An artificial intelligence-based light-cured 3D printing intelligent slicing optimization method

Abstract

The application provides an artificial intelligence-based light-curing 3D printing intelligent slicing optimization method, and relates to the technical field of light-curing 3D printing.The method collects 3D printing model file and printing parameter data to generate a target model summary file; performs slicing processing on model data in the target model summary file to generate model slice data; analyzes the geometric complexity of the model by using a deep convolutional neural network and dynamically adjusts the slice layer thickness based on the complexity coefficient; optimizes the printing quality, time and material consumption through multi-objective optimization, dynamically adjusts the printing settings according to the optimization results; monitors the printing state in real time, adjusts the slicing parameters according to the monitoring data, verifies the optimization results before actual printing, and adjusts and optimizes the slicing according to the verification results.The application can automatically analyze the 3D printing model file and printing parameter data input by the user, monitor the printing process in real time, dynamically adjust the slicing parameters, and improve the printing quality and efficiency.

Description

Technical Field

[0001] The present invention relates to the field of light-curing 3D printing technology, and in particular to an artificial intelligence-based light-curing 3D printing intelligent slicing optimization method. Background Art

[0002] As a key branch of additive manufacturing technology, stereolithography (SLA) 3D printing has been widely used in manufacturing, healthcare, jewelry, and other fields. In traditional SLA 3D printing, slicing parameters (such as layer thickness and exposure time) must be manually adjusted based on user experience or standard models. Due to factors such as model complexity and material properties, precise slicing settings are difficult to achieve, leading to frequent printing defects, material waste, and low production efficiency. Therefore, optimizing the slicing process through intelligent means has become a key issue in improving the quality of SLA 3D printing. Summary of the Invention

[0003] In order to solve the above problems, the present invention proposes an artificial intelligence-based light-curing 3D printing intelligent slicing optimization method. This method can automatically analyze the 3D printing model file and printing parameter data input by the user, monitor the printing process in real time, dynamically adjust the slicing parameters, improve printing quality and efficiency, and has dynamic adjustment capabilities to reduce printing defects and material waste.

[0004] The present invention is achieved by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a method for optimizing intelligent slicing of light-curing 3D printing based on artificial intelligence, the method comprising the following steps:

[0006] Collect 3D printing model files and printing parameter data to generate target model summary files;

[0007] Slice the model data in the target model summary file to generate model slice data;

[0008] Use deep convolutional neural networks to analyze the geometric complexity of the model and dynamically adjust the slice layer thickness based on the complexity coefficient;

[0009] Optimize print quality, time and material consumption through multiple objectives, and dynamically adjust print settings based on the optimization results;

[0010] Monitor the printing status in real time and adjust the slicing parameters according to the monitoring data. Verify the optimization results before actual printing and adjust and optimize the slicing based on the verification results.

[0011] As a further solution of the present invention, when collecting 3D printing model files and printing parameter data, it includes:

[0012] Get the 3D printing model file uploaded by the user;

[0013] Parse the geometric information in the model file and extract the basic geometric data of the 3D model;

[0014] Divide the model into several sub-models and identify the key features in the model.

[0015] As a further solution of the present invention, basic geometric data of the 3D model is extracted, including a triangular mesh structure, normal vector information, and surface area; key features of the model identified include surface, corner, and edge features of the 3D model.

[0016] As a further solution of the present invention, the collected printing parameter data includes the filling rate of the 3D model, the printing layer thickness, the printing speed, the hardness and flexibility of the photocurable resin, and the support structure data.

[0017] As a further solution of the present invention, when generating a target model summary file, models with the same printing parameters are summarized according to the printing parameter data, the model files are grouped according to the same parameters, all model files in the same group are summarized in a unified format and saved as a target model summary file. The summary file uses JSON or XML format.

