3D printing success rate evaluation method and system based on big data analysis

Abstract

The invention relates to a 3D printing success rate evaluation method and system based on big data analysis, and relates to the field of 3D printing.The method comprises the steps that model parameters are obtained for complexity analysis, and model complexity is obtained; obtaining slicing precision, printing material characteristic parameters and environment characteristic parameters; performing basic printing success rate analysis according to the model complexity, the printing material characteristic parameters and the environment characteristic parameters to obtain a basic printing success rate; and obtaining a printing difficulty coefficient according to the slicing precision classification, and correcting the basic printing success rate to obtain the printing success rate. Through the method, the technical problem that in an existing method, due to the fact that the printing success rate of the article cannot be accurately evaluated, article printing optimization is difficult to achieve, and the article printing failure rate is high can be solved; the printing success rate of the article is comprehensively evaluated by combining multiple factors, the accuracy and reliability of printing success rate evaluation can be remarkably improved, and the overall success rate and production efficiency of 3D printing are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of 3D printing, and in particular to a 3D printing success rate evaluation method and system based on big data analysis. Background Art

[0002] 3D printing is a manufacturing technology that uses computer-aided design (CAD) files to create three-dimensional objects by adding materials layer by layer. Unlike traditional subtractive manufacturing methods, 3D printing can build complex geometric shapes by stacking layers, greatly improving design flexibility and production efficiency.

[0003] With the rapid development of 3D printing technology, its application in manufacturing, medical, aerospace, consumer products and other fields is becoming more and more extensive. However, although 3D printing has high design flexibility and manufacturing efficiency, how to accurately evaluate the printing success rate is still a technical problem that needs to be solved urgently.

[0004] At present, the existing 3D printing success rate evaluation method has the limitation that it cannot be effectively combined with the actual printing scenario, resulting in insufficient accuracy of the evaluation results. This not only affects the optimization process of object printing, but also causes a high printing failure rate and increases the waste of time and resources. Summary of the invention

[0005] The present invention aims to solve the technical problem that the existing 3D printing success rate evaluation method cannot accurately evaluate the printing success rate of an object in combination with the actual printing scenario, resulting in difficulty in optimizing the printing of the object and a high failure rate of the printing of the object. A 3D printing success rate evaluation method and system based on big data analysis are provided to solve the problem.

[0006] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a 3D printing success rate evaluation method based on big data analysis, comprising: obtaining model parameters of an object model currently being 3D printed, performing model complexity analysis, and obtaining model complexity; obtaining slicing accuracy for slicing the object model, and collecting printing material characteristic parameters and environmental characteristic parameters currently being printed; performing basic printing success rate analysis based on the model complexity, printing material characteristic parameters, and environmental characteristic parameters to obtain a basic printing success rate; obtaining a printing difficulty coefficient based on the slicing accuracy, correcting the basic printing success rate, and obtaining a printing success rate as a printing success rate evaluation result.

[0007] In a second aspect, the present invention provides a 3D printing success rate evaluation system based on big data analysis, including: a model complexity analysis module, used to obtain model parameters of an object model currently being 3D printed, perform model complexity analysis, and obtain model complexity; an information acquisition module, used to obtain the slicing accuracy of the object model, and collect the printing material characteristic parameters and environmental characteristic parameters currently being printed; a basic printing success rate analysis module, used to perform basic printing success rate analysis based on the model complexity, printing material characteristic parameters and environmental characteristic parameters, and obtain a basic printing success rate; a basic printing success rate correction module, used to classify and obtain a printing difficulty coefficient based on the slicing accuracy, correct the basic printing success rate, and obtain a printing success rate as a printing success rate evaluation result.

[0008] In a third aspect, the present invention further provides an electronic device, comprising: At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can perform the steps of any one of the methods described in the first aspect above.

[0009] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the steps of the method described in any one of the first aspects are implemented.

