3D Printing Exposure Pre - waiting Time Prediction Method, Device, Equipment and Medium

Abstract

The present disclosure relates to a method, apparatus, device and medium for predicting the waiting time before exposure in 3D printing. The method includes: obtaining a mask image of each printing cross-section in a 3D printing model; determining the edge angles in the mask image and determining the geometric parameters of the edge angles; inputting the geometric parameters of the edge angles into a pre-trained prediction model for processing to generate a waiting time corresponding to the edge angles; and determining the waiting time of the printing cross-section corresponding to the mask image according to the waiting time corresponding to the edge angles. According to the technical solution of the present disclosure, the waiting time before exposure of each printing cross-section can be predicted in real time and accurately.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and particularly to a method, apparatus, device and medium for predicting the waiting time before exposure in 3D printing. Background Art

[0002] 3D printing is a rapid prototyping technology (also known as additive manufacturing). In the up-pull surface forming 3D printing, when the printing platform descends, it will squeeze the resin liquid, causing certain deformations in the Z-axis of the printer and the material box. During the deformation recovery process, resin is extruded. If the light-curing model is performed at this time, some resin will still flow out when it is cured into a colloid, adhering to the model surface and resulting in a rough model surface. Therefore, it is necessary to wait for a period of time.

[0003] Currently, by setting an empirical time as the waiting time before exposure, this empirical time is used for all models and each layer. However, the accuracy of the empirically set time by humans is relatively low; alternatively, by detecting the drainage force with a force sensor and stopping waiting when the drainage force is less than a threshold value, this method requires a force sensor for detection, and for specific positions, it is impossible to use a force sensor to judge the flow rate and the waiting time. Summary of the Invention

[0004] To solve the above technical problems, the present disclosure provides a method, apparatus, device and medium for predicting the waiting time before exposure in 3D printing.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for predicting the waiting time before exposure in 3D printing, including:

[0006] Obtaining mask images of each printing section in the 3D printing model;

[0007] Determining the edge angles in the mask image and determining the geometric parameters of the edge angles;

[0008] Inputting the geometric parameters of the edge angles into a pre-trained prediction model for processing to generate a waiting time corresponding to the edge angles;

[0009] Determining the waiting time of the printing section corresponding to the mask image according to the waiting time corresponding to the edge angles.

[0010] In a second aspect, an embodiment of the present disclosure provides a device for predicting the waiting time before exposure in 3D printing, including:

[0011] An obtaining module, configured to obtain mask images of each printing section in the 3D printing model;

[0012] A determining module, configured to determine the edge angles in the mask image and determine the geometric parameters of the edge angles;

[0013] A prediction module, configured to input the geometric parameters of the edge angle into a pre-trained prediction model for processing, and generate a waiting time corresponding to the edge angle.

[0014] A generation module, configured to determine the waiting time of the printing section corresponding to the mask image according to the waiting time corresponding to the edge angle.

[0015] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor; a memory for storing executable instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the 3D printing pre-exposure waiting time prediction method described in the first aspect above.

[0016] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, where the storage medium stores a computer program, and when the computer program is executed by a processor, it implements the 3D printing pre-exposure waiting time prediction method described in the first aspect above.

[0017] The technical solution provided by the embodiment of the present disclosure has the following advantages compared with the prior art: By obtaining the mask images of each printing section in the 3D printing model, determining the geometric parameters of the edge angles in the mask images, and inputting the geometric parameters of the edge angles into a pre-trained prediction model for processing, the waiting time of the printing section corresponding to the mask image is determined. Thus, it is possible to predict the pre-exposure waiting time of each layer of the printing section in real time and accurately. The prediction can be achieved based on the geometric parameters of the edge angles, without the need to detect the drainage force through a force sensor, improving the accuracy and efficiency of the pre-exposure waiting time. Description of the Drawings

[0018] The drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0019] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a schematic flowchart of a 3D printing pre-exposure waiting time prediction method provided by an embodiment of the present disclosure;

[0021] Figure 2 It is a schematic diagram of the geometric parameters of a concave angle provided by an embodiment of the present disclosure;

[0022] Figure 3Schematic diagram of another geometric parameter of the concave corner provided by the embodiments of the present disclosure;

[0023] Figure 4 Schematic diagram of a distance field provided by the embodiments of the present disclosure;

[0024] Figure 5 Schematic diagram of a prediction process provided by the embodiments of the present disclosure;

[0025] Figure 6 Schematic diagram of a prediction model training process provided by the embodiments of the present disclosure;