[0018] As a further solution of the present invention, slicing the model data in the target model summary file to generate model slice data includes the following steps:

[0019] Initialize the slicing tool and set the basic parameters required for slicing, including slice layer thickness and filling structure;

[0020] The slicing engine of the slicing tool divides the 3D model into several two-dimensional cross sections to form slice layers for the printer to print layer by layer;

[0021] During slicing, the model is scanned layer by layer from bottom to top according to the geometric data, and the layer thickness is automatically adjusted to generate a two-dimensional cross-section of each layer;

[0022] After completing the slicing of all layers, output the sliced ​​data to the specified directory to obtain the slice files corresponding to each model.

[0023] As a further solution of the present invention, when using a deep convolutional neural network to analyze the geometric complexity of the model, the complexity adaptive adjustment steps are:

[0024] Feature areas of edges, corners, and surfaces based on image segmentation recognition models;

[0025] The complexity coefficient C of the model is calculated, and the slice layer thickness is adjusted according to the value of the complexity coefficient C.

[0026] As a further solution of the present invention, the calculation formula of the complexity coefficient C of the model is:

[0027]

[0028] When the complexity coefficient C is greater than the preset threshold, the layer thickness of the area is automatically reduced.

[0029] As a further aspect of the present invention, the layer thickness adjustment rule is defined by the following formula:

[0030]

[0031] in, is the maximum layer thickness, is the minimum layer thickness, is the geometric complexity coefficient.

[0032] As a further solution of the present invention, when optimizing printing quality, time and material consumption through multi-objective optimization, a genetic algorithm is used to optimize between printing quality, time and material consumption to find the optimal slicing strategy; wherein the objective function includes print quality Q, printing time T, and material consumption M; when estimating printing time, the slicing device obtains the remaining printing time of all 3D printers, and calculates the expected printing time of the model based on the printing parameter data, and distributes the slicing data in sequence to the 3D printers with the shortest remaining printing time according to the order of the printing time of the models from longest to shortest.

[0033] As a further solution of the present invention, the multi-objective optimization module uses a genetic algorithm to optimize printing parameters based on the following objective function:

[0034]

[0035] Among them, Q represents printing quality, T represents printing time, and M represents material consumption. and is the weight coefficient.

[0036] As a further solution of the present invention, the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method also includes determining the extreme radial distance of the slice layer; when determining the extreme radial distance of the slice layer, the layer image data of the slice layer is obtained, and the extreme radial distance between the slice layer and the center of the rotating support platform is determined, including the minimum radial distance and the maximum radial distance; the arc formed by the extreme radial distance is used to determine the boundary position of the printing.

[0037] As a further solution of the present invention, the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method also includes laser motion control; during laser motion control, the printing data of the slice layer is obtained, and the movement path and speed of the laser are controlled according to the boundary position and layer printing data.

[0038] In a second aspect, the present invention further includes an artificial intelligence-based light-curing 3D printing intelligent slicing optimization system, the system comprising:

[0039] The geometric complexity analysis module is used to receive and parse the input 3D printing model file, analyze the geometric complexity of the model based on the deep convolutional neural network (CNN) model, and output the geometric complexity coefficient C;

[0040] The slice thickness dynamic adjustment module is used to dynamically calculate and adjust the slice layer thickness h of different areas based on the geometric complexity coefficient C and the preset layer thickness adjustment rules, where the areas with higher complexity use smaller slice layer thicknesses, and the areas with lower complexity use larger slice layer thicknesses;

[0041] A multi-objective optimization module is used to optimize slicing parameters based on a multi-objective optimization algorithm for print quality, print time, and material consumption, generating the optimal combination of printing parameters, including but not limited to slice layer thickness, print speed, and fill rate, to achieve a balance between print quality, time, and material consumption;

[0042] The slice generation module is used to generate slice data and G-code instructions for each layer based on the optimized printing parameters, and dynamically adjust the slice layer thickness according to the geometric complexity of different areas;

[0043] The printing parameter feedback module is used to monitor the printing status in real time during the printing process, collect data on printing quality, time and material consumption, and feed it back to the multi-objective optimization module to dynamically adjust the printing settings to ensure continuous optimization of the printing effect.

