Three-dimensional printing method and equipment and three-dimensional printing data processing method and device

Abstract

The present disclosure provides a three-dimensional printing method and apparatus, as well as a three-dimensional printing data processing method and apparatus, relating to the technical field of three-dimensional printing. The disclosed three-dimensional printing data processing method for digital light processing printing includes: obtaining three-dimensional data of an object to be printed, wherein the three-dimensional data includes the location of the interface between different printing materials required for printing the object to be printed; generating a diffusion structure at the location of the interface, wherein the diffusion structure is used to diffuse the printing material used later at the printing interface within the diffusion structure, and the printing material corresponding to the diffusion structure is the printing material used earlier at the printing interface; and generating three-dimensional printing data based on the three-dimensional data and the diffusion structure.

Description

Technical Field

[0001] The present disclosure relates to the field of three-dimensional printing technology, and in particular to a three-dimensional printing method and device, and a three-dimensional printing data processing method and device. Background Art

[0002] Multi-material 3D printing has attracted considerable attention for its ability to produce components with diverse compositions and complex structures. This technology can be achieved using mainstream technologies such as FDM (Fused Deposition Modeling), inkjet printing, and DLP (Digital Light Processing). Compared to other technologies, DLP multi-material printing demonstrates significant potential across various engineering fields due to its high resolution, wide material compatibility, and low cost.

[0003] In multi-material 3D printing, the printing materials need to be frequently replaced. For example, in FDM printing, multiple print heads are used, each print head uses a printing material, and when printing a print layer including multiple materials, the print heads work alternately. For another example, when using DLP multi-material printing, the printing materials need to be frequently replaced for the print layer including multiple printing materials. Summary of the Invention

[0004] One purpose of the present disclosure is to improve the efficiency of multi-material printing and reduce printing costs.

[0005] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing data processing method for digital light processing printing is proposed, comprising: acquiring three-dimensional data of an object to be printed, wherein the three-dimensional data includes the position of an interface of different printing materials required for the object to be printed; generating a diffusion structure at the position of the interface, wherein the diffusion structure is used to cause a printing material used later at the position of the printing interface to diffuse in the diffusion structure, and the printing material corresponding to the diffusion structure is the printing material used earlier at the position of the printing interface; and generating three-dimensional printing data based on the three-dimensional data and the diffusion structure.

[0006] In some embodiments, the interface intersects an interface between printed layers.

[0007] In some embodiments, the diffusion structure includes one or more of a biomimetic wedge-angle edge structure, a capillary groove structure, a capillary protrusion structure, and a capillary hole structure.

[0008] In some embodiments, generating a diffusion structure at the interface includes: generating the diffusion structure by training a machine learning network model based on three-dimensional data, wherein the machine learning network model is obtained by training the machine learning network using preset diffusion structure sample data and corresponding material diffusion result data.

[0009] In some embodiments, the three-dimensional printing data processing method also includes: collecting first three-dimensional morphological data of a preset diffusion structure, and obtaining second three-dimensional morphological data after the preset diffusion structure is immersed in the printing material; extracting point cloud features according to the first three-dimensional morphological data and the second three-dimensional morphological data, and obtaining a mapping relationship between the point cloud features of the first three-dimensional morphological data and the point cloud features of the second three-dimensional morphological data; according to the mapping relationship, training the constructed machine learning network to obtain a machine learning network model.

[0010] In some embodiments, obtaining three-dimensional data of an object to be printed includes: determining a printing direction based on the three-dimensional shape of the object to be printed; determining a position of a layered interface for material replacement based on the three-dimensional shape and the printing direction to reduce the number of layered interfaces for material replacement, wherein at least one layered interface intersects with an extended surface of the interface.

[0011] In some embodiments, generating three-dimensional printing data based on three-dimensional data and diffusion structure includes: determining the three-dimensional data and diffusion structure of the printing material used first at the position of the printing interface in accordance with the printing order as the first printing data; determining the three-dimensional data of the printing material used later at the position of the printing interface in accordance with the printing order as the later printing data, wherein the number of the first printing data and the number of the later printing data in the three-dimensional printing data are respectively the same as the number of material changes. When the number of material changes is greater than 1, the later printing data corresponding to the previous interface is the first printing data corresponding to the next interface in accordance with the printing order.

[0012] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing method is proposed, including: a digital light processing three-dimensional printer obtains three-dimensional printing data, wherein the three-dimensional printing data is generated according to any one of the three-dimensional printing data processing methods for digital light processing printing described above; using a printing material determined according to a printing order, and performing a photocuring operation according to the three-dimensional printing data corresponding to the printing material, until printing reaches a corresponding layered interface for material replacement or printing is completed, wherein, if printing reaches a corresponding layered interface for material replacement, using a printing material replaced according to the printing order, and performing a photocuring operation according to the three-dimensional printing data corresponding to the replaced printing material, until printing reaches a corresponding layered interface for material replacement or printing is completed.

[0013] In some embodiments, the three-dimensional printing method further includes: after the digital light processing three-dimensional printer completes printing, removing excess printing material from the surface of the printed object and performing secondary curing on the printed object.

