Three-dimensional model placing method, three-dimensional model printing method and three-dimensional model printing equipment

Abstract

The embodiment of the invention provides a three-dimensional model placing method, a three-dimensional model printing method and printing equipment. The three-dimensional model placing method comprises the steps that multiple three-dimensional models are obtained; obtaining at least a first interval needing to be kept in the horizontal direction of the model space and at least a second interval needing to be kept in the printing direction of the multiple three-dimensional models; performing first amplification in the horizontal direction based on the first spacing; performing second magnification in the printing direction and the opposite direction of the printing direction based on the second spacing; and determining the placement positions of the plurality of three-dimensional models in the model space based on the collision relationship of the plurality of amplified three-dimensional models. The model is amplified through the spacing parameter, so that placement and collision detection are performed based on the amplified three-dimensional model, arrangement in a three-dimensional space is realized, and the space utilization rate is improved. And independent interval parameters are set in the horizontal direction and the printing direction correspondingly, multi-dimensional differential interval regulation and control are achieved, and therefore the space utilization rate is increased, and interference of the supporting structure is avoided.

Description

Technical Field

[0001] This application relates to the field of additive manufacturing, and in particular to a method for placing three-dimensional models, a method for printing three-dimensional models, and a printing device. Background Technology

[0002] Additive manufacturing (e.g., 3D printing) provides techniques for creating objects, typically by solidifying portions of building material in specific locations. Additive manufacturing techniques may include stereolithography (or photopolymerization), selective or fused deposition modeling, direct composite manufacturing, laminated object manufacturing, selective phase region deposition, multiphase jet solidification, ballistic particle manufacturing, particle deposition, laser sintering, or combinations thereof.

[0003] When using 3D printing technology in a limited model space (or printing space), it is necessary to consider the layout of the 3D model in the model space, while meeting the requirements of the printing process for support structure, optical interference and model spacing. Summary of the Invention

[0004] In a first aspect, embodiments of this application provide a method for arranging a three-dimensional model, including:

[0005] Obtain multiple 3D models;

[0006] Obtain the first spacing that multiple 3D models need to maintain in the horizontal direction in the model space, and perform a first magnification on the surface of each 3D model in the horizontal direction based on the first spacing;

[0007] Obtain the second spacing that multiple 3D models need to maintain at least in the printing direction in the model space, and perform a second magnification on the surface of each 3D model based on the second spacing in the printing direction and the opposite direction of the printing direction;

[0008] Based on the collision relationships of multiple magnified 3D models, adjust the position of at least one 3D model in the model space.

[0009] In one possible implementation, the first magnification is based on half of the first spacing, and the second magnification is based on half of the second spacing.

[0010] In one possible implementation, the model space is defined by the printing space of multiple 3D models.

[0011] In one possible implementation, adjusting the position of at least one 3D model in model space based on the collision relationships of the magnified multiple 3D models includes:

[0012] Identify multiple colliding 3D models that have collision relationships among the multiple magnified 3D models;

[0013] Adjust the position of at least one of the multiple colliding 3D models in model space to eliminate the collision relationship.

[0014] In one possible implementation, it also includes:

[0015] Obtain the initial placement position of the adjusted multiple 3D models in model space;

[0016] Optimization objectives are constructed, and constraints are determined based on the first spacing and the second spacing. The optimization objectives include minimizing the printing height, maximizing the number of models per unit area, and reducing at least one of the supports.

[0017] Using a trained machine learning model, the first placement position is optimized based on the optimization objective and constraints, and the second placement positions of multiple 3D models in the model space are output.

[0018] In one possible implementation, it also includes:

[0019] Identify one or more sensitive parts of multiple 3D models;

[0020] The first amplification performed on one or more sensitive areas has a larger first spacing and / or the second amplification performed has a larger second spacing.

[0021] In one possible implementation, identifying one or more sensitive areas of multiple 3D models includes:

[0022] Extracting geometric parameters of multiple 3D models from mesh data of multiple 3D models;

[0023] Based on geometric parameters, one or more sensitive parts of multiple 3D models are identified, wherein the geometric parameters include at least one of curvature, rate of change of normal, and acute angle of boundary.

[0024] In one possible implementation, identifying one or more sensitive areas of multiple 3D models includes:

[0025] Based on mesh data from multiple 3D models, a trained machine learning model is used to identify sensitive parts of the multiple 3D models.

