Detection method, device, equipment and storage medium for light-curing 3D printer

Abstract

The present invention discloses a method, apparatus, device, and storage medium for testing a light-curing 3D printer. The method comprises: setting a 3D test model for testing; performing light-curing 3D printing layer by layer based on the 3D test model, and recording the actual printing parameters of each layer during light-curing 3D printing using a target sensor; measuring the dimensions of the printed model product using a three-dimensional optical scanner to obtain the actual dimensions of each printed layer; calculating the dimensional error between the actual and theoretical dimensions of each printed layer, and calculating the parameter error between the actual and theoretical printing parameters; and obtaining a print quality test result of the light-curing 3D printer based on the dimensional and parameter errors of each printed layer. The present invention can accurately evaluate and quantify the printing accuracy and consistency of a light-curing 3D printer, thereby determining its overall print quality level.

Description

Technical Field

[0001] The present invention relates to the field of 3D printing technology, and in particular to a detection method, device, equipment and storage medium for a light-curing 3D printer. Background Art

[0002] Modern stereolithography 3D printing technology has enabled sophisticated and high-precision three-dimensional fabrication, particularly in the field of stereolithography (SLA). Printers rely on a precisely controlled light source system to solidify liquid photosensitive resin layer by layer to create complex three-dimensional objects. To ensure print quality, existing stereolithography 3D printers require not only advanced hardware configurations, such as a precise printing platform, optical system, and control unit, but also rigorous quality control methods.

[0003] While existing stereolithography 3D printers are technically capable of achieving a high degree of automation and parameter monitoring, establishing a comprehensive, accurate, and easy-to-implement 3D printing quality inspection system to accurately evaluate and provide feedback on the printer's stability and precision during continuous printing remains a key technical challenge in this field. In particular, optimizing inspection model design and parameter adjustment strategies to further improve the printer's adaptability to various printing conditions and the consistency of final product quality under complex variations in layer thickness and cross-sectional area remains a key technical issue that needs to be addressed. Summary of the Invention

[0004] Embodiments of the present invention provide a method, apparatus, device, and storage medium for detecting a light-curing 3D printer, which can accurately evaluate and quantify the printing accuracy and consistency of the light-curing 3D printer, thereby determining its overall printing quality level.

[0005] An embodiment of the present invention provides a method for detecting a light-curing 3D printer, comprising:

[0006] A 3D test model is set up for testing; each printed layer of the 3D test model has the same thickness, each printed layer has a square cross-section, and the cross-sectional area of ​​each printed layer increases from top to bottom;

[0007] Perform layer-by-layer photocuring 3D printing based on the 3D test model, and use the target sensor to record the actual printing parameters of each layer during photocuring 3D printing; the actual printing parameters include the actual exposure time and the actual exposure light intensity;

[0008] The printed model product is measured using a 3D optical scanner to obtain the actual size of each printed layer. The actual size includes actual thickness, actual length, and actual width.

[0009] Calculate the dimensional error between the actual size and theoretical size of each printed layer, and calculate the parameter error between the actual printing parameters and theoretical printing parameters;

[0010] Based on the dimensional error and parameter error of each printing layer, the printing quality test results of the light-curing 3D printer are obtained.

[0011] As an improvement to the above solution, the printing quality test results of the light-curing 3D printer are obtained based on the dimensional error and parameter error of each printing layer, including:

[0012] The comprehensive error coefficient of each printing layer is calculated according to the dimensional error and parameter error of each printing layer and the following calculation formula: E n =α d ·|Δd n |+α l ·|Δl n |+α w ·|Δw n |+β t ·Δt n |+β I |ΔI n |, where α d , α l , α w , β t , β I Respectively represent the preset weight coefficients corresponding to each size error and each parameter error, Δd n is the thickness error in the size error, Δl n is the length error in the size error, Δw n is the width error in the size error, Δt n is the exposure time error in the parameter error, ΔI n is the exposure intensity error in the parameter error;

[0013] If the relevant errors of the printed layer do not meet the following error qualification conditions, the printing quality of the printed layer does not meet the requirements; the error qualification conditions include: the comprehensive error coefficient is less than a preset error coefficient threshold, and the individual errors of the dimensional error and the parameter error are both less than a preset error threshold;

[0014] If the relevant error of the printed layer meets the error qualification condition, the printing quality of the printed layer meets the requirement.

