3D printing intelligent control system

Abstract

The invention, which belongs to the technical field of 3D printing intelligent control, discloses a 3D printing intelligent control system comprising a user terminal and an execution terminal. The user side comprises a model module, an analysis module, a manual parameter module and a remote control module; the model module is used for determining a target model of a printing target; the analysis module is used for analyzing the target model, determining printing control parameters of the printing target and sending the printing control parameters to the remote control module; the manual parameter module is used for manually setting printing control parameters by a user and sending the printing control parameters to the remote control module; the remote control module is used for remotely controlling the 3D printing equipment according to the received printing control parameters; identifying the received printing control parameter, generating a corresponding control instruction according to the printing control parameter, and sending the control instruction to the execution end; and the execution end is used for controlling the 3D printing equipment to perform 3D printing according to the received control instruction to obtain a 3D printing product of the printing target.

Description

Technical Field

[0001] The invention belongs to the technical field of 3D printing intelligent control, and in particular is a 3D printing intelligent control system. Background Art

[0002] With the rapid development of 3D printing technology, its application fields are becoming increasingly extensive, gradually penetrating from the professional field to the home user market. Home 3D printing equipment has been favored by more and more consumers with its diversified functions such as personalized manufacturing, education and entertainment. However, existing home 3D printing equipment still has significant problems in intelligent control, especially the complexity of operation and low printing efficiency, which seriously affects the personalized manufacturing experience of home users and the teaching application for children. The 3D printing process involves many parameter settings, such as printing speed, temperature, layer thickness, etc. Home users often lack relevant professional knowledge and find it difficult to accurately adjust these parameters, which affects the printing effect. Especially for family members who are not familiar with technology, such as children and the elderly, it increases the difficulty of operation.

[0003] Based on this, in order to solve the above problems, the present invention provides a 3D printing intelligent control system. Summary of the invention

[0004] In order to solve the problems existing in the above-mentioned solutions, the present invention provides a 3D printing intelligent control system.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A 3D printing intelligent control system, comprising a user end and an execution end; The user end includes a model module, an analysis module, a manual parameter module, and a remote control module; The model module is used to determine the target model of the printing target; Further, the model module includes an input conversion unit and a standard model unit; The input conversion unit is used for the user to upload the conversion model of the printing target, and convert the conversion model to obtain the target model of the printing target; The standard model unit is used by the user to establish the target model of the printing target according to a preset modeling method.

[0006] Furthermore, the method for converting the conversion model includes: The platform presets the model requirements, and establishes a conversion judgment model based on the model requirements. The expression of the conversion judgment model is: ; Where: (MU, BM) is the input data, MU is the model identification feature set of the transformation model; BM is the model requirement; MU→BM means that the model identification feature set meets the model requirement; the output data is the transformation judgment value ZP (MU, BM), and the transformation judgment value is 1 or 0; Performing feature recognition on the conversion model to obtain a model recognition feature set of the conversion model; Analyzing the model recognition feature set through the conversion judgment model to obtain a conversion judgment value of the conversion model; When the conversion judgment value is 1, the conversion model is marked as a target model; When the conversion judgment value is 0, the model non-conformity item is determined, and the conversion model is converted according to the model non-conformity item to obtain the target model.

[0007] Furthermore, the model module further includes a shortcut model unit, which is used for the user to establish a target model of a printing target and obtain the user's printing target material, wherein the printing target material includes a printing target picture and target requirements; An initial model is generated according to the printing target material, and the initial model is optimized and adjusted according to preset optimization factors to obtain a target model, wherein the optimization factors include the amount of consumables and the printing time.

[0008] Furthermore, the method for obtaining the user's printing target material includes: Obtaining target description data of the printing target from the user; performing image retrieval according to the target description data to obtain a number of target images to be selected that meet the target description data; Estimate the printing time of the target image to be selected, and mark it as the estimated time to be selected; sort the target images to be selected in ascending order of the estimated time to be selected to obtain a recommendation list; The recommendation list is displayed to the user, and the user selects less than or equal to K of the target images to be selected as user selected images, where K is a positive integer; and the printing target image of the printing target is determined according to the user selected images; A material template is generated according to the printing target picture, a user is assisted in setting a target requirement according to the material template and the printing target picture, and a printing target material is generated according to the target requirement and the printing target picture.

