Three-dimensional printing method, printer and system and data processing method and device

Abstract

The invention provides a three-dimensional printing method and system, a printer and a data processing method and device, and relates to the technical field of three-dimensional printing. The three-dimensional printing data processing method disclosed by the invention comprises the following steps: according to three-dimensional data of an object to be printed, obtaining a slice image containing gray information; the slice image is sent to a photocuring ceramic printer, a light source in the photocuring ceramic printer emits light with fixed intensity to a light adjusting mechanism, the light adjusting mechanism adjusts the intensity of the light projected to a printing platform according to gray scale information in the slice image, and the surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry.

Description

Technical Field

[0001] The present disclosure relates to the technical field of three-dimensional printing, and particularly to a three-dimensional printing method, a printer and a system, as well as a data processing method and device. Background Art

[0002] Ceramic stereolithography additive manufacturing is a process of precisely controlling the polymerization process of multifunctional polymer monomers, and then converting a liquid slurry containing ceramic particles into a solid three-dimensional object. This innovation has overturned the traditional manufacturing method of ceramic parts and has extensive applications and impacts in the fields of tissue engineering, dentistry, microfluidics, bioprinting, soft robotics, metamaterials, and photonics.

[0003] When printing an object using the method of surface projection ceramic stereolithography additive manufacturing, in the related art, a three-dimensional model to be printed is first designed using 3D graphics software or obtained through scanning and modeling. For some complex shapes, specific support structures usually need to be additionally set to ensure the printing quality and efficiency. Subsequently, the model is sliced in a slicing software according to a certain rule and discretely decomposed into a series of ordered slice units. Finally, by setting different printing parameters, according to the slice units (printing files) separated by the previous slicing, the printing slurry is connected layer by layer through the method of stereolithography, and then the target three-dimensional ceramic part is obtained.

[0004] The general working principle of ceramic stereolithography 3D printing technology is based on the photopolymerization reaction of liquid photosensitive resin, that is, the ceramic printing slurry containing photosensitive resin can rapidly undergo a photopolymerization reaction under the irradiation of ultraviolet light with a specific wavelength and intensity, causing the molecular weight to increase sharply, and the material changes from a liquid state to a solid state. Ideally, the energy of the light beam is concentrated, and a uniform curing area can be formed. However, in actual situations, the light beam penetrates the printing slurry in a Gaussian distribution form. When the light intensity reaches the critical energy (E c ), the photopolymerization reaction begins, and the curing area at this time is C d (curing depth) and C w (curing width). Summary of the Invention

[0005] The inventors found that due to the scattering of light in the ceramic slurry and other reasons, the photon energy diffuses in a large range, destroying the concentration of the light beam, and the printed object is rough and has low precision.

[0006] An object of the present disclosure is to improve the precision of stereolithography ceramic printing.

[0007] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing data processing method is provided, including: obtaining a sliced image containing gray-scale information based on the three-dimensional data of the object to be printed; sending the sliced image to a stereolithography ceramic 3D printer, wherein a light source in the stereolithography ceramic 3D printer emits light with a fixed intensity to a light ray adjusting mechanism, and the light ray adjusting mechanism adjusts the light intensity projected onto the printing platform according to the gray-scale information in the sliced image, and the surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry.

[0008] In some embodiments, obtaining a sliced image containing gray-scale information includes: obtaining the gray-scale information corresponding to the three-dimensional data based on a machine learning model, and obtaining a sliced image including the gray-scale information of each pixel point.

[0009] In some embodiments, the machine learning model is trained to generate a corresponding gray-scale image sequence according to ceramic stereolithography samples, wherein the ceramic stereolithography samples include the correspondence between gray-scale image sample data and the three-dimensional data of the corresponding cured object.

[0010] In some embodiments, the light ray adjusting mechanism includes a digital micromirror device (DMD) or a spatial light modulator (SLM), and the DMD adjusts the reflection angle of the corresponding pixel's wafer according to the gray-scale information to adjust the light intensity projected onto the printing platform.

[0011] In some embodiments, obtaining a sliced image containing gray-scale information includes: obtaining the gray-scale information corresponding to each pixel according to the three-dimensional data, and obtaining a first image including the gray-scale information; gradually linearly shrinking or expanding the two-dimensional graph corresponding to the boundary contour of the image to a set ratio, and generating a set number of second images as the sliced images.

[0012] In some embodiments, obtaining a sliced image containing gray-scale information based on the three-dimensional data of the object to be printed includes: obtaining model slice data according to the three-dimensional data; and obtaining each sliced image containing gray-scale information according to the depth-gray superposition information corresponding to the three-dimensional data voxels layer by layer according to the number of sliced layers.

[0013] In some embodiments, obtaining a sliced image containing gray-scale information respectively according to the three-dimensional data in each slice data includes: for each slice data, obtaining the gray-scale information corresponding to each pixel according to the three-dimensional data, and obtaining a first image including the gray-scale information; for each first image, gradually linearly shrinking or expanding the two-dimensional graph corresponding to the boundary contour of the image to a set ratio, and generating a set number of second images as the sliced images.

[0014] In some embodiments, the light intensity of the light source used to generate the ceramic stereolithography samples is the same as the light intensity of the light source in the stereolithography ceramic 3D printer.

[0015] In some embodiments, the total printing duration of the cured object corresponding to each sample data in the ceramic photocuring sample is the same as the duration of the photocuring ceramic printer for printing a slice image.

[0016] In some embodiments, the data processing method further includes: determining a gray value sequence according to a predetermined gradient, generating gray image sample data for each gray value in the gray value sequence, using a photocuring ceramic printer to obtain three-dimensional data of the cured object generated by printing the gray image sample data, and determining the mapping relationship between the gray image sample data and the corresponding three-dimensional data of the cured object; obtaining a ceramic photocuring sample according to the correspondence between the gray image sample data of each gray value in the gray value sequence and the three-dimensional data of the cured object; training the constructed machine learning neural network with the ceramic photocuring sample to obtain a machine learning model.

[0017] In some embodiments, the object to be printed includes a dental veneer.

[0018] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing method for a photocuring ceramic printer is provided, including: obtaining a slice image, where the slice image is generated according to any one of the three-dimensional printing data processing methods mentioned above; emitting light with a fixed intensity to a light adjusting mechanism; and the light adjusting mechanism adjusting the light intensity projected onto the printing platform according to the gray information in the slice image, and the surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry.

[0019] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing data processing device is provided, including: a slice image acquisition unit configured to obtain a slice image containing gray information according to the three-dimensional data of the object to be printed; and a data sending unit configured to send the slice image to a photocuring ceramic printer, where a light source in the photocuring ceramic printer emits light with a fixed intensity to a light adjusting mechanism, and the light adjusting mechanism adjusts the light intensity projected onto the printing platform according to the gray information in the slice image, and the surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry.

