Intelligent design optimization and 3D printing manufacturing method and device of gradient shielding material

Abstract

The application provides a method and device for intelligent design optimization and 3D printing manufacturing of gradient shielding materials, and relates to the field of artificial intelligence. The method comprises the following steps: obtaining material design data and inputting the data into an intelligent optimization design framework to output a gradient configuration scheme; based on the gradient configuration scheme, preparing a target composite powder, and through a laser powder bed melting equipment of a multi-hopper powder feeding system, performing zoning and layering scheduling to form a shielding functional area, a composition gradient transition layer and a bearing structure area; through a laser ultrasonic detection structure and a defect identification model of an in-situ quality detection system, performing defect identification, and based on a defect detection result, adjusting 3D printing process parameters and performing compensation repair on a defect area; performing performance verification on a repaired formed part, and outputting a structure and function integrated shielding material. The application solves the problems of difficult design optimization of multi-material gradient shielding materials and difficult timely detection and repair of forming defects.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and in particular to a method and apparatus for intelligent design optimization and 3D printing manufacturing of gradient shielding materials. Background Technology

[0002] With the development of nuclear energy utilization, nuclear medicine diagnosis and treatment, and aerospace, the demand for integrated materials that combine radiation shielding and structural load-bearing capacity is constantly increasing. Current technologies typically involve composite materials within a metal matrix. , Functional phase materials such as W are used, and additive manufacturing technology is combined to form complex shielding structures to improve the neutron absorption, gamma-ray attenuation and lightweight properties of the materials.

[0003] However, in multi-material gradient laser powder bed melting manufacturing scenarios, due to , Differences in density, melting point, and thermal properties between W and Al alloys can easily lead to problems such as powder segregation, unstable molten pools, insufficient interfacial bonding, and internal porosity, making it difficult to synergistically optimize shielding and load-bearing performance. In other words, existing gradient shielding material manufacturing systems... , In multi-material synergistic forming scenarios such as W and Al alloys, it is difficult to achieve intelligent optimization of material composition and gradient configuration, and it is impossible to detect and repair defects inside the forming area in a timely manner during the laser powder bed melting forming process, which can easily cause the shielding performance and load-bearing performance of the formed part to deviate from the design requirements.

[0004] Therefore, there is an urgent need for an intelligent design optimization and 3D printing manufacturing method and device for gradient shielding materials. Summary of the Invention

[0005] This application provides an intelligent design optimization and 3D printing manufacturing method and apparatus for gradient shielding materials, which solves the problems of design optimization difficulties for multi-material gradient shielding materials and the difficulty in timely detection and repair of forming defects.

[0006] The first aspect of this application provides an intelligent design optimization and 3D printing manufacturing method for gradient shielding materials. The method includes: acquiring material design data and inputting the material design data into an intelligent optimization design framework, the intelligent optimization design framework outputting a gradient configuration scheme based on target optimization parameters as constraints; the gradient configuration scheme is sequentially divided along the printing direction into a shielding functional area, a composition gradient transition layer, and a load-bearing structure area; based on the gradient configuration scheme, processing the composite material raw material through a powder preparation process, and preparing the target composite powder through ultrasonic vibration-assisted wet coating; the powder preparation process includes planetary ball milling and airflow classification; based on the gradient configuration scheme, using a laser powder bed melting equipment with a multi-hopper powder feeding system to... The target composite powder is partitioned and layered, forming a shielding functional area, a composition gradient transition layer, and a load-bearing structural area during a single printing process. An in-situ quality inspection system identifies defects in each layer of the target composite powder and outputs the defect detection results. This system includes a laser ultrasonic testing structure and a defect identification model. Based on the defect detection results, 3D printing process parameters are adjusted, and the defective areas are compensated and repaired using the adjusted parameters. The performance of the repaired part is verified, and the part that passes the performance verification is output as a structurally and functionally integrated shielding material. Performance verification includes radiation shielding performance verification, mechanical performance verification, and microstructure performance verification.

[0007] Optionally, an intelligent optimization design framework constrained by target optimization parameters is constructed, specifically including: constructing an intelligent optimization design framework based on the coupling of deep reinforcement learning algorithms and Monte Carlo particle transport simulation; the deep reinforcement learning algorithm adopts a proximal policy optimization algorithm, and a Monte Carlo particle transport simulation is invoked for verification each time the decision variables are updated; the decision variables include Volume fraction Volume fraction, W volume fraction, and Al alloy matrix composition; target optimization parameters include gamma-ray shielding coefficient, thermal neutron absorptivity, tensile strength, and relative density.

[0008] Optionally, based on a gradient configuration scheme, the composite material raw materials are processed using a powder preparation process, and the target composite powder is prepared by ultrasonic vibration-assisted wet coating. Specifically, this includes: determining the component ratio of the composite material raw materials based on the gradient configuration scheme, and performing planetary ball milling on the composite material raw materials to obtain initial composite powder; performing airflow classification on the initial composite powder, and screening and controlling the composite material raw materials according to the particle size distribution to obtain pretreated composite powder; placing the pretreated composite powder in a coating medium for ultrasonic vibration-assisted wet coating, and using ultrasonic vibration to disperse and attach the functional phase particles to the surface of the Al alloy matrix to obtain the target composite powder; the volume fraction of the functional phase particles is controlled along the printing direction according to the gradient change relationship corresponding to the gradient configuration scheme.

[0009] Optionally, during a single printing process, a shielding functional area, a composition gradient transition layer, and a load-bearing structural area are formed. Specifically, this includes: determining the material composition information corresponding to different printing areas based on the gradient configuration scheme, and controlling the multi-hopper powder feeding system to switch and schedule the target composite powder according to the material composition information; the material composition information is the component proportion corresponding to different decision variables; determining the interlayer configuration information corresponding to different printing areas based on the gradient configuration scheme, and controlling the laser powder bed melting equipment to perform layer-by-layer powder spreading and laser melting forming according to the interlayer configuration information, so that the target composite powder with different material compositions forms a shielding functional area, a composition gradient transition layer, and a load-bearing structural area in the same printing process.

[0010] Optionally, an in-situ quality inspection system is used to identify defects in each forming region corresponding to the target composite powder and output defect detection results. Specifically, this includes: obtaining ultrasonic detection signals corresponding to each forming region based on a laser ultrasonic detection structure, and obtaining forming quality inspection information corresponding to each forming region based on the ultrasonic wave propagation state of the ultrasonic detection signals; performing feature analysis on the forming quality inspection information based on a defect identification model to obtain defect detection results; training the defect identification model using preset defect sample data; and including defect type information, defect location information, and defect size information in the defect detection results.

[0011] Optionally, the 3D printing process parameters are adjusted based on the defect detection results, and the defect area is compensated and repaired using the adjusted 3D printing process parameters. Specifically, this includes: determining the defect repair method corresponding to the defect area based on defect type information; determining the printing layer position and scanning path range corresponding to the defect area based on defect location information; determining the repair area range and compensation forming parameters corresponding to the defect area based on defect size information; associating the defect repair method, printing layer position, scanning path range, and compensation forming parameters to obtain a defect repair process plan; adjusting the 3D printing process parameters based on the defect repair process plan, and controlling the laser powder bed melting equipment to compensate and repair the defect area according to the adjusted 3D printing process parameters.

[0012] Optionally, the performance of the molded part after defect repair is verified, and the molded part that passes the performance verification is output as a structural-functional integrated shielding material. Specifically, this includes: obtaining performance verification results based on the molded part after defect repair; the performance verification results include radiation shielding performance, mechanical properties, and microstructure properties; matching the radiation shielding performance, mechanical properties, and microstructure properties with preset performance requirements, and determining whether the molded part after defect repair meets the performance requirements of the structural-functional integrated shielding material; if the molded part after defect repair meets the performance requirements of the structural-functional integrated shielding material, the molded part after defect repair is output as the structural-functional integrated shielding material; if the molded part after defect repair does not meet the performance requirements of the structural-functional integrated shielding material, the 3D printing process parameters are readjusted for compensation and repair.

[0013] A second aspect of this application provides an intelligent design optimization and 3D printing manufacturing apparatus for gradient shielding materials. The apparatus includes an intelligent optimization design module, a composite powder preparation module, a gradient laser powder bed fusion molding module, an in-situ quality inspection module, a defect closed-loop compensation and repair module, and a performance verification output module. The intelligent optimization design module is used to acquire material design data and input the material design data into the intelligent optimization design framework. The intelligent optimization design framework outputs a gradient configuration scheme based on the target optimization parameters as constraints. The gradient configuration scheme is divided into a shielding functional area, a composition gradient transition layer and a load-bearing structure area along the printing direction.

[0014] The composite powder preparation module is used to process composite material raw materials through powder preparation processes based on gradient configuration schemes, and to prepare target composite powders through ultrasonic vibration-assisted wet coating processes; the powder preparation processes include planetary ball milling and airflow classification.

[0015] The gradient laser powder bed melting and forming module is used to partition and layer the target composite powder based on the gradient configuration scheme and through the laser powder bed melting equipment of the multi-hopper powder feeding system, and form the shielding functional area, the composition gradient transition layer and the load-bearing structure area in a single printing process.

[0016] The in-situ quality inspection module is used to identify defects in each layer of the target composite powder through the in-situ quality inspection system and output the defect inspection results; the in-situ quality inspection system includes a laser ultrasonic inspection structure and a defect identification model.

[0017] The defect closed-loop compensation and repair module is used to adjust the 3D printing process parameters based on the defect detection results, and to compensate and repair the defect area using the adjusted 3D printing process parameters.

[0018] The performance verification output module is used to verify the performance of the molded part after defect repair, and output the molded part that passes the performance verification as a structural and functional integrated shielding material; the performance verification includes radiation shielding performance verification, mechanical performance verification and microstructure performance verification.

[0019] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described above.

[0020] A fourth aspect of this application provides a non-transitory computer-readable storage medium storing a computer program, the computer program being executed by a processor using any of the methods described above.

[0021] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By acquiring material design data and inputting it into an intelligent optimization design framework based on the coupling of deep reinforcement learning algorithm and Monte Carlo particle transport simulation, a gradient configuration scheme that meets the requirements of radiation shielding performance and mechanical performance is generated. Based on the gradient configuration scheme, the composite material raw material is prepared into powder and subjected to ultrasonic vibration-assisted wet coating treatment to obtain target composite powder with gradient component characteristics. The target composite powder is partitioned and layered by a laser powder bed melting equipment with a multi-hopper powder feeding system to form a shielding functional area, a component gradient transition layer, and a load-bearing structure area in a single printing process. Defects in the forming process are identified using an in-situ quality inspection system including a laser ultrasonic detection structure and a defect identification model, and the 3D printing process parameters are dynamically adjusted for compensation and repair based on the defect detection results. By verifying the radiation shielding performance, mechanical properties, and microstructure performance of the repaired formed part, the problems of difficulty in co-optimizing material composition and gradient configuration in the design of multi-material gradient shielding materials, and the difficulty in timely detection and repair of internal defects in the laser powder bed melting forming process, which leads to the performance of the formed part deviating from the design requirements, are solved.