[0014] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing data processing device for digital light processing printing is proposed, comprising: a three-dimensional data acquisition unit, configured to acquire three-dimensional data of an object to be printed, wherein the three-dimensional data includes the position of an interface of different printing materials required for the object to be printed; a diffusion structure generation unit, configured to generate a diffusion structure at the position of the interface, wherein the diffusion structure is used to cause a printing material used later at the position of the printing interface to diffuse in the diffusion structure, and the printing material corresponding to the diffusion structure is the printing material used first at the position of the printing interface; and a printing data generation unit, configured to generate three-dimensional printing data based on the three-dimensional data and the diffusion structure.

[0015] In some embodiments, the three-dimensional printing data processing device also includes a model training unit, which is configured to: collect first three-dimensional morphological data of a preset diffusion structure, and obtain second three-dimensional morphological data after the preset diffusion structure is immersed in the printing material; extract point cloud features based on the first three-dimensional morphological data and the second three-dimensional morphological data, and obtain a mapping relationship between the point cloud features of the first three-dimensional morphological data and the point cloud features of the second three-dimensional morphological data; train the constructed machine learning network based on the mapping relationship, wherein the diffusion structure generation unit is configured to generate a diffusion structure based on the three-dimensional data through the machine learning network model obtained by training.

[0016] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing data processing device for digital light processing printing is proposed, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute any one of the above-mentioned three-dimensional printing data processing methods for DLP printing based on instructions stored in the memory.

[0017] According to one aspect of some embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, any one of the above-mentioned three-dimensional printing data processing methods for DLP printing is implemented.

[0018] According to one aspect of some embodiments of the present disclosure, a computer program product is provided, including a computer program or instructions, which, when executed by a processor, implements any one of the above three-dimensional printing data processing methods for DLP printing.

[0019] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing device is proposed, including: a digital light processing three-dimensional printer, configured to: obtain three-dimensional printing data, wherein the three-dimensional printing data is generated according to any one of the three-dimensional printing data processing methods for DLP printing described above; use a printing material determined according to a printing order, and perform a photocuring operation according to the three-dimensional printing data corresponding to the printing material until printing reaches a corresponding layered interface for material replacement or printing is completed, wherein, if printing reaches a corresponding layered interface for material replacement, use a printing material replaced according to the printing order, and perform a photocuring operation according to the three-dimensional printing data corresponding to the replaced printing material until printing reaches a corresponding layered interface for material replacement or printing is completed.

[0020] In some embodiments, the three-dimensional printing device further includes: a secondary processing device configured to remove excess printing material from the surface of the printed object and perform secondary curing on the printed object after the digital light processing three-dimensional printer completes printing. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide further understanding of the present disclosure and constitute a part of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute improper limitations on the present disclosure.

[0022] Figure 1 Flowcharts of some embodiments of the three-dimensional printing data processing method for digital light processing printing disclosed herein.

[0023] Figure 2 Schematic diagrams of some embodiments of printing objects and diffusion structure maps in the three-dimensional printing data processing method for digital light processing printing disclosed in the present invention.

[0024] Figure 3 Schematic diagrams of some embodiments of the model building method in the three-dimensional printing data processing method for digital light processing printing disclosed in the present invention.

[0025] Figure 4 Flowcharts of some embodiments of the 3D printing data processing method disclosed herein.

[0026] Figure 5 Schematic diagrams of some embodiments of the three-dimensional printing data processing device for digital light processing printing disclosed herein.

[0027] Figure 6 Schematic diagrams of some embodiments of the three-dimensional printing data processing device for digital light processing printing disclosed herein.

[0028] Figure 7 Schematic diagrams of some embodiments of the three-dimensional printing data processing device for digital light processing printing disclosed herein.

[0029] Figure 8 Schematic diagrams of some embodiments of the three-dimensional printing device disclosed herein.

[0030] Figure 9 Schematic diagrams of some embodiments of the printing results and diffusion structures of the three-dimensional printing device disclosed herein. DETAILED DESCRIPTION

[0031] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and examples.

[0032] In DLP multi-material printing, the use of different printing materials requires the replacement of material tanks (such as resin tanks) during the printing process, or the need to combine direct ink in water (DIW) with multi-channel feeding. Frequent resin tank replacement is particularly necessary when printing relatively irregular structures, printing different materials on the same layer, or printing a large number of layers with different materials. This not only requires complex printer modifications, limiting its large-scale application, but also reduces printing efficiency. Furthermore, the frequent removal of residual slurry from the printed part inevitably leads to slurry waste, cross-contamination, and damage to the printed part structure.

[0033] Due to the aforementioned issues, DLP printing technology is primarily used for single-material printing. Frequent replacement of slurry tanks or the addition of complex feeding systems, complicated processes, and varying degrees of contamination of printed materials have hindered the development of DLP multi-material printing.

[0034] In response to the above problems, the present disclosure proposes a three-dimensional printing data processing method, device, and three-dimensional printing method and equipment for DLP printing. By generating a diffusion structure at the interface of different materials, the subsequent printing material can diffuse in the diffusion structure, reducing the difficulty of printing at the interface and the number of times the printing material needs to be replaced. Therefore, while improving printing efficiency, it reduces material waste, reduces the probability of cross contamination, and reduces printing costs.

