and detector structure material attribute parameters; constructing a detector solid heat transfer transient model; setting physical field boundary conditions of the solid heat transfer transient model and performing grid division; setting solver parameters, specifically, inputting the moving laser pulse width and the moving laser frequency into a pre-trained linear neural network model, and calculating by applying an expression of the model to obtain the solver parameters; and based on the solver parameters, solving the solid heat transfer transient model in the solver, judging the thermal damage condition of the detector by calling domain ordinary differential and differential algebraic equation modules, and if it is determined that the detector is damaged, calculating the damage area and volume of the detector to obtain the spatial distribution condition of the damage area of the detector.

Description

Technical Field

[0001] The present invention relates to the field of optoelectronic technology, and in particular to a method and system for evaluating damage caused by moving laser irradiation of a detector. Background Art

[0002] In the field of optoelectronic technology, HgCdTe detectors are extremely susceptible to interference and damage from lasers due to their high precision, high sensitivity, and high resolution. Accurately determining the damaged area of ​​HgCdTe detectors under laser irradiation is crucial for evaluating the detector's ability to resist laser damage, optimizing protection strategies, and improving overall system performance.

[0003] Traditional damage determination methods mostly rely on physical inspections after the experiment, such as microscopic observation and scanning electron microscopy (SEM) analysis. Although these methods are intuitive, they have limitations such as high cost and time consumption. In addition, the HgCdTe detector itself is expensive, and the use of laser sources for damage experiments is difficult and costly. In addition, most experiments revolve around static laser interference damage and do not consider the irradiation of mobile laser light sources.

[0004] In summary, it is usually impossible to obtain the characteristics of detector movement laser irradiation damage through a large number of experiments. Summary of the invention

[0005] The present invention provides a detector moving laser irradiation damage assessment method and system, which assess the damage of the detector caused by moving laser irradiation, obtain the temperature field change of the detector under the moving laser by building a model and solving it, and assess the damage of the detector.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: In a first aspect, the present invention provides a method for evaluating damage caused by laser irradiation caused by moving a detector, the method comprising the following steps: Determine the moving laser parameters and the detector structure material property parameters; Construct a transient model of solid heat transfer in the detector; Set the boundary conditions of the solid heat transfer transient model physics field and perform meshing; Set solver parameters; the solver parameters include an initial step size of the solver, a storage time step of a laser irradiation time period and a laser non-irradiation time period, and a maximum step size constraint of a laser irradiation time period and a laser non-irradiation time period; the solver parameters are determined by using a pre-trained linear neural network model, specifically: inputting a mobile laser pulse width and a mobile laser frequency into a pre-trained linear neural network model, and using a pre-trained linear neural network model expression to calculate and obtain the solver parameters; Based on the solver parameters, the solid heat transfer transient model is solved in the solver, and the thermal damage of the detector is determined by calling the domain ordinary differential and differential algebraic equation modules. If it is determined that the detector is damaged, the damaged area and volume of the detector are calculated to obtain the spatial distribution of the damaged area of ​​the detector.

[0007] As a possible implementation method, the pre-trained linear neural network model includes an input layer and an output layer; wherein the parameters of the input layer include a moving laser pulse width node and a moving laser frequency node; the parameters of the output layer include a storage time step node, an initial step node, and a maximum step constraint node of the solver in the laser irradiation time period and the laser non-irradiation time period.

[0008] As a possible implementation, the pre-trained linear neural network model expression is: ; in, is the weight matrix, ; is the bias vector, ; is the storage time step of the solver during the laser irradiation period; The storage time step of the solver during the laser non-irradiation period; is the initial step size of the solver; is the maximum step size constraint of the solver during the laser irradiation period; It is the maximum step size constraint of the solver during the laser non-irradiation period; To move the laser pulse width; To shift the laser frequency.

