Optimal configuration method for nuclear radiation prevention equipment

Abstract

The invention relates to an optimal configuration method for nuclear radiation prevention equipment. The method comprises the following steps: firstly, acquiring radiation environment data, and performing deep analysis on the data to generate a first reflection configuration scheme; then, inputting reflection path data in the first reflection configuration scheme into the multi-parameter evaluation model to obtain a dynamic adjustment strategy; and if the weakening rate of the strategy does not reach the preset threshold value, relevant parameters are adjusted to carry out iterative calculation to obtain a second reflection configuration scheme. And then, fusing the second reflection configuration scheme and the radiation source direction data, and inputting the fused second reflection configuration scheme and the radiation source direction data into the path prediction model to obtain a structure optimization scheme. And analyzing the matching degree of the reflection efficiency and the radiation weakening according to the scheme. And if the matching degree is lower than a preset standard, generating a protection performance optimization scheme through iteration. Finally, the protection performance optimization scheme and the structure optimization scheme are organically fused, and final protection equipment design parameters are obtained. The protection efficiency of the protection equipment is greatly improved, and radiation hazards are effectively reduced.

Description

Technical Field

[0001] The invention belongs to the fields of nuclear engineering and nuclear technology, and in particular relates to an optimization configuration method for nuclear radiation protection equipment. Background Art

[0002] With the development of nuclear engineering and technology, a technique for optimizing the configuration of nuclear radiation protection equipment has emerged. With the vigorous development of the global nuclear energy industry, nuclear technology is increasingly being applied in a wide range of fields, including energy supply, healthcare, and scientific research. However, the potential hazards posed by nuclear radiation have also aroused widespread concern. In scenarios such as nuclear facility operation, nuclear waste disposal, and radiation environment monitoring, nuclear radiation protection equipment is crucial for ensuring personnel safety and equipment operation. Traditional methods for configuring nuclear radiation protection equipment are often based on empirical experience and simple theoretical models, lacking the ability to accurately analyze and dynamically adapt to complex radiation environments. Faced with variable radiation intensity, complex radiation source distribution, and diverse protection requirements, existing methods struggle to achieve optimal equipment configuration, resulting in poor protection effectiveness and wasteful resources. This makes it difficult to meet the growing demand for nuclear radiation protection and improve the safety and reliability of nuclear-related activities. Summary of the Invention

[0003] Based on this, it is necessary to provide an optimization configuration method for nuclear radiation protection equipment to address the above technical problems, which can effectively improve the radiation attenuation effect and enhance the overall performance of the protection equipment.

[0004] In a first aspect, the present application provides a method for optimizing configuration of nuclear radiation protection equipment, comprising:

[0005] Acquire radiation environment data; construct a radiation distribution characteristic map for the radiation environment data, and use Monte Carlo simulation to evaluate the reflection path to obtain a first reflection configuration scheme.

[0006] The reflection path data in the first reflection configuration scheme is input into the multi-parameter evaluation model for analysis to obtain a dynamic adjustment strategy; if the attenuation rate of the radiation attenuation effect data in the dynamic adjustment strategy is lower than the preset threshold, the relevant parameters are adjusted for iterative calculation to obtain the second reflection configuration scheme.

[0007] According to the second reflection configuration scheme, the radiation source direction data is integrated into the path prediction model to obtain the structural optimization scheme.

[0008] Based on the structural optimization scheme, the structural parameters are extracted and combined with the dynamic adjustment strategy and path prediction data to analyze the matching degree between reflection efficiency and radiation attenuation. If the matching degree is lower than the preset threshold, the multi-parameter evaluation weights are adjusted and the protection performance optimization scheme is iteratively generated.

[0009] According to the protection performance optimization plan and the structural optimization plan, the particle swarm optimization algorithm is used to calculate the final design parameters of the protection equipment.

[0010] In one embodiment, a radiation distribution characteristic map is constructed based on radiation environment data, and a first reflection configuration scheme is obtained by evaluating a reflection path using Monte Carlo simulation, including:

[0011] A time-domain radiation intensity sequence is obtained from radiation environment data; the time-domain radiation intensity sequence includes radiation values ​​of multiple monitoring points.

[0012] Fourier transform is performed on the time domain radiation intensity sequence to construct a frequency domain characteristic matrix; the frequency domain characteristic matrix includes energy distribution parameters of each frequency band.

[0013] The main frequency component in the frequency domain feature matrix is ​​extracted to obtain a radiation distribution feature map; the radiation distribution feature map includes a mapping relationship between spatial position and main frequency energy.

[0014] The radiation distribution characteristic map is input into the Monte Carlo simulator to generate a set of reflection paths according to the geometric parameters of the reflecting surface.

[0015] The attenuation coefficient of each path in the reflection path set is calculated, and reflection paths with attenuation coefficients lower than a preset threshold are screened to obtain a candidate reflection path set.

[0016] A reflection path topology network is constructed based on the candidate reflection path set, and the reflection path topology network is processed using a graph convolutional network to obtain path optimization parameters.

[0017] The reflection surface angle parameters are adjusted according to the path optimization parameters to generate a first reflection configuration scheme.