[0009] Furthermore, the printing target picture is the user-selected picture with the shortest estimated selection time.

[0010] Furthermore, the printing target picture is a combined picture of pictures selected by the user.

[0011] Furthermore, the method for optimizing and adjusting the initial model according to preset optimization factors includes: Step SA1: performing a printing simulation on the initial model to obtain the simulated consumables amount and simulation duration of the initial model; calculating a corresponding optimization evaluation value according to a preset optimization evaluation formula, and marking the optimization evaluation value of the initial model as a benchmark evaluation value; Step SA2: forming an adjustment requirement according to the printing target material and the benchmark evaluation value, wherein the adjustment requirement includes satisfying the printing target material requirement and the optimized evaluation value of the adjusted initial model being less than the benchmark evaluation value; adjusting the initial model according to the adjustment requirement to form a new initial model, and determining the benchmark evaluation value of the new initial model; Step SA3: loop step SA2 until there is no new initial model, and mark the initial model as the target model.

[0012] Furthermore, the optimization evaluation formula is: ; Where: YP is the optimization evaluation value; b1 and b2 are proportional coefficients, and the value range is 0≤b1≤1, 0≤b2≤1; HL is the simulated consumables; TM is the simulation time.

[0013] Furthermore, when the target model does not meet the user's requirements, model change data is generated according to the adjustment process of the initial model, and the user determines the target model that meets the user's requirements according to the model change data.

[0014] The analysis module is used to analyze the target model, determine the printing control parameters of the printing target, and send the printing control parameters to the remote control module.

[0015] Furthermore, the method for determining the printing control parameters includes: Analyze the target model, determine the initial printing parameters, and obtain the user's printing requirements; The initial printing parameters are adjusted according to the printing requirements to obtain printing control parameters of the printing target.

[0016] The manual parameter module is used for the user to manually set the printing control parameters and send the printing control parameters to the remote control module.

[0017] The remote control module is used to remotely control the 3D printing device according to the received printing control parameters; identify the received printing control parameters, generate corresponding control instructions according to the printing control parameters, and send the control instructions to the execution end.

[0018] The execution end is used to control the 3D printing device to perform 3D printing according to the received control instruction, so as to obtain the 3D printed product of the printing target.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention realizes intelligent 3D printing in application scenarios through the mutual cooperation between various modules, and solves the problem that the current home 3D printing cannot intelligently follow the user's needs for intelligent adjustment; at the same time, through the settings of the user end and the execution end, the service resources at the user's place are fully utilized, and it is also convenient for users to manage printing, and the probability of equipment failure that may be operated by directly operating the 3D printing equipment is reduced; through the integration of intelligent control functions, the full-process automatic monitoring and adjustment of the 3D printing process is realized; users do not need to have professional 3D printing knowledge to easily complete the printing task, which greatly reduces the difficulty of operation and improves the user experience; it is not only suitable for the daily printing needs of individual users, but also can be used as a tool for family education and innovation. By providing rich 3D printing resources and tutorials, this system can stimulate children's creativity and imagination, and cultivate their hands-on ability and problem-solving ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0022] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] like Figure 1 As shown, a 3D printing intelligent control system includes a user end and an execution end; The user terminal is used by users in smart devices, such as common smart phones, computers, etc., and can be set in the form of apps, small programs, etc., and is specifically set according to user needs and platform needs; including model modules, analysis modules, manual parameter modules, and remote control modules; The model module is used to determine the product model of the product to be 3D printed, mark it as the target model, and mark the 3D product to be printed as the printing target; The model module includes a quick model unit, a standard model unit and an input conversion unit; The shortcut model unit, the standard model unit and the input conversion unit correspond to three ways of determining the target model respectively.