[0026] In one possible implementation, the second spacing is determined based on the support structure during the printing of multiple 3D models, the thickness of each layer, and the demolding force after printing.

[0027] In one possible implementation, the first spacing and the second spacing are different.

[0028] In one possible implementation, the first spacing is smaller than the second spacing.

[0029] In one possible implementation, it also includes:

[0030] After adjustment, the first magnification of multiple 3D models is restored in the horizontal direction, and the second magnification is restored in the printing direction and the opposite direction of the printing direction.

[0031] Secondly, embodiments of this application provide a method for printing a three-dimensional model, including:

[0032] The placement of multiple three-dimensional models in model space is determined based on the methods in the first aspect and / or various possible implementations of the first aspect described above.

[0033] Based on the placement of multiple 3D models in the model space, generate printing data for multiple 3D models;

[0034] Printing is performed based on the print data.

[0035] Thirdly, embodiments of this application provide a printing device, including: a processor; a memory communicatively connected to the processor, the memory storing computer execution instructions; the processor executing the computer execution instructions stored in the memory to implement the first aspect and / or various possible implementations of the first aspect, and / or implementations of the second aspect.

[0036] Fourthly, embodiments of this application provide a computer device, including: a memory and a processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0037] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0038] This application provides a method for arranging three-dimensional models, a method for printing three-dimensional models, and a printing device. The method includes: acquiring multiple three-dimensional models; acquiring a first spacing that the multiple three-dimensional models need to maintain at least in the horizontal direction of the model space; performing a first magnification on the surface of each three-dimensional model in the horizontal direction based on the first spacing; acquiring a second spacing that the multiple three-dimensional models need to maintain at least in the printing direction of the model space; performing a second magnification on the surface of each three-dimensional model in the opposite direction of the printing direction based on the second spacing; and adjusting the position of at least one three-dimensional model in the model space based on the collision relationship of the magnified multiple three-dimensional models. By magnifying the three-dimensional models through spacing parameters in the horizontal and printing directions, placement and collision detection can be performed based on the magnified three-dimensional models. This allows for placement based on the contour shape of the three-dimensional models themselves, achieving arrangement in three-dimensional space and improving space utilization. Furthermore, by setting independent spacing parameters in the horizontal direction (e.g., XY) and the printing direction (e.g., Z-axis), multi-dimensional differentiated spacing control can be achieved, thereby improving space utilization and avoiding interference with the supporting structure. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0040] Figure 1 A flowchart illustrating the three-dimensional model placement method provided in the embodiments of this application. Figure 1 ;

[0041] Figure 2 A schematic diagram showing the relative positions of three-dimensional models in the model space provided in the embodiments of this application;

[0042] Figure 3 This is a schematic diagram illustrating the placement effect of the three-dimensional model provided in the embodiments of this application;

[0043] Figure 4 A flowchart illustrating the three-dimensional model placement method provided in the embodiments of this application. Figure 2 ;

[0044] Figure 5 A flowchart illustrating the three-dimensional model placement method provided in the embodiments of this application. Figure 3 ;

[0045] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0046] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0047] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0048] Additive manufacturing (e.g., 3D printing) provides techniques for creating objects, typically by solidifying portions of building material in specific locations. Additive manufacturing techniques may include stereolithography (or photopolymerization), selective or fused deposition modeling, direct composite manufacturing, laminated object manufacturing, selective phase region deposition, multiphase jet solidification, ballistic particle manufacturing, particle deposition, laser sintering, or combinations thereof.

[0049] Using 3D printing technology in a limited model space (or printing space) requires consideration of the layout of the 3D model within the model space, while also meeting the special requirements of the printing process for the support structure, optical interference, and model spacing.

[0050] In some examples, smaller 3D printing devices (e.g., devices known as capsule printers) will be used for fine printing, such as printing small workpieces, crafts, or other suitable models. Creating multiple models in the model (printing) space improves printing efficiency. For example, in digital dental production, 3D printing is widely used to manufacture restorations such as crowns, veneers, and bridges. In some examples, the required dental models can be printed by curing liquid resin layer by layer using projection light, such as Digital Light Processing (DLP), Stereo Lithography Appearance (SLA), or Liquid-crystal display. Because dental models or other fine workpieces and crafts typically have complex geometries and require precise assembly, efficiently arranging multiple models within the limited model space of a miniaturized 3D printing device, while simultaneously meeting the printing process's requirements for support structures, optical interference, and model spacing, presents a challenge to improving production efficiency and material utilization.

