Optimization design method and system, equipment and medium for laser additive manufacturing of high-temperature titanium alloy

Abstract

The application discloses a kind of high-temperature titanium alloy laser additive manufacturing optimization design method and system, equipment, medium, the method is by constructing with defect control, microstructure regulation and control and high-temperature performance guarantee as optimization target multi-objective optimization model, innovatively realizes the collaborative optimization control of defect, microstructure and high-temperature performance, breaks through the limitation of traditional single defect optimization, breaks the technical prejudice that three cannot be compatible, realizes the integrated optimization of defect reaching standard, microstructure adaptation, high-temperature performance excellent in forming stage, solves the industry pain point that defect reaches standard but high-temperature service performance is insufficient, fills the blank of high-temperature titanium alloy LPBF additive manufacturing process multidimensional optimization.

Description

Technical Field

[0001] This invention relates to the field of additive manufacturing technology for metallic materials, and in particular, to an optimized design method and system for laser additive manufacturing of high-temperature titanium alloys, electronic equipment, and computer-readable storage media. Background Technology

[0002] Compared to nickel-based superalloys, titanium-based superalloys possess outstanding advantages such as low density, high specific strength, and corrosion resistance. They are core materials for critical components used in advanced aero-engine high-pressure compressors operating in environments of 550–600°C. However, these components often have complex structures that are difficult to form using conventional casting and forging processes. Laser powder bed fusion (LPBF) additive manufacturing technology has become the preferred solution. LPBF additive manufacturing is a complex nonlinear process involving the continuous interaction of multiple process parameters, including laser power, scanning speed, scanning spacing, and powder layer thickness. Therefore, the selection of process parameters directly affects product quality. Currently, engineering still heavily relies on traditional experimental trial-and-error methods to design and optimize additive manufacturing process parameters within a relatively narrow range. However, because experimental trial-and-error methods are difficult to flexibly and efficiently explore the multi-parameter space of additive manufacturing, and the optimal process parameters vary significantly for different material systems, the optimization phase of the process parameter window consumes a great deal of time and money, hindering rapid product response and iterative upgrades. This severely restricts the progress and widespread application of LPBF additive manufacturing technology.

[0003] With the widespread application of machine learning technology, some existing studies have utilized machine learning to optimize the process parameters of additive manufacturing. However, the current research approach prioritizes ensuring defect-free forming first, then improves performance through post-processing techniques (such as hot isostatic pressing and solution treatment). For example, Chinese invention patent application CN119888361A discloses a method for optimizing and controlling processing parameters of a laser selective melting forming system based on deep learning. This method uses defect control as the sole optimization indicator, achieving optimized design of processing parameters and ensuring defect-free forming. However, for titanium-based superalloys, whose service temperature is 550℃~600℃, and 600℃ is considered the thermal barrier temperature of traditional titanium-based superalloys, above this temperature, their creep properties, microstructure stability, and surface oxidation resistance will be difficult to meet service requirements. Optimizing high-temperature performance solely through post-processing is insufficient to meet these requirements, resulting in defects meeting standards but high-temperature performance failing to meet them. This remains a long-standing pain point in the industry. Furthermore, existing technologies generally believe that there is an irreconcilable trade-off between defect control and microstructure regulation in the LPBF process. For example, in order to reduce porosity, the laser energy density needs to be increased, but excessively high energy density will lead to coarse β-phase grains in titanium-based alloys, which will worsen the high-temperature creep performance. On the other hand, in order to refine the β-phase grains, the energy density needs to be reduced, but this is prone to causing non-fusion defects. Summary of the Invention

[0004] This invention provides an optimized design method and system for laser additive manufacturing of high-temperature titanium alloys, which can achieve integrated optimization of defect compliance, microstructure adaptation, and high-temperature performance during the forming stage. It solves the industry pain point of meeting defect standards but insufficient high-temperature service performance and fills the gap in multi-dimensional optimization of high-temperature titanium alloy LPBF additive manufacturing process.

