Component laser additive manufacturing method and device based on heterogeneous material evolution analysis

Abstract

The invention discloses a part laser additive manufacturing method and device based on heterogeneous material evolution analysis, and relates to the technical field of additive manufacturing, and the method comprises the following steps: analyzing target microscopic size data of a heterogeneous material required by a target part; performing geometric shape analysis on the heterogeneous material based on pixel error probability compensation; carrying out spatial distribution analysis on the heterogeneous material; initial process parameter analysis of laser additive manufacturing is conducted on the basis of the target microscopic size data, the geometrical shape data and the spatial distribution data in combination with heterogeneous material structure evolution influence analysis; component material performance analysis is carried out based on a laser additive manufacturing simulation result; adjusting the initial process parameters based on component material performance analysis data in combination with energy consumption analysis to obtain target process parameters; and performing laser additive manufacturing treatment on the target part based on the target process parameters. According to the method, the performance and the morphological structure of the manufactured part can achieve more ideal effects by accurately regulating and controlling the technological parameters.

Description

Technical Field

[0001] The present invention relates to the field of additive manufacturing technology, and in particular to a component laser additive manufacturing method and device based on heterogeneous material evolution analysis. Background Art

[0002] Laser additive manufacturing is a component manufacturing method that uses a high-energy laser beam as an energy source to stack materials layer by layer. Since laser additive manufacturing has greater advantages in manufacturing complex components than traditional material forming manufacturing methods, it is increasingly used in the field of industrial manufacturing. Heterogeneous materials are structures composed of materials with different physical and chemical properties. Due to their more diverse physical and chemical properties, they have gradually been used in additive manufacturing. In the current methods of laser additive manufacturing using heterogeneous materials, the process parameters of laser additive manufacturing are usually determined only by analyzing the geometric morphology of the heterogeneous materials. The influence of the microscopic size and spatial distribution of the components of the heterogeneous materials is not taken into account. At the same time, the influence of the structural evolution of the heterogeneous materials is also not taken into account. As a result, the analyzed process parameters are not reliable enough, and the performance and morphological structure of the manufactured components deviate greatly from the expected effects. Usually, after analyzing the process parameters, further adjustments and optimizations are required to ensure the reliability of laser additive manufacturing. Currently, the adjustment of process parameters is mainly determined by data statistics conducted by relevant personnel. However, this method is too dependent on the professional qualities of the relevant personnel, making it difficult to guarantee the accuracy of process parameter adjustments. In addition, its processing efficiency is also low, affecting the efficiency and precision of laser additive manufacturing of components. Summary of the Invention

[0003] The purpose of the present invention is to overcome the shortcomings of the existing technology. The present invention provides a component laser additive manufacturing method and device based on the evolution analysis of heterogeneous materials. Through precise control of parameters, the performance and morphological structure of the manufactured components can achieve more ideal effects.

[0004] In order to solve the above technical problems, the present invention provides a component laser additive manufacturing method based on heterogeneous material evolution analysis, the method comprising:

[0005] Analyze the target micro-dimensional data of heterogeneous materials required for target components;

[0006] Performing geometric shape analysis on heterogeneous materials based on pixel error probability compensation to obtain geometric shape data;

[0007] Perform spatial distribution analysis on heterogeneous materials to obtain spatial distribution data;

[0008] Based on the target micro-size data, geometric shape data and spatial distribution data combined with the analysis of the influence of heterogeneous material structure evolution, the initial process parameters of laser additive manufacturing of the target component are analyzed to obtain the initial process parameters;

[0009] Performing laser additive manufacturing simulation based on initial process parameters to obtain laser additive manufacturing simulation results, and performing component material performance analysis based on the laser additive manufacturing simulation results to obtain component material performance analysis data;

[0010] Adjust the initial process parameters based on component material performance analysis data combined with energy consumption analysis to obtain target process parameters;

[0011] The target component is laser-added for manufacturing based on the target process parameters.

[0012] Optionally, the target microscopic size data of the heterogeneous material required for analyzing the target component includes:

[0013] Using white light interferometry technology based on an optical 3D surface profiler to measure the microscopic dimensions of heterogeneous materials, the first microscopic dimension data is obtained;

[0014] The microscopic size of the heterogeneous material is measured by using a confocal technique based on a confocal microscope to obtain second microscopic size data, and target microscopic size data is generated based on the first microscopic size data and the second microscopic size data.

[0015] Optionally, performing geometric shape analysis on the heterogeneous material based on pixel error probability compensation to obtain geometric shape data includes:

[0016] Perform saliency processing and binarization on the target image of the heterogeneous material to obtain a binary target saliency map;

[0017] Determining the foreground pixel probability and the background pixel probability of the binary target saliency map based on the pixel probability model, and performing error probability compensation on the foreground pixel probability and the background pixel probability to obtain the target foreground pixel probability and the target background pixel probability;

[0018] Determine the region outline of the heterogeneous material in the target image based on the target foreground pixel probability and the target background pixel probability;

[0019] A geometric shape analysis is performed based on the regional contour of the heterogeneous material to obtain geometric shape data.

[0020] Optionally, performing error probability compensation on the foreground pixel probability and the background pixel probability to obtain the target foreground pixel probability and the target background pixel probability includes:

[0021] Perform classification error analysis on the pixel probability model to obtain classification error data;

[0022] Compensation values ​​of foreground pixel probabilities and background pixel probabilities are determined based on the classification error data, and error probability compensation is performed on the foreground pixel probabilities and background pixel probabilities based on the compensation values ​​to obtain target foreground pixel probabilities and target background pixel probabilities.