[0020] In some embodiments, the data processing device further includes: a sample data acquisition unit configured to determine a grayscale value sequence according to a predetermined gradient, generate grayscale image sample data for each grayscale value in the grayscale value sequence, use a stereolithography ceramic printer to acquire three-dimensional data of a cured object generated by printing the grayscale image sample data, and determine the correspondence between the grayscale image sample data and the three-dimensional data of the corresponding cured object; obtain a ceramic stereolithography sample according to the correspondence between the grayscale image sample data of each grayscale value in the grayscale value sequence and the three-dimensional data of the cured object; a model training unit configured to train the constructed machine learning network using the ceramic stereolithography sample to obtain a machine learning model, wherein the slice image acquisition unit is configured to obtain the grayscale information corresponding to the three-dimensional data based on the machine learning model and obtain a slice image including the grayscale information of each pixel point.

[0021] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing data processing device is provided, including: a memory; and a processor coupled to the memory, the processor being configured to execute any one of the above three-dimensional printing data processing methods based on instructions stored in the memory.

[0022] According to one aspect of some embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, any one of the above three-dimensional printing data processing methods is implemented.

[0023] According to one aspect of some embodiments of the present disclosure, a computer program product is provided, including a computer program or instructions, and when the computer program or instructions are executed by a processor, any one of the above three-dimensional printing data processing methods is implemented.

[0024] According to one aspect of some embodiments of the present disclosure, a three-dimensional printer is provided, including: a communication mechanism configured to acquire a slice image, where the slice image is generated according to any one of the above three-dimensional printing data processing methods; a light source configured to emit light with a fixed intensity to a light adjustment mechanism; the light adjustment mechanism configured to adjust the light intensity projected onto the printing platform according to the grayscale information in the slice image; and a printing platform, the surface of which is located on the upper surface of the photosensitive ceramic slurry, configured to carry the printed object.

[0025] According to one aspect of some embodiments of the present disclosure, a three-dimensional printing system is provided, including: any one of the above three-dimensional printing data processing devices; and any one of the above three-dimensional printers. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings described herein are used to provide a further understanding of the present disclosure, and constitute a part of the present disclosure. The schematic embodiments and descriptions thereof of the present disclosure are used to explain the present disclosure, and do not constitute an improper limitation of the present disclosure. In the drawings:

[0027] Figure 1 is a flowchart of some embodiments of the three-dimensional printing data processing method of the present disclosure.

[0028] Figure 2 is a schematic diagram of some embodiments of gamma correction of a digital light processing (DLP) optical machine in the three-dimensional printing data processing method of the present disclosure.

[0029] Figure 3 is a graph showing the relationship between the ultraviolet curing depth and the exposure energy of a ceramic slurry in the three-dimensional printing data processing method of the present disclosure.

[0030] Figure 4 is a graph showing the relationship between the ultraviolet curing depth and the exposure time of a ceramic slurry at a fixed light intensity in the three-dimensional printing data processing method of the present disclosure.

[0031] Figure 5 is a schematic diagram of some embodiments of a machine learning network algorithm in the three-dimensional printing data processing method of the present disclosure.

[0032] Figure 6 is a flowchart of some embodiments of model training in the three-dimensional printing data processing method of the present disclosure.

[0033] Figure 7 is a flowchart of some embodiments of the three-dimensional printing method of the present disclosure.

[0034] Figure 8 is a schematic diagram of some embodiments of the three-dimensional printing data processing apparatus of the present disclosure.

[0035] Figure 9 is a schematic diagram of some other embodiments of the three-dimensional printing data processing apparatus of the present disclosure.

[0036] Figure 10 is a schematic diagram of some further embodiments of the three-dimensional printing data processing apparatus of the present disclosure.

[0037] Figure 11 is a schematic diagram of some embodiments of the three-dimensional printer of the present disclosure.

[0038] Figure 12 is a schematic diagram of some embodiments of the three-dimensional printing system of the present disclosure.

[0039] Figure 13 is a schematic diagram of an embodiment applying the three-dimensional printing data processing method and the three-dimensional printing method of the present disclosure.

[0040] Figure 14 Schematic diagram of another embodiment of applying the three-dimensional printing data processing method and three-dimensional printing method of the present disclosure.

[0041] Figure 15 Schematic diagram of yet another embodiment of applying the three-dimensional printing data processing method and three-dimensional printing method of the present disclosure.

[0042] Figure 16 Schematic diagram of still another embodiment of applying the three-dimensional printing data processing method and three-dimensional printing method of the present disclosure.

[0043] Figure 17 Schematic diagram of a control experiment. Detailed implementation manners

[0044] The technical solutions of the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments.

[0045] The inventors found that during the actual printing process, the printing slurry will cause different degrees of scattering of the incident light, resulting in the diffusion of photon energy in a large range and destroying the concentration of the light beam. Light scattering will increase the width (C w increase), but the curing depth (C d ) will become smaller. Generally, the solid content of ceramic particles in the micro-nano scale in the ceramic slurry used for photocuring 3D printing is as high as 80 wt% (the volume fraction is close to or exceeds 50 vol%), which has a significant light scattering effect.

[0046] In view of the problems existing in the related art, the present disclosure provides a three-dimensional printing method, printer and system, and data processing method and device, which reduce the influence of light scattering in the liquid on the printing accuracy and improve the accuracy of photocuring ceramic printing.

[0047] The flowcharts of some embodiments of the three-dimensional printing data processing method of the present disclosure are as Figure 1 shown.

[0048] In step S12, according to the three-dimensional data of the object to be printed, a sliced image containing grayscale information is obtained.

[0049] In some embodiments, the grayscale information corresponding to each pixel can be obtained first according to the three-dimensional data to obtain a first image including grayscale information. Further, the two-dimensional graph corresponding to the boundary contour of the image is gradually linearly reduced or enlarged to a set ratio to generate a set number of (for example, 10 - 100) second image combinations, and the second image combinations are used as the overall sliced image of the sample. In some embodiments, the printer prints the sliced image as a continuous operation without lifting the printing platform, and the position of the printing platform and the distance from the light source remain unchanged, that is, the set number of second image combinations belong to the same layer of the printed object.

[0050] In the related art, the surface projection stereolithography 3D printing adopts a layer-by-layer additive manufacturing technology. The basic principle is to divide a designed three-dimensional model into continuous thin layers (sliced model) according to a certain layer thickness, and then construct a complete three-dimensional part by means of layer-by-layer curing and stacking. However, this layer-by-layer stacking manufacturing method may cause problems such as differences in bonding strength within and between layers (insufficient interlayer bonding strength) and printing internal stress due to uneven distribution of projection light or flow leveling problems, etc., ultimately resulting in phenomena such as printing failure, cracking after sintering, or poor mechanical strength of the formed part. At the same time, layer-by-layer stacking usually requires the introduction of additional printing support rods to prevent the overall deformation of the printing blank, which additionally introduces pre- and post-processing steps such as the design and removal of printing support rods, increasing the complexity of the work and the printing process is relatively long (the printing time is usually several hours). In particular, for some extremely thin and precise complex parts, removing the support rods may cause problems such as part deformation, cracking, or microcracks. In addition, the surface of the parts printed layer by layer often has printing layer lines and it is difficult to directly form a smooth surface.