[0015] As an improvement to the above solution, after obtaining the print quality test result of the light-curing 3D printer based on the dimensional error and parameter error of each printed layer, the method further includes:

[0016] Collecting printing data samples of each printing layer; the printing data samples include: theoretical size, size error, theoretical printing parameters and parameter error;

[0017] Using the printing data samples collected multiple times to train a printing error correction model for correcting printing errors of each printing layer, to obtain a trained printing error correction model;

[0018] During the printing process of the actual 3D model, the theoretical size and theoretical printing parameters of each printing layer of the actual 3D model are input into the trained printing error correction model to obtain the corrected theoretical size and theoretical printing parameters;

[0019] Printing is performed according to the corrected theoretical size and theoretical printing parameters of each printing layer.

[0020] As an improvement to the above solution, the trained printing error correction model includes:

[0021] Dimensional error E S Prediction model: Among them, E S is the actual size error vector of dimension (3×1); is a weight matrix of dimension (3×3) used to map from the theoretical size vector to the size error vector; S theo is a theoretical size vector of dimension (3×1); is a weight matrix of dimension (2×3) used to map from the theoretical printing parameter vector to the size error vector; P theo is the theoretical printing parameter vector of dimension (2×1); b S is the bias vector associated with size error prediction;

[0022] Parameter error E P Prediction model: Among them, E P Represents the new parameter error prediction vector of the layer to be printed, including the predicted exposure time and light source intensity error; is a weight matrix of dimension (2×3) used to map from the theoretical size vector to the parameter error prediction vector; is a weight matrix of dimension (2×2) used to map from the theoretical printed parameter vector to the parameter error prediction vector; b P is the bias vector associated with parameter error prediction; S theo is a theoretical size vector of dimension (3×1); P theo is the theoretical printing parameter vector of dimension (2×1);

[0023] Theoretical size correction model: S corr =S theo-E S ;

[0024] Theoretical printing parameter correction model: P corr =P theo -E P ;

[0025] In the actual application process, the theoretical size and theoretical printing parameters of the layer to be printed are input, and the prediction error is calculated through the above-trained printing error correction model to calculate the corrected theoretical value, thereby obtaining the corrected theoretical size and theoretical printing parameters.

[0026] Another embodiment of the present invention provides a detection device for a light-curing 3D printer, including:

[0027] a setting module for setting a 3D test model for testing; wherein each printed layer of the 3D test model has the same thickness, each printed layer has a square cross-section, and the cross-sectional area of ​​each printed layer increases from top to bottom;

[0028] The test printing module is used to perform layer-by-layer photocuring 3D printing based on the 3D test model and record the actual printing parameters of each layer during photocuring 3D printing through the target sensor; the actual printing parameters include actual exposure time and actual exposure light intensity;

[0029] The measurement module is used to measure the dimensions of the printed model product using a 3D optical scanner to obtain the actual dimensions of each printed layer; the actual dimensions include actual thickness, actual length, and actual width;

[0030] A calculation module is used to calculate the dimensional error between the actual size of each printing layer and the theoretical size, and to calculate the parameter error between the actual printing parameters and the theoretical printing parameters;

[0031] The analysis module is used to obtain the printing quality detection result of the light-curing 3D printer based on the dimensional error and parameter error of each printing layer.

[0032] As an improvement to the above solution, the analysis module is specifically used to:

[0033] The comprehensive error coefficient of each printing layer is calculated according to the dimensional error and parameter error of each printing layer and the following calculation formula: E n =α d ·|Δd n |+α l ·|Δl n |+α w ·|Δw n |+β t ·|Δt n |+β I|ΔI n |, where α d , α l , α w , β t , β I Respectively represent the preset weight coefficients corresponding to each size error and each parameter error, Δd n is the thickness error in the size error, Δl n is the length error in the size error, Δω n is the width error in the size error, Δt n is the exposure time error in the parameter error, ΔI n is the exposure intensity error in the parameter error;

[0034] If the relevant errors of the printed layer do not meet the following error qualification conditions, the printing quality of the printed layer does not meet the requirements; the error qualification conditions include: the comprehensive error coefficient is less than a preset error coefficient threshold, and the individual errors of the dimensional error and the parameter error are both less than a preset error threshold;

[0035] If the relevant error of the printed layer meets the error qualification condition, the printing quality of the printed layer meets the requirement.

[0036] As an improvement to the above solution, the device further includes:

[0037] A collection module is used to collect printing data samples of each printing layer; the printing data samples include: theoretical size, size error, theoretical printing parameters and parameter error;

[0038] A training module, configured to train a printing error correction model for correcting printing errors of each printing layer using printing data samples collected multiple times, thereby obtaining a trained printing error correction model;

[0039] A correction module is used to input the theoretical size and theoretical printing parameters of each printing layer of the actual 3D model into the trained printing error correction model during the printing process of the actual 3D model to obtain the corrected theoretical size and theoretical printing parameters;

[0040] The actual printing module is used to print according to the corrected theoretical size and theoretical printing parameters of each printing layer.