[0023] Optionally, performing spatial distribution analysis on the heterogeneous material to obtain spatial distribution data includes:

[0024] Constructing a representative volume unit of the heterogeneous material and performing mesh division on the representative volume unit to obtain a plurality of meshes corresponding to the representative volume unit;

[0025] Construct a structural simulation model of heterogeneous materials, and perform component position coordinate analysis and material property analysis on each grid based on the structural simulation model to obtain component position coordinates and material properties;

[0026] The spatial distribution data is determined based on the component position coordinates and material properties of each grid.

[0027] Optionally, the initial process parameter analysis for laser additive manufacturing of the target component based on the target micro-size data, geometric shape data, and spatial distribution data combined with the analysis of the influence of the heterogeneous material structure evolution is performed to obtain the initial process parameters, including:

[0028] Based on the different process parameters of laser additive manufacturing and combined with the target micro-size data, geometric shape data and spatial distribution data, a physical field coupling model is constructed using finite element simulation technology;

[0029] Constructing a microstructure evolution model based on the physical field coupling model, and performing heterogeneous material structure evolution impact analysis based on the microstructure evolution model to obtain heterogeneous material structure evolution impact data;

[0030] Based on the heterogeneous material structure evolution influence data, target micro-size data, geometric shape data and spatial distribution data combined with the process correlation model, the initial process parameters are analyzed to obtain the initial process parameters.

[0031] Optionally, performing laser additive manufacturing simulation based on the initial process parameters to obtain laser additive manufacturing simulation results, and performing component material performance analysis based on the laser additive manufacturing simulation results to obtain component material performance analysis data, includes:

[0032] Perform laser additive manufacturing simulation based on initial process parameters, target micro-size data, geometric shape data, and spatial distribution data to obtain laser additive manufacturing simulation results;

[0033] Based on the laser additive manufacturing simulation results, the impact resistance, wear resistance and corrosion resistance are analyzed using a simulation control model to obtain component material performance analysis data.

[0034] Optionally, adjusting the initial process parameters based on the component material performance analysis data combined with the energy consumption analysis to obtain target process parameters includes:

[0035] Determine the adjustment range of initial process parameters based on component material performance analysis data;

[0036] Set up the time model and energy consumption model of the laser additive manufacturing process, and build a target optimization model based on the time model and energy consumption model;

[0037] Based on the adjustment range of the initial process parameters, the energy consumption analysis of the laser additive manufacturing process is carried out using the time model and energy consumption model combined with orthogonal experiments to obtain energy consumption analysis data;

[0038] Adjustment parameters are determined based on energy consumption analysis data and the target optimization model, and the initial process parameters are adjusted based on the adjustment parameters to obtain target process parameters.

[0039] Optionally, performing laser additive manufacturing of a target component based on target process parameters includes:

[0040] Based on the geometric shape data and spatial distribution data combined with the component forming requirements, the path planning of the laser additive manufacturing process is carried out to obtain the path data;

[0041] A processing instruction is generated based on the path data and the target process parameters, and the laser additive manufacturing equipment performs laser additive manufacturing processing on the target component based on the processing instruction.

[0042] In addition, the present invention also provides a component laser additive manufacturing device based on heterogeneous material evolution analysis, the device comprising:

[0043] Micro-size analysis module: used to analyze the target micro-size data of heterogeneous materials required for target components;

[0044] Geometric shape analysis module: used to perform geometric shape analysis on heterogeneous materials based on pixel error probability compensation to obtain geometric shape data;

[0045] Spatial distribution analysis module: used to perform spatial distribution analysis on heterogeneous materials and obtain spatial distribution data;

[0046] Parameter analysis module: used to analyze the initial process parameters of laser additive manufacturing of target components based on target micro-size data, geometric shape data, and spatial distribution data combined with the analysis of the influence of heterogeneous material structure evolution to obtain the initial process parameters;

[0047] Material performance analysis module: used to perform laser additive manufacturing simulation based on initial process parameters to obtain laser additive manufacturing simulation results, and to perform component material performance analysis based on the laser additive manufacturing simulation results to obtain component material performance analysis data;

[0048] Parameter adjustment module: used to adjust the initial process parameters based on component material performance analysis data combined with energy consumption analysis to obtain target process parameters;

[0049] Laser Additive Manufacturing Module: Used to perform laser additive manufacturing processing of target parts based on target process parameters.

[0050] In an embodiment of the present invention, geometric shape analysis of heterogeneous materials is performed based on pixel error probability compensation, which can improve the accuracy of geometric shape analysis of heterogeneous materials. Initial process parameter analysis of target component laser additive manufacturing is performed based on target microscopic size data, geometric shape data and spatial distribution data combined with heterogeneous material structural evolution influence analysis, and the influence data of heterogeneous material structural evolution is clarified to provide more comprehensive and accurate data support for initial process parameter analysis, making the obtained initial process parameters more reliable. Laser additive manufacturing simulation is performed based on the initial process parameters to obtain laser additive manufacturing simulation results, and component material performance analysis is performed based on the laser additive manufacturing simulation results. The initial process parameters are adjusted based on the component material performance analysis data combined with energy consumption analysis, which can ensure the accuracy of the initial process parameter adjustment and improve the efficiency of parameter adjustment analysis. Laser additive manufacturing processing of target components is performed based on the target process parameters. Through precise control of the parameters, the performance and morphological structure of the manufactured components can achieve more ideal results. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 1 is a schematic flow chart of a component laser additive manufacturing method based on heterogeneous material evolution analysis in an embodiment of the present invention;