[0024] The input conversion unit is used for users to upload product models of printing targets obtained by other means, mark them as conversion models, and convert the conversion models according to the model requirements of the target model to form a target model. For example, data conversion such as format can be converted using existing methods; it is used to solve the problem of incompatibility of conversion models obtained by home users from the Internet, friends and other channels.

[0025] In one embodiment, the target model may be transformed as follows: The platform presets model requirements, such as file format requirements, etc.; a conversion judgment model is established according to the model requirements. The conversion judgment model is used to identify the conversion model and determine whether the conversion model meets the model requirements. The expression of the conversion judgment model is: ; Where: (MU, BM) is the input data, MU is the model identification feature set of the transformation model; BM is the model requirement; MU→BM means that the model identification feature set meets the model requirement; the output data is the transformation judgment value ZP (MU, BM), and the transformation judgment value is 1 or 0; Perform feature recognition on the conversion model to obtain a model recognition feature set of the conversion model, that is, determine the model recognition features that need to be recognized according to the model requirements, such as file format, etc.; Analyzing the model recognition feature set through the transformation judgment model to obtain the transformation judgment value of the transformation model; When the conversion judgment value is 1, the conversion model is marked as the target model; When the conversion judgment value is 0, the model non-conforming items are determined, that is, the corresponding data items that do not meet the model requirements, such as data items corresponding to the file format; the conversion model is transformed according to the model non-conforming items to obtain the target model.

[0026] The standard model unit is used by the user to establish a target model of the printing target according to a preset modeling method, such as modeling according to a specified 3D modeling software, and can be set in accordance with the current 3D printing modeling method.

[0027] The quick model unit is used for the user to quickly establish a target model of a printing target and obtain the user's printing target material, which includes a printing target picture, corresponding description requirements for the printing target and other data; Generate an initial model based on the printing target material, optimize and adjust the initial model according to the preset optimization factors to obtain the target model. The optimization factors include the amount of consumables and printing time.

[0028] In one embodiment, the printing target material can be set by the user, such as collecting and uploading pictures of the printing target and corresponding description requirements of the printing target by the user.

[0029] In one embodiment, most of the quick model units are for interesting teaching, simple applications, etc. at home. It takes time and energy for users to set the printing target materials by themselves. Therefore, in this embodiment, the following method is used to assist users in setting the printing target materials. The method includes: Obtain target description data of the user for the printing target, such as a No. 5 wrench, a sphere with a diameter of 5 cm, and other related descriptions; Perform image retrieval according to the target description data, obtain a number of candidate target images that meet the target description data, estimate the printing time of each candidate target image, mark them as the candidate estimated time, and use existing estimation methods to estimate the printing time, such as estimating according to the historical printing data of the 3D printer; sort the candidate target images in ascending order of the candidate estimated time to obtain a recommendation list; display the recommendation list to the user, and the user selects less than or equal to K candidate target images as user selection images, where K is a positive integer set by the platform, and is generally set in the interval [3, 5]; Determine a print target image of a print target according to an image selected by a user; Generate a material template based on a print target image, that is, generate a target model of a print target based on the print target image. The target model is generated based on the print target image. The target model is used to prompt the user what target requirements are needed, such as common sizes and models. The existing physical products for reference can also be determined based on the print target image. The referenced physical product information is provided for the user to choose and then determine the target requirements. For example, a template generation model can be established based on a neural network such as a CNN network or a DNN network. The corresponding training set is established manually for training. The training set includes input data and output data. The input data is the print target image, and the output data is the material template. The template generation model after successful training is used for analysis. Assist users to set target requirements based on material templates and printed target images, such as voice inquiry, material template display, etc. Generate printing target materials according to target requirements and printing target images.

[0030] In one embodiment, a print target picture of a print target is determined according to a user selected picture, and the print target picture is a user selected picture with the shortest estimated time to be selected among the user selected pictures.

