Lightweight method for selective laser melting forming titanium alloy gradient lattice structure

Abstract

The invention discloses a lightweight method for a titanium alloy gradient lattice structure formed by selective laser melting, and relates to the technical field of manufacturing of titanium alloy gradient lattice structures, comprising the following steps: constructing a titanium alloy gradient lattice database; based on the data obtained by the database, establishing an intelligent optimization model by adopting a generative adversarial network + reinforcement learning mode; the training target of the intelligent optimization model is to generate a feasible structure meeting SLM (selective laser melting) manufacturing requirements; and lattice forming quality is optimized based on SLM process parameters, and a multi-objective optimization algorithm is adopted to perform global optimization on the generated intelligent lattice structure. According to the method, the generative adversarial network and reinforcement learning are combined, and lattice structures under different working conditions are accurately simulated and optimized. By means of unit cell size adjustment of reinforcement learning, light weight can be achieved to the maximum degree on the premise that the structural strength is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of the manufacture of titanium alloy gradient lattice structures, and particularly to a lightweight method for laser selective melting forming of titanium alloy gradient lattice structures. Background Art

[0002] With the continuous development of the laser selective melting (SLM) technology, the application of titanium alloys and their gradient lattice structures has received extensive attention in multiple fields. Titanium alloy materials, with their excellent mechanical properties, corrosion resistance, and relatively low density, have become important materials for high-performance components. However, traditional processing methods for titanium alloys have problems such as high cost, long manufacturing cycle, and uneven local properties. Especially when manufacturing complex structures, it is difficult to balance the strength and weight of the structure.

[0003] As a new type of structure, the gradient lattice structure (GLS) can optimize its mechanical properties and weight by changing the lattice size and density in different regions, and is particularly suitable for additive manufacturing technologies such as 3D printing. However, designing and optimizing such a structure still faces multiple technical challenges:

[0004] How to design a gradient lattice structure that can withstand external forces and achieve lightweight through a suitable parametric modeling method, and traditional lattice optimization methods usually only design based on a single objective (such as minimum mass or maximum strength), lacking consideration of multiple indicators such as thermal stress accumulation and complexity of laser scanning paths. Summary of the Invention

[0005] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title. However, such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the problems existing in the above-mentioned prior art, the present invention is proposed.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] Including the following steps:

[0009] Construct a titanium alloy gradient lattice database, which includes: parameters of different lattice topologies, mechanical properties, and the influence on the final forming quality under various process parameters;

[0010] Based on the data obtained from the database, establish an intelligent optimization model by using the generative adversarial network + reinforcement learning method;

[0011] Among them, the generative adversarial network is responsible for simulating lightweight design solutions under various working conditions; reinforcement learning is responsible for adjusting the unit cell parameters to optimize the lattice while ensuring both structural strength and minimizing weight to the greatest extent. The training objective of the intelligent optimization model is to generate a feasible structure X that meets the requirements of SLM (selective laser melting) manufacturing. opt ;

[0012] Optimize the lattice forming quality based on the SLM process parameters, and use a multi-objective optimization algorithm to globally optimize the generated intelligent lattice structure.

[0013] As a preferred solution of the lightweight method for the laser selective melting formed titanium alloy gradient lattice structure described in the present invention, among them: the generative adversarial network includes a generator G ( z; θ G) and a discriminator D ( X; θ D) , where the generator G ( z; θ G) generates a potential lattice structure X according to the input noise, that is, random data z gen , while the discriminator D ( X; θ D ) outputs a probability value according to the generated lattice structure X gen to determine whether the lattice structure is real;

[0014] By minimizing the optimization objective function L GAN to promote continuous improvement of both the generator and the discriminator. Eventually, the generator will generate a realistic lattice structure, where the optimization objective function L GAN has the following expression:

[0015]

[0016] where D ( X ) represents the output of the discriminator, and G ( z ) represents the output of the generator.