[0041] As an improvement to the above solution, the trained printing error correction model includes:

[0042] Dimensional error E S Prediction model: Among them, E S is the actual size error vector of dimension (3×1); is a weight matrix of dimension (3×3) used to map from the theoretical size vector to the size error vector; S theo is a theoretical size vector of dimension (3×1); is a weight matrix of dimension (2×3) used to map from the theoretical printing parameter vector to the size error vector; P theo is the theoretical printing parameter vector of dimension (2×1); b S is the bias vector associated with size error prediction;

[0043] Parameter error E P Prediction model: Among them, E P Represents the new parameter error prediction vector of the layer to be printed, including the predicted exposure time and light source intensity error; is a weight matrix of dimension (2×3) used to map from the theoretical size vector to the parameter error prediction vector; is a weight matrix of dimension (2×2) used to map from the theoretical printed parameter vector to the parameter error prediction vector; b P is the bias vector associated with parameter error prediction; S theo is a theoretical size vector of dimension (3×1); P theo is the theoretical printing parameter vector of dimension (2×1);

[0044] Theoretical size correction model: S corr =S theo- E S ;

[0045] Theoretical printing parameter correction model: P corr =P theo -E P ;

[0046] In the actual application process, the theoretical size and theoretical printing parameters of the layer to be printed are input, and the prediction error is calculated through the above-trained printing error correction model to calculate the corrected theoretical value, thereby obtaining the corrected theoretical size and theoretical printing parameters.

[0047] Another embodiment of the present invention provides a detection device for a light-curing 3D printer, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the detection method for the light-curing 3D printer described in the above-mentioned embodiment of the invention is implemented.

[0048] Another embodiment of the present invention provides a storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device containing the computer-readable storage medium is controlled to execute the detection method for the light-curing 3D printer described in the above-mentioned embodiment of the invention.

[0049] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0050] The embodiment of the present invention designs and prints a 3D test model with special specifications (a square structure with consistent thickness of each layer and gradually increasing cross-sectional area according to a preset rule, which facilitates error calculation). During the printing process, the target sensor monitors and records key printing parameters such as the actual exposure time and exposure light intensity of each layer in real time. After printing is completed, a three-dimensional optical scanner is used to perform a comprehensive dimensional detection of the model to obtain the actual thickness, length and width data of each printed layer, and compare the theoretical design dimensions to calculate the dimensional error. At the same time, the actual printing parameters are compared with the ideal theoretical parameters to obtain the parameter error. Based on the dimensional error and parameter error obtained in the above steps, the printing accuracy and consistency of the light-curing 3D printer can be accurately evaluated and quantified, thereby determining its overall printing quality level. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 1 is a flow chart of a method for detecting a light-curing 3D printer provided by one embodiment of the present invention;

[0052] Figure 2 1 is a schematic structural diagram of a detection device for a light-curing 3D printer provided by one embodiment of the present invention;

[0053] Figure 3 The figure is a schematic structural diagram of a detection device for a light-curing 3D printer provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0055] See also Figure 1 , is a flow chart of a method for detecting a light-curing 3D printer provided by one embodiment of the present invention. The method for detecting a light-curing 3D printer comprises steps S10 to S14:

[0056] S10, setting a 3D test model for testing; wherein each printed layer of the 3D test model has the same thickness, each printed layer has a square cross-section, and the cross-sectional area of ​​each printed layer increases from top to bottom;

[0057] S11, performing photocuring 3D printing layer by layer based on the 3D test model, and recording actual printing parameters of each layer during photocuring 3D printing through a target sensor; the actual printing parameters include actual exposure time and actual exposure light intensity;

[0058] S12, measuring the dimensions of the printed model product using a 3D optical scanner to obtain the actual dimensions of each printed layer; the actual dimensions include actual thickness, actual length, and actual width;

[0059] S13, calculating the size error between the actual size of each printing layer and the theoretical size, and calculating the parameter error between the actual printing parameters and the theoretical printing parameters;

[0060] S14, obtaining a printing quality test result of the light-curing 3D printer based on the dimensional error and parameter error of each printing layer.

[0061] The embodiment of the present invention designs and prints a 3D test model with special specifications (a square structure with consistent thickness of each layer and gradually increasing cross-sectional area according to a preset rule, which facilitates error calculation). During the printing process, the target sensor monitors and records key printing parameters such as the actual exposure time and exposure light intensity of each layer in real time. After printing is completed, a three-dimensional optical scanner is used to perform a comprehensive dimensional detection of the model to obtain the actual thickness, length and width data of each printed layer, and compare the theoretical design dimensions to calculate the dimensional error. At the same time, the actual printing parameters are compared with the ideal theoretical parameters to obtain the parameter error. Based on the dimensional error and parameter error obtained in the above steps, the printing accuracy and consistency of the light-curing 3D printer can be accurately evaluated and quantified, thereby determining its overall printing quality level.