[0022] 2. Based on the defect detection results, a dynamic correlation is established between the defect status and the 3D printing process parameters. The corresponding repair strategy is determined according to the defect type, defect location, and defect size, and an adaptive compensation repair scheme for the defect area is generated, thereby achieving precise defect repair during the forming process and improving the forming quality and structural reliability of the gradient shielding material. Attached Figure Description

[0023] Figure 1 This is a schematic flowchart of an intelligent design optimization and 3D printing manufacturing method for a gradient shielding material provided in an embodiment of this application; Figure 2 This is a schematic diagram of a gradient shielding material configuration provided in an embodiment of this application; Figure 3 This is a schematic diagram of additive manufacturing and defect closed-loop control of a gradient shielding material provided in an embodiment of this application; Figure 4 This is a schematic diagram of a module for an intelligent design optimization and 3D printing manufacturing device for gradient shielding materials provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0024] Figure labeling: 41. Intelligent optimization design module; 42. Composite powder preparation module; 43. Gradient laser powder bed melting and forming module; 44. In-situ quality inspection module; 45. Defect closed-loop compensation and repair module; 46. Performance verification output module; 501. Processor; 502. Communication bus; 503. User interface; 504. Network interface; 505. Memory. Detailed Implementation

[0025] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0026] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to and includes any or all possible combinations of one or more of the listed items.

[0027] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0028] To enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0029] Please refer to Figure 1 The flowchart illustrates a method for intelligent design optimization and 3D printing manufacturing of a gradient shielding material provided in this application embodiment. The flowchart mainly includes the following steps: S101 to S106.

[0030] Step S101: Obtain material design data and input the material design data into the intelligent optimization design framework. The intelligent optimization design framework outputs gradient configuration schemes based on the target optimization parameters as constraints.

[0031] Specifically, material design data is acquired and input into an intelligent optimization design framework, which outputs gradient configuration schemes based on the target optimization parameters as constraints.

[0032] Specifically, nuclear radiation protection materials need to simultaneously meet the comprehensive requirements of radiation shielding and structural load-bearing. In applications such as nuclear energy utilization, nuclear medicine diagnosis and treatment, and radioactive waste disposal, neutrons and gamma rays are the main sources of radiation hazards. Thermal neutrons have a large activation cross-section, fast neutrons have strong penetrating power, and gamma rays have high energy and strong ionizing power, all of which can affect personnel safety and the reliable operation of equipment. Therefore, shielding materials not only need to have efficient neutron moderation and absorption capabilities and gamma ray attenuation capabilities, but also need to have the mechanical load-bearing capacity to meet the requirements of engineering applications.

[0033] To address the above requirements, a system is constructed using... , Composite material systems composed of W and Al alloy matrices are used as the material design object. It has a high thermal neutron absorption capacity, which is used to enhance thermal neutron shielding performance; Combining neutron absorption capacity with lightweight and high-hardness properties, it is used to enhance neutron protection capabilities and improve the overall performance of materials; W has a high atomic number to enhance gamma-ray attenuation capability; the Al alloy matrix provides structural load-bearing capacity and additive manufacturing adaptability. By performing gradient configuration design on the above multi-component material system, different functional regions have corresponding material compositions, thereby achieving integrated shielding and load-bearing functions.

[0034] Since improving shielding performance typically relies on increasing the content of high atomic number or high density functional components, but an excessively high proportion of functional components can lead to increased material mass, reduced interfacial bonding performance, and decreased mechanical properties, there is a strong coupling relationship between radiation shielding performance and structural load-bearing capacity, forming a multi-objective optimization problem involving material composition, gradient configuration, and performance indicators. Traditional methods relying on empirical design or parameter traversal are insufficient to cover complex design spaces, and each candidate scheme requires shielding performance evaluation through Monte Carlo particle transport simulation, resulting in low optimization efficiency.

[0035] Based on this, material design data, including material composition information, gradient configuration information, and performance constraint information, is acquired and input into an intelligent optimization design framework. This framework is constructed by coupling deep reinforcement learning algorithms with Monte Carlo particle transport simulation. A deep reinforcement learning agent iteratively decides on the material design parameters and uses Monte Carlo particle transport simulation to calculate the radiation shielding performance corresponding to the current design scheme. Feedback information is generated based on the simulation results to optimize and adjust the material composition and gradient configuration parameters. The intelligent optimization design framework uses gamma-ray shielding coefficient, thermal neutron absorptivity, tensile strength, and relative density as target optimization parameters to collaboratively optimize the material design data, outputting a gradient configuration scheme that meets both shielding and load-bearing performance requirements.

[0036] Among them, the decision variables in the material design data include Volume fraction Volume fraction, W volume fraction, Al alloy matrix composition, and gradient configuration parameters, including the number of compositional gradient transition layers and the gradient variation pattern, are used. An intelligent optimization design framework is employed to optimize these decision variables, enabling the output gradient configuration scheme to provide material composition guidance for subsequent composite powder preparation, multi-hopper powder feeding control, and laser powder bed melting processes. The gradient configuration scheme is sequentially divided along the printing direction into a shielding functional area, a compositional gradient transition layer, and a load-bearing structural area.

[0037] Compared to traditional single-objective optimization or surrogate model fitting methods, this scheme achieves closed-loop coupling between the deep reinforcement learning decision-making process and the Monte Carlo particle transport simulation evaluation process. This allows the material design process to continuously optimize based on feedback from shielding performance and mechanical properties, and directly transfers the optimized material composition and gradient configuration parameters to the subsequent manufacturing process, realizing data correlation between material design, performance evaluation, and manufacturing. This approach solves the problems of complex optimization space, low performance evaluation efficiency, and difficulty in directly guiding manufacturing in the design of multi-component shielding materials. The briefing clearly states that a proximal strategy optimization deep reinforcement learning algorithm is deeply coupled with Monte Carlo particle transport simulation, and iterative optimization is achieved through decision variable output, simulation calculation of performance target values, and reward feedback. The decision variables are... Volume fraction Composition of volume fraction, W volume fraction, aluminum alloy volume fraction, and gradient configuration parameters.

[0038] Please refer to Figure 2 The document presents a schematic diagram of a gradient shielding material configuration provided in an embodiment of this application. Figure 2In the process, the gradient configuration scheme is divided into a shielding functional gradient region, a composition gradient transition layer, and a load-bearing structure region along the printing direction. The shielding functional gradient region is located at the top of the formed part and is used to improve the... , The material incorporates functional phases such as W to enhance gamma-ray attenuation and neutron absorption. A load-bearing structural region, located at the bottom of the formed part, utilizes an Al alloy matrix to provide structural support. A compositional gradient transition layer, situated between the shielding functional gradient region and the load-bearing structural region, enables continuous variation in functional phase content, reducing interfacial stress concentration caused by abrupt compositional changes between different material regions. This gradient configuration allows the material to form a structure that continuously transitions from the top functional phase-rich region to the bottom Al alloy matrix region along the printing direction, achieving synergistic optimization of radiation shielding performance and mechanical load-bearing capacity.

[0039] In one possible implementation, step S101 further includes: constructing an intelligent optimization design framework based on the coupling of a deep reinforcement learning algorithm and a Monte Carlo particle transport simulation; the deep reinforcement learning algorithm employs a proximal policy optimization algorithm, and a Monte Carlo particle transport simulation is invoked for verification each time the decision variables are updated; the decision variables include Volume fraction Volume fraction, W volume fraction, and Al alloy matrix composition; target optimization parameters include gamma-ray shielding coefficient, thermal neutron absorptivity, tensile strength, and relative density.

[0040] Specifically, an intelligent optimization design framework is constructed by coupling deep reinforcement learning algorithms with Monte Carlo particle transport simulations. The deep reinforcement learning algorithm employs proximal policy optimization (PPO), and a Monte Carlo particle transport simulation is invoked for verification each time the decision variables are updated. The decision variables include... Volume fraction Volume fraction, W volume fraction, and Al alloy matrix composition; target optimization parameters include gamma-ray shielding coefficient, thermal neutron absorptivity, tensile strength, and relative density.

[0041] Specifically, targeting , A multi-component composite shielding material system composed of W and Al alloys exhibits varying effects of different material components on radiation shielding performance and structural load-bearing capacity. It has a high thermal neutron absorption capacity. With neutron absorption capabilities and lightweight yet high hardness, W possesses a high atomic number and can enhance gamma-ray attenuation. The Al alloy matrix provides structural load-bearing capacity and adaptability during laser powder bed melting. Therefore, a complex nonlinear coupling relationship exists between the material composition ratio and gradient configuration parameters. To achieve synergistic optimization of radiation shielding performance and structural load-bearing performance, the material design process is transformed into a multi-objective optimization process based on deep reinforcement learning. Deep reinforcement learning algorithms are used to intelligently optimize the material composition and gradient configuration parameters, and Monte Carlo particle transport simulations are used to verify the physical performance of the optimization results.

[0042] Specifically, material composition parameters and gradient configuration parameters are used together as decision variables in the intelligent optimization design framework to construct a set of decision variables:

[0043] in, Represents the set of decision variables; express Volume fraction; express Volume fraction; W represents the volume fraction; The matrix composition of the Al alloy is represented by ; N represents the number of discrete layers in the composition gradient transition layer; and m represents the composition gradient power exponent, used to control the variation of material composition in the gradient configuration scheme. By jointly describing the material composition and gradient structure through the above decision variables, the intelligent optimization design framework can simultaneously optimize both the material proportions and the spatial configuration.

[0044] Specifically, a deep reinforcement learning optimization process is constructed based on decision variables. The state of the decision variables corresponding to the current material design scheme is input into the PPO algorithm. The PPO algorithm generates corresponding action parameters based on the current state and updates the decision variables based on the action parameters. The decision variable update process is represented as follows:

[0045] in, Let represent the state of the decision variable during the t-th iteration; This represents the action parameters output by the PPO algorithm; This represents the minimum value constraint corresponding to the decision variable; This represents the maximum value constraint for the decision variable; This represents a constraint function used to limit the updated decision variables to a preset range.