[0017] As a preferred solution of the lightweight method for the laser selective melting formed titanium alloy gradient lattice structure described in the present invention, among them: based on the lattice scheme generated by the generative adversarial network, use reinforcement learning to adjust the structural parameters to minimize the mass while ensuring the mechanical properties. Specifically:

[0018] S201: Define: the state S t = X t as the current lattice structure parameters; the state A t is the adjustment amount of the lattice structure parameters, and the reward function Rt = -λ 1 L mech (S t ) - λ 2 L mass (S t ) + λ 3 L SLM (S t );

[0019] Among them, L mech (S t ) represents the constrained mechanical properties; L mass (S t ) represents the restricted weight condition, L SLM (S t ) represents the feasibility loss of the lattice structure SLM; λ 1 , λ 2 , λ 3 respectively represent the corresponding weight coefficients;

[0020] S202: Optimize the policy π θ = (A t |S t ) to maximize the cumulative reward, and the process is expressed as:

[0021]

[0022] Among them, γ t represents the discount factor, which is used to balance short-term and long-term benefits.

[0023] As a preferred solution of the lightweight method for the laser selective melting formed titanium alloy gradient lattice structure described in the present invention, wherein: the multi-objective optimization algorithm in the step three is the NSGA-II algorithm; it includes:

[0024] S301: Use the multiple lightweight lattice structure design solutions obtained in step two as the initial solutions;

[0025] S302: Calculate the performance of each solution on all objectives;

[0026] S303: Divide the solutions into multiple levels according to the relative superiority of the objective function, and select the frontier solution ParetoFront;

[0027] S304: Calculate the crowding degree for each solution, that is, the density of the solution in the frontier solution Pareto Front, to avoid the algorithm falling into local optimum;

[0028] S305: Then generate a new generation of solutions through the mechanism of the genetic algorithm, and after multiple iterations of optimization, finally obtain a set of Pareto optimal solutions.

[0029] As a preferred solution of the lightweight method for the selective laser melting formed titanium alloy gradient lattice structure described in the present invention, wherein: the performance of each solution on the target includes:

[0030] Calculate the manufacturing mass loss f opt of the lattice structure X 1 (X); calculate the thermal stress accumulation f opt caused by the laser scanning path of the lattice structure X 2 (X); calculate the complexity f opt of the lattice structure X 3 on the laser scanning path, and the smaller the better for all of them.

[0031] As a preferred solution of the lightweight method for the selective laser melting formed titanium alloy gradient lattice structure described in the present invention, wherein: the calculation method of the crowding degree is to calculate the crowding distance of the solution, and the calculation method is:

[0032]

[0033] wherein, M represents the number of initial solutions, represents the value of the adjacent solution on the current target f j , represents the maximum and minimum values on the current target f j .

[0034] As a preferred solution of the lightweight method for the selective laser melting formed titanium alloy gradient lattice structure described in the present invention, wherein: the final optimal lattice structure is tested, and the test indexes include: dimensional accuracy test, mechanical property test, density detection and surface roughness measurement. Through the test, the reliability of the optimization model is evaluated. If a certain index does not meet the standard, it is fed back to the previous steps for adjustment.

[0035] A system applied to the above-mentioned lightweight method for the selective laser melting formed titanium alloy gradient lattice structure, the system includes:

[0036] A data collection module, which collects the parameters of different lattice topologies, mechanical properties and the influence data of various process parameters on the final forming quality, and constructs a titanium alloy gradient lattice database;

[0037] An intelligent lattice generation and optimization module, which generates an optimized gradient lattice structure through an intelligent optimization model established by the generative adversarial network + reinforcement learning;

[0038] An SLM process adaptation and optimization module, which is used to calculate the laser energy input, scanning path and scanning speed parameters during the SLM process to ensure the strong manufacturability of the generated lattice structure;

[0039] The multi-objective optimization module uses a multi-objective optimization algorithm to balance among multiple objectives and select the best lattice structure scheme.

