Processing step detection method of 3D printing device, electronic device and storage medium

Abstract

The application provides a processing step detection method of a 3D printing device, an electronic device and a storage medium. The 3D printing device comprises a nozzle assembly, a printing platform and a laser light source. The method comprises: obtaining working data of a current processing step of the 3D printing device, wherein the processing step at least comprises extrusion flow detection of the nozzle assembly, first layer detection and leveling detection of the printing platform; inputting the working data into a preset model, wherein the preset model is obtained by training historical working data of the 3D printing device; and detecting whether the current processing step is abnormal according to an output result of the preset model. The application can automatically detect whether the processing step of the 3D printing device in the working process is abnormal, so as to find and solve the abnormal step in time, thereby ensuring the printing quality of the 3D printing device.

Description

Technical Field

[0001] This application relates to the field of 3D printing technology, and in particular to a method for detecting the processing steps of a 3D printing device, an electronic device, and a storage medium. Background Technology

[0002] With the popularization of concepts such as intelligent manufacturing engineering and Industry 4.0, 3D printing technology is becoming increasingly widespread. 3D printing technology first appeared in the mid-1990s and is essentially a new rapid prototyping device utilizing techniques such as photopolymerization and paper lamination. Its working principle is basically the same as ordinary printing; the printer contains liquid or powder "printing materials," and after being connected to a computer, the computer controls the layering of these "printing materials" to ultimately transform the blueprint on the computer into a physical object. This printing technology is called 3D stereolithography.

[0003] In related technologies, the processing steps of 3D printing equipment require manual inspection to check for abnormalities. On the one hand, this consumes a lot of manpower, and on the other hand, the accuracy of manual inspection is not high, which leads to a poor user experience. Summary of the Invention

[0004] In view of this, this application provides a 3D printing method, electronic device and storage medium that can automatically detect whether the processing steps of the 3D printing equipment are abnormal during operation, so as to promptly detect and resolve abnormal steps, thereby ensuring the printing quality of the 3D printing equipment.

[0005] The first aspect of this application provides a method for detecting processing steps in a 3D printing device. The 3D printing device includes a nozzle assembly, a printing platform, and a laser light source. The method includes: acquiring working data of the current processing step of the 3D printing device, wherein the processing step includes at least extrusion flow detection of the nozzle assembly, first-layer detection, and leveling detection of the printing platform; inputting the working data into a preset model, wherein the preset model is trained based on historical working data of the 3D printing device; and detecting whether the current processing step is abnormal based on the output of the preset model.

[0006] Compared with related technologies, the embodiments of this application have at least the following advantages: by acquiring the working data of the current processing step of the 3D printing equipment and then inputting the working data into the trained preset model, it is possible to detect whether the current processing step is abnormal based on the output result of the preset model, thereby realizing the automatic detection of the processing steps of the 3D printing equipment, so that the staff can discover and solve abnormal steps in time, thereby ensuring the printing quality of the 3D printing equipment.

[0007] In some possible implementations, the preset model is trained as follows: the historical working data is input into the initial model to train the initial model; the performance parameters of the trained initial model are checked to see if they meet the preset requirements; when the performance parameters of the trained initial model meet the preset requirements, the trained initial model is used as the preset model; when the performance parameters of the trained initial model do not meet the preset requirements, new historical working data is obtained, and the trained initial model is trained again based on the new historical working data.

[0008] By adopting this technical solution, the accuracy of the output results of the preset model can be improved.

[0009] In some possible implementations, before inputting the historical working data into the initial model, the method further includes: processing the historical working data to obtain processed data that meets the model training requirements; the step of inputting the historical working data into the initial model to train the initial model includes: inputting the processed data into the initial model to train the initial model.

[0010] By adopting this technical solution, the accuracy of the output results of the preset model can be further improved.

[0011] In some possible implementations, the historical working data includes image data, and the data processing of the historical working data includes cropping, scaling, and enhancing the image data.

[0012] In some possible implementations, the historical working data includes point cloud data, and the data processing of the historical working data includes filtering and sampling the point cloud data.

[0013] In some possible implementations, the preset model is one of a convolutional neural network model, a recurrent neural network model, or an autoencoder.

[0014] In some possible implementations, after detecting an anomaly in the current processing step based on the output of the preset model, the method further includes: sending an alarm signal, and / or controlling the 3D printing equipment to stop working.

[0015] In some possible implementations, the historical work data includes first historical work data when the 3D printing equipment is in normal working condition, and second historical work data when the 3D printing equipment is in abnormal working condition.

[0016] By adopting this technical solution, model training can be performed using more comprehensive historical data, thereby improving the accuracy of the output results of the preset model.

[0017] The second aspect of this application discloses an electronic device, which includes a processor and a memory. The memory is used to store instructions, and the processor is used to call the instructions in the memory to cause the electronic device to execute the above-described method for detecting the processing steps of a 3D printing device.

[0018] A third aspect of this application discloses a storage medium including computer instructions that, when executed on an electronic device, cause the electronic device to perform the aforementioned method for detecting the processing steps of a 3D printing device.

[0019] Understandably, the electronic device of the second aspect and the storage medium of the third aspect provided above correspond to the method of the first aspect. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart of a processing step detection method for a 3D printing device provided in an embodiment of this application.

[0022] Figure 2 This is a diagram illustrating the working interaction of a 3D printing device provided in one embodiment of this application.

[0023] Figure 3 This is a flowchart illustrating the first-layer detection of a 3D printing device according to an embodiment of this application.

[0024] Figure 4 This is a flowchart illustrating the leveling of the printing platform of a 3D printing device provided in an embodiment of this application.

[0025] Figure 5 This is a flowchart illustrating the leveling of the printing platform of a 3D printing device provided in an embodiment of this application.

[0026] Figure 6 This is a schematic diagram of the structure of a printing line A provided in an embodiment of this application.

[0027] Figure 7 This is a flowchart illustrating the leveling of the printing platform of a 3D printing device provided in an embodiment of this application.

[0028] Figure 8 An image showing the effect of a 3D printing device provided in an embodiment of this application printing on a printing platform.