[0026] Figure 7 Schematic diagram of the concave corner mask of a real model provided by the embodiments of the present disclosure;

[0027] Figure 8 Schematic diagram of the structure of a 3D printing pre-exposure waiting time prediction device provided by the embodiments of the present disclosure. Detailed implementation manners

[0028] In order to more clearly understand the above objects, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0029] Many specific details are set forth in the following description in order to fully understand the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0030] Figure 1 Schematic diagram of the process of a 3D printing pre-exposure waiting time prediction method provided by the embodiments of the present disclosure. The method provided by the embodiments of the present disclosure can be executed by a 3D printing pre-exposure waiting time prediction device, and the device can be implemented by software and / or hardware and can be integrated on any electronic device with computing capabilities.

[0031] As Figure 1 shown, the 3D printing pre-exposure waiting time prediction method provided by the embodiments of the present disclosure may include:

[0032] Step 101, obtaining the mask images of each printing section in the 3D printing model.

[0033] The method of the embodiments of the present disclosure can be applied to a surface exposure-based stereolithography printer.

[0034] In this embodiment, the 3D printing model to be printed is sliced to determine multiple printing sections, and then the mask images of each printing section are generated, where the mask images include the masks of the printing sections.

[0035] Step 102, determine the edge angles in the mask image and determine the geometric parameters of the edge angles.

[0036] In this embodiment, for the mask image of a certain printing cross-section, detect the edge angles of the mask in the mask image. Among them, the edge angle is the angle between adjacent sides, and the edge angle includes concave angles. Among them, the concave angle refers to an angle with an angle less than 180° outside the mask. For example Figure 2 as shown by θ in

[0037] As an example, based on the edge detection algorithm, perform edge detection on the mask image, and then determine the edge angles according to the edge detection results.

[0038] In this embodiment, the edge angles include two categories: concave angles and non-concave angles. Set corresponding geometric parameters according to the category of the edge angles. The geometric parameters of the edge angles are used to describe geometric information. The geometric parameters include, for example, angles, areas, lengths, etc. Optionally, the geometric parameters of the concave angles include angles and areas, and the geometric parameters of the non-concave angles include angles and lengths.

[0039] As an example, if there are concave angles in the mask image, determine the first region and the second region where convection occurs at the concave angles based on the mask image, and then determine the area of the first region and the area of the second region. Take the angle of the concave angle, the area of the first region, and the area of the second region as the geometric parameters of the edge angle.

[0040] Among them, as Figure 3 shown, any point p1 in the first region A1 and any point p2 in the second region A2 generate convection in the specified direction. The specified direction is the y-axis direction. Optionally, there are various ways to determine the first region and the second region where convection occurs at the concave angles. It is possible to determine the set of pixel points closest to the concave angle in the mask image. This type of pixel points flows out from the concave angle along the gradient direction in the distance field. The distance field is as Figure 4 shown. Thus, divide the set of pixel points into the first region and the second region according to the direction; or, determine the first region and the second region from the mask image by means of skeleton extraction.

[0041] In this example, if any one of all the edge angles of the mask is a concave angle, it is determined that there is a concave angle in the mask image, as Figure 2As shown in the figure, there is a concave angle θ in the figure. Then, the geometric parameters [θ, A1, A2] of this concave angle are used as the geometric parameters for subsequent input into the prediction model. In the geometric parameters, θ represents the angle of the concave angle, and A1 and A2 are the areas of the first region and the second region respectively. It should be noted that the above example is described with the presence of one concave angle in the mask image. For the case where there are multiple concave angles, multiple sets of geometric parameters can be determined corresponding to the multiple concave angles according to the above description and used as the geometric parameters for subsequent input into the prediction model. Thus, the waiting time of the concave angle can be accurately predicted through the geometric parameters of the concave angle.

[0042] As another example, if there is no concave angle in the mask image, then determine the maximum inscribed circle radius of the mask in the mask image. Among them, the preset target angle and the maximum inscribed circle radius are used as the geometric parameters of the edge angle.

[0043] In this example, if all the edge angles of the mask are not concave angles, it is determined that there is no concave angle in the mask image. For example, for the mask of a convex polygon, it is determined that there is no concave angle. In the case where there is no concave angle, determine the maximum inscribed circle radius R of the mask. For [θ, A1, A2] in the above example, where θ takes the preset target angle, and A1 and A2 both take the maximum inscribed circle radius. The target angle is, for example, 0. That is, when there is no concave angle in the mask image, the geometric parameters [0, R, R] are used as the geometric parameters for subsequent input into the prediction model. Thus, it is possible to support the prediction of the waiting time of the convex polygon mask.

