3D printing support setting method and related equipment thereof

Abstract

The invention relates to the technical field of 3D printing, in particular to a 3D printing support setting method and related equipment thereof. The method comprises the steps of obtaining a model file of a 3D printing model; based on a pre-trained supporting body setting model and a model file, supporting structure information of the 3D printing model is determined, the supporting structure information comprises adding information of one or more supporting bodies, and the supporting body setting model is used for extracting global statistical characteristics of the 3D printing model and overhanging area characteristics of the 3D printing model from the model file; determining support structure information of the 3D printing model based on the global statistical characteristics and the suspension area characteristics; and slice configuration information of the 3D printing model is obtained, and a printing parameter file is generated based on the slice configuration information and the supporting structure information. According to the method, whether the support body needs to be added in the overhanging area can be intelligently judged, and the adding efficiency and accuracy of the support body are improved.

Description

Technical Field

[0001] This application relates to the field of three-dimensional (3D) printing technology, specifically to a 3D printing support setup method and related equipment. Background Technology

[0002] 3D printers are rapid prototyping devices. Fused deposition modeling (FDM) is a widely used printing technology in 3D printing, utilizing powdered materials such as metal or plastic to construct three-dimensional objects layer by layer. If the printed product contains overhanging structures, support structures are needed to prevent collapse during printing. However, current printing software requires users to choose whether to add support structures. Inexperienced users may choose not to add support structures when needed, leading to printing failures, or they may add support structures when unnecessary, resulting in wasted printing material. Summary of the Invention

[0003] In view of the above, embodiments of this application provide a 3D printing support setting method and related equipment, which can intelligently determine whether a support body needs to be added, thereby improving the efficiency and accuracy of adding the support body.

[0004] In a first aspect, embodiments of this application provide a 3D printing support setting method, comprising: acquiring a model file of a 3D printing model; determining support structure information of the 3D printing model based on a pre-trained support setting model and the model file, wherein the support structure information includes addition information of one or more supports, the support setting model being used to extract global statistical features and overhang region features of the 3D printing model from the model file, and determining the support structure information of the 3D printing model based on the global statistical features and the overhang region features, wherein the global statistical features are used to indicate the measurement features of the overall model structure of the 3D printing model, and the overhang region features are used to indicate the measurement features of the overhang region in the 3D printing model; acquiring slice configuration information of the 3D printing model, and generating a printing parameter file based on the slice configuration information and the support structure information.

[0005] The above technical solution can intelligently and accurately predict whether the input model structure needs to add a support based on the pre-trained support setting model, as well as the support addition information, thereby improving the efficiency and accuracy of support addition. Subsequently, a printing parameter file is generated based on the slicing configuration information (e.g., slice layer height) and support structure information of the 3D printing model, so that the 3D printer can directly execute the printing of the 3D printing model based on the printing parameter file, thereby improving the printing quality of the 3D printing model.

[0006] In some embodiments, the support structure information includes information on a first overhanging region where a support needs to be added and information on a second overhanging region where a support does not need to be added, determined via the support setting model. Generating a printing parameter file based on the slice configuration information and the support structure information includes: verifying whether each overhanging region in the second overhanging region information needs a support based on a preset verification rule; updating the support structure information based on the verification result; and generating the printing parameter file based on the slice configuration information and the updated support structure information.

[0007] In some embodiments, the preset verification rules include: determining whether the overhanging area to be verified meets preset requirements, the preset requirements including any of the following: whether the ratio of the projected area of ​​the overhanging area to be verified on the XY plane to the projected perimeter meets a first requirement; whether the ratio of the projected area of ​​the overhanging area to be verified on the XY plane to the projected area of ​​the 3D printed model on the XY plane meets a second requirement; whether the absolute values ​​of the length and width of the overhanging area to be verified meet a third requirement, wherein the XY plane is the printing reference plane of the printed model; when the overhanging area to be verified meets the preset requirements and the model confidence is less than a preset value, the overhanging area to be verified is updated from not needing to add a support to needing to add a support, wherein the model confidence is the confidence level of the support setting model in determining that the overhanging area to be verified does not need to add a support.

[0008] In some embodiments, the preset verification rules include: determining the bottom contact area of ​​the 3D printed model and the projected area of ​​the 3D printed model in the XY plane, wherein the bottom contact area is the contact area between the 3D printed model and the XY plane, and the XY plane is the printing reference plane of the printed model; when the ratio of the bottom contact area to the projected area meets the fourth requirement and the model confidence is less than a preset value, updating the overhanging area to be verified from not needing to add a support to needing to add a support, wherein the model confidence is the confidence level of the support setting model in determining that the overhanging area to be verified does not need to add a support.

[0009] In some embodiments, the support structure model is trained through the following steps: obtaining a sample model file set, which includes sample model files of multiple 3D printed model samples; for a first 3D printed model sample among the multiple 3D printed model samples, obtaining the support label of the first 3D printed model sample based on the sample model file of the first 3D printed model sample; determining the normal vectors of all facets of the first 3D printed model sample, and determining the overhang facets of the first 3D printed model sample based on the normal vectors; determining the overhang region contained in the first 3D printed model sample based on the overhang facets; determining the first 3D printed... The overhang region features of each overhang region in the first 3D printed model sample are determined; the overhang region features of each overhang region in the first 3D printed model sample are fused based on a preset attention mechanism to determine the overhang region fusion feature of the first 3D printed model sample; the global statistical features of the first 3D printed model sample are determined; the model training features of the first 3D printed model sample are determined based on the overhang region fusion feature and the global statistical features; a preset machine learning model is trained based on the model training features of each 3D printed model sample and the support label to determine the support setting model.

[0010] In some embodiments, determining the overhang region contained in the first 3D printed model sample based on the overhanging surface includes: establishing an index adjacency table for each overhanging surface in the first 3D printed model sample, wherein the index adjacency table records the indices of each overhanging surface adjacent to the current overhanging surface; performing an overhanging surface search based on the index adjacency table to determine whether the angle between the searched overhanging surface and the current overhanging surface is less than a preset angle; if the angle is determined to be less than the preset angle, classifying the searched overhanging surface as belonging to the same overhang region as the current overhanging surface.