[0005] According to one aspect of the present invention, a laser additive manufacturing optimization design method for high-temperature titanium alloys is provided, comprising the following: Multi-dimensional index data of high-temperature titanium alloys manufactured by laser additive manufacturing based on different process parameters were collected; among them, the multi-dimensional indexes include basic forming quality indexes, microstructure control indexes, and high-temperature performance assurance indexes. A sample dataset is constructed based on multi-dimensional index data corresponding to different process parameters; where the input for each sample in the sample dataset is the process parameter and the output is the multi-dimensional index data. Construct a multi-dimensional indicator prediction model and train it using a sample dataset until the model converges. A multi-objective optimization model with defect control, microstructure regulation, and high-temperature performance assurance as optimization objectives was constructed and iteratively solved to obtain the optimal process parameters for high-temperature titanium alloy laser additive manufacturing.

[0006] Furthermore, the objective function of the multi-objective optimization model is: ; in, F Indicates the overall optimization objective. F 1 indicates the basic forming quality index. F 2 represents a micro-organizational regulation indicator. F 3 indicates the high-temperature performance guarantee index. , , This represents the weighting coefficient.

[0007] Furthermore, multi-dimensional indicators are calculated based on the following formula: ; ; ; in, This represents the probability of regular pore defects. This represents the probability of irregular unfusion defects. R Indicates the total porosity. D The measured value representing the average grain size of the β phase. The threshold representing the average grain size of the β phase. Indicates the grain orientation dispersion. T The measured value representing the thickness of the high-temperature oxide layer. T max The threshold value representing the thickness of the high-temperature oxide layer. The measured value representing high-temperature creep strain. This represents the threshold for high-temperature creep strain.

[0008] Furthermore, when collecting basic forming quality index data, defects with an aspect ratio greater than or equal to a preset threshold are classified as regular pores, and defects with an aspect ratio less than the preset threshold are classified as irregular unfused defects. The probability of regular pore defects, the probability of irregular unfused defects, and the overall porosity are calculated based on the following formulas: , , .

[0009] Furthermore, when collecting data on microstructure control indicators, a metallographic microscope was used to collect the β-phase grain size. Under a preset magnification, n random line segments were drawn, and the intersections of these segments with grain boundaries were extracted. The average grain size of the β-phase was then calculated based on the following formula: n represents the number of line segments, N represents the number of intersections between the line segments and the β-phase grain boundaries, and L i This represents the length of the i-th line segment.

[0010] Furthermore, the process of collecting high-temperature performance assurance indicators is as follows: The sample was placed in a box-type resistance furnace and oxidized in air at 600℃. Metallographic samples were prepared along the cross-section. The cross-section of the oxide layer was observed using a scanning electron microscope. The composition of the oxide layer was confirmed to meet the requirements by energy dispersive spectroscopy analysis. The thickness of multiple sites was measured and the average value was taken as the thickness of the high-temperature oxide layer. Creep samples were prepared. The temperature was set at 600℃ and the stress at 150MPa. The high-temperature creep testing machine was used to continuously test for a preset time and the creep strain curve was recorded. The endpoint strain value was taken as the high-temperature creep strain.

[0011] Furthermore, an interleaved scanning strategy is adopted in the laser additive manufacturing process for forming. During iterative solving, the scanning layer thickness is fixed at 0.03 mm, the laser scanning spacing is fixed at 0.09 mm, and the laser energy density is constrained to [40 J / mm²]. 3 55J / mm 3 Within the specified range, laser input power and laser scanning speed are used as decision variables.