[0046] After updating the decision variables, a Monte Carlo particle transport simulation is invoked to verify the current material design. By establishing a radiation transport model corresponding to the current material composition and gradient configuration, the propagation process of gamma rays and neutrons within the composite material is simulated. The gamma-ray shielding performance and thermal neutron absorption performance corresponding to the current material design are obtained, and the simulation results are fed back to the PPO algorithm to update the decision strategy in the next round of optimization. Through the coupling of the PPO algorithm and the Monte Carlo particle transport simulation, the material design process forms a closed-loop optimization process of "parameter generation, physical simulation, performance evaluation, and strategy update." The deep reinforcement learning algorithm and the Monte Carlo particle transport simulation are deeply coupled, and a surrogate model is used to reduce the impact of time-consuming simulation calculations on optimization efficiency.

[0047] Specifically, a reward function is constructed based on the Monte Carlo particle transport simulation output. This reward function is used to comprehensively evaluate the radiation shielding performance, mechanical properties, and internal defect state of the current material design scheme. The reward function is expressed as follows:

[0048] in, This indicates the reward value corresponding to the current material design scheme; This represents the normalized gamma-ray shielding coefficient, used to evaluate the attenuation capability of current material schemes against gamma rays; This represents the normalized thermal neutron absorptivity, used to evaluate the thermal neutron absorption capacity of current material designs. This represents the normalized tensile strength, used to evaluate the structural load-bearing capacity of the current material scheme. Normalized porosity is used to evaluate the degree of internal defects in the current material design. , , as well as This represents the weighting coefficient of the corresponding evaluation index. The weighting coefficient is a non-negative parameter with a value range of [0,1], and is automatically assigned according to the radiation hazard level in the actual application scenario.

[0049] The reward function described above enables the PPO algorithm to comprehensively consider radiation shielding performance, structural load-bearing capacity, and material forming quality, thus avoiding the problem of declining overall material performance caused by optimizing only a single shielding index.

[0050] Furthermore, to improve the search accuracy of material design schemes, a multi-round iterative optimization process is set up in the intelligent optimization design framework. Each iteration sequentially performs decision variable updates, Monte Carlo particle transport simulation verification, and reward feedback updates. The number of iterations is no less than 5000. Through a large number of iterations, the performance variation laws corresponding to different material composition combinations and gradient configuration parameters are obtained, and a Pareto optimal solution set that satisfies multi-objective constraints is output. The target gradient configuration scheme is selected from the Pareto optimal solution set.

[0051] The target gradient configuration scheme also includes macroscopic configuration design information and functional enhancement parameters. The macroscopic configuration design information is used to determine the structural form corresponding to different regions. The macroscopic configuration is selected from one or more of the following: Schwartz Diamond Triple Periodic Minimal Surface (TPMS) lattice, honeycomb-column hybrid sandwich structure, and biomimetic multi-level gradient structure. Specifically, the Schwartz Diamond Triple Periodic Minimal Surface lattice forms a continuous load transfer path through periodic curved surface structures, creating a multi-directional support network within the material, thereby reducing structural mass while increasing load-bearing capacity; the honeycomb-column hybrid sandwich structure provides lightweight support through honeycomb units and enhances local stiffness through columnar connection structures, thereby improving the compressive load-bearing capacity of the gradient configuration scheme; the biomimetic multi-level gradient structure simulates the hierarchical organization characteristics in natural materials, creating a continuous transition between different regions and improving the interface bonding performance between the shielding functional area and the load-bearing structural area.

[0052] Furthermore, the gradient configuration scheme output by the intelligent optimization design framework is divided sequentially along the printing direction into a shielding functional area, a composition gradient transition layer, and a load-bearing structural area. The shielding functional area provides radiation shielding capability, the load-bearing structural area provides structural support capability, and the composition gradient transition layer connects the shielding functional area and the load-bearing structural area, allowing the material composition to change continuously along the printing direction, thereby reducing interfacial stress concentration caused by abrupt changes in composition between different material regions.

[0053] The material composition in the shielding functional area is configured according to radiation shielding requirements, among which... The volume fraction is 5% to 15%. The volume fraction is 5%–20%, the volume fraction of W is 3%–10%, and the balance is an Al alloy matrix. This is achieved by improving… and The increased content enhances the thermal neutron absorption capacity and improves the gamma-ray attenuation capacity by increasing the W content.

[0054] The load-bearing structural region uses an Al alloy matrix as the main component material and contains W particles with a mass fraction of no more than 5%. The small amount of W particles improves the gamma-ray scattering buffering capacity while maintaining the mechanical properties of the Al alloy matrix and the stability of additive manufacturing.

[0055] A composition gradient transition layer is set between the shielding functional area and the load-bearing structure area. The thickness of the composition gradient transition layer is 0.5-2mm. The volume fraction of the functional phase material changes continuously along the printing direction, so that the material properties gradually transition from the high shielding area to the high load-bearing area.

[0056] The relationship between the volume fraction of functional phase materials along the gradient direction is expressed as follows:

[0057] in, This represents the volume fraction of the functional phase material corresponding to the i-th gradient region; The maximum functional phase material volume fraction corresponds to the shielding functional area; i represents the current gradient layer number; N represents the total number of composition gradient transition layers; m represents the gradient power exponent, used to control the variation trend of functional phase material along the printing direction.

[0058] For example, when setting When N=5 and m=1.5, The volume fraction gradually increases along the printing direction, corresponding to each gradient layer. The volume fractions are 1.34 vol%, 3.80 vol%, 6.97 vol%, 10.73 vol%, and 15.00 vol%, respectively, which allows the material to gradually transition from the load-bearing structural region to the high shielding functional region.

[0059] Through the above methods, the intelligent optimization design framework can automatically determine the material composition ratio and gradient configuration parameters based on target optimization parameters such as gamma-ray shielding performance, thermal neutron absorption performance, tensile strength, and relative density. This ensures that the output gradient configuration scheme simultaneously meets radiation protection requirements, structural load-bearing requirements, and additive manufacturing requirements, providing a design basis for subsequent target composite powder preparation and laser powder bed fusion printing processes.

[0060] Furthermore, the intelligent optimization design framework in this application pre-configures optimization strategies corresponding to different application scenarios and determines the current optimization mode based on the input application scenario requirements. When the application scenario switches to the fast neutron shielding priority mode, since fast neutrons have strong penetrating power, it is necessary to improve the neutron moderation and absorption capacity in the material system. Therefore, the intelligent optimization design framework automatically adjusts the constraint range of decision variables. The upper limit of volume fraction was increased from the original constraint range to 25%, and the design parameters of hydrogen-containing polymer coating were introduced into the decision variables. By adding hydrogen-containing structural parameters to participate in the gradient configuration scheme optimization, fast neutrons are absorbed after multiple scattering and slowing down inside the material, thereby improving the fast neutron shielding performance.

[0061] When the application scenario is switched to gamma-ray re-shielding mode, since gamma rays have strong penetrating power, it is necessary to increase the proportion of high atomic number materials. Therefore, the intelligent optimization design framework automatically adjusts the optimization constraint range corresponding to the W material, increases the upper limit of the W volume fraction to 15%, and enables a double-layer composite configuration template. By constructing a high-density gamma-ray attenuation layer and a gradient transition bearing layer, the high atomic number material is concentrated on the radiation incident side to improve the gamma-ray attenuation capability, while ensuring that the structural region has sufficient bearing capacity.

[0062] The intelligent optimization design framework synchronously adjusts the target weights according to different application scenarios, enabling the deep reinforcement learning algorithm to have different optimization directions under different radiation environments. In the fast neutron shielding priority mode, the weights of the target parameters related to thermal neutron absorption rate and neutron moderation are increased; in the gamma-ray heavy shielding mode, the weights of the target parameter related to the gamma-ray shielding coefficient are increased, so that the output gradient configuration scheme can adapt to different radiation protection requirements.

[0063] Through the aforementioned multi-scenario adaptive switching mechanism, the intelligent optimization design framework can automatically adjust material composition constraints, functional layer configurations, and optimization objectives according to the actual application environment, thereby generating gradient configuration schemes for different scenarios such as fast neutron shielding and gamma-ray re-shielding under the same optimization framework.

[0064] Step S102: Based on the gradient configuration scheme, the composite material raw materials are processed by powder preparation process, and the target composite powder is prepared by ultrasonic vibration-assisted wet coating process.

[0065] Specifically, due to , The differences in density, melting point, and surface properties between the W and Al alloy matrices make direct mixing prone to powder segregation, reduced flowability, and insufficient spreading uniformity, failing to meet the requirements of laser powder bed melting processes for powder particle size distribution and flow properties. Therefore, the composite material raw materials are sequentially subjected to planetary ball milling, airflow classification, and ultrasonic vibration-assisted wet coating to ensure uniform dispersion and adhesion of functional phase particles to the Al alloy matrix powder surface, thereby obtaining the target composite powder that meets the requirements of gradient printing.

[0066] Determined based on gradient configuration scheme , The material composition ratios of W and Al alloy matrices were determined, and the composite material raw materials were mixed according to these ratios. The composite material raw materials were then mechanically processed using a planetary ball mill to ensure sufficient contact between different material components, improve the dispersion of functional phase particles, and reduce localized enrichment caused by differences in material density, thus obtaining the initial composite powder.

[0067] Furthermore, the initial composite powder undergoes airflow classification treatment, and powder particles of different size ranges are screened and controlled according to their particle size distribution to ensure that the composite powder meets the powder spreading requirements during the laser powder bed melting process. The composite powder after particle size control includes functional phase particles of different size ranges and Al alloy base powder, with the particle size distribution of the composite powder being: The particle size is 1–5 μm. The particle size is 3–10 μm, the W particle size is 1–5 μm, and the Al alloy base powder particle size is 15–53 μm.

[0068] By using the above particle size ratio, smaller particle sizes can be achieved. Particles, The particles and W particles can fill the spaces between Al alloy base powder particles, improving the uniformity of powder packing, while avoiding the problem of powder flowability degradation caused by excessively large functional phase particle size, thus providing a foundation for uniform powder spreading during the subsequent laser powder bed melting process.

[0069] Furthermore, the pretreated composite powder after airflow classification is placed in a coating medium for ultrasonic vibration-assisted wet coating treatment. Through the cavitation effect and mechanical disturbance generated by ultrasonic vibration, the functional phase particles are fully dispersed in the coating medium and the functional phase particles are uniformly attached to the surface of Al alloy base powder to form a target composite powder with core-shell coating structure characteristics.

[0070] In the ultrasonic vibration-assisted wet coating process, anhydrous ethanol was used as the coating medium, with the ultrasonic power set to 200–500 W and the ultrasonic frequency set to 20–40 kHz. Under the action of the above ultrasonic parameters, ... Particles, The particles and W particles maintain a stable dispersion in the liquid phase environment, reducing particle agglomeration and improving the uniformity of functional phase particle coating on the Al alloy base powder surface.

[0071] After ultrasonic vibration-assisted wet coating, the composite powder is dried to remove anhydrous ethanol from the coating medium and maintain the bonding state between powder particles. Vacuum drying is used at a temperature of 60–80℃ for at least 12 hours to ensure a stable particle structure in the coated composite powder.