[0040] And the intelligent verification and simulation module conducts virtual tests on the finally optimized lattice structure through multi-physics field simulation technology to ensure that it meets the design requirements.

[0041] The present invention also discloses a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned lightweight method for a laser powder bed fusion formed titanium alloy gradient lattice structure are implemented.

[0042] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned lightweight method for a laser powder bed fusion formed titanium alloy gradient lattice structure are implemented.

[0043] Advantages of the present invention:

[0044] 1. The present invention combines generative adversarial networks (GAN) and reinforcement learning (RL) to accurately simulate and optimize lattice structures under different working conditions. Through the adjustment of the unit cell size by reinforcement learning, it can ensure the maximum degree of lightweight while guaranteeing the structural strength. This optimization process takes into account both the mechanical properties and lightweight requirements of the structure in theory and practical applications, providing a brand-new design idea that the prior art cannot offer.

[0045] 2. The present invention calculates the objective function values such as the manufacturing quality loss, thermal stress, and scanning path optimization of individuals, reduces the thermal stress generated during the laser scanning process, reduces the risk of deformation and cracks caused by thermal stress, ensures the stability of the structure, and also optimizes the manufacturing quality loss and the complexity of the laser scanning path, significantly improving the manufacturing efficiency, reducing energy consumption, and enhancing the production cost-effectiveness. Description of the Drawings

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0047] Figure 1 It is a three-dimensional model construction diagram of a laser powder bed fusion formed titanium alloy gradient lattice structure proposed by the present invention;

[0048] Figure 2Schematic flow chart of a lightweight method for a laser powder bed fusion formed titanium alloy gradient lattice structure proposed by the present invention. Detailed implementation manners

[0049] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific implementation manners of the present invention will be given with reference to the accompanying drawings of the specification.

[0050] In the following description, many specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0051] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments.

[0052] Referring to Figure 1 - Figure 2 , in one embodiment of the present invention, a lightweight method for a laser powder bed fusion formed titanium alloy gradient lattice structure is provided. This method includes the following steps:

[0053] Step 1: Construct a titanium alloy gradient lattice database, which includes: parameters of different lattice topologies, mechanical properties, and the influence on the final forming quality under various process parameters;

[0054] Step 2: Based on the data obtained from the database, establish an intelligent optimization model by using the generative adversarial network + reinforcement learning method.

[0055] Among them, the generative adversarial network is responsible for simulating lightweight design solutions under various working conditions. Specifically: the generative adversarial network includes a generator G ( z; θ G) and a discriminator D ( X; θ D) , where the generator G ( z; θ G) generates a potential lattice structure X according to the input noise, that is, random data z gen , and the discriminator D ( X; θ D ) outputs a probability value based on the generated lattice structure X gen to determine whether the lattice structure is real;

[0056] By minimizing the optimization objective function L GANTo promote continuous improvement of both the generator and the discriminator, the generator will ultimately generate a realistic lattice structure, where the optimization objective function L GAN is expressed as:

[0057]

[0058] where D ( X ) represents the output of the discriminator, and G ( z ) represents the output of the generator.

[0059] Reinforcement learning is responsible for adjusting the unit cell parameters to optimize the lattice while ensuring both structural strength and minimizing weight to the greatest extent. The training objective of the intelligent optimization model is to generate a feasible structure X opt that meets the requirements of SLM (Selective Laser Melting) manufacturing; specifically: Based on the lattice scheme generated by the generative adversarial network, reinforcement learning is used to adjust the structural parameters to minimize the mass while ensuring mechanical properties, specifically:

[0060] S201: Define: State S t = X t as the current lattice structure parameters; State A t is the adjustment amount of the lattice structure parameters, and the reward function R t = -λ 1 L mech (S t ) - λ 2 L mass (S t ) + λ 3 L SLM (S t );

[0061] where L mech (S t ) represents the constrained mechanical properties (such as mechanical strength loss); L mass (S t ) represents the restricted weight condition (such as the value higher than the target weight), and L SLM (S t ) represents the feasibility loss of the lattice structure SLM (such as manufacturing error); λ 1 , λ 2 , λ 3 represent the corresponding weight coefficients respectively;

[0062] S202: Optimize the policy π θ = (A t |S t ) through the policy gradient method to maximize the cumulative reward, and the process is expressed as:

[0063]

[0064] Among them, γ t represents the discount factor, which is used to balance short-term and long-term benefits.