[0012] In addition, the present invention also provides an optimized design system for laser additive manufacturing of high-temperature titanium alloys, comprising: The data acquisition module is used to collect multi-dimensional index data of high-temperature titanium alloys manufactured by laser additive manufacturing based on different process parameters. Among them, the multi-dimensional indexes include basic forming quality indexes, microstructure control indexes, and high-temperature performance assurance indexes. The sample dataset construction module is used to construct sample datasets based on multi-dimensional index data corresponding to different process parameters. In the sample dataset, the input for each sample is the process parameter and the output is the multi-dimensional index data. The model building and training module is used to build a multi-dimensional indicator prediction model and train the multi-dimensional indicator prediction model using a sample dataset until the model converges. The multi-objective optimization solution module is used to construct a multi-objective optimization model with defect control, microstructure regulation and high-temperature performance assurance as optimization objectives, and perform iterative solution to obtain the optimal process parameters for high-temperature titanium alloy laser additive manufacturing.

[0013] In addition, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method described above by calling the computer program stored in the memory.

[0014] In addition, the present invention provides a computer-readable storage medium for storing a computer program for optimizing the laser additive manufacturing of high-temperature titanium alloys, wherein the computer program executes the steps of the method described above when running on a computer.

[0015] The present invention has the following beneficial effects: The laser additive manufacturing optimization design method for high-temperature titanium alloys of this invention innovatively achieves synergistic optimization and control of defects, microstructure, and high-temperature performance by constructing a multi-objective optimization model with defect control, microstructure regulation, and high-temperature performance assurance as optimization objectives. This method breaks through the limitations of traditional single defect optimization and overcomes the technical bias that these three aspects cannot be simultaneously achieved. It realizes integrated optimization of defect compliance, microstructure adaptation, and excellent high-temperature performance in the forming stage, solving the industry pain point of defect compliance but insufficient high-temperature service performance, and filling the gap in multi-dimensional optimization of high-temperature titanium alloy LPBF additive manufacturing process.

[0016] In addition, the laser additive manufacturing optimization design system for high-temperature titanium alloys of the present invention also has the above-mentioned advantages.

[0017] In addition to the objectives, features, and advantages described above, the present invention has other objectives, features, and advantages. The invention will now be described in further detail with reference to the figures. Attached Figure Description

[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart illustrating the laser additive manufacturing optimization design method for high-temperature titanium alloys according to a preferred embodiment of this application. Figure 2 This is a schematic diagram of regular pore defects in the microstructure of laser powder bed melting Ti150 high-temperature titanium alloy formed in the embodiments of this application; Figure 3 This is a schematic diagram of irregular unfused defects in the microstructure of laser powder bed melting Ti150 high-temperature titanium alloy in the embodiments of this application; Figure 4 This is a schematic diagram showing the variation of the average grain size of the β phase in the laser powder bed melting of Ti150 high-temperature titanium alloy under different process parameters in the embodiments of this application; Figure 5 This is a schematic diagram of the optimized laser powder bed melting Ti150 high-temperature titanium alloy forming structure in the embodiments of this application; Figure 6 This is a schematic diagram of the module structure of a laser additive manufacturing optimization design system for high-temperature titanium alloys according to another embodiment of this application. Detailed Implementation

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Reference Figure 1 A preferred embodiment of this application provides an optimized design method for laser additive manufacturing of high-temperature titanium alloys, including the following: Step S1: Collect multi-dimensional index data of high-temperature titanium alloys manufactured by laser additive manufacturing based on different process parameters; among which, the multi-dimensional indexes include basic forming quality indexes, microstructure control indexes, and high-temperature performance assurance indexes. Step S2: Construct a sample dataset based on multi-dimensional index data corresponding to different process parameters; wherein, the input of each sample in the sample dataset is the process parameter and the output is the multi-dimensional index data. Step S3: Construct a multi-dimensional indicator prediction model and train the model using the sample dataset until the model converges. Step S4: Construct a multi-objective optimization model with defect control, microstructure regulation and high-temperature performance assurance as optimization objectives, and perform iterative solution to obtain the optimal process parameters for high-temperature titanium alloy laser additive manufacturing.