[0018] In one embodiment, the reflection path data in the first reflection configuration scheme is input into a multi-parameter evaluation model for analysis to obtain a dynamic adjustment strategy, including:

[0019] Path loss coefficient and phase deviation matrix are extracted from the reflection path data in the first reflection configuration scheme to obtain a reflection path data subset.

[0020] The reflection path data subset is input into the multi-parameter evaluation model to obtain the model weight parameters.

[0021] Based on the model weight parameters, the genetic algorithm is used to traverse the parameter space of the strategy execution threshold and the number of optimization iterations to obtain the traversal results.

[0022] A candidate dynamic adjustment strategy set is generated according to the traversal results, and strategies that meet the reflection intensity constraint condition are screened from the candidate dynamic adjustment strategy set to obtain a dynamic adjustment strategy.

[0023] In one embodiment, the second reflection configuration scheme is integrated with the radiation source direction data input path prediction model to obtain a structural optimization scheme, including:

[0024] A first reflection parameter in a second reflection configuration scheme is obtained; the first reflection parameter includes radiation source direction data.

[0025] A radiation field intensity distribution map is generated according to the first reflection parameter and input into a path prediction model, and a structural deformation threshold matrix is ​​obtained by processing with a finite element analysis algorithm.

[0026] The first reflection parameter is adjusted according to the structural deformation threshold to obtain the second reflection parameter.

[0027] The second reflection parameter is input into the path prediction model to obtain the radiation avoidance path.

[0028] The radiation avoidance path is used to update the meshing strategy in the finite element analysis to obtain the optimized structural parameter set.

[0029] The structural parameter set is fused with the second reflection parameter to generate a structural optimization solution.

[0030] In one embodiment, a radiation field intensity distribution map is generated according to the first reflection parameter and input into a path prediction model, and a structural deformation threshold matrix is ​​obtained by processing using a finite element analysis algorithm, including:

[0031] A radiation field intensity distribution map is generated according to the first reflection parameter, and the radiation field intensity distribution map includes field intensity gradient distribution information.

[0032] The field intensity gradient distribution information is extracted from the radiation field intensity distribution map and input into the path prediction model to obtain the deformation coupling coefficient; the field intensity gradient distribution information includes the field intensity change rate and the direction vector.

[0033] Finite element meshing is performed according to the deformation coupling coefficient to generate dynamic stress distribution data.

[0034] The stress peak value is detected on the dynamic stress distribution data to obtain the structural deformation threshold matrix.

[0035] In one embodiment, the protection performance optimization scheme is integrated with the structure optimization scheme, and the particle swarm optimization algorithm is used to calculate the final protection equipment design parameters, including:

[0036] An initial input parameter set is constructed based on the structural optimization scheme and the positioning accuracy enhancement results to generate a fusion weight matrix; the initial input parameter set includes the protective layer thickness and the positioning error compensation coefficient; the fusion weight matrix is ​​used to balance the structural stiffness and positioning stability.

[0037] The fusion weight matrix is ​​used as the constraint condition of the particle swarm optimization algorithm to obtain the multi-dimensional parameter vector of the protective equipment.

[0038] The multidimensional parameter vector is judged based on the preset protection effectiveness threshold. If the preset protection effectiveness threshold is not met, the dynamic attenuation factor in the fusion weight matrix is ​​adjusted.

[0039] The multidimensional parameter vector is recalculated according to the adjusted dynamic attenuation factor until the protection effectiveness threshold reaches the boundary condition, and the final protection equipment design parameters are obtained.

[0040] In one embodiment, the fusion weight matrix is ​​used as a constraint condition of the particle swarm optimization algorithm, including:

[0041] The constraints are obtained using the following formula:

[0042]

[0043] Among them, F(X i ) represents the constraint condition, X i Represents the fusion weight matrix parameter vector, d represents the matrix dimension, param k Indicates the kth parameter vector value, weight k Indicates the corresponding weight value, γ k Represents the adjustment coefficient.

[0044] The aforementioned method, computer device, and storage medium for optimizing the configuration of nuclear radiation protection equipment first obtains radiation environment data, conducts in-depth analysis of this data to construct a radiation distribution characteristic map, and uses Monte Carlo simulation to evaluate reflection paths, thereby generating a first reflection configuration scheme. Next, the reflection path data from the first reflection configuration scheme is input into a multi-parameter evaluation model, and a dynamic adjustment strategy is derived through detailed analysis. If the radiation attenuation rate under this strategy does not reach a preset threshold, relevant parameters are adjusted and iterative calculations are performed to obtain a second reflection configuration scheme. Subsequently, this second reflection configuration scheme is integrated with radiation source direction data and input into a path prediction model to obtain a structural optimization scheme. Structural parameters are then extracted based on the structural optimization scheme. The dynamic adjustment strategy and path prediction data are combined to analyze the matching degree between reflection efficiency and radiation attenuation. If the matching degree falls below a preset standard, the multi-parameter evaluation weights are adjusted, and a protection performance optimization scheme is generated through iteration. Finally, the protection performance optimization scheme and the structural optimization scheme are organically integrated, and a particle swarm optimization algorithm is used for precise calculation to determine the final protection equipment design parameters. Through the comprehensive application of multiple steps and models, we can accurately analyze the radiation environment and optimize various aspects such as reflection paths, structural design, and protective performance. This allows for a more comprehensive and in-depth consideration of the interplay of multiple factors, greatly improving the effectiveness of protective equipment, effectively reducing radiation hazards, and providing more reliable protection for relevant sites and personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A flowchart of a method for optimizing configuration of nuclear radiation protection equipment provided by an embodiment of the present invention;

[0047] Figure 2 A flowchart of an embodiment of the present invention is provided for obtaining a structural optimization solution by fusing radiation source direction data into a path prediction model according to a second reflection configuration solution. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0049] In one embodiment, Figure 1 As shown, the present application provides a method for optimizing the configuration of nuclear radiation protection equipment, which may include the following steps:

[0050] Step S101 , obtaining radiation environment data; constructing a radiation distribution characteristic map for the radiation environment data, and evaluating the reflection path using Monte Carlo simulation to obtain a first reflection configuration scheme.