[0051] Through the method in the above embodiments of the present disclosure, the layer-by-layer printing can be transformed into a continuous printing process, avoiding problems such as layer lines, internal stress, anisotropy, support structure, and part deformation, defects, and cracking caused by removing the support during the layer-by-layer stacking, and improving the printing efficiency and accuracy.

[0052] In some embodiments, when the object to be printed is relatively thick (for example, the thickness exceeds the predetermined layer height), the object to be printed can be first subjected to layer-by-layer slicing to obtain the sliced data of each layer. Furthermore, for the sliced data of each layer, the gray-scale information of each slice is obtained as the first image corresponding to the slice. Further, for each first image, according to the superposition information of depth-gray scale corresponding to the three-dimensional data voxels, each sliced image containing gray-scale information is obtained according to the number of sliced layers. For example, the two-dimensional graph corresponding to the boundary contour of the image is gradually linearly reduced or enlarged to a set ratio to generate a set number of second images, so as to obtain a combination of multiple second images, all of which are used as sliced images. In some embodiments, the printer prints the sliced images in the same second image combination as a continuous operation without lifting the printing platform, that is, the second images belonging to the same second image combination belong to the same layer of the printed object; when the printing of one second image combination is completed, the height of the printing platform is adjusted once, and the printing of the next second image combination is executed, so as to reduce the number of required layers while realizing the printing of a relatively thick object and improve the printing accuracy of each layer.

[0053] In some embodiments, the operation of obtaining grayscale information based on three-dimensional data can be implemented using a machine learning model (such as a machine learning neural network). For example, the three-dimensional data is input into the machine learning neural network, and the machine learning network can obtain the grayscale information corresponding to each pixel point in the three-dimensional data, and then output a slice image including the grayscale information of each pixel point, improving the data processing efficiency.

[0054] In some embodiments, the machine learning model adopted in the present disclosure is a deep learning neural network model. The deep learning network is trained according to the ceramic stereolithography samples to generate a corresponding grayscale image sequence, and a generation network model is obtained. The ceramic stereolithography samples include the corresponding relationship between the grayscale image sample data and the three-dimensional data of the corresponding cured object. By such a method, the generation network model can be enabled to have the ability to convert three-dimensional data into grayscale images. Since the corresponding relationship between the three-dimensional data of the cured object and the grayscale image is established, the printing deviation caused by reasons such as light scattering can be overcome, the matching degree between the grayscale image and the desired printing result can be improved, and the printing accuracy can be improved.

[0055] In some embodiments, the light intensity of the light source used to generate the ceramic stereolithography samples is the same as the light intensity of the light source in the ceramic stereolithography printer. By the method in the above embodiments, the deviation of the object printed from the grayscale image generated based on the deep learning generation model caused by the change of the light intensity can be avoided, and the printing accuracy can be further improved.

[0056] In some embodiments, the total printing duration of the cured object corresponding to each sample data in the ceramic stereolithography samples is the same as the duration of printing a slice image by the ceramic stereolithography printer. By the method in the above embodiments, the deviation of the object printed from the grayscale image generated based on the generation network model caused by the change of the printing duration can be avoided, and the printing accuracy can be further improved.

[0057] In step S14, the slice image is sent to the ceramic stereolithography printer.

[0058] In the ceramic stereolithography printer, the light source emits light with a fixed intensity to the light adjusting mechanism. The light adjusting mechanism adjusts the light intensity projected onto the printing platform according to the grayscale information in the slice image. The surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry. In some embodiments, the light adjusting mechanism includes a DMD, and the DMD adjusts the reflection angle of the corresponding pixel's wafer according to the grayscale information to adjust the light intensity projected onto the printing platform. In some embodiments, the height of the printing platform can be adjusted in the same manner as in the embodiment shown in step S12 above, so as to avoid or reduce the layer-by-layer stacking structure of the printed object, and improve the printing efficiency and accuracy.

[0059] Based on the method in the above embodiment, the three-dimensional data of the object to be printed can be converted into a slice image including grayscale information, and the light-curing ceramic printer adjusts the intensity of the light projected onto the printing platform according to the grayscale information. The grayscale information has multiple levels of grayscale (for example, 256 levels of grayscale). Compared with binary images, the use of rich grayscale data can make the transition between different areas smoother, and the details and surface smoothness can be better expressed during printing exposure, reducing the step effect of the printing layer, improving the surface quality, and improving the printing accuracy. In addition, changing the layer-by-layer stacking printing method to the method of projecting the image including grayscale information can avoid problems such as weak interlayer bonding and surface layer patterns caused by the hierarchical structure, and further improve the printing accuracy.

[0060] In some embodiments, the object to be printed includes a tooth patch. The three-dimensional printing data processing method and the three-dimensional printing method proposed in the present disclosure can reduce the thickness of the printed tooth patch, improve the fit between the patch and the patient's teeth, reduce the adjustment height required for the patient's teeth, and improve user comfort.

[0061] DLP (Digital Light Processing) is a photocuring 3D printing technology based on surface projection, which consists of a high-intensity light source (such as UV lamp or LED) and a DMD (Digital Micromirror Device). DMD is a chip containing millions of tiny lenses, each of which can be tilted independently to control the reflection of light. When the printer receives the printing command, the light emitted by the light source is modulated by the DMD. Each lens on the DMD is tilted according to the slice data of the 3D model to form a corresponding grayscale image. The image of each layer is projected onto the surface of the photosensitive resin in the resin tank through the DMD. The light causes the photocurable slurry layer to solidify and form according to the predetermined design.

[0062] DLP printing relies on the ultra-sensitive photo-induced reaction of the photocurable slurry to light for curing, so the light irradiation intensity and curing degree of each area can be precisely controlled by using a grayscale map. Figure 1 Generally can provide 256 gray levels (such as Figure 2 As shown in the figure, this allows for better detail and surface smoothness during printing exposure. Compared to binary images, grayscale images can transition between different areas more smoothly, thereby reducing the step effect of the printed layer and improving the surface quality. In view of this, the exposure intensity of different areas in the photocurable slurry can be accurately controlled, thereby achieving precise control of the curing depth and degree of the photosensitive slurry in different areas of the three-dimensional space, laying the foundation for the subsequent preparation of complex structures.