[0044] As a further solution of the present invention, the geometric complexity analysis module converts the 3D model into a two-dimensional slice image or point cloud data, and uses a deep convolutional neural network to analyze the geometric complexity of each part.

[0045] As a further solution of the present invention, the layer thickness adjustment rule of the slice thickness dynamic adjustment module is defined by the following formula:

[0046]

[0047] in, is the maximum layer thickness, is the minimum layer thickness, is the geometric complexity coefficient.

[0048] As a further solution of the present invention, the multi-objective optimization module uses a genetic algorithm to optimize printing parameters based on the following objective function:

[0049]

[0050] Among them, Q represents printing quality, T represents printing time, and M represents material consumption. and is the weight coefficient.

[0051] As a further solution of the present invention, the printing parameter feedback module can further adjust the printing speed, layer thickness and material filling rate based on real-time monitoring data feedback, thereby achieving a dynamic balance between detail accuracy and time efficiency during the printing process.

[0052] As a further solution of the present invention, the artificial intelligence-based light-curing 3D printing intelligent slicing optimization system also includes a material selection module that automatically selects and adjusts material properties according to the specific requirements of the printing task to further optimize printing performance.

[0053] The present invention also includes a computer device comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method.

[0054] The present invention also includes a computer-readable storage medium storing computer instructions, which are used to enable the computer to execute the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method.

[0055] Compared with the existing technology, the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method provided by the present invention has the following beneficial effects:

[0056] 1. Accurate geometric complexity analysis: Through deep convolutional neural networks (CNN), the system can efficiently and accurately analyze the geometric complexity of 3D models, allowing the slicing optimization process to be adjusted according to the actual model complexity, improving printing accuracy and surface quality.

[0057] 2. Dynamic slice layer thickness adjustment is implemented: the slice layer thickness is dynamically adjusted according to the geometric complexity coefficient C of the model, so that complex areas use smaller layer thicknesses to improve detail accuracy, while simple areas use larger layer thicknesses to reduce printing time. The adjustment optimizes the balance between printing efficiency and model details.

[0058] 3. Achieved multi-objective optimization: By comprehensively considering printing quality, time and material consumption, the present invention can generate the optimal printing parameter combination and realize an efficient and economical printing solution, which can not only ensure printing quality but also reduce material waste and shorten printing time.

[0059] 4. Real-time feedback and adjustment: The printing parameter feedback module monitors and feedbacks data in real time during the printing process, dynamically adjusts the printing settings, and ensures continuous optimization of the printing effect. The real-time adjustment mechanism can respond to changes in actual printing and further improve printing quality and efficiency.

[0060] 5. Automated slice generation is achieved: Slice data and G-code instructions are automatically generated based on optimized parameters, which simplifies the user operation process and improves the system's automation level and user experience.

[0061] These and other aspects of the present invention will become more readily apparent in the following description of the embodiments. It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and are not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for the exemplary embodiments or related technical descriptions. The drawings are used to provide a further understanding of the present invention and constitute part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the drawings:

[0063] Figure 1 This is a flowchart of an artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to an embodiment of the present invention.

[0064] Figure 2 This is a flowchart of generating model slicing data in the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0067] The following will clearly and completely describe the technical solutions in the exemplary embodiments of the present invention in conjunction with the accompanying drawings of the exemplary embodiments of the present invention. Obviously, the exemplary embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0068] Due to changes in factors such as model complexity and material properties, it is difficult to achieve accurate slicing settings, resulting in frequent printing defects, material waste and low production efficiency. The present invention provides a light-curing 3D printing intelligent slicing optimization method based on artificial intelligence. By automatically analyzing the 3D printing model file and printing parameter data input by the user, and monitoring the printing process in real time, the slicing parameters are dynamically adjusted to improve printing quality and efficiency. The method has dynamic adjustment capabilities and reduces printing defects and material waste.