[0031] In one embodiment, a printing target picture of a printing target is determined based on a picture selected by a user. The printing target picture is a combination picture of pictures selected by each user. That is, the printing time of each target part in the picture selected by each user is estimated first, and the product in a picture selected by a certain user is used as a benchmark. For example, the user selected picture with the shortest estimated time to be selected is replaced and combined according to the printing time of each part to form a product with the shortest time and stable structure. After confirmation by the user, it is marked as a printing target image. If the user is not satisfied with the combined image, the unsatisfactory part is marked, and replacement and adjustment are performed until the user's requirements are met.

[0032] In one embodiment, the user-selected pictures may be combined based on other existing methods to form a print target picture, and the combination may be performed based on the printing time requirement.

[0033] In one embodiment, an initial model is generated based on the printing target material. The initial model is the first model generated based on the printing target material that meets the requirements of the printing target material, such as being generated directly based on existing model generation technology; or matching can be performed based on the printing target material to obtain an existing model that meets the requirements of the printing target material, that is, matching is performed based on the appearance being the same as or highly similar to the printing target image; corresponding parameters such as size are adjusted according to the target requirements to meet the printing material requirements; there are multiple ways to generate the initial model.

[0034] In one embodiment, the method for optimizing and adjusting the initial model according to the optimization factors includes: Step SA1: Perform printing simulation on the initial model to obtain the simulated consumables amount and simulation time; calculate the corresponding optimization evaluation value according to the preset optimization evaluation formula and mark it as the benchmark evaluation value; The optimization evaluation formula is: ; Where: YP is the optimization evaluation value; b1 and b2 are both proportional coefficients, with a value range of 0≤b1≤1, 0≤b2≤1; HL is the simulated consumables; TM is the simulation time; to remove the dimension, the numerical value is taken for calculation; Step SA2: forming an adjustment requirement according to the printing target material and the benchmark evaluation value, the adjustment requirement including satisfying the printing target material requirement and the optimized evaluation value of the adjusted initial model being less than the benchmark evaluation value; adjusting the initial model according to the adjustment requirement to form a new initial model, and determining the benchmark evaluation value of the new initial model; Step SA3: loop step SA2 until there is no new initial model, and mark the last obtained initial model as the target model; When the user is not satisfied with the target model, model change data is generated according to the adjustment change process of the initial model, that is, the adjustment change process data of the initial model. The change video, picture, etc. can be used as the adjustment change process data. The user determines the target model that meets the user's requirements based on the model change data.

[0035] In one embodiment, the initial model is simulated for printing, specifically, the model is printed in the manner of subsequent 3D printing according to the target model, and the corresponding consumables amount and printing time are estimated, which are marked as simulated consumables amount and simulation time. The estimation can also be performed based on other existing methods.

[0036] Exemplarily, the platform establishes a simulation evaluation model based on 3D printing, and the simulation evaluation model is used to simulate and evaluate the initial model or the subsequent optimized initial model to determine the corresponding simulation consumables and simulation time; such as: Collect 3D model data: Obtain 3D models of various types and complexities as training samples; ensure that these models have been successfully printed and record the actual printing time and consumables amount.

[0037] Collect printer performance data: record the technical parameters of different printers, such as printing speed, layer thickness, nozzle diameter, etc. Obtain the performance of the printer under different conditions, such as printing efficiency under different materials and different temperatures.

[0038] Data preprocessing: Standardize 3D model data, such as unifying size, resolution, etc. Normalize printer performance data to facilitate subsequent calculation and analysis.

[0039] Feature extraction: Extract key features from the 3D model, such as volume, surface area, complexity (such as number of faces, level of detail), etc. Consider printer-related features such as printing speed, layer thickness, filling density, etc.

[0040] Feature selection: Use feature selection algorithms (such as information gain, chi-square test, etc.) to screen out features that have a significant impact on the prediction of printing time and consumables. Remove redundant and noisy features to improve the prediction accuracy and generalization ability of the model.