[0053] Figure 2 is a schematic flow chart of a component laser additive manufacturing method based on heterogeneous material evolution analysis in another embodiment of the present invention;

[0054] Figure 3 Schematic diagram of the structural composition of a component laser additive manufacturing device based on heterogeneous material evolution analysis in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0056] Example 1

[0057] See also Figure 1 , Figure 1 : is a schematic flow chart of a component laser additive manufacturing method based on heterogeneous material evolution analysis in an embodiment of the present invention, the method comprising:

[0058] S11: Analyze the target micro-dimensional data of the heterogeneous materials required for the target component;

[0059] In the specific implementation process of the present invention, the target micro-size data of the heterogeneous material required for the analysis of the target component includes: performing micro-size measurement of the heterogeneous material using white light interferometry technology based on an optical 3D surface profiler to obtain first micro-size data; performing micro-size measurement of the heterogeneous material using confocal technology based on a confocal microscope to obtain second micro-size data, and generating target micro-size data based on the first micro-size data and the second micro-size data.

[0060] Specifically, the target components can be gears, shafts and other key transmission basic functional components of offshore wind power equipment in the field of new energy, and heterogeneous materials such as a combination of high-strength and tough medium-entropy alloys and wear-resistant and corrosion-resistant martensitic stainless steel powders. Based on an optical three-dimensional (3D) surface profiler, white light interferometry technology is used to measure the microscopic dimensions of heterogeneous materials. The optical 3D surface profiler is a non-contact metrology instrument based on white light interferometry technology. The instrument has nanometer-level resolution and sub-nanometer-level repeatability, and is suitable for microscopic dimension measurement and analysis. White light interferometry technology is a technology that uses the interference principle to measure the difference in optical path to determine related physical quantities. The light emitted by the light source is expanded and collimated and then divided into two beams by a spectroscopic prism. One beam of light is reflected back by the measured surface, and the other beam of light is reflected by a reference mirror. The two reflected beams eventually converge and interfere. Any change in the optical path difference between the two coherent light beams will sensitively cause the movement of the interference fringes. The change in the optical path of a coherent light beam is caused by the change in the geometric path it passes through or the refractive index of the medium. By measuring the interference fringes By observing the changes in the surface area, the relevant physical quantities of the measured surface can be measured. The optical 3D surface profiler uses white light interferometry technology to perform sub-nanometer measurement of heterogeneous materials to obtain first microscopic size data; based on the confocal microscope, the confocal technology is used to measure the microscopic size of heterogeneous materials. The confocal microscope is a high-resolution and high-photosensitivity measuring instrument. The confocal technology of the confocal microscope uses a laser scanning beam to pass through a grating pinhole to form a point light source, and scans point by point on the focal plane of the measured sample. The light signal of the collection point reaches the photomultiplier tube through the detection pinhole, and then undergoes signal processing and analysis on the system to obtain the micro-nanoscale measurement data of the heterogeneous material, that is, the second microscopic size data is obtained, and the target microscopic size data is generated based on the first microscopic size data and the second microscopic size data, that is, the target microscopic size data is composed of the first microscopic size data and the second microscopic size data.

[0061] S12: performing geometric shape analysis on the heterogeneous material based on pixel error probability compensation to obtain geometric shape data;

[0062] In the specific implementation process of the present invention, the geometric shape analysis of the heterogeneous material based on pixel error probability compensation to obtain geometric shape data includes: performing saliency processing and binarization processing on the target image of the heterogeneous material to obtain a binarized target saliency map; determining the foreground pixel probability and background pixel probability of the binarized target saliency map based on a pixel probability model, and performing error probability compensation on the foreground pixel probability and background pixel probability to obtain target foreground pixel probability and target background pixel probability; determining the regional outline of the heterogeneous material in the target image based on the target foreground pixel probability and target background pixel probability; and performing geometric shape analysis based on the regional outline of the heterogeneous material to obtain geometric shape data.

[0063] Furthermore, the error probability compensation of the foreground pixel probability and the background pixel probability to obtain the target foreground pixel probability and the target background pixel probability includes: performing classification error analysis on the pixel probability model to obtain classification error data; determining compensation values ​​of the foreground pixel probability and the background pixel probability based on the classification error data, and performing error probability compensation on the foreground pixel probability and the background pixel probability based on the compensation value to obtain the target foreground pixel probability and the target background pixel probability.