[0035] The flowcharts of some embodiments of the three-dimensional printing data processing method for digital light processing printing disclosed in the present invention are as follows: Figure 1 shown.

[0036] In step S12, three-dimensional data of the object to be printed is obtained, where the three-dimensional data includes the locations of the interfaces between different printing materials required to print the object. The object to be printed requires at least two materials to be printed, and the materials may differ in one or more of color, density, composition, etc.

[0037] In some embodiments, at least a portion of the interface intersects with the interface between printed layers, meaning that at least a portion of the printed layers require printing with two materials for each layer. When printing such an object using related-art printing methods, due to limitations in light penetration and curing depth, the printing material must be changed with almost every layer, significantly impacting printing efficiency and cost. The method disclosed herein can effectively address this situation, reducing the number of printing material changes and increasing the bond strength between different materials, thereby improving print quality.

[0038] In some embodiments, after determining the three-dimensional form of the object to be printed, the interface position of the slurry tank to be replaced when printing the model is determined according to the principle of printing as directly as possible and reducing the establishment of diffusion structures, and the printing direction is determined according to the position of the replaced layered interface so that the interface is perpendicular to the printing direction. In some embodiments, the position of the layered interface of material replacement can be determined according to the three-dimensional form of different material interfaces to reduce the area of ​​the diffusion structure of the material replacement and the number of layered interfaces, wherein at least one layered interface intersects with the extended surface of the interface; the printing direction is determined according to the position of the layered interface of the object to be printed. Figure 2 Taking the maxillary and mandibular print models shown in the figure as an example, the teeth are white and the gums are red. Depending on the distribution of the desired printing material and the convenience of object placement, you can choose to print the teeth or gums first. The printing direction is perpendicular to the upper palate, from teeth to gums, or vice versa. The layering interface for material replacement is the interface where the printing position farthest from the initial printing position of the first material is located after the complete printing. For example, when printing from teeth to gums, the layering interface is the interface where the point of the tooth closest to the root is located.

[0039] In step S14, a diffusion structure is generated at the interface position. The diffusion structure is used to diffuse the printed material used after printing at the interface position in the diffusion structure, and the printing material corresponding to the diffusion structure is the printed material used before printing at the interface position. The "previous printed material" mentioned in this disclosure refers to the printed material used before replacing the printed material at the interface position; similarly, the "later printed material" refers to the printed material used after replacing the printed material at the interface position. The "previous printed data" mentioned in this disclosure refers to data printed using the above-mentioned "previous printed material", and the "later printed data" refers to data printed using the above-mentioned "later printed material".

[0040] The printing material is a liquid material. Under the influence of capillary phenomena, the liquid will flow along the surface inside the diffusion structure, infiltrate and rise in the pores of the diffusion structure, and expand the adhesion range of the printing material on the printed object.

[0041] In some embodiments, the diffusion structure includes a biomimetic wedge-shaped edge structure (e.g. Figure 2 One or more of the following: the pitcher plant-like wedge-shaped edge structure (shown in the lower-middle image), capillary groove structure, capillary protrusion structure, and capillary hole structure. Experimentation has shown that different diffusion structures can achieve different liquid diffusion effects in DLP printing.

[0042] In some embodiments, the diffusion structure can be generated using a pre-trained machine learning network model. The machine learning network model generates a structure that is more suitable for subsequent material diffusion based on the position and morphology of the collected interface, thereby optimizing the material diffusion effect and improving the printing quality.

[0043] In some embodiments, the above-mentioned machine learning network model is generated by training a pre-built machine learning network using preset diffusion structure sample data and corresponding material diffusion result data, so that the machine learning network model has the ability to determine a more suitable subsequent material diffusion structure, thereby improving the matching degree between the generated diffusion structure and the printed object.

[0044] In step S16 , three-dimensional printing data is generated based on the three-dimensional data and the diffusion structure.

[0045] In some embodiments, the three-dimensional data and diffusion structure of the printing material used at the position of the print interface first can be determined according to the printing order as the first print data; and the three-dimensional data of the printing material used at the position of the print interface later can be determined according to the printing order as the later print data. The number of the first print data and the number of the later print data in the three-dimensional print data are the same as the number of material replacements. If the number of material replacements is greater than one, the later print data corresponding to the previous interface will be the first print data corresponding to the next interface according to the printing order.

[0046] For example, if you print an object like Figure 2 As shown in , the number of printing materials used is 2, the number of interfaces is 1, and printing is performed in the direction from the teeth to the gums. The first printed material is white material, and the second printed material is pink material. The first printed data generated is the printing data using white material and the tooth part, and the interface with the pink material is the diffusion structure data to diffuse the pink material; the second printed data generated is the printing data using pink material and the gum part.

[0047] For another example, when there are two interfaces and there is a third material (which may be the same as the first material), the prior print data for the second interface according to the printing order is the subsequent print data for the first interface, wherein the subsequent print data for the first interface records the data of the diffusion structure at the second interface.