[0010] The beneficial effects of the present invention are as follows: by obtaining the model parameters of the object model currently being 3D printed, the model complexity analysis is performed according to the model parameters to obtain the model complexity; then the slicing accuracy of the object model is obtained, and the characteristic parameters of the printing material and the environmental characteristic parameters of the current printing are collected; then according to the model complexity, the characteristic parameters of the printing material and the environmental characteristic parameters, a basic printing success rate analysis is performed to obtain the basic printing success rate; finally, according to the slicing accuracy, the printing difficulty coefficient is obtained by classification, the basic printing success rate is corrected, and the printing success rate is obtained as the printing success rate evaluation result. By comprehensively evaluating the printing success rate of an object by combining multiple factors, the accuracy and reliability of the printing success rate evaluation can be significantly improved, thereby providing a basis for optimizing and adjusting the printing parameters, and achieving the technical effect of effectively improving the overall success rate and production efficiency of 3D printing. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of the process of the 3D printing success rate evaluation method based on big data analysis provided by the present invention; Figure 2A schematic diagram of the structure of a 3D printing success rate evaluation system based on big data analysis provided by the present invention; Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention; Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0012] In the accompanying drawings, the components represented by the reference numerals are described as follows: Model complexity analysis module 01, information collection module 02, basic printing success rate analysis module 03, basic printing success rate correction module 04, electronic device 500, memory 510, processor 520, first computer program 511, computer readable storage medium 600, second computer program 611. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0014] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0015] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0016] Embodiment 1, as Figure 1 As shown, the embodiment of the present invention provides a 3D printing success rate evaluation method based on big data analysis, which specifically includes: S100: Obtain model parameters of the object model currently being 3D printed, perform model complexity analysis, and obtain model complexity.

[0017] In one embodiment, step S100 of the present application further includes: S110: Training model complex identifier.

[0018] In one embodiment, step S110 of the present application further includes: S111: According to the 3D printing record data in the historical time, a sample model parameter set is collected, and according to the minimum size parameter in each sample model parameter, the sample model complexity set is obtained by processing and labeling; S112: Using the sample model parameter set and the sample model complexity set, a model complexity identifier is trained until convergence.

[0019] Specifically, first, collect the historical printing data of the 3D printing device within a predetermined time period, and the predetermined time period can be set according to demand, for example, within the past three months, wherein the historical printing data includes model parameters (such as size, shape, material type, etc.), printing results (success rate, time, cost, etc.) and other data. Then collect sample model parameters in the historical printing data to obtain a sample model parameter set; further obtain the minimum size parameter in each sample model parameter, wherein the minimum size parameter refers to the minimum feature size that affects the printing quality and feasibility in the 3D printing model, such as the minimum wall thickness; then annotate the model complexity of the sample model parameters according to the minimum size parameter, wherein the minimum size parameter and the model complexity are negatively correlated, that is, the smaller the minimum size parameter, the greater the model complexity, and obtain multiple sample model complexities corresponding to multiple sample model parameters, and construct a sample model complexity set.

[0020] Then, a model complexity identifier is constructed based on the BP neural network. The model complexity identifier is a neural network model that can be iteratively optimized in machine learning, including an input layer, multiple hidden layers and an output layer, wherein the input data of the input layer is the model parameter, and the output data of the output layer is the model complexity. Then, the sample model parameters are used as input data, the sample model complexity is used as supervision data, and the sample model parameter set and the sample model complexity set are used as training data to perform supervised training on the model complexity identifier. First, the sample model parameters are input into the neural network, and the output of each layer is calculated until the output layer generates a predicted complexity. value; then, use the loss function (such as mean square error or cross entropy loss) to calculate the gap between the predicted value and the true label; then, based on the result of the loss function, calculate the gradient of each parameter (weight and bias) to the loss, and backpropagate the gradient from the output layer to the input layer through the chain rule to update the weights and biases of each layer; further, use an optimization algorithm (such as gradient descent) to update the weights and biases according to the calculated gradient, and the learning rate determines the step size of the update; finally, repeat the process of forward propagation, loss calculation, backpropagation, and weight update until the set number of iterations is reached or the loss converges, and the trained model complex recognizer is obtained.

[0021] By constructing a model complexity identifier based on the BP neural network, the complexity of the sample model can be effectively analyzed, while improving the efficiency and accuracy of model complexity prediction.

[0022] S120: Acquire model parameters of the object model currently being 3D printed; S130: Input the model parameters into the model complexity identifier, and output the obtained model complexity.

[0023] Specifically, the model parameters of the current object, including size parameters, material parameters, etc., are extracted from the 3D printing software or model file; the model parameters are then input into the model complexity identifier for analysis, and the model complexity is output. Through the above steps, the model parameters of the current 3D printed object can be effectively obtained, and the model complexity identifier can be used to predict its complexity to provide support for the printing process.

[0024] S200: Acquire the slicing accuracy of the object model, and collect characteristic parameters of the printing material and the environment characteristic parameters currently being printed.