[0065] Step 3: Optimize the lattice forming quality based on the SLM process parameters. In this embodiment, the SLM forming gradient lattice process parameters are set as follows: laser power 210W, scanning speed 1200mm / s. In the scanning strategy, contour scanning is not performed, the spot diameter is 0.1mm, the scanning spacing is 0.12mm, the powder spreading layer thickness is 0.03mm, and the steel scraper spreads the powder unidirectionally. The forming chamber is formed in an environment with high-purity argon as the protective gas. Under these process conditions, the forming density can reach 99.96%, and the surface roughness is about 8μm. The multi-objective optimization algorithm is used to globally optimize the generated intelligent lattice structure.

[0066] Specifically, the multi-objective optimization algorithm is the NSGA-II algorithm, including:

[0067] S301: Use the multiple lightweight lattice structure design schemes obtained in Step 2 as the initial solutions.

[0068] S302: Calculate the performance of each solution on all objectives, respectively:

[0069] Calculate the manufacturing quality loss f opt of the lattice structure X 1 (X);

[0070]

[0071] Among them, N c represents the total number of lattice units; V defect,i represents the defect volume of the i-th unit cell; V total,i represents the total volume of the i-th unit cell;

[0072] Calculate the thermal stress accumulation f opt caused by the laser scanning path of the lattice structure X 2 (X);

[0073]

[0074] Among them, Ω represents the volume of the lattice structure, represents the temperature gradient;

[0075] Calculate the complexity f opt of the laser scanning path of the lattice structure X 3 (X), and all of them are better when they are smaller.

[0076]

[0077] Among them, N s represents the number of scanning segments, and d i represents the scanning length of the i-th segment, and E i represents the energy density of the i-th segment.

[0078] Suppose that step two generates 3 lightweight design schemes. At this time, the 3 design schemes correspond to 3 candidate solutions as the initial solutions.

[0079] S303: Divide the solutions into multiple levels according to the relative superiority of the objective function; taking the above table data as an example, calculate the objective function values of each solution and perform non-dominated sorting to divide the solutions into multiple Pareto levels:

[0080] Level 1: No solution can completely dominate them (the set of optimal solutions);

[0081] Level 2: Dominated by the solutions in Level 1 but superior to Level 3.

[0082] S304: Calculate the crowding degree for each solution, that is, the density of the solution in the Pareto Front of the frontier solutions, to avoid the algorithm falling into local optimality. The calculation method of the crowding degree is to calculate the crowding distance of the solution, and the calculation method is:

[0083]

[0084] Among them, M represents the number of initial solutions, represents the value of adjacent solutions for the current objective f j , represents the current objective f j and the maximum and minimum values on it.

[0085] S305: Then generate a new generation of solutions through the mechanism of the genetic algorithm. The genetic operations generally include: Selection: Select excellent solutions from the Pareto levels, and better solutions are more likely to be selected. Crossover: Randomly select two solutions and generate new solutions by combining some parameters; Mutation: Apply small random perturbations to some parameters to increase the population diversity.

[0086] After multiple iterations of optimization: Repeat non-dominated sorting → calculate the crowding degree → selection, crossover, mutation until the algorithm converges. NSGA-II will converge to a Pareto Front, that is, a set of optimal design schemes, and the user can select the most suitable scheme from them.