[0048] In some embodiments, for each interface, the structure of the diffusion structure and the space occupied by its pores need not be considered in the subsequent print data, meaning it does not need to be aligned with the corresponding prior print data. This approach utilizes liquid diffusion to fill the pores, achieving a close bond between the prior and subsequent materials while reducing the complexity of the subsequent print data and improving printing efficiency.

[0049] Based on the method in the above embodiment of the present disclosure, by generating a diffusion structure at the interface of different materials, the subsequent printed material can diffuse in the diffusion structure, which significantly improves printing efficiency, reduces material waste, reduces the probability of cross contamination, and reduces printing costs.

[0050] In some embodiments, as Figure 1 As shown, the three-dimensional printing data processing method for digital light processing printing disclosed in the present invention further includes step S11.

[0051] In step S11, sample data is collected to train the machine learning network built to obtain a machine learning network model used in the subsequent step S14. In some embodiments, the machine learning model can be specifically a neural network model based on deep learning.

[0052] In some embodiments, multiple diffusion structures, such as any of those mentioned above, can be preset. A three-dimensional form of a printed object including the diffusion structure is generated as first three-dimensional form data. An object having this form is then experimentally printed and immersed in a subsequent printing material to obtain second three-dimensional form data after immersion in the printing material. Furthermore, point cloud features are extracted from the first and second three-dimensional form data, respectively, and a mapping relationship between the point cloud features of the first and second three-dimensional form data is obtained. The constructed machine learning network is then trained based on this mapping relationship.

[0053] Through this method, the model can be trained through real test results, so that the diffusion structure generated by the model can conform to the actual diffusion situation, thereby improving the reliability and printing quality of the diffusion structure.

[0054] For example, schematic diagrams of some embodiments of the model building method in the three-dimensional printing data processing method for digital light processing printing disclosed in the present invention are as follows: Figure 3As shown in , an infiltration model based on a deep learning network is established in this process. The main steps include: First, by collecting the three-dimensional model data of the preset surface / interface structure of the uninfiltrated slurry and the corresponding three-dimensional data of the slurry infiltration morphology, a dataset of infiltration predictions of different slurries on the preset surface / interface structure is constructed. Second, local feature extraction of point clouds before and after infiltration, using kernel point convolution of different sizes to construct a feature pyramid to extract the structural point cloud features before and after infiltration. Third, alignment of two-way point cloud features to extract the mapping relationship between the shape after infiltration and the three-dimensional morphology of slurry attachment. Fourth, regression prediction of the point cloud position after infiltration, using a point cloud position regression generator to regress and predict the denture point cloud features before infiltration, generate the denture point cloud after infiltration, and calculate the loss with the corresponding real point cloud features, so that the generated point cloud after infiltration is closer to the features of the real point cloud. Fifth, establishment of a slurry infiltration point cloud prediction model.

[0055] The flowcharts of some embodiments of the 3D printing data processing method disclosed herein are as follows: Figure 4 As shown, after generating 3D printing data based on the method in any of the above embodiments, a printing operation is performed based on the 3D printing data. The printing device includes a DLP 3D printer.

[0056] In step S41, the DLP 3D printer obtains 3D printing data. The 3D printing data is generated according to any of the 3D printing data processing methods for digital light processing printing described above. In some embodiments, the 3D printing data can be sent to the DLP 3D printer using wired or wireless data transmission.

[0057] In step S42, the DLP three-dimensional printer uses the printing material determined according to the printing order and performs a light curing operation according to the three-dimensional printing data corresponding to the printing material.

[0058] In step S43, it is determined whether the printer has completed printing all the three-dimensional printing data. If all the three-dimensional printing data have been processed, then printing is complete; otherwise, step S44 is executed.

[0059] In step S44, it is determined whether the printing is performed on the corresponding layered interface of the material change. If the printing is performed on the layered interface of the material change, step S45 is executed; otherwise, step S42 is fed back.

[0060] In step S45 , the printing material replaced according to the printing sequence is used, and a light curing operation is performed according to the three-dimensional printing data corresponding to the replaced printing material, and then step S43 is performed.

[0061] In some embodiments, in step S45, the object on which the previous material has been printed can be taken out first, and the first slurry remaining in the preset multi-scale structure can be removed by wiping, blowing, etc., and then the resin tank containing the printing material can be replaced and the printing operation can be continued, thereby avoiding the influence of the previous printing material liquid attached to the object on the printing effect of the subsequent printing material, and avoiding contamination of the subsequent printing material, thereby further improving the printing quality.

[0062] Based on the method in the embodiment shown above, a DLP three-dimensional printer can be used to print objects that require multiple materials, wherein the interface between different materials is provided with a diffusion structure, and the subsequent printed material can diffuse in the diffusion structure, thereby reducing the difficulty of printing the interface. While improving printing efficiency, it also reduces material waste, reduces the probability of cross contamination, and reduces printing costs.

[0063] In some embodiments, as Figure 4 As shown in , in the above step S43, if it is determined that printing is completed, step S46 can also be executed.