[0051] The placement schemes involved in related technologies typically only consider the horizontal direction (assuming the printing direction of the model is taken as the vertical direction), which cannot fully utilize the model space, resulting in only a limited number of 3D models that can be printed. Some solutions employ a layer-by-layer placement strategy, placing the 3D models one layer at a time along the printing direction, with the height of each layer depending on the maximum height of the models placed in that layer. While this solution achieves 3D placement, it essentially considers 2D plane placement within each layer; therefore, although space utilization is improved, it is not significant.

[0052] Furthermore, photopolymerization techniques such as DLP have specific requirements for the spacing in the model printing direction: a support structure needs to be added to the bottom of the model during printing, and the spacing requirements in the horizontal direction differ significantly from those in the printing direction. Therefore, a larger spacing is needed in the printing direction to avoid optical interference and the risk of cross-contamination of the support structure, while the spacing in the horizontal direction needs to be compressed as much as possible to increase the arrangement density.

[0053] To address the aforementioned technical problems, embodiments of this application provide a method for arranging three-dimensional models, such as... Figure 1 As shown, the method includes:

[0054] Step 101: Obtain multiple 3D models;

[0055] Step 102: Obtain the first spacing that multiple 3D models need to maintain in the horizontal direction in the model space, and perform a first magnification on the surface of each 3D model in the horizontal direction based on the first spacing;

[0056] Step 103: Obtain the second spacing that multiple 3D models need to maintain at least in the printing direction in the model space, and perform a second magnification on the surface of each 3D model based on the second spacing in the printing direction and the opposite direction of the printing direction;

[0057] Step 104: Based on the collision relationship of the magnified multiple 3D models, adjust the position of at least one 3D model in the model space.

[0058] Multiple 3D models refer to several independent models created in the same printing task, such as through light curing. These models can be identical in shape and size or differ from one another, depending on the application requirements. In practical applications, such as model printing in the dental field, because restorations (such as crowns, teeth, etc.) or orthodontic appliances often need to be customized according to the individual patient's oral condition, the multiple 3D models included in a single printing task often have different geometric features to meet the needs of personalized medicine.

[0059] Model space refers to the space used to place multiple 3D models. It defines the placement range of the 3D models and represents the available space in a physical printer; it is a virtual mapping of the actual printing space. Therefore, the size and shape of the model space are determined by the printing space of the printing device. The size of the model space cannot exceed the size of the actual printing space to ensure that the 3D models placed in the model space can be printed completely by the printer. Based on the shape of the printing space, the shape of the model space can be cuboid, cylindrical, or adapted to the 3D model to be printed. In one embodiment, the printing device is a capsule printing device, and its printing space can be cylindrical; therefore, the model space can also be cylindrical.

[0060] It is understood that a capsule printing device or capsule printer can refer to a printing device that performs printing tasks using a printing capsule containing printing material such as a photosensitive polymer. The printing capsule can be based on a pay-as-you-go concept or a single-use or multi-use concept, allowing a user to print objects using a printing capsule containing a predetermined amount of resin or photosensitive polymer material sufficient for that print or a predetermined number of prints. Each printing capsule may include a readable identification device that can be read by the printing device's tracking system. This readable identification device can be an identification tag such as an RFID tag, barcode indicator, QR code, optical reader, etc., which facilitates monitoring the number of prints and the use of the printing capsules, such as monitoring the remaining amount of resin or photosensitive polymer within the printing capsule.

[0061] In some examples, a virtual model space can be constructed based on the print space, allowing multiple 3D models to be imported and placed within it. Therefore, the model space has a maximum capacity for placing 3D models, a value determined by the size of the model space, the size / shape of the multiple 3D models, and the density of their placement. Typically, to ensure the proper generation of the subsequent support structure, when placing multiple 3D models, the maximum capacity may not be used, allowing for a certain margin. In actual placement, it's possible to add 3D models while placing them to prevent an excessive influx of models into the model space.