[0029] Figure 9 Another rendering of the 3D printing device provided in one embodiment of this application printed on a printing platform.

[0030] Figure 10 This is a schematic diagram of a 3D printing device scanning printing platform provided in an embodiment of this application.

[0031] Figure 11 This is a schematic diagram of the normal vectors of the standard horizontal plane and the fitted plane provided in an embodiment of this application.

[0032] Figure 12 This is an application scenario diagram of the printing platform deformation printing compensation provided in an embodiment of this application.

[0033] Figure 13 This is a schematic diagram of a scenario for line height detection in a 3D printing device provided in an embodiment of this application.

[0034] Figure 14 Images captured by a camera of a 3D printing apparatus provided in an embodiment of this application.

[0035] Figure 15 Another image taken by the camera of a 3D printing device provided in one embodiment of this application.

[0036] Figure 16 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0037] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0038] The following description sets forth many specific details to provide a full understanding of this application. The described embodiments are only some, not all, of the embodiments of this application.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0040] It should be further noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0041] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural.

[0042] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0043] For ease of understanding, some concepts related to the embodiments of this application are illustrated and explained by way of example for reference.

[0044] 3D printing equipment, also known as three-dimensional printers or stereo printers, is a rapid prototyping process that typically uses digital technology to print materials. 3D printing equipment is commonly used in mold making, industrial design, and other fields to create models or parts.

[0045] Please refer to Figure 1 This is a flowchart of a method for detecting processing steps in a 3D printing device provided in this application embodiment. The 3D printing device includes a nozzle assembly, a printing platform, and a laser light source. The method includes the following steps:

[0046] Step 101: Obtain the working data of the current processing step of the 3D printing equipment. The processing step includes at least the extrusion flow detection of the nozzle assembly, the first layer detection, and the leveling detection of the printing platform.

[0047] In some embodiments, the type of working data may be images, point clouds, videos, etc., and this embodiment does not specifically limit the type of working data.

[0048] There are various ways to acquire work data, such as acquiring video of the 3D printing equipment during the working process using a camera, acquiring point cloud data using a laser light source, or acquiring images using a camera. This embodiment does not specifically limit the method of acquiring work data.

[0049] The processes of extrusion flow detection, first-layer detection, and printing platform leveling detection are described in detail in subsequent embodiments, and will not be repeated here to avoid repetition.

[0050] Step 102: Input the working data into the preset model, which is trained based on the historical working data of the 3D printing equipment.

[0051] In some embodiments, the preset model is trained as follows: the historical working data is input into the initial model to train the initial model; the performance parameters of the trained initial model are detected to meet preset requirements; when the performance parameters of the trained initial model meet the preset requirements, the trained initial model is used as the preset model; when the performance parameters of the trained initial model do not meet the preset requirements, new historical working data is obtained, and the trained initial model is trained again based on the new historical working data.

[0052] Specifically, the initial model needs thorough validation and optimization during training and testing to achieve good detection results. Therefore, extensive repeated training of the initial model is necessary to improve the detection accuracy of the final preset model.

[0053] In some embodiments, to improve the efficiency and accuracy of model training, before inputting historical working data into the initial model, the method further includes: processing the historical working data to obtain processed data that meets the model training requirements; and then training the initial model based on the processed data.

[0054] Specifically, the types of historical working data include point clouds, images, and videos. Taking point clouds as an example, the data processing of the historical working data includes filtering and sampling the point cloud data; taking image data as an example, the data processing of the historical working data includes cropping, scaling, and enhancing the image data.

[0055] It is worth mentioning that the collection and processing of historical working data need to fully consider the actual situation and cover as many possible anomalies as possible in order to improve the robustness and reliability of the preset model.

[0056] Step 103: Detect whether the current processing step is abnormal based on the output results of the preset model.

[0057] In some embodiments, the preset model is one of a convolutional neural network model, a recurrent neural network model, or an autoencoder.

[0058] In some embodiments, after detecting an abnormality in the current processing step based on the output of a preset model, the method further includes: sending an alarm signal, and / or controlling the 3D printing equipment to stop working.

[0059] Specifically, 3D printing equipment can directly send alarm information, such as voice broadcasts or text reminders to the user's terminal device; 3D printing equipment can also directly stop working to avoid the printing of poor-quality products due to continued operation.

[0060] In some embodiments, taking the extrusion flow detection of the nozzle assembly as an example, when the 3D printing equipment detects an abnormality in the extrusion flow of the nozzle assembly, the extrusion flow of the nozzle assembly can be directly adjusted before continuing operation. This method allows the 3D printing equipment to automatically resolve some anomalies, further improving the user experience.

[0061] Specifically, the entire process of inspecting the processing steps of the 3D printing equipment in this embodiment is divided into the following steps:

[0062] (1) Data collection: Collect data for each processing step, including data under normal and abnormal conditions. This data can be in the form of images, videos, point clouds, etc.

[0063] (2) Data preprocessing: The collected data is preprocessed, such as cropping, scaling and enhancing the images, and filtering and sampling the point clouds, so as to facilitate the subsequent training and testing of the deep learning model.

[0064] (3) Model training: Using the collected data, a deep learning model is trained to detect whether each processing step is abnormal. Commonly used models include convolutional neural networks, recurrent neural networks, and autoencoders.

[0065] (4) Model testing: Use the trained deep learning model to test new data and determine whether the current processing step is abnormal. Some metrics such as accuracy, recall, and F1-score can be used to evaluate the model's performance.

[0066] (5) Integration into the system: Integrate the trained deep learning model into the actual system, detect each processing step, and give corresponding prompts or take corresponding measures if there are any abnormalities.

[0067] To facilitate understanding, let's take the processing steps as the first layer of detection as an example, combined with... Figure 2 The processing step detection method of this embodiment will be described in detail:

[0068] Please refer to Figure 2 This is a diagram illustrating the working interaction of a 3D printing device provided in an embodiment of this application.