[0064] In step S46, after the DLP 3D printer completes printing, excess printing material is removed from the surface of the printed object and the printed object is post-cured. In some embodiments, supports may be removed, excess printing material may be wiped from the surface of the printed object, and uncured material within the structure may be post-cured. The object may then be rinsed with a cleaning agent and dried to complete printing, yielding the desired multi-material structural characteristics.

[0065] Based on the method in the above embodiment, the object can be secondary cured to avoid the impact of insufficient curing of the post-printed material inside the diffusion structure on the structural stability of the object, thereby further improving the quality of the printed object.

[0066] Schematic diagrams of some embodiments of the three-dimensional printing data processing device for digital light processing printing disclosed in the present invention are as follows Figure 5 shown.

[0067] The 3D data acquisition unit 511 can acquire 3D data of the object to be printed, wherein the 3D data includes the locations of interfaces between different printing materials required for printing the object. In some embodiments, the 3D data acquisition unit 511 can execute the method of any embodiment of step S12 above.

[0068] The diffusion structure generation unit 512 can generate a diffusion structure at the interface. The diffusion structure is configured to diffuse the printed material used after the interface is printed. The printed material corresponding to the diffusion structure is the printed material used before the interface. In some embodiments, the diffusion structure generation unit 512 can execute the method of any of the above-described embodiments of step S14.

[0069] The print data generation unit 513 can generate three-dimensional print data according to the three-dimensional data and the diffusion structure. In some embodiments, the print data generation unit 513 can execute the method in any embodiment of the above step S16.

[0070] Based on the device in the above-mentioned embodiment of the present disclosure, a diffusion structure is generated at the interface of different materials, so that the subsequent printed material can diffuse in the diffusion structure, thereby reducing the difficulty of printing at the interface and the number of times the printing material needs to be replaced. This improves printing efficiency while reducing material waste, reducing the probability of cross-contamination, and reducing printing costs.

[0071] In some embodiments, as Figure 5 As shown, the 3D printing data processing apparatus for digital light processing printing further includes a model training unit 514, which can collect sample data to train the constructed machine learning network to obtain a machine learning model used by the diffusion structure generation unit 512. In some embodiments, the model training unit 514 can execute the method of any embodiment of step S11 above.

[0072] Based on the device in the above embodiment of the present disclosure, the model can be trained through real test results, so that the diffusion structure generated by the model can conform to the actual diffusion situation, thereby improving the reliability and printing quality of the diffusion structure.

[0073] A schematic structural diagram of an embodiment of a three-dimensional printing data processing device for digital light processing printing disclosed in the present invention is shown in FIG. Figure 6 As shown. A three-dimensional printing data processing device for digital light processing printing includes a memory 601 and a processor 602. The memory 601 may be a disk, a flash memory, or any other non-volatile storage medium. The memory is used to store instructions in the corresponding embodiments of the three-dimensional printing data processing method for digital light processing printing described above. The processor 602 is coupled to the memory 601 and may be implemented as one or more integrated circuits, such as a microprocessor or a microcontroller. The processor 602 is used to execute instructions stored in the memory, thereby improving the efficiency of multi-material printing and reducing printing costs.

[0074] In one embodiment, it is also possible to Figure 7 As shown, a 3D printing data processing device 700 for digital light processing printing includes a memory 701 and a processor 702. The processor 702 is coupled to the memory 701 via a BUS 703. The 3D printing data processing device 700 for digital light processing printing can also be connected to an external storage device 705 via a storage interface 704 to access external data, and can also be connected to a network or another computer system (not shown) via a network interface 706. These will not be described in detail here.

[0075] In this embodiment, by storing data instructions in a memory and then processing the instructions through a processor, the efficiency of multi-material printing can be improved and the printing cost can be reduced.

[0076] In another embodiment, a computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the steps of the method in the corresponding embodiment of the three-dimensional printing data processing method for digital light processing printing. Those skilled in the art will understand that the embodiments of the present disclosure can be provided as methods, devices, or computer program products. Therefore, the present disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] Schematic diagrams of some embodiments of the three-dimensional printing device disclosed herein are as follows Figure 8 shown.

[0078] In some embodiments, the 3D printing device is a digital light processing 3D printer 81 .

[0079] The digital light processing 3D printer 81 is capable of acquiring 3D printing data, where the 3D printing data is generated according to any of the 3D printing data processing methods for digital light processing printing described above. In some embodiments, the digital light processing 3D printer 81 can utilize wired or wireless data transmission to acquire the 3D printing data generated by the 3D printing data processing device for digital light processing printing.

[0080] Furthermore, the digital light processing 3D printer 81 can also use printing materials determined according to the printing order, and perform photocuring operations according to the 3D printing data corresponding to the printing materials until printing reaches the corresponding layered interface of material replacement or printing is completed. Among them, if printing reaches the corresponding layered interface of material replacement, the printing materials replaced according to the printing order are used, and photocuring operations are performed according to the 3D printing data corresponding to the replaced printing materials until printing reaches the corresponding layered interface of material replacement or printing is completed.

[0081] In some embodiments, the digital light processing 3D printer 81 is capable of performing the above Figure 4 The method in any embodiment shown in steps S41-S45.