[0044] Step 103: Input the geometric parameters of the edge angle into the pre-trained prediction model for processing to generate the waiting time corresponding to the edge angle.

[0045] In this embodiment, the prediction model is implemented based on machine learning. The machine learning model is pre-trained. The input of this machine learning model is the geometric parameter, and the output is the predicted waiting time. As an example, the input is 3D [θ, A1, A2], and the output is 1D waiting time.

[0046] Optionally, use a mask / true model with known geometric parameters for 3D printing, and observe and obtain the waiting time of each mask / true model. Label the observed waiting time to obtain a data set for model training, and then train the prediction model according to the data set and machine learning techniques.

[0047] Step 104: Determine the waiting time of the print section corresponding to the mask image according to the waiting time corresponding to the edge angle.

[0048] In this embodiment, for the mask image of a certain printing cross-section, the waiting time corresponding to at least one edge angle is determined based on the prediction model, and then the pre-exposure waiting time (also known as the drainage waiting time) of the printing cross-section is determined according to the waiting time corresponding to at least one edge angle. For example, there is a concave angle in the mask image. The geometric parameters of the concave angle are input into the prediction model to obtain the waiting time of the concave angle, and the waiting time of the concave angle is used as the pre-exposure waiting time of the printing cross-section. Another example is that if there is no concave angle in the mask image, the target angle and the radius of the largest inscribed circle are input into the prediction model, and the obtained waiting time is used as the pre-exposure waiting time of the printing cross-section.

[0049] In an embodiment of the present disclosure, the prediction model outputs multiple waiting times corresponding to the edge angles, determines the maximum value among the multiple waiting times corresponding to the multiple edge angles, and uses the maximum value as the waiting time of the mask image corresponding to the printing cross-section.

[0050] As an example, there are multiple concave angles in the mask image. The geometric parameters of the multiple concave angles are respectively input into the prediction model to obtain the prediction times of the multiple concave angles, and the maximum value among the prediction times of the multiple concave angles is used as the waiting time of the mask image corresponding to the printing cross-section. Refer to Figure 5 , the 3D printing model to be printed is sliced to obtain n layers of printing cross-sections. For the i-th layer of printing cross-section, the input is the mask image of the printing cross-section, and the pre-exposure waiting time of the printing cross-section is determined based on the foregoing steps.

[0051] According to the technical solution of the embodiment of the present disclosure, by obtaining the mask images of each printing cross-section in the 3D printing model, determining the geometric parameters of the edge angles in the mask image, inputting the geometric parameters of the edge angles into the pre-trained prediction model for processing, generating the waiting time corresponding to the edge angle, and then determining the waiting time of the mask image corresponding to the printing cross-section. Thus, it is possible to predict the pre-exposure waiting time of each layer of printing cross-section in real time and accurately, improve the accuracy compared with the method of setting the empirical time, and realize the prediction based on the geometric parameters of the edge angle, without detecting the drainage force through a force sensor, improving the accuracy and efficiency of the pre-exposure waiting time.

[0052] The training process of the prediction model will be described below.

[0053] Figure 6 is a schematic diagram of a prediction model training process provided by an embodiment of the present disclosure. As shown in Figure 6 , it includes the following steps:

[0054] Step 601, obtain a data set based on the concave angle mask and / or the circular mask, where the data set is labeled with the waiting time of the concave angle mask and / or the circular mask.

[0055] In this embodiment, a specific model is printed to obtain training data. Among them, for the dataset based on the concave corner mask, concave corner masks with different concave corner angles and different convection area sizes are printed, or the concave corner mask of the real model is printed. The concave corner mask of the real model is as shown in Figure 7 . For the dataset based on the circular mask, disks with different radii are printed. On a surface-exposure stereolithography printer, the waiting time usually gradually changes from 0.1 s to 12 s. By observing the waiting time required for each mask, the data is sorted as the training data of the prediction model.

[0056] Optionally, the prediction model is a Multilayer Perceptron (MLP).

[0057] Step 602: Train the prediction model based on the dataset.

[0058] In this embodiment, the dataset based on the concave corner mask includes the angle of the concave corner mask, the convection area size, and the waiting time. The dataset based on the circular mask includes the target angle, the radius, and the waiting time. Using the Multilayer Perceptron for model training according to the above datasets, the input of the model is 3-dimensional [θ, A1, A2], and the output is 1-dimensional waiting time.