[0009] As a possible implementation method, the parameters of the input layer and the parameters of the output layer are normalized, and the normalization range is [0, 1]; the normalized expression is: ; in, is the result after normalization of the corresponding parameter value in the training data set; is the corresponding parameter value in the training data set; and are the minimum and maximum values ​​of the corresponding parameters in the training data set, respectively.

[0010] As a possible implementation, , and The parameters must satisfy physical constraints: ; If the prediction results do not meet the above constraints, they should be corrected in the following ways: ; .

[0011] As a possible implementation method, free triangulation is used for meshing the upper surface of the silicon substrate and the lower surface of the indium column array, and the segment size of the mesh is predefined to be finer; swept meshing is performed on the rest of the transient model.

[0012] As a possible implementation, the mobile laser pulse width is 100ps-500ns, the repetition frequency is 1K-10K, and the moving speed is 0-500mm / s.

[0013] As a possible implementation method, the backward difference formula is set in the solver to solve the time step; the initial step size of the solver, the storage time step size of the solver in the laser irradiation section, the storage time step size of the solver in the laser non-irradiation time period, the maximum step size constraint of the solver in the laser irradiation time period, and the maximum step size constraint of the solver in the laser non-irradiation time period are all set according to the results of the pre-trained linear neural network model.

[0014] As a possible implementation method, the method for determining and evaluating the thermal damage of the detector is to call the domain ordinary differential and differential algebraic equation modules to obtain the highest temperature at a certain location in the solid heat transfer transient model in the past time; if the highest temperature is greater than the melting point of the detector material, the detector is damaged; and then the spatial distribution of the damaged area of ​​the detector is obtained by calculating the damaged area and volume.

[0015] In a second aspect, the present invention provides a detector moving laser irradiation damage assessment system, specifically comprising: An evaluation parameter configuration unit, used to configure evaluation parameters, wherein the evaluation parameters include moving laser parameters and detector structure material property parameters; The detector solid heat transfer transient model building unit builds the solid heat transfer transient model of the detector and determines the boundary conditions of the heat transfer physical field of the solid heat transfer transient model; Meshing unit, which performs meshing on the transient solid heat transfer model based on the heat transfer physical field; A solver parameter configuration unit, used to configure solver parameters, the solver parameters include an initial step size of the solver, a laser irradiation time period and a storage time step of the laser irradiation time period, and a maximum step size constraint of the laser irradiation time period and the laser non-irradiation time period; the solver parameters are determined by using a pre-trained linear neural network model, specifically: the mobile laser pulse width and the mobile laser frequency are input into the pre-trained linear neural network model, and the pre-trained linear neural network model expression is used to calculate and obtain the solver parameters; The detector damage determination unit applies the solver parameters to solve the solid heat transfer transient model in the solver, and determines the thermal damage of the detector by calling the domain ordinary differential and differential algebraic equation modules. If it is determined that the detector is damaged, the damaged area and volume of the detector are calculated to obtain the spatial distribution of the damaged area of ​​the detector.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. The present invention proposes a method for evaluating damage caused by moving laser irradiation of a detector. Compared with the traditional experiment focusing on the damage caused by fixed-point irradiation of the detector by static laser, the present invention can effectively solve the problem of evaluating damage caused by moving laser irradiation of the detector.

[0017] 2. The present invention proposes a detector moving laser irradiation damage assessment method, which is easy to implement, has high accuracy, short time consumption and low cost.

[0018] 3. The present invention proposes a method for evaluating damage of a moving detector irradiated by laser, which helps to optimize the protection strategy of the detector against laser to improve the radiation resistance of the detector, and can also save experimental costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 Flow chart of the laser irradiation damage assessment method for detector movement; Figure 2 A schematic diagram of a detector structure material according to an embodiment of the present invention; Figure 3 A schematic diagram of a laser pulse switch function according to an embodiment of the present invention; Figure 4 A schematic diagram of grid division according to an embodiment of the present invention; Figure 5 is a damage volume change curve diagram of the HgCdTe layer in an embodiment of the present invention; Figure 6is a curve diagram of the damage area change on the lower surface of the HgCdTe layer in an embodiment of the present invention; Figure 7 The temperature field distribution of the HgCdTe detector at three typical irradiation times (t1=1.2us, t2=1201.2us, t3=2334.5us) provided in the embodiment of the present invention; Figure 8 The damage conditions of the lower surface of the HgCdTe layer at three typical irradiation times (t1=1.2us, t2=1201.2us, t3=2334.5us) provided in the embodiments of the present invention. DETAILED DESCRIPTION