[0082] Such 3D printing equipment can use DLP 3D printers to print objects that require multiple materials. Among them, the interface between different materials is equipped with a diffusion structure, and the subsequent printing material can diffuse in the diffusion structure, which reduces the difficulty of printing the interface and the number of times the printing material needs to be replaced. Therefore, while improving printing efficiency, it reduces material waste, reduces the probability of cross contamination, and reduces printing costs.

[0083] In some embodiments, as Figure 8 As shown, the 3D printing apparatus also includes a secondary processing device 82, which is configured to remove excess printing material from the surface of the printed object and perform secondary curing on the printed object after the digital light processing 3D printer completes printing. In some embodiments, supports can be removed, excess printing material can be wiped off the surface of the printed object, and uncured material within the structure can be post-cured. The object can then be rinsed with a cleaning agent and dried to complete printing, thereby obtaining the desired multi-material structural characteristics.

[0084] Such 3D printing equipment can perform secondary curing on objects, avoiding the impact of insufficient curing of post-printing materials inside the diffusion structure on the structural stability of the object, and further improving the quality of the printed object.

[0085] In some embodiments, taking printing an object using two printing materials (referred to as slurry in this embodiment) with only one interface as an example, the entire process of generating 3D printing data and executing a printing operation using the 3D printing device of the present disclosure is as follows.

[0086] 1. Build an infiltration model based on a deep learning network. The steps to build the model include:

[0087] 1.1. By collecting the 3D model data of the preset surface / interface structure of the uninfiltrated slurry and the corresponding 3D data of the slurry infiltration morphology, a wetting prediction dataset of different slurries on the preset surface / interface structure is constructed.

[0088] 1.2, Local feature extraction of point cloud before and after infiltration, kernel point convolution of different sizes is used to construct a feature pyramid to extract the structural point cloud features before and after infiltration.

[0089] 1.3, alignment of dual-path point cloud features to extract the mapping relationship between the post-infiltration shape and the 3D morphology of the slurry attachment.

[0090] 1.4. Regression prediction of the point cloud position after infiltration. The point cloud position regression generator is used to regress the pre-infiltration denture point cloud features to generate the post-infiltration denture point cloud, and the loss is calculated with the corresponding real point cloud features, so that the generated post-infiltration point cloud is closer to the features of the real point cloud.

[0091] 1.5. Establish a slurry infiltration point cloud prediction model.

[0092] 2. Establish a multi-material printing target model and determine the printing direction based on its surface / interface characteristics.

[0093] 3. Based on the principle of direct printing as much as possible and minimizing the creation of diffusion structures, the interface position of the slurry tank when printing this model was determined, so that this interface was perpendicular to the printing direction. In the second slurry distribution area, the area above this interface is covered by the second slurry, and the area below this interface is directly printed with the second slurry.

[0094] 4. Using the model generated above, perform regression prediction on the point cloud features of the slurry-infiltrated part to generate a model with the surface / interface topological micro-nanostructure before infiltration.

[0095] 5. Import the pre-infiltration model into the slicing software and slice the model perpendicular to the printing direction by optimizing the posture. Make sure to print the part corresponding to the first slurry first.

[0096] 6. Place the resin tank containing the first slurry, set the corresponding parameters, and start printing. Pause printing at the layer corresponding to the interface mentioned in step 3. Remove the remaining first slurry in the preset multi-scale structure by wiping, blowing, etc. Then replace the resin tank with the second slurry, aligning the static liquid level of the second slurry with the interface defined in step 3. After a certain period of stagnant time, raise the height of the formed model, change the corresponding printing parameters, and continue printing the second material on the bottom until it is time to change to the third material. Repeat this process.

[0097] 7. After printing is complete, remove the support, wipe off the excess slurry on the surface, post-cure the uncured resin in the structure, rinse with a detergent, dry, and complete the printing to obtain the desired multi-material structural characteristics object.

[0098] Based on the device described in the above-mentioned embodiments of the present disclosure, by running the above-mentioned method, it is possible to construct and control the mapping relationship between the surface / interface gradient biomimetic structure of the printed part and the wetting state and diffusion dynamics of the printing slurry, thereby achieving the directional infiltration, spreading, and accumulation of different printing slurries in a specified area. After further curing, it is possible to achieve integrated multi-material high-precision light-curing 3D printing. Compared with existing multi-material printing technologies, this achieves DLP multi-material three-dimensional layered integrated printing without the need for complex modifications to the 3D printer, such as direct coupling with ink technology, which is conducive to large-scale technology promotion.

[0099] In some embodiments, to print the above Figure 2 Taking the upper and lower jaw models in the illustrated embodiment as an example, the entire process of generating three-dimensional printing data and executing a printing operation using the three-dimensional printing device disclosed herein is as follows.

[0100] 1. Import the maxillary data of a patient scanned by the scanner into the dental design software to generate and design the corresponding full denture model.

