A self-adaptive method and related equipment for laser selective melting of overhanging structure

Abstract

The present invention discloses an adaptive method for laser selective melting of an overhang structure and related equipment, the method comprising: generating a three-dimensional model according to an input standard model file of a part to be printed; slicing the three-dimensional model using slicing software to obtain layered slicing data; performing an overhang recognition operation on the slice layer in the layered slicing data to calculate the overhang angle size of the area with overhang characteristics; calculating and optimizing the optimal process parameters according to the overhang angle size and a non-parametric model; and printing the part to be printed according to the optimal process parameters. By using slicing software to slice the three-dimensional model, performing an overhang recognition operation on the obtained slice layer to calculate the overhang angle size, and calculating the optimal process parameters according to the overhang angle size and the non-parametric model, so as to print the part to be printed, the optimal process parameters can be adaptively selected according to the parts to be printed with different overhang angles for printing.

Description

Technical Field

[0001] The present invention relates to the technical field of additive manufacturing, and in particular to an adaptive method for a selective laser melting process of a suspension structure and related equipment. Background Art

[0002] Additive Manufacturing (AM), also known as 3D printing, is an emerging molding technology based on the discrete-accumulation principle. This technology can efficiently form parts with complex shapes at a low cost, and is widely used in aviation, automobile manufacturing, biomedicine and other fields. Commonly used additive manufacturing technologies include stereolithography (SLA), fused deposition modeling (FDM) and selective laser melting (SLM).

[0003] The laser selective melting forming technology with powder bed as the main technical feature breaks through the constraints of product structure and morphology. It uses high-energy laser beam as a direct heat source, selectively heats and melts the metal powder bed area, and then stacks layer by layer, so that it can directly process complex parts with unconventional structural features that cannot be processed or are difficult to process by traditional manufacturing processes. However, the step effect caused by the layer-by-layer printing method of AM manufacturing methods, as well as the warping defects caused by residual stress and thermal shrinkage of materials in the SLM printing process, will seriously reduce the surface quality of parts and cause structural misalignment. Especially in the molding overhang structure, if a support structure is added during the printing process, a lot of manpower and material resources are required for post-processing. In view of the characteristics of the overhang structure, it is very important to successfully print the parts without adding support structures and ensure good surface quality and reduce structural warping. According to research, the most important factor affecting the warping defect of SLM is the energy input during the printing process. The laser power and laser printing speed directly affect the energy input. Therefore, the impact on the warping defect is transformed into the selection of process parameters for printing overhang structures. Currently in the field of additive manufacturing, most SLM overhang processes select process parameters for overhang structures mainly through a large amount of experimental accumulation and literature research, which undoubtedly costs a lot of time and cost.

[0004] Therefore, seeking a method that can achieve adaptive process parameter adjustment for overhang structures in SLM printing may be an urgent problem to be solved by people in this field.

[0005] Therefore the prior art still needs to be improved and enhanced. Summary of the invention

[0006] The main purpose of the present invention is to provide a method and related equipment for adaptively adjusting the process of laser selective melting of a overhanging structure, aiming to solve the problem that the process parameters of the overhanging structure under the SLM printing method in the prior art cannot be adaptively adjusted.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A method for self-adapting a process of laser selective melting of a suspension structure, the method comprising:

[0009] Generate a three-dimensional model according to an input standard model file of a part to be printed; wherein the standard model file is a file expressed in a standard triangle language;

[0010] Slicing the three-dimensional model using slicing software to obtain layered slicing data; wherein the slicing software is laser selective melting forming data preparation software;

[0011] Performing an overhang recognition operation on the slice layers in the layered slice data to calculate the overhang angle of the area with overhang characteristics;

[0012] Calculate and optimize the optimal process parameters according to the overhang angle and the non-parametric model; wherein the non-parametric model includes a Gaussian process regression model;

[0013] The component to be printed is printed according to the optimal process parameters.

[0014] In the adaptive method for the selective laser melting process of an overhang structure, the step of performing an overhang recognition operation on the slice layers in the layered slice data and calculating the overhang angle size of the area with the overhang feature specifically includes:

[0015] Use the slicer to generate connecting line segments in each slice layer;

[0016] Projecting the connecting line segment on the current slice layer onto the next slice layer to obtain a projection line;

[0017] Splitting the projection line that is longer than a preset length to obtain a split projection line;

[0018] Calculate the overhang angle at the midpoint of each segmented projection line.