[0063] For example, with a laser power of 125 mW / cm 2Take the DLP printer as an example. Generally, the output brightness of the projector used in DLP printing is non-linear. Therefore, it is necessary to perform gamma correction on the input grayscale image to ensure that the brightness of the light source output matches the expected target data of the image, so as to achieve precise control of the curing degree of the target area. Fix the initial power of the laser, adjust a series of grayscale values of the input image (for example, marked as 0 - 255 in the order of decreasing grayscale value), and use a light intensity meter to measure the actual light intensity values corresponding to different grayscale levels in the printing area. Then, the non-linear relationship between the grayscale value in the slice data and the actual projection light intensity can be obtained (as shown in Figure 2 ). Gamma correction usually uses the following formula:

[0064]

[0065] In the formula: I is the corresponding light power value; C is the known grayscale value; γ is the gamma value, which determines the degree of adjustment.

[0066] After the projection light machine undergoes gamma correction, the photosensitive characteristics of the photocurable slurry are characterized by studying two characteristic parameters: the critical exposure amount and the curing depth. Place the photocurable ceramic slurry in a self-made quartz groove with a depth of 1 mm and an area of 50×50 mm (such as shown in Figure 13 (c)). After waiting for self-leveling, place it on the printing platform of the up-projection DLP printer. Fix the laser power of the projector (125 mW / cm 2 ), as well as the curing time (1 s). By changing the grayscale value of the projection image, adjust the actual irradiation intensity of the laser, so as to determine the critical exposure amount of this photocurable ceramic slurry. Through experiments, it is found that when the grayscale value is less than 5, it is impossible to form. This is because the absorption of ultraviolet light by the liquid photosensitive slurry usually follows the Beer-Lambert theorem, and at the same time, the irradiation of ultraviolet laser on the surface of the photosensitive slurry also conforms to the Beer-Lambert theorem, that is, the energy of the ultraviolet laser decays exponentially along the irradiation depth, that is

[0067]

[0068] In the formula, E is the incident energy density of ultraviolet light; Z is the depth, and E(z) is the laser energy density transmitted to the depth Z; Dp is the curing depth, which is an inherent parameter of the photosensitive slurry, indicating the strength of the absorption ability of the ultraviolet laser. The smaller the Dp value, the stronger the absorption of the ultraviolet laser by the slurry.

[0069] The critical exposure energy (Ec) is the minimum laser irradiation energy value required for the ceramic slurry to form a solid layer, that is, the minimum energy value required for 3D printing. When the exposure amount (E) of the liquid photosensitive slurry to ultraviolet light exceeds a certain threshold, that is, the critical exposure energy Ec, that is, when

[0070]

[0071] The photosensitive paste will rapidly polymerize and undergo a phase change, changing from a liquid state to a solid state. At this time,

[0072]

[0073] That is, the curing depth can be further expressed as

[0074]

[0075] Taking lnE as the abscissa and C d as the ordinate, it can be seen that lnE and C d show a linear relationship, and the slope of the straight line is D p , and the intersection point of the straight line and the lnE axis is lnE c . By setting a series of exposure light intensities and using a thickness gauge to measure the thickness of the cured slurry, the relationship between the cured layer thickness and the corresponding energy input is plotted. The UV light intensity represents the amount of UV photon energy received per unit area within a specified wavelength range and represents the photon flux. Therefore, the light energy can also be controlled by increasing the exposure time of the 3D printer:

[0076]

[0077] In the formula, I is the light intensity, with the unit of mW / cm 2 , t is the exposure time, with the unit of s. Combining with the curing depth formula, fitting calculations can obtain the values of E c and D p as shown in Figure 3 .

[0078] At the same exposure time, the curing depth usually increases with the increase of the light intensity ( ); however, at a certain light intensity, the curing depth of the printed part tends to level off with the increase of the exposure time (as shown in Figure 4 ).

[0079] Therefore, the penetration depth and curing position of the laser can be changed by adjusting the light intensity and light time of the projection light, so as to obtain a ceramic part with a controllable three-dimensional space thickness.

[0080] Based on the above principle, by adjusting the light intensity and light time of the projection light, the penetration depth and curing position of the laser can be changed, providing a theoretical basis for realizing the method of the present disclosure. In the present disclosure, the penetration depth and curing position of the laser are changed by adjusting the light intensity of the projection light; at the same time, the increase in the exposure time is avoided from having too much influence on the penetration depth and curing position, which is beneficial to realizing continuous printing by continuously projecting different slice images containing gray information, and is beneficial to improving the printing accuracy and efficiency.

[0081] The flowchart of some embodiments of model training in the 3D printing data processing method of the present disclosure is as Figure 5 shown.

[0082] In step 511, a gray value sequence is determined according to a predetermined gradient. In some embodiments, gray value sequences can be generated respectively according to the levels of gray values. For example, 256 sequences are generated to improve the accuracy of model training and subsequent printing.

[0083] In some embodiments, as mentioned above, when the gray value is less than 5, the light cannot be cured. Therefore, gray value sequences can be generated for gray values greater than 5, thereby reducing the data volume.

[0084] In some embodiments, the predetermined gradient can be set to be greater than 1, thereby further reducing the data volume to be processed and printed and improving the efficiency of sample acquisition and model training.

[0085] In step 512, for each gray value in the gray value sequence, gray image sample data is generated. In some embodiments, at least one shape of gray image can be generated for each gray value in the gray value sequence as the gray image sample data.

[0086] In step 513, using a stereolithography ceramic 3D printer, the three-dimensional data of the cured object generated by printing the gray image sample data is obtained, and the correspondence between the gray image sample data and the three-dimensional data of the corresponding cured object is determined. In some embodiments, after the stereolithography ceramic 3D printer finishes printing, the printed cured object can be scanned to obtain the three-dimensional data of the object, and then the gray image sample data used to print the object is associated with the three-dimensional data obtained by scanning the object to obtain the correspondence, which is used as a ceramic stereolithography sample. The illumination intensity of the light source adopted in the printing process in step 513 is the same as that adopted in subsequent use, so as to avoid inaccurate data conversion caused by inconsistent illumination intensity and improve the reliability of the data processing method.

[0087] In step 514, according to the correspondence between the gray image sample data of each gray value in the gray value sequence and the three-dimensional data of the cured object, ceramic stereolithography samples are obtained. For example, by summarizing each gray image sample data obtained for each gray value in step 512 above and the correspondence obtained in step 513, all ceramic stereolithography samples are obtained.

[0088] In step 515, the network built, such as a deep learning network, is trained using the ceramic stereolithography samples to obtain the machine learning model used in step S12 above, such as a generative network model.

[0089] Based on the method in the above - mentioned embodiments, the gray - scale information and the curing range are obtained through experiments and used as sample data to train a deep - learning network, so as to realize the reverse engineering of the curing effect (including depth and range) into a gray - scale image by using the deep - learning network, generate an image with gray - scale information, and thus realize the dynamic regulation of the projection light energy to form three - dimensional parts with different thicknesses in one step.