[0025] In one embodiment, step S200 of the present application further includes: S210: Acquire the minimum slice size for slicing the object model, and calculate the ratio of the average slice size to the minimum slice size as slice accuracy information; S220: Collect characteristic parameters of the printing material currently being printed and current environmental parameters.

[0026] Specifically, the minimum slice size for slicing the object model is obtained, that is, the minimum slice size of the current object model is extracted from the slicing software used. The minimum slice size refers to the minimum layer thickness that can be achieved during the slicing process, which affects the printing accuracy and detail performance. Then, the slicing data is collected from previous printing records to calculate the average slice size in the historical time. This data can be queried through the database or extracted from the log file, such as calculating the average slice size of the past three. Then the ratio of the average slice size and the minimum slice size is calculated, and the ratio is used as the slicing accuracy information. If the ratio is close to 1, it means that the slicing accuracy is high; if the ratio is greater than 1, it means that the average slice size is relatively large, which may affect the detail performance of the print.

[0027] On the other hand, characteristic parameters of the printing material currently being printed and the current environmental parameters are collected, where the characteristic parameters of the printing material include characteristics such as material type, material density, melting point, glass transition temperature and fluidity; environmental parameters include parameters such as ambient temperature and ambient humidity, where environmental parameters will affect the printing success rate. For example, too high or too low ambient temperature will affect the melting characteristics and cooling speed of the material, low temperature may cause incomplete curing of the material, and high temperature may cause thermal deformation.

[0028] S300: Performing a basic printing success rate analysis according to the model complexity, printing material characteristic parameters and environmental characteristic parameters to obtain a basic printing success rate.

[0029] In one embodiment, step S300 of the present application further includes: S310: Based on the historical data of 3D printing, collect the sample model complexity set, the sample printing material feature parameter set and the sample environment feature parameter set, and calculate and label the sample basic printing success rate set according to the printing success ratio; S320: Use the sample model complexity set, the sample printing material feature parameter set, the sample environment feature parameter set and the sample basic printing success rate set to train the basic printing predictor; S330: Input the model complexity, printing material feature parameters and environmental feature parameters into the basic printing predictor, and output the basic printing success rate.

[0030] Specifically, historical data of 3D printing is obtained, and information is extracted from the historical printing data to collect a set of sample model complexities, a set of sample printing material characteristic parameters, and a set of sample environment characteristic parameters. Further statistics are collected on the proportion of successful printings in the historical printing data under different sample model complexities, different sample printing material characteristic parameters, and different sample environment characteristic parameters, that is, the ratio of the number of successful printings to the total number of printings, and the sample basic printing success rate is calculated to obtain a set of sample basic printing success rates.

[0031] Then, a basic printing predictor is constructed based on the BP neural network, wherein the basic printing predictor comprises an input layer, a plurality of hidden layers and an output layer, wherein the input data of the input layer are model complexity, printing material characteristic parameters and environmental characteristic parameters, and the output data are basic printing success rate; then, the sample model complexity, the sample printing material characteristic parameters and the sample environmental characteristic parameters are used as input, the sample basic printing success rate is used as supervision, and the sample model complexity set, the sample printing material characteristic parameter set, the sample environmental characteristic parameter set and the sample basic printing success rate set are used as training data to perform supervised training and verification training on the basic printing predictor, firstly, the data set is divided into a training set and a verification set (for example, 80% is used for training, 20% for verification); then supervise the basic printing predictor through the training set, for example, input the input feature data into the neural network, after each layer of calculation, get the output value (predicted basic printing success rate), then use the loss function (such as mean square error) to calculate the error between the predicted value and the true value, and calculate the gradient of the loss function for each weight and bias, and back propagate the gradient from the output layer to the input layer through the chain rule to update the weight and bias; further use the optimization algorithm (such as stochastic gradient descent, Adam, etc.) to update the network parameters, adjust the step size of the weight update according to the learning rate; repeat the process of forward propagation, loss calculation, back propagation and weight update until the set number of iterations is reached or the loss converges. Then verify the basic printing predictor through the validation set, that is, use the validation set for evaluation, calculate the prediction accuracy and loss of the model on the validation set, and judge the generalization ability of the model; according to the validation results, adjust the model structure and hyperparameters (such as learning rate, number of hidden layer nodes, etc.) to optimize the model performance; finally, get the basic printing predictor that meets the expected conditions.