[0051] Specifically, radiation environment data is extensively collected through various professional monitoring equipment. This data covers multi-dimensional information such as radiation intensity, radiation frequency, and spatial location. After acquiring the data, advanced mathematical algorithms such as Fourier transform are used to convert the time-domain radiation environment data into frequency-domain characteristics, thereby constructing a radiation distribution characteristic map. This map intuitively presents the energy distribution of radiation in different frequency bands and different spatial locations. Based on this radiation distribution characteristic map, Monte Carlo simulation technology is used to consider parameters such as the material and geometry of the reflecting surface. A large number of random simulations of the possible reflection paths of the incident radiation are performed to evaluate the feasibility and effectiveness of different reflection paths, and ultimately determine and obtain the first reflection configuration scheme.

[0052] Step S102: Input the reflection path data in the first reflection configuration scheme into a multi-parameter evaluation model for analysis to obtain a dynamic adjustment strategy; if the attenuation rate of the radiation attenuation effect data in the dynamic adjustment strategy is lower than a preset threshold, adjust the relevant parameters for iterative calculation to obtain a second reflection configuration scheme.

[0053] Reflection path data is precisely extracted from the first reflection configuration. This data contains key information such as the path direction, length, and radiation attenuation characteristics along each path. This data is then input into a carefully constructed multi-parameter evaluation model. The model comprehensively considers multiple factors, such as the path loss coefficient and the phase deviation matrix, and conducts an in-depth analysis of the reflection path data. A specific algorithm is then used to derive a dynamic adjustment strategy designed to further optimize the radiation attenuation effect. Subsequently, the radiation attenuation effect data under the dynamic adjustment strategy is evaluated. If the attenuation rate does not reach a pre-set threshold, indicating that the current strategy is not achieving the desired effect, the relevant parameters in the model, such as material properties and geometric design parameters, need to be adjusted, and the data is re-entered for iterative calculation until a second reflection configuration that meets the requirements is obtained.

[0054] Step S103 , fusing the radiation source direction data with the input path prediction model according to the second reflection configuration scheme to obtain a structural optimization scheme.

[0055] Specifically, the key first reflection parameters in the second reflection configuration scheme are obtained, which especially include the radiation source direction data, which is crucial for the subsequent analysis of the radiation propagation path. Based on these parameters, a radiation field intensity distribution map is generated with the help of professional software and algorithms. The map clearly shows the distribution and changes of the radiation field intensity in space. This radiation field intensity distribution map is input into a high-precision path prediction model, and the model is processed using a finite element analysis algorithm. Factors such as the mechanical properties of the material and the stress conditions of the structure are fully considered. Through a refined analysis of the grid units in the model, the deformation threshold matrix of the structure under the action of radiation is obtained. Based on this matrix, the first reflection parameters are adjusted in a targeted manner to form the second reflection parameters, which are input into the path prediction model again. Finally, a radiation avoidance path that can effectively avoid high-intensity radiation areas is obtained. Based on this, the meshing strategy in the finite element analysis is updated, and the optimized parameters are integrated to generate a comprehensive structural optimization solution.

[0056] Step S104: extract structural parameters based on the structural optimization solution and combine the dynamic adjustment strategy with the path prediction data to analyze the matching degree between the reflection efficiency and the radiation attenuation. If the matching degree is lower than the preset threshold, adjust the multi-parameter evaluation weights and iteratively generate the protection performance optimization solution.

[0057] Accurately extract structural parameters from the structural optimization scheme, including but not limited to the thickness of the protective layer, the geometric shape and size of the structure, etc. Combine these parameters with the previously obtained dynamic adjustment strategy and path prediction data to conduct an in-depth analysis of the matching degree between reflection efficiency and radiation attenuation. During the analysis process, consider the impact of various factors on the relationship between the two, such as the performance of the reflective material, the complexity of the radiation propagation path, etc. If the matching degree is lower than the pre-set threshold, it means that the current scheme has deficiencies in protection performance. At this time, it is necessary to adjust the weights in the multi-parameter evaluation model, redistribute the importance of each parameter in the evaluation process, perform iterative calculations again, and continuously optimize the scheme until a protection performance optimization scheme that meets the protection performance requirements is generated.

[0058] Step S105 , according to the protection performance optimization scheme and the structural optimization scheme, the particle swarm optimization algorithm is used to calculate and obtain the final protection equipment design parameters.