[0011] In some embodiments, after determining the overhanging patches of the first 3D printed model sample based on the normal vector, the method further includes: obtaining the tilt angle of each overhanging patch in the first 3D printed model sample; dividing the overhanging patches contained in the first 3D printed model sample into multiple categories based on the tilt angle, and determining the number of overhanging patches in each category; generating overhanging patch tilt statistical features of the first 3D printed model sample based on the number of overhanging patches in each category; and determining the model training features of the first 3D printed model sample based on the overhanging region fusion features and global statistical features of the first 3D printed model sample, including: fusing the global statistical features and overhanging patch tilt statistical features of the first 3D printed model sample to determine global statistical fusion features; and determining the model training features of the first 3D printed model sample based on the overhanging region fusion features and global statistical fusion features.

[0012] In some embodiments, the overhanging region features include one or more of the following: the area of ​​the overhanging region, the centroid of the overhanging region, the minimum and maximum coordinates of the overhanging region in the XYZ directions, the average normal vector of the overhanging region, the standard deviation of the normal vector of the overhanging region, the average Z coordinate of the overhanging region, the projected area of ​​the overhanging region on the XY plane, the projected perimeter of the overhanging region on the XY plane, the ratio of the projected area of ​​the overhanging region on the XY plane to the surface area of ​​the printed model, and the compactness of the overhanging region; the global statistical features include one or more of the following: the complexity of the printed model, the size and aspect ratio of the bounding box of the printed model, the spatial structural features of the printed model, the normal vector distribution features of the printed model, the Z coordinate range of the printed model, the features of the bottom contact surface of the printed model, and the curvature of the printed model.

[0013] Secondly, embodiments of this application also provide a 3D printing support setting device, comprising: an acquisition module for acquiring a model file of a 3D printing model; a determination module for determining the support structure information of the 3D printing model based on a pre-trained support setting model and the model file, wherein the support structure information includes addition information of one or more supports, the support setting model being used to extract global statistical features and overhang region features of the 3D printing model from the model file, and to determine the support structure information of the 3D printing model based on the global statistical features and the overhang region features, wherein the global statistical features are used to indicate the measurement features of the overall model structure of the 3D printing model, and the overhang region features are used to indicate the measurement features of the overhang region in the 3D printing model; and a generation module for acquiring slice configuration information of the 3D printing model, and generating a printing parameter file based on the slice configuration information and the support structure information.

[0014] Thirdly, embodiments of this application also provide a computer device, the computer device including a processor and a memory, the memory being used to store instructions, and the processor being used to call the instructions in the memory, causing the computer device to execute the 3D printing support setting method as described in the first aspect.

[0015] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the 3D printing support setting method as described in the first aspect.

[0016] One of the above technical solutions has the following advantages or beneficial effects: it can intelligently and accurately predict whether the input model structure needs to add a support body based on the pre-trained support body setting model, as well as the support body addition information, thereby improving the efficiency and accuracy of support body addition. Subsequently, a printing parameter file is generated based on the slicing configuration information and support structure information of the 3D printing model, so that the 3D printer can directly execute the printing of the 3D printing model based on the printing parameter file, thereby improving the printing quality of the 3D printing model. Attached Figure Description

[0017] Figure 1 This is a schematic diagram illustrating the training steps of a support structure model provided in an embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating one step of a 3D printing support setting method provided in an embodiment of this application.

[0019] Figure 3 A flowchart illustrating one step of a 3D printing support setting method provided in another embodiment of this application.

[0020] Figure 4 This is a schematic diagram of the functional modules of a 3D printing support setting device provided in an embodiment of this application.

[0021] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0022] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0023] Numerous specific details are set forth in the following description to provide a full understanding of this application. The described embodiments are only a part of, and not all, of the embodiments of this application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0024] It should be further noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0025] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence. In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0026] Due to the diversity of models, some parts of the model may be suspended, meaning there is no support underneath. During printing, these unsupported parts may sink or fall off, which can reduce print quality or even cause print failure. Therefore, it is necessary to add support to these suspended parts.

[0027] Based on this, embodiments of this application provide a 3D printing support setting method and related equipment, which can automatically and accurately set the support body and improve the printing quality of 3D models.

[0028] The 3D printing support setting method of this application can be applied to computer devices. For example, when slicing a 3D printed model, the computer device can intelligently determine whether a support needs to be added to the overhanging area based on the 3D printing support setting method. The computer device can also communicate with the 3D printer to transmit the generated printing parameter file (e.g., G-code file) to the 3D printer, enabling the 3D printer to perform printing of the 3D printed model based on the printing parameter file. The 3D printer in this application embodiment can be a 3D printer supporting fused deposition modeling (FDM) technology or other 3D printing technologies. The computer device in this application embodiment can be a desktop computer, laptop computer, industrial computer, server, or other similar device.

[0029] In some embodiments, the computer device of this application may be deployed with slicing software and a pre-trained support structure model. The slicing software can be used to slice the model file, and the support structure model can be used to intelligently determine the addition information of the support structure based on the model file.

[0030] The training steps of the support structure model provided in this application embodiment will be described in detail below.

[0031] Please see Figure 1 As shown, Figure 1 This is a flowchart illustrating the training steps of an embodiment of the support structure model provided in this application. The trained support structure model can also be quantized and then deployed on a computer device. Depending on different needs... Figure 1 The order of steps in the flowchart shown can be changed, and some steps can be omitted or combined.

[0032] The training process for this support structure model may include the following steps: S101, Obtain the sample model file set, which includes sample model files of multiple 3D printed model samples.

[0033] In the following embodiments, the sample model file may be a 3MF (3D Manufacturing Format) file, an STL (Standard Tessellation Language) file, etc., and this application embodiment does not limit this. The following example uses a 3MF format sample model file.