[0090] In some embodiments, as mentioned above, taking the use of a deep - learning neural network as an example, a sequence of gray - scale image sample data and the corresponding three - dimensional data are used as the input of the deep - learning network. For example, PointNet is used to extract the distribution features of the three - dimensional data. The calculation process is as follows:

[0091]

[0092]

[0093]

[0094] In the formula, and represent the global feature and the local feature of the three - dimensional data, represents the three - dimensional data (taking point - cloud data as an example).

[0095] Furthermore, the constructed 3D CNN is used to extract the image features in the gray - scale image sequence, and fuse them with the distribution features of the three - dimensional data to improve the semantic consistency of the two types of features, thereby establishing the mapping feature relationship between the single - layer image gray - scale value and the curing degree. Then, a recurrent neural network (RNN) is used to extract the sequential information of the gray - scale image sequence, that is, in each layer of the gray - scale image, the curing influence of the scattering effect of the exposure dose corresponding to the current layer on the previous layers. The calculation process of the RNN is as shown in the formula:

[0096]

[0097] In the formula, and represent the three - dimensional data + gray - scale fusion features of the current layer and the previous layer respectively, and represent the pre - set weight parameters respectively, is the input image of the current target structure, is the non - linear activation function.

[0098] Finally, an optimized gray - scale image sequence is generated through the image sequence generator, so as to realize the intelligent regulation of the projection light. The network structure flow of the above - mentioned processing process is as Figure 6 shown.

[0099] Based on the method in the above embodiments of the present disclosure, it is possible to intelligently and programmably regulate the degree of photocuring reaction caused by the projection light in different regions according to a predetermined design, obtain the relationship between the light dose and curing through a deep learning algorithm, generate the gray information of the optimized slice file, and then regulate the distribution and change of the projection light energy in three-dimensional space to different degrees. Thus, it is expected to form a ceramic component with a complex three-dimensional structure in one go in a very short time, without additional front and back processing steps of designing and removing printing support rods, simplifying the process and significantly improving the printing efficiency.

[0100] Flowcharts of some embodiments of the three-dimensional printing method of the present disclosure are as Figure 7 shown.

[0101] In step S71, a slice image is obtained. The slice image is generated according to any one of the three-dimensional printing data processing methods mentioned above.

[0102] In step S72, a light ray with a fixed intensity is emitted to the light ray adjustment mechanism. In some embodiments, the light ray adjustment mechanism is a DMD.

[0103] In step S73, the light ray adjustment mechanism adjusts the intensity of the light ray projected onto the printing platform according to the gray information in the slice image. The surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry. In some embodiments, during the process of printing the object corresponding to the slice image, the position between the printing platform and the light ray adjustment mechanism remains unchanged.

[0104] Based on the method in the above embodiments, it is possible to adjust the intensity of the light ray projected onto the printing platform by using the slice image including gray information obtained by converting the three-dimensional data of the object to be printed. Compared with a binary image, by using rich gray data, it is possible to more smoothly transition different regions, better display details and surface smoothness during printing exposure, reduce the step effect of the printing layer, improve the surface quality, and improve the printing accuracy; in addition, by changing the way of projecting an image including gray information from the way of layer-by-layer stacking printing, it is possible to avoid problems such as weak interlayer bonding and surface layer lines caused by the hierarchical structure, and further improve the printing accuracy.

[0105] Schematic diagrams of some embodiments of the three-dimensional printing data processing device of the present disclosure are as Figure 8 shown.

[0106] The slice image acquisition unit 813 can acquire a slice image including gray information according to the three-dimensional data of the object to be printed. In some embodiments, the slice image acquisition unit 812 can execute the method in any embodiment of step S12 above.

[0107] The data sending unit 814 can send the sliced image to the stereolithography ceramic printer. In the stereolithography ceramic printer, a light source emits light with a fixed intensity to a light ray adjusting mechanism. The light ray adjusting mechanism 3 adjusts the light intensity projected onto the printing platform according to the gray information in the sliced image, and the surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry. In some embodiments, the data sending unit 814 can execute the method in any of the above-mentioned steps S14.

[0108] Based on the device in the above embodiments, it is possible to adjust the light intensity projected onto the printing platform by using the sliced image including gray information converted from the three-dimensional data of the object to be printed. Compared with binary images, using rich gray data can achieve a smoother transition between different regions, better display details and surface smoothness during printing exposure, reduce the step effect of the printed layer, improve the surface quality, and improve the printing accuracy. In addition, by changing the way of projecting the image including gray information from the layer-by-layer stacking printing method, problems such as weak interlayer bonding and surface layer lines caused by the hierarchical structure can be avoided, further improving the printing accuracy.

[0109] In some embodiments, as Figure 8 shown, the three-dimensional printing data processing device further includes a sample data acquisition unit 811 and a model training unit 812.

[0110] The sample data acquisition unit 811 can determine a gray value sequence according to a predetermined gradient. For each gray value in the gray value sequence, it generates gray image sample data, uses the stereolithography ceramic printer to obtain the three-dimensional data of the solidified object generated by printing the gray image sample data, determines the correspondence between the gray image sample data and the three-dimensional data of the corresponding solidified object, and obtains the ceramic stereolithography sample according to the correspondence between the gray image sample data of each gray value in the gray value sequence and the three-dimensional data of the solidified object. In some embodiments, the sample data acquisition unit 811 can execute the method in any of the above-mentioned steps 511 - 514.

[0111] The model training unit 812 can use the ceramic stereolithography sample to train the constructed deep learning network to obtain a machine learning model, such as a generative network model. The sliced image acquisition unit 813 can obtain the gray information corresponding to the three-dimensional data based on the machine learning model, and obtain a sliced image including the gray information of each pixel point.

[0112] Based on the device in the above embodiments shown, it is possible to obtain the gray information and solidification range through experiments, use them as sample data to train the deep learning network, realize the reverse engineering of the solidification effect (including depth and range) to the gray image by using the deep learning network model, generate an image with gray information, so as to realize the dynamic regulation of the projection light energy and form three-dimensional parts with different thicknesses in one step.

[0113] The structural schematic diagram of an embodiment of the three-dimensional printing data processing device disclosed in the present disclosure is as shown in Figure 9 Figure. The three-dimensional printing data processing device includes a memory 901 and a processor 902. Among them: The memory 901 can be a magnetic disk, a flash memory, or any other non-volatile storage medium. The memory is used to store the instructions in the corresponding embodiment of the three-dimensional printing data processing method described above. The processor 902 is coupled to the memory 901 and can be implemented as one or more integrated circuits, such as a microprocessor or a microcontroller. The processor 902 is used to execute the instructions stored in the memory and can improve the accuracy of light-curing ceramic printing.