[0064] Specifically, a surface image of a heterogeneous material, i.e., a target image, is captured using a high-resolution image acquisition device. The target image contains the heterogeneous material and its background. Saliency processing and binarization are performed on the target image of the heterogeneous material. Noise reduction is performed on the target image to obtain a target image after noise reduction. Frequency domain features of the target image after noise reduction are extracted. A spectrum graph is generated based on the frequency domain features. The spectrum graph is filtered to obtain a filtered spectrum graph. The filtered spectrum graph is converted into a time domain graph through an inverse Fourier transform and an inverse wavelet transform. The time domain graph is input into a visual saliency model for saliency processing to obtain a target saliency map. Image saliency processing can determine the importance of each pixel in the image relative to the background. The target saliency map is binarized using the Otsu algorithm. The Otsu algorithm binarizes the image by calculating a binarization threshold to obtain a binary target saliency map. Based on the pixel probability model, the foreground pixel probability and the background pixel probability of the binary target saliency map are determined, and a sample image and a sample background image are collected. The sample image includes the sample heterogeneous material and the background in which it is located. The sample background image is the area where the background of the sample image is located. The distance between each pixel point of the sample image and the pixel point at the corresponding position of the sample background image is calculated. When the distance is greater than a first preset distance threshold, the corresponding pixel point is determined as a seed foreground pixel point. When the distance is less than a second preset distance threshold, the corresponding pixel point is determined as a seed background pixel point. The first preset distance threshold is greater than the second preset distance threshold. The sample image is marked with the seed foreground pixel point and the seed background pixel point. A deep convolutional neural network is trained according to the marked sample image. The trained deep convolutional neural network is used as a pixel probability model. The binary target saliency map is input into the pixel probability model for pixel probability analysis, and the corresponding foreground pixel probability and background pixel probability can be obtained, that is, the probability that the pixel point of the image belongs to the foreground pixel point and the probability that it belongs to the background pixel point. The pixel probability model is subjected to classification error analysis. There may be certain errors in the pixel probability analysis of the pixel probability model. For example, a pixel belonging to the background may have a higher probability of being assigned to the foreground pixel. Therefore, the pixel probability model needs to be subjected to classification error analysis of the pixel probability. An error compensator is constructed using test data of pixel point probabilities in simulation applications of pixel probability calculation. The error compensator analyzes the output errors of the pixel probability model for background pixel probabilities and foreground pixel probabilities to obtain classification error data. Based on the classification error data, compensation values ​​for the foreground pixel probabilities and background pixel probabilities are determined. That is, the compensation values ​​for the foreground pixel probabilities and background pixel probabilities are matched with the classification error data, and error probability compensation is performed on the foreground pixel probabilities and background pixel probabilities based on the compensation values. That is, the foreground pixel probabilities and background pixel probabilities are calculated with the corresponding compensation values ​​to obtain the target foreground pixel probabilities and target background pixel probabilities.The regional outline of the heterogeneous material in the target image is determined based on the target foreground pixel probability and the target background pixel probability. The target foreground pixel probability and the target background pixel probability are input into the segmentation model to obtain the regional outline of the heterogeneous material in the target image. The geometric shape analysis is performed based on the regional outline of the heterogeneous material to determine the coordinate information of the contour points of the regional outline. The regional outline and contour point coordinate information of the heterogeneous material are used by the recognition model to identify the geometric shape of the heterogeneous material. The geometric shape data is generated from the geometric shape and contour point coordinate information.

[0065] S13: Perform spatial distribution analysis on heterogeneous materials to obtain spatial distribution data;

[0066] In the specific implementation process of the present invention, the spatial distribution analysis of heterogeneous materials to obtain spatial distribution data includes: constructing a representative volume unit of the heterogeneous material, and gridding the representative volume unit to obtain a plurality of grids corresponding to the representative volume unit; constructing a structural simulation model of the heterogeneous material, and performing component position coordinate analysis and material property analysis on each grid based on the structural simulation model to obtain component position coordinates and material properties; and determining the spatial distribution data based on the component position coordinates and material properties of each grid.

[0067] Specifically, a representative volume unit of the heterogeneous material is constructed. Finite element analysis software is used to construct a corresponding representative volume unit using microscopic size information, geometric shape information, and the structure of the heterogeneous material. The representative volume unit contains sufficient geometric and distribution information of the microstructural components. The representative volume unit is then meshed according to preset horizontal and vertical spacing to obtain a number of grids corresponding to the representative volume unit. A structural simulation model of the heterogeneous material is constructed, and the phase separation data of the heterogeneous material is used as training data to train a machine learning model to obtain the structural simulation model. Phase separation refers to the process of an alloy mixture splitting into two or more phases with different physical and chemical properties. The structural simulation model can describe the interface evolution of the phase separation phenomenon in heterogeneous materials. Based on the structural simulation model, component position coordinates and material properties are analyzed for each grid to obtain the component material data of the heterogeneous material. For example, if the heterogeneous material uses a high-strength and tough medium-entropy alloy and wear-resistant and corrosion-resistant martensitic stainless steel powder, what are the respective ratios of the two? The component material data is input into the structural simulation model to analyze the material properties of each grid and the position coordinates of all component phases in each grid, thereby obtaining the component position coordinates and material properties. The spatial distribution data is determined based on the component position coordinates and material properties of each grid, and the spatial distribution of the components of the heterogeneous material structure can be described by the component position coordinates and material properties of each grid.

[0068] S14: Based on the target micro-size data, geometric shape data and spatial distribution data combined with the analysis of the influence of heterogeneous material structure evolution, the initial process parameters of the laser additive manufacturing of the target component are analyzed to obtain the initial process parameters;

[0069] In the specific implementation process of the present invention, the initial process parameter analysis of the target component laser additive manufacturing based on the target micro-size data, geometric shape data and spatial distribution data combined with the heterogeneous material structure evolution influence analysis is performed to obtain the initial process parameters, including: constructing a physical field coupling model based on the different process parameters of laser additive manufacturing in combination with the target micro-size data, geometric shape data and spatial distribution data using finite element simulation technology; constructing a microstructure evolution model based on the physical field coupling model, and performing heterogeneous material structure evolution influence analysis based on the microstructure evolution model to obtain heterogeneous material structure evolution influence data; performing initial process parameter analysis based on the heterogeneous material structure evolution influence data, target micro-size data, geometric shape data and spatial distribution data combined with the process association model to obtain the initial process parameters.