[0034] In some embodiments, after obtaining the sample model file set, the sample model files in the sample model file set can be further divided into a training set and a test set, or a training set, a test set, and a validation set. Each sample model file can be processed in a similar manner to extract features for model training.

[0035] In some embodiments, a sample model file may include a single model object (i.e., a 3D printed model sample), or it may include two or more model objects. When a sample model file includes multiple model objects, the model data for each model object can be split, and subsequent model training feature extraction will target the model data of a single model object.

[0036] The following explanation uses the example of the first sample model file in the sample model file set containing only one model object (the first sample model file includes the first 3D printed model sample). The processing of other sample model files can be carried out in the same way as the first sample model file. If other sample model files contain multiple model objects, the model data can be split first so that one sample model file contains one model object.

[0037] S102, based on the first sample model file of the first 3D printed model sample, obtain the support label of the first 3D printed model sample.

[0038] In some embodiments, each sample model file in the sample model file set may be a sample model file that has been configured with support information. The support label of the first 3D printed model sample can be obtained by parsing the first sample model file.

[0039] For example, by parsing the first sample model file, parameters such as the vertex coordinates, the vertices to which the facets (e.g., triangular facets) belong, the rotation matrix of the facets, whether the facets have open supports, and the type of open supports can be obtained from the first sample model file. For example, the vertex coordinates, the vertices to which the facets belong, the rotation matrix of the facets, whether the facets have open supports, and the type of open supports can be obtained from the first sample model file through field matching.

[0040] S103, determine the normal vectors of all facets of the first 3D printed model sample, and determine the overhang facets of the first 3D printed model sample based on the normal vectors.

[0041] In some embodiments, the overhanging facets included in the first 3D printed model sample can be determined by calculating the normal vectors of all facets in the first 3D printed model sample and then based on the normal vectors of each facet. Specifically, the normal vector of each facet can be calculated using methods described in related technologies, which will not be elaborated upon in this embodiment. For example, the normal vector of each facet can be calculated using the Trimesh library (a core library in Python for processing 3D mesh data). After obtaining the normal vectors of all facets, facets that simultaneously meet the following three conditions can be identified as overhanging facets: (a) The angle between the normal vector of the face and the direction of gravity (vertically downward) is less than a first preset angle, for example, the first preset angle is 30° or 45°, which indicates that the current face is tilted downward more obviously; (b) The Z component of the normal vector of the patch is less than 0, which means that the current patch is oriented downwards, and the Z direction is the printing direction; (c) The Z coordinates of the three vertices of the patch are all greater than the minimum Z coordinate in the printing model, which means that the current patch is not a patch with its bottom attached to the printing platform; In some embodiments, the overhanging sheet may be determined based solely on condition (a), or a combination of condition (a) and condition (c).

[0042] S104, determine the overhang area contained in the first 3D printed model sample based on the overhang patch.

[0043] In some embodiments, the overhang region can be considered as a region formed by the aggregation of overhang patches. After determining the overhang patches contained in the first 3D printed model sample, the overhang region contained in the first 3D printed model sample can be further determined based on the determined overhang patches.

[0044] Specifically, determining the overhang region contained in the first 3D printed model sample based on the overhang patch may include: (1) Establish an index adjacency table for each overhanging facet in the first 3D printed model sample. The index adjacency table records the indexes of each overhanging facet adjacent to the current overhanging facet. (2) Based on the index adjacency list, perform a drooping face search to determine whether the angle between the searched drooping face and the current drooping face is less than the second preset angle. (3) If the included angle is determined to be less than the second preset angle, the searched overhanging surface is classified as belonging to the same overhanging region as the current overhanging surface. The second preset angle can be set according to actual needs, and this application embodiment does not limit it. For example, the second preset angle is 15°.

[0045] (4) If the included angle is determined to be no less than the second preset angle, it is considered that the searched hanging surface and the current hanging surface do not belong to the same hanging area.

[0046] In some embodiments, for each overhanging surface, a depth-first search algorithm can be used to find each overhanging surface adjacent to the current overhanging surface, and determine whether the angle between the found overhanging surface and the current overhanging surface is less than 15°. If so, it is included in the same overhanging region. Based on this method, overhanging regions with relatively smooth transitions can be formed.

[0047] In some embodiments, the tilt angle (i.e., the angle between the normal vector and the direction of gravity) of each overhanging surface in the first 3D printed model sample can be obtained. Based on the tilt angle, the overhanging surfaces contained in the first 3D printed model sample can be divided into multiple categories, the number of overhanging surfaces in each category can be determined, and then the overhanging surface tilt statistical features of the first 3D printed model sample can be generated based on the number of overhanging surfaces in each category. The overhanging surface tilt statistical features can be used for subsequent training of the support structure model. In other embodiments, the overhanging surface tilt statistical features may not be used to train the support structure model.

[0048] In some embodiments, taking a first preset angle of 30° as an example, determining the number of overhanging sheets in each category can be done by dividing the overhanging sheets into three categories according to the tilt angles of 0~5°, 5°~25°, and 25°~30°, and counting the number of overhanging sheets in each category.

[0049] S105, Determine the overhang region characteristics of each overhang region in the first 3D printed model sample.

[0050] In some embodiments, after determining the various overhang regions in the first 3D printed model sample, each overhang region can be processed separately to determine the overhang region characteristics of each overhang region. The overhang region characteristics are used to indicate the metric features of the overhang region.