[0062] It can be understood that the horizontal direction refers to the XY horizontal direction or layer plane direction perpendicular to the printing direction of the printing equipment. The first spacing refers to the minimum safe distance that needs to be maintained between models or between the edges of the model space in the horizontal direction. By setting the first spacing, and following the principle that the shortest line connecting models or the edges of the model space should have a projection in the horizontal direction smaller than the first spacing when placing them, it can be ensured that multiple 3D models will not collide in the horizontal direction when placed, so that the models will not stick together after printing, and the process of a model detaching from the build plane will not easily affect other models.

[0063] It can be understood that the printing direction refers to the build direction or the Z-direction. For example, when a printing device, such as a capsule printer, is normally placed on a horizontal plane, the printing direction can be a direction perpendicular to the horizontal plane, such as the direction from the bottom to the top of the capsule printer. The second spacing refers to the minimum safe distance that needs to be maintained between models or between the edges of model spaces in the printing direction. By setting the second spacing, following the principle that the shortest line connecting models or the edges of model spaces should have a projection in the printing direction smaller than the second spacing during placement, it can be ensured that multiple 3D models will not collide in the printing direction during placement, thus preventing them from sticking together after printing, and minimizing the impact of models detaching from the build plane on other models. Furthermore, it should be noted that the objects defined by the first spacing (horizontal direction) and the second spacing (printing direction) are any two models that have a risk of collision in spatial position, such as two adjacent models. For two non-adjacent models (e.g., isolated by at least one other model), it is only necessary to ensure that each model and at least one other model meet the requirements of the first and second spacings. Figure 2 Models 1 and 3 in the text. From Figure 2 As can be seen, Model 1 and Model 3 are diagonally opposite each other. Compared to Model 2, Model 4, and Model 5, Model 1 and Model 3 are not adjacent models; they are isolated by Model 3. Therefore, when considering spacing constraints, Model 3 can be disregarded for Model 1. As long as Model 1 satisfies the spacing constraints with Model 2, Model 4, and Model 5, and Model 3 satisfies the spacing constraints with Model 2, Model 4, and Model 5, then Model 1 and Model 3 must also satisfy the spacing requirements.

[0064] In some examples, the first and second spacings are set independently. In some embodiments, because a support structure needs to be added to the bottom of the model during printing, a larger spacing is required in the printing direction to avoid optical bleed and the risk of cross-contamination of the support structure; therefore, the second spacing is set to be greater than the first spacing. Examples of the placement of multiple 3D models when the first and second spacings differ can be as follows: Figure 3 As shown.

[0065] In some examples, the second spacing is determined based on the support structure during the printing of multiple 3D models, the thickness of each layer, and the demolding force after printing.

[0066] After obtaining the first and second spacing, each 3D model is first enlarged in the horizontal direction based on the first spacing, and then second enlarged in the printing direction and the opposite direction based on the second spacing, resulting in enlarged 3D models. This double enlargement is equivalent to adding a buffer layer outside the outline of the original 3D model. Even if two enlarged 3D models touch at a certain point during placement, there is still a minimum safe distance between them and the original 3D model.

[0067] Taking horizontal magnification as an example, the first horizontal magnification of each 3D model has two conditions: magnification direction and magnification degree. The magnification direction includes the positive and negative directions of the X-axis and Y-axis. The magnification degree is determined by a first spacing, which must be at least half of the first spacing. For example, if the first spacing is 4mm, then by offsetting the surface of each 3D model 2mm outward in the horizontal direction, the actual distance between the two magnified 3D models at the contact point will be exactly 4mm when they just touch. If the offset distance is less than 2mm, the actual distance between them will be less than 4mm, failing to meet the first spacing condition.

[0068] Similarly, when performing a second magnification in the printing direction based on the second spacing, the magnification direction includes the positive and negative directions of the Z-axis, and the magnification degree is determined by the second spacing and is not less than half of the second spacing.

[0069] In one embodiment, the first magnification is based on half of the first spacing, and the second magnification is based on half of the second spacing.

[0070] After performing a first and second magnification on each 3D model, an magnified 3D model is obtained. When placing multiple 3D models, collision detection is performed based on the magnified 3D models to determine the collision relationship between the magnified 3D models. The positions of the 3D models with collisions are then adjusted to eliminate the collisions.

[0071] Furthermore, for some enlarged 3D models that do not have collision relationships, their positions can be adjusted to save space in the model space. For example, they can be moved to positions closer to where collision relationships exist, allowing for the import of more other 3D models into the model space. It should be noted that collision detection must be performed based on the enlarged 3D model during all adjustments.