[0059] The protection performance optimization scheme and the structural optimization scheme are deeply integrated, and multiple factors such as protection performance and structural stability are comprehensively considered. Based on the structural parameters in the structural optimization scheme and the positioning accuracy enhancement results, an initial input parameter set is constructed, which includes key parameters such as the thickness of the protective layer and the positioning error compensation coefficient. At the same time, a fusion weight matrix is ​​generated, which is used to reasonably balance the influence of structural stiffness and positioning stability in the calculation process. The fusion weight matrix is ​​used as an important constraint condition of the particle swarm optimization algorithm. Through continuous search and iteration of the particle swarm in the multidimensional parameter space, the multidimensional parameter vector of the protective equipment is calculated. The vector is continuously judged according to the preset protection effectiveness threshold. If the threshold requirement is not met, the dynamic attenuation factor in the fusion weight matrix is ​​adjusted, and the multidimensional parameter vector is recalculated. This process is repeated until the protection effectiveness threshold reaches the ideal boundary condition, thereby obtaining accurate and efficient final protection equipment design parameters to ensure that the protective equipment has the best protection performance.

[0060] The aforementioned method for optimizing the configuration of nuclear radiation protection equipment begins by acquiring radiation environment data. This data is then analyzed in depth to construct a radiation distribution feature map. Reflection paths are then evaluated using Monte Carlo simulation to generate a first reflection configuration solution. Next, the reflection path data from the first reflection configuration solution is input into a multi-parameter evaluation model, and a dynamic adjustment strategy is derived through detailed analysis. If the radiation attenuation rate under this strategy does not reach a preset threshold, relevant parameters are adjusted and iterative calculations are performed to generate a second reflection configuration solution. This second reflection configuration solution is then integrated with radiation source direction data and input into a path prediction model to obtain a structural optimization solution. Structural parameters are then extracted based on the structural optimization solution. The dynamic adjustment strategy and path prediction data are combined to analyze the matching between reflection efficiency and radiation attenuation. If the matching falls below a preset standard, the multi-parameter evaluation weights are adjusted, and a protection performance optimization solution is generated through iteration. Finally, the protection performance optimization solution and the structural optimization solution are integrated, and a particle swarm optimization algorithm is used for precise calculation to determine the final design parameters for the protection equipment. Through the comprehensive application of multiple steps and models, we can accurately analyze the radiation environment and optimize various aspects such as reflection paths, structural design, and protective performance. This allows for a more comprehensive and in-depth consideration of the interplay of multiple factors, greatly improving the effectiveness of protective equipment, effectively reducing radiation hazards, and providing more reliable protection for relevant sites and personnel.

[0061] In one embodiment, constructing a radiation distribution characteristic map based on radiation environment data and evaluating the reflection path using Monte Carlo simulation to obtain a first reflection configuration scheme may include the following steps:

[0062] Step S201: obtaining a time-domain radiation intensity sequence in radiation environment data; the time-domain radiation intensity sequence includes radiation values ​​of multiple monitoring points.

[0063] Step S202 , performing Fourier transform according to the time domain radiation intensity sequence to construct and generate a frequency domain characteristic matrix; the frequency domain characteristic matrix includes energy distribution parameters of each frequency band.

[0064] Step S203 , extracting the main frequency component in the frequency domain feature matrix to obtain a radiation distribution feature diagram; the radiation distribution feature diagram includes a mapping relationship between spatial position and main frequency energy.

[0065] Step S204: input the radiation distribution characteristic diagram into a Monte Carlo simulator to generate a set of reflection paths according to the geometric parameters of the reflection surface.

[0066] Step S205 : calculating the attenuation coefficient of each path in the reflection path set, screening reflection paths with attenuation coefficients lower than a preset threshold, and obtaining a candidate reflection path set.

[0067] Step S206: construct a reflection path topology network based on the candidate reflection path set, and use a graph convolutional network to process the reflection path topology network to obtain path optimization parameters.

[0068] Step S207: adjusting the reflection surface angle parameters according to the path optimization parameters to generate a first reflection configuration scheme.

[0069] First, a precise time-domain radiation intensity sequence is extracted from the radiation environment data. This sequence comprehensively records the radiation values ​​at multiple monitoring points, providing the foundational data for subsequent analysis. Subsequently, the powerful mathematical tool of Fourier transform is used to convert the time-domain radiation intensity sequence into a frequency-domain feature matrix. This matrix clearly displays the energy distribution parameters for each frequency band, achieving information conversion and feature extraction from the time domain to the frequency domain. Next, the dominant frequency component is extracted from the frequency-domain feature matrix to construct a radiation distribution feature map. This map maps spatial position with dominant frequency energy, visually demonstrating the spatial distribution characteristics of radiation energy. Based on the generated radiation distribution feature map, it is fed into a Monte Carlo simulator and, combined with the geometric parameters of the reflecting surface, a set of reflection paths is generated through a large number of random simulations. For each reflection path in the set, its attenuation coefficient is carefully calculated, and paths with attenuation coefficients below a preset threshold are selected to obtain a set of candidate reflection paths. A reflection path topology network is then constructed based on this set of candidate reflection paths. This network is then processed using a graph convolutional network to explore underlying patterns and ultimately determine path optimization parameters. Based on these optimization parameters, the reflecting surface angle parameters are adjusted to generate the first reflection configuration.