[0062] The target sensor may be a light intensity sensor for monitoring the exposure intensity and exposure duration of an ultraviolet (UV) light source or other light source to ensure that the light intensity is maintained at an appropriate curing level during the printing process.

[0063] As an improvement to the above solution, the printing quality test results of the light-curing 3D printer are obtained based on the dimensional error and parameter error of each printing layer, including:

[0064] The comprehensive error coefficient of each printing layer is calculated according to the dimensional error and parameter error of each printing layer and the following calculation formula: E n =α d ·|Δd n |+α l·|Δl n |+α w ·|Δw n |+β t ·|Δt n |+β I |ΔI n |, where α d , α l , α w , β t ,β I Respectively represent the preset weight coefficients corresponding to each size error and each parameter error, Δd n is the thickness error in the size error, Δl n is the length error in the size error, Δω n is the width error in the size error, Δt n is the exposure time error in the parameter error, ΔI n is the exposure intensity error in the parameter error;

[0065] If the relevant errors of the printed layer do not meet the following error qualification conditions, the printing quality of the printed layer does not meet the requirements; the error qualification conditions include: the comprehensive error coefficient is less than a preset error coefficient threshold, and the individual errors of the dimensional error and the parameter error are both less than a preset error threshold;

[0066] If the relevant error of the printed layer meets the error qualification condition, the printing quality of the printed layer meets the requirement.

[0067] In an embodiment of the present invention, a comprehensive error coefficient for each printed layer is calculated using preset weighting coefficients by combining the specific dimensional errors (such as thickness error, length error, and width error) and parameter errors (such as exposure time error and exposure light intensity error) of each printed layer. When the comprehensive error coefficient is below a preset threshold, and all individual dimensional errors and parameter errors are also below their respective set error thresholds, the print quality of that printed layer is considered to have met the standard. This not only accurately measures the geometric dimensional control accuracy of a light-curing 3D printer during actual printing, but also assesses its stability and consistency with key process parameters (exposure time and light intensity), thereby comprehensively evaluating the printer's overall performance and print quality.

[0068] As an improvement to the above solution, after obtaining the print quality test result of the light-curing 3D printer based on the dimensional error and parameter error of each printed layer, the method further includes:

[0069] Collecting printing data samples of each printing layer; the printing data samples include: theoretical size, size error, theoretical printing parameters and parameter error;

[0070] Using the printing data samples collected multiple times to train a printing error correction model for correcting printing errors of each printing layer, to obtain a trained printing error correction model;

[0071] During the printing process of the actual 3D model, the theoretical size and theoretical printing parameters of each printing layer of the actual 3D model are input into the trained printing error correction model to obtain the corrected theoretical size and theoretical printing parameters;

[0072] Printing is performed according to the corrected theoretical size and theoretical printing parameters of each printing layer.

[0073] In this embodiment, a printing error correction model is innovatively introduced based on obtaining the dimensional error and parameter error of each printing layer to evaluate printing quality. First, print data samples containing theoretical dimensions, dimensional errors, theoretical printing parameters, and parameter errors are collected. These samples are used to train the error correction model to generate a printing error correction model with prediction and correction functions. In the subsequent actual 3D model printing stage, the original theoretical dimensions and theoretical printing parameters of each printing layer are input into the trained model to obtain new parameters that have been corrected and optimized. Printing based on these corrected theoretical dimensions and parameters can effectively improve the accuracy, adaptability, and stability of light-curing 3D printing, achieving personalized calibration and continuous optimization of product quality.

[0074] It is understandable that the printing error correction model training process can be:

[0075] 1. Data Collection and Preprocessing: Using a pre-defined 3D test model, we print layer by layer, using a target sensor to record parameters such as the actual exposure time and actual light intensity for each layer in real time. After printing, we use a 3D optical scanner to accurately measure the actual thickness, length, and width of each printed layer. The actual dimensions are compared with the theoretical dimensions to calculate the dimensional error, and the corresponding actual printing parameters are recorded.

[0076] 2. Feature Engineering: Construct a dataset containing theoretical dimensions, dimension errors, theoretical printing parameters, and parameter errors.