[0041] Model selection: Choose an appropriate machine learning algorithm based on the nature of the problem and the characteristics of the data, such as linear regression, decision tree, random forest, neural network, etc. For complex nonlinear relationships, you can consider using deep learning algorithms (such as convolutional neural network CNN) for modeling.

[0042] Train the model: The model is trained using the preprocessed dataset, and the model parameters are continuously adjusted to minimize the prediction error. The performance of the model is evaluated using methods such as cross-validation to ensure that the model has good generalization ability.

[0043] Model optimization: Adjust the model structure and parameters based on the validation results to improve prediction accuracy. Consider using ensemble learning methods (such as bagging, boosting, etc.) to further improve model performance.

[0044] Model verification: Use new, untrained 3D models and printer data to verify that the model can accurately predict printing time and consumables. Analyze the difference between the predicted results and the actual values, identify possible sources of error and make corrections.

[0045] In one embodiment, the initial model is sliced ​​using professional 3D printing software, and the printing time and consumables are estimated. Such software can usually accurately estimate the printing time and consumables based on the model's geometry, size, printing speed, layer height, and other printing parameters.

[0046] In one embodiment, the initial model is adjusted according to the adjustment requirements, and the adjustment can be performed in an existing manner, such as by establishing an intelligent adjustment model for intelligent adjustment; Establishment of intelligent adjustment model: Clarify the goal of intelligent adjustment, that is, shorten the optimization evaluation value while ensuring that the initial model meets the requirements of the target printing material. Use the adjustment requirements as constraints in the intelligent adjustment process.

[0047] In order to train the intelligent adjustment model, a large amount of 3D model data and its corresponding printing parameters and optimization evaluation values ​​need to be collected. This data can come from actual 3D printing cases or be obtained through simulation. When collecting data, it is necessary to ensure the diversity and representativeness of the data to cover 3D models of different complexity and types.

[0048] Extract key features from the collected 3D model data, which should be able to reflect the model's geometry, size, complexity, printing parameters, etc. Then, use feature selection algorithms to screen out features that have a significant impact on the optimization evaluation value to improve the accuracy and efficiency of the intelligent adjustment model.

[0049] Based on the extracted features, a prediction model is established using machine learning or deep learning algorithms. This can be the intelligent model established above for estimating consumables and printing time. The goal of this model is to predict the corresponding optimized evaluation value based on the input 3D model features and printing parameters. When establishing the model, regression algorithms (such as linear regression, random forest regression, etc.) or neural networks (such as multilayer perceptron, convolutional neural network, etc.) can be used for training.

[0050] In the intelligent adjustment model, in addition to the prediction model, an optimization algorithm needs to be designed. The goal of this algorithm is to shorten the optimization evaluation value by adjusting the printing parameters or simplifying the model geometry, etc., under the premise of meeting the preset printing target material requirements. The optimization algorithm can use heuristic search (such as genetic algorithms, simulated annealing, etc.) or gradient descent optimization methods.

[0051] The intelligent adjustment model is trained using the collected training data, and the performance of the model is evaluated through methods such as cross-validation. During the training process, the model parameters need to be continuously adjusted and the optimization algorithm needs to be optimized to improve the prediction accuracy and optimization effect of the model. At the same time, the model needs to be tested for robustness to ensure its stability and reliability in practical applications.

[0052] The analysis module is used to analyze the target model, determine the printing control parameters of the printing target, such as layer height, filling density, printing speed, temperature, etc.; and send the obtained printing control parameters to the remote control module.

[0053] In one embodiment, the target model may be analyzed based on existing methods to determine corresponding printing control parameters, such as using an analysis model or system provided by a common 3D printing device for analysis.