[0020] In order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and their order is not limited. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0021] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0022] In the present invention, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. The following at least one item (items) or similar expressions thereof refer to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one item (items) of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.

[0023] The embodiment of the present invention aims to provide a method and system for evaluating damage caused by mobile laser irradiation of a detector, which can efficiently and accurately evaluate the damage caused by mobile laser irradiation of the detector by constructing a model, optimizing solution parameters and solving the problem. The specific implementation methods are as follows: In a first aspect, an embodiment of the present invention provides a method for evaluating damage caused by laser irradiation caused by moving a detector. Specifically, see Figure 1 , the evaluation method includes the following steps: Determine the moving laser parameters and the detector structure and material property parameters; As a possible implementation, the mobile laser pulse width is 100ps-500ns, the repetition frequency is 1K-10K, and the moving speed is 0-500mm / s.

[0024] As a possible implementation, the moving laser parameters include laser pulse width, laser single pulse energy, laser irradiation center point position, laser spot size, laser repetition frequency and laser moving speed.

[0025] The example of irradiating HgCdTe detector with a high repetition rate short pulse moving laser source with a pulse width of 200ns, a repetition rate of 10KHz and a moving speed of 226.27mm / s is used for explanation.

[0026] Exemplarily, the detailed parameters of the mobile laser used in this embodiment are shown in Table 1 below: Table 1 Mobile laser parameter table This embodiment uses a HgCdTe detector, which is a multi-layer structure. Figure 2 As shown, the multi-layer structure of the detector is CdZnTe layer, HgCdTe layer, indium column array and silicon substrate from bottom to top; wherein, the thickness of the CdZnTe layer is 50um; the thickness of the HgCdTe layer is 10um; the radius of the indium column is 10um, and the height is 10um. The indium columns are evenly arranged in an 11×11 array on the upper surface of the silicon substrate with a spacing of 15um; the thickness of the silicon substrate is 50um.

[0027] As a possible implementation, the detector material property parameters include density, thermal conductivity, and heat capacity; For example, the detector material property parameters are shown in Table 2 below: Table 2 Detector material property parameters Construct the solid heat transfer transient model of the detector, set the boundary conditions of the transient model physical field and perform meshing; As a possible implementation method, COMSOL Multiphysics software is used to build a solid heat transfer transient model of the detector. Specifically, solid heat transfer, domain ordinary differential and differential algebraic equation modules are added to the COMSOL Multiphysics software, and the boundary conditions of the physical field are set.

[0028] For example, the solid heat transfer module expression is: in, T is the instantaneous temperature; is the material density; is the heat capacity of the material; is the thermal conductivity of the material.

[0029] For example, the expression of the thermal radiation of the detector surface to the environment is: ; in, is the surface emissivity, is the Stefan constant, is the ambient temperature. Since the operating temperature of the HgCdTe detector is generally maintained at about 77K, the ambient temperature is set to 77K. For example, the convective heat transfer heat flux expression corresponding to the convective heat transfer between the detector surface and the environment is: ; in, h is the convective heat transfer coefficient; is the ambient temperature; T is the instantaneous temperature.