[0059] As an example, the above datasets based on the concave corner mask and the circular mask are used to train the prediction model. In this example, the above two datasets are used to train the prediction model uniformly. Furthermore, in the prediction process, regardless of whether there is a concave corner in the mask image, the geometric parameters of the edge angle are input into the prediction model for processing to generate the waiting time corresponding to the edge angle.

[0060] As another example, the first prediction model is trained using the dataset based on the concave corner mask, and the second prediction model is trained using the dataset based on the circular mask. In this example, the above two datasets are used to train the prediction models separately. Furthermore, in the prediction process, if there is a concave corner in the mask image, the geometric parameters of the edge angle are input into the first prediction model for processing, and if there is no concave corner in the mask image, the geometric parameters of the edge angle are input into the second prediction model for processing. Thus, the prediction accuracy can be further improved.

[0061] The following gives an example of the model training and prediction process.

[0062] First, training data is collected, and a machine learning-based prediction model is trained based on the data. Furthermore, during 3D printing and prediction, the 3D printing model is sliced, and the sliced mask image is processed based on the prediction model. If there is a concave corner in the mask image, the geometric parameters [θ, A1, A2] of the concave corner are input into the prediction model to output the predicted time of the concave corner. If there are multiple predicted times, the maximum value among them is used as the waiting time for the printing cross-section of this layer. If there is no concave corner in the mask image, the maximum inscribed circle radius R of the mask is determined, and [θ, A1, A2] is input into the prediction model to output the corresponding predicted time and use it as the waiting time for the printing cross-section of this layer.

[0063] According to the technical solution of the embodiment of the present disclosure, the prediction model is trained through the data set of the concave corner mask and the data set of the circular mask. Based on geometric information such as the geometric parameters of the concave corner, the data required for machine learning can be satisfied, so as to accurately predict the waiting time before exposure of the printing cross-section, without detecting the drainage force through a force sensor, and improving the real-time performance of waiting time prediction.

[0064] Figure 8 The following is a schematic structural diagram of a device for predicting the waiting time before 3D printing exposure provided by an embodiment of the present disclosure. As Figure 8 shown, the device for predicting the waiting time before 3D printing exposure includes: an acquisition module 81, a determination module 82, a prediction module 83, and a generation module 84.

[0065] Among them, the acquisition module 81 is used to acquire the mask images of each printing cross-section in the 3D printing model;

[0066] The determination module 82 is used to determine the edge angles in the mask image and determine the geometric parameters of the edge angles;

[0067] The prediction module 83 is used to input the geometric parameters of the edge angles into a pre-trained prediction model for processing to generate a waiting time corresponding to the edge angles;

[0068] The generation module 84 is used to determine the waiting time of the printing cross-section corresponding to the mask image according to the waiting time corresponding to the edge angles.

[0069] In an embodiment of the present disclosure, the determination module 82 is specifically used for: if there is a concave corner in the mask image, based on the mask image, determine a first region and a second region where convection occurs at the concave corner, where any point in the first region and any point in the second region generate convection in a specified direction; determine the area of the first region and the area of the second region, and use the angle of the concave corner, the area of the first region, and the area of the second region as the geometric parameters of the edge angle.

[0070] In one embodiment of the present disclosure, the determining module 82 is specifically configured to: if there is no concave angle in the mask image, determine the radius of the largest inscribed circle of the mask in the mask image, where the preset target angle and the radius of the largest inscribed circle are used as the geometric parameters of the edge angle.

[0071] In one embodiment of the present disclosure, the prediction model is a multi-layer perceptron, and the apparatus further includes: a training module, configured to obtain a data set based on a concave angle mask and / or a circular mask, where the data set is labeled with the waiting time of the concave angle mask and / or the circular mask; and train the prediction model based on the data set.

[0072] In one embodiment of the present disclosure, the training module is specifically configured to: train a first prediction model using a data set based on a concave angle mask, and train a second prediction model using a data set based on a circular mask;

[0073] The prediction module 83 is specifically configured to: if there is a concave angle in the mask image, input the geometric parameters of the edge angle into the first prediction model for processing; if there is no concave angle in the mask image, input the geometric parameters of the edge angle into the second prediction model for processing.

[0074] In one embodiment of the present disclosure, the number of edge angles is multiple, and the generating module 84 is specifically configured to: determine the maximum value among the multiple waiting times corresponding to the multiple edge angles, where the maximum value is used as the waiting time of the printing section corresponding to the mask image.