[0051] For example, the overhang region characteristics may include one or more of the following features: a. The area of ​​the overhanging region, which can be the sum of the areas of all the overhanging patches contained within the overhanging region; b. The centroid of the overhanging area, the minimum and maximum coordinates of the overhanging area in the XYZ directions, where the XY plane can be the printing reference plane of the printed model, that is, the printed model is sliced ​​along the Z-axis, and the printed model is cut into a series of slices parallel to the XY plane. In some embodiments, the centroid of the overhanging region can be determined as follows: the centroid of each overhanging surface is obtained by averaging the X, Y, and Z coordinates of the three vertices of each overhanging surface in the overhanging region; then, the centroids are weighted according to the area of ​​each overhanging surface to obtain the centroid of the overhanging region. The minimum and maximum coordinates of the overhanging region in the X, Y, and Z directions can be determined as follows: the minimum and maximum coordinates in the X, Y, and Z directions are determined based on the X, Y, and Z coordinates of the three vertices of each overhanging surface in the overhanging region.

[0052] c. Average normal vector of the overhanging region, standard deviation of the normal vector of the overhanging region, and average Z-coordinate of the overhanging region; In some embodiments, since the normal vector of each patch can be calculated previously using the Trimesh library, i.e., the normal vector of each overhanging patch in the overhanging region can be calculated previously, the average normal vector and the standard deviation of the overhanging region's normal vector are then determined based on the normal vector of each overhanging patch in the overhanging region. The average Z-coordinate of the overhanging region can be determined based on the Z-coordinates of the three vertices of each overhanging patch in the overhanging region.

[0053] d. The projected area and perimeter of the overhanging region on the XY plane; In some embodiments, the projected area and projected perimeter of the overhanging region on the XY plane can be determined as follows: the XY coordinates of the three vertices of all overhanging patches in the overhanging region are selected as the projections on the XY plane, and the convex hull information of the projection on the XY plane (a convex polygon formed by connecting the outermost points, containing all vertices) is obtained through a third-party library. Based on this convex hull information, the volume attribute represents the projected area of ​​the overhanging region on the XY plane, and the area attribute represents the projected perimeter of the overhanging region on the XY plane.

[0054] e. The ratio of the projected area of ​​the overhanging region on the XY plane to the surface area of ​​the printed model; In some embodiments, the surface area of ​​the printed model can be the sum of the areas of all the facets contained in the printed model (e.g., a first 3D printed model sample).

[0055] f. Compactness of the overhanging area.

[0056] In some embodiments, the compactness of the overhanging region can be represented by the ratio of the square of the projected perimeter (projected perimeter in the XY plane) of the overhanging region to the projected area (projected area in the XY plane).

[0057] S106, Based on a preset attention mechanism, the overhang region features of each overhang region in the first 3D printed model sample are fused to determine the overhang region fusion features of the first 3D printed model sample.

[0058] In some embodiments, the first 3D printed model sample may include multiple overhang regions. Through the above steps, each overhang region can obtain corresponding overhang region features. Overhang region fusion features can refer to features obtained by fusing the overhang region features of all overhang regions. The overhang region fusion features can be obtained by fusing the overhang region features of multiple overhang regions through a preset attention mechanism.

[0059] For example, the overhang region fusion features can be determined as follows: Since the calculation method of the overhang region features of each overhang region is consistent, the feature dimensions of the obtained overhang region features are the same (assuming F feature dimensions). Taking the first 3D printing model sample, which includes N overhang regions, as an example, the desired fusion feature dimension is set as output_dim (for example, the dimension of the overhang region fusion feature is set to 16 dimensions). Based on the above-defined input and output, an attention fusion network is established based on a deep learning algorithm. The input features are (N, F), and the output feature dimension is output_dim. The feature fusion network is trained to obtain the feature fusion network. Then, based on the overhang region features of multiple overhang regions of subsequent printing models, the overhang region fusion features of a fixed dimension can be obtained. That is, for different printing models, even if the number of overhang regions is different, the overhang region fusion features of the same dimension can be obtained.

[0060] S107, Determine the global statistical characteristics of the first 3D printed model sample.

[0061] In some embodiments, global statistical features of the first 3D printed model sample can be determined based on a first sample model file of the first 3D printed model sample. Global statistical features are used to indicate the quantitative characteristics of the overall model structure of the printed model.

[0062] For example, global statistical features may include one or more of the following features: a. Print model complexity; In some embodiments, model complexity may be represented by the number of faces and / or the number of vertices.

[0063] b. The dimensions and proportions of the printed model's bounding box; In some embodiments, the bounding box of the printed model can be the bounding box of a first 3D printed model sample. The size of the bounding box may include its dimensions in the X, Y, and Z directions, and the proportions of the bounding box may include one or more of its aspect ratio, length-to-width ratio, and height-to-width ratio. For example, the bounding box of the printed model and its related attribute data can be determined based on the Trimesh library.

[0064] c. Spatial structural features of the printed model; In some embodiments, the spatial structural features of the printed model can be characterized by one or more of the following: the centroid height of the printed model, the Z-coordinate distribution of the vertices, and the Z-coordinate distribution of the center points of the facets.

[0065] d. Characteristics of the normal vector distribution of the printed model; In some embodiments, the normal vector distribution characteristics of the printed model can be determined by the average direction of the normal vectors (average normal vector) and the standard deviation of the normal direction. The average direction of the normal vectors can be the direction obtained by averaging the normal vectors of all facets. The standard deviation of the normal direction can be the degree of dispersion of the normal vectors of all facets relative to the average normal vector, which can be achieved by calculating the angle between the normal vector of each facet and the average normal vector, and then calculating the standard deviation of all angles.

[0066] e. The Z-coordinate range of the printed model; In some embodiments, the Z-coordinate range may include the maximum value, minimum value, and Z-coordinate fluctuation range (e.g., the difference between the maximum and minimum values).

[0067] f. Features of the bottom contact surface of the printed model; In some embodiments, the bottom contact surface of the printed model may refer to the contact surface between the printed model and the printing reference plane. Characteristics of the bottom contact surface may include the number of vertices and its area.

[0068] g. The curvature of the printed model; In some embodiments, the curvature of the printed model can be characterized by the average of the angles between all adjacent facets (the mean facet angle).

[0069] S108, Based on the overhang region fusion features and global statistical features of the first 3D printed model sample, determine the model training features of the first 3D printed model sample.