[0114] In one embodiment, it can also be as shown in Figure 10 Figure. The three-dimensional printing data processing device 1000 includes a memory 1001 and a processor 1002. The processor 1002 is coupled to the memory 1001 through the BUS bus 1003. The three-dimensional printing data processing device 1000 can also be connected to an external storage device 1005 through a storage interface 1004 to call external data, and can also be connected to a network or another computer system (not shown) through a network interface 1006. Details are not described here.

[0115] In this embodiment, by storing data instructions in the memory and then processing the above instructions through the processor, the accuracy of light-curing ceramic printing can be improved.

[0116] In another embodiment, a computer-readable storage medium stores computer program instructions, and when the instructions are executed by a processor, the steps of the method in the corresponding embodiment of the three-dimensional printing data processing method are implemented. Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a device, or a computer program product. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete 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 magnetic disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0117] The schematic diagrams of some embodiments of the three-dimensional printer disclosed in the present disclosure are as shown in Figure 11 Figure.

[0118] The communication mechanism 1211 can acquire sliced images. The sliced images are generated according to any of the three-dimensional printing data processing methods mentioned above, for example, generated by any of the three-dimensional printing data processing devices mentioned above. The sliced images are transmitted to the communication mechanism 1211 by wired or wireless means, and after being processed by the communication mechanism 1211 or the controller of the 3D printer, control instructions are sent to other parts of the 3D printer. The transmission direction of the instructions can be as Figure 11 shown by the direction of the thin arrow in

[0119] The light source 1122 can emit light with a fixed intensity to the light adjusting mechanism.

[0120] The light adjusting mechanism 1123 can adjust the light intensity projected onto the printing platform according to the gray-scale information in the sliced image. In some embodiments, the light adjusting mechanism 1123 can continuously project light according to the sliced image without interruption during the process of projecting different sliced images.

[0121] The surface of the printing platform 1124 is located on the upper surface of the photosensitive ceramic slurry, and the printing platform can carry the printed object. In some embodiments, the printing platform 1124 keeps its position unchanged.

[0122] The 3D printer in the above-described embodiments can adjust the light intensity projected onto the printing platform by using the sliced images including gray-scale information converted from the three-dimensional data of the object to be printed. Compared with binary images, by using rich gray-scale data, it can achieve a smoother transition between different regions, better display details and surface smoothness during printing exposure, reduce the step effect of the printed layers, improve the surface quality, and improve the printing accuracy; in addition, by changing the way of projecting images including gray-scale information from the layer-by-layer stacking printing method, it can avoid problems such as weak interlayer bonding and surface layer lines caused by the hierarchical structure, and further improve the printing accuracy.

[0123] Schematic diagrams of some embodiments of the 3D printing system of the present disclosure are as Figure 12 shown.

[0124] The 3D printing data processing device 1210 can be any of the 3D printing data processing devices mentioned above. The 3D printer 1220 can be any of the 3D printers mentioned above.

[0125] The three-dimensional printing system proposed in this disclosure can adjust the light intensity projected onto the printing platform by using a sliced image including gray-scale information converted from the three-dimensional data of the object to be printed. Compared with binary images, by using rich gray-scale data, it can more smoothly transition different regions, better display details and surface smoothness during printing exposure, reduce the step effect of the printed layer, improve the surface quality, and improve the printing accuracy. In addition, by changing the way of projecting the image including gray-scale information from the layer-by-layer stacking printing method, it can avoid problems such as weak interlayer bonding and surface layer lines caused by the hierarchical structure, and further improve the printing accuracy.

[0126] By establishing a mapping relationship between the surface projection light intensity and the curing effect through an intelligent programming control method based on deep learning, irradiating the forming area in a full-frame manner, and affecting the initiation sequence and degree of the photocuring slurry in different regions through linearly and dynamically changing projection light, and further optimizing the local photocuring reaction kinetic process, it is possible to suppress the over-curing phenomenon caused by light scattering and then eliminate the rough boundary to realize the three-dimensional forming of the target geometric body without layer-by-layer stacking and additional support. This method can greatly improve the printing efficiency of ceramic parts (the printing time is shortened by more than 1000 times), and fundamentally eliminate problems such as layer lines, internal stress, anisotropy, support structure, and part deformation, defects and fractures caused by removing the support during traditional layer-by-layer photocuring stacking forming.

[0127] The following shows the effects of the three-dimensional printing method, printer and system, and data processing method and device of this disclosure through multiple printing examples.

Example 1

[0128] To achieve the integrated forming of complex-shaped curved surface ceramic parts, first use three-dimensional modeling software to construct the printing model, with a maximum height of 0.2 cm, and arrange the models in a certain placement posture without adding a support structure (as shown in Figure 13 shown in (a)). Subsequently, decouple the three-dimensional information of the model into a series of two-dimensional sliced files containing pixel-level gray-scale information in the python programming software (as shown in Figure 13 shown in (b)). Specifically, set the two-dimensional horizontal size of the ceramic part model in the initial picture to 10.00×10.00 mm, and keep the gray-scale value at 255. Based on the deep learning network algorithm, linearly reduce the two-dimensional graph corresponding to the boundary contour of the extremely thin part (split into 10 steps for smooth display of the transition process) to 7 / 8 of the original area size.

[0129] The power of the fixed light source is 125 mW / cm 2, a commercially available photosensitive ceramic slurry is placed in a quartz plate with a self-made groove having a depth of 1 mm and an area of 50×50 mm (as shown in Figure 13 (c)), and after self-leveling, it is placed on the printing platform of an upper projection DLP printer (as shown in Figure 13 (d)). The exposure time of a single grayscale image is set to 0.1 s, and the above-mentioned sliced data set is continuously exposed until the end. Thus, the printing time for forming a complex free-form surface thin-walled ceramic part at one time is 40 s. This stereolithography method has extremely high forming efficiency, and ceramic parts can usually be completed within a few minutes.

[0130] As shown in Figure 13 (e), the overall appearance of the printed object shows a ceramic part with a 2.5D arc surface having a complex free-form surface. The physical object matches well with the preset model, and its bending depth changes along the longitudinal direction, conforming to the preset target. The method does not require additional front and back processing steps of designing and removing printing support rods, greatly simplifying the overall process; in addition, the method prepares a ceramic part by utilizing the light scattering generated by incident light and highly particle-filled ceramic slurry, showing its advantage of programmable design.

[0131]

Example 2

[0132] To achieve the integrated forming of complex-shaped curved surface ceramic parts, first, a three-dimensional modeling software is used to construct a printing model with a maximum height of 0.5 cm, and the models are arranged in a certain posture without adding a support structure (as shown in Figure 14 (a)). Subsequently, the three-dimensional information of the model is decoupled into a series of two-dimensional sliced files containing pixel-level grayscale information in a python programming software (as shown in Figure 14 (b)). Specifically, the two-dimensional maximum horizontal size of the ceramic part model in the initial image is set to 10.00×10.00 mm, and the grayscale value remains 255. Based on the deep learning network algorithm, the two-dimensional graph corresponding to the boundary contour of the extremely thin part is linearly reduced (split into 100 steps to smoothly display the transition process) to 1 / 4 of the original area size (as shown in Figure 14 (b)).