[0087] Test the final optimal lattice structure. The test indicators include: dimensional accuracy test, mechanical property test, density detection, and surface roughness measurement. Through the test, evaluate the reliability of the optimization model. If a certain indicator does not meet the standard, feedback to the previous steps for adjustment.

[0088] In summary, the present invention combines generative adversarial networks (GANs) and reinforcement learning (RL) to accurately simulate and optimize lattice structures under different working conditions. Through the adjustment of the unit cell size by reinforcement learning, it is possible to achieve the maximum degree of lightweighting while ensuring structural strength. This optimization process takes into account both the mechanical properties and lightweighting requirements of the structure in theory and practical applications, providing a new design concept that cannot be offered by the prior art. The present invention calculates the objective function values such as the manufacturing quality loss, thermal stress, and scanning path optimization of individuals, reduces the thermal stress generated during the laser scanning process, reduces the risk of deformation and cracks caused by thermal stress, and ensures the stability of the structure. It also optimizes the manufacturing quality loss and the complexity of the laser scanning path, significantly improving the manufacturing efficiency, reducing energy consumption, and enhancing the production cost-effectiveness.

[0089] This embodiment also provides a system applied to a lightweighting method for a selective laser melting formed titanium alloy gradient lattice structure, including:

[0090] A data collection module that collects the parameters of different lattice topologies, mechanical properties, and the data on the influence of various process parameters on the final forming quality, and constructs a titanium alloy gradient lattice database; an intelligent lattice generation and optimization module that generates an optimized gradient lattice structure through an intelligent optimization model established by the combination of generative adversarial networks + reinforcement learning; an SLM process adaptation and optimization module that calculates the laser energy input, scanning path, and scanning speed parameters during the SLM process to ensure the strong manufacturability of the generated lattice structure; a multi-objective optimization module that uses a multi-objective optimization algorithm to balance between multiple objectives and select the best lattice structure solution; and an intelligent verification and simulation module that conducts virtual tests on the finally optimized lattice structure through multi-physics field simulation technology to ensure that it meets the design requirements.

[0091] This embodiment also provides a computer device applicable to a lightweighting method for a selective laser melting formed titanium alloy gradient lattice structure, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement a lightweighting method for a selective laser melting formed titanium alloy gradient lattice structure as proposed in the above embodiment.

[0092] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0093] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the lightweight method for a selective laser melting formed titanium alloy gradient lattice structure as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0094] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A lightweight method for forming a titanium alloy gradient lattice structure by laser selective melting, characterized in that: The following steps are involved: Construct a titanium alloy gradient lattice database, which includes parameters of different lattice topological structures, mechanical properties, and the influence of various process parameters on the final forming quality; Based on the data obtained from the database, an intelligent optimization model is established using the generative adversarial network + reinforcement learning method; Among them, the generative adversarial network is responsible for simulating lightweight design solutions under various working conditions; reinforcement learning is responsible for adjusting the unit cell parameters to optimize the lattice while ensuring structural strength and minimizing weight. The training goal of the intelligent optimization model is to generate a feasible structure X that meets the SLM manufacturing requirements. opt ; The lattice forming quality is optimized based on the SLM process parameters, and the generated smart lattice structure is globally optimized using a multi-objective optimization algorithm.

2. The lightweight method for forming a titanium alloy gradient lattice structure by laser selective melting according to claim 2, characterized in that: In step 2, the generative adversarial network includes a generator G(z; θ G ) and the discriminator D(X;θ D ), where the generator G(z;θ G ) is to generate a potential lattice structure X based on the input noise, i.e. random data z gen , and the discriminator D(X;θ D ) According to the generated lattice structure X gen Output a probability value to determine whether the lattice structure is real; By minimizing the objective function L GAN To promote the continuous improvement of both the generator and the discriminator, the generator will eventually generate a realistic lattice structure, where the objective function L is optimized. GAN The expression is: Among them, D(X) represents the output of the discriminator and G(z) represents the output of the generator.