[0070] Specifically, a physical field coupling model is constructed based on different process parameters of laser additive manufacturing in combination with target micro-size data, geometric shape data and spatial distribution data using finite element simulation technology. The process parameters include laser power, scanning speed, overlap parameters, etc. Different process parameters, target micro-size data, geometric shape data and spatial distribution data are input into the finite element simulation model to construct the electromagnetic field mathematical model, thermal field mathematical model and flow field mathematical model of the laser additive manufacturing process. The electromagnetic field mathematical model can adopt Maxwell's equations, the thermal field mathematical model can adopt the heat conduction equation, and the flow field mathematical model can adopt the Navier-Stokes equations. The physical field coupling model is constructed using the electromagnetic field mathematical model, the thermal field mathematical model and the flow field mathematical model through a preset coupling strategy. The preset coupling strategy is that the electromagnetic field and the thermal field are coupled through the Joule heat source term, and the electromagnetic field and the flow field are coupled through the Lorentz force; the thermal field and the flow field are coupled through temperature distribution, phase change latent heat and surface tension. A microstructure evolution model is constructed based on the physical field coupling model. The corresponding grain growth equation, phase field equation and diffusion equation are determined by the microscopic size, geometric shape and component spatial distribution of the heterogeneous material. The grain growth equation describes the growth process after the formation of the crystal nucleus. The phase field equation describes the phase change and movement process of the heterogeneous material, which can describe the evolution of the solid-liquid interface. The diffusion equation describes the solute redistribution process. The microstructure evolution model is formed by the physical field coupling model, the grain growth equation, the phase field equation and the diffusion equation. The dynamic evolution of the microstructure of the heterogeneous material during the laser additive manufacturing process can be analyzed through the microstructure evolution model. The microstructure evolution model analyzes the influence of heterogeneous material structure evolution under different process parameters, and analyzes the microstructure evolution information of heterogeneous materials under different process parameters in combination with target micro-size data, geometric shape data, and spatial distribution data. The microstructure evolution information is used to analyze the influence data on the performance of the formed component. For example, the finer the grains in the microstructure, the better the mechanical properties, and the more grain interfaces, the better the toughness and toughness of the material. In other words, the influence data of the microstructure evolution of heterogeneous materials under different process parameters on the performance of the formed component are analyzed to obtain the influence data of the structure evolution of heterogeneous materials. The initial process parameter analysis is performed based on the influence data of the structure evolution of heterogeneous materials, target micro-size data, geometric shape data, and spatial distribution data combined with the process association model. The process association model adopts a deep learning model. The process association model matches the corresponding process parameters according to the heterogeneous material structure evolution influence data, target micro-size data, geometric shape data, spatial distribution data, and the forming requirements of the target component, that is, obtains the initial process parameters, so that the obtained initial process parameters can fit the expected performance and morphology of the component.

[0071] S15: performing laser additive manufacturing simulation based on the initial process parameters to obtain laser additive manufacturing simulation results, and performing component material performance analysis based on the laser additive manufacturing simulation results to obtain component material performance analysis data;

[0072] In the specific implementation process of the present invention, the laser additive manufacturing simulation is performed based on the initial process parameters to obtain the laser additive manufacturing simulation results, and the component material performance analysis is performed based on the laser additive manufacturing simulation results to obtain the component material performance analysis data, including: performing laser additive manufacturing simulation based on the initial process parameters, target microscopic size data, geometric shape data and spatial distribution data to obtain the laser additive manufacturing simulation results; and performing impact resistance, wear resistance and corrosion resistance analysis using a simulation control model based on the laser additive manufacturing simulation results to obtain the component material performance analysis data.

[0073] Specifically, laser additive manufacturing simulation is performed based on initial process parameters, target micro-size data, geometric shape data and spatial distribution data. The initial process parameters, target micro-size data, geometric shape data and spatial distribution data are input into the simulation software to perform laser additive manufacturing simulation of the target component, and a simulated manufacturing model of the target component is obtained, that is, a laser additive manufacturing simulation result is obtained. Based on the laser additive manufacturing simulation results, a simulation control model is used to analyze the impact resistance, wear resistance and corrosion resistance. The simulation control model includes an impact simulation control model, a wear simulation control model and a corrosion simulation control model. The simulation control model is used to characterize the advantages and disadvantages of the impact resistance, wear resistance and corrosion resistance. Several nodes are set in the simulation manufacturing model of the target component, and impact parameters, wear parameters and corrosion parameters are set. Impact parameters include impact velocity, wear parameters include friction, and corrosion parameters include corrosive medium concentration. According to the set impact parameters, wear parameters and corrosion parameters, impact simulation tests, wear simulation tests and corrosion simulation tests are performed on several nodes. The impact simulation test results, wear simulation test results and corrosion simulation test results are compared with the corresponding simulation control model to obtain the impact resistance data, wear resistance data and wear resistance data of the target component obtained by laser additive manufacturing according to the initial process parameters, and the component material performance analysis data is generated from the impact resistance data, wear resistance data and wear resistance data.

[0074] S16: Adjust the initial process parameters based on the component material performance analysis data combined with the energy consumption analysis to obtain the target process parameters;

[0075] In the specific implementation process of the present invention, the initial process parameters are adjusted based on the component material performance analysis data in combination with the energy consumption analysis to obtain the target process parameters, including: determining the adjustment range of the initial process parameters based on the component material performance analysis data; setting a time model and an energy consumption model of the laser additive manufacturing process, and constructing a target optimization model based on the time model and the energy consumption model; based on the adjustment range of the initial process parameters, using the time model and the energy consumption model in combination with orthogonal experiments to perform energy consumption analysis of the laser additive manufacturing process to obtain energy consumption analysis data; determining adjustment parameters based on the energy consumption analysis data and the target optimization model, and adjusting the initial process parameters based on the adjustment parameters to obtain the target process parameters.