[0030] For example, when the moving laser irradiates the HgCdTe detector, the laser beam directly passes through the CdZnTe layer, and most of the energy is deposited in the HgCdTe layer. Therefore, the laser heat source on the HgCdTe layer is set as a body heat source, and the corresponding laser energy deposition expression is: ; ; ; ; ; in, is the laser heat source, is the absorption coefficient of HgCdTe to laser, is the reflectivity of HgCdTe to laser, is the position of any point on the laser energy deposition surface, ( ) is the center position of the spot on the laser energy deposition surface, is the radius of the laser spot, For time, For laser The velocity component in the direction, For laser The velocity component in the direction, ( ) is the initial position of the spot on the laser energy deposition surface, For the laser beam Function of direction, is the average output power of a single pulse of the laser, is the laser single pulse energy, is the laser pulse width, is the laser pulse switching time function, and the function in the embodiment is specifically as follows Figure 3 As shown, is the laser repetition frequency, , It is a Gaussian pulse function with a peak value of 1 and a standard deviation of the pulse width.

[0031] As a possible implementation, Figure 4 As shown, the meshing is performed by using free triangulation for the upper surface of the silicon substrate and the lower surface of the indium column array, and the segment element size of the mesh is predefined to be finer; the rest of the solid heat transfer transient model is meshed by swept meshing.

[0032] Set solver parameters; the solver parameters include an initial step size of the solver, a storage time step of a laser irradiation time period and a laser non-irradiation time period, and a maximum step size constraint of a laser irradiation time period and a laser non-irradiation time period; the solver parameters are determined by using a pre-trained linear neural network model, specifically: inputting a mobile laser pulse width and a mobile laser frequency into a pre-trained linear neural network model, and using a pre-trained linear neural network model expression to calculate and obtain the solver parameters; As a possible implementation method, the pre-trained linear neural network model includes an input layer and an output layer; wherein the parameters of the input layer include a moving laser pulse width node and a moving laser frequency node; the parameters of the output layer include a storage time step node, an initial step node, and a maximum step constraint node of the solver in the laser irradiation time period and the laser non-irradiation time period.

[0033] As a possible implementation, the pre-trained linear neural network model expression is: ; in, is the weight matrix, ; is the bias vector, ; is the storage time step of the solver during the laser irradiation period; The storage time step of the solver during the laser non-irradiation period; is the initial step size of the solver; is the maximum step size constraint of the solver during the laser irradiation period; It is the maximum step size constraint of the solver during the laser non-irradiation period; To move the laser pulse width; To shift the laser frequency.

[0034] As a possible implementation method, the parameters of the input layer and the parameters of the output layer are normalized, and the normalization range is [0, 1]; the normalized expression is: ; in, is the result after normalization of the corresponding parameter value in the training data set; is the corresponding parameter value in the training data set; and are the minimum and maximum values ​​of the corresponding parameters in the training data set, respectively.

[0035] As a possible implementation, , and The parameters must satisfy physical constraints: ; If the prediction results do not meet the above constraints, they should be corrected in the following ways: ; .

[0036] Based on the solver parameters, the solid heat transfer transient model is solved in the solver, and the thermal damage of the detector is determined by calling the domain ordinary differential and differential algebraic equation modules. If it is determined that the detector is damaged, the damaged area and volume of the detector are calculated to obtain the spatial distribution of the damaged area of ​​the detector.

[0037] In the specific implementation, the backward difference formula is used to solve the time step in the solver; the solver step size is set to adaptive; the initial step size , set to ; During the laser irradiation period, the maximum step length is set to one tenth of the laser pulse; during the laser non-irradiation period, the maximum step length is set to one third of the pulse period.

[0038] For example, the domain ordinary differential and differential algebraic equation modules are called to obtain the maximum temperature of a location in the solid heat transfer transient model in the past time step, specifically to construct a model about the field variables u About Time t The second-order differential equation is as follows, where the field variable Used to store the maximum temperature; g is the source item, which is set to determine whether the current temperature is the maximum temperature of the grid node.