[0070] In some embodiments, after determining the overhang region fusion features and global statistical features of the first 3D printed model sample, model training features of the first 3D printed model sample can be determined based on the overhang region fusion features and global statistical features. For example, the dimension of the global statistical features is F1, and the dimension of the overhang region fusion features is F2. The overhang region fusion features and global statistical features are concatenated to obtain model training features of dimension F1+F2, which are then used as feature inputs for subsequent machine learning models.

[0071] In some embodiments, the statistical features of the overhanging surface tilt can also be used for model training. Specifically, determining the model training features of the first 3D printed model sample based on the overhanging region fusion features and global statistical features of the first 3D printed model sample may further include: fusing the global statistical features and the overhanging surface tilt statistical features of the first 3D printed model sample to determine global statistical fusion features; and determining the model training features of the first 3D printed model sample based on the overhanging region fusion features and global statistical fusion features. For example, if the dimension of the global statistical fusion features is F3, the model training features with a dimension of F3+F2 can be obtained by concatenating the overhanging region fusion features and the global statistical fusion features. The model training features serve as the feature input for subsequent machine learning models.

[0072] In some embodiments, fusing the global statistical features and the overhang tilt statistical features of the first 3D printed model sample to determine the global statistical fusion feature may include: concatenating the global statistical features and the overhang tilt statistical features to obtain the global statistical fusion feature. For example, if the dimension of the global statistical features is F1 and the dimension of the overhang tilt statistical features is F4, concatenating the global statistical features and the overhang tilt statistical features yields a global statistical fusion feature with dimension F1+F4. In other embodiments, the fusion of the global statistical features and the overhang tilt statistical features may also be achieved based on an attention mechanism.

[0073] S109, Based on the model training features and support labels of each 3D printed model sample in multiple 3D printed model samples, a preset machine learning model is trained to determine the support setting model.

[0074] In some embodiments, the model training features of the first 3D printed model sample can be determined through the above steps. For other printed model samples, the model training features of each printed model sample can be determined in the same manner as described above. After obtaining the model training features of each printed model sample, a preset machine learning model can be trained based on the model training features and the support body label to determine the support body setting model. For example, the model training features and support body label of each printed model sample can be combined into a training feature pair, and the preset machine learning model can be trained based on multiple training feature pairs.

[0075] For example, the optimal parameter combination can be found in the parameter space based on the random forest classification algorithm. Then, the model can be trained based on the optimal parameters and training features to obtain the support model. Specifically, the training features of the training set can be used to train the model, and the training features of the test set can be used to test the trained model. If the test results do not meet the requirements, the model parameters can be adjusted, and training and testing can be repeated until a model that meets the requirements is obtained. This model that meets the requirements can be used as the support model.

[0076] The above method can be used to train a support setting model, learn various printed model structures and the implicit relationship between them and whether or not a support needs to be added, and then intelligently and accurately predict whether the input model structure needs to be added with a support, as well as the information on adding the support.

[0077] In some embodiments, after training the support configuration model, the support configuration model can be used to infer the model file to be processed to determine the support addition information.

[0078] The following describes in detail the steps and flow of the 3D printing support setting method provided in the embodiments of this application.

[0079] Please refer to the following: Figure 2 As shown, Figure 2 This is a flowchart illustrating the steps of an embodiment of the 3D printing support setting method provided in this application. The 3D printing support setting method can be applied to computer devices. Depending on different needs... Figure 2 The order of steps in the flowchart shown can be changed, and some steps can be omitted or combined.

[0080] The 3D printing support setup method may include the following steps: Step S201: Obtain the model file of the 3D printed model.

[0081] In some embodiments, by obtaining the model file of the 3D printed model to be printed, it is convenient to use the support to set the model and reason about the model file to determine the support addition information.

[0082] Step S202: Based on the pre-trained support body setting model and model file, determine the support structure information of the 3D printing model. The support structure information includes the addition information of one or more supports. The support body setting model is used to extract the global statistical features and the overhang region features of the 3D printing model from the model file, and determine the support structure information of the 3D printing model based on the global statistical features and the overhang region features.

[0083] In some embodiments, global statistical features are used to indicate the metrological characteristics of the overall model structure of the 3D printed model, and overhang region features are used to indicate the metrological characteristics of the overhang regions in the 3D printed model.

[0084] In some embodiments, after obtaining the model file of the 3D printed model, the support structure information of the 3D printed model can be determined based on a pre-trained support setting model and the model file. For example, the model file can be input into the support setting model, which extracts the global statistical features and overhang region features of the 3D printed model from the model file, and determines the support structure information of the 3D printed model based on the global statistical features and overhang region features. For example, the support setting model can extract the global statistical features and overhang region features of the 3D printed model from the model file by executing the above steps S103~S107.

[0085] In some embodiments, the features extracted from the model file by the support structure model may further include statistical features of the overhanging surface tilt. The support structure model determines the support structure information of the 3D printed model based on global statistical features, overhanging region features, and overhanging surface tilt statistical features. For example, overhanging region fusion features can be determined first based on the overhanging region features of each overhanging region, global statistical fusion features can be determined based on global statistical features and overhanging surface tilt statistical features, and then the support structure information of the 3D printed model can be determined based on the global statistical fusion features and overhanging region fusion features.

[0086] In some embodiments, feature extraction can also be achieved by training a feature extraction network, and then the extracted features can be input into the support model for inference.

[0087] For example, training a feature extraction network can extract global statistical features, overhang region features, and overhang surface tilt statistical features from the model file. Then, based on the global statistical features, overhang region features, and overhang surface tilt statistical features, the overhang region fusion features and global statistical fusion features can be determined. Subsequently, the overhang region fusion features and global statistical fusion features can be directly input into the support body setting model to determine the support structure information of the 3D printing model.