[0076] Specifically, the adjustment range of the initial process parameters is determined based on the component material performance analysis data, which is then compared with the expected performance data. The adjustment range of the initial process parameters is then matched based on the comparison results. A time model and energy consumption model for the laser additive manufacturing process are set. A total time model is constructed based on the time model of each step in the laser additive manufacturing process. An energy consumption model is constructed based on the operating time and equipment output power of each step in the laser additive manufacturing process. A target optimization model is constructed based on the time model and energy consumption model. Minimizing the time and energy consumption of the laser additive manufacturing process and maximizing the utilization of heterogeneous materials are taken as optimization goals. The target optimization model is constructed by combining the time model and energy consumption model. Based on the adjustment range of the initial process parameters, the energy consumption analysis of the laser additive manufacturing process is conducted using a time model and an energy consumption model combined with an orthogonal experiment. One adjustment parameter is selected within the adjustment range of the initial process parameters, and the initial process parameters are adjusted according to the adjustment parameter. An orthogonal experiment is conducted with the adjusted initial process parameters. The time required for laser additive manufacturing under the adjustment parameter is analyzed using the time model. Energy consumption data is analyzed based on the required time combined with the energy consumption model. All adjustment parameters within the adjustment range are tested, and all energy consumption data and time data obtained are energy consumption analysis data. Adjustment parameters are determined based on the energy consumption analysis data and the target optimization model. The material utilization rate of each adjustment parameter is determined based on the adjustment range of the initial process parameters. The adjustment parameters are analyzed based on the energy consumption analysis data and the material utilization rate combined with the target optimization model to obtain the final adjustment parameters. The initial process parameters are then adjusted based on the adjustment parameters to obtain the target process parameters, so that the obtained target process parameters can both reduce the energy consumption of laser additive manufacturing and improve the material utilization rate.

[0077] S17: Performing laser additive manufacturing processing on the target component based on the target process parameters.

[0078] In the specific implementation process of the present invention, the laser additive manufacturing processing of the target component based on the target process parameters includes: performing path planning of the laser additive manufacturing process based on geometric shape data and spatial distribution data in combination with component forming requirements to obtain path data; generating processing instructions based on the path data and target process parameters, and the laser additive manufacturing equipment performing laser additive manufacturing processing of the target component based on the processing instructions.

[0079] Specifically, the path planning of the laser additive manufacturing process is carried out based on the geometric shape data and spatial distribution data combined with the component forming requirements. The component shape is determined according to the component forming requirements. The component shape is used to determine the operation path of the laser additive equipment based on the geometric shape data and spatial distribution data of the heterogeneous material, that is, the path data is obtained. Based on the path data and the target process parameters, processing instructions are generated, and the processing instructions are transmitted to the laser additive equipment. The laser additive equipment performs laser additive manufacturing processing on the target component based on the processing instructions. The laser additive equipment uses the corresponding heterogeneous material to perform laser selection melting, powder spreading and laser melting according to the processing instructions until the entire target component is constructed. The impact resistance, wear resistance and corrosion resistance of the target component are improved, and the service performance and life of key components are significantly improved.

[0080] In an embodiment of the present invention, geometric shape analysis of heterogeneous materials is performed based on pixel error probability compensation, which can improve the accuracy of geometric shape analysis of heterogeneous materials. Initial process parameter analysis of target component laser additive manufacturing is performed based on target microscopic size data, geometric shape data and spatial distribution data combined with heterogeneous material structural evolution influence analysis, and the influence data of heterogeneous material structural evolution is clarified to provide more comprehensive and accurate data support for initial process parameter analysis, making the obtained initial process parameters more reliable. Laser additive manufacturing simulation is performed based on the initial process parameters to obtain laser additive manufacturing simulation results, and component material performance analysis is performed based on the laser additive manufacturing simulation results. The initial process parameters are adjusted based on the component material performance analysis data combined with energy consumption analysis, which can ensure the accuracy of the initial process parameter adjustment and improve the efficiency of parameter adjustment analysis. Laser additive manufacturing processing of target components is performed based on the target process parameters. Through precise control of the parameters, the performance and morphological structure of the manufactured components can achieve more ideal results.

[0081] Example 2

[0082] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of a component laser additive manufacturing method based on heterogeneous material evolution analysis in another embodiment of the present invention, the method comprising:

[0083] S201: Analyze target micro-dimensional data of heterogeneous materials required for target components;

[0084] S202: Performing geometric shape analysis on the heterogeneous material based on pixel error probability compensation to obtain geometric shape data;

[0085] S203: Perform spatial distribution analysis on the heterogeneous material to obtain spatial distribution data;

[0086] S204: Based on different process parameters of laser additive manufacturing and combined with target micro-size data, geometric shape data and spatial distribution data, a physical field coupling model is constructed using finite element simulation technology;

[0087] S205: constructing a microstructure evolution model based on the physical field coupling model, and performing heterogeneous material structure evolution impact analysis based on the microstructure evolution model to obtain heterogeneous material structure evolution impact data;

[0088] S206: performing initial process parameter analysis based on heterogeneous material structure evolution impact data, target micro-size data, geometric shape data, and spatial distribution data in combination with a process correlation model to obtain initial process parameters;

[0089] S207: performing a laser additive manufacturing simulation based on the initial process parameters to obtain a laser additive manufacturing simulation result, and performing a component material performance analysis based on the laser additive manufacturing simulation result to obtain component material performance analysis data;

[0090] S208: Adjusting initial process parameters based on component material performance analysis data combined with energy consumption analysis to obtain target process parameters;

[0091] S209: Performing laser additive manufacturing processing on the target component based on the target process parameters.