[0021] It is understood that the laser additive manufacturing optimization design method for high-temperature titanium alloys in this embodiment innovatively achieves synergistic optimization and control of defects, microstructure, and high-temperature performance by constructing a multi-objective optimization model with defect control, microstructure regulation, and high-temperature performance assurance as optimization objectives. This breaks through the limitations of traditional single defect optimization and overcomes the technical bias that these three aspects cannot be simultaneously achieved. It realizes integrated optimization of defect compliance, microstructure adaptation, and excellent high-temperature performance in the forming stage, solving the industry pain point of defect compliance but insufficient high-temperature service performance, and filling the gap in multi-dimensional optimization of high-temperature titanium alloy LPBF additive manufacturing process.

[0022] In step S1, a high-temperature titanium alloy is manufactured using the LPBF forming method, based on the laser energy density formula. The design process parameter combination, among which... E Indicates laser energy density, P Indicates the laser input power. v Indicates the laser scanning speed. h Indicates the thickness of the scanned layer. dThe laser scanning distance ranges from 90 to 350 W, the laser input power ranges from 500 to 2000 mm / s, the scanning layer thickness ranges from 0.03 to 0.06 mm, and the laser scanning distance ranges from 0.05 to 0.1 mm. Samples were formed based on different combinations of process parameters, with sample sizes of 10 mm × 10 mm × 10 mm. A total of 50 samples corresponding to different combinations of process parameters were prepared for subsequent multi-dimensional index data acquisition and model training. These multi-dimensional indicators include basic forming quality indicators, microstructure control indicators, and high-temperature performance assurance indicators. The basic forming quality indicators include the probability of regular pore defects, the probability of irregular unfused defects, and the overall porosity. The microstructure control indicators include the average grain size of the β phase and the grain orientation dispersion. The high-temperature performance assurance indicators include the high-temperature oxide layer thickness and the high-temperature creep strain.

[0023] For the basic forming quality index data, a metallographic microscope was used to observe the cross-section of the sample. Three non-overlapping statistical fields of view were selected at a magnification of 100x. Defects with an aspect ratio greater than or equal to a preset threshold (e.g., 0.8) were classified as regular pores. Specifically, as follows... Figure 2 As shown, defects with an aspect ratio less than a preset threshold are classified as irregular unfused defects, specifically as follows: Figure 3 As shown, the average values ​​of three fields of view are taken as the final data, and the probability of regular pore defects, the probability of irregular unfused defects, and the overall porosity are calculated based on the following formulas: , , .

[0024] In addition, for the microstructure control index, the average grain size of the β phase was collected using a metallographic microscope. Specifically, n random line segments were drawn under a preset magnification (e.g., 100x), the intersection points of the line segments and grain boundaries were extracted, and the average grain size of the β phase was calculated based on the following formula: n represents the number of line segments, N represents the number of intersections between the line segments and the β-phase grain boundaries, and L i This represents the length of the i-th line segment, where the variation of the average grain size of the β-phase formed under different process parameters is as follows: Figure 4 As shown in the figure. The grain orientation dispersion is obtained by collecting data through EBSD and calculating the average deviation angle of the grain orientation relative to the main axis of the texture using TSL OIM Analysis software.

[0025] In addition, for the high-temperature performance assurance index, the sample was placed in a box-type resistance furnace and oxidized in air at 600℃ for 100h. Metallographic samples were prepared along the cross-section, and the oxide layer cross-section was observed by scanning electron microscopy. Energy dispersive spectroscopy analysis confirmed that the oxide layer composition met the requirements, that is, the oxide layer composition was mainly TiO2. The thickness of multiple sites (e.g., 3 sites) was measured and the average value was taken as the high-temperature oxide layer thickness. Creep samples were prepared with a size of Φ5mm×66mm. The temperature was set at 600℃ and the stress at 150MPa. The high-temperature creep testing machine was used to continuously test for a preset time (e.g., 100h), and the creep strain curve was recorded. The endpoint strain value was taken as the high-temperature creep strain.