[0069] Specifically, Figure 2 The interactive diagram shown illustrates the workflow of a 3D printing device during the initial layer inspection. This process utilizes computer vision, deep learning, and point cloud methods for data acquisition and comparison to detect defects on the heated bed surface and problems with nozzle extrusion printing. The results are then analyzed and alerted. Essentially, the purpose of this interactive workflow is to perform a self-check of the environment and equipment before printing, ensuring print quality and success rate, and promptly alerting the user in case of any anomalies.

[0070] Compared with related technologies, the embodiments of this application have at least the following advantages: by acquiring the working data of the current processing step of the 3D printing equipment and then inputting the working data into the trained preset model, it is possible to detect whether the current processing step is abnormal based on the output result of the preset model, thereby realizing the automatic detection of the processing steps of the 3D printing equipment, so that the staff can discover and solve abnormal steps in time, thereby ensuring the printing quality of the 3D printing equipment.

[0071] Please refer to Figure 3 This is a flowchart of the first-layer detection of a 3D printing device provided in this application embodiment. This embodiment is applied to the 3D printing device of the aforementioned embodiment. The 3D printing device includes a nozzle assembly, a printing platform, and an imaging device. The nozzle assembly is used to spray printing material onto the printing platform, including the following steps:

[0072] Step 201: Control the shooting device to move to the first position. When the shooting device is in the first position, the shooting device is at a preset distance from the printing platform, and the angle between the shooting device and the printing platform is a preset angle.

[0073] In some embodiments, the 3D printing equipment includes a motor connected to an imaging device for controlling changes in the angle and position of the imaging device.

[0074] Step 202: Take an initial image of the current printing platform.

[0075] In some embodiments, the number of initial images is not specifically limited, and multiple initial images may be taken at the first location.

[0076] In some embodiments, the number of first positions is not specifically limited, that is, multiple initial images can be taken at different angles and / or different distances from the printing platform.

[0077] Step 203: Obtain the first layer information from the feature file. The feature file is used to command the 3D printing equipment to perform 3D printing work.

[0078] In some embodiments, the first-layer information also includes point cloud data of the first layer, and the first-layer information in the gcode file can be read using programming languages ​​such as Python.

[0079] In some embodiments, the feature file is a gcode file used to command the 3D printing process. The gcode file is used to instruct the 3D printing operation. To print a 3D model from a computer using a 3D printer, the model (commonly in .stl and .obj formats) first needs to be imported into 3D slicing software (such as Cura) for planar slicing, and then a gcode file is generated. The gcode file is then sent to the 3D printer for reading, and the nozzle assembly of the 3D printer will fill each layer according to the planned path, stacking them layer by layer to finally form the 3D model.

[0080] Step 204: Control the nozzle assembly to print the first layer of the 3D model based on the first layer information.

[0081] Step 205: After the first layer is printed, control the imaging device to capture the final image of the printing platform from the first position.

[0082] In some embodiments, the number of final images is the same as the number of initial images. For example, if the imaging device takes three initial images at the first position in step 102, then after the first layer is printed, the imaging device takes three final images at the first position again. If the imaging device takes one initial image at the first position and one initial image at the second position in step 202, then after the first layer is printed, the imaging device takes one final image at the first position and one final image at the second position respectively.

[0083] Step 206: Determine the printing quality of the 3D printing equipment based on the initial and final images.

[0084] In some embodiments, the printing quality of the 3D printing device is determined by: acquiring a difference image between an initial image and a final image; performing binarization denoising on the difference image to obtain a processed image; and comparing the processed image with a two-dimensional planar image to determine the printing quality of the 3D printing device.

[0085] In some embodiments, after determining the print quality of the 3D printing device, the method further includes: sending the print quality determination result of the 3D printing device to the user.

[0086] Specifically, the printing quality assessment results of the 3D printing equipment can be sent to the user's terminal device via SMS, pop-up reminders, etc. This embodiment does not impose specific limitations on the method of sending the printing quality assessment results. In addition, the printing quality assessment results can be displayed as text prompts, such as "Printing quality is good" or "Printing quality needs improvement," or as images, or as voice prompts. This embodiment does not impose specific limitations on the method of displaying the printing quality assessment results.

[0087] In some embodiments, a difference image is generated based on the initial image and the final image, and then the difference image is binarized and denoised. The processed image is compared with the planar two-dimensional image in the first layer information to determine the printing quality of the 3D printing device.

[0088] To facilitate understanding, the process of determining the printing quality of the 3D printing equipment in this embodiment will be explained in detail below:

[0089] (1) Use programming languages ​​such as Python to read the first-level information in the gcode file. The first-level information includes at least the first-level two-dimensional planar graph.

[0090] (2) Before printing the first layer, control the shooting device to be at a preset distance from the printing platform and the angle between the shooting device and the printing platform to be a preset angle, and then take an initial image of the printing platform.

[0091] (3) The 3D printing equipment receives the first layer information and performs the first layer printing.

[0092] (4) After the first layer is printed, control the shooting device to take the final image of the printing platform at the same position as the initial image.

[0093] (5) Use programming languages ​​such as Python to obtain the difference image between the initial image and the final image.

[0094] (6) Use libraries such as OpenCV to perform binarization and denoising on the difference image to obtain the processed image.

[0095] (7) Use programming languages ​​such as Python to compare the processed image with the first layer information in the gcode file to detect the printing quality of the 3D printing equipment.

[0096] (8) Inform users of the printing quality of the 3D printing equipment via email, SMS or other means.

[0097] Compared with related technologies, the embodiments of this application have at least the following advantages: by moving the imaging device to a first position to capture the initial image of the printing platform, and after completing the first layer printing, controlling the imaging device to capture the final image of the printing platform again at the same first position, the printing quality of the 3D printing equipment can be determined based on the initial image and the final image. In other words, the first layer printing detection is automatically realized, and the printing quality of the 3D printing equipment can be automatically informed to the user, avoiding the user from manually checking the printing quality of the 3D printing equipment, and further improving the user experience.