[0069] The technical solution of the present invention is further described below with reference to specific embodiments:

[0070] See Figure 1 As shown, Figure 1 A flowchart of an artificial intelligence-based smart slicing optimization method for photocuring 3D printing provided by the present invention. An artificial intelligence-based smart slicing optimization method for photocuring 3D printing provided in one embodiment of the present invention includes the following steps:

[0071] Step S10: Collect 3D printing model files and printing parameter data to generate a target model summary file.

[0072] In this step, collecting 3D printing model files and printing parameter data includes:

[0073] Obtain the 3D printing model file uploaded by the user; wherein, the 3D printing model file uploaded by the user can be saved in formats such as .stl, .obj or .3mf, and the 3D geometric information contained in the model file can include basic data such as vertices, edges and faces, as well as basic geometric data such as triangular mesh structure, normal vector information and surface area.

[0074] Parse the geometric information in the model file and extract the basic geometric data of the 3D model;

[0075] The model is divided into several sub-models, and key features in the model are identified, wherein the identified key features in the model include surface, corner and edge features of the 3D model.

[0076] In this embodiment, the collected printing parameter data includes but is not limited to: filling rate of the 3D model, printing layer thickness, printing speed, hardness and flexibility of the photocurable resin, and support structure data.

[0077] The fill rate is the filling density inside the model (such as 20%, 50%, etc.).

[0078] The print layer thickness is the height of each layer (such as 0.1mm, 0.2mm, etc.).

[0079] Printing speed is the speed at which the laser moves.

[0080] The hardness and flexibility of the photocurable resin are the material type and characteristic parameters of the photocurable resin.

[0081] Support structure data indicates whether additional support structures are required during printing to maintain the stability of the model.

[0082] In this embodiment, when generating a target model summary file, models with the same printing parameters are summarized according to the printing parameter data, the model files are grouped according to the same parameters, and all model files in the same group are summarized in a unified format and saved as a target model summary file. The summary file uses JSON or XML format.

[0083] Step S20: Slice the model data in the target model summary file to generate model slice data.

[0084] In this step, see Figure 2 As shown, slicing the model data in the target model summary file to generate model slice data includes the following steps:

[0085] Step S201: Initialize the slicing tool and set the basic parameters required for slicing, including slice layer thickness and filling structure. The layer thickness information of each model is read from the summary file, the printing height of each layer is initialized, and the filling mode during slicing, such as honeycomb, grid, etc., is set according to the internal filling rate of the model.

[0086] Step S202: Slice the 3D model into a number of two-dimensional cross sections using the slicing engine (Cura Engine) of the slicing tool to form slice layers for printing layer by layer by the printer;

[0087] Step S203: During slicing, the model is scanned layer by layer from bottom to top according to the geometric data, and the layer thickness is automatically adjusted to generate a two-dimensional cross section of each layer;

[0088] Step S204: After completing the slicing of all layers, output the slice data to the specified directory to obtain the slice file corresponding to each model.

[0089] Step S30: Analyze the geometric complexity of the model using a deep convolutional neural network, and dynamically adjust the slice layer thickness based on the complexity coefficient.

[0090] In this step, when using a deep convolutional neural network to analyze the geometric complexity of the model, the complexity adaptive adjustment steps are:

[0091] Feature areas of edges, corners, and surfaces based on image segmentation recognition models;

[0092] The complexity coefficient C of the model is calculated, and the slice layer thickness is adjusted according to the value of the complexity coefficient C.

[0093] As a further solution of the present invention, the calculation formula of the complexity coefficient C of the model is:

[0094]

[0095] When the complexity coefficient C is greater than the preset threshold, the layer thickness of the area is automatically reduced.