3. The lightweight method for forming a titanium alloy gradient lattice structure by laser selective melting according to claim 2, characterized in that: In the second step, based on the lattice scheme generated by the generative adversarial network, reinforcement learning is used to adjust the structural parameters to minimize the mass while ensuring the mechanical properties, specifically: S201: Definition: State S t =X t is the current lattice structure parameter; state A t is the adjustment amount of the lattice structure parameters, and the reward function R t =-λ1L mech (S t )-λ2L mass (S t )+λ3L SLM (S t ); Among them, L mech (S t ) represents the constrained mechanical properties; L mass (S t ) indicates the weight limit condition, L SLM (S t ) represents the feasibility loss of the lattice structure SLM; λ1, λ2, λ3 represent the corresponding weight coefficients respectively; S202: Optimizing strategy π through policy gradient method θ =(A t |S t ), maximize the cumulative reward, the process is expressed as: Among them, γ t Represents the discount factor, which is used to balance short-term and long-term benefits.

4. The lightweight method for forming a titanium alloy gradient lattice structure by laser selective melting according to claim 3, characterized in that: The multi-objective optimization algorithm in step 3 is the NSGA-II algorithm; including: S301: taking multiple lightweight lattice structure design solutions obtained in step 2 as initial solutions; S302: Calculate the performance of each solution on all objectives; S303: Classify the solutions into multiple levels according to the relative superiority of the objective function, and select the Pareto Front solution; S304: Calculate the congestion degree for each solution, that is, the density of the solution in the Pareto Front, to prevent the algorithm from falling into a local optimum; S305: A new generation of solutions is then generated through the mechanism of a genetic algorithm, and after multiple iterations of optimization, a set of Pareto optimal solutions is finally obtained.

5. The lightweight method for forming a titanium alloy gradient lattice structure by selective laser melting according to claim 4, characterized in that: The performance of each solution on the target includes: Calculate the lattice structure X opt Manufacturing quality loss f1(X); Calculate the lattice structure X opt Thermal stress accumulation f2(X) due to the laser scanning path; calculation of the lattice structure X opt The complexity of the laser scanning path f3(X) is as small as possible.

6. The lightweight method for forming a titanium alloy gradient lattice structure by selective laser melting according to claim 5, characterized in that: The method for calculating the congestion degree is to calculate the congestion distance of the solution, and the calculation method is: Where M represents the number of initial solutions, Indicates that at the current target f j The value of the upper adjacent solution, Indicates the current target f j The maximum and minimum values ​​on .

7. The lightweight method for forming a titanium alloy gradient lattice structure by selective laser melting according to claim 6, characterized in that: The final optimal lattice structure is tested. The test indicators include: dimensional accuracy test, mechanical property test, density detection and surface roughness measurement. The reliability of the optimization model is evaluated through testing. If an indicator does not meet the standard, it will be fed back to the previous step for adjustment.

8. The system for a lightweight method for forming a titanium alloy gradient lattice structure by selective laser melting according to claim 7, characterized in that: The system includes: The data collection module collects the parameters of different lattice topological structures, mechanical properties, and the influence of various process parameters on the final forming quality, and builds a titanium alloy gradient lattice database; Intelligent lattice generation and optimization module, which generates optimized gradient lattice structure through intelligent optimization model established by generative adversarial network + reinforcement learning; The SLM process adaptation and optimization module is used to calculate the laser energy input, scanning path, and scanning speed parameters during the SLM process to ensure that the generated lattice structure has strong manufacturability; The multi-objective optimization module uses a multi-objective optimization algorithm to balance multiple objectives and select the best lattice structure solution; As well as the intelligent verification and simulation module, it uses multi-physics field simulation technology to conduct virtual testing on the final optimized lattice structure to ensure that it meets the design requirements.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a lightweight method for forming a titanium alloy gradient lattice structure by selective laser melting are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a lightweight method for forming a titanium alloy gradient lattice structure by selective laser melting are implemented as described in any one of claims 1 to 7.

Images