[0072] Furthermore, the dried target composite powder is subjected to powder performance testing to evaluate whether it meets the requirements for laser powder bed fusion printing. Specifically, the Hall flowability of the target composite powder is no greater than 35 s / 50 g, and the loose packing density uniformity is better than ±0.05 g / cm³. By controlling the particle size distribution of the composite powder, the coating state of the functional phase particles, and the powder flowability, the target composite powder can be stably conveyed in the subsequent multi-hopper powder feeding system, ensuring accurate control of the material components corresponding to different functional areas.

[0073] Through the above powder preparation process, the target composite powder can simultaneously meet the material composition requirements corresponding to the gradient configuration scheme and the powder performance requirements corresponding to the laser powder bed melting process, providing a material basis for subsequent partitioning, layering scheduling and integrated structural and functional forming based on the multi-hopper powder feeding system.

[0074] In one possible implementation, step S102 further includes: determining the component ratio of the composite material raw materials based on the gradient configuration scheme, and performing planetary ball milling on the composite material raw materials to obtain initial composite powder; performing airflow classification on the initial composite powder, and screening and controlling the composite material raw materials according to the particle size distribution to obtain pretreated composite powder; placing the pretreated composite powder in a coating medium for ultrasonic vibration-assisted wet coating treatment, and dispersing and attaching the functional phase particles to the surface of the Al alloy matrix through ultrasonic vibration to obtain target composite powder; and controlling the volume fraction of the functional phase particles along the printing direction according to the gradient change relationship corresponding to the gradient configuration scheme.

[0075] Specifically, planetary ball milling includes processing materials configured according to the component ratio. powder, Powder, W powder, and Al alloy-based powder are added to a planetary ball mill. Through the centrifugal force generated by the high-speed rotation of the mill jar and the impact, compression, and shearing effects between the grinding media and powder particles, the different material particles undergo mechanical mixing and surface activation. During planetary ball milling, larger powder agglomerates are broken up by repeated impacts, further homogenizing the size of the functional phase particles and promoting… Particles, The initial dispersion of particles and W particles around the Al alloy matrix powder increases the contact area between different material components.

[0076] Furthermore, during the planetary ball milling process, by controlling the milling speed, ball-to-powder ratio, and milling time, uniform mixing of powder particles is achieved while avoiding excessive crushing and cold welding agglomeration. Planetary ball milling is primarily used to improve the compositional uniformity of multi-component powder systems, ensuring that the functional phase particle distribution in the initial composite powder meets the requirements of subsequent coating processes.

[0077] After planetary ball milling, the initial composite powder is obtained. Since planetary ball milling mainly achieves uniform mixing between powder particles, but particle size distribution differences may still exist between different materials, the initial composite powder is further subjected to airflow classification. Airflow classification utilizes the inertial differences of powder particles of different sizes in the airflow field to separate powder particles of different size ranges, thereby removing excessively large particles and abnormally agglomerated particles, and obtaining pretreated composite powder with a particle size distribution that meets the requirements of laser powder bed melting process.

[0078] After airflow classification, the particle size of the pretreated composite powder is matched and configured. The particle size is 1–5 μm. The particle size is 3–10 μm, the W particle size is 1–5 μm, and the Al alloy base powder particle size is 15–53 μm. This combination of particle sizes allows the smaller functional phase particles to be distributed within the gaps between the Al alloy base powder particles, improving powder packing density while ensuring good flowability and spreading continuity during powder spreading.

[0079] Furthermore, the pretreated composite powder, after airflow classification, undergoes ultrasonic vibration-assisted wet coating to improve the bonding stability between the functional phase particles and the Al alloy matrix powder. Specifically, the pretreated composite powder is added to anhydrous ethanol to form a powder suspension system, which is then treated by ultrasonic vibration. During ultrasonic vibration, periodic pressure changes occur within the liquid medium, causing the formation of numerous microbubbles and cavitation. The local impact of bubble bursting and the disturbance of liquid flow further cavitate the aggregated particles. Particles, The particles and W particles are redispersed.

[0080] Meanwhile, under the action of ultrasonic vibration, the functional phase particles are driven by the liquid phase flow and come into full contact with the surface of Al alloy base powder. Under the influence of interparticle forces and surface adsorption, they adhere to the surface of Al alloy base powder, so that the functional phase particles are uniformly coated on the periphery of Al alloy base powder, forming a composite powder structure with Al alloy base powder as the main body and functional phase particles uniformly distributed.

[0081] The ultrasonic power for ultrasonic vibration-assisted wet coating treatment is 200–500 W, and the ultrasonic frequency is 20–40 kHz. By adjusting the ultrasonic power and frequency, the functional phase particles are kept in a stable dispersed state, avoiding particle agglomeration due to insufficient ultrasonic energy or damage to the powder particle structure due to excessive ultrasonic energy.

[0082] After ultrasonic vibration-assisted wet coating, the resulting composite powder is subjected to vacuum drying to remove coating media such as anhydrous ethanol and maintain the adhesion of functional phase particles to the Al alloy base powder surface. The drying temperature is 60–80℃, and the vacuum drying time is no less than 12 hours. Low-temperature, long-duration vacuum drying reduces the risk of powder oxidation and ensures that the composite powder has a stable particle structure.

[0083] Furthermore, after completing the above processing, the performance of the target composite powder is tested. Specifically, the Hall flowability of the target composite powder is no greater than 35 s / 50 g, and the loose packing density uniformity is better than ±0.05 g / cm³. Initial uniform mixing of the multi-component powders is achieved through planetary ball milling; particle size distribution is optimized through airflow classification; and uniform adhesion of functional phase particles to the Al alloy base powder surface is achieved through ultrasonic vibration-assisted wet coating. This ensures that the resulting target composite powder simultaneously meets the material composition requirements corresponding to the gradient configuration scheme and the powder feeding, spreading, and forming requirements during the laser powder bed melting process.

[0084] Step S103: Based on the gradient configuration scheme, the target composite powder is partitioned and layered by the laser powder bed melting equipment of the multi-hopper powder feeding system, and a shielding functional area, a component gradient transition layer and a load-bearing structure area are formed during a single printing process.

[0085] Specifically, since the gradient configuration scheme obtained in step S101 sequentially sets the shielding functional area, the composition gradient transition layer, and the load-bearing structure area along the printing direction, and different areas correspond to different material composition ratios, it is necessary to partition and layer the target composite powder according to the gradient configuration scheme so that the laser powder bed melting equipment can complete the continuous forming of different functional areas according to the preset material composition relationship in the same printing process.

[0086] Specifically, the target composite powder is classified and stored according to the material composition relationship corresponding to the gradient configuration scheme, and then loaded into different hoppers of the multi-hopper powder feeding system. The multi-hopper powder feeding system selectively delivers the target composite powder in different hoppers based on the region division information and interlayer material change information in the gradient configuration scheme, so that the composite powder composition corresponding to different printing layers is consistent with the target gradient configuration scheme.

[0087] Furthermore, the material composition information corresponding to the current printing layer is determined based on the gradient configuration scheme, and the multi-hopper powder feeding system is controlled to perform powder switching scheduling based on the material composition information. Specifically, for the shielded functional area, the multi-hopper powder feeding system is controlled to convey powder with high efficiency. , In addition, a target composite powder with a W functional phase ratio is used to improve the neutron absorption capacity and gamma-ray attenuation capacity of the forming area; for the load-bearing structure area, the multi-hopper powder feeding system is controlled to transport the target composite powder with Al alloy matrix as the main component to ensure the structural load-bearing capacity of the forming area; for the composition gradient transition layer, the target composite powder in different hoppers is continuously proportionally adjusted according to the functional phase volume fraction change relationship corresponding to the gradient configuration scheme, so that the functional phase particle content gradually changes along the printing direction.

[0088] Specifically, the multi-hopper powder feeding system rapidly switches target composite powders with different composition ratios according to a preset inter-layer scheduling sequence, ensuring that the powder composition of each printing layer matches the gradient configuration scheme. The switching response time of the multi-hopper powder feeding system is no more than 0.1 seconds to guarantee the continuity of material composition switching between adjacent printing areas and avoid gradient region shifts due to powder switching delays.

[0089] Furthermore, to avoid cross-contamination of powders with different compositions in different hoppers during the switching process, an isolation and sealing structure is set between the hoppers in the multi-hopper powder feeding system. The isolation and sealing effect reduces the mixing effect between powders of different materials, so that the powder cross-contamination rate is no more than 0.01wt%, ensuring the accuracy of the material composition ratio corresponding to different printing areas.

[0090] After the target composite powder is partitioned and layered, a laser powder bed melting equipment is used to lay the layered target composite powder and then laser melt it into shape. The process parameters for the multi-material gradient laser powder bed melting process are set as follows: laser power of 150-400W, scanning speed of 500-1500mm / s, layer thickness of 20-50μm, scanning spacing of 60-120μm, and spot diameter of 50-100μm.

[0091] Specifically, during the printing process, by controlling process parameters such as laser power, scanning speed, scanning spacing, and layer thickness, the laser energy is applied to the currently laid target composite powder layer, causing the powder particles to melt, fuse, and solidify, thereby forming a continuous and dense shaped layer. At the same time, by controlling the spot diameter and scanning path, the stability of the molten pool corresponding to the laser action area is improved, reducing the probability of forming defects such as porosity and incomplete fusion.

[0092] Furthermore, to prevent oxidation of the active metal materials during the printing process, the laser powder bed melting equipment employs a protective atmosphere for forming. The protective gas used is high-purity argon with a purity of no less than 99.999%, and the oxygen content in the forming environment is controlled below 10 ppm. This low-oxygen protective environment reduces the oxidation risk of the Al alloy matrix and functional phase materials during high-temperature melting, thereby improving the internal structural stability of the formed parts.

[0093] Furthermore, during the laser powder bed melting process, to suppress the formation of coarse columnar crystals in the Al alloy matrix under rapid solidification conditions and improve the uniformity of the microstructure in the forming region, a grain refiner is simultaneously transported into the laser molten pool. The grain refiner includes nano-TiB2 or nano-SiC particles, with a mass fraction of 0.1% to 0.5%.

[0094] When nano-TiB2 or nano-SiC grain refiners are introduced into the laser molten pool simultaneously with the target composite powder, they act as heterogeneous nucleation nuclei during the rapid heating and solidification process of the molten pool. By increasing the number of effective nuclei during the solidification process of the Al matrix, they reduce the tendency of continuous epitaxial growth of grains along the heat flow direction, thereby inhibiting the formation of coarse columnar crystals and promoting the formation of equiaxed crystal structures.