[0032] Finally, the model complexity, printing material characteristic parameters and environmental characteristic parameters are input into the basic printing predictor, and the basic printing success rate is obtained by output. By constructing a basic printing predictor for intelligent prediction, the efficiency, accuracy and reliability of the basic printing success rate can be improved, thereby improving the accuracy and reliability of the final printing success rate evaluation.

[0033] S400: According to the slicing accuracy, the printing difficulty coefficient is obtained by classification, and the basic printing success rate is corrected to obtain the printing success rate as a printing success rate evaluation result.

[0034] In one embodiment, step S400 of the present application further includes: S410: Classify and obtain a printing difficulty coefficient according to the slicing accuracy.

[0035] In one embodiment, step S410 of the present application further includes: S411: Based on the historical data of 3D printing, a set of sample slicing accuracy is collected, and the average proportion of the decrease in printing success rate under different sample slicing accuracy is collected to obtain a set of sample printing difficulty coefficients; S412: A mapping relationship between the sample slicing accuracy set and the sample printing difficulty coefficient set is constructed to obtain a printing difficulty classifier; S413: The slicing accuracy is input into the printing difficulty classifier, and the printing difficulty coefficient is obtained by mapping and classification.

[0036] Specifically, based on the historical data of 3D printing, a set of sample slicing accuracy is collected, and the sample reduction ratios of the printing success rate under different sample slicing accuracy are collected to obtain multiple sample reduction ratios, and the average of the multiple sample reduction ratios is calculated to obtain the sample average reduction ratio, and the sample average reduction ratio is set as the sample printing difficulty coefficient to obtain the sample printing difficulty coefficient set. Through the above steps, the sample slicing accuracy set and the printing success rate reduction ratio can be effectively collected, and the sample printing difficulty coefficient can be calculated, providing a reference for optimizing the 3D printing process.

[0037] Based on the decision tree principle, the sample slicing accuracy is the child node of the tree, and the sample printing difficulty coefficient is the leaf node of the child node. According to the mapping relationship between the sample slicing accuracy and the sample printing difficulty coefficient, the sample slicing accuracy set and the sample printing difficulty coefficient set are used as construction data to construct a printing difficulty classifier. Finally, the slicing accuracy is input into the printing difficulty classifier for matching, and the printing difficulty coefficient is obtained by mapping and classification.

[0038] S420: Using the printing difficulty coefficient, perform correction calculation on the basic printing success rate to obtain a printing success rate as a printing success rate evaluation result.

[0039] Specifically, a correction coefficient is set according to the printing difficulty coefficient, wherein the correction coefficient is used to adjust the printing success rate, reflecting the influence of the printing difficulty coefficient on the success rate. The larger the printing difficulty coefficient, the larger the correction coefficient should be, indicating that the success rate decreases more. Then, the basic printing success rate is corrected and calculated according to the correction coefficient. For example, 1 minus the correction coefficient is used as the correction weight, and the product of the correction weight and the basic printing success rate is used as the printing success rate, and the printing success rate is obtained as the printing success rate evaluation result. By correcting the basic printing success rate according to the printing difficulty coefficient, the accuracy and reliability of the printing success rate evaluation can be further improved.

[0040] The 3D printing success rate evaluation method based on big data analysis provided by the embodiment of the present invention has at least the following technical effects: By obtaining the model parameters of the object model currently being 3D printed, the model complexity analysis is performed based on the model parameters to obtain the model complexity; then the slicing accuracy of the object model is obtained, and the characteristic parameters of the printing material and the environmental characteristic parameters of the current printing are collected; then the basic printing success rate analysis is performed based on the model complexity, the characteristic parameters of the printing material and the environmental characteristic parameters to obtain the basic printing success rate; finally, according to the slicing accuracy, the printing difficulty coefficient is obtained by classification, and the basic printing success rate is corrected to obtain the printing success rate as the printing success rate evaluation result. By comprehensively evaluating the printing success rate of an object by combining multiple factors, the accuracy and reliability of the printing success rate evaluation can be significantly improved, thereby providing a basis for optimizing and adjusting the printing parameters, and achieving the technical effect of effectively improving the overall success rate and production efficiency of 3D printing.