[0098] Please refer to Figure 4 This is a flowchart of leveling the printing platform of a 3D printing device provided in this application embodiment. This embodiment is applied to the 3D printing device of the aforementioned embodiment. The 3D printing device includes a nozzle assembly, a printing platform, and an imaging device. The nozzle assembly is used to spray printing material onto the printing platform, including the following steps:

[0099] Step 301: Control the printhead assembly to print at least one preset line in the informal printing area.

[0100] In some embodiments, the 3D printing device is communicatively connected to 3D printing slicing software, or the 3D printing device is equipped with 3D printing slicing software. Before controlling the nozzle assembly to print a preset line, the 3D printing slicing software receives preset slicing parameters and printing material parameters of the 3D model to be printed input by the user. The 3D printing slicing software obtains preset extrusion parameter values ​​based on the preset slicing parameters and printing material parameters. The 3D printing device controls the nozzle assembly to print at least one preset line in the informal printing area based on the preset extrusion parameter values.

[0101] Specifically, preset slicing parameters include, but are not limited to: temperature, layer height, speed, support, and retraction. Temperature refers to the nozzle temperature; when the 3D printing equipment has a heated bed, the temperature also includes the temperature of the heated bed. Layer height is the height of each layer of the 3D model to be printed; the smaller the layer height, the more layers are required for the entire print. Speed ​​generally refers to the movement speed of the print head, and can also include the material filling speed, wall speed, etc. Support is the structure that supports the overhanging features on the 3D model to be printed. Retraction includes retraction distance and retraction speed; retraction determines the number and speed at which the filament is drawn back into the nozzle to prevent material from seeping out before extrusion.

[0102] Printing material parameters include, but are not limited to: the type of material and the required quantity.

[0103] In some embodiments, the relative positional relationship between the formal printing area and the informal printing area is not specifically defined. For example, the central area of ​​the printing platform can be used as the formal printing area, and the surrounding area around the central area can be used as the informal printing area. Alternatively, other areas of the printing platform can be used as the formal printing area according to actual needs. These will not be elaborated on here.

[0104] Step 302: Obtain the actual line width of the preset line.

[0105] In some embodiments, the 3D printing equipment includes an imaging device, which captures an image of a preset line and then obtains the actual line width of the preset line based on the image.

[0106] In some embodiments, the actual line width of the preset line can also be measured using tools such as digital calipers and microscopes.

[0107] Step 303: Compare the actual line width with the preset printing line width of the 3D model to be printed, and determine the adjustment value based on the comparison result. The adjustment value is used to adjust the relative distance between the printing platform and the nozzle assembly.

[0108] In some embodiments, the 3D printing slicing software receives preset slicing parameters and printing material parameters of the 3D model to be printed input by the user, and obtains the preset printing linewidth based on the preset slicing parameters and printing material parameters.

[0109] In some embodiments, the adjustment value is determined as follows: when the actual line width is greater than the preset print line width, the adjustment value is determined to increase the relative distance between the print platform and the printhead assembly; when the actual line width is less than the preset print line width, the adjustment value is determined to decrease the relative distance between the print platform and the printhead assembly.

[0110] Specifically, if the actual line width is greater than the preset print line width, it means that the distance between the printing platform and the printhead assembly is too close. The printing platform needs to be adjusted downwards by a certain distance to increase the relative distance between the printing platform and the printhead assembly. If the actual line width is less than the preset print line width, it means that the distance between the printing platform and the printhead assembly is too far. The printing platform needs to be adjusted upwards by a certain distance to reduce the relative distance between the printing platform and the printhead assembly.

[0111] In some embodiments, the 3D printing equipment includes a motor connected to the printing platform for controlling the lifting and lowering of the printing platform. When the actual line width is greater than the preset printing line width, the motor controls the printing platform to descend; when the actual line width is less than the preset printing line width, the motor controls the printing platform to rise.

[0112] In some embodiments, the 3D printing equipment is preset with a distance adjustment value. Taking a distance adjustment value of 5 mm as an example, when the printing platform needs to rise, the motor controls the printing platform to rise by 5 mm. Then, the 3D printing equipment controls the nozzle assembly to reprint a preset line in the informal printing area. The width of the new preset line is compared with the preset printing line width to determine whether it is necessary to control the printing platform to rise by 5 mm again. This process continues until the difference between the actual width of the preset line printed by the nozzle assembly in the informal printing area and the preset printing line width meets the printing requirements. Then, the control of the printing platform to rise by 5 mm is stopped, and the 3D model to be printed is printed according to the relative distance between the printing platform and the nozzle assembly at this time.

[0113] Step 304: After adjusting the relative distance between the printing platform and the printhead assembly according to the adjustment value, control the imaging device to move to the first position.

[0114] Step 305: Take an initial image of the current printing platform.

[0115] Step 306: Obtain the first layer information from the feature file. The feature file is used to command the 3D printing equipment to perform 3D printing work.

[0116] Step 307: Control the nozzle assembly to print the first layer of the 3D model based on the first layer information.

[0117] Step 308: After the first layer of printing is completed, control the imaging device to capture the final image of the printing platform at the first position.

[0118] Step 309: Determine the print quality of the 3D printing equipment based on the initial and final images.

[0119] Steps 305 to 309 in this embodiment are similar to steps 202 to 206 in the previous embodiment. To avoid repetition, they will not be described again here.

[0120] Compared with related technologies, the embodiments of this application have at least the following advantages: By controlling the nozzle assembly to print a preset line in the informal printing area, the actual line width of the printed line currently being printed by the 3D printing equipment can be known. Then, the actual line width is compared with the preset line width of the 3D model to be printed, and the relative distance between the printing platform and the nozzle assembly is adjusted according to the comparison result. This ensures that the distance between the nozzle assembly and the printing platform reaches a suitable value, thereby ensuring that the printed line formed after the nozzle assembly sprays printing material on the printing platform meets the preset line width requirements. This avoids the situation where "the relative distance between the printing platform and the nozzle assembly is too large or too small, resulting in the line width of the printed line formed after the nozzle assembly sprays printing material on the printing platform being too small or too large," thus improving the printing accuracy of the 3D printing equipment and improving the user experience.