[0088] In some embodiments, the training feature extraction network can also be integrated into the support structure model. In this case, the support structure model can directly determine the support structure information of the 3D printed model based on the model file of the 3D printed model.

[0089] Step S203: Obtain the slice configuration information of the 3D printing model, and generate a printing parameter file based on the slice configuration information and support structure information.

[0090] In some embodiments, the printing parameter file can be a file recognizable by the 3D printer. After determining the support structure information of the 3D printed model, the printing parameter file can be generated based on the slicing configuration information (e.g., slice layer height) and support structure information of the 3D printed model. For example, the printing parameter file is a G-code file, enabling the 3D printer to perform printing of the 3D printed model based on the printing parameter file. The slice configuration information can be set manually by the user or automatically by the slicing software. For example, the slicing software can automatically set the slice configuration information for different consumables (PLA, ABS, PETG, etc.) and different 3D printer models.

[0091] Compared with the prior art, the embodiments of this application have at least the following advantages: In this embodiment, the support structure setting model can intelligently and accurately predict whether the input model structure needs to be supported and the support addition information based on the pre-trained support structure setting model, thereby improving the efficiency and accuracy of support addition. Subsequently, a printing parameter file is generated based on the slicing configuration information and support structure information of the 3D printing model, so that the 3D printer can directly execute the printing of the 3D printing model based on the printing parameter file, thereby improving the printing quality of the 3D printing model.

[0092] Please refer to Figure 3 This is a flowchart illustrating the steps of another embodiment of the 3D printing support setting method provided in this application. The 3D printing support setting method can be applied to computer devices. Depending on different needs... Figure 3 The order of steps in the flowchart shown can be changed, and some steps can be omitted or combined.

[0093] Step S301: Obtain the model file of the 3D printed model.

[0094] Step S301 in this embodiment is similar to step S201 in the previous embodiment. To avoid repetition, it will not be described again here.

[0095] Step S302: Based on the pre-trained support body setting model and model file, determine the support structure information of the 3D printing model. The support structure information includes the information of the first overhang area where a support body needs to be added and the information of the second overhang area where a support body does not need to be added, determined by the support body setting model.

[0096] In some embodiments, for each overhanging region of a 3D printed model, the support setting model may infer whether a support needs to be added or not. The information of the overhanging region that needs to be added can be classified as the first overhanging region information, and the information of the overhanging region that does not need to be added can be classified as the second overhanging region information.

[0097] Step S303: Based on preset verification rules, verify whether each suspension area in the second suspension area information needs to be supported.

[0098] In some embodiments, during the investigation and analysis of whether the model structure needs a support, there are some overhanging areas that obviously need support. Corresponding preset verification rules can be defined for secondary verification and judgment to reduce the possibility of misjudgment in the model with support, and minimize the prediction that overhanging areas that need support do not need support, which could lead to the collapse of the overhanging areas, thereby further improving the printing quality of the printed model.

[0099] Specifically, for suspended areas that are inferred from the support setting model as not requiring additional support, the need for additional support can be re-verified for each suspended area in the second suspended area information based on preset verification rules. For example, each overhanging region in the second overhanging region information can be verified sequentially. The preset verification rules may include: determining whether the overhanging region to be verified meets preset requirements. The preset requirements may include any of the following: whether the ratio of the projected area of ​​the overhanging region to be verified on the XY plane to the projected perimeter (representing the shape of the overhanging region) meets the first requirement; whether the ratio of the projected area of ​​the overhanging region to be verified on the XY plane to the projected area of ​​the 3D printed model on the XY plane (representing the relative size of the overhanging region) meets the second requirement; and whether the absolute value of the length and the absolute value of the width of the overhanging region to be verified (representing the actual size of the overhanging region) meets the third requirement. If the overhanging region to be verified meets the preset requirements and the model confidence is less than the preset value, the overhanging region to be verified is updated from "no support needs to be added" to "support needs to be added". The model confidence is the confidence level of the overhanging region to be verified that does not need to be added. The first, second, and third requirements can all be set according to actual needs, and this application embodiment does not limit them. For example, the first requirement is that the ratio of the projected area of ​​the overhanging region to be verified on the XY plane to its projected perimeter is greater than a first threshold; the second requirement is that the ratio of the projected area of ​​the overhanging region to be verified on the XY plane to the projected area of ​​the 3D printed model on the XY plane is greater than a second threshold; and the third requirement is that the absolute values ​​of the length and width of the overhanging region to be verified are both greater than the corresponding preset length and preset width. The various judgment thresholds can be dynamically adjusted according to actual needs. The preset values ​​can also be set according to actual needs, and this application embodiment does not limit them. For example, the preset value can be set to 0.7 or 0.8.

[0100] In some embodiments, for a support setting model, the inference result may include support prediction information for the overhanging area and the confidence level of the support prediction information.

[0101] In some embodiments, the requirement that the overhanging area to be verified meets the preset requirements can mean that it meets the above three conditions at the same time: the ratio of the projected area of ​​the overhanging area to be verified on the XY plane to the projected perimeter meets the first requirement; the ratio of the projected area of ​​the overhanging area to be verified on the XY plane to the projected area of ​​the 3D printed model on the XY plane meets the second requirement; and the absolute values ​​of the length and width of the overhanging area to be verified meet the third requirement.

[0102] For example, the preset verification rules may also include: determining the bottom contact area of ​​the 3D printed model and the projected area of ​​the 3D printed model in the XY plane, wherein the bottom contact area can be the contact area between the 3D printed model and the XY plane; if the ratio of the bottom contact area to the projected area meets the fourth requirement and the model confidence is less than the preset value, the overhanging area to be verified is updated from "no support required" to "support required". The fourth requirement can be set according to actual needs, and this application embodiment does not limit it. For example, the fourth requirement is that the ratio of the bottom contact area to the projected area is greater than the third threshold.