[0070] This embodiment uses mathematical analysis such as Fourier transform and technical means such as Monte Carlo simulation to deeply analyze the characteristics of the radiation environment and accurately simulate the reflection path. The use of graph convolutional networks further optimizes the path, making the generated first reflection configuration scheme highly scientific and reasonable at the theoretical level. Compared with traditional methods based on experience or simple estimates, this process can more comprehensively and accurately consider the impact of multiple factors on radiation reflection, providing a solid and reliable foundation for the design and optimization of subsequent protective equipment, effectively improving the accuracy and effectiveness of radiation protection plan formulation, and reducing the potential harm of radiation to related areas and personnel.

[0071] In one embodiment, inputting the reflection path data in the first reflection configuration scheme into a multi-parameter evaluation model for analysis to obtain a dynamic adjustment strategy may include the following steps:

[0072] Step S301 : extracting the path loss coefficient and the phase deviation matrix from the reflection path data in the first reflection configuration scheme to obtain a reflection path data subset.

[0073] Step S302: Input the reflection path data subset into a multi-parameter evaluation model to obtain model weight parameters.

[0074] Step S303 , based on the model weight parameters, a genetic algorithm is used to traverse the parameter space of the strategy execution threshold and the number of optimization iterations to obtain a traversal result.

[0075] Step S304 : generating a candidate dynamic adjustment strategy set according to the traversal result, and screening strategies that meet the reflection intensity constraint condition from the candidate dynamic adjustment strategy set to obtain a dynamic adjustment strategy.

[0076] The reflection path data from the generated first reflection configuration is refined. Using a specific algorithm, the path loss coefficient and phase deviation matrix are precisely extracted from the reflection path data. These two key elements effectively characterize the reflection path. Based on the extracted results, a subset of the reflection path data is constructed, which highly condenses the core information of the original reflection path data. This subset is then fed into a carefully constructed multi-parameter evaluation model. The model deeply analyzes the data using a pre-defined complex algorithm. Through multiple rounds of calculations and feedback adjustments, it ultimately outputs model weight parameters. These weight parameters reflect the relative importance of different parameters in the evaluation process. Based on these model weight parameters, the search capabilities of a genetic algorithm are utilized to comprehensively traverse two key parameters, the strategy execution threshold and the number of optimization iterations, within a specific parameter space. The genetic algorithm simulates the natural evolutionary process, continuously selecting optimal solutions through operations such as selection, crossover, and mutation, ultimately generating a traversal result. Based on the traversal results, a set of candidate dynamic adjustment strategies is generated. From this set of strategies, strategies that meet the reflection intensity constraints are rigorously screened. Through this screening process, a dynamic adjustment strategy suitable for the current radiation protection scenario is obtained.

[0077] From the data processing perspective, by extracting the path loss coefficient and phase deviation matrix to construct a data subset, we can achieve efficient condensation of complex reflection path data, remove redundant information, and improve the efficiency of subsequent analysis. The combination of multi-parameter evaluation model and genetic algorithm can search for near-optimal strategy execution thresholds and optimization iterations in a huge parameter space, greatly improving the scientific nature and accuracy of strategy generation. By screening strategies that meet the reflection intensity constraints, we ensure that the generated dynamic adjustment strategy can be effective in practical applications and meet the strict requirements of radiation protection for reflection intensity. Overall, this process provides a rigorous, scientific, and efficient method for the formulation of dynamic adjustment strategies for radiation protection equipment. Compared with traditional strategy formulation methods, it can more accurately respond to complex and changing radiation environments, significantly improve radiation protection effects, reduce radiation hazard risks, and provide strong support for safety assurance in related fields.

[0078] In one embodiment, Figure 2 As shown, according to the second reflection configuration scheme, the radiation source direction data is integrated into the path prediction model to obtain a structural optimization scheme, which may include the following steps:

[0079] Step S401: Acquire a first reflection parameter in a second reflection configuration scheme; the first reflection parameter includes radiation source direction data.

[0080] Step S402 : generating a radiation field intensity distribution map according to the first reflection parameter and inputting the radiation field intensity distribution map into a path prediction model, and processing the model using a finite element analysis algorithm to obtain a structural deformation threshold matrix.

[0081] Step S403: adjusting the first reflection parameter according to the structural deformation threshold to obtain a second reflection parameter.

[0082] Step S404: input the second reflection parameter into the path prediction model to obtain a radiation avoidance path.

[0083] Step S405 : using the radiation avoidance path to update the meshing strategy in the finite element analysis to obtain an optimized set of structural parameters.

[0084] Step S406: Fusing the structural parameter set and the second reflection parameter to generate a structural optimization solution.

[0085] Specifically, key first reflection parameters are first obtained from the second reflection configuration. These parameters include data on the radiation source direction, which plays a crucial role in the subsequent analysis of radiation propagation paths and device structural responses. Based on these first reflection parameters, specialized computational software and algorithms are used to generate a radiation field intensity distribution map. This map visually illustrates the spatial distribution and changing trends of the radiation field intensity. This radiation field intensity distribution map is then fed into a high-precision path prediction model, where it is further processed using a finite element analysis algorithm. The finite element analysis algorithm discretizes the complex structure into numerous tiny units. Mechanical analysis of each unit comprehensively considers factors such as material properties and stress conditions, ultimately yielding a structural deformation threshold matrix that reflects the deformation characteristics of the structure under radiation. Based on the resulting structural deformation threshold, the first reflection parameters are adjusted to obtain the second reflection parameters. The second reflection parameters are then fed back into the path prediction model, where computations are performed to accurately determine the radiation avoidance path, representing the optimal path to effectively avoid high-intensity radiation areas under the given structural and radiation conditions. Using this radiation avoidance path, the meshing strategy used in finite element analysis was updated to better reflect the actual forces and radiation propagation of the structure, resulting in an optimized set of structural parameters. Finally, this optimized set of structural parameters was organically integrated with the second reflection parameter, comprehensively considering the mechanical properties and radiation protection requirements of the structure to generate a comprehensive and scientific structural optimization solution.