[0121] Please refer to Figure 5 This is a flowchart illustrating the leveling process of the printing platform of the 3D printing equipment provided in this embodiment. This embodiment is a further improvement upon the aforementioned embodiments. The main improvement lies in that: in this embodiment, different preset extrusion parameter values ​​are set for different parts of the 3D model to be printed, and the nozzle assembly is controlled to print preset lines in the informal printing area according to each preset extrusion parameter value. Finally, the average line width of each preset line is compared with the preset printing line width to obtain a more precise adjustment value, further improving the printing accuracy of the 3D printing equipment, thereby further enhancing the user experience.

[0122] The specific process of this embodiment is as follows: Figure 5 As shown, it includes the following steps:

[0123] Step 401: Obtain N preset extrusion parameter values ​​for the nozzle assembly based on the preset slicing parameters and printing material parameters. Different parts of the 3D model to be printed correspond to at least one preset extrusion parameter value.

[0124] Specifically, N is an integer greater than 1. This embodiment does not impose specific limitations on the value of N, and it can be set according to actual needs.

[0125] In some embodiments, the parts of the 3D model to be printed include internal walls, external walls, and infill areas. Preset extrusion parameter values ​​include, but are not limited to, extrusion speed, extrusion temperature, and layer height.

[0126] Step 402: Control the nozzle assembly to print N preset lines in the informal printing area according to N preset extrusion parameter values, where one preset extrusion parameter value corresponds to one preset line.

[0127] In some embodiments, each preset extrusion parameter value corresponds to a part of the 3D model to be printed. For ease of understanding, the following example illustrates how the nozzle assembly controls the printing of preset lines in the informal printing area, using the following scenario: the 3D model to be printed includes part 1, part 2, and part 3; the preset extrusion parameter values ​​include a first preset extrusion parameter value, a second preset extrusion parameter value, and a third preset extrusion parameter value; and the preset lines include a first preset line, a second preset line, and a third preset line.

[0128] The first preset extrusion parameter value corresponds to part 1, the second preset extrusion parameter value corresponds to part 2, and the third preset extrusion parameter value corresponds to part 3. The 3D printing equipment controls the nozzle assembly to print the first preset line according to the first preset extrusion parameter value, the second preset line according to the second preset extrusion parameter value, and the third preset line according to the third preset extrusion parameter value.

[0129] It is understandable that the first preset line, the second preset line, and the third preset line can be connected end to end, that is, the first preset line, the second preset line, and the third preset line can be viewed as a single printed line; or the first preset line, the second preset line, and the third preset line can be unconnected, that is, the first preset line, the second preset line, and the third preset line can be independent printed lines.

[0130] Please refer to Figure 6 This is a schematic diagram of the structure of the printing line A provided in this embodiment. The first preset line, the second preset line, and the third preset line are connected end to end. The 3D printing equipment prints a continuous printing line A in the informal printing area according to the first preset extrusion parameter value, the second preset extrusion parameter value, and the third preset extrusion parameter value. The printing line A can be divided into three parts, each of which corresponds to a preset extrusion parameter value.

[0131] Step 403: Obtain the N actual line widths of the N preset lines.

[0132] The method for obtaining the actual line width in this embodiment is the same as that in the previous embodiment. To avoid repetition, it will not be described again here.

[0133] Step 404: Compare the size of N actual line widths with the preset printed line widths, and determine the adjustment value based on the comparison results.

[0134] In some embodiments, the adjustment value can be determined by comparing the sizes of N actual line widths and the preset printed line width in the following manner: calculating the average value of the N actual line widths; comparing the average value with the preset printed line width; and determining the adjustment value based on the comparison result.

[0135] Specifically, assuming N is 5, calculate the average P of the 5 actual line widths, and compare the average P with the preset print line width. If the average P is greater than the preset print line width, it means that the distance between the printing platform and the printhead assembly is too close, and the printing platform needs to be adjusted downwards by a certain distance to increase the relative distance between the printing platform and the printhead assembly. If the average P is less than the preset print line width, it means that the distance between the printing platform and the printhead assembly is too far, and the printing platform needs to be adjusted upwards by a certain distance to decrease the relative distance between the printing platform and the printhead assembly.

[0136] In some embodiments, the median of N actual line widths can be calculated, the median can be compared with the preset printed line width, and the adjustment value can be determined based on the comparison result.

[0137] It is understandable that after obtaining N actual line widths, this embodiment does not limit the method of calculating the N actual line widths, but only needs to ensure that the result of the calculation can reflect the overall line width of the preset line.

[0138] Step 405: After adjusting the relative distance between the printing platform and the printhead assembly according to the adjustment value, control the imaging device to move to the first position.

[0139] Step 406: Take an initial image of the current printing platform.

[0140] Step 407: Obtain the first layer information from the feature file. The feature file is used to command the 3D printing equipment to perform 3D printing work.

[0141] Step 408: Control the nozzle assembly to print the first layer of the 3D model based on the first layer information.

[0142] Step 409: After the first layer of printing is completed, control the imaging device to capture the final image of the printing platform at the first position.

[0143] Step 410: Determine the print quality of the 3D printing equipment based on the initial and final images.

[0144] Steps 406 to 410 in this embodiment are similar to steps 202 to 206 in the previous embodiment. To avoid repetition, they will not be described again here.

[0145] Compared with related technologies, the embodiments of this application have at least the following advantages: By setting different preset extrusion parameter values ​​for different parts of the 3D model to be printed, and controlling the nozzle assembly to print preset lines in the informal printing area according to each preset extrusion parameter value, and finally comparing the average line width of each preset line with the preset printing line width, and adjusting the relative distance between the printing platform and the nozzle assembly according to the comparison result, the distance between the nozzle assembly and the printing platform can be made to reach a suitable value, thereby ensuring that the printing lines formed after the nozzle assembly sprays printing material on the printing platform meet the preset printing line width requirements. This avoids the situation where "the relative distance between the printing platform and the nozzle assembly is too large or too small, resulting in the printing line width being too small or too large after the nozzle assembly sprays printing material on the printing platform," thus improving the printing accuracy of the 3D printing equipment and improving the user experience.