[0072] In this embodiment, the placement methods for multiple 3D models include overlap removal and feasible solution-based methods. Overlap removal involves placing the 3D models one by one into the model space. Each time a 3D model is placed, the collision relationship between the new model and the already placed models is detected based on the magnified 3D model; that is, placement is performed sequentially based on each magnified 3D model. The feasible solution-based method involves first placing multiple 3D models in the model space, initially disregarding collision relationships, and then performing collision detection and adjustment based on the magnified 3D model corresponding to each 3D model to eliminate collisions.

[0073] It should be noted that after placing all the 3D models and determining the position of each 3D model in model space, they need to be restored to their original size to avoid printing the enlarged 3D models. The restoration process refers to restoring the first and second enlargements.

[0074] Specifically, after adjustment, the first magnification of multiple 3D models is restored in the horizontal direction, and the second magnification is restored in the printing direction and the opposite direction. More specifically, the second magnification is restored first, followed by the first magnification, or the first magnification is restored first, followed by the second magnification, or both magnifications are restored simultaneously, thus obtaining the original 3D model.

[0075] The method provided in the above embodiments involves: acquiring multiple 3D models in a model space; acquiring a first spacing that the multiple 3D models need to maintain at least in the horizontal direction of the model space; performing a first magnification on the surface of each 3D model in the horizontal direction based on the first spacing; acquiring a second spacing that the multiple 3D models need to maintain at least in the printing direction of the model space; performing a second magnification on the surface of each 3D model in the opposite direction of the printing direction based on the second spacing; and adjusting the position of at least one 3D model in the model space based on the collision relationship of the magnified multiple 3D models. By magnifying the 3D models using spacing parameters in the horizontal and printing directions, placement and collision detection can be performed based on the magnified 3D models, enabling placement based on the contour shape of the 3D models themselves, achieving arrangement in 3D space, and improving space utilization. Furthermore, by setting independent spacing parameters in the horizontal direction (XY) and the printing direction (Z-axis), multi-dimensional differentiated spacing control is achieved, thereby improving space utilization and avoiding interference with the supporting structure.

[0076] In one embodiment, adjusting the position of at least one 3D model in the model space based on the collision relationship of the magnified multiple 3D models includes:

[0077] Identify multiple colliding 3D models that have collision relationships among the multiple magnified 3D models;

[0078] Adjust the position of at least one of the multiple colliding 3D models in model space to eliminate the collision relationship.

[0079] The existence of a collision relationship means that the magnified 3D model has at least one point, line, or surface in contact or overlapping.

[0080] In this embodiment, all the 3D models to be placed can be first placed in the model space, and collision detection can be performed to determine whether there is a collision relationship between the enlarged 3D models. If so, the 3D models with a collision relationship are defined as colliding 3D models. From multiple colliding 3D models, at least one is selected for position adjustment. In the step-by-step placement scheme, for the enlarged 3D model being placed, if a collision relationship is detected between the enlarged 3D model and the already placed enlarged 3D models, the position of the enlarged 3D model can be directly adjusted. If the collision detection requirements are still not met, other already placed enlarged 3D models can be adjusted.

[0081] The method provided in the above embodiments detects collision relationships using an enlarged 3D model and adjusts the positions of the parts of the model that have collision relationships. Unlike placing the model based on the outer contour rectangle or cuboid of the 3D model, this method can effectively improve space utilization.

[0082] In one embodiment, such as Figure 4 As shown, it also includes:

[0083] Step 401: Obtain the first placement position of the adjusted multiple 3D models in the model space;

[0084] Step 402: Construct optimization objectives and determine constraints based on the first spacing and the second spacing. The optimization objectives include minimizing the printing height, maximizing the number of models per unit area, and reducing the number of supports.

[0085] Step 403: Using the trained machine learning model, optimize the first placement position based on the optimization objective and constraints, and output the second placement positions of multiple 3D models in the model space.

[0086] The first placement position is determined based on the magnified 3D model. This first placement position ensures that the distances between multiple 3D models meet the requirements of the first and second spacing. However, in model space, there are multiple possible placements for 3D models. Simply ensuring no collisions might result in excessively large distances between the 3D models, leading to inefficient space utilization.

[0087] In 3D printing, such as photopolymerization, the model is printed layer by layer. With a fixed layer height, the printing height directly determines the printing time. The lower the total height of the 3D model, the fewer layers are needed, and the shorter the total printing time. Simultaneously, a lower model height typically requires less resin. Therefore, the printing height can be used as an optimization target to optimize the initial placement position.