[0039] ; For example, it is determined whether the maximum temperature exceeds the melting point of the detector material. If the maximum temperature exceeds the melting point of the detector, it is determined that the detector is damaged. Then, the damaged volume of the HgCdTe layer of the detector and the damaged area of ​​the lower surface of the HgCdTe layer are calculated respectively. Specifically, in post-processing, the volume of the HgCdTe layer is integrated, and the surface of the lower surface of the HgCdTe layer is integrated, and the integral expression column is input: if(u>993[K],1,0); This expression sets 993K (the melting point of HgCdTe) as the thermal damage threshold for the HgCdTe layer. This expression can also be set as an expression in a plot group to evaluate the spatial distribution of the damaged area.

[0040] The corresponding change curves of the damage volume of the HgCdTe layer and the damage area on the lower surface of the HgCdTe layer are shown in the figure below. Figure 5 and Figure 6 As shown. Figure 7 As shown, in this embodiment, a three-dimensional drawing group is added to draw the temperature distribution diagram of the HgCdTe detector when t1=1.2us, t2=1201.2us, and t3=2334.5us respectively; Figure 8 As shown, in this embodiment, a two-dimensional drawing group is added, the lower surface of the HgCdTe layer is selected, and in the expression column, if(u>993[K],1,0) is input to draw the damage area distribution diagrams when t1=1.2us, t2=1201.2us, and t3=2334.5us respectively.

[0041] Depend on Figure 5 and Figure 6 It can be seen that the damage volume and damage area increase in a "step-like" manner, which well demonstrates the damage process of the pulse laser with a certain repetition frequency to the detector during movement; Figure 7 The temporal and spatial distribution of the temperature field of the detector during the movement of the laser spot can be obtained, and the thermal influence of the pulse laser on the detector during the movement of the pulse laser at different times can be obtained; Figure 8 It can be seen that the damaged surface area during the movement of the pulsed laser can provide a basis for the evolution characteristics of the spatial and temporal distribution of the damaged area of ​​the detector.

[0042] This invention uses COMSOL Multiphysics to establish a transient model of solid heat transfer in the detector, analyzes the damage of the moving laser to the detector, and combines the physical processes of heat conduction, convection heat transfer with the environment, and thermal radiation during laser irradiation to obtain the distribution of the temperature field at different irradiation times. Through the domain ordinary differential and differential algebraic equation modules in the software, the thermal damage area can be determined and calculated. The evaluation method of the damage of the moving laser irradiation of the detector helps to optimize the protection strategy of the detector against laser to improve the anti-irradiation performance of the detector, and also saves experimental costs.

[0043] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the illustrations of the drawings. In the specification, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit can implement several functions listed in the specification. Certain measures are recorded in different embodiments, but this does not mean that these measures cannot be combined to produce good results.

[0044] Although the present invention has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present invention. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present invention and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present invention. Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations if they fall within the scope of the present invention and its equivalents.

Claims

1. A detector moving laser irradiation damage assessment method, characterized in that: The evaluation method includes the following steps: Determine the moving laser parameters and the detector structure material property parameters; Construct a transient model of solid heat transfer in the detector; Set the boundary conditions of the solid heat transfer transient model physics field and perform meshing; Set solver parameters; the solver parameters include an initial step size of the solver, a storage time step of a laser irradiation time period and a laser non-irradiation time period, and a maximum step size constraint of a laser irradiation time period and a laser non-irradiation time period; the solver parameters are determined by using a pre-trained linear neural network model, specifically: inputting a mobile laser pulse width and a mobile laser frequency into a pre-trained linear neural network model, and using a pre-trained linear neural network model expression to calculate and obtain the solver parameters; Based on the solver parameters, the solid heat transfer transient model is solved in the solver, and the thermal damage of the detector is determined by calling the domain ordinary differential and differential algebraic equation modules. If it is determined that the detector is damaged, the damaged area and volume of the detector are calculated to obtain the spatial distribution of the damaged area of ​​the detector.

2. The detector moving laser irradiation damage assessment method according to claim 1 is characterized in that: The pre-trained linear neural network model includes an input layer and an output layer; wherein the parameters of the input layer include a moving laser pulse width node and a moving laser frequency node; the parameters of the output layer include a storage time step node, an initial step node, and a maximum step constraint node of the solver in the laser irradiation time period and the laser non-irradiation time period.