[0146] Please refer to Figure 7 This is a flowchart illustrating the leveling process of the printing platform of the 3D printing equipment provided in this embodiment. This embodiment is a further improvement based on the aforementioned embodiments. The main improvement is that, in this embodiment, each part of the 3D model corresponds to at least two preset extrusion parameter values. The optimal extrusion parameter value is selected from the preset extrusion parameter values ​​corresponding to each part, thereby further improving the printing accuracy of the 3D printing equipment and ensuring printing quality.

[0147] The specific process of this embodiment is as follows: Figure 7 As shown, it includes the following steps:

[0148] Step 501: Obtain N preset extrusion parameter values ​​for the nozzle assembly based on the preset slicing parameters and printing material parameters. The 3D model to be printed includes M different parts, and each part corresponds to at least two preset extrusion parameter values.

[0149] Specifically, M is an integer greater than 1.

[0150] In some embodiments, the number of preset extrusion parameter values ​​is the same for each part of the 3D model to be printed. For example, assuming that M is 6, the 3D model to be printed includes 6 different parts, and each part corresponds to 3 preset extrusion parameter values.

[0151] In some embodiments, the number of preset extrusion parameter values ​​corresponding to each part of the 3D model to be printed is not the same. For example, assuming that M is 4, that is, the 3D model to be printed includes 4 different parts (part A, part B, part C, and part D respectively), part A corresponds to 2 preset extrusion parameter values, part B corresponds to 3 preset extrusion parameter values, part C corresponds to 4 preset extrusion parameter values, and part D corresponds to 2 preset extrusion parameter values.

[0152] Step 502: Control the nozzle assembly to print N preset lines in the informal printing area according to N preset extrusion parameter values, with one preset extrusion parameter value corresponding to one preset line.

[0153] Step 503: Select the optimal preset line for each part from the preset lines corresponding to the M parts, and use the preset extrusion parameter value corresponding to the optimal preset line for each part as the final extrusion parameter value for printing the 3D model to be printed.

[0154] In some embodiments, the optimal preset line for each of the M preset lines can be selected from the preset lines corresponding to the M parts in the following manner: calculate the standard deviation of the line width of the preset line corresponding to each part, and take the preset line with the smallest standard deviation of the line width of each part as the optimal preset line for that part.

[0155] Specifically, the line width standard deviation is calculated as follows: obtaining the line width values ​​of the preset line at multiple different positions; calculating the average line width of the preset line based on the multiple line width values; and calculating the line width standard deviation based on the average line width and the multiple line width values.

[0156] To make it easier to understand, the following examples illustrate how to select the optimal preset line for each part:

[0157] Assuming M is 3, meaning the 3D model to be printed includes 3 different parts (part A, part B, and part C), taking part A as an example, and assuming part A corresponds to 3 preset lines (preset line 1, preset line 2, and preset line 3), measure the line width at different positions on preset line 1. For example, take three measurement points at the front, middle, and rear of preset line 1, and measure the line width at these three points, let's call them L1, L2, and L3. Calculate the average value of L1, L2, and L3. Then, calculate the standard deviation of the line width of the preset line one according to the following formula. Where σ is the standard deviation of the line width of the preset line one, and L i Let i be the line width value at the i-th point. The average line width of the preset line 1 is n, where n is the number of measurement points.

[0158] It is understandable that the method for calculating the standard deviation of line width for preset line two and preset line three is the same as that for preset line one. To avoid repetition, it will not be repeated here.

[0159] After calculating the standard deviation of the line width corresponding to preset line one, preset line two, and preset line three, the size of the three standard deviations of line width is compared, and the preset line with the smallest standard deviation of line width is taken as the optimal preset line.

[0160] It is understandable that the methods for obtaining the optimal preset line for parts B and C are the same as those for obtaining the optimal preset line for part A. To avoid repetition, they will not be described again here.

[0161] Please refer to Figure 8 This is an image showing the effect of a 3D printer printing on a printing platform. From... Figure 8 As can be seen, the printed lines with preset extrusion parameters ranging from 0.004 to 0.096 are all straight. The printed lines with preset extrusion parameters ranging from 0.004 to 0.036 exhibit discontinuity at the leading edge and material accumulation at the trailing edge. The printed lines with preset extrusion parameters ranging from 0.04 to 0.056 are relatively uniform. The printed lines with preset extrusion parameters ranging from 0.06 to 0.096 exhibit discontinuity at the trailing edge and material accumulation at the leading edge.

[0162] Specifically, a print line with preset extrusion parameters of 0.004 to 0.036 has a smaller extrusion parameter at the front end, resulting in a break in the material at the front. Conversely, a print line with a larger extrusion parameter at the rear end results in material accumulation. By increasing the print parameters at the front end and decreasing the print parameters at the rear end, a print line with preset extrusion parameters of 0.04 to 0.056 can be obtained. The final extrusion parameters are 0.04 to 0.056.

[0163] Please refer to Figure 9 This is another rendering of a 3D printer printing on a printing platform. From Figure 9 As can be seen, the printed lines with preset extrusion parameters from 0.02 to 0.08 are all broken line groups. By detecting the spacing between adjacent printed lines, the printing condition of the inflection points of the printed lines, and the printing condition of the start and end positions of the printed lines, the printing quality of the 3D printing equipment can be determined.

[0164] Specifically, before the 3D printing equipment controls the nozzle assembly to print folds, it first controls the nozzle assembly to accelerate to the preset printing speed at a rated acceleration, and then controls the nozzle assembly to print folds on the printing platform at the preset printing speed. It can be understood that the number of printed folds is the same as the number of preset extrusion parameters; that is, the number of printed folds controlled by the 3D printing equipment depends on how many preset extrusion parameters need to be detected.

[0165] In some embodiments, the 3D printing equipment controls the nozzle assembly to accelerate at a rate of 5000 mm / s, stops accelerating after reaching 12000 mm / s, and controls the nozzle assembly to print on the printing platform at a speed of 12000 mm / s. Figure 9 The broken line shown has an included angle of 45 degrees.