[0101] 2. Input the point cloud data of the full denture model into the 3D database of the corresponding point clouds before and after infiltration, perform regression prediction on the 3D point cloud data of the denture before infiltration, establish a point cloud prediction model, and convert it into an STL model. In this case, the lyophilic structure that can achieve the final personalized and full morphological characteristics of the gingival papilla is a concave structure with a general shape of an elongated isosceles triangle between the two artificial teeth, which imitates the spatial structure occupied by the real gingival papilla and is about 3mm deep. The inner wall of the concave structure is a bionic wedge angle structure, and the inner wall surface is a bionic groove structure. The specific spatial distribution is personalized and arranged through deep learning, such as Figure 2 The wedge-shaped structure of Nepenthes imitativeis is shown in the lower middle image.

[0102] 3. Import the maxillary denture model into the modeling software, add a preset plane as the horizontal plane at the junction of the white artificial tooth and the red base on the labial side, and make most of the bottom of the concave structure close to the horizontal plane.

[0103] 4. Import the model into the slicing software and adjust the model orientation so that the preset plane is parallel to the bottom of the resin tank or the build platform. Print the artificial teeth first. Avoid adding supports in the grooves. Record the number of layers required to print to a flat surface.

[0104] 5. Pour the artificial tooth slurry and start printing. Pause printing at the preset plane, remove the white resin in the groove, replace it with the slurry required for the base, and continue printing. At this time, the base slurry infiltrates and climbs in the preset bionic superstructure.

[0105] 6. After printing, remove the excess slurry except the liquid in the groove and place it in a light curing machine for post-curing to completely cure the slurry in the structure.

[0106] 7. Use ethanol to clean the denture structure, and then perform simple grinding and polishing to complete the maxillary full denture production. Figure 2 As shown in the two pictures above.

[0107] In some embodiments, to print Figure 9 Taking the sawtooth model in the illustrated embodiment as an example, the entire process of generating 3D printing data and executing a printing operation using the 3D printing device of the present disclosure is as follows.

[0108] 1. Input the point cloud data of the sawtooth model into the 3D database of the corresponding point clouds before and after infiltration, perform regression prediction on the 3D point cloud data of the denture before infiltration, establish a point cloud prediction model, and convert it into an STL model. Each sawtooth in this case is 5mm high, about 1.5mm deep, and about 2mm wide. The inner wall of the concave structure is a bionic wedge angle structure, and the inner wall surface is a bionic groove structure. The specific spatial distribution is personalized through deep learning, such as Figure 9 As shown in the lower middle figure.

[0109] 2. Import the predicted STL model into the slicing software. Adjust the model so that the print interface of the two materials is parallel to the bottom of the resin tank. Print the part with the preset structure first. When adding supports, avoid adding them in the grooves. Record the number of layers required to print to a flat surface.

[0110] 3. Pour the first slurry and start printing. Pause printing at the preset interface, remove the remaining resin in the groove, replace it with the second slurry, and continue printing. At this time, the second slurry infiltrates and climbs within the preset bionic superstructure.

[0111] 4. After printing, remove excess slurry other than the liquid in the groove and place it in a light curing machine for post-curing to completely cure the slurry in the structure.

[0112] 5. Clean the entire model with ethanol to complete the production of the sawtooth model. Figure 9 As shown in the upper middle figure.

[0113] The aforementioned embodiments demonstrate that the 3D printing data processing method, apparatus, and 3D printing method and equipment proposed in this disclosure maintain the inherent high resolution, speed, and precision of DLP printing while achieving in-situ, one-step formation of 3D layered structures, a feature not available in related DLP multi-material printing technologies. This results in efficient, smooth printing with virtually zero material waste and pollution. For example, when printing an object with a single material interface, DLP printing of multiple materials can be achieved with a single resin tank replacement, eliminating the need for complex 3D printer modifications, such as direct ink coupling technology, facilitating large-scale technology adoption.

[0114] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0117] The present disclosure has been described in detail so far. To avoid obscuring the concept of the present disclosure, some details known in the art have not been described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

[0118] The methods and apparatus of the present disclosure may be implemented in many ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the methods according to the present disclosure. Therefore, the present disclosure also covers recording media that store programs for executing the methods according to the present disclosure.

[0119] It should be noted that the terms "first", "second", etc. in the specification, claims, and drawings of the present disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or apparatus.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure and not to limit it. Although the present disclosure has been described in detail with reference to the preferred embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present disclosure can still be modified or some technical features can be replaced by equivalents without departing from the spirit of the technical solutions of the present disclosure, which should all be included in the scope of the technical solutions requested for protection in the present disclosure.

Claims

1. A three-dimensional printing data processing method for digital light processing printing, comprising: Collecting first three-dimensional morphological data of a preset diffusion structure, and obtaining second three-dimensional morphological data of the preset diffusion structure after it is immersed in a printing material; Extracting point cloud features from the first three-dimensional morphological data and the second three-dimensional morphological data, respectively, and obtaining a mapping relationship between the point cloud features of the first three-dimensional morphological data and the point cloud features of the second three-dimensional morphological data; According to the mapping relationship, the constructed machine learning network is trained to obtain a machine learning network model; Acquiring three-dimensional data of an object to be printed, wherein the three-dimensional data includes positions of interfaces between different printing materials required for the object to be printed; generating a diffusion structure at the interface location using a machine learning network model based on the three-dimensional data, wherein the diffusion structure is configured to diffuse a printing material used later for printing the interface location within the diffusion structure, and the printing material corresponding to the diffusion structure is the printing material used earlier for printing the interface location; Three-dimensional printing data is generated according to the three-dimensional data and the diffusion structure.