[0088] Optimization objectives are established based on print height, number of models per unit area, and number of supports, such as minimizing print height, maximizing the number of models per unit area, and reducing supports. A machine learning model is used to optimize the placement, resulting in a second placement position that meets the optimization objectives. During the optimization process, the first and second spacings are used as constraints to prevent collisions, models being too close together and interfering with each other, and the generation of supports.

[0089] In some embodiments, after obtaining the magnified 3D model, it is not necessary to obtain the first placement position. Instead, based on the magnified 3D model, the placement positions of multiple magnified 3D models can be directly obtained by constructing an optimization objective and determining constraints. After determining the placement positions of the magnified 3D models, performing a first magnification restoration and a second magnification restoration yields the final placement position of the 3D model.

[0090] In one embodiment, such as Figure 5 As shown, the method also includes:

[0091] Step 501: Identify one or more sensitive parts of multiple 3D models;

[0092] Step 502, a first amplification performed at one or more sensitive sites has a larger first spacing and / or a second amplification performed has a larger second spacing.

[0093] Sensitive areas refer to specific regions on a 3D model. When placing 3D models, the shape of these areas needs to be considered to avoid overlapping between models. For example, the mounting surface of a dental crown is concave. If it is enlarged according to the same parameters, it is very likely that a part of one model will be placed in the sensitive area of ​​another model, resulting in collision or difficulty in separation.

[0094] To prevent a protruding part of one model from getting stuck in a recessed part of another model during placement, these sensitive areas are enlarged to a greater extent, i.e., the protective layer is thickened. This enlargement fills the recessed areas more, making them shallower and reducing the risk of a protruding part of one model embedding into a recessed part of another.

[0095] The adjustment of the first and / or second spacing at sensitive areas needs to be specifically adjusted based on the geometric parameters of the sensitive areas. In batch printing, the specific first and / or second spacing can also be determined based on the type of the 3D model to be printed.

[0096] Sensitive parts of a 3D model can be identified and classified based on preset rules, or they can be determined through manual annotation, or the sensitive parts can be identified first using an algorithm and then combined with the results of manual annotation.

[0097] In one embodiment, identifying one or more sensitive areas of multiple 3D models includes:

[0098] Extracting geometric parameters of multiple 3D models from mesh data of multiple 3D models;

[0099] Based on geometric parameters, one or more sensitive parts of multiple 3D models are identified, wherein the geometric parameters include at least one of curvature, rate of change of normal, and acute angle of boundary.

[0100] It is understandable that geometric parameters quantitatively describe and measure the geometric properties of a 3D model surface. Identifying sensitive areas of a 3D model through geometric analysis primarily involves finding regions where the geometric properties of the model surface undergo drastic changes. For example, curvature characterizes the degree of bending of each defined region on the surface of a 3D model. Curvature can be used to identify high-curvature regions on the surface of a 3D model, such as the regions associated with all edges and corners of a cube, or the region associated with the edge of the top face of a cylinder. The rate of change of normal is used to calculate the difference in the normal direction of adjacent triangular facets / mesh regions composed of triangular facets in a 3D model. Boundary acute angles are analyzed to determine the internal and external angles of the model's opening boundaries. Regions with a large rate of change of normal usually indicate rapid curvature changes. When identifying sensitive areas through geometric parameters, multiple regions with geometric parameters exceeding a certain threshold can also be identified. These regions can then be integrated using clustering or region connectivity algorithms.

[0101] In other examples, textures or geometric patterns can be combined to identify more details of a 3D model, such as holes, slots, text, or assembly parts. For instance, a geometry or texture library can be pre-stored in the 3D printing software. Identification is achieved by matching the local geometry and texture of the 3D model to these libraries. For example, a template for a hole might be the geometric definition of the inner wall of a cylinder. By scanning / searching the 3D model for all "inwardly pointing cylindrical surfaces," once found and matched, parameters such as the hole's depth and radius can be used to not only mark an area but also identify a "hole" feature, from which its parameters can be extracted. Similarly, for assembly parts, the stored templates could be threaded holes, pin holes, locating slots, or any other regular or irregular assembly template. For example, if the 3D printing software identifies these features, it can consider the area where these features are located to be a sensitive area designed for connection and mating with other parts.