[0166] After all the fold lines are printed, images are taken using the imaging device of the 3D printing equipment, such as... Figure 9 The resulting image is then examined using a simulated human eye method to observe whether there are gaps or protrusions at the bends of each zigzag line, i.e., to observe the uniformity of each zigzag line at the bends. Specifically, zigzag lines with preset extrusion parameters of 0.02 to 0.036 have protrusions at the bends; zigzag lines with preset extrusion parameters of 0.04 to 0.052 have neither protrusions nor gaps at the bends; and zigzag lines with preset extrusion parameters of 0.056 to 0.08 have gaps at the bends. Therefore, the final extrusion parameters are 0.04 to 0.052.

[0167] Please see further. Figure 9 , Figure 9 Each group of fold lines shown is formed by the same number of printed lines. The preset extrusion parameters for each group of fold lines are different, but the preset extrusion parameters for the printed lines within each group are the same. It is understood that each group of fold lines can also be formed by a different number of printed lines; this embodiment does not specifically limit this. In some embodiments, the effect image captured by the imaging device can be input into a preset uniformity recognition model, and the output of the uniformity recognition model can be used to detect whether there are gaps or protrusions at the bends of each fold line.

[0168] Specifically, historical image data of the printed polylines is collected, and then a primitive model is trained using this historical image data. This trained primitive model is then used as the uniformity recognition model. After all the polylines are printed, images are taken using the imaging device of the 3D printing equipment. Figure 9The effect shown is then input into the uniformity recognition model, which can automatically detect whether there are gaps or protrusions at the bends of each line.

[0169] Step 504: Obtain the N actual line widths of the N preset lines.

[0170] Step 505: Compare the size of N actual line widths with the preset printed line widths, and determine the adjustment value based on the comparison results.

[0171] Step 506: After adjusting the relative distance between the printing platform and the printhead assembly according to the adjustment value, control the imaging device to move to the first position.

[0172] Step 507: Take an initial image of the current printing platform.

[0173] Step 508: Obtain the first layer information from the feature file. The feature file is used to command the 3D printing equipment to perform 3D printing work.

[0174] Step 509: Control the nozzle assembly to print the first layer of the 3D model based on the first layer information.

[0175] Step 510: After the first layer of printing is completed, control the imaging device to capture the final image of the printing platform from the first position.

[0176] Step 511: Determine the print quality of the 3D printing equipment based on the initial and final images.

[0177] Steps 507 to 511 in this embodiment are similar to steps 202 to 206 in the previous embodiment. To avoid repetition, they will not be described again here.

[0178] Compared with related technologies, the embodiments of this application have at least the following advantages: By setting different preset extrusion parameter values ​​for different parts of the 3D model to be printed, and controlling the nozzle assembly to print preset lines in the informal printing area according to each preset extrusion parameter value, and finally comparing the average line width of each preset line with the preset printing line width, and adjusting the relative distance between the printing platform and the nozzle assembly according to the comparison result, the distance between the nozzle assembly and the printing platform can be made to reach a suitable value, thereby ensuring that the printing lines formed after the nozzle assembly sprays printing material on the printing platform meet the preset printing line width requirements. This avoids the situation where "the relative distance between the printing platform and the nozzle assembly is too large or too small, resulting in the printing line width being too small or too large after the nozzle assembly sprays printing material on the printing platform," thus improving the printing accuracy of the 3D printing equipment and improving the user experience. Furthermore, by setting at least two preset extrusion parameter values ​​for each part of the 3D model to be printed, the optimal extrusion parameter value can be selected from the preset extrusion parameter values ​​corresponding to each part. This allows the 3D printing equipment to control the nozzle assembly to print the 3D model according to the optimal extrusion parameter value. This enables the 3D printing equipment to be applicable to different application scenarios and avoids the situation where "the 3D printing equipment prints 3D models for various application scenarios using the initially set extrusion parameter values, resulting in poor printing quality or even printing failure." This ensures the printing quality of the 3D printing equipment in different scenarios and further improves the user experience.

[0179] Please refer to Figure 10 This is a schematic diagram of the scanning printing platform of the 3D printing equipment provided in this embodiment. This embodiment is a further improvement on the foregoing embodiments, mainly in that: in this embodiment, before controlling the nozzle assembly to print at least one preset line in the informal printing area of ​​the printing platform, a laser scan is used to level the printing platform. In this way, the 3D printing equipment can complete the automatic leveling of the printing platform with a single scan, which is highly efficient and easy to operate; in addition, it ensures the horizontality of the printing platform, thereby further improving the printing accuracy of the 3D printing equipment.

[0180] Specifically, 3D printing equipment also includes a laser source for emitting line lasers, such as... Figure 10 As shown, the 3D printing equipment controls a laser light source to scan the printing platform line by line in a strip manner, collects point cloud data of each line, and stitches the point clouds together to generate a 3D model of the entire printing platform.

[0181] During the scanning process, the printing platform may undergo slight deformation, leading to errors in the collected point cloud data. This embodiment addresses this by performing planar fitting on the stitched point cloud, determining the normal vector of the fitted plane, and thus determining the horizontal offset of the printing platform, ultimately deciding on the correction amount for the printing platform.

[0182] To facilitate understanding, the following will be combined with... Figure 11 This embodiment provides specific examples of how to determine the calibration amount of the printing platform and how to level the printing platform after determining the calibration amount:

[0183] Please refer to Figure 11 This is a schematic diagram of the normal vectors of the standard horizontal plane and the fitted plane provided in this embodiment.

[0184] (1) Assume the normal vector of the fitting plane is The normal vector of the standard horizontal plane is normal vector Projecting onto a standard horizontal plane yields a vector. Calculate vectors and The included angle θ between them.

[0185] (2) Calculate the vector using the following formula. and The included angle θ between them: in,

[0186] (3) The horizontal offset of the printing platform is calculated using the following formula: Horizontal offset of printing platform = sinθ × density of point cloud data, where θ is a vector. and The angle between them, and the density of the point cloud data is the number of point cloud data per square meter.