[0096] The layer thickness adjustment rule is defined by the following formula:

[0097]

[0098] in, is the maximum layer thickness, is the minimum layer thickness, is the geometric complexity coefficient.

[0099] Step S40: Optimize printing quality, time, and material consumption through multiple objectives, and dynamically adjust printing settings according to the optimization results.

[0100] In this step, a genetic algorithm is used to optimize the printing quality, time and material consumption through multi-objective optimization to find the optimal slicing strategy. The objective function includes print quality Q, printing time T, and material consumption M. When estimating the printing time, the slicing device obtains the remaining printing time of all 3D printers and calculates the expected printing time of the model based on the printing parameter data. The slicing data is distributed in order from the longest to the shortest printing time to the 3D printers with the shortest remaining printing time.

[0101] The multi-objective optimization module uses a genetic algorithm to optimize printing parameters based on the following objective functions:

[0102]

[0103] Among them, Q represents printing quality, T represents printing time, and M represents material consumption. and is the weight coefficient.

[0104] Step S50: monitor the printing status in real time, adjust the slicing parameters according to the monitoring data, verify the optimization results before actual printing, and adjust and optimize the slicing according to the verification results.

[0105] In this step, the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method also includes determining the extreme radial distance of the slice layer; when determining the extreme radial distance of the slice layer, the layer image data of the slice layer is obtained, and the extreme radial distance between the slice layer and the center of the rotating support platform is determined, including the minimum radial distance and the maximum radial distance; the arc formed by the extreme radial distance is used to determine the boundary position of the printing.

[0106] In the present invention, the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method also includes laser motion control; during laser motion control, the printing data of the slice layer is obtained, and the movement path and speed of the laser are controlled according to the boundary position and layer printing data.

[0107] It should be understood that, although the above is described in a certain order, these steps are not necessarily performed in sequence according to the above order. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, a part of the steps of the present embodiment may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps.

[0108] In one embodiment, the present invention provides an artificial intelligence-based intelligent slicing optimization system for stereolithography 3D printing, which is used to execute the artificial intelligence-based intelligent slicing optimization method for stereolithography 3D printing. The system includes:

[0109] The geometric complexity analysis module is used to receive and parse the input 3D printing model file, analyze the geometric complexity of the model based on the deep convolutional neural network (CNN) model, and output the geometric complexity coefficient C;

[0110] The slice thickness dynamic adjustment module is used to dynamically calculate and adjust the slice layer thickness h of different areas based on the geometric complexity coefficient C and the preset layer thickness adjustment rules, where the areas with higher complexity use smaller slice layer thicknesses, and the areas with lower complexity use larger slice layer thicknesses;

[0111] A multi-objective optimization module is used to optimize slicing parameters based on a multi-objective optimization algorithm for print quality, print time, and material consumption, generating the optimal combination of printing parameters, including but not limited to slice layer thickness, print speed, and fill rate, to achieve a balance between print quality, time, and material consumption;

[0112] The slice generation module is used to generate slice data and G-code instructions for each layer based on the optimized printing parameters, and dynamically adjust the slice layer thickness according to the geometric complexity of different areas;

[0113] The printing parameter feedback module is used to monitor the printing status in real time during the printing process, collect data on printing quality, time and material consumption, and feed it back to the multi-objective optimization module to dynamically adjust the printing settings to ensure continuous optimization of the printing effect.

[0114] The geometric complexity analysis module converts the 3D model into two-dimensional slice images or point cloud data, and uses a deep convolutional neural network to analyze the geometric complexity of each part.

[0115] In this embodiment, the slice thickness adjustment rule of the dynamic slice thickness adjustment module is defined by the following formula:

[0116]

[0117] in, is the maximum layer thickness, is the minimum layer thickness, is the geometric complexity coefficient.

[0118] The multi-objective optimization module uses a genetic algorithm to optimize printing parameters based on the following objective functions:

[0119]

[0120] Among them, Q represents printing quality, T represents printing time, and M represents material consumption. and is the weight coefficient.