[0095] By controlling the proportion of grain refiner, the grain size of the Al matrix during solidification is kept within the range of 1–5 μm, reducing the decrease in mechanical properties and microstructure anisotropy caused by coarse grains, and improving the microstructure continuity between gradient configuration regions. Simultaneously, the grain refiner and… , Together with the W functional phase particles, they improve the density and structural stability of the formed region while ensuring radiation shielding performance.

[0096] After completing the partitioning, layering, and laser powder bed melting of the target composite powder, a shielding functional area, a composition gradient transition layer, and a load-bearing structural area are formed in a single printing process. Specifically, the shielding functional area achieves radiation shielding through a high proportion of functional phase materials, the load-bearing structural area achieves structural load-bearing through an Al alloy matrix, and the composition gradient transition layer achieves a smooth connection between the two functional areas through continuous changes in material composition, thereby avoiding the performance degradation problem caused by interface connection in traditional split manufacturing processes.

[0097] By using the above method, a multi-hopper powder feeding system is used to precisely schedule target composite powders of different compositions. Combined with the control of laser powder bed melting process parameters, the gradient configuration scheme obtained in the material design stage can be directly mapped to the actual manufacturing process. In a single printing process, a structural and functional integrated shielding material with continuous material gradient changes can be formed.

[0098] In one possible implementation, step S103 further includes: determining the material composition information corresponding to different printing areas based on the gradient configuration scheme, and controlling the multi-hopper powder feeding system to switch and schedule the target composite powder according to the material composition information; the material composition information is the component proportion corresponding to different decision variables; determining the interlayer configuration information corresponding to different printing areas based on the gradient configuration scheme, and controlling the laser powder bed melting equipment to perform layer-by-layer powder spreading and laser melting forming according to the interlayer configuration information, so that the target composite powder with different material compositions forms a shielding functional area, a component gradient transition layer and a load-bearing structural area in the same printing process.

[0099] The gradient configuration scheme involves material composition variations and spatial structure distribution relationships, requiring conversion into powder scheduling and forming control information corresponding to the manufacturing process. By acquiring material composition information for different printing areas, the proportions of functional phase materials and matrix materials for each printing area are determined. This material composition information is then mapped to a multi-hopper powder feeding system to ensure that the actual supply ratio of the target composite powder remains consistent with the gradient configuration scheme.

[0100] Material composition information consists of the proportions of components corresponding to different decision variables, where the decision variables include... Volume fraction Volume fraction, W volume fraction, and Al alloy matrix composition. Based on the component ratio corresponding to different printing areas, target composite powders with different composition ratios are respectively placed in different hoppers of the multi-hopper powder feeding system, and powder switching is performed according to the printing sequence corresponding to the gradient configuration scheme.

[0101] For the shielded functional area, the multi-hopper powder feeding system is controlled according to the material composition information to convey the target composite powder with high functional phase content, so that... , And the proportion of W corresponding to the component meets the radiation shielding requirements; for the load-bearing structure area, the multi-hopper powder feeding system is controlled to transport the target composite powder with a high Al alloy matrix content to improve the mechanical load-bearing capacity of the formed structure; for the composition gradient transition layer, the supply ratio of the target composite powder in different hoppers is continuously adjusted according to the gradient change relationship corresponding to the gradient configuration scheme, so that the volume fraction of functional phase particles gradually changes along the printing direction.

[0102] The multi-hopper powder feeding system generates a corresponding powder switching sequence based on the material composition information and executes the target composite powder scheduling according to the powder switching sequence. The switching response time of the multi-hopper powder feeding system is no more than 0.1s to ensure the continuity of material composition changes between adjacent printing areas; the hoppers adopt an isolated and sealed structure to keep powders of different compositions transported independently, with a powder cross-contamination rate of no more than 0.01wt%, avoiding deviation of the actual printed material composition from the design requirements due to powder mixing.

[0103] Based on the gradient configuration scheme, the interlayer configuration information corresponding to different printing areas is determined. The interlayer configuration information includes the region division relationship, material composition change relationship, and forming sequence information corresponding to different printing layers. According to the interlayer configuration information, the laser powder bed melting equipment is controlled to perform layer-by-layer powder laying and laser melting forming, so that the target composite powder composition and spatial position corresponding to the current printing layer are matched with the gradient configuration scheme.

[0104] During the forming process of each printed layer, the multi-hopper powder feeding system delivers the target composite powder according to the material composition information of the current printed layer. The laser powder bed melting equipment controls the powder spreading range and laser scanning path according to the interlayer configuration information, so that the target composite powders with different compositions can be melted, fused and solidified in the corresponding areas. Through the layer-by-layer accumulation forming method, the high-functional phase material area gradually forms a shielding functional area, the area with continuously changing functional phase ratio forms a composition gradient transition layer, and the area with a high proportion of Al alloy matrix forms a load-bearing structural area.

[0105] The process parameters for multi-material gradient laser powder bed melting were set as follows: laser power 150–400 W, scanning speed 500–1500 mm / s, layer thickness 20–50 μm, scanning spacing 60–120 μm, and spot diameter 50–100 μm. By controlling the laser process parameters, powder layers with different material compositions received matched energy input, reducing defects such as porosity and incomplete fusion caused by differences in material melting points and thermal properties.

[0106] The laser powder bed melting equipment performs the printing process in a protective atmosphere. The protective gas is high-purity argon with a purity of not less than 99.999%, and the oxygen content in the printing area is controlled below 10 ppm to reduce the oxidation of the Al alloy matrix and functional phase materials during the high-temperature melting process and improve the internal structure stability of the formed parts.

[0107] Through the above process, the material composition information in the gradient configuration scheme is converted into multi-hopper powder feeding scheduling instructions, and the interlayer configuration information is converted into laser powder bed melting and forming control parameters, so that the target composite powder with different material composition can complete continuous gradient forming in one printing process, forming a structural and functional integrated shielding material with shielding functional area, composition gradient transition layer and load-bearing structural area.

[0108] Step S104: Defect identification is performed on each forming area corresponding to the target composite powder using an in-situ quality inspection system, and the defect detection results are output. The in-situ quality inspection system includes a laser ultrasonic detection structure and a defect identification model.

[0109] Specifically, the ultrasonic detection signal corresponding to each forming area is obtained through the laser ultrasonic detection structure, and the ultrasonic detection signal is analyzed using a defect identification model to identify defects such as pores, cracks, and lack of fusion generated during the laser powder bed melting process. The defect detection results, including defect type, defect location, and defect size, are obtained, providing a basis for subsequent 3D printing process parameter adjustment and defect compensation and repair.

[0110] In one possible implementation, step S104 further includes: acquiring ultrasonic detection signals corresponding to each forming area based on the laser ultrasonic detection structure, and acquiring forming quality detection information corresponding to each forming area based on the ultrasonic wave propagation state of the ultrasonic detection signals; performing feature analysis on the forming quality detection information based on the defect recognition model to obtain defect detection results; training the defect recognition model using preset defect sample data; and including defect type information, defect location information, and defect size information.

[0111] Specifically, the laser ultrasonic testing structure includes a pulsed laser excitation module and a broadband piezoelectric sensor receiving array. The pulsed laser excitation module applies laser pulses to each forming region, generating a transient thermoelastic response within the material through photothermal conversion, thereby exciting ultrasonic wave propagation signals. The laser wavelength of the pulsed laser excitation module is 1064 nm, the pulse width is no greater than 10 ns, and the repetition frequency is 10–100 Hz. This short-pulse-width, high-frequency excitation method improves the ultrasonic signal response speed, meeting the online detection requirements during the laser powder bed melting layer-by-layer forming process.

[0112] A broadband piezoelectric sensor array is used to acquire the response signal of ultrasonic waves after propagation through the forming region. Its frequency response range is 0.5–20 MHz, and it can acquire ultrasonic reflection signals, scattering signals, and energy attenuation signals corresponding to different defect states. Since defects such as pores, lack of fusion, and cracks will change the ultrasonic propagation path and acoustic impedance matching relationship, forming quality detection information reflecting the current internal quality state of the forming layer can be obtained based on the acquired ultrasonic detection signals.

[0113] Furthermore, the defect identification model is constructed using a convolutional neural network (CNN). The model is trained using pre-set defect sample data, which includes ultrasonic detection signals, defect location annotations, and defect size annotations corresponding to different types of defects. During training, the temporal, frequency, and propagation response features of the ultrasonic detection signals are input into the initial CNN model. Convolutional layers extract local variation features from the ultrasonic signals, pooling layers reduce feature dimensionality and enhance feature robustness, and fully connected layers output the corresponding defect category probability and spatial distribution information.

[0114] The classification results of the defect identification model are optimized using a loss function, which is expressed as:

[0115] in, This represents the loss value during the training process of the defect identification model; Indicates the number of preset defect categories; Indicates the first The actual label value corresponding to the class defect; The first output of the model represents the... Defect category prediction probability values. By continuously adjusting the weight parameters in the convolutional neural network, the deviation between the model's output defect category probability and the actual defect label is reduced, thereby improving the accuracy of defect identification.

[0116] The trained defect recognition model is used to perform feature analysis on the forming quality inspection information to obtain defect detection results. These results include defect type information, defect location information, and defect size information. Specifically, the defect type information determines the defect category corresponding to the current forming area; the defect location information determines the spatial position of the defect within the current printing layer; and the defect size information determines the affected area of ​​the defect region.

[0117] The in-situ quality inspection system has a detection spatial resolution of no more than 200μm and a single-layer detection time of no more than 30s / dm², enabling the in-situ quality inspection system to perform real-time detection on each layer of the forming area while meeting the requirements of the laser powder bed melting forming cycle time, and to feed back the defect detection results to the subsequent process control process.

[0118] Furthermore, based on the defect type, location, and size information from the defect detection results, a corresponding compensation and repair strategy is determined. When a defect is detected in the target area, the process control module adjusts the process parameters for subsequent printing layers according to the defect status. This is achieved by increasing the number of plasma remelting cycles in subsequent layers or decreasing the scanning speed of subsequent layers. Specifically, for detected defective areas, the number of plasma remelting cycles in subsequent layers is increased by 1–3 times to promote the remelting and bonding of unfused areas through repeated heat input; or the scanning speed of subsequent layers is reduced by 5%–20% to increase the energy input per unit area, allowing the defective area to fully melt, thereby reducing the impact of defects on the performance of the final molded part.

[0119] Using the above method, an in-situ laser ultrasonic detection structure composed of a pulsed laser excitation module and a broadband piezoelectric sensor receiving array is used to obtain the internal quality status of each layer forming area in real time. The defect type, defect location and defect size are identified by a defect recognition model based on a convolutional neural network. At the same time, the subsequent 3D printing process parameters are adjusted according to the recognition results to realize online detection and closed-loop repair in the additive manufacturing process of gradient shielding materials.