[0133] The power of the fixed light source is 125 mW / cm 2 , a commercially available photosensitive ceramic slurry is placed in a quartz plate with a self-made groove having a depth of 1 mm and an area of 50×50 mm (as shown in Figure 13 (c)), and after self-leveling, it is placed on the printing platform of an upper projection DLP printer (as shown in Figure 14(as shown in (c)). Set the exposure time of a single grayscale image to 0.1 s, and continuously expose the above slice dataset until completion, so that the printing time of the complex free-form surface thin-walled ceramic part is 5 min 30 s at one time. The stereolithography method has extremely high forming efficiency, and ceramic parts can usually be completed within a few minutes.

[0134] As Figure 14 (d) shows a physical picture of the printed part obtained in Example 2. The overall appearance shows a petal-shaped ceramic part with a large curvature. The physical object matches the preset model well, and the bending depth changes along the longitudinal direction, which is in line with the preset target. This method does not require additional front and back processing steps of designing and removing printing support rods, greatly simplifying the overall process; in addition, the method prepares the ceramic part by using the light scattering generated by the incident light and the highly particle-filled ceramic slurry, showing its advantage of programmable design.

[0135]

Example 3

[0136] In order to achieve the integrated forming of complex-shaped curved surface ceramic parts, first use 3D modeling software to construct the printing model, and arrange the models in a certain placement posture without adding a support structure (as Figure 15 (shown in (a)). Subsequently, decouple the three-dimensional information of the model into a series of two-dimensional slice files containing pixel-level grayscale information in the python programming software (as Figure 15 (shown in (b)). Specifically, set the two-dimensional horizontal size of the thin-walled ceramic part model in the initial picture to 11.86×9.8 mm, where the grayscale value linearly changes from 64 to 255 from left to right. Keeping this setting unchanged, based on the deep learning network algorithm, linearly reduce the two-dimensional graph corresponding to the boundary contour of the extremely thin part (split into 100 steps to smoothly display the transition process) to 3 / 4 of the original area size (as Figure 15 (shown in (b) and (c), where (c) shows the linear transformation and grayscale gradient diffusion process of the projection picture).

[0137] Fix the power of the light source at 200 mW / cm 2 , place the commercially available photosensitive ceramic slurry in a quartz plate with a self-made groove with a depth of 1 mm and an area of 50×50 mm (as Figure 13 (shown in (c)), and place it on the printing platform of the upper projection DLP printer after self-leveling (as Figure 13(as shown in (d)), set the exposure time of a single grayscale image to 0.1 s, and continuously expose the above slice dataset until it ends, so that the printing time of the complex freeform surface thin-walled ceramic part is formed at one time for 5 min 30 s. This stereolithography method has extremely high forming efficiency, and thin-walled ceramic parts can usually be completed within a few minutes.

[0138] According to the previous experimental results, decouple the three-dimensional information of the model, and by coupling the relationship between the critical exposure amount and the curing depth of the photocurable ceramic slurry, inversely calculate the required optical information, so as to obtain information such as the gray scale, light intensity, time, i.e., exposure superposition, etc. of the target 3D structure, and then realize the integrated construction of pixel-level light energy regulation and the three-dimensional morphology of the target part.

[0139] Figure 15 Figure (d) shows the physical diagram of the printed part obtained in Example 3. The overall appearance shows a thin-walled ceramic part with a complex freeform surface. The physical object matches well with the preset model (as Figure 15 shown in (e), which shows the fit degree between the formed thin-walled ceramic part and the preset model), can fit well with the model, and its thickness changes along the longitudinal direction, which is in line with the preset target (as Figure 15 shown in (f), which shows the thickness change of the stereolithography thin-walled ceramic part by three-dimensional scanning). By observing its microscopic morphology, it is found that the grain size distribution of the printed part obtained by this stereolithography is relatively uniform. Different from the preparation method of layer-by-layer stacking, the method completely eliminates the layer lines, reduces the interlayer defects and weak bonding interfaces, and effectively improves the manufacturing success rate and the performance of the part (as Figure 15 shown in (g), which shows the physical diagram and three-dimensional morphology diagram of the printed part. The two on the upper left are 1000 times magnified views of the outside and inside of the printed part; the one in the upper right corner is a 5000 times magnified view of the cross-section; the three below are 10000 times magnified views of the outside, inside, and cross-section of the printed part). At the same time, this method does not require additional front and back processing steps of designing and removing the printing support rods, which greatly simplifies the overall process; in addition, the ceramic part prepared by this method has a gradient thickness, indicating its advantage of programmable design.

Example 4

[0140] The steps of Example 4 are the same as those of Example 3, and the only difference is the setting method of the two-dimensional slice image of the printing model. Specifically: set the two-dimensional horizontal size of the model in the initial picture to 11.86×9.8 mm, where the gray scale values are fixed (the gray scale values are set to 64, 128, and 160 in sequence), so as to obtain a thin-walled ceramic part with a uniform thickness. Keep this setting unchanged, linearly reduce the two-dimensional graph of the contour of the thin-walled ceramic part model to 3 / 4 of the original size, and split it into 100 steps to smoothly display the transition process (as Figure 16as shown in (a) and (b), where Figure 16 (a) shows a slice file of the printed model containing information on the linear change in pixel-level graphic size, Figure 16 and (b) shows the linear transformation process of the projected picture.

[0141] As Figure 16 shown in (c) is a physical picture of the printed part obtained in Example 4. As Figure 16 shown in (d) is a comparison diagram of the thickness changes of the thin-walled ceramic parts obtained by the 3D scanning and stereolithography method in Example 3 (left picture) and Example 4 (right picture). The results show that, compared with Example 3, the thin-walled ceramic part obtained by uniformly linearly changing and exposing the projected picture in Example 4 has a relatively uniform thickness, and thin-walled ceramic parts with different uniform thicknesses can be obtained by adjusting the gray value.

Example 5

[0142] In the control example, the two-dimensional gray image converted from the contour of the thin-walled ceramic part model is directly exposed without any processing (gray value is 255) ( Figure 17 as shown in (a)), and the exposure time is set to 10 s. The results show that the obtained sample is quite different from the preset model, has no obvious curing boundary, and has a very poor matching degree with the preset model ( Figure 17 as shown in (b)).

[0143] The above results prove that, compared with the method of directly transmitting the binary image of the morphological structure of the object to be printed, the method of generating an image with gray information in the present disclosure can well control the printing range, improve the printing accuracy, reduce the workload of subsequent model repair, simplify the overall printing process, and improve the printing efficiency.

[0144] The different grayscales in the attached drawings of the specification of the present disclosure are only for effect display and do not provide additional information.