[0086] This embodiment adjusts the reflection parameters through the structural deformation threshold to ensure the stability and safety of the structure in the radiation environment. The acquisition of the radiation avoidance path provides a clear direction for optimizing the structural design, so that the structure can better adapt to the radiation environment and reduce the damage to the structure caused by radiation. The grid division strategy is updated and the parameters are integrated to generate the structural optimization scheme to further improve the accuracy and rationality of the structural design. Compared with the traditional structural design method, this process can more comprehensively and deeply consider the impact of radiation factors on the structure, greatly improving the radiation resistance and overall performance of the structure, providing strong technical support for the radiation protection design in related engineering fields, and effectively reducing the potential threat of the radiation environment to facilities and personnel.

[0087] In one embodiment, generating a radiation field intensity distribution map based on the first reflection parameter and inputting the radiation field intensity distribution map into a path prediction model, and processing the obtained structure deformation threshold matrix using a finite element analysis algorithm may include the following steps:

[0088] Step S501 : generating a radiation field intensity distribution map according to a first reflection parameter, wherein the radiation field intensity distribution map includes field intensity gradient distribution information.

[0089] Step S502 , extracting field intensity gradient distribution information from the radiation field intensity distribution diagram and inputting it into a path prediction model to obtain a deformation coupling coefficient; the field intensity gradient distribution information includes a field intensity change rate and a direction vector.

[0090] Step S503 : performing finite element meshing according to the deformation coupling coefficient to generate dynamic stress distribution data.

[0091] Step S504: performing stress peak detection on the dynamic stress distribution data to obtain a structural deformation threshold matrix.

[0092] First, based on the first reflection parameter, a radiation field intensity distribution map is generated using specialized modeling and calculation tools. This map not only clearly depicts the spatial distribution of the radiation field intensity but, more importantly, encompasses information on the field intensity gradient, crucial for understanding the changing trends and detailed intensity variations of the radiation field. Subsequently, the field intensity gradient distribution, including the rate of change and directional vector, is precisely extracted from the radiation field intensity distribution map. This critical information is then fed into the path prediction model. Complex and sophisticated algorithms within the model derive the deformation coupling coefficient, which reflects the interaction between the radiation field and the structure. Based on the obtained deformation coupling coefficient, the structure is meshed using finite element methods. This scientifically and rationally meshed structure discretizes the complex structure into numerous tiny elements, generating dynamic stress distribution data that details the stress variations at various locations under the influence of radiation. To further assess the stability and reliability of the structure, stress peak detection is performed on the dynamic stress distribution data. By accurately identifying the stress peaks, the maximum stress conditions expected at different locations within the structure are determined. Ultimately, a structural deformation threshold matrix is ​​generated, which comprehensively reflects the structural deformation limit parameters under the influence of radiation.

[0093] From the generation of the radiation field intensity distribution map to the acquisition of the structural deformation threshold matrix, each link is closely linked to form a complete and rigorous analysis system. By extracting the field intensity gradient distribution information and combining it with the path prediction model to obtain the deformation coupling coefficient, the coupling effect between the radiation field and the structure is fully considered, which improves the accuracy and scientificity of the analysis. The finite element mesh division and the generation of dynamic stress distribution data provide a refined means for in-depth study of the mechanical response of the structure in the radiation environment. The stress peak detection and the determination of the structural deformation threshold matrix provide clear quantitative indicators for structural design, which can effectively guide structural optimization, ensure that the structure remains stable in the radiation environment, and avoid excessive deformation caused by radiation that affects its performance and safety. Compared with traditional structural design and analysis methods, this process greatly improves the understanding and control of the mechanical behavior of structures in radiation environments, provides solid technical support for the optimization design of radiation protection structures, and effectively guarantees the reliable operation of related facilities in radiation environments.

[0094] In one embodiment, the protection performance optimization scheme is integrated with the structure optimization scheme, and the particle swarm optimization algorithm is used to calculate the final protection equipment design parameters, which may include the following steps:

[0095] Step S601: construct an initial input parameter set based on the structural optimization scheme and the positioning accuracy enhancement results, and generate a fusion weight matrix; the initial input parameter set includes the protective layer thickness and the positioning error compensation coefficient; the fusion weight matrix is ​​used to balance the structural stiffness and positioning stability.

[0096] Step S602: Using the fusion weight matrix as a constraint condition of the particle swarm algorithm to obtain a multi-dimensional parameter vector of the protective device.

[0097] Step S603: The multi-dimensional parameter vector is judged based on a preset protection effectiveness threshold. If the preset protection effectiveness threshold is not met, the dynamic attenuation factor in the fusion weight matrix is ​​adjusted.