[0092] In an embodiment of the present invention, geometric shape analysis of heterogeneous materials is performed based on pixel error probability compensation, which can improve the accuracy of geometric shape analysis of heterogeneous materials. Initial process parameter analysis of target component laser additive manufacturing is performed based on target microscopic size data, geometric shape data and spatial distribution data combined with heterogeneous material structural evolution influence analysis, and the influence data of heterogeneous material structural evolution is clarified to provide more comprehensive and accurate data support for initial process parameter analysis, making the obtained initial process parameters more reliable. Laser additive manufacturing simulation is performed based on the initial process parameters to obtain laser additive manufacturing simulation results, and component material performance analysis is performed based on the laser additive manufacturing simulation results. The initial process parameters are adjusted based on the component material performance analysis data combined with energy consumption analysis, which can ensure the accuracy of the initial process parameter adjustment and improve the efficiency of parameter adjustment analysis. Laser additive manufacturing processing of target components is performed based on the target process parameters. Through precise control of the parameters, the performance and morphological structure of the manufactured components can achieve more ideal results.

[0093] Example 3

[0094] See also Figure 3 , Figure 3 : is a schematic diagram of the structural composition of a component laser additive manufacturing device based on heterogeneous material evolution analysis in an embodiment of the present invention, the device comprising:

[0095] Micro-size analysis module 31: used for analyzing target micro-size data of heterogeneous materials required for target components;

[0096] Geometric shape analysis module 32: used for performing geometric shape analysis on heterogeneous materials based on pixel error probability compensation to obtain geometric shape data;

[0097] Spatial distribution analysis module 33: used to perform spatial distribution analysis on heterogeneous materials and obtain spatial distribution data;

[0098] Parameter analysis module 34: used to analyze initial process parameters of laser additive manufacturing of target components based on target micro-size data, geometric shape data, and spatial distribution data combined with heterogeneous material structure evolution impact analysis to obtain initial process parameters;

[0099] Material performance analysis module 35: used to perform laser additive manufacturing simulation based on initial process parameters to obtain laser additive manufacturing simulation results, and perform component material performance analysis based on the laser additive manufacturing simulation results to obtain component material performance analysis data;

[0100] Parameter adjustment module 36: used to adjust the initial process parameters based on the component material performance analysis data combined with the energy consumption analysis to obtain the target process parameters;

[0101] Laser additive manufacturing module 37: used for performing laser additive manufacturing processing of target components based on target process parameters.

[0102] In the specific implementation process of the present invention, the specific implementation method of the device item can refer to the implementation method of the above-mentioned method item, which will not be repeated here.

[0103] In an embodiment of the present invention, geometric shape analysis of heterogeneous materials is performed based on pixel error probability compensation, which can improve the accuracy of geometric shape analysis of heterogeneous materials. Initial process parameter analysis of target component laser additive manufacturing is performed based on target microscopic size data, geometric shape data and spatial distribution data combined with heterogeneous material structural evolution influence analysis, and the influence data of heterogeneous material structural evolution is clarified to provide more comprehensive and accurate data support for initial process parameter analysis, making the obtained initial process parameters more reliable. Laser additive manufacturing simulation is performed based on the initial process parameters to obtain laser additive manufacturing simulation results, and component material performance analysis is performed based on the laser additive manufacturing simulation results. The initial process parameters are adjusted based on the component material performance analysis data combined with energy consumption analysis, which can ensure the accuracy of the initial process parameter adjustment and improve the efficiency of parameter adjustment analysis. Laser additive manufacturing processing of target components is performed based on the target process parameters. Through precise control of the parameters, the performance and morphological structure of the manufactured components can achieve more ideal results.

[0104] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0105] In addition, the above is a detailed introduction to the component laser additive manufacturing method and device based on heterogeneous material evolution analysis provided by the embodiments of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A component laser additive manufacturing method based on heterogeneous material evolution analysis, characterized in that: The method comprises: Analyze the target micro-dimensional data of heterogeneous materials required for target components; Performing geometric shape analysis on heterogeneous materials based on pixel error probability compensation to obtain geometric shape data; Perform spatial distribution analysis on heterogeneous materials to obtain spatial distribution data; Based on the target micro-size data, geometric shape data and spatial distribution data combined with the analysis of the influence of heterogeneous material structure evolution, the initial process parameters of laser additive manufacturing of the target component are analyzed to obtain the initial process parameters; Performing laser additive manufacturing simulation based on initial process parameters to obtain laser additive manufacturing simulation results, and performing component material performance analysis based on the laser additive manufacturing simulation results to obtain component material performance analysis data; Adjust the initial process parameters based on component material performance analysis data combined with energy consumption analysis to obtain target process parameters; The target component is laser-added manufactured based on the target process parameters.

2. The component laser additive manufacturing method based on heterogeneous material evolution analysis according to claim 1 is characterized in that: The target microscopic size data of the heterogeneous material required for analyzing the target component includes: Using white light interferometry technology based on an optical 3D surface profiler to measure the microscopic dimensions of heterogeneous materials, the first microscopic dimension data is obtained; The microscopic size of the heterogeneous material is measured by using a confocal technique based on a confocal microscope to obtain second microscopic size data, and target microscopic size data is generated based on the first microscopic size data and the second microscopic size data.