[0077] 3. Model Training: Based on the aforementioned error dataset, a machine learning algorithm (e.g., regression analysis, neural networks, or support vector machines) is used to train the model. The goal is to enable the model to learn the nonlinear relationship between actual dimensional error, theoretical dimensions, and actual printing parameters, thereby predicting the potential error for a given theoretical dimension and printing parameters. Specific model training methods can be referenced in existing technologies and are not detailed here.

[0078] 4. Model Validation and Optimization: Divide the dataset into training and test sets to validate the model and ensure its generalization ability. Optimize model performance by iteratively adjusting model parameters and structure until the model achieves satisfactory error prediction accuracy on the test set.

[0079] 5. Apply the model for error correction: For new print jobs, when entering theoretical dimensions and printing parameters, these parameters are fed into the trained error correction model. The model outputs predicted dimensional errors and printing parameter deviations. Based on these predictions, the actual operating parameters of each print layer are corrected. This can include increasing or decreasing exposure time, adjusting light intensity, or adjusting the print dimensions of that layer (because factors such as temperature and the thermal expansion and contraction coefficient of the material during the printing process can cause errors in the print dimensions of that layer, this can be corrected in advance).

[0080] 6. Closed-loop feedback system: In actual applications, new printing data is continuously collected and the model is updated to form a continuously improved closed-loop control system to ensure that the model always maintains good prediction and correction capabilities for printing errors.

[0081] Through the above process, an intelligent error correction system can be established, which can predict possible errors based on current conditions before printing and automatically adjust relevant parameters to minimize dimensional errors and parameter errors during the printing process.

[0082] As an improvement to the above solution, the trained printing error correction model includes:

[0083] Dimensional error E S Prediction model: Among them, E S是 The actual size error vector of dimension (3×1); is a weight matrix of dimension (3×3) used to map from the theoretical size vector to the size error vector; S theo is a theoretical size vector of dimension (3×1); is a weight matrix of dimension (2×3) used to map from the theoretical printing parameter vector to the size error vector; P theo is the theoretical printing parameter vector of dimension (2×1); b S is the bias vector associated with size error prediction;

[0084] Parameter error E P Prediction model: Among them, E P Represents the new parameter error prediction vector of the layer to be printed, including the predicted exposure time and light source intensity error; is a weight matrix of dimension (2×3) used to map from the theoretical size vector to the parameter error prediction vector; is a weight matrix of dimension (2×2) used to map from the theoretical printed parameter vector to the parameter error prediction vector; b P is the bias vector associated with parameter error prediction; S theo is a theoretical size vector of dimension (3×1); P theo is the theoretical printing parameter vector of dimension (2×1);

[0085] Theoretical size correction model: S corr =S theo -E S ;

[0086] Theoretical printing parameter correction model: P corr =P theo -E P ;

[0087] In the actual application process, the theoretical size and theoretical printing parameters of the layer to be printed are input, and the prediction error is calculated through the above-trained printing error correction model to calculate the corrected theoretical value, thereby obtaining the corrected theoretical size and theoretical printing parameters.

[0088] In an embodiment of the present invention, a printing error correction model constructed based on a neural network or regression analysis is divided into two parts: a size error prediction model and a parameter error prediction model, to explore the potential relationship between theoretical dimensions and theoretical printing parameters and actual printing errors. The size error prediction model uses a weight matrix and a bias term to map the theoretical dimensions and theoretical printing parameters to the actual size error prediction, while the parameter error prediction model further predicts the exposure time and light source intensity errors. In addition, by constructing a theoretical size correction model and a theoretical printing parameter correction model, they are used to receive the initial theoretical dimensions and parameters of the layer to be printed in actual application, calculate the error prediction value through the trained prediction model, and then accurately correct the original theoretical value to obtain a corrected theoretical dimension and theoretical printing parameter that is closer to reality. The embodiment of the present invention can predict and compensate for possible size and parameter errors in advance, thereby ensuring the consistency and accuracy of printing quality. In practical applications, it can not only reduce scrap rate and rework costs, but also help improve printing speed and resource utilization. It should be noted that the construction process of the correlation matrix and vector in the above formula can refer to the specific construction process of the neural network or regression analysis algorithm. The construction of these individual formula parameters is not the invention of this solution. The innovation of this solution lies in the comprehensive consideration of various parameter factors and the reconstruction of the above correlation model.