[0019] In the self-adaptive method for selective laser melting of overhang structure, the step of calculating and optimizing the optimal process parameters according to the overhang angle and non-parametric model specifically includes:

[0020] After building the non-parametric model, a full factorial experimental design method is used to obtain sample points as a training data set for the non-parametric model;

[0021] Obtaining a data validation set for the non-parametric model, and obtaining a correlation coefficient of the non-parametric model using a cross-validation analysis method;

[0022] A multi-objective optimization problem is constructed according to minimizing deformation and surface roughness, and an optimal solution set of the multi-objective optimization problem is calculated using a multi-objective optimization method; wherein the optimal solution set is the optimal process parameters.

[0023] In the adaptive method for the selective laser melting process of the overhang structure, the step of calculating the overhang angle at the midpoint of each segmented projection line specifically includes:

[0024] Taking the connecting line segment as a direction vector and multiplying it by a rotation matrix to obtain a vertical line segment;

[0025] Calculating the minimum distance between the midpoint and the intersection of the vertical line segment and the next slice layer;

[0026] The overhang angle is calculated based on the minimum distance and the thickness of the next slice layer; wherein the calculation formula of the overhang angle is: Among them, d min is the minimum distance; h is the layer thickness.

[0027] In the self-adaptive method for selective laser melting of overhanging structure, after building the non-parametric model, the step of using a full factorial experimental design method to obtain sample points as a training data set for the non-parametric model specifically includes:

[0028] After the non-parametric model is constructed, a first preset amount of laser power and a second preset amount of laser scanning speed are used as variable parameters, and a non-variable parameter is selected;

[0029] The non-variable parameters include the thickness of the slice layer, the overlap spacing and the inter-layer rotation angle, the printing material and specification, and the material and size of the substrate; the printing material includes titanium alloy, aluminum alloy and high-temperature nickel-based alloy material powder;

[0030] The variable parameters are applied to a third preset number of to-be-printed parts with overhang angles to obtain data samples as the training data set.

[0031] In the self-adaptive method for selective laser melting of overhanging structure, the step of obtaining a data validation set of the non-parametric model and obtaining a correlation coefficient of the non-parametric model by using a cross-validation analysis method specifically includes:

[0032] Taking the first preset number of laser powers, the second preset number of laser scanning speeds and the third preset number of overhang angle sizes as interval ranges, randomly selecting a fourth preset number of sample points as the data verification set;

[0033] The correlation coefficient of the non-parametric model is calculated using the cross-validation analysis method.

[0034] In the adaptive method for the selective laser melting process of the overhang structure, the steps of constructing a multi-objective optimization problem according to minimizing deformation and surface roughness, and calculating the optimal solution set of the multi-objective optimization problem using the multi-objective optimization method specifically include:

[0035] Obtaining the minimized deformation and surface roughness of the data sample;

[0036] Constructing the multi-objective optimization problem with the minimization of deformation and surface roughness as the goal;

[0037] The optimal solution set of the multi-objective optimization problem is obtained by using a multi-objective optimization method based on an evolutionary algorithm.

[0038] In the self-adaptive method for selective laser melting of overhanging structure, the step of printing the to-be-printed component according to the optimal process parameters specifically includes:

[0039] Grind the surface of the substrate with an angle grinder until there is no oxide, and clean it with an organic cleaning agent;

[0040] After the printing chamber is evacuated, a protective gas is introduced to make the oxygen content lower than a preset concentration, and the cleaned substrate is preheated to a preset temperature;

[0041] According to the optimal process parameters, the printing material is printed on the heated substrate in the printing chamber to obtain the component to be printed.

[0042] A self-adaptive system for selective laser melting of a suspension structure, the self-adaptive system for selective laser melting of a suspension structure comprising:

[0043] A three-dimensional model generation module, used to generate a three-dimensional model according to an input standard model file of a component to be printed; wherein the standard model file is a file expressed in a standard triangle language;

[0044] A layered slice data generation module, used for slicing the three-dimensional model using slicing software to obtain layered slice data; wherein the slicing software is laser selective melting forming data preparation software;

[0045] An overhang angle calculation module is used to perform an overhang recognition operation on the slice layer in the layered slice data to calculate the overhang angle size of the area with overhang characteristics;

[0046] An optimal process parameter calculation module, used to calculate and optimize the optimal process parameters according to the overhang angle and the non-parametric model; wherein the non-parametric model includes a Gaussian process regression model;

[0047] A printing module is used to print the component to be printed according to the optimal process parameters.

[0048] A controller comprises: a memory, a processor, a display, and an adaptive program for a selective laser melting process of a drape structure stored in the memory and executable on the processor. When the adaptive program for a selective laser melting process of a drape structure is executed by the processor, the steps of the adaptive method for a selective laser melting process of a drape structure as described above are implemented.

[0049] Compared with the prior art, the present invention provides an adaptive method for laser selective melting of overhang structures and related equipment, the method comprising: generating a three-dimensional model according to an input standard model file of a part to be printed; slicing the three-dimensional model using slicing software to obtain layered slicing data; performing an overhang recognition operation on the slice layers in the layered slicing data to calculate the overhang angle size of the area with overhang characteristics; calculating and optimizing the optimal process parameters according to the overhang angle size and non-parametric model; printing the part to be printed according to the optimal process parameters. By using slicing software to slice the three-dimensional model, performing an overhang recognition operation on the obtained slice layers to calculate the overhang angle size, and calculating the optimal process parameters according to the overhang angle size and non-parametric model, so as to print the part to be printed, the optimal process parameters are adaptively selected according to the parts to be printed with different overhang angles for printing. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flow chart of a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0051] Figure 2 A schematic diagram of a three-dimensional model in a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0052] Figure 3 A flowchart of step S300 in a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0053] Figure 4 A flowchart of step S340 in a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0054] Figure 5An explanatory diagram of the overhang angle in a preferred embodiment of the adaptive method for selective laser melting of an overhang structure provided by the present invention;

[0055] Figure 6 A flowchart of step S400 in a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0056] Figure 7 A flowchart of step S410 in a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0057] Figure 8 A flowchart of step S420 in a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0058] Fig. 9 A flowchart of step S430 in a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0059] Fig.10 A flowchart of step S500 in a preferred embodiment of the adaptive method for selective laser melting of a suspension structure provided by the present invention;

[0060] Fig.11 The architecture relationship diagram of the adaptive system for the selective laser melting process of the overhanging structure provided by the present invention;

[0061] Fig.12 A schematic diagram of the operating environment of a preferred embodiment of the controller provided by the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0063] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0064] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as herein.

[0065] In order to facilitate understanding of the embodiments of the present application, the background technology involved in the embodiments of the present invention is first introduced here.

[0066] Laser selective melting printing technology is currently a key research direction in the field of additive manufacturing, but the selection of process parameters for overhanging structures often takes a lot of time and cost.

[0067] In order to solve the above-mentioned prior art problems, the present invention provides an adaptive method for laser selective melting of overhang structure and related equipment. In the present invention, the slicing software is used to slice the three-dimensional model, and the obtained slice layer is subjected to overhang recognition operation to calculate the overhang angle size, and then the optimal process parameters are calculated and optimized according to the overhang angle size and non-parametric model to print the parts to be printed, thereby realizing the adaptive selection of the optimal process parameters for printing according to the parts to be printed with different overhang angles, effectively reducing time and labor costs.

[0068] The following describes the design scheme of the adaptive method for the selective laser melting process of the overhanging structure through specific exemplary embodiments. It should be noted that the following embodiments are only used to explain the technical scheme of the invention and are not specifically limited:

[0069] See also Figure 1The present invention provides an adaptive method for a selective laser melting process of a suspension structure, and the adaptive method for selective laser melting process of a suspension structure comprises:

[0070] S100, generating a three-dimensional model according to an input standard model file of a component to be printed; wherein the standard model file is a file expressed in a standard triangle language.

[0071] Specifically, before 3D printing, some preparations must be done first: design the standard model file of the part to be printed, that is, the file expressed in standard triangle language (STL: standard triangulation language, a standard file format for collaboration between software and printers, and a universal interface format currently used by 3D printing manufacturing equipment), prepare a 3D printer, such as the HY-M300 3D printing device, and prepare the printing material (aluminum alloy and other metal powders).

[0072] Then, the standard model file of the three-dimensional model of the required part to be printed is input into the printer. The schematic diagram of the three-dimensional model is as follows: Figure 2 As shown, secondly, the three-dimensional model is generated on a 3D printer according to the standard model file.

[0073] In the present invention, the three-dimensional model is modeled by using a file in a standard file format applied to a printer so as to perform operable processing on the three-dimensional model.

[0074] For further information, please refer to Figure 1 S200: Slice the three-dimensional model using slicing software to obtain layered slicing data; wherein the slicing software is laser selective melting forming data preparation software.

[0075] Specifically, after generating the three-dimensional model, STL file editing software such as Netfabb and Magics is first used to open the STL file (standard model file) and display some error information in the model. It includes basic functions for STL files: analysis, scaling, measurement and repair.

[0076] Secondly, input data such as layer thickness, and use the slicing software (laser selective melting molding data preparation software, such as Cura, XBuilder and Makerbot software) to automatically slice the three-dimensional model to obtain the layered slicing data, use the slicing software to adjust the parameters of the 3D model (three-dimensional model), and convert the model slices into a format that can be recognized by the 3D printer for printing operations.

[0077] For further information, please refer to Figure 1, S300, performing an overhang recognition operation on the slice layer in the layered slice data, and calculating the overhang angle size of the overhang feature area.

[0078] Specifically, after performing a slicing operation to obtain the layered slicing data, an algorithm program is used to perform an overhang recognition operation on the slicing layer in the layered slicing data to calculate the overhang angle size of the area with the overhang feature, so as to calculate and optimize the optimal process parameters based on the overhang angle size.

[0079] For further information, see Figure 3 The step of performing an overhang recognition operation on the slice layers in the layered slice data and calculating the overhang angle of the region with overhang characteristics in S300 specifically includes:

[0080] S310, using a slicer to generate connecting line segments in each slice layer;

[0081] S320, projecting the connecting line segment on the current slice layer onto the next slice layer to obtain a projection line;

[0082] S330, segmenting the projection line that is longer than a preset length to obtain segmented projection lines;

[0083] S340, calculating the size of the overhang angle at the midpoint of each segmented projection line.

[0084] Specifically, the specific steps for performing the overhang recognition operation are as follows, taking two slice layers i and i-1 as an example:

[0085] First, in order to obtain the overhang angle, a slicer is used to generate connecting line segments in each slice layer. The connecting line segments on the current slice layer are projected onto the next slice layer to obtain projection lines, that is, for each connecting line segment in the i-th slice layer, the connecting line segment itself and its midpoint are directly projected onto the layer below (or directly onto the top in the case of the first layer) to obtain the projection line. If the overhang angle at the midpoint is a good approximation of the overhang angle of the entire connecting line segment as long as the line segment is short enough, then the projection line greater than the preset length can be segmented to obtain segmented projection lines, for example, a longer line can be divided into smaller segments with a length of less than 5 mm. Finally, the overhang angle at the midpoint of each segmented projection line is calculated.

[0086] For further information, see Figure 4 The step of calculating the overhang angle at the midpoint of each segmented projection line in S340 specifically includes:

[0087] S341, taking the connecting line segment as a direction vector and multiplying it by a rotation matrix to obtain a vertical line segment;

[0088] S342, calculating the minimum distance between the midpoint and the intersection of the vertical line segment and the next slice layer;

[0089] S343, calculating the overhang angle according to the minimum distance and the thickness of the next slice layer; wherein the calculation formula of the overhang angle is: Among them, d min is the minimum distance; h is the layer thickness.

[0090] Specifically, see Figure 5 After obtaining the segmented projection line, the original line segment (connecting line segment) is used as the direction vector, multiplied by the rotation matrix and rotated 90° to obtain the vertical line segment L. If the vertical line segment L has any intersection with the i-1th slice layer, it is considered that d min is the minimum distance between the midpoint M and any intersection point on the i-1th slice layer, where the overhang angle (degrees) θ is shown in the figure below: Figure 5 Therefore, the overhang angle θ of the connecting line segment is determined by the following equation: (1), where h is the layer thickness, d min It is the minimum distance between the midpoint M and any intersection point on the i-1th slice layer.

[0091] For further information, please refer to Figure 1 , S400, calculating and optimizing the optimal process parameters according to the overhang angle size and the non-parametric model; wherein the non-parametric model includes a Gaussian process regression model.

[0092] Specifically, after the overhang angle size is calculated, the optimal process parameters are calculated and optimized according to the overhang angle size and the non-parametric model, wherein the non-parametric model includes a Gaussian process regression model. The Gaussian process regression model (Gaussian Process Regression, GPR) is a non-parameteric model (non-parameteric model) that uses Gaussian process (Gaussian Process, GP) prior to perform regression analysis on data, so as to derive the optimal printing parameters corresponding to each overhang angle according to the different overhang angle sizes and the non-parametric model.

[0093] For further information, see Figure 6 The step of calculating and optimizing the optimal process parameters according to the overhang angle size and the non-parametric model in S400 specifically includes:

[0094] S410, after building the non-parametric model, using a full factorial experimental design method to obtain sample points as a training data set for the non-parametric model;

[0095] S420, obtaining a data validation set for the non-parametric model, and obtaining a correlation coefficient of the non-parametric model using a cross-validation analysis method;

[0096] S430, constructing a multi-objective optimization problem according to minimizing deformation and surface roughness, and calculating an optimal solution set of the multi-objective optimization problem using a multi-objective optimization method; wherein the optimal solution set is the optimal process parameters.

[0097] Specifically, the specific steps for calculating the optimal process parameters are as follows:

[0098] First, it is necessary to build the non-parametric model, such as a Gaussian process regression model, wherein the input variables of the non-parametric model are laser power, laser scanning speed and overhang angle, and the output variables are the deformation of the parts and the surface roughness. Afterwards, in order to make the response surface model obtained by the Gaussian process regression process more accurate, a full factorial experimental design method is used (full factorial experimental design DOE means that all combinations of all levels of all factors are tested at least once, and all main effects and all order interaction effects can be estimated) to obtain more sample points as the training data set of the non-parametric model. The full factorial experimental design method is used to obtain more sample points to better perform subsequent Gaussian process regression.

[0099] Secondly, obtain the data validation set of the non-parametric model and use the cross-validation analysis method to obtain the correlation coefficient R of the non-parametric model. 2 is about 0.9; finally, a multi-objective optimization problem is constructed according to the minimization of deformation and surface roughness, and the optimal solution set (optimal process parameters) of the multi-objective optimization problem is calculated by using a multi-objective optimization method (MOEA) based on evolutionary algorithms such as NSGA-II.

[0100] For further information, see Figure 7 The step of S410, after building the non-parametric model, using a full factorial experimental design method to obtain sample points as a training data set for the non-parametric model, specifically includes:

[0101] S411, after building the non-parametric model, taking the first preset number of laser powers and the second preset number of laser scanning speeds as variable parameters, and selecting non-variable parameters;

[0102] The non-variable parameters include the thickness of the slice layer, the overlap spacing and the inter-layer rotation angle, the printing material and specification, and the material and size of the substrate; the printing material includes titanium alloy, aluminum alloy and high-temperature nickel-based alloy material powder;

[0103] S412: Apply the variable parameters to the to-be-printed parts with a third preset number of overhang angles to obtain data samples as the training data set.

[0104] Specifically, after building the non-parametric model, the steps of establishing a training data set are as follows:

[0105] First, the laser power of the first preset number and the laser scanning speed of the second preset number are used as variable parameters, for example: the laser power of the first preset number: 250W, 275W, 300W, 325W, 350W, and the laser scanning speed of the second preset number: 800mm / s, 900mm / s, 1000mm / s, 1100mm / s, 1200mm / s are used as the variable parameters. At the same time, the non-variable parameters used include the layer thickness, overlap spacing and interlayer rotation angle of the slice layer, the printing material and specifications, and the material and size of the substrate; the printing material includes titanium alloy, aluminum alloy and high-temperature nickel-based alloy material powder; for example: the layer thickness is 50μm; the overlap spacing is 100μm; the printing method is an interlayer rotation angle of 67° to release residual stress; the printing material used is titanium alloy, and its particle size distribution is 17μm-51μm; the substrate material is Ti6Al4V (titanium hexaaluminum tetravanadium), and the size of the substrate is 300mm.

[0106] Then, the variable parameters are applied to the parts to be printed with the overhang angle size of the third preset number, that is, by changing the two parameters (laser power and laser scanning speed) that have the greatest impact on the surface quality of the overhang structure, and applying this 5×5 parameter table to the parts with the overhang angle of the third preset number (30°, 35°, 40°, 45°, 50°, 55°, 60°, 65°, 70°, 75°), a total of 250 data samples can be obtained as the training data set for machine learning, and after learning the data set through the machine learning method of Gaussian process regression, the response surface is established.

[0107] For further information, see Figure 8 The step of obtaining the data validation set of the non-parametric model and obtaining the correlation coefficient of the non-parametric model by using a cross-validation analysis method in S420 specifically includes:

[0108] S421, taking the first preset number of laser powers, the second preset number of laser scanning speeds and the third preset number of overhang angle sizes as the interval range, randomly selecting a fourth preset number of sample points as the data verification set;

[0109] S422. Calculate the correlation coefficient of the non-parametric model using the cross-validation analysis method.

[0110] Specifically, when obtaining the data verification set of the non-parametric model, a first preset number of laser powers, a second preset number of laser scanning speeds, and a third preset number of overhang angle sizes are used as the interval range, and a fourth preset number of sample points are randomly selected as the data verification set, that is, 25 groups (the fourth preset number) of sample points are randomly generated within the parameter range of laser power of 250W to 350W, laser scanning speed of 800mm / s to 1200mm / s, and overhang angle of 30° to 75° as the data verification set of the Gaussian process regression model.

[0111] Afterwards, the correlation coefficient of the nonparametric model is calculated using the cross-validation analysis method. The correlation coefficient of the Gaussian process regression model in this embodiment (the correlation coefficient refers to the degree of fit between the test data and the fitting function) R 2 About 0.9.

[0112] For further information, see Fig. 9 The step of constructing a multi-objective optimization problem according to minimizing deformation and surface roughness and calculating the optimal solution set of the multi-objective optimization problem using a multi-objective optimization method in S430 specifically includes:

[0113] S431, obtaining the minimum deformation amount and surface roughness of the data sample;

[0114] S432, constructing the multi-objective optimization problem with the goal of minimizing the deformation and the surface roughness;

[0115] S433. Obtain an optimal solution set for the multi-objective optimization problem using a multi-objective optimization method based on an evolutionary algorithm.

[0116] Specifically, while applying the variable parameters to the to-be-printed parts with a third preset number of overhang angles, the minimum deformation and the surface roughness of all the data samples are obtained through experiments. Then, with the minimization of the deformation and the surface roughness as the goal, a multi-objective optimization problem is constructed through Matlab programming, and a multi-objective optimization method (MOEA) based on an evolutionary algorithm such as NSGA-II is used to obtain the optimal solution set (optimal process parameters) of the multi-objective optimization problem, thereby completing the self-adaptation of the printing process.

[0117] For further information, please refer to Figure 1 , S500, printing the component to be printed according to the optimal process parameters.

[0118] Finally, enter the printing stage:

[0119] After completing the preparation steps before printing, the printer prints the printing material on the substrate according to the optimal process parameters to obtain the component to be printed.

[0120] For further information, see Fig.10 The step of S500, printing the component to be printed according to the optimal process parameters, specifically includes:

[0121] S510, grinding the surface of the substrate with an angle grinder until there is no oxide, and cleaning it with an organic cleaning agent;

[0122] S520, after the printing chamber is evacuated, a protective gas is input to make the oxygen content lower than a preset concentration, and the cleaned substrate is preheated to a preset temperature;

[0123] S530: Print the printing material on the heated substrate in the printing chamber according to the optimal process parameters to obtain the component to be printed.

[0124] Specifically, before starting printing, the surface of the substrate is first grinded with an angle grinder until there is no oxide, and then cleaned with an organic cleaning agent, such as acetone and alcohol, to clean the oil and dirt on the surface respectively, and then a sandblasting machine is used to sandblast the surface of the cleaned substrate.

[0125] Then, the printing chamber is evacuated and a protective gas is input to make the oxygen content lower than a preset concentration, and the cleaned substrate is preheated to a preset temperature, that is, the printing chamber is evacuated and the oxygen content is lower than 450ppm, argon is used as a protective gas to prevent oxidation, and the cleaned substrate is preheated 120° in advance. Finally, according to the optimal process parameters, the printing material is printed on the heated substrate in the printing chamber to obtain the component to be printed.

[0126] For further information, see Fig.11 The present invention provides an adaptive system for selective laser melting of a suspension structure, and the adaptive system for selective laser melting of a suspension structure comprises:

[0127] A three-dimensional model generation module 1 is used to generate a three-dimensional model according to an input standard model file of a part to be printed; wherein the standard model file is a file expressed in a standard triangle language;

[0128] A layered slice data generating module 2 is used to slice the three-dimensional model using a slice software to obtain layered slice data; wherein the slice software is a laser selective melting forming data preparation software;

[0129] The overhang angle calculation module 3 is used to perform an overhang recognition operation on the slice layer in the layered slice data, and calculate the overhang angle size of the overhang feature area;

[0130] An optimal process parameter calculation module 4 is used to calculate and optimize the optimal process parameters according to the overhang angle and the non-parametric model; wherein the non-parametric model includes a Gaussian process regression model;

[0131] The printing module 5 is used to print the component to be printed according to the optimal process parameters.

[0132] Specifically, the overhang structure laser selective melting process adaptive method is applied to the overhang structure laser selective melting process adaptive system, and the overhang structure laser selective melting process adaptive method steps are as follows:

[0133] Before 3D printing, some preparation work must be done first: design the standard model file of the part to be printed, that is, the standard triangle language, prepare the 3D printer, and prepare the printing materials, including titanium alloy, aluminum alloy, high-temperature nickel-based alloy and other material powders.

[0134] Then, the standard model file of the three-dimensional model of the required part to be printed is input into the printer, and the three-dimensional model is generated on the 3D printer according to the standard model file. Secondly, the three-dimensional model is sliced ​​by the slicing software to obtain the layered slicing data, and the slicing layer in the layered slicing data is subjected to overhang recognition operation by the algorithm program to calculate the overhang angle size of the overhang feature area. Furthermore, the optimal process parameters are calculated and optimized according to the overhang angle size and the non-parametric model. Finally, the printer prints the printing material on the substrate according to the optimal process parameters to obtain the part to be printed, and the surface roughness and deformation of the printed parts are measured, and the roughness Ra is measured to be 14μm and the deformation is 0.9mm.

[0135] The present invention adaptively matches the corresponding optimal process parameters through a three-dimensional model, thereby printing parts with better surface quality and smaller deformation, and realizes a technology for adaptively selecting process parameters for printing parts with different overhang angles.

[0136] Furthermore, if Fig.11 As shown, based on the above-mentioned adaptive method for selective laser melting of overhanging structure, the present invention also provides a controller accordingly, and the controller includes a processor 10, a memory 20, and a display 30. Fig.11 Only some of the components of the controller are shown, but it should be understood that implementation of all of the components shown is not required, and more or fewer components may be implemented instead.

[0137] In some embodiments, the memory 20 may be an internal storage unit of the controller, such as a hard disk or memory of the controller. In other embodiments, the memory 20 may also be an external storage device of the controller, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the controller. Furthermore, the memory 20 may also include both an internal storage unit of the controller and an external storage device. The memory 20 is used to store application software and various types of data installed in the controller, such as the program code of the installed controller. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 20 stores an adaptive program 40 for the laser selective melting process of a draped structure, and the adaptive program 40 for the laser selective melting process of a draped structure can be executed by the processor 10, thereby realizing the adaptive method for the laser selective melting process of a draped structure in the present application.

[0138] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the adaptive method of the overhang structure laser selective melting process.

[0139] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the controller and to display a visual user interface. The components 10-30 of the controller communicate with each other via a system bus.

[0140] In one embodiment, the steps implemented when the processor 10 executes the overhang structure laser selective melting process adaptive program 40 in the memory 20 can refer to the corresponding description in the above-mentioned overhang structure laser selective melting process adaptive method, which will not be repeated here.

[0141] In summary, the present invention provides an adaptive method for laser selective melting of an overhang structure and related equipment, the method comprising: generating a three-dimensional model according to an input standard model file of a part to be printed; slicing the three-dimensional model using slicing software to obtain layered slicing data; performing an overhang recognition operation on the slice layers in the layered slicing data to calculate the overhang angle size of the area with overhang characteristics; calculating and optimizing the optimal process parameters according to the overhang angle size and a non-parametric model; and printing the part to be printed according to the optimal process parameters. By using slicing software to slice the three-dimensional model, performing an overhang recognition operation on the obtained slice layers to calculate the overhang angle size, and calculating the optimal process parameters according to the overhang angle size and a non-parametric model, so as to print the part to be printed, the optimal process parameters are adaptively selected according to the parts to be printed with different overhang angles for printing.

[0142] It is understandable that those skilled in the art can make equivalent substitutions or changes based on the technical solution and inventive concept of the present invention, and all these changes or substitutions should fall within the protection scope of the claims attached to the present invention.

Claims

1. An adaptive method for selective laser melting of a suspension structure, characterized in that: The self-adaptive method for the selective laser melting process of the overhanging structure comprises: Generate a three-dimensional model according to an input standard model file of a component to be printed; wherein the standard model file is a file expressed in a standard triangle language; Slicing the three-dimensional model using slicing software to obtain layered slicing data; wherein the slicing software is laser selective melting forming data preparation software; Performing an overhang recognition operation on the slice layers in the layered slice data to calculate the overhang angle of the area with overhang characteristics; Calculate and optimize the optimal process parameters according to the overhang angle and the non-parametric model; wherein the non-parametric model includes a Gaussian process regression model; Printing the to-be-printed component according to the optimal process parameters; The step of performing an overhang recognition operation on the slice layers in the layered slice data to calculate the overhang angle size of the area with overhang feature specifically includes: Use the slicer to generate connecting line segments in each slice layer; Projecting the connecting line segment on the current slice layer onto the next slice layer to obtain a projection line; Splitting the projection line that is longer than a preset length to obtain a split projection line; Calculate the overhang angle at the midpoint of each segmented projection line; The step of calculating and optimizing the optimal process parameters according to the overhang angle and non-parametric model specifically includes: After building the non-parametric model, a full factorial experimental design method is used to obtain sample points as a training data set for the non-parametric model; Obtaining a data validation set for the non-parametric model, and obtaining a correlation coefficient of the non-parametric model using a cross-validation analysis method; A multi-objective optimization problem is constructed according to minimizing deformation and surface roughness, and an optimal solution set of the multi-objective optimization problem is calculated using a multi-objective optimization method; wherein the optimal solution set is the optimal process parameters; The step of calculating the overhang angle at the midpoint of each segmented projection line specifically includes: Taking the connecting line segment as a direction vector and multiplying it by a rotation matrix to obtain a vertical line segment; Calculating the minimum distance between the midpoint and the intersection of the vertical line segment and the next slice layer; The overhang angle is calculated based on the minimum distance and the thickness of the next slice layer; wherein the calculation formula of the overhang angle is: ; where d min is the minimum distance; h is the layer thickness.

2. The adaptive method for selective laser melting of overhanging structure according to claim 1, characterized in that: After the non-parametric model is constructed, the step of using a full factorial experimental design method to obtain sample points as a training data set for the non-parametric model specifically includes: After the non-parametric model is constructed, a first preset amount of laser power and a second preset amount of laser scanning speed are used as variable parameters, and a non-variable parameter is selected; The non-variable parameters include the thickness of the slice layer, the overlap spacing and the inter-layer rotation angle, the printing material and specification, and the material and size of the substrate; the printing material includes titanium alloy, aluminum alloy and high-temperature nickel-based alloy material powder; The variable parameters are applied to a third preset number of to-be-printed parts with overhang angles to obtain data samples as the training data set.

3. The adaptive method for selective laser melting of overhanging structure according to claim 1, characterized in that: The step of obtaining a data validation set for the non-parametric model and obtaining the correlation coefficient of the non-parametric model using a cross-validation analysis method specifically includes: Taking the first preset number of laser powers, the second preset number of laser scanning speeds and the third preset number of overhang angle sizes as interval ranges, randomly selecting a fourth preset number of sample points as the data verification set; The correlation coefficient of the non-parametric model is calculated using the cross-validation analysis method.

4. The adaptive method for selective laser melting of overhanging structure according to claim 2, characterized in that: The steps of constructing a multi-objective optimization problem based on minimizing deformation and surface roughness, and calculating the optimal solution set of the multi-objective optimization problem using a multi-objective optimization method specifically include: Obtaining the minimized deformation and surface roughness of the data sample; Constructing the multi-objective optimization problem with the minimization of deformation and surface roughness as the goal; The optimal solution set of the multi-objective optimization problem is obtained by using a multi-objective optimization method based on an evolutionary algorithm.

5. The adaptive method for selective laser melting of overhanging structure according to claim 2, characterized in that: The step of printing the component to be printed according to the optimal process parameters specifically includes: Grind the surface of the substrate with an angle grinder until there is no oxide, and clean it with an organic cleaning agent; After the printing chamber is evacuated, a protective gas is introduced to make the oxygen content lower than a preset concentration, and the cleaned substrate is preheated to a preset temperature; According to the optimal process parameters, the printing material is printed on the heated substrate in the printing chamber to obtain the component to be printed.

6. An adaptive system for selective laser melting of overhanging structures, characterized in that: The overhang structure laser selective melting process adaptive system comprises: A three-dimensional model generation module, used to generate a three-dimensional model according to an input standard model file of a component to be printed; wherein the standard model file is a file expressed in a standard triangle language; A layered slice data generation module, used for slicing the three-dimensional model using slicing software to obtain layered slice data; wherein the slicing software is laser selective melting forming data preparation software; An overhang angle calculation module is used to perform an overhang recognition operation on the slice layer in the layered slice data to calculate the overhang angle size of the area with overhang characteristics; The step of performing an overhang recognition operation on the slice layers in the layered slice data to calculate the overhang angle size of the area with overhang feature specifically includes: Use the slicer to generate connecting line segments in each slice layer; Projecting the connecting line segment on the current slice layer onto the next slice layer to obtain a projection line; Splitting the projection line that is longer than a preset length to obtain a split projection line; Calculate the overhang angle at the midpoint of each segmented projection line; The step of calculating the overhang angle at the midpoint of each segmented projection line specifically includes: Taking the connecting line segment as a direction vector and multiplying it by a rotation matrix to obtain a vertical line segment; Calculating the minimum distance between the midpoint and the intersection of the vertical line segment and the next slice layer; The overhang angle is calculated based on the minimum distance and the thickness of the next slice layer; wherein the calculation formula of the overhang angle is: ; where d min is the minimum distance; h is the layer thickness; An optimal process parameter calculation module, used to calculate and optimize the optimal process parameters according to the overhang angle and the non-parametric model; wherein the non-parametric model includes a Gaussian process regression model; The step of calculating and optimizing the optimal process parameters according to the overhang angle and non-parametric model specifically includes: After building the non-parametric model, a full factorial experimental design method is used to obtain sample points as a training data set for the non-parametric model; Obtaining a data validation set for the non-parametric model, and obtaining a correlation coefficient of the non-parametric model using a cross-validation analysis method; A multi-objective optimization problem is constructed according to minimizing deformation and surface roughness, and an optimal solution set of the multi-objective optimization problem is calculated using a multi-objective optimization method; wherein the optimal solution set is the optimal process parameters; A printing module is used to print the component to be printed according to the optimal process parameters.

7. A controller, characterized in that: The controller includes: a memory, a processor, a display, and an adaptive program for the laser selective melting process of a drape structure stored in the memory and executable on the processor. When the adaptive program for the laser selective melting process of a drape structure is executed by the processor, the steps of the adaptive method for the laser selective melting process of a drape structure as described in any one of claims 1 to 5 are implemented.

Images