3. The component laser additive manufacturing method based on heterogeneous material evolution analysis according to claim 1 is characterized in that: The performing of geometric shape analysis on the heterogeneous material based on pixel error probability compensation to obtain geometric shape data includes: Perform saliency processing and binarization on the target image of the heterogeneous material to obtain a binary target saliency map; Determining the foreground pixel probability and the background pixel probability of the binary target saliency map based on the pixel probability model, and performing error probability compensation on the foreground pixel probability and the background pixel probability to obtain the target foreground pixel probability and the target background pixel probability; Determine the region outline of the heterogeneous material in the target image based on the target foreground pixel probability and the target background pixel probability; A geometric shape analysis is performed based on the regional contour of the heterogeneous material to obtain geometric shape data.

4. The component laser additive manufacturing method based on heterogeneous material evolution analysis according to claim 3 is characterized in that: The performing error probability compensation on the foreground pixel probability and the background pixel probability to obtain the target foreground pixel probability and the target background pixel probability includes: Perform classification error analysis on the pixel probability model to obtain classification error data; Compensation values ​​of foreground pixel probabilities and background pixel probabilities are determined based on the classification error data, and error probability compensation is performed on the foreground pixel probabilities and background pixel probabilities based on the compensation values ​​to obtain target foreground pixel probabilities and target background pixel probabilities.

5. The component laser additive manufacturing method based on heterogeneous material evolution analysis according to claim 1, characterized in that: The performing of spatial distribution analysis on the heterogeneous material to obtain spatial distribution data includes: Constructing a representative volume unit of the heterogeneous material and performing mesh division on the representative volume unit to obtain a plurality of meshes corresponding to the representative volume unit; Construct a structural simulation model of heterogeneous materials, and perform component position coordinate analysis and material property analysis on each grid based on the structural simulation model to obtain component position coordinates and material properties; The spatial distribution data is determined based on the component position coordinates and material properties of each grid.

6. The component laser additive manufacturing method based on heterogeneous material evolution analysis according to claim 1 is characterized in that: The initial process parameter analysis of the target component laser additive manufacturing based on the target micro-size data, geometric shape data and spatial distribution data combined with the analysis of the influence of the heterogeneous material structure evolution is performed to obtain the initial process parameters, including: Based on the different process parameters of laser additive manufacturing and combined with the target micro-size data, geometric shape data and spatial distribution data, a physical field coupling model is constructed using finite element simulation technology; Constructing a microstructure evolution model based on the physical field coupling model, and performing heterogeneous material structure evolution impact analysis based on the microstructure evolution model to obtain heterogeneous material structure evolution impact data; Based on the heterogeneous material structure evolution influence data, target micro-size data, geometric shape data and spatial distribution data combined with the process correlation model, the initial process parameters are analyzed to obtain the initial process parameters.

7. The component laser additive manufacturing method based on heterogeneous material evolution analysis according to claim 1 is characterized in that: The laser additive manufacturing simulation is performed based on the initial process parameters to obtain the laser additive manufacturing simulation results, and component material performance analysis is performed based on the laser additive manufacturing simulation results to obtain component material performance analysis data, including: Perform laser additive manufacturing simulation based on initial process parameters, target micro-size data, geometric shape data, and spatial distribution data to obtain laser additive manufacturing simulation results; Based on the laser additive manufacturing simulation results, the impact resistance, wear resistance and corrosion resistance are analyzed using a simulation control model to obtain component material performance analysis data.

8. The component laser additive manufacturing method based on heterogeneous material evolution analysis according to claim 1 is characterized in that: The initial process parameters are adjusted based on the component material performance analysis data combined with the energy consumption analysis to obtain the target process parameters, including: Determine the adjustment range of initial process parameters based on component material performance analysis data; Set up the time model and energy consumption model of the laser additive manufacturing process, and build a target optimization model based on the time model and energy consumption model; Based on the adjustment range of the initial process parameters, the energy consumption analysis of the laser additive manufacturing process is carried out using the time model and energy consumption model combined with orthogonal experiments to obtain energy consumption analysis data; Adjustment parameters are determined based on energy consumption analysis data and the target optimization model, and the initial process parameters are adjusted based on the adjustment parameters to obtain target process parameters.

9. The component laser additive manufacturing method based on heterogeneous material evolution analysis according to claim 1, characterized in that: The laser additive manufacturing process of the target component based on the target process parameters includes: Based on the geometric shape data and spatial distribution data combined with the component forming requirements, the path planning of the laser additive manufacturing process is carried out to obtain the path data; A processing instruction is generated based on the path data and the target process parameters, and the laser additive manufacturing equipment performs laser additive manufacturing processing on the target component based on the processing instruction.

10. A component laser additive manufacturing device based on heterogeneous material evolution analysis, characterized in that: The device comprises: Micro-size analysis module: used to analyze the target micro-size data of heterogeneous materials required for target components; Geometric shape analysis module: used to perform geometric shape analysis on heterogeneous materials based on pixel error probability compensation to obtain geometric shape data; Spatial distribution analysis module: used to perform spatial distribution analysis on heterogeneous materials and obtain spatial distribution data; Parameter analysis module: used to analyze the initial process parameters of laser additive manufacturing of target components based on target micro-size data, geometric shape data, and spatial distribution data combined with the analysis of the influence of heterogeneous material structure evolution to obtain the initial process parameters; Material performance analysis module: used to perform laser additive manufacturing simulation based on initial process parameters to obtain laser additive manufacturing simulation results, and to perform component material performance analysis based on the laser additive manufacturing simulation results to obtain component material performance analysis data; Parameter adjustment module: used to adjust the initial process parameters based on component material performance analysis data combined with energy consumption analysis to obtain target process parameters; Laser Additive Manufacturing Module: Used to perform laser additive manufacturing processing of target parts based on target process parameters.

Images