[0089] See also Figure 2 , is a schematic diagram of a detection device for a light-curing 3D printer provided by one embodiment of the present invention. The detection device for the light-curing 3D printer includes:

[0090] A setting module 10 is configured to set a 3D test model for testing; each printed layer of the 3D test model has the same thickness, each printed layer has a square cross-section, and the cross-sectional area of ​​each printed layer increases from top to bottom;

[0091] A test printing module 11 is used to perform layer-by-layer photocuring 3D printing based on the 3D test model and record the actual printing parameters of each layer during photocuring 3D printing through a target sensor; the actual printing parameters include actual exposure time and actual exposure light intensity;

[0092] The measuring module 12 is used to measure the dimensions of the printed model product using a 3D optical scanner to obtain the actual dimensions of each printed layer; the actual dimensions include actual thickness, actual length, and actual width;

[0093] A calculation module 13 is used to calculate the size error between the actual size of each printing layer and the theoretical size, and to calculate the parameter error between the actual printing parameters and the theoretical printing parameters;

[0094] The analysis module 14 is used to obtain a printing quality test result of the light-curing 3D printer based on the dimensional error and parameter error of each printing layer.

[0095] The embodiment of the present invention designs and prints a 3D test model with special specifications (a square structure with consistent thickness of each layer and gradually increasing cross-sectional area according to a preset rule, which facilitates error calculation). During the printing process, the target sensor monitors and records key printing parameters such as the actual exposure time and exposure light intensity of each layer in real time. After printing is completed, a three-dimensional optical scanner is used to perform a comprehensive dimensional detection of the model to obtain the actual thickness, length and width data of each printed layer, and compare the theoretical design dimensions to calculate the dimensional error. At the same time, the actual printing parameters are compared with the ideal theoretical parameters to obtain the parameter error. Based on the dimensional error and parameter error obtained in the above steps, the printing accuracy and consistency of the light-curing 3D printer can be accurately evaluated and quantified, thereby determining its overall printing quality level.

[0096] As an improvement to the above solution, the analysis module is specifically used to:

[0097] The comprehensive error coefficient of each printing layer is calculated according to the dimensional error and parameter error of each printing layer and the following calculation formula: E n =α d ·|Δd n |+α l ·|Δl n |+α w ·|Δw n |+β t ·|Δtn |+β I |ΔI n |, where α d , α l , α w , β t , β I Respectively represent the preset weight coefficients corresponding to each size error and each parameter error, Δd n is the thickness error in the size error, Δl n is the length error in the size error, Δw n is the width error in the size error, Δt n is the exposure time error in the parameter error, ΔI n is the exposure intensity error in the parameter error;

[0098] If the relevant errors of the printed layer do not meet the following error qualification conditions, the printing quality of the printed layer does not meet the requirements; the error qualification conditions include: the comprehensive error coefficient is less than a preset error coefficient threshold, and the individual errors of the dimensional error and the parameter error are both less than a preset error threshold;

[0099] If the relevant error of the printed layer meets the error qualification condition, the printing quality of the printed layer meets the requirement.

[0100] As an improvement to the above solution, the device further includes:

[0101] A collection module is used to collect printing data samples of each printing layer; the printing data samples include: theoretical size, size error, theoretical printing parameters and parameter error;

[0102] A training module, configured to train a printing error correction model for correcting printing errors of each printing layer using printing data samples collected multiple times, thereby obtaining a trained printing error correction model;

[0103] A correction module is used to input the theoretical size and theoretical printing parameters of each printing layer of the actual 3D model into the trained printing error correction model during the printing process of the actual 3D model to obtain the corrected theoretical size and theoretical printing parameters;

[0104] The actual printing module is used to print according to the corrected theoretical size and theoretical printing parameters of each printing layer.

[0105] As an improvement to the above solution, the trained printing error correction model includes:

[0106] Dimensional error E S Prediction model: Among them, E Sis the actual size error vector of dimension (3×1); is a weight matrix of dimension (3×3) used to map from the theoretical size vector to the size error vector; S theo is a theoretical size vector of dimension (3×1); is a weight matrix of dimension (2×3) used to map from the theoretical printing parameter vector to the size error vector; P theo is the theoretical printing parameter vector of dimension (2×1); b S is the bias vector associated with size error prediction;

[0107] Parameter error E P Prediction model: Among them, E P Represents the new parameter error prediction vector of the layer to be printed, including the predicted exposure time and light source intensity error; is a weight matrix of dimension (2×3) used to map from the theoretical size vector to the parameter error prediction vector; is a weight matrix of dimension (2×2) used to map from the theoretical printed parameter vector to the parameter error prediction vector; b P is the bias vector associated with parameter error prediction; S theo is a theoretical size vector of dimension (3×1); P theo is the theoretical printing parameter vector of dimension (2×1);

[0108] Theoretical size correction model: S corr =S theo -E S ;

[0109] Theoretical printing parameter correction model: P corr =P theo -E P ;

[0110] In the actual application process, the theoretical size and theoretical printing parameters of the layer to be printed are input, and the prediction error is calculated through the above-trained printing error correction model to calculate the corrected theoretical value, thereby obtaining the corrected theoretical size and theoretical printing parameters.