[0075] The 3D printing pre-exposure waiting time prediction apparatus provided by the embodiments of the present disclosure can execute any 3D printing pre-exposure waiting time prediction method provided by the embodiments of the present disclosure, and has the corresponding functional modules and beneficial effects for executing the method. The content not described in detail in the apparatus embodiments of the present disclosure can be referred to the description in any method embodiment of the present disclosure.

[0076] An electronic device provided by an embodiment of the present disclosure includes one or more processors and a memory. The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. The memory may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor may run the program instructions to implement the methods of the embodiments of the present disclosure above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage media.

[0077] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms. In addition, the input device may include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including the determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc. In addition, according to specific application scenarios, the electronic device may further include any other appropriate components such as a bus, an input / output interface, etc.

[0078] In addition to the above methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions that cause the processor to execute any method provided by the embodiments of the present disclosure when the computer program instructions are run by the processor.

[0079] The computer program product may be written in any combination of one or more programming languages to write program code for performing the operations of the embodiments of the present disclosure. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0080] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium storing computer program instructions, which, when run by a processor, cause the processor to execute any method provided by the embodiments of the present disclosure.

[0081] The computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0082] It should be noted that, in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0083] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting the waiting time before 3D printing exposure, characterized in that, Including: Obtain the mask images of each printing section in the 3D printing model; Determine the edge angles in the mask images, and determine the geometric parameters of the edge angles; Input the geometric parameters of the edge angles into a pre-trained prediction model for processing to generate a waiting time corresponding to the edge angles; Determine the waiting time of the printing section corresponding to the mask image according to the waiting time corresponding to the edge angles; Wherein, the determining the geometric parameters of the edge angles includes: If there are concave angles in the mask image, based on the mask image, determine a first area and a second area where convection occurs at the concave angles, wherein any point in the first area and any point in the second area generate convection in a specified direction; Determine the area of the first area and the area of the second area, wherein the angle of the concave angle, the area of the first area, and the area of the second area are used as the geometric parameters of the edge angle; and / or, If there are no concave angles in the mask image, determine the radius of the largest inscribed circle of the mask in the mask image, wherein a preset target angle and the radius of the largest inscribed circle are used as the geometric parameters of the edge angle.

2. The method according to claim 1, wherein The prediction model is a multi-layer perceptron, and the method further includes: Obtain a data set based on concave angle masks and / or circular masks, wherein the waiting times of the concave angle masks and / or circular masks are labeled in the data set; Train the prediction model based on the data set.

3. The method according to claim 2, characterized in that, The training the prediction model based on the data set includes: Train a first prediction model using a data set based on concave angle masks, and train a second prediction model using a data set based on circular masks; The inputting the geometric parameters of the edge angles into a pre-trained prediction model for processing includes: If there are concave angles in the mask image, input the geometric parameters of the edge angles into the first prediction model for processing; If there are no concave angles in the mask image, input the geometric parameters of the edge angles into the second prediction model for processing.

4. The method according to claim 1, wherein The number of the edge angles is multiple, and the determining the waiting time of the printing section corresponding to the mask image according to the waiting time corresponding to the edge angles includes: Determine the maximum value among the multiple waiting times corresponding to the multiple edge angles, wherein the maximum value is used as the waiting time of the printing section corresponding to the mask image.

5. A device for predicting the waiting time before 3D printing exposure, characterized in that, Including: An obtaining module, configured to obtain the mask images of each printing section in the 3D printing model; A determining module, configured to determine the edge angles in the mask images and determine the geometric parameters of the edge angles; A prediction module, configured to input the geometric parameters of the edge angles into a pre-trained prediction model for processing to generate a waiting time corresponding to the edge angles; A generating module, configured to determine the waiting time of the printing section corresponding to the mask image according to the waiting time corresponding to the edge angles; Wherein, the determining module is specifically configured to: If there is a concave angle in the mask image, determine a first region and a second region where convection occurs at the concave angle based on the mask image, wherein any point in the first region and any point in the second region generate convection in a specified direction; Determine the area of the first region and the area of the second region, wherein the angle of the concave angle, the area of the first region, and the area of the second region are used as geometric parameters of the edge included angle; and / or, If there is no concave angle in the mask image, determine the radius of the largest inscribed circle of the mask in the mask image, wherein a preset target angle and the radius of the largest inscribed circle are used as geometric parameters of the edge included angle.

6. An electronic device, characterized in that, Comprising: A processor; A memory for storing executable instructions of the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the 3D printing pre-exposure waiting time prediction method according to any one of claims 1-4 above.

7. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by a processor, it implements the 3D printing pre-exposure waiting time prediction method according to any one of claims 1-4 above.

Images