[0102] In one embodiment, identifying one or more sensitive areas of multiple 3D models includes:

[0103] Based on mesh data from multiple 3D models, a trained machine learning model is used to identify sensitive parts of the multiple 3D models.

[0104] For areas that are not geometrically prominent but functionally important, it is difficult to define them using geometric parameters. Therefore, machine learning models can be used for intelligent identification. Compared to geometric analysis, machine learning models do not rely on fixed rules but learn the characteristics of sensitive areas from large amounts of data to perform identification.

[0105] For example, a Convolutional Neural Network (CNN) can be used to render a 3D model as a 2D image from multiple perspectives, and then identify features similar to recognizing cats and dogs. Alternatively, a Graph Convolutional Neural Network (GCN) can be used to directly treat the 3D mesh as a graph structure (vertices are nodes, edges are connections), learning the relationships between vertices and edges. PointNet++ can also be used to directly process 3D point cloud data, learning local and global features of points. Segmentation models (such as 3D variants of U-Net) can label each vertex or face on the model, for example, "assembled face" or "unassembled face." Alternatively, a large model or pre-trained large model, which includes only a decoder and has more parameters than a regular machine learning model, can be used to directly input the 3D model into the large model or pre-trained large model to obtain one or more sensitive parts of the 3D model. It can be understood that the trained machine learning model is obtained through training on a large amount of labeled data, or through fine-tuning a pre-trained machine learning model with a small amount of labeled data. In one embodiment, the mesh data of the 3D model can be input into a trained machine learning model to directly obtain the recognition results of the 3D model surface. In terms of visualization, after obtaining the label of each grid on the surface of the 3D model through the trained machine learning model, different colors can be used to display different labels for easy distinction. For example, red labels can be used for sensitive areas, while green labels can be used for non-sensitive areas.

[0106] In some embodiments, in order to improve the accuracy of identifying sensitive parts of the model, a combination of geometric analysis and machine learning analysis is used for identification. By combining geometric analysis (curvature, normal, acute angle of boundary, etc.) and machine learning analysis, the automatic identification and classification of sensitive parts of the model can be achieved.

[0107] The method provided in the above embodiments, by applying a larger magnification spacing to sensitive areas with recesses, can effectively prevent the protruding part of one model from sinking into the recessed part of another model during the printing process, thereby preventing the models from getting stuck together and reducing the risk of physical collisions. Typically, capsule printers generate and construct platform supports on certain surfaces of the models to support the three-dimensional fabrication of the models in the printing space. When multiple models are stacked three-dimensionally in the printing space, these supports may touch sensitive areas of the models. For example, a support generated by an upper-layer model may touch a sensitive area of ​​a lower-layer model. Therefore, by applying a larger magnification spacing to sensitive areas, the possibility of support contact is avoided.

[0108] Based on all the above embodiments, a three-dimensional stacking method with free spacing is provided, suitable for printing dental models, enabling stacking in three-dimensional space. The method includes:

[0109] Obtain multiple 3D models; obtain the first spacing that the multiple 3D models must maintain in the horizontal direction in model space; obtain the second spacing that the multiple 3D models must maintain in the printing direction in model space.

[0110] Identify one or more sensitive parts of multiple 3D models;

[0111] The surface of each 3D model is first magnified in the horizontal direction based on a first spacing, and the surface of each 3D model is second magnified in the printing direction and the opposite direction of the printing direction based on a second spacing; the first magnification performed at one or more sensitive locations has a larger first spacing and / or the second magnification performed has a larger second spacing;

[0112] Optimization objectives are constructed, and constraints are determined based on the first spacing and the second spacing. The optimization objectives include minimizing the printing height, maximizing the number of models per unit area, and reducing at least one of the supports.

[0113] Using a trained machine learning model based on optimization objectives and constraints, the placement of multiple magnified 3D models is optimized, and the placement of the multiple magnified 3D models in the model space is output.

[0114] The first magnification of multiple enlarged 3D models is restored in the horizontal direction, and the second magnification is restored in the printing direction and the opposite direction, so as to obtain the placement of multiple 3D models in the model space.

[0115] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0116] This application also provides a method for printing a three-dimensional model, including:

[0117] Based on the three-dimensional model placement method in any of the above embodiments, the placement positions of multiple three-dimensional models in the model space are determined.