[0111] See also Figure 3 is a schematic diagram of a test device for a stereolithography 3D printer according to one embodiment of the present invention. The test device for a stereolithography 3D printer according to this embodiment includes a processor 100, a memory 101, and a computer program stored in the memory 101 and executable on the processor 100, such as a test program for a stereolithography 3D printer. When the processor 100 executes the computer program, it implements the steps described in the various embodiments of the test method for a stereolithography 3D printer described above.

[0112] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the detection device of the stereolithography 3D printer.

[0113] The detection device for the light-curing 3D printer can be a light-curing 3D printer, or a computing device such as a desktop computer, laptop, PDA, or cloud server that is communicatively connected to the light-curing 3D printer. The detection device for the light-curing 3D printer can include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the schematic diagram is merely an example of a detection device for a light-curing 3D printer and does not constitute a limitation on the detection device for a light-curing 3D printer. The detection device can include more or fewer components than shown, or a combination of certain components, or different components. For example, the detection device for the light-curing 3D printer can also include input and output devices, network access devices, buses, etc.

[0114] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor serves as the control center of the detection device of the stereolithography 3D printer, connecting various components of the detection device of the stereolithography 3D printer using various interfaces and circuits.

[0115] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the detection device of the light-curing 3D printer by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0116] Wherein, if the module / unit integrated into the detection device of the light-curing 3D printer is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. Wherein, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0117] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0118] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for detecting a light-curing 3D printer, characterized in that: include: A 3D test model is set up for testing; each printed layer of the 3D test model has the same thickness, each printed layer has a square cross-section, and the cross-sectional area of ​​each printed layer increases from top to bottom; Perform layer-by-layer photocuring 3D printing based on the 3D test model, and use the target sensor to record the actual printing parameters of each layer of photocuring 3D printing; The actual printing parameters include actual exposure time and actual exposure light intensity; The printed model product is measured using a 3D optical scanner to obtain the actual size of each printed layer; Actual dimensions include actual thickness, actual length and actual width; Calculate the dimensional error between the actual size and theoretical size of each printed layer, and calculate the parameter error between the actual printing parameters and theoretical printing parameters; Based on the dimensional error and parameter error of each printing layer, the printing quality test results of the light-curing 3D printer are obtained; The printing quality test result of the light-curing 3D printer is obtained based on the dimensional error and parameter error of each printing layer, including: The comprehensive error coefficient of each printing layer is calculated based on the dimensional error and parameter error of each printing layer and the following calculation formula: ， in, Respectively represent the preset weight coefficients corresponding to each size error and each parameter error, is the thickness error in the size error, is the length error in the size error, is the width error in the size error, is the exposure time error in the parameter error, is the exposure intensity error in the parameter error; If the relevant errors of the printed layer do not meet the following error qualification conditions, the printing quality of the printed layer does not meet the requirements; the error qualification conditions include: the comprehensive error coefficient is less than a preset error coefficient threshold, and the individual errors of the dimensional error and the parameter error are both less than a preset error threshold; If the relevant error of the printed layer meets the error qualification condition, the printing quality of the printed layer meets the requirement.

2. The detection method of a light-curing 3D printer according to claim 1, wherein: After obtaining the print quality test result of the light-curing 3D printer based on the dimensional error and parameter error of each printing layer, the method further includes: Collecting printing data samples of each printing layer; the printing data samples include: theoretical size, size error, theoretical printing parameters and parameter error; Using the printing data samples collected multiple times to train a printing error correction model for correcting printing errors of each printing layer, to obtain a trained printing error correction model; During the printing process of the actual 3D model, the theoretical size and theoretical printing parameters of each printing layer of the actual 3D model are input into the trained printing error correction model to obtain the corrected theoretical size and theoretical printing parameters; Printing is performed according to the corrected theoretical size and theoretical printing parameters of each printing layer.