[0054] In one embodiment, due to the differences in printing in scenarios such as home use, users may have large fluctuations in their demands for printing time and product quality. For example, in some cases, users may greatly pursue printing time and reduce their requirements for product instructions. In some cases, users may pay more attention to product quality and have low requirements for printing time. At the same time, due to the differences in professional knowledge of some users, users may not be able to perform accurate analysis based on actual needs. Therefore, in this embodiment, the target model is analyzed in the following manner, including: Analyze the target model to determine initial printing parameters, that is, the printing control parameters determined in the above embodiment; Determine the user's printing needs, which are usually in the printing target material, and can also be collected separately, such as manual input by the user, voice input, etc. The printing needs include the user's requirements for printing time and printing quality; Adjust the initial printing parameters according to the printing requirements to obtain the printing control parameters.

[0055] In one embodiment, the initial printing parameters are adjusted according to the printing requirements, and the platform can use existing intelligent technologies to establish a corresponding intelligent model for adjustment, such as: Establishment and training of intelligent models: Data collection: Collect a large amount of 3D printing case data, including printing parameters, printing time, printing quality and other information of different models. Pre-process the data to remove outliers and duplicate data to ensure data quality.

[0056] Feature extraction: Extract key features from the data, such as model size, complexity, printing material, printer model, etc. These features will be used as input to the intelligent model to predict printing time and print quality.

[0057] Model selection: According to the complexity of the problem, select a suitable machine learning or deep learning model, such as a regression model, neural network, etc. Initialize the model and set appropriate hyperparameters.

[0058] Model training: Use preprocessed data to train the model so that it can accurately predict printing time and quality. Evaluate the performance of the model through methods such as cross-validation to ensure the generalization ability of the model.

[0059] Using intelligent models to adjust initial control parameters: Enter user requirements: The user inputs specific requirements for the quality of the printed product and the printing time, i.e. the printing demand. These requirements will serve as the basis for the intelligent model to adjust the control parameters.

[0060] Model prediction and optimization: Input user requirements and initial control parameters into the intelligent model. The model predicts the printing time and print quality based on the input information and gives optimization suggestions. According to the optimization suggestions, the initial control parameters are adjusted to obtain the target control parameters.

[0061] Verification and adjustment: Use the adjusted control parameters to conduct printing experiments to verify the printing effect. Based on the experimental results, further fine-tune the control parameters to ensure that they meet user requirements.

[0062] Output results and subsequent optimization: Output results: The final target control parameters are output to the user to guide the user to perform 3D printing operations.

[0063] Subsequent optimization: Collect user feedback and print result data to improve the performance of the intelligent model. As data accumulates, continuously train and optimize the intelligent model to improve its prediction accuracy and generalization ability.

[0064] In one embodiment, the initial control parameters may be adjusted according to printing requirements in other ways.

[0065] The manual parameter module is used for the user to manually set the printing control parameters according to their own needs, and send the set printing control parameters to the remote control module.

[0066] The remote control module is used to remotely control the 3D printing device according to the received printing control parameters; identify the received printing control parameters, generate corresponding control instructions according to the received printing control parameters, and send the control instructions to the execution end.

[0067] The execution end is arranged in the 3D printing device, and is used to control and adjust the 3D printing device, and control the operation of the 3D printing device according to the received control instructions.

[0068] In one embodiment, the execution end also includes other existing modules, such as quality detection, fault detection and other related functional modules.

[0069] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0070] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A 3D printing intelligent control system, characterized in that: Including user end and execution end; The user end includes a model module, an analysis module, a manual parameter module, and a remote control module; The model module is used to determine the target model of the printing target; The analysis module is used to analyze the target model, determine the printing control parameters of the printing target, and send the printing control parameters to the remote control module; The manual parameter module is used for the user to manually set the printing control parameters and send the printing control parameters to the remote control module; The remote control module is used to remotely control the 3D printing device according to the received printing control parameters; identify the received printing control parameters, generate corresponding control instructions according to the printing control parameters, and send the control instructions to the execution end; The execution end is used to control the 3D printing device to perform 3D printing according to the received control instruction, so as to obtain the 3D printed product of the printing target.

2. A 3D printing intelligent control system according to claim 1, characterized in that: The model module includes an input conversion unit and a standard model unit; The input conversion unit is used for the user to upload the conversion model of the printing target, and convert the conversion model to obtain the target model of the printing target; The standard model unit is used by the user to establish the target model of the printing target according to a preset modeling method.