[0121] The printing parameter feedback module can further adjust the printing speed, layer thickness and material filling rate based on the real-time monitoring data feedback, so as to achieve a dynamic balance between detail accuracy and time efficiency during the printing process.

[0122] The artificial intelligence-based light-curing 3D printing intelligent slicing optimization system of the present invention also includes a material selection module that automatically selects and adjusts material properties according to the specific requirements of the printing task to further optimize printing performance.

[0123] In this embodiment, the artificial intelligence-based light-curing 3D printing intelligent slicing optimization system adopts the steps of the aforementioned artificial intelligence-based light-curing 3D printing intelligent slicing optimization method during execution. Therefore, the operation process of the artificial intelligence-based light-curing 3D printing intelligent slicing optimization system will not be introduced in detail in this embodiment.

[0124] In summary, the present invention's AI-based intelligent slicing optimization method for stereolithography 3D printing utilizes a deep convolutional neural network (CNN) to efficiently and accurately analyze the geometric complexity of 3D models. The system converts 3D model data into a format suitable for CNN processing, such as two-dimensional slice images or point cloud data, and uses the CNN model to extract geometric complexity features and generate a geometric complexity coefficient C. This intelligent complexity analysis method ensures that the slicing process can adapt to the complexity of the model in real time, improving the accuracy of printed details and surface quality. The present invention dynamically adjusts the slice layer thickness based on the geometric complexity coefficient C. Using preset layer thickness adjustment rules, the slice layer thickness for different regions is automatically calculated and adjusted. Complex areas use smaller layer thicknesses to preserve detail, while simple areas use larger layer thicknesses to speed up printing. This dynamic adjustment mechanism significantly improves printing efficiency and the balance between model detail, optimizing the overall printing effect.

[0125] The present invention introduces multi-objective optimization, comprehensively considering print quality, print time, and material consumption to generate the optimal combination of printing parameters. By optimizing the objective function, this method reduces material waste and shortens printing time while ensuring high print quality, achieving an efficient and economical printing solution. The printing parameter feedback module of the present invention monitors the printing status in real time during the printing process, collects data on print quality, time, and material consumption, and feeds back to the multi-objective optimization module. Based on the real-time monitoring data, the system can dynamically adjust printing parameters (such as print speed, layer thickness, material fill rate) to ensure continuous optimization of the printing effect. The real-time adjustment mechanism can flexibly respond to changes in actual printing, further improving print quality and efficiency.

[0126] Combined with optimized printing parameters, the present invention can automatically generate slice data and G-code instructions for each layer. The slice generation module dynamically adjusts the slice layer thickness according to the geometric complexity of different areas to ensure that the generated slice data meets the optimal printing parameters. This not only simplifies the user operation process, but also improves the system's automation level and user experience. By combining artificial intelligence technology and multi-objective optimization methods, the present invention proposes an intelligent and automated light-curing 3D printing slice optimization method. This method not only improves printing accuracy and efficiency, but also significantly reduces material consumption and printing time, and has broad application prospects and significant practical value.

[0127] Through comprehensive data acquisition, intelligent semantic analysis, precise homework guidance and efficient personalized homework generation, the accuracy and personalization of homework generation have been significantly improved, promoting the improvement of students' learning outcomes and education quality.

[0128] In one embodiment, a computer device is further provided in an embodiment of the present invention, comprising at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor performs the steps of the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method.

[0129] In one embodiment, the present invention further provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the steps of the artificial intelligence-based light-curing 3D printing intelligent slicing optimization method.

[0130] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program represented by computer instructions. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above-mentioned methods. In addition, any reference to memory, storage, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory.

[0131] Non-volatile memory may include read-only memory, magnetic tape, floppy disk, flash memory, or optical storage. Volatile memory may include random access memory or external cache memory. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory or dynamic random access memory.