[0120] Step S105: Adjust the 3D printing process parameters based on the defect detection results, and compensate and repair the defect area using the adjusted 3D printing process parameters.

[0121] Specifically, the process control module locates defect areas based on defect detection results and adjusts the 3D printing process parameters of subsequent layers according to different defect states. For detected defects such as incomplete fusion and porosity, the heat input to the defect area is increased by increasing the number of plasma remelting cycles in subsequent layers, allowing the incompletely melted areas to remelt and achieve material bonding. For defect areas caused by insufficient energy input, the scanning speed of subsequent layers is reduced, and the laser action time is extended to increase the energy input per unit area, thereby achieving compensation and repair of the defect area.

[0122] By means of the above method, the defect detection results output by the in-situ quality inspection system are fed back to the laser powder bed melting equipment, so that the printing process is transformed from fixed parameter forming to dynamic process adjustment based on defect status, realizing closed-loop control of defect detection, parameter adjustment and defect repair in the forming process.

[0123] In one possible implementation, step S105 further includes: adjusting the 3D printing process parameters based on the defect detection results, and compensating and repairing the defect area using the adjusted 3D printing process parameters. Specifically, this includes: determining the defect repair method corresponding to the defect area based on defect type information; determining the printing layer position and scanning path range corresponding to the defect area based on defect location information; determining the repair area range and compensation forming parameters corresponding to the defect area based on defect size information; associating the defect repair method, printing layer position, scanning path range, and compensation forming parameters to obtain a defect repair process plan; adjusting the 3D printing process parameters based on the defect repair process plan, and controlling the laser powder bed melting equipment to compensate and repair the defect area according to the adjusted 3D printing process parameters.

[0124] Specifically, because the target composite powder includes , The W and Al alloy matrices, with different printing areas corresponding to different functional proportions, result in variations in the molten pool temperature, material flow state, and solidification behavior during the laser powder bed melting process. When the in-situ quality inspection system detects defects such as porosity, lack of fusion, and cracks, the subsequent printing process needs to be dynamically adjusted based on the defect type, location, and size to ensure that the defective area receives the thermal input conditions required for metallurgical bonding.

[0125] The defect repair method corresponding to the defect region is determined based on defect type information. Defect type information is output by the defect identification model and is used to represent the defect category corresponding to the current forming region. For different defect formation mechanisms, a mapping relationship between defect type and repair method is established. Specifically, for porosity defects and incomplete fusion defects caused by insufficient laser energy, the local heat input is increased by increasing the number of subsequent plasma remelting layers or reducing the scanning speed; for crack defects, the risk of defect propagation is reduced by adjusting the scanning path direction and decreasing the rate of change of the thermal gradient.

[0126] Construct a defect repair decision model based on defect type information:

[0127] in, This indicates the final determined method for defect repair; This represents a set of preset defect repair methods; This represents the j-th candidate repair method; Indicates the characteristics of the defect type; Indicates the size characteristics of the defect; This indicates the material composition characteristics corresponding to the current printing area; Indicates historical print thermal input characteristics; Let k represent the evaluation function, which is used to evaluate the impact of different repair methods on the defect elimination effect; This represents the weight parameter corresponding to the k-th evaluation function, with a value range of [0,1]. A repair method matching the current defect state is selected by comprehensively evaluating the defect type, material composition, and historical forming state.

[0128] The location of the defect is determined based on the defect location information, which determines the corresponding printing layer position and scanning path range. The defect location information is determined by the ultrasonic propagation state acquired by the laser ultrasonic testing structure and converted into the spatial coordinate system corresponding to the laser powder bed melting equipment, so that the detected defect area can be correlated with the actual printing path.

[0129] The defect spatial location mapping process is represented as:

[0130] in, Represents the transformed defect space coordinates; This represents the spatial mapping matrix between the laser ultrasonic testing coordinate system and the laser powder bed melting equipment coordinate system; Indicates the initial position of ultrasonic excitation; Indicates the time it takes for ultrasound to travel; Indicates time The corresponding ultrasonic propagation speed inside the material; This represents the ultrasonic propagation direction vector. Through mapping, the detected defect location is converted into the printing layer number, scanning path position, and coordinates of the local repair area.

[0131] The repair area and compensation forming parameters corresponding to the defect region are determined based on the defect size information. Since there are heat-affected zones and potential areas of insufficient bonding around the defect region, the actual repair area needs to be expanded according to the defect size to ensure that the defect boundary area can be remelted and bonded.

[0132] The repair area is calculated as follows:

[0133] in, Indicates the area to be compensated and repaired; Indicates the defect detection area; Indicates the region expansion operation; This represents a region expansion function based on defect size and material properties; Indicates the defect size parameter; Indicates the current thermal conductivity parameters of the material; This represents the historical thermal input impact parameters. The repair area is calculated to ensure the compensation repair process covers the defective area and the affected areas surrounding it.

[0134] The compensation forming parameters are further determined based on the repair area. These parameters include laser power adjustment, scanning speed adjustment, and plasma remelting times. Their calculation relationship is expressed as follows:

[0135] in, Represents the set of compensation forming parameters; This indicates the severity rating of the defect; Indicates the initial laser power parameters; Indicates the initial scan speed parameter; This parameter represents the initial number of remelting cycles. This indicates the density parameter of the material composition in the current region; This indicates the material composition information for the current area; This represents the compensation parameter adjustment function. By using this function, different degrees of process parameter correction are applied to different defect states.

[0136] Furthermore, the defect repair method, printing layer position, scanning path range, and compensation forming parameters are correlated to obtain a defect repair process scheme. The correlation processing is used to convert the defect status information obtained from detection into control commands that can be executed by the laser powder bed melting equipment.

[0137] The defect repair process is represented as follows:

[0138] in, This indicates the defect repair process plan; Indicates the defect repair method; Indicates the location of the defect in the printed layer; Indicates the range of the scan path corresponding to the defect; Indicates the compensation forming parameters; This represents the severity rating of the defect. By correlating these parameters, the remediation strategy can simultaneously match the defect category, spatial location, and impact level.

[0139] Based on the defect repair process plan, the 3D printing process parameters are adjusted, and the laser powder bed melting equipment is controlled to compensate and repair the defective areas according to the adjusted 3D printing process parameters. The process control module adjusts the laser power, scanning speed, and remelting times for subsequent printing layers according to the defect repair process plan. Specifically, for detected defective areas, the plasma remelting times of subsequent layers are increased by 1 to 3 times, allowing the defective areas to remelt and bond after multiple thermal cycles; or the scanning speed of subsequent layers is reduced by 5% to 20%, increasing the energy input per unit area to ensure sufficient melting of the defective areas.

[0140] Through the above process, the defect detection results output by the in-situ quality inspection system are dynamically linked with the process control process of the laser powder bed melting equipment. This enables the printing process to automatically adjust the repair strategy based on the real-time detected defect status, achieving closed-loop control of defect identification, repair scheme generation, process parameter optimization, and defect compensation and repair, thereby improving the forming quality of the integrated structural and functional shielding material.

[0141] Step S106: Perform performance verification on the molded part after defect repair, and output the molded part that passes the performance verification as a structural and functional integrated shielding material; the performance verification includes radiation shielding performance verification, mechanical performance verification and microstructure performance verification.

[0142] Specifically, the molded part after defect repair undergoes staged heat treatment to release residual stress within the material and promote the uniform precipitation of the Al matrix reinforcing phase, thereby improving the structural stability of the molded part. The heat treatment process includes a low-temperature stress relief stage, a medium-temperature strengthening stage, and a slow cooling stage. The entire heat treatment process is carried out under the protection of argon or a vacuum inert atmosphere to prevent oxidation or abnormal element diffusion of the composite material during high-temperature treatment.

[0143] After heat treatment, the formed parts undergo further performance verification, including radiation shielding performance verification, mechanical property verification, and microstructure performance verification. Among these, radiation shielding performance verification is used to evaluate… , The study also examines the neutron absorption and gamma-ray attenuation effects of the W functional phase in gradient configurations; mechanical property verification is used to evaluate the load-bearing capacity of the formed parts and the structural stability after defect repair; and microstructure performance verification is used to analyze the internal grain morphology, functional phase distribution, and interface bonding state of the material after heat treatment.

[0144] The heat treatment process includes the following steps: the first stage involves holding at 100–150℃ for 1–2 hours to gradually release the residual thermal stress generated during the rapid melting and solidification process, thereby reducing internal stress concentration; the second stage involves holding at 200–250℃ for 2–4 hours to promote the uniform precipitation of the Al matrix strengthening phase, thereby improving the stability of the matrix structure and its mechanical properties; the third stage involves cooling the furnace to room temperature, with the cooling rate controlled to be no more than 2℃ / min, to reduce the secondary thermal stress caused by rapid temperature changes.

[0145] Through the above processing, the molded part after defect repair obtains a stable microstructure, and its compliance with the design requirements of a structurally and functionally integrated shielding material is determined through multi-dimensional performance verification. For molded parts that meet the requirements for radiation shielding performance, mechanical properties, and microstructure performance, they are output as structurally and functionally integrated shielding materials.

[0146] In one possible implementation, step S106 further includes: obtaining performance verification results based on the defect-repaired molded part; the performance verification results include radiation shielding performance, mechanical properties, and microstructure performance; matching the radiation shielding performance, mechanical properties, and microstructure performance with preset performance requirements, and determining whether the defect-repaired molded part meets the performance requirements of the integrated structural and functional shielding material; if the defect-repaired molded part meets the performance requirements of the integrated structural and functional shielding material, outputting the defect-repaired molded part as the integrated structural and functional shielding material; if the defect-repaired molded part does not meet the performance requirements of the integrated structural and functional shielding material, readjusting the 3D printing process parameters for compensation repair.

[0147] Specifically, the molded parts after defect compensation and repair require further post-processing and multi-dimensional performance verification to evaluate whether the material properties after gradient configuration design, multi-material laser powder bed melting forming, and defect closed-loop repair meet the design requirements of a structurally functional integrated shielding material. Since the molded parts simultaneously bear radiation protection and structural load-bearing functions, they cannot be judged based on a single performance index, but require a comprehensive evaluation of radiation shielding performance, mechanical properties, and microstructure performance.

[0148] Before performance verification, the defect-repaired molded parts underwent staged heat treatment to reduce residual thermal stress generated during the rapid melting and solidification process of additive manufacturing and to improve the precipitation state of the reinforcing phase in the Al matrix. The heat treatment process consisted of three stages: the first stage involved holding at 100–150℃ for 1–2 hours to gradually release the residual thermal stress accumulated during the forming process and reduce internal stress concentration; the second stage involved holding at 200–250℃ for 2–4 hours to allow the reinforcing phase in the Al matrix to precipitate uniformly and improve the material's structural stability; the third stage involved furnace cooling to room temperature at a rate controlled not exceeding 2℃ / min to avoid rapid cooling and the generation of new thermal stress. The entire heat treatment process was carried out under argon or vacuum inert atmosphere protection to reduce the risk of material oxidation at high temperatures.