3. A 3D printing intelligent control system according to claim 2, characterized in that: Methods for transforming the transformation model include: The platform presets the model requirements, and establishes a conversion judgment model based on the model requirements. The expression of the conversion judgment model is: ; Where: (MU, BM) is the input data, MU is the model identification feature set of the transformation model; BM is the model requirement; MU→BM means that the model identification feature set meets the model requirement; the output data is the transformation judgment value ZP (MU, BM), and the transformation judgment value is 1 or 0; Performing feature recognition on the conversion model to obtain a model recognition feature set of the conversion model; Analyzing the model recognition feature set through the conversion judgment model to obtain a conversion judgment value of the conversion model; When the conversion judgment value is 1, the conversion model is marked as a target model; When the conversion judgment value is 0, the model non-conformity item is determined, and the conversion model is converted according to the model non-conformity item to obtain the target model.

4. A 3D printing intelligent control system according to claim 1 or 2, characterized in that: The model module also includes a shortcut model unit, which is used by the user to establish a target model of a printing target and obtain the user's printing target material, wherein the printing target material includes a printing target picture and target requirements; An initial model is generated according to the printing target material, and the initial model is optimized and adjusted according to preset optimization factors to obtain a target model, wherein the optimization factors include the amount of consumables and the printing time.

5. A 3D printing intelligent control system according to claim 4, characterized in that: The method of obtaining the user's printing target material includes: Obtaining target description data of the printing target from the user; performing image retrieval according to the target description data to obtain a number of target images to be selected that meet the target description data; Estimate the printing time of the target image to be selected, and mark it as the estimated time to be selected; sort the target images to be selected in ascending order of the estimated time to be selected to obtain a recommendation list; The recommendation list is displayed to the user, and the user selects less than or equal to K of the target images to be selected as user selected images, where K is a positive integer; and the printing target image of the printing target is determined according to the user selected images; A material template is generated according to the printing target picture, a user is assisted in setting a target requirement according to the material template and the printing target picture, and a printing target material is generated according to the target requirement and the printing target picture.

6. A 3D printing intelligent control system according to claim 5, characterized in that: The printing target picture is the user-selected picture with the shortest estimated selection time.

7. A 3D printing intelligent control system according to claim 5, characterized in that: The printing target picture is a combined picture of the pictures selected by the user.

8. A 3D printing intelligent control system according to claim 4, characterized in that: The method for optimizing and adjusting the initial model according to the preset optimization factors includes: Step SA1: performing a printing simulation on the initial model to obtain the simulated consumables amount and simulation duration of the initial model; calculating a corresponding optimization evaluation value according to a preset optimization evaluation formula, and marking the optimization evaluation value of the initial model as a benchmark evaluation value; The optimization evaluation formula is: ; Where: YP is the optimization evaluation value; b1 and b2 are both proportional coefficients, with a value range of 0≤b1≤1, 0≤b2≤1; HL is the simulated consumables; TM is the simulation time; Step SA2: forming an adjustment requirement according to the printing target material and the benchmark evaluation value, wherein the adjustment requirement includes satisfying the printing target material requirement and the optimized evaluation value of the adjusted initial model being less than the benchmark evaluation value; adjusting the initial model according to the adjustment requirement to form a new initial model, and determining the benchmark evaluation value of the new initial model; Step SA3: loop step SA2 until there is no new initial model, and mark the initial model as the target model.

9. A 3D printing intelligent control system according to claim 8, characterized in that: When the target model does not meet the user's requirements, model change data is generated according to the adjustment process of the initial model, and the user determines the target model that meets the user's requirements according to the model change data.

10. The 3D printing intelligent control system according to claim 1, characterized in that: The method for determining the printing control parameters includes: Analyze the target model, determine the initial printing parameters, and obtain the user's printing requirements; The initial printing parameters are adjusted according to the printing requirements to obtain printing control parameters of the printing target.

Images