[0026] Furthermore, in step S2, a structured sample dataset of process parameters and multi-dimensional indicators can be constructed based on the multi-dimensional indicator data corresponding to different process parameters. The input for each sample is the process parameter, and the output is the multi-dimensional indicator data. The sample dataset is divided into a training set and a validation set in a 7:3 ratio to facilitate model training. Additionally, the data in the sample dataset can be normalized. Specific normalization methods can include max-min normalization, Z-score normalization, etc. This invention uses Z-score normalization, which can be expressed as: ,in, This represents the data after normalization. This represents the data before normalization. Indicates standard deviation, The mean is represented. For example, this invention uses the process parameters (laser energy density, laser input power, laser scanning speed, scanning layer thickness, and laser scanning spacing) of 50 sets of samples as input, and the multi-dimensional index data (probability of regular pore defects, probability of irregular non-fusion defects, overall porosity, average grain size of β phase, grain orientation dispersion, high-temperature oxide layer thickness, and high-temperature creep strain) corresponding to each sample as output data, forming a structured sample dataset with 5-dimensional input and 7-dimensional output. Some data are shown in Table 1 below. Then, the sample dataset is normalized using Z-score, and outlier data under the 3σ criterion is removed (a total of 2 sets are removed). The remaining 48 sets of data are divided into a training set (34 sets) and a validation set (14 sets) in a 7:3 ratio.

[0027] Table 1. Partial sample data from the sample dataset .

[0028] In addition, in step S3, a multi-dimensional indicator prediction model is constructed based on the Python platform. For example, an SVM model or an LSTM model can be used. Bayesian optimization methods are employed to adaptively optimize the model hyperparameters (such as the penalty factor C, kernel function coefficient γ, loss function tolerance ε, etc.). The prediction model is trained using a training set, enabling it to learn the mapping relationship between process parameters and multi-dimensional indicators. During model training, mean squared error (MSE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R²) are used. 2 The performance of the prediction model is evaluated using the training set and the validation set until the model converges. The performance of the prediction model on the training set and the validation set is then verified. The evaluation performance of the prediction model on the training set and the validation set is shown in Tables 2 and 3.

[0029] Table 2. Evaluation performance of the prediction model on the training set ; Table 3. Evaluation performance of the prediction model on the validation set .

[0030] It can be seen that the training set R 2 =0.986, MSE=0.00015, validation set R 2 =0.958, MSE=0.00082, satisfying "training set R 2 ≥0.98, MSE≤0.0002; Validation set R 2 The judgment criteria of "≥0.95, MSE≤0.001" indicate that the accuracy of the prediction model meets the requirements, and it can achieve high-precision prediction of multi-dimensional index data of high-temperature titanium alloys formed with different process parameters.

[0031] Furthermore, in step S4, a multi-objective optimization model is constructed with defect control, microstructure regulation, and high-temperature performance assurance as optimization objectives. The objective function of the multi-objective optimization model is: ; in, F Indicates the overall optimization objective. F 1 indicates the basic forming quality index. F 2 represents a micro-organizational regulation indicator. F 3 indicates the high-temperature performance guarantee index. , , This represents the weighting coefficient. The multi-dimensional index is calculated based on the following formula: ; ; ; in, This represents the probability of regular pore defects. This represents the probability of irregular unfusion defects. R Indicates the total porosity. D The measured value representing the average grain size of the β phase. The threshold representing the average grain size of the β phase is typically set to 50 μm. Indicates the grain orientation dispersion. T The measured value representing the thickness of the high-temperature oxide layer. T max The threshold value representing the thickness of the high-temperature oxide layer is typically set to 5 μm. The measured value representing high-temperature creep strain. The threshold for high-temperature creep strain is typically set to 0.16%.