3. The detection method of a light-curing 3D printer according to claim 2, wherein: The trained printing error correction model includes: Dimensional error Prediction model: ,in, is the actual size error vector of dimension (3×1); is a weight matrix of dimension (3×3) used to map from the theoretical size vector to the size error vector; is a theoretical size vector of dimension (3×1); is a weight matrix of dimension (2×3) used to map from the theoretical printing parameter vector to the size error vector; is the theoretical printing parameter vector of dimension (2×1); is the bias vector associated with size error prediction; Parameter error Prediction model: ,in, Represents the new parameter error prediction vector of the layer to be printed, including the predicted exposure time and light source intensity error; is a weight matrix of dimension (2×3) used to map from the theoretical size vector to the parameter error prediction vector; is a weight matrix of dimension (2×2) used to map from the theoretical printed parameter vector to the parameter error prediction vector; is the bias vector associated with the parameter error prediction; is a theoretical size vector of dimension (3×1); is the theoretical printing parameter vector of dimension (2×1); Theoretical size correction model: ; Theoretical printing parameter correction model: ; In the actual application process, the theoretical size and theoretical printing parameters of the layer to be printed are input, and the prediction error is calculated through the above-trained printing error correction model to calculate the corrected theoretical value, thereby obtaining the corrected theoretical size and theoretical printing parameters.

4. A detection device for a light-curing 3D printer, characterized in that: include: a setting module for setting a 3D test model for testing; wherein each printed layer of the 3D test model has the same thickness, each printed layer has a square cross-section, and the cross-sectional area of ​​each printed layer increases from top to bottom; The test printing module is used to perform layer-by-layer photocuring 3D printing based on the 3D test model and record the actual printing parameters of each layer during photocuring 3D printing through the target sensor; The actual printing parameters include actual exposure time and actual exposure light intensity; The measurement module is used to measure the dimensions of the printed model product using a 3D optical scanner to obtain the actual dimensions of each printed layer; the actual dimensions include actual thickness, actual length, and actual width; A calculation module is used to calculate the dimensional error between the actual size of each printing layer and the theoretical size, and to calculate the parameter error between the actual printing parameters and the theoretical printing parameters; An analysis module is used to obtain a print quality test result of the light-curing 3D printer based on the dimensional error and parameter error of each printing layer; The analysis module is specifically used to calculate the comprehensive error coefficient of each printing layer according to the dimensional error and parameter error of each printing layer and the following calculation formula: ， in, Respectively represent the preset weight coefficients corresponding to each size error and each parameter error, is the thickness error in the size error, is the length error in the size error, is the width error in the size error, is the exposure time error in the parameter error, is the exposure intensity error in the parameter error; If the relevant errors of the printed layer do not meet the following error qualification conditions, the printing quality of the printed layer does not meet the requirements; the error qualification conditions include: the comprehensive error coefficient is less than a preset error coefficient threshold, and the individual errors of the dimensional error and the parameter error are both less than a preset error threshold; If the relevant error of the printed layer meets the error qualification condition, the printing quality of the printed layer meets the requirement.

5. The detection device for a light-curing 3D printer according to claim 4, wherein: The device further comprises: A collection module is used to collect printing data samples of each printing layer; the printing data samples include: theoretical size, size error, theoretical printing parameters and parameter error; A training module, configured to train a printing error correction model for correcting printing errors of each printing layer using printing data samples collected multiple times, thereby obtaining a trained printing error correction model; A correction module is used to input the theoretical size and theoretical printing parameters of each printing layer of the actual 3D model into the trained printing error correction model during the printing process of the actual 3D model to obtain the corrected theoretical size and theoretical printing parameters; The actual printing module is used to print according to the corrected theoretical size and theoretical printing parameters of each printing layer.

6. The detection device for a light-curing 3D printer according to claim 5, wherein: The trained printing error correction model includes: Dimensional error Prediction model: ,in, is the actual size error vector of dimension (3×1); is a weight matrix of dimension (3×3) used to map from the theoretical size vector to the size error vector; is a theoretical size vector of dimension (3×1); is a weight matrix of dimension (2×3) used to map from the theoretical printing parameter vector to the size error vector; is the theoretical printing parameter vector of dimension (2×1); is the bias vector associated with size error prediction; Parameter error Prediction model: ,in, Represents the new parameter error prediction vector of the layer to be printed, including the predicted exposure time and light source intensity error; is a weight matrix of dimension (2×3) used to map from the theoretical size vector to the parameter error prediction vector; is a weight matrix of dimension (2×2) used to map from the theoretical printed parameter vector to the parameter error prediction vector; is the bias vector associated with the parameter error prediction; is a theoretical size vector of dimension (3×1); is the theoretical printing parameter vector of dimension (2×1); Theoretical size correction model: ; Theoretical printing parameter correction model: ; In the actual application process, the theoretical size and theoretical printing parameters of the layer to be printed are input, and the prediction error is calculated through the above-trained printing error correction model to calculate the corrected theoretical value, thereby obtaining the corrected theoretical size and theoretical printing parameters.

7. A detection device for a light-curing 3D printer, characterized in that: The device comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the detection method for a light-curing 3D printer according to any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the detection method for a light-curing 3D printer according to any one of claims 1 to 3.

Images