[0132] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A light-curing 3D printing intelligent slicing optimization method based on artificial intelligence, characterized in that: The method comprises the following steps: Collect 3D printing model files and printing parameter data to generate target model summary files; Slice the model data in the target model summary file to generate model slice data; Use deep convolutional neural networks to analyze the geometric complexity of the model and dynamically adjust the slice layer thickness based on the complexity coefficient; Optimize print quality, time and material consumption through multiple objectives, and dynamically adjust print settings based on the optimization results; Monitor the printing status in real time and adjust the slicing parameters according to the monitoring data. Verify the optimization results before actual printing and adjust and optimize the slicing according to the verification results. When using a deep convolutional neural network to analyze the geometric complexity of the model, the complexity adaptive adjustment steps are: Feature areas of edges, corners, and surfaces based on image segmentation recognition models; Calculate the complexity coefficient C of the model and adjust the slice layer thickness according to the value of the complexity coefficient C; Among them, the calculation formula of the complexity coefficient C of the model is: When the complexity coefficient C is greater than the preset threshold, the layer thickness of the area is automatically reduced; The layer thickness adjustment rule is defined by the following formula: in, is the maximum layer thickness, is the minimum layer thickness, is the geometric complexity coefficient.

2. The artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to claim 1, characterized in that: When collecting 3D printing model files and printing parameter data, include: Get the 3D printing model file uploaded by the user; Parse the geometric information in the model file and extract the basic geometric data of the 3D model; Divide the model into several sub-models and identify the key features in the model.

3. The artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to claim 2, characterized in that: Extracting basic geometric data of 3D models including triangular mesh structure, normal vector information and surface area; identifying key features of the model including surface, corner and edge features of the 3D model; The collected printing parameter data includes the filling rate of the 3D model, printing layer thickness, printing speed, hardness and flexibility of the photocurable resin, and support structure data.

4. The artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to claim 3, characterized in that: When generating a target model summary file, summarize the models with the same printing parameters based on the printing parameter data, group the model files by the same parameters, summarize all the model files in the same group in a unified format, and save them as a target model summary file in JSON or XML format.

5. The artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to claim 4, characterized in that: Slicing the model data in the target model summary file to generate model slice data includes the following steps: Initialize the slicing tool and set the basic parameters required for slicing, including slice layer thickness and filling structure; The slicing engine of the slicing tool divides the 3D model into several two-dimensional cross sections to form slice layers for the printer to print layer by layer; During slicing, the model is scanned layer by layer from bottom to top according to the geometric data, and the layer thickness is automatically adjusted to generate a two-dimensional cross-section of each layer; After completing the slicing of all layers, output the sliced ​​data to the specified directory to obtain the slice files corresponding to each model.

6. The artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to claim 5, characterized in that: When optimizing print quality, time, and material consumption through multiple objectives, a genetic algorithm is used to optimize between print quality, time, and material consumption to find the optimal slicing strategy. The objective function includes print quality Q, print time T, and material consumption M. When estimating print time, the slicing device obtains the remaining print time of all 3D printers and calculates the expected print time of the model based on the printing parameter data. The slicing data is then distributed in order from longest to shortest print time to the 3D printer with the shortest remaining print time.

7. The artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to claim 6, characterized in that: The multi-objective optimization adopts a genetic algorithm to optimize the printing parameters based on the following objective function: Among them, Q represents printing quality, T represents printing time, and M represents material consumption. and is the weight coefficient.

8. The artificial intelligence-based light-curing 3D printing intelligent slicing optimization method according to claim 1, characterized in that: The artificial intelligence-based light-curing 3D printing intelligent slicing optimization method also includes determining the limit radial distance of the slice layer; when determining the limit radial distance of the slice layer, layer image data of the slice layer is obtained, and the limit radial distance between the slice layer and the center of the rotating support platform is determined, including the minimum radial distance and the maximum radial distance; and the printing boundary position is determined using the arc formed by the limit radial distance.

Images