[0032] Then, multi-objective optimization is implemented using the TPOP library in Python, with the optimization objective being the objective function. F Minimize, the specific steps are as follows: Initialization: Randomly generate several sets (e.g., 50 sets) of candidate process parameters as the initial population; Evaluation: Substitute the candidate process parameters into the model to predict the corresponding F1, F2, F3 and F values; Selection, crossover, and mutation: Based on non-dominated sorting and crowding calculation, excellent individuals are selected, and a new generation of population is generated through genetic operators; Iteration: Repeat the above steps until convergence (set the number of iterations to 100 generations), output the Pareto optimal solution set, and thus obtain the optimal combination of process parameters.

[0033] Optionally, an interleaved scanning strategy is adopted in the laser additive manufacturing process for forming. During iterative solving, the scanning layer thickness is fixed at 0.03 mm, the laser scanning spacing is fixed at 0.09 mm, and the laser energy density is constrained to [40 J / mm²]. 3 55J / mm 3 Within the specified range, laser input power and laser scanning speed are used as decision variables.

[0034] It is understood that this invention constrains the laser energy density to [40 J / mm²]. 3 55J / mm 3 Within this metastable range, and through an interleaved scanning strategy matched with a fixed layer thickness of 0.03 mm, bidirectional control of the molten pool behavior can be achieved, ensuring a molten pool depth ≥ 0.04 mm, covering the layer thickness, guaranteeing full powder fusion, avoiding incomplete fusion defects, and maintaining a molten pool cooling rate within [5 × 10⁻⁶]. 4 K / s, 8×10 4Within the range of K / s, it is in the critical range for β-phase grain refinement, which avoids grain coarsening under high energy density and prevents amorphous phase precipitation due to excessively rapid cooling. Existing technologies usually only focus on the extreme ranges of high / low energy density and cannot achieve bidirectional control of molten pool behavior.

[0035] Furthermore, based on the aforementioned multi-objective optimization model, this invention can also find a stable LPBF additive manufacturing process window for high-temperature titanium alloys with continuous laser power (150-180W) and scanning speed (800-1100mm / s) under the constraints of regular pore defect probability <5%, irregular unfused defect probability <3%, and porosity <2%. Under the optimized forming parameters, the alloy microstructure shows no obvious defects, specifically as follows... Figure 5 As shown. Furthermore, to verify the effectiveness of the optimized process parameters, this invention also selected the optimal process parameters from the Pareto optimal solution set: laser power P = 160~180W, scanning speed v = 850~1050mm / s, corresponding to energy density E = 43.2~51.3J / mm². 3 The sample was formed according to the process parameters, and the index was compared with the sample before optimization. The comparison results are shown in Table 4.

[0036] Table 4. Comparison of indicators before and after optimization ; It can be seen that all indicators after optimization meet the constraints, and the micro-organization indicators are significantly improved compared with those before optimization.

[0037] In addition, the present invention also conducted high-temperature service performance verification. The optimized sample was tested according to the standard for high-temperature components of aero-engines. The high-temperature oxidation resistance was verified; after oxidation at 600℃ for 100h, the oxide layer thickness T=2.8μm and the oxidation weight gain was 0.32mg / cm³. 2 The performance meets the standard requirements; the high-temperature creep performance, with a creep strain ε=0.09% at 600℃ / 150MPa / 100h, meets the standard requirements; the mechanical properties, with a room temperature tensile strength of 1150MPa, a tensile strength of 680MPa at 600℃, and an elongation of 14.2%, all meet the service requirements of high-pressure compressor components for aero-engines, and the performance is improved by about 18.3% compared with the original.

[0038] Therefore, through multi-objective optimization, this invention achieves coordinated control of "defects-microstructure-high temperature performance" in the high-temperature titanium alloy LPBF process. The optimized process window is stable and reliable, and the high-temperature service performance of the formed samples meets the requirements of key components of aero-engines, fully demonstrating the effectiveness and engineering applicability of the method of this invention.