[0098] Step S604 , recalculating the multidimensional parameter vector according to the adjusted dynamic attenuation factor until the protection effectiveness threshold reaches the boundary condition, thereby obtaining the final protection equipment design parameters.

[0099] Specifically, the structural optimization plan and positioning accuracy enhancement results are first integrated. Key parameters related to structural protection performance, such as protective layer thickness, are extracted from the structural optimization plan. Important data, such as the positioning error compensation coefficient, is obtained from the positioning accuracy enhancement results. These parameters are then combined to form the initial input parameter set. Based on this, a fusion weight matrix is ​​generated. This matrix is ​​crucial for balancing structural stiffness and positioning stability. By rationally assigning weights to different parameters, it coordinates the relationship between structural strength and positioning accuracy for the protective device. Next, the fusion weight matrix is ​​used as a constraint during the particle swarm optimization (PSO) algorithm. With its efficient search capabilities, the PSO algorithm continuously explores the multidimensional parameter space. Constrained by the fusion weight matrix, the algorithm undergoes multiple rounds of iterations to ultimately determine the multidimensional parameter vector for the protective device. The resulting multidimensional parameter vector is then rigorously evaluated against a pre-set protection effectiveness threshold. If the pre-set protection effectiveness threshold is not met, the dynamic attenuation factor in the fusion weight matrix is ​​adjusted. This dynamic attenuation factor plays a key role in the optimization process, flexibly varying the influence of different parameters during the iterations. After the adjustment, the particle swarm algorithm is used to recalculate the multidimensional parameter vector, and this cycle is repeated until the protection effectiveness threshold reaches the ideal boundary condition. The multidimensional parameter vector determined at this time is the final protection equipment design parameter.

[0100] From constructing the initial input parameter set to generating the fusion weight matrix, the dual requirements of the protective equipment in terms of structural performance and positioning function are fully considered, and an organic balance between the two is achieved through the weight matrix. The application of the particle swarm algorithm under the constraints of the fusion weight matrix can efficiently search for parameter combinations close to the optimal solution in a complex multi-dimensional parameter space, greatly improving the efficiency and accuracy of the design parameter determination. Based on the judgment of the protection effectiveness threshold and the adjustment mechanism of the dynamic attenuation factor, the entire optimization process has good adaptability and iterative optimization capabilities. Compared with the traditional design parameter determination method, this process can more comprehensively and accurately take into account the various performance indicators of the protective equipment, ensuring that the protective equipment under the final design parameters has the best protection effectiveness, providing reliable protection guarantees for actual application scenarios, and effectively reducing the potential hazards of radiation and other risks to relevant personnel and facilities.

[0101] In one embodiment, using the fusion weight matrix as a constraint condition of the particle swarm optimization algorithm may include the following steps:

[0102] The constraints are obtained using the following formula:

[0103]

[0104] Among them, F(X i ) represents the constraint condition, X i Represents the fusion weight matrix parameter vector, d represents the matrix dimension, param k Indicates the kth parameter vector value, weight k Indicates the corresponding weight value, γ k Represents the adjustment coefficient.

[0105] This embodiment greatly improves the operating efficiency and convergence speed of the algorithm. Through the careful setting of elements such as the fusion weight matrix parameter vector, it is possible to fully integrate the design requirements of the protective equipment in terms of structural stiffness, positioning stability, etc., to ensure that the parameter vectors obtained by the algorithm search meet the expectations for the comprehensive performance of the protective equipment in actual engineering. The introduction of the adjustment coefficient further enhances the flexibility of the constraint condition, which can be dynamically adjusted according to different protection scenarios and optimization focuses. Compared with the application of algorithms without clear constraints or simple constraints, this method can determine the design parameters of protective equipment more scientifically and efficiently, significantly improve the design quality and performance of protective equipment, provide more reliable technical support for related fields such as radiation protection, and effectively reduce the threat of potential risks to personnel and facilities.

[0106] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0107] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for optimizing configuration of nuclear radiation protection equipment are implemented.

[0108] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0109] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0110] The above-described embodiments merely represent several implementation methods of the embodiments of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the concept of the embodiments of the present application, and these modifications and improvements fall within the scope of protection of the embodiments of the present application.

Claims

1. A method for optimizing the configuration of nuclear radiation protection equipment, characterized in that: The method comprises: Acquiring radiation environment data; constructing a radiation distribution characteristic map for the radiation environment data, and evaluating the reflection path using Monte Carlo simulation to obtain a first reflection configuration scheme; Inputting the reflection path data in the first reflection configuration scheme into a multi-parameter evaluation model for analysis to obtain a dynamic adjustment strategy; if the attenuation rate of the radiation attenuation effect data in the dynamic adjustment strategy is lower than a preset threshold, adjusting relevant parameters for iterative calculation to obtain a second reflection configuration scheme; According to the second reflection configuration scheme, the radiation source direction data is integrated into the path prediction model to obtain a structural optimization scheme; Extracting structural parameters based on the structural optimization scheme and combining the dynamic adjustment strategy with path prediction data to analyze the matching degree between reflection efficiency and radiation attenuation; if the matching degree is lower than a preset threshold, adjusting the multi-parameter evaluation weights and iteratively generating a protection performance optimization scheme; According to the protection performance optimization scheme and the structural optimization scheme, the final protection equipment design parameters are calculated using the particle swarm optimization algorithm.