[0118] Based on the placement of multiple 3D models in the model space, generate printing data for multiple 3D models;

[0119] Printing is performed based on the print data.

[0120] Figure 6 A schematic diagram of the structure of the computer device provided in this application. Figure 6 As shown, the computer device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0121] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.

[0122] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0123] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0124] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0125] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0126] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0127] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0128] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0129] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0130] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0131] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0132] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0133] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0134] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0135] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for placing three-dimensional models, comprising: obtaining a plurality of three-dimensional models; obtaining a first spacing at least required to be maintained by the plurality of three-dimensional models in a horizontal direction of a model space, performing a first scaling on a surface of each three-dimensional model based on the first spacing in the horizontal direction; obtaining a second spacing at least required to be maintained by the plurality of three-dimensional models in a printing direction of the model space, performing a second scaling on a surface of each three-dimensional model based on the second spacing in the printing direction and an opposite direction of the printing direction; and adjusting a position of at least one three-dimensional model in the model space based on a collision relationship of the scaled plurality of three-dimensional models. The first scaling is performed based on half of the first spacing, and the second scaling is performed based on half of the second spacing.

2. The method of claim 1, wherein, The model space is defined by a printing space of the plurality of three-dimensional models.

3. The method of claim 1, wherein, The adjusting a position of at least one three-dimensional model in the model space based on a collision relationship of the scaled plurality of three-dimensional models comprises:

4. The method of claim 1, wherein, determining a plurality of collision three-dimensional models having a collision relationship in the scaled plurality of three-dimensional models; adjusting a position of at least one three-dimensional model in the model space to eliminate the collision relationship.

5. The method of claim 4, further comprising: obtaining a first placement position of the adjusted plurality of three-dimensional models in the model space; constructing an optimization objective, determining a constraint condition based on the first spacing and the second spacing, wherein the optimization objective comprises at least one of minimizing a printing height, maximizing a number of models per unit area, and reducing a support; using a trained machine learning model to optimize the first placement position based on the optimization objective and the constraint condition, and outputting a second placement position of the plurality of three-dimensional models in the model space.

6. The method of claim 1, further comprising: identifying one or more sensitive parts of the plurality of three-dimensional models; the first scaling performed at the one or more sensitive parts has a larger first spacing and / or the second scaling performed at the one or more sensitive parts has a larger second spacing. The identifying one or more sensitive parts of the plurality of three-dimensional models comprises:

7. The method of claim 6, wherein, extracting geometric parameters of the plurality of three-dimensional models from mesh data of the plurality of three-dimensional models; identifying one or more sensitive parts of the plurality of three-dimensional models based on the geometric parameters, wherein the geometric parameters comprise at least one of a curvature, a normal change rate, and a boundary acute angle. The identifying one or more sensitive parts of the plurality of three-dimensional models comprises:

8. The method of claim 6, wherein, identifying sensitive parts of the plurality of three-dimensional models based on mesh data of the plurality of three-dimensional models using a trained machine learning model. The second spacing is determined based on a support structure when the plurality of three-dimensional models is printed, a thickness of each layer, and a demolding force after printing is completed.

9. The method of claim 1, wherein, The first spacing and the second spacing are different.

10. The method of any one of claims 1-9, wherein, The first spacing is smaller than the second spacing.

11. The method of claim 10, wherein, 12. The method of any one of claims 1-8, further comprising: ​ After the adjusting, the first magnification is reversed in the horizontal direction and the second magnification is reversed in the printing direction and the opposite direction of the printing direction for the plurality of three-dimensional models. 13.A printing method of three-dimensional models, comprising: determining the placement of a plurality of three-dimensional models in a model space based on the method of any one of claims 1-12; generating printing data of the plurality of three-dimensional models according to the placement of the plurality of three-dimensional models in the model space; performing printing based on the printing data. 14.A printing device, comprising: a processor; a memory connected to the processor in communication, the memory storing computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the three-dimensional model placement method of any one of claims 1-12 and / or the printing method of three-dimensional models of claim 13.

15. A computer device comprising: a processor; a memory connected to the processor in communication, the memory storing computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method of any one of claims 1-12. 16.A computer-readable storage medium, the computer-readable storage medium storing computer-executable instructions, the computer-executable instructions being executed by a processor to implement the method of any one of claims 1-12 and / or the printing method of three-dimensional models of claim 13.

Images