[0039] In addition, such as Figure 6As shown, another embodiment of the present invention also provides a laser additive manufacturing optimization design system for high-temperature titanium alloys, preferably employing the laser additive manufacturing optimization design method for high-temperature titanium alloys as described above, comprising: The data acquisition module is used to collect multi-dimensional index data of high-temperature titanium alloys manufactured by laser additive manufacturing based on different process parameters. Among them, the multi-dimensional indexes include basic forming quality indexes, microstructure control indexes, and high-temperature performance assurance indexes. The sample dataset construction module is used to construct sample datasets based on multi-dimensional index data corresponding to different process parameters. In the sample dataset, the input for each sample is the process parameter and the output is the multi-dimensional index data. The model building and training module is used to build a multi-dimensional indicator prediction model and train the multi-dimensional indicator prediction model using a sample dataset until the model converges. The multi-objective optimization solution module is used to construct a multi-objective optimization model with defect control, microstructure regulation and high-temperature performance assurance as optimization objectives, and perform iterative solution to obtain the optimal process parameters for high-temperature titanium alloy laser additive manufacturing.

[0040] It is understood that the laser additive manufacturing optimization design system for high-temperature titanium alloys in this embodiment innovatively achieves synergistic optimization and control of defects, microstructure, and high-temperature performance by constructing a multi-objective optimization model with defect control, microstructure regulation, and high-temperature performance assurance as optimization goals. This breaks through the limitations of traditional single defect optimization and overcomes the technical bias that these three aspects cannot be achieved simultaneously. It realizes integrated optimization of defect compliance, microstructure adaptation, and excellent high-temperature performance in the forming stage, solving the industry pain point of defect compliance but insufficient high-temperature service performance, and filling the gap in multi-dimensional optimization of high-temperature titanium alloy LPBF additive manufacturing process.

[0041] In addition, another embodiment of the present invention provides an electronic device including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method described above by calling the computer program stored in the memory.

[0042] In addition, another embodiment of the present invention provides a computer-readable storage medium for storing a computer program for laser additive manufacturing optimization design of high-temperature titanium alloys, wherein the computer program executes the steps of the method described above when running on a computer.

[0043] Common computer-readable storage media include: floppy disks, flexible disks, hard disks, magnetic tapes, any other magnetic media, CD-ROMs, any other optical media, punch cards, paper tape, any other physical media with perforated patterns, random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), flash erasable programmable read-only memory (FLASH-EPROM), any other memory chips or cartridges, or any other media readable by a computer. Instructions may further be transmitted or received by a transmission medium. The term transmission medium can include any tangible or intangible medium used to store, encode, or carry instructions for execution by a machine, and includes digital or analog carrier communication signals or intangible media that facilitate communication of such instructions. Transmission media include coaxial cables, copper wires, and optical fibers, which contain conductors for transmitting a bus of computer data signals.

[0044] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0045] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0046] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0047] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0048] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0049] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0050] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A laser additive manufacturing optimization design method for high-temperature titanium alloys, characterized in that, Includes the following: Multi-dimensional index data of high-temperature titanium alloys manufactured by laser additive manufacturing based on different process parameters were collected; among them, the multi-dimensional indexes include basic forming quality indexes, microstructure control indexes, and high-temperature performance assurance indexes. A sample dataset is constructed based on multi-dimensional index data corresponding to different process parameters; where the input for each sample in the sample dataset is the process parameter and the output is the multi-dimensional index data. Construct a multi-dimensional indicator prediction model and train it using a sample dataset until the model converges. A multi-objective optimization model with defect control, microstructure regulation, and high-temperature performance assurance as optimization objectives was constructed and iteratively solved to obtain the optimal process parameters for high-temperature titanium alloy laser additive manufacturing.

2. The laser additive manufacturing optimization design method for high-temperature titanium alloys as described in claim 1, characterized in that, The objective function of the multi-objective optimization model is: ； in, F Indicates the overall optimization objective. F 1 indicates the basic forming quality index. F 2 represents a micro-organizational regulation indicator. F 3 indicates the high-temperature performance guarantee index. , , This represents the weighting coefficient.