[0103] Using the above method, when the inference result of the support setting model predicts that no support is needed and the confidence level is less than the preset value, if it is determined that the ratio of the bottom contact area of ​​the model object to the overall projected area is greater than the third threshold, or if it is determined that the overhanging area has a large overhanging structure (the overhanging area to be verified meets the preset requirements), the final inference result will be adjusted from no support needed to support needed.

[0104] Step S304: Update the support structure information based on the verification results.

[0105] After obtaining the verification results of each overhang region in the second overhang region information, the support structure information can be updated based on the verification results to minimize the prediction that overhang regions that require support are not required.

[0106] Step S305: Obtain the slice configuration information of the 3D printing model, and generate a printing parameter file based on the slice configuration information and the updated support structure information.

[0107] In some embodiments, after updating the support structure information, a printing parameter file can be generated based on the slice configuration information of the 3D printing model and the updated support structure information.

[0108] Compared with the prior art, the embodiments of this application have at least the following advantages: In this embodiment, a pre-trained support structure setting model can intelligently and accurately predict whether the input model structure needs to add support, as well as the support addition information, thereby improving the efficiency and accuracy of support addition. Furthermore, it compensates for model misjudgments through preset verification rules, correcting inference results that may be misjudged as not needing support when they actually require it, reducing the impact of such misjudgments on the printing task. Subsequently, a printing parameter file is generated based on the slicing configuration information of the 3D printing model and the updated support structure information, enabling the 3D printer to directly execute the printing of the 3D printing model based on the printing parameter file, thus improving the printing quality of the 3D printing model.

[0109] Please see Figure 4 This application provides a 3D printing support device 200. For example... Figure 4 As shown, the 3D printing support device 200 includes: Module 2001 is used to acquire the model file of the 3D printed model.

[0110] The determination module 2002 is used to determine the support structure information of the 3D printed model based on the pre-trained support setting model and the model file. The support structure information includes the addition information of one or more supports. The support setting model is used to extract the global statistical features and the overhang region features of the 3D printed model from the model file, and to determine the support structure information of the 3D printed model based on the global statistical features and the overhang region features. The global statistical features are used to indicate the measurement features of the overall model structure of the 3D printed model, and the overhang region features are used to indicate the measurement features of the overhang region in the 3D printed model.

[0111] The generation module 2003 is used to obtain the slice configuration information of the 3D printing model and generate a printing parameter file based on the slice configuration information and support structure information.

[0112] The aforementioned modules can be programmable software instructions stored in memory and executable by the processor. It is understood that in other embodiments, the aforementioned modules can also be program instructions or firmware embedded in the processor.

[0113] Figure 5 This is a schematic diagram of an embodiment of the computer device of this application.

[0114] The computer device 1000 includes a memory 1001, a processor 1002, and a computer program 1003 stored in the memory 1001 and executable on the processor 1002. The processor 1002 is used to implement the steps in the above-described 3D printing support setting method embodiment when executing the computer program 1003.

[0115] In some embodiments, the computer device 1000 may communicate with the 3D printer. In other embodiments, as 3D printing technology evolves, the computer device 1000 may also be integrated into the 3D printer.

[0116] For example, computer program 1003 can also be divided into one or more modules / units, which are stored in memory 1001 and executed by processor 1002. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of computer program 1003 in computer device 1000.

[0117] Those skilled in the art will understand that the schematic diagram is merely an example of the computer device 1000 and does not constitute a limitation on the computer device 1000. It may include more or fewer components than shown, or combine certain components, or different components. For example, the computer device 1000 may also include input / output devices, network access devices, buses, etc.

[0118] Processor 1002 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), etc. General-purpose processors can be microprocessors, single-chip microcomputers, or any conventional processor.

[0119] The memory 1001 can be used to store computer programs 1003 and / or modules / units. The processor 1002 implements various functions of the computer device 1000 by running or executing the computer programs and / or modules / units stored in the memory 1001 and by calling data stored in the memory 1001. The memory 1001 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0120] This application also provides a computer-readable storage medium that stores computer instructions that, when executed on a computer device, cause the computer device to perform the 3D printing support setting method described above.

[0121] If the modules / units integrated in the computer device 1000 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), etc.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed computer devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and other division methods may be used in actual implementation.

[0123] Furthermore, the functional units in the various embodiments of this application can be integrated into the same processing unit, or each unit can exist physically separately, or two or more units can be integrated into the same unit. The integrated units described above can be implemented in hardware or in the form of hardware plus software functional modules.

[0124] Compared with the prior art, the embodiments of this application have at least the following advantages: This application embodiment can intelligently and accurately predict whether the input model structure needs to add a support based on the pre-trained support setting model, as well as the support addition information, thereby improving the efficiency and accuracy of support addition. Subsequently, a printing parameter file is generated based on the slicing configuration information and support structure information of the 3D printing model, so that the 3D printer can directly execute the printing of the 3D printing model based on the printing parameter file, thereby improving the printing quality of the 3D printing model.

[0125] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects. Multiple units described in the apparatus, or the apparatus itself, may also be comprised of the same unit, or the apparatus may be implemented by software or hardware.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for setting up a support in 3D printing, characterized in that, The method includes: Obtain the model file of the 3D printed model; Based on a pre-trained support structure model and the model file, the support structure information of the 3D printed model is determined. The support structure information includes the addition information of one or more supports. The support structure model is used to extract the global statistical features and the overhang region features of the 3D printed model from the model file, and to determine the support structure information of the 3D printed model based on the global statistical features and the overhang region features. The global statistical features are used to indicate the measurement characteristics of the overall model structure of the 3D printed model, and the overhang region features are used to indicate the measurement characteristics of the overhang region in the 3D printed model. Obtain the slice configuration information of the 3D printing model, and generate a printing parameter file based on the slice configuration information and the support structure information.

2. The 3D printing support setting method as described in claim 1, characterized in that, The support structure information includes information on a first overhanging region where a support needs to be added and information on a second overhanging region where a support does not need to be added, determined by the support setting model. The step of generating a printing parameter file based on the slice configuration information and the support structure information includes: Based on preset verification rules, the system verifies whether each suspended region in the second suspended region information needs to be supported. The supporting structure information is updated based on the verification results; The printing parameter file is generated based on the slice configuration information and the updated support structure information.