[0041] Embodiment 2, as Figure 2 As shown, based on the same inventive concept as the 3D printing success rate evaluation method based on big data analysis provided in Example 1, the embodiment of the present invention also provides a 3D printing success rate evaluation system based on big data analysis, including: The model complexity analysis module 01 is used to obtain the model parameters of the object model currently being 3D printed, perform model complexity analysis, and obtain the model complexity; the information acquisition module 02 is used to obtain the slicing accuracy of the object model, and collect the printing material characteristic parameters and environmental characteristic parameters currently being printed; the basic printing success rate analysis module 03 is used to perform basic printing success rate analysis based on the model complexity, printing material characteristic parameters and environmental characteristic parameters to obtain the basic printing success rate; the basic printing success rate correction module 04 is used to classify and obtain the printing difficulty coefficient based on the slicing accuracy, correct the basic printing success rate, and obtain the printing success rate as the printing success rate evaluation result.

[0042] In one embodiment, the 3D printing success rate evaluation system based on big data analysis further includes: Training a model complexity identifier; obtaining model parameters of a model of an object currently being 3D printed; inputting the model parameters into the model complexity identifier, and outputting the obtained model complexity.

[0043] In one embodiment, the 3D printing success rate evaluation system based on big data analysis further includes: According to the 3D printing record data in the historical time, a sample model parameter set is collected, and according to the minimum size parameter in each sample model parameter, the labeling is processed to obtain a sample model complexity set; the sample model parameter set and the sample model complexity set are used to train the model complexity identifier until convergence.

[0044] In one embodiment, the 3D printing success rate evaluation system based on big data analysis further includes: The minimum slice size for slicing the object model is obtained, and the ratio of the average slice size to the minimum slice size is calculated as the slice accuracy information; characteristic parameters of the printing material currently being printed and the current environmental parameters are collected.

[0045] In one embodiment, the 3D printing success rate evaluation system based on big data analysis further includes: According to the historical data of 3D printing, a sample model complexity set, a sample printing material characteristic parameter set and a sample environment characteristic parameter set are collected, and according to the printing success ratio, a sample basic printing success rate set is calculated and labeled; the sample model complexity set, the sample printing material characteristic parameter set, the sample environment characteristic parameter set and the sample basic printing success rate set are used to train a basic printing predictor; the model complexity, printing material characteristic parameters and environmental characteristic parameters are input into the basic printing predictor, and the basic printing success rate is obtained as output.

[0046] In one embodiment, the 3D printing success rate evaluation system based on big data analysis further includes: According to the slicing accuracy, a printing difficulty coefficient is obtained by classification; the basic printing success rate is corrected and calculated using the printing difficulty coefficient to obtain a printing success rate as a printing success rate evaluation result.

[0047] In one embodiment, the 3D printing success rate evaluation system based on big data analysis further includes: According to the historical data of 3D printing, a set of sample slicing accuracy is collected, and the average proportion of the decrease in printing success rate under different sample slicing accuracy is collected to obtain a set of sample printing difficulty coefficients; a mapping relationship between the sample slicing accuracy set and the sample printing difficulty coefficient set is constructed to obtain a printing difficulty classifier; the slicing accuracy is input into the printing difficulty classifier, and the printing difficulty coefficient is obtained by mapping and classification.

[0048] For example 3, please refer to Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: obtaining model parameters of an object model currently being 3D printed, performing a model complexity analysis, and obtaining the model complexity; obtaining a slicing accuracy for slicing the object model, and collecting characteristic parameters of printing materials and environmental characteristic parameters currently being printed; performing a basic printing success rate analysis based on the model complexity, printing material characteristic parameters, and environmental characteristic parameters to obtain a basic printing success rate; obtaining a printing difficulty coefficient based on the slicing accuracy, correcting the basic printing success rate, and obtaining a printing success rate as a printing success rate evaluation result.

[0049] Example 4, please refer to Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by the processor, the following steps are implemented: obtaining model parameters of the object model currently being 3D printed, performing model complexity analysis, and obtaining model complexity; obtaining the slicing accuracy of the object model, and collecting the printing material characteristic parameters and environmental characteristic parameters of the current printing; performing basic printing success rate analysis based on the model complexity, printing material characteristic parameters and environmental characteristic parameters to obtain a basic printing success rate; according to the slicing accuracy, classifying and obtaining the printing difficulty coefficient, correcting the basic printing success rate, and obtaining the printing success rate as a printing success rate evaluation result.