3. The laser additive manufacturing optimization design method for high-temperature titanium alloys as described in claim 2, characterized in that, Multidimensional indicators are calculated based on the following formula: ； ； ； in, This represents the probability of regular pore defects. This represents the probability of irregular unfusion defects. R Indicates the total porosity. D The measured value representing the average grain size of the β phase. The threshold representing the average grain size of the β phase. Indicates the grain orientation dispersion. T The measured value representing the thickness of the high-temperature oxide layer. T max The threshold value representing the thickness of the high-temperature oxide layer. The measured value representing high-temperature creep strain. This represents the threshold for high-temperature creep strain.

4. The laser additive manufacturing optimization design method for high-temperature titanium alloys as described in claim 3, characterized in that, When collecting basic forming quality index data, defects with an aspect ratio greater than or equal to a preset threshold are classified as regular pores, and defects with an aspect ratio less than the preset threshold are classified as irregular unfused defects. The probability of regular pore defects, the probability of irregular unfused defects, and the overall porosity are calculated based on the following formulas: , , .

5. The laser additive manufacturing optimization design method for high-temperature titanium alloys as described in claim 3, characterized in that, When collecting data on microstructure control indicators, a metallographic microscope was used to collect the β-phase grain size. Under a preset magnification, n random line segments were drawn, and the intersections of these segments with grain boundaries were extracted. The average grain size of the β-phase was then calculated based on the following formula: n represents the number of line segments, N represents the number of intersections between the line segments and the β-phase grain boundaries, and L i This represents the length of the i-th line segment.

6. The laser additive manufacturing optimization design method for high-temperature titanium alloys as described in claim 3, characterized in that, The process of collecting high-temperature performance assurance indicators is as follows: The sample was placed in a box-type resistance furnace and oxidized in air at 600℃. Metallographic samples were prepared along the cross-section. The cross-section of the oxide layer was observed using a scanning electron microscope. The composition of the oxide layer was confirmed to meet the requirements by energy dispersive spectroscopy analysis. The thickness of multiple sites was measured and the average value was taken as the thickness of the high-temperature oxide layer. Creep samples were prepared. The temperature was set at 600℃ and the stress at 150MPa. The high-temperature creep testing machine was used to continuously test for a preset time and the creep strain curve was recorded. The endpoint strain value was taken as the high-temperature creep strain.

7. The laser additive manufacturing optimization design method for high-temperature titanium alloys as described in claim 1, characterized in that, In the laser additive manufacturing process, an interlaced scanning strategy is adopted for forming. During iterative solution, the scanning layer thickness is fixed at 0.03 mm, the laser scanning spacing is fixed at 0.09 mm, and the laser energy density is constrained to [40 J / mm²]. 3 55J / mm 3 Within the specified range, laser input power and laser scanning speed are used as decision variables.

8. A laser additive manufacturing optimization design system for high-temperature titanium alloys, characterized in that, include: The data acquisition module is used to collect multi-dimensional index data of high-temperature titanium alloys manufactured by laser additive manufacturing based on different process parameters. Among them, the multi-dimensional indexes include basic forming quality indexes, microstructure control indexes, and high-temperature performance assurance indexes. The sample dataset construction module is used to construct sample datasets based on multi-dimensional index data corresponding to different process parameters. In the sample dataset, the input for each sample is the process parameter and the output is the multi-dimensional index data. The model building and training module is used to build a multi-dimensional indicator prediction model and train the multi-dimensional indicator prediction model using a sample dataset until the model converges. The multi-objective optimization solution module is used to construct a multi-objective optimization model with defect control, microstructure regulation and high-temperature performance assurance as optimization objectives, and perform iterative solution to obtain the optimal process parameters for high-temperature titanium alloy laser additive manufacturing.

9. An electronic device, characterized in that, The method includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium for storing a computer program for optimizing the laser additive manufacturing of high-temperature titanium alloys, characterized in that, The computer program, when run on a computer, performs the steps of the method as described in any one of claims 1 to 7.

Images