[0149] After heat treatment, the performance verification results of the formed part after defect repair were obtained. Among these, radiation shielding performance was used to evaluate the gradient configuration scheme. , And the shielding ability of W-function relative to gamma rays and neutrons; mechanical properties are used to evaluate the strength, plasticity and structural stability of the load-bearing structural region and the gradient transition region; microstructure properties are used to evaluate the grain size, functional phase particle distribution, porosity and interface bonding of the formed part.

[0150] During the radiation shielding performance verification process, the material's attenuation capability against different radiation sources is evaluated by obtaining the gamma-ray shielding coefficient and thermal neutron absorptivity corresponding to the molded part. The comprehensive radiation shielding performance evaluation value can be expressed as:

[0151]

[0152] in, This indicates the radiation shielding performance evaluation value; Represents the normalized gamma-ray shielding coefficient; This represents the normalized thermal neutron absorptivity; and This represents the weighting parameter corresponding to the radiation shielding index, with a value range of [0,1]. It is used to adjust the importance of gamma-ray shielding capability and neutron absorption capability according to the actual application scenario.

[0153] During the mechanical performance verification process, the structural reliability of the load-bearing structural region and the composition gradient transition layer is evaluated by acquiring the tensile strength, structural compactness, and load-bearing stability parameters corresponding to the formed part. The mechanical performance evaluation values ​​can be expressed as:

[0154]

[0155] in, Indicates the mechanical performance evaluation value; Represents normalized tensile strength; Represents the normalized relative density; This represents the normalized fracture elongation performance parameter; , as well as This represents the weighting parameter for evaluating mechanical properties, with a value range of [0,1].

[0156] During the structural performance verification process, the internal microstructure of the molded part is obtained through microstructure detection, grain size analysis, and functional phase distribution detection. Since this scheme uses nano-TiB2 or nano-SiC grain refiners to suppress the growth of coarse columnar crystals in the Al matrix, it is necessary to verify whether the grain size meets the design requirements and to determine whether the functional phase particles are uniformly distributed.

[0157] The organizational structure performance evaluation value can be expressed as:

[0158] in, Indicates the performance evaluation value of the organizational structure; This indicates the average grain size obtained from the detection; Indicates the preset maximum grain size; Indicates the organizational defect rate; Indicates the evaluation parameters for the uniformity of functional phase particle distribution; , as well as This represents the organizational structure performance weight parameter, with a value range of [0,1].

[0159] Furthermore, the radiation shielding performance, mechanical properties, and microstructure properties are matched with preset performance requirements, and a comprehensive performance evaluation model is used to determine whether the molded part after defect repair meets the requirements of a structurally and functionally integrated shielding material.

[0160] The comprehensive performance evaluation model is expressed as follows:

[0161] in, This represents the overall performance evaluation value of the formed part; This indicates the radiation shielding performance evaluation value; Indicates the mechanical performance evaluation value; Indicates the performance evaluation value of the organizational structure; , as well as This represents the weighting parameter for comprehensive performance evaluation, with a value range of [0,1].

[0162] The comprehensive performance evaluation value Q is compared with the preset performance threshold. When the comprehensive performance evaluation value meets the preset requirements, and the radiation shielding performance, mechanical performance and microstructure performance meet the corresponding performance index requirements, the molded part after defect repair is determined to meet the requirements of the integrated structural and functional shielding material, and the molded part after defect repair is output as the integrated structural and functional shielding material.

[0163] When the repaired part fails to meet the preset performance requirements, the corresponding performance deviation type is determined based on the unmet performance indicators, and the performance verification results are fed back into the 3D printing process parameter adjustment process. Specifically, if the radiation shielding performance is insufficient, adjustments are made to the subsequent printing areas. , The laser energy input, scanning path, or gradient transition region configuration parameters should be adjusted if the mechanical properties are insufficient. If the microstructure properties are insufficient, the laser scanning speed, remelting times, and grain refiner delivery ratio should be adjusted.

[0164] Build a process parameter feedback adjustment model based on performance deviations:

[0165] in, This indicates the amount of adjustment for 3D printing process parameters; This indicates the results of the radiation shielding performance evaluation; This indicates the results of the mechanical performance evaluation; This indicates the results of the organizational structure performance evaluation; This indicates the deviation between the overall performance evaluation value and the preset performance threshold; This represents a process parameter mapping function, used to determine the direction of parameter adjustments in the next printing process based on performance deviations.

[0166] Through the above process, the performance verification results are fed back to the printing process control process, forming a closed-loop control system for material design, additive manufacturing, defect detection, defect repair, and performance evaluation. Material output is completed when the formed part meets the performance requirements of the integrated structural and functional shielding material; when the performance does not meet the requirements, the 3D printing process parameters are readjusted according to the performance deviation, and compensation repair is performed, thereby improving the radiation shielding performance, structural load-bearing capacity, and microstructure stability of the final formed material.

[0167] Please refer to Figure 3It presents a schematic diagram of additive manufacturing and defect closed-loop control of a gradient shielding material according to an embodiment of this application. Figure 3 In this process, composite powders of different components are transported to the forming area through a multi-hopper powder feeding system, and gradient forming of the shielding functional area, transition layer and load-bearing structure area is performed based on laser powder bed melting equipment; the forming process is controlled by laser scanning through a laser and galvanometer scanning system, and defects in the forming area are detected by in-situ laser ultrasonic testing. Based on the detection results, the printing process parameters are adjusted to achieve defect compensation and repair.

[0168] Please refer to Figure 4 The illustration shows a schematic diagram of the modules of an intelligent design optimization and 3D printing manufacturing device for a gradient shielding material provided in an embodiment of this application. The device includes an intelligent optimization design module 41, a composite powder preparation module 42, a gradient laser powder bed melting and forming module 43, an in-situ quality inspection module 44, a defect closed-loop compensation and repair module 45, and a performance verification output module 46. The intelligent optimization design module 41 is used to acquire material design data and input the material design data into the intelligent optimization design framework. The intelligent optimization design framework outputs a gradient configuration scheme based on the target optimization parameters as constraints. The gradient configuration scheme is divided into a shielding functional area, a composition gradient transition layer and a load-bearing structure area along the printing direction.

[0169] The composite powder preparation module 42 is used to process the composite material raw materials through a powder preparation process based on a gradient configuration scheme, and to prepare the target composite powder through ultrasonic vibration-assisted wet coating process; the powder preparation process includes planetary ball milling and airflow classification.

[0170] The gradient laser powder bed melting and forming module 43 is used to partition and layer the target composite powder based on the gradient configuration scheme and through the laser powder bed melting equipment of the multi-hopper powder feeding system, and form the shielding functional area, the component gradient transition layer and the load-bearing structure area in a single printing process.

[0171] The in-situ quality inspection module 44 is used to identify defects in each forming area corresponding to the target composite powder through the in-situ quality inspection system and output the defect inspection results; the in-situ quality inspection system includes a laser ultrasonic inspection structure and a defect identification model.

[0172] The defect closed-loop compensation and repair module 45 is used to adjust the 3D printing process parameters based on the defect detection results, and to compensate and repair the defect area through the adjusted 3D printing process parameters.

[0173] The performance verification output module 46 is used to perform performance verification on the molded part after defect repair, and output the molded part that passes the performance verification as a structural and functional integrated shielding material; the performance verification includes radiation shielding performance verification, mechanical performance verification and microstructure performance verification.

[0174] In one possible implementation, the intelligent optimization design module 41 is used to construct an intelligent optimization design framework constrained by target optimization parameters. Specifically, this includes: constructing an intelligent optimization design framework based on the coupling of a deep reinforcement learning algorithm and a Monte Carlo particle transport simulation; the deep reinforcement learning algorithm employs a proximal policy optimization algorithm, and a Monte Carlo particle transport simulation is invoked for verification each time the decision variables are updated; the decision variables include... Volume fraction Volume fraction, W volume fraction, and Al alloy matrix composition; target optimization parameters include gamma-ray shielding coefficient, thermal neutron absorptivity, tensile strength, and relative density.

[0175] In one possible implementation, the composite powder preparation module 42 is used to process composite material raw materials through a powder preparation process based on a gradient configuration scheme, and to prepare target composite powder through ultrasonic vibration-assisted wet coating treatment. Specifically, it includes: determining the component ratio corresponding to the composite material raw materials based on the gradient configuration scheme, and performing planetary ball milling on the composite material raw materials to obtain initial composite powder; performing airflow classification treatment on the initial composite powder, and screening and controlling the composite material raw materials according to the particle size distribution to obtain pretreated composite powder; placing the pretreated composite powder in a coating medium for ultrasonic vibration-assisted wet coating treatment, and dispersing and attaching functional phase particles to the surface of the Al alloy matrix through ultrasonic vibration to obtain target composite powder; the volume fraction of functional phase particles is controlled along the printing direction according to the gradient change relationship corresponding to the gradient configuration scheme.

[0176] In one possible implementation, the gradient laser powder bed melting and forming module 43 is used to form a shielding functional area, a composition gradient transition layer, and a load-bearing structural area during a single printing process. Specifically, it includes: determining the material composition information corresponding to different printing areas based on the gradient configuration scheme, and controlling the multi-hopper powder feeding system to switch and schedule the target composite powder according to the material composition information; the material composition information is the component proportion corresponding to different decision variables; determining the interlayer configuration information corresponding to different printing areas based on the gradient configuration scheme, and controlling the laser powder bed melting equipment to perform layer-by-layer powder spreading and laser melting and forming according to the interlayer configuration information, so that the target composite powder with different material compositions forms a shielding functional area, a composition gradient transition layer, and a load-bearing structural area in the same printing process.

[0177] In one possible implementation, the in-situ quality inspection module 44 is used to identify defects in each forming region corresponding to the target composite powder through the in-situ quality inspection system and output defect detection results. Specifically, it includes: acquiring the ultrasonic detection signal corresponding to each forming region based on the laser ultrasonic detection structure, and acquiring the forming quality inspection information corresponding to each forming region based on the ultrasonic wave propagation state of the ultrasonic detection signal; performing feature analysis on the forming quality inspection information based on the defect identification model to obtain defect detection results; the defect identification model is trained by preset defect sample data; the defect detection results include defect type information, defect location information, and defect size information.