3. The detector moving laser irradiation damage assessment method according to claim 2, characterized in that: The pre-trained linear neural network model expression is: ； in, is the weight matrix, ; is the bias vector, ; is the storage time step of the solver during the laser irradiation period; The storage time step of the solver during the laser non-irradiation period; is the initial step size of the solver; is the maximum step size constraint of the solver during the laser irradiation period; It is the maximum step size constraint of the solver during the laser non-irradiation period; To move the laser pulse width; To shift the laser frequency.

4. The detector moving laser irradiation damage assessment method according to claim 2, characterized in that: The parameters of the input layer and the output layer are normalized, and the normalization range is [0, 1]. The normalized expression is: ； in, is the result after normalization of the corresponding parameter value in the training data set; is the corresponding parameter value in the training data set; and are the minimum and maximum values ​​of the corresponding parameters in the training data set, respectively.

5. The detector moving laser irradiation damage assessment method according to claim 2, characterized in that: , and The parameters must satisfy physical constraints: ； If the prediction results do not meet the above constraints, they should be corrected in the following ways: 。 6. The detector moving laser irradiation damage assessment method according to claim 1, characterized in that: The mesh division adopts free triangular network division for the upper surface of the silicon substrate and the lower surface of the indium column array, and the segment element size of the mesh is predefined to be finer; and the remaining part of the solid heat transfer transient model is subjected to swept mesh division.

7. The detector moving laser irradiation damage assessment method according to claim 1, characterized in that: The mobile laser pulse width is 100ps-500ns, the repetition frequency is 1K-10K, and the moving speed is 0-500mm / s.

8. The detector moving laser irradiation damage assessment method according to claim 1, characterized in that: The solver is set to use the backward difference formula to solve the time step; the initial step size of the solver, the storage time step size of the solver in the laser irradiation section, the storage time step size of the solver in the laser non-irradiation time period, the maximum step size constraint of the solver in the laser irradiation time period, and the maximum step size constraint of the solver in the laser non-irradiation time period are all set according to the pre-trained linear neural network model results.

9. The detector moving laser irradiation damage assessment method according to claim 1, characterized in that: The method for determining and evaluating the thermal damage of the detector is to call the domain ordinary differential and differential algebraic equation modules to obtain the highest temperature at a certain position in the solid heat transfer transient model in the past time; if the highest temperature is greater than the melting point of the detector material, the detector is damaged; Then, by calculating the damaged area and volume, the spatial distribution of the damaged area of ​​the detector can be obtained.

10. A detector moving laser irradiation damage assessment system, characterized in that: include: An evaluation parameter configuration unit, used to configure evaluation parameters, wherein the evaluation parameters include moving laser parameters and detector structure material property parameters; The detector solid heat transfer transient model building unit builds the solid heat transfer transient model of the detector and determines the boundary conditions of the heat transfer physical field of the solid heat transfer transient model; Meshing unit, which performs meshing on the transient solid heat transfer model based on the heat transfer physical field; A solver parameter configuration unit, used to configure solver parameters, the solver parameters include an initial step size of the solver, a laser irradiation time period and a storage time step of the laser irradiation time period, and a maximum step size constraint of the laser irradiation time period and the laser non-irradiation time period; the solver parameters are determined by using a pre-trained linear neural network model, specifically: the mobile laser pulse width and the mobile laser frequency are input into the pre-trained linear neural network model, and the pre-trained linear neural network model expression is used to calculate and obtain the solver parameters; The detector damage determination unit applies the solver parameters to solve the solid heat transfer transient model in the solver, and determines the thermal damage of the detector by calling the domain ordinary differential and differential algebraic equation modules. If it is determined that the detector is damaged, the damaged area and volume of the detector are calculated to obtain the spatial distribution of the damaged area of ​​the detector.

Images