[0187] (4) After determining the horizontal offset of the printing platform, the correction amount can be obtained. Once the correction amount is determined, it can be applied to the point cloud data to correct errors during the scanning process. Specifically, the correction amount can be added to the coordinate values ​​of each point in the point cloud data to ensure that these points are in the correct position relative to the printing platform. This process can be performed during post-processing after point cloud data acquisition or applied immediately during scanning.

[0188] In some embodiments, after leveling the printing platform, it can be verified whether the printing platform has been successfully calibrated. For example, the automatically leveled printing platform can be laser-scanned multiple times. If the point cloud data obtained from each scan is very similar, it indicates that the printing platform has been successfully calibrated. If there are significant differences in the point cloud data obtained from multiple scans, the calibration values ​​need to be obtained again to further level the printing platform and ensure the printing accuracy of the 3D printing equipment.

[0189] Please refer to Figure 12This diagram illustrates an application scenario for deformation compensation of the printing platform provided in this embodiment. This embodiment is a further improvement upon the aforementioned embodiments, primarily in that deformation compensation is performed on the printing platform before the nozzle assembly prints at least one preset line in the informal printing area of ​​the printing platform. This method ensures the flatness of the printing platform, thereby improving the printing quality of the 3D printing equipment.

[0190] To facilitate understanding, the following is a detailed explanation of how this embodiment performs deformation printing compensation on the printing platform:

[0191] (1) Assume the printing platform is a rectangular printing platform with dimensions of 100 mm × 80 mm and a thickness of 2 mm. Use the line laser generator of the 3D printing equipment to scan the printing platform and obtain point cloud data of the printing platform surface.

[0192] (2) Use point cloud processing software (such as CloudCompare or MeshLab) to process the point cloud data of the printing platform surface and extract the surface information of the printing platform. Specifically, use point cloud processing software to perform filtering, smoothing and surface extraction operations on the point cloud data of the printing platform surface to obtain a smooth point cloud model of the printing platform surface.

[0193] (3) Determine the sampling interval to calculate the print compensation value, such as Figure 12 As shown, a sampling interval of 5 mm is selected, that is, the point cloud data of the printing platform surface is sampled once every 5 mm.

[0194] (4) Using point cloud processing software or programming language (such as Python or MATLAB), sampling is performed on the point cloud model of the printing platform surface obtained above at a sampling interval of 5 mm, resulting in a total of 20 sampling point sets.

[0195] (5) Use programming languages ​​such as Python or MATLAB to perform surface fitting on the 20 sampling point sets to obtain 20 fitted sub-surfaces, and then use the surface fitting algorithm to calculate the actual curvature of each sub-surface.

[0196] (6) Compare the actual curvature of the subsurface with the theoretical curvature of the original printing platform, and calculate the compensation value for each subsurface using the following formula:

[0197] Compensation value = Compensation coefficient × Deviation; Deviation = Theoretical curvature - Actual curvature.

[0198] Specifically, the compensation coefficient is a constant that is related to factors such as the printing and processing procedures, the geometry and size of the printing platform, the printer's operating mode, and the required printing precision. Generally, the compensation coefficient ranges from 0.1 to 0.5.

[0199] In some embodiments, the compensation coefficient can be determined as follows: 1. Select a printing platform, and use the same 3D printing equipment and printing parameters to print multiple times on the platform, recording the deviation of each print. 2. Calculate the corresponding compensation value for each print deviation, which can be done according to the formula above. 3. Fit the calculated compensation value to the actual deviation data, using methods such as curve fitting or regression analysis. 4. Select a suitable compensation coefficient based on the fitting result, so that the calculated compensation value best fits the actual deviation data. It should be noted that the selection of the compensation coefficient is a relatively empirical process and needs to be adjusted according to specific circumstances. Furthermore, after determining the compensation coefficient, multiple experiments are needed to verify its effectiveness and make adjustments.

[0200] (7) The compensation value calculated above is processed by the point cloud processing software to update the point cloud model on the surface of the printing platform, thereby realizing the deformation printing compensation of the printing platform.

[0201] Please refer to Figure 13 This is a schematic diagram illustrating a scenario for line height detection using a 3D printing device provided in this embodiment. This embodiment specifically describes the functions of the 3D printing device and explains how to measure the line height of an object under test using the 3D printing device provided in this embodiment. This method enables automatic detection of the line height of the object under test, improving the user experience.

[0202] like Figure 13 As shown, the 3D printing equipment includes a printing platform 1, a line laser generator 2, and a camera 3. The object to be measured is placed on the printing platform 1. The basic formula for line height detection is: Line height of the object = Projected offset distance / tan(angle between the laser and the horizontal plane); where the projected offset distance refers to the offset distance on the image captured by the camera 3 after the line laser irradiates the surface of the object, relative to its unirradiated position. Figure 14 The image shown is taken by camera 3. Specifically, Figure 14 The white line shown is the laser emitted by laser source 2, the object being measured is the printed line, and the extension direction of the laser is perpendicular to the extension direction of the printed line; tan (angle between the laser and the horizontal plane) refers to the tangent of the angle between the laser and the horizontal plane.

[0203] Please refer to Figure 15 , is an image taken by camera 3 when the object being measured is a triangular object. Figure 15 The white line shown is the laser light emitted from laser source 2, from... Figure 15 As can be seen, the triangular object has a certain height, causing the laser beam illuminating the object to be measured to deflect.

[0204] To facilitate understanding, the following is a detailed explanation of how the line height of the object under test is detected in this embodiment:

[0205] Assuming the distance between the object to be measured and the line laser generator 2 is L, the angle between the line laser emitted by the line laser generator 2 and the horizontal plane is α, and the projection offset distance of the line laser on the surface of the object to be measured is d, then the formula for calculating the height H of the line laser on the object to be measured is:

[0206] H = d / tan(α);

[0207] The projection offset distance d of the line laser on the surface of the object to be measured is calculated as follows: the projection distance of the line laser on the horizontal plane D1=L×cos(α); the projection offset distance of the line laser on the physical surface in similar triangles D2=