2. The 3D printing data processing method according to claim 1, wherein: The interface intersects with the interface between the printed layers.

3. The 3D printing data processing method according to claim 1, wherein: The diffusion structure includes one or more of a bionic wedge-angle edge structure, a capillary groove structure, a capillary protrusion structure, and a capillary hole structure.

4. The 3D printing data processing method according to claim 1, wherein: The step of obtaining three-dimensional data of the object to be printed includes: Determining the position of the layered interface of the material replacement according to the three-dimensional morphology of the interface of the different materials, so as to reduce the area of ​​the diffusion structure of the material replacement and the number of the layered interfaces, wherein at least one layered interface intersects with the extended surface of the interface; The printing direction is determined according to the position of the layered interface where the material of the object to be printed is changed.

5. The 3D printing data processing method according to claim 1, wherein: Generating three-dimensional printing data according to the three-dimensional data and the diffusion structure includes: Determining, in a printing order, to use the three-dimensional data and the diffusion structure of the printing material previously used to print the position of the interface as the prior printing data; Determine, in accordance with the printing order, the three-dimensional data of the printing material to be used after printing the position of the interface as the subsequent printing data, Among them, the number of the prior printing data and the number of the subsequent printing data in the three-dimensional printing data are respectively the same as the number of material changes. When the number of material changes is greater than 1, according to the printing order, the subsequent printing data corresponding to the previous interface is the prior printing data corresponding to the subsequent interface.

6. A three-dimensional printing method, comprising: The digital light processing 3D printer acquires 3D printing data, wherein the 3D printing data is generated by the 3D printing data processing method for digital light processing printing according to any one of claims 1 to 5; Using the printing material determined according to the printing order, performing the light curing operation according to the three-dimensional printing data corresponding to the printing material until printing reaches the corresponding layer interface of material replacement or printing is completed, Among them, if printing reaches the corresponding material replacement layer interface, the printing material replaced according to the printing order is used, and the light curing operation is performed according to the three-dimensional printing data corresponding to the replaced printing material until printing reaches the corresponding material replacement layer interface or printing is completed.

7. The three-dimensional printing method according to claim 6, further comprising: After the digital light processing 3D printer completes printing, excess printing material on the surface of the printed object is removed, and the printed object is subjected to secondary curing.

8. A three-dimensional printing data processing device for digital light processing printing, comprising: The model training unit is configured to: collect first three-dimensional morphological data of a preset diffusion structure, and obtain second three-dimensional morphological data after the preset diffusion structure is immersed in a printing material; extract point cloud features based on the first three-dimensional morphological data and the second three-dimensional morphological data, and obtain a mapping relationship between the point cloud features of the first three-dimensional morphological data and the point cloud features of the second three-dimensional morphological data; and train the constructed machine learning network based on the mapping relationship to obtain a machine learning network model; a three-dimensional data acquisition unit configured to acquire three-dimensional data of an object to be printed, wherein the three-dimensional data includes a position of an interface between different printing materials required for the object to be printed; a diffusion structure generating unit configured to generate a diffusion structure at the position of the interface using the machine learning network model based on the three-dimensional data, wherein the diffusion structure is used to diffuse a printing material used later for printing the position of the interface within the diffusion structure, and the printing material corresponding to the diffusion structure is the printing material used earlier for printing the position of the interface; The printing data generating unit is configured to generate three-dimensional printing data according to the three-dimensional data and the diffusion structure.

9. A three-dimensional printing data processing device for digital light processing printing, comprising: Memory; and a processor coupled to the memory, wherein the processor is configured to execute the three-dimensional printing data processing method according to any one of claims 1 to 5 based on instructions stored in the memory.

10. A computer-readable storage medium having computer instructions stored thereon, wherein when the instructions are executed by a processor, the three-dimensional printing data processing method according to any one of claims 1 to 5 is implemented.

11. A computer program product, comprising a computer program or instructions, wherein when the computer program or instructions are executed by a processor, the three-dimensional printing data processing method according to any one of claims 1 to 5 is implemented.

12. A three-dimensional printing device comprising: A digital light processing 3D printer is configured to: Acquiring three-dimensional printing data, wherein the three-dimensional printing data is generated according to the three-dimensional printing data processing method for digital light processing printing according to any one of claims 1 to 5; Using the printing material determined according to the printing order, performing the light curing operation according to the three-dimensional printing data corresponding to the printing material until printing reaches the corresponding layer interface of material replacement or printing is completed, Among them, if printing reaches the corresponding material replacement layer interface, the printing material replaced according to the printing order is used, and the light curing operation is performed according to the three-dimensional printing data corresponding to the replaced printing material until printing reaches the corresponding material replacement layer interface or printing is completed.

13. The three-dimensional printing device according to claim 12, further comprising: The secondary processing device is configured to remove excess printing material from the surface of the printed object after printing is completed by the digital light processing 3D printer, and perform secondary curing on the printed object.

Images