[0050] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0051] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0053] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0055] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0056] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A 3D printing success rate evaluation method based on big data analysis, characterized in that: Methods include: Obtain model parameters of the object model currently being 3D printed, perform model complexity analysis, and obtain model complexity; Acquiring the slicing accuracy of the object model, and collecting characteristic parameters of the printing material and the environment characteristic parameters currently being printed; Performing a basic printing success rate analysis according to the model complexity, printing material characteristic parameters and environmental characteristic parameters to obtain a basic printing success rate; According to the slicing accuracy, the printing difficulty coefficient is classified and the basic printing success rate is corrected to obtain the printing success rate as the printing success rate evaluation result.

2. The 3D printing success rate evaluation method based on big data analysis according to claim 1, characterized in that: Obtain model parameters of the object model currently being 3D printed, perform model complexity analysis, and obtain model complexity, including: Training model complex recognizer; Get the model parameters of the object model currently being 3D printed; The model parameters are input into the model complexity identifier, and the model complexity is obtained as output.

3. The 3D printing success rate evaluation method based on big data analysis according to claim 2 is characterized in that: Training model complex recognizer, including: According to the 3D printing record data in the historical time, a set of sample model parameters is collected, and according to the minimum size parameter in each sample model parameter, the annotation is processed to obtain a set of sample model complexity; The sample model parameter set and the sample model complexity set are used to train a model complexity identifier until convergence.

4. The 3D printing success rate evaluation method based on big data analysis according to claim 1, characterized in that: Acquiring the slicing accuracy of the object model and collecting characteristic parameters of the printing material and the environment characteristic parameters currently being printed include: Acquire the minimum slice size for slicing the object model, and calculate the ratio of the average slice size to the minimum slice size as the slicing accuracy information; Collect the characteristic parameters of the printing material currently being printed and the current environmental parameters.

5. The 3D printing success rate evaluation method based on big data analysis according to claim 1, characterized in that: According to the model complexity, printing material characteristic parameters and environmental characteristic parameters, a basic printing success rate analysis is performed to obtain a basic printing success rate, including: According to the historical data of 3D printing, the sample model complexity set, the sample printing material characteristic parameter set and the sample environment characteristic parameter set are collected, and according to the printing success ratio, the sample basic printing success rate set is calculated and annotated; Using the sample model complexity set, the sample printing material characteristic parameter set, the sample environment characteristic parameter set and the sample basic printing success rate set, to train a basic printing predictor; The model complexity, printing material characteristic parameters and environmental characteristic parameters are input into the basic printing predictor, and the basic printing success rate is obtained as an output.

6. The 3D printing success rate evaluation method based on big data analysis according to claim 1, characterized in that: According to the slicing accuracy, the printing difficulty coefficient is obtained by classification, and the basic printing success rate is corrected to obtain the printing success rate as the printing success rate evaluation result, including: According to the slicing accuracy, a printing difficulty coefficient is obtained by classification; The printing difficulty coefficient is used to perform a correction calculation on the basic printing success rate to obtain a printing success rate as a printing success rate evaluation result.

7. The 3D printing success rate evaluation method based on big data analysis according to claim 6, characterized in that: According to the slicing accuracy, the printing difficulty coefficient is classified, including: According to the historical data of 3D printing, a set of sample slice accuracy is collected, and the average proportion of the decrease in printing success rate under different sample slice accuracy is collected to obtain a set of sample printing difficulty coefficients; Constructing a mapping relationship between the sample slicing precision set and the sample printing difficulty coefficient set to obtain a printing difficulty classifier; The slicing accuracy is input into the printing difficulty classifier, and the printing difficulty coefficient is obtained by mapping and classifying.

8. A 3D printing success rate evaluation system based on big data analysis, characterized in that: The steps for implementing the 3D printing success rate evaluation method based on big data analysis as described in any one of claims 1 to 7 include: The model complexity analysis module is used to obtain the model parameters of the object model currently being 3D printed, perform model complexity analysis, and obtain the model complexity; An information collection module, used to obtain the slicing accuracy of the object model, and to collect characteristic parameters of the printing material and the environment characteristic parameters currently being printed; A basic printing success rate analysis module is used to perform a basic printing success rate analysis based on the model complexity, printing material characteristic parameters and environmental characteristic parameters to obtain a basic printing success rate; The basic printing success rate correction module is used to classify and obtain the printing difficulty coefficient according to the slicing accuracy, correct the basic printing success rate, and obtain the printing success rate as the printing success rate evaluation result.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the steps of the 3D printing success rate evaluation method based on big data analysis as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the steps of the 3D printing success rate evaluation method based on big data analysis as described in any one of claims 1 to 7.

Images