[0145] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (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, and the combination 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0146] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0148] So far, the present disclosure has been described in detail. To avoid obscuring the concept of the present disclosure, some details well known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

[0149] The methods and apparatuses of the present disclosure may be implemented in many ways. For example, the methods and apparatuses of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of the steps for the methods is for illustration only, and the steps of the methods of the present disclosure are not limited to the specific order described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the methods according to the present disclosure.

[0150] 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 do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data may be interchanged under appropriate circumstances 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 "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or apparatuses.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure and are not intended to limit them; although the present disclosure has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that: it is still possible to modify the specific implementation manners of the present disclosure or perform equivalent replacements for some technical features; without departing from the spirit of the technical solutions of the present disclosure, they should all be covered within the scope of the technical solutions claimed in the present disclosure.

Claims

1. A three-dimensional printing data processing method, comprising: Acquire a slice image containing grayscale information according to the three-dimensional data of the object to be printed; The slice image is sent to a light-curing ceramic printer, Among them, the light source in the light-curing ceramic printer emits light of fixed intensity to the light adjustment mechanism, and the light adjustment mechanism adjusts the intensity of light projected onto the printing platform according to the grayscale information in the slice image. The surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry.

2. The data processing method according to claim 1, wherein: The obtaining of the slice image containing grayscale information comprises: The grayscale information corresponding to the three-dimensional data is obtained based on a machine learning model, and the slice image including the grayscale information of each pixel is obtained.

3. The data processing method according to claim 2, wherein: The machine learning model is generated based on ceramic photocuring sample training, wherein the ceramic photocuring sample includes a correspondence between grayscale image sample data and corresponding three-dimensional data of the object after curing.

4. The data processing method according to claim 1, wherein: The light adjustment mechanism includes a digital micromirror chip DMD, and the DMD adjusts the reflection angle of the chip corresponding to the pixel according to the grayscale information to adjust the intensity of the light projected onto the printing platform.

5. The data processing method according to claim 1, wherein: The obtaining of the slice image containing grayscale information comprises: Acquire the grayscale information corresponding to each pixel according to the three-dimensional data, and acquire a first image including the grayscale information; The two-dimensional graphics corresponding to the boundary contour of the image are gradually linearly reduced or enlarged to a set ratio to generate a set number of second images as the slice image.

6. The data processing method according to claim 1, wherein: The step of obtaining a slice image containing grayscale information according to the three-dimensional data of the object to be printed comprises: Acquire model slice data according to the three-dimensional data; The slice images containing grayscale information are acquired respectively according to the three-dimensional data in each slice data.

7. The data processing method according to claim 6, wherein: The step of respectively acquiring the slice images containing grayscale information according to the three-dimensional data in each slice data comprises: For each piece of the slice data, respectively obtain the grayscale information corresponding to each pixel according to the three-dimensional data, and obtain a first image including the grayscale information; For each of the first images, the two-dimensional graphics corresponding to the boundary contour of the image are gradually linearly reduced or enlarged to a set ratio to generate a set number of second images as the slice images.

8. The data processing method according to claim 2, wherein: The light intensity of the light source used to generate the ceramic light-cured sample is the same as the light intensity of the light source in the light-cured ceramic printer; and / or The total printing time of the cured object corresponding to each sample data in the ceramic light-curing sample is generated, which is the same as the time taken by the light-curing ceramic printer to print one slice image.

9. The data processing method according to claim 3 or 8, further comprising: Determine a grayscale value sequence according to a predetermined gradient, generate grayscale image sample data for each grayscale value in the grayscale value sequence, obtain three-dimensional data of a cured object generated by printing the grayscale image sample data using the light-curing ceramic printer, and determine a corresponding relationship between the grayscale image sample data and the corresponding three-dimensional data of the cured object; Acquire the ceramic light-cured sample according to a mapping relationship between the grayscale image sample data of each grayscale value in the grayscale value sequence and the three-dimensional data of the cured object; The machine learning model is obtained by training a machine learning neural network constructed using the ceramic photocuring sample.

10. The data processing method according to claim 1, wherein: The object to be printed includes a tooth veneer.

11. A three-dimensional printing method for a light-curing ceramic printer, comprising: Acquire a slice image, wherein the slice image is generated according to the three-dimensional printing data processing method according to any one of claims 1 to 8; emitting light of a fixed intensity to the light adjustment mechanism; The light adjustment mechanism adjusts the intensity of light projected onto the printing platform according to the grayscale information in the slice image, and the surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry.

12. A three-dimensional printing data processing device, comprising: A slice image acquisition unit is configured to acquire a slice image containing grayscale information according to three-dimensional data of the object to be printed; a data sending unit, configured to send the slice image to a light-curing ceramic printer, Among them, the light source in the light-curing ceramic printer emits light of fixed intensity to the light adjustment mechanism, and the light adjustment mechanism adjusts the intensity of light projected onto the printing platform according to the grayscale information in the slice image. The surface of the printing platform is located on the upper surface of the photosensitive ceramic slurry.

13. The data processing apparatus according to claim 12, further comprising: a sample data acquisition unit configured to determine a grayscale value sequence according to a predetermined gradient, generate grayscale image sample data for each grayscale value in the grayscale value sequence, obtain three-dimensional data of a cured object generated by printing the grayscale image sample data using the light-curing ceramic printer, and determine a corresponding relationship between the grayscale image sample data and the corresponding three-dimensional data of the cured object; Acquire the ceramic light-cured sample according to the correspondence between the grayscale image sample data of each grayscale value in the grayscale value sequence and the three-dimensional data of the cured object; A model training unit is configured to use the ceramic light-curing sample to train the machine learning neural network to obtain the machine learning model. Among them, the slice image acquisition unit is configured to acquire the grayscale information corresponding to the three-dimensional data based on a machine learning neural network model, and acquire the slice image including the grayscale information of each pixel.

14. A three-dimensional printing data processing device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the method according to any one of claims 1 to 10 based on instructions stored in the memory.

15. A computer-readable storage medium having computer instructions stored thereon, which implement the method according to any one of claims 1 to 10 when executed by a processor.

16. A computer program product, comprising a computer program or instructions, wherein when the computer program or instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

17. A three-dimensional printer, comprising: A communication mechanism, configured to obtain a slice image, wherein the slice image is generated according to the three-dimensional printing data processing method according to any one of claims 1 to 8; a light source configured to emit light of a fixed intensity toward the light adjustment mechanism; A light adjustment mechanism configured to adjust the intensity of light projected onto the printing platform according to the grayscale information in the slice image; and A printing platform, the surface of which is located on the upper surface of the photosensitive ceramic slurry, is configured to carry the printed object.

18. A three-dimensional printing system, comprising: The three-dimensional printing data processing device according to any one of claims 12 to 14; and The three-dimensional printer of claim 17.

Images