2. The method according to claim 1, characterized in that The step of constructing a radiation distribution characteristic map of the radiation environment data and evaluating the reflection path using Monte Carlo simulation to obtain a first reflection configuration scheme includes: Acquire a time-domain radiation intensity sequence from the radiation environment data; the time-domain radiation intensity sequence includes radiation values ​​of a plurality of monitoring points; Performing Fourier transform on the time-domain radiation intensity sequence to construct a frequency-domain characteristic matrix; the frequency-domain characteristic matrix includes energy distribution parameters of each frequency band; Extracting the main frequency component in the frequency domain feature matrix to obtain a radiation distribution feature map; the radiation distribution feature map includes a mapping relationship between spatial position and main frequency energy; Inputting the radiation distribution characteristic diagram into a Monte Carlo simulator to generate a reflection path set according to the geometric parameters of the reflection surface; Calculating the attenuation coefficient of each path in the reflection path set, screening reflection paths whose attenuation coefficients are lower than a preset threshold, and obtaining a candidate reflection path set; Constructing a reflection path topology network based on the candidate reflection path set, and processing the reflection path topology network using a graph convolutional network to obtain path optimization parameters; The reflecting surface angle parameters are adjusted according to the path optimization parameters to generate a first reflection configuration scheme.

3. The method according to claim 1, characterized in that The step of inputting the reflection path data in the first reflection configuration scheme into a multi-parameter evaluation model for analysis to obtain a dynamic adjustment strategy includes: Extracting a path loss coefficient and a phase deviation matrix from the reflection path data in the first reflection configuration scheme to obtain a reflection path data subset; Inputting the reflection path data subset into a multi-parameter evaluation model to obtain model weight parameters; Based on the model weight parameters, a genetic algorithm is used to traverse the parameter space of the strategy execution threshold and the number of optimization iterations to obtain a traversal result; A candidate dynamic adjustment strategy set is generated according to the traversal result, and strategies that meet the reflection intensity constraint condition are screened from the candidate dynamic adjustment strategy set to obtain a dynamic adjustment strategy.

4. The method according to claim 1, wherein The step of fusing the radiation source direction data into the path prediction model according to the second reflection configuration scheme to obtain a structural optimization scheme includes: Acquire a first reflection parameter in the second reflection configuration scheme; the first reflection parameter includes radiation source direction data; generating a radiation field intensity distribution map according to the first reflection parameter, inputting the radiation field intensity distribution map into a path prediction model, and processing the map using a finite element analysis algorithm to obtain a structural deformation threshold matrix; adjusting the first reflection parameter according to the structural deformation threshold to obtain a second reflection parameter; inputting the second reflection parameter into the path prediction model to obtain a radiation avoidance path; Using the radiation avoidance path to update the meshing strategy in the finite element analysis to obtain an optimized set of structural parameters; The structural parameter set and the second reflection parameter are fused to generate a structural optimization solution.

5. The method according to any one of claim 4, characterized in that Generating a radiation field intensity distribution map according to the first reflection parameter and inputting the radiation field intensity distribution map into a path prediction model, and obtaining a structural deformation threshold matrix by using a finite element analysis algorithm, includes: generating a radiation field intensity distribution map according to the first reflection parameter, wherein the radiation field intensity distribution map includes field intensity gradient distribution information; Extracting field intensity gradient distribution information from the radiation field intensity distribution map and inputting it into a path prediction model to obtain a deformation coupling coefficient; the field intensity gradient distribution information includes a field intensity change rate and a direction vector; Performing finite element meshing according to the deformation coupling coefficient to generate dynamic stress distribution data; Stress peak detection is performed on the dynamic stress distribution data to obtain a structural deformation threshold matrix.

6. The method according to claim 1, characterized in that The method of integrating the structural optimization scheme with the protection performance optimization scheme and using a particle swarm optimization algorithm to calculate the final protection equipment design parameters includes: An initial input parameter set is constructed based on the structural optimization scheme and the positioning accuracy enhancement result, and a fusion weight matrix is ​​generated; the initial input parameter set includes the protective layer thickness and the positioning error compensation coefficient; the fusion weight matrix is ​​used to balance the structural stiffness and positioning stability; Using the fusion weight matrix as a constraint condition of the particle swarm algorithm, a multi-dimensional parameter vector of the protective equipment is obtained; The multidimensional parameter vector is judged based on a preset protection effectiveness threshold, and if the preset protection effectiveness threshold is not met, the dynamic attenuation factor in the fusion weight matrix is ​​adjusted; The multidimensional parameter vector is recalculated according to the adjusted dynamic attenuation factor until the protection effectiveness threshold reaches the boundary condition, thereby obtaining the final protection equipment design parameters.

7. The method according to claim 6, characterized in that The method of using the fusion weight matrix as a constraint condition of the particle swarm algorithm includes: The constraints are obtained using the following formula: Among them, F(X i ) represents the constraint condition, X i Represents the fusion weight matrix parameter vector, d represents the matrix dimension, param k Indicates the kth parameter vector value, weight k Indicates the corresponding weight value, γ k Represents the adjustment coefficient.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images