[0178] In one possible implementation, the defect closed-loop compensation and repair module 45 is used to adjust the 3D printing process parameters based on the defect detection results, and to compensate and repair the defect area using the adjusted 3D printing process parameters. Specifically, this includes: determining the defect repair method corresponding to the defect area based on defect type information; determining the printing layer position and scanning path range corresponding to the defect area based on defect location information; determining the repair area range and compensation forming parameters corresponding to the defect area based on defect size information; associating the defect repair method, printing layer position, scanning path range, and compensation forming parameters to obtain a defect repair process plan; adjusting the 3D printing process parameters based on the defect repair process plan, and controlling the laser powder bed melting equipment to compensate and repair the defect area according to the adjusted 3D printing process parameters.

[0179] In one possible implementation, the performance verification output module 46 is used to perform performance verification on the molded part after defect repair, and output the molded part that passes the performance verification as a structural-functional integrated shielding material. Specifically, this includes: obtaining performance verification results based on the molded part after defect repair; the performance verification results include radiation shielding performance, mechanical properties, and microstructure performance; matching the radiation shielding performance, mechanical properties, and microstructure performance with preset performance requirements, and determining whether the molded part after defect repair meets the performance requirements of the structural-functional integrated shielding material; if the molded part after defect repair meets the performance requirements of the structural-functional integrated shielding material, outputting the molded part after defect repair as a structural-functional integrated shielding material; if the molded part after defect repair does not meet the performance requirements of the structural-functional integrated shielding material, readjusting the 3D printing process parameters for compensation and repair.

[0180] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0181] This application also provides an electronic device. (See reference...) Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: at least one processor 501, at least one communication bus 502, a user interface 503, at least one network interface 504, and a memory 505.

[0182] The communication bus 502 is used to enable communication between these components.

[0183] The user interface 503 may include a display screen and a camera. Optionally, the user interface 503 may also include a standard wired interface and a wireless interface.

[0184] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0185] The processor 501 may include one or more processing cores. The processor 501 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 505, and by calling data stored in memory 505. Optionally, the processor 501 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 501 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 501 and may be implemented as a separate chip.

[0186] The memory 505 may include random access memory (RAM) or read-only memory. Optionally, the memory 505 may include a non-transitory computer-readable storage medium. The memory 505 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 505 may also be at least one storage device located remotely from the aforementioned processor 501. (Refer to...) Figure 5 The memory 505, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and intelligent design optimization and 3D printing manufacturing applications for gradient shielding materials.

[0187] exist Figure 5In the illustrated electronic device, the user interface 503 is primarily used to provide an input interface for the user and acquire user input data; while the processor 501 can be used to call the intelligent design optimization and 3D printing manufacturing application stored in the memory 505 for gradient shielding materials. When executed by one or more processors 501, the electronic device performs one or more of the methods described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0188] This application also provides a non-transitory computer-readable storage medium storing instructions. When executed by one or more processors, these instructions cause an electronic device to perform one or more of the methods described in the above embodiments.

[0189] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0190] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0191] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0192] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0193] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0194] The above description is merely an exemplary embodiment disclosed in this application and should not be construed as limiting the scope of this application. Any equivalent changes and modifications made in accordance with the teachings of this application shall still fall within the scope of this application.

[0195] This application is intended to cover any variations, uses, or adaptations disclosed herein that follow the general principles disclosed herein and include common knowledge or customary technical means in the art that are not described in this application.

Claims

1. A method for intelligent design optimization and 3D printing manufacturing of a gradient shielding material, characterized in that, The method includes: Material design data is acquired and input into an intelligent optimization design framework. The intelligent optimization design framework outputs a gradient configuration scheme based on the target optimization parameters as constraints. The gradient configuration scheme is divided into a shielding functional area, a composition gradient transition layer, and a load-bearing structure area along the printing direction. Based on the aforementioned gradient configuration scheme, the composite material raw materials are processed using a powder preparation process, and the target composite powder is prepared by ultrasonic vibration-assisted wet coating; the powder preparation process includes planetary ball milling and airflow classification. Based on the gradient configuration scheme, the target composite powder is partitioned and layered by the laser powder bed melting equipment of the multi-hopper powder feeding system, and the shielding functional area, the component gradient transition layer and the load-bearing structure area are formed in a single printing process. The in-situ quality inspection system identifies defects in each layer of the target composite powder forming area and outputs the defect detection results; the in-situ quality inspection system includes a laser ultrasonic testing structure and a defect identification model. The 3D printing process parameters are adjusted based on the defect detection results, and the defective areas are compensated and repaired using the adjusted 3D printing process parameters. The performance of the molded part after defect repair is verified, and the molded part that passes the performance verification is output as a structural and functional integrated shielding material; the performance verification includes radiation shielding performance verification, mechanical performance verification and microstructure performance verification.

2. The method according to claim 1, characterized in that, The method further includes constructing an intelligent optimization design framework constrained by the target optimization parameters, specifically including: The intelligent optimization design framework is constructed by coupling a deep reinforcement learning algorithm with Monte Carlo particle transport simulation. The deep reinforcement learning algorithm employs a proximal policy optimization algorithm, and the Monte Carlo particle transport simulation is invoked once for verification each time the decision variables are updated. The decision variables include... Volume fraction Volume fraction, W volume fraction, and Al alloy matrix composition; the target optimization parameters include gamma-ray shielding coefficient parameter, thermal neutron absorptivity parameter, tensile strength parameter, and relative density parameter.

3. The method according to claim 2, characterized in that, The process based on the gradient configuration scheme involves treating the composite material raw materials using a powder preparation process and preparing the target composite powder through ultrasonic vibration-assisted wet coating, specifically including: Based on the gradient configuration scheme, the component ratio of the composite material raw material is determined, and the composite material raw material is subjected to planetary ball milling to obtain the initial composite powder. The initial composite powder is subjected to airflow classification treatment, and the raw materials of the composite material are screened and controlled according to the particle size distribution to obtain pretreated composite powder. The pretreated composite powder is placed in a coating medium and subjected to ultrasonic vibration-assisted wet coating treatment. The functional phase particles are dispersed and attached to the surface of the Al alloy matrix by ultrasonic vibration to obtain the target composite powder. The volume fraction of the functional phase particles is controlled along the printing direction according to the gradient change relationship corresponding to the gradient configuration scheme.

4. The method according to claim 2, characterized in that, The formation of the shielding functional area, the composition gradient transition layer, and the load-bearing structure area during a single printing process specifically includes: Based on the gradient configuration scheme, the material composition information corresponding to different printing areas is determined, and the multi-hopper powder feeding system is controlled to switch and schedule the target composite powder according to the material composition information; the material composition information is the component proportion corresponding to different decision variables; Based on the gradient configuration scheme, the interlayer configuration information corresponding to different printing areas is determined, and the laser powder bed melting equipment is controlled to perform layer-by-layer powder spreading and laser melting forming according to the interlayer configuration information, so that the target composite powder with different material composition forms the shielding functional area, the composition gradient transition layer and the load-bearing structural area in the same printing process.

5. The method according to claim 1, characterized in that, The process of identifying defects in each forming region corresponding to the target composite powder using an in-situ quality inspection system and outputting the defect detection results specifically includes: Based on the laser ultrasonic detection structure, ultrasonic detection signals corresponding to each layer of the forming area are obtained, and forming quality detection information corresponding to each layer of the forming area is obtained according to the ultrasonic wave propagation state of the ultrasonic detection signals. The defect detection results are obtained by performing feature analysis on the forming quality inspection information based on the defect identification model; the defect identification model is trained by preset defect sample data; the defect detection results include defect type information, defect location information and defect size information.

6. The method according to claim 5, characterized in that, The process of adjusting 3D printing process parameters based on the defect detection results, and then compensating and repairing the defective area using the adjusted 3D printing process parameters, specifically includes: Based on the defect type information, determine the defect repair method corresponding to the defect area; Based on the defect location information, the printing layer position and scanning path range corresponding to the defect area are determined. Based on the defect size information, determine the repair area range and compensation forming parameters corresponding to the defect area; By associating the defect repair method, the printing layer position, the scanning path range, and the compensation forming parameters, a defect repair process scheme is obtained. Based on the defect repair process scheme, the 3D printing process parameters are adjusted, and the laser powder bed melting equipment is controlled to compensate and repair the defect area according to the adjusted 3D printing process parameters.

7. The method according to claim 1, characterized in that, The process of verifying the performance of the molded part after defect repair, and outputting the molded part that passes the performance verification as a structurally and functionally integrated shielding material, specifically includes: Performance verification results are obtained based on the molded part after defect repair; the performance verification results include radiation shielding performance, mechanical properties, and microstructure properties; The radiation shielding performance, mechanical properties, and microstructure properties are matched with preset performance requirements, and it is determined whether the molded part after defect repair meets the performance requirements of the integrated structural and functional shielding material. If the molded part after defect repair meets the performance requirements of the integrated structural and functional shielding material, the molded part after defect repair will be output as the integrated structural and functional shielding material. If the molded part after defect repair does not meet the performance requirements of the integrated structural and functional shielding material, the 3D printing process parameters are readjusted for compensation and repair.

8. A smart design optimization and 3D printing manufacturing device for gradient shielding materials, characterized in that, The device includes an intelligent optimization design module, a composite powder preparation module, a gradient laser powder bed melting and forming module, an in-situ quality inspection module, a defect closed-loop compensation and repair module, and a performance verification output module. The intelligent optimization design module is used to acquire material design data and input the material design data into the intelligent optimization design framework. The intelligent optimization design framework outputs a gradient configuration scheme based on the target optimization parameters as constraints. The gradient configuration scheme is divided into a shielding functional area, a composition gradient transition layer and a load-bearing structure area along the printing direction. The composite powder preparation module is used to process the composite material raw materials through a powder preparation process based on the gradient configuration scheme, and to prepare the target composite powder through ultrasonic vibration-assisted wet coating; the powder preparation process includes planetary ball milling and airflow classification. The gradient laser powder bed melting and forming module is used to partition and layer the target composite powder based on the gradient configuration scheme, and to form the shielding functional area, the component gradient transition layer and the load-bearing structure area in a single printing process. The in-situ quality inspection module is used to identify defects in each forming area corresponding to the target composite powder through the in-situ quality inspection system and output the defect inspection results; the in-situ quality inspection system includes a laser ultrasonic inspection structure and a defect identification model; The defect closed-loop compensation and repair module is used to adjust the 3D printing process parameters based on the defect detection results, and to compensate and repair the defect area using the adjusted 3D printing process parameters. The performance verification output module is used to perform performance verification on the molded part after defect repair, and output the molded part that passes the performance verification as a structural and functional integrated shielding material; the performance verification includes radiation shielding performance verification, mechanical performance verification and microstructure performance verification.

9. An electronic device, characterized in that, It includes a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the intelligent design optimization and 3D printing manufacturing method for the gradient shielding material as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1 to 7.

Images