3. The 3D printing support setting method as described in claim 2, characterized in that, The preset verification rules include: Determine whether the overhanging area to be verified meets the preset requirements, which include any of the following: whether the ratio of the projected area of ​​the overhanging area to be verified on the XY plane to the projected perimeter meets the first requirement; whether the ratio of the projected area of ​​the overhanging area to be verified on the XY plane to the projected area of ​​the 3D printed model on the XY plane meets the second requirement; whether the absolute values ​​of the length and width of the overhanging area to be verified meet the third requirement; and the XY plane is the printing reference plane of the printed model. If the overhanging area to be verified meets the preset requirements and the model confidence is less than the preset value, the overhanging area to be verified is updated from not needing to add a support to needing to add a support. The model confidence is the confidence level of the support setting model in determining that the overhanging area to be verified does not need to add a support. Alternatively, the preset verification rules include: Determine the bottom contact area of ​​the 3D printed model and the projected area of ​​the 3D printed model in the XY plane. The bottom contact area is the contact area between the 3D printed model and the XY plane, and the XY plane is the printing reference plane of the printed model. If the ratio of the bottom contact area to the projected area meets the fourth requirement and the model confidence is less than the preset value, the overhanging area to be verified is updated from not needing to add a support to needing to add a support. The model confidence is the confidence level of the support setting model in determining that the overhanging area to be verified does not need to add a support.

4. The 3D printing support setting method as described in claim 1, characterized in that, The support structure model is trained through the following steps: Obtain a sample model file set, which includes sample model files of multiple 3D printed model samples; For the first 3D printed model sample among the plurality of 3D printed model samples, the support label of the first 3D printed model sample is obtained based on the sample model file of the first 3D printed model sample; Determine the normal vectors of all facets of the first 3D printed model sample, and determine the overhang facets of the first 3D printed model sample based on the normal vectors; The overhanging area contained in the first 3D printed model sample is determined based on the overhanging surface. Determine the overhang region characteristics of each overhang region in the first 3D printed model sample; Based on a preset attention mechanism, the overhang region features of each overhang region in the first 3D printed model sample are fused to determine the overhang region fusion features of the first 3D printed model sample. Determine the global statistical characteristics of the first 3D printed model sample; Based on the overhang region fusion features and global statistical features of the first 3D printed model sample, the model training features of the first 3D printed model sample are determined. The preset machine learning model is trained based on the model training features and support labels of each of the multiple 3D printed model samples to determine the support setting model.

5. The 3D printing support setting method as described in claim 4, characterized in that, Determining the overhang region contained in the first 3D printed model sample based on the overhang patch includes: Establish an index adjacency table for each overhanging surface in the first 3D printed model sample. The index adjacency table records the indexes of each overhanging surface adjacent to the current overhanging surface. Based on the indexed adjacency list, perform a drooping face search to determine whether the angle between the searched drooping face and the current drooping face is less than a preset angle. If it is determined that the included angle is less than the preset angle, the searched overhanging surface is classified as belonging to the same overhanging region as the current overhanging surface.

6. The 3D printing support setting method as described in claim 4, characterized in that, After determining the overhanging surface of the first 3D printed model sample based on the normal vector, the method further includes: Obtain the tilt angle of each overhanging patch in the first 3D printed model sample; Based on the tilt angle, the overhanging panels contained in the first 3D printed model sample are divided into multiple categories, and the number of overhanging panels in each category is determined. Based on the number of overhanging patches in each category, the statistical characteristics of the tilt of the overhanging patches in the first 3D printed model sample are generated. The determination of model training features of the first 3D printed model sample based on the overhang region fusion features and global statistical features of the first 3D printed model sample includes: The global statistical features and the tilt statistical features of the overhanging surface of the first 3D printed model sample are fused to determine the global statistical fusion features; Based on the overhang region fusion features and global statistical fusion features of the first 3D printed model sample, the model training features of the first 3D printed model sample are determined.

7. The 3D printing support setting method as described in claim 4, characterized in that, The overhanging region features include one or more of the following: the area of ​​the overhanging region, the centroid of the overhanging region, the minimum and maximum coordinates of the overhanging region in the XYZ directions, the average normal vector of the overhanging region, the standard deviation of the normal vector of the overhanging region, the average Z coordinate of the overhanging region, the projected area of ​​the overhanging region on the XY plane, the projected perimeter of the overhanging region on the XY plane, the ratio of the projected area of ​​the overhanging region on the XY plane to the surface area of ​​the printed model, and the compactness of the overhanging region. The global statistical features include one or more of the following: print model complexity, print model bounding box size and aspect ratio, print model spatial structure features, print model normal vector distribution features, print model Z coordinate range, print model bottom contact surface features, and print model curvature.

8. A 3D printing support setting device, characterized in that, The device includes: The acquisition module is used to acquire the model file of the 3D printed model; A determination module is used to determine the support structure information of the 3D printed model based on a pre-trained support setting model and the model file. The support structure information includes the addition information of one or more supports. The support setting model is used to extract the global statistical features and the overhang region features of the 3D printed model from the model file, and to determine the support structure information of the 3D printed model based on the global statistical features and the overhang region features. The global statistical features are used to indicate the measurement characteristics of the overall model structure of the 3D printed model, and the overhang region features are used to indicate the measurement characteristics of the overhang region in the 3D printed model. The generation module is used to obtain the slice configuration information of the 3D printing model, and generate a printing parameter file based on the slice configuration information and the support structure information.

9. A computer device, characterized in that, The computer device includes a processor and a memory, the memory being used to store instructions, and the processor being used to invoke the instructions in the memory, causing the computer device to execute the 3D printing support setting method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the 3D printing support setup method as described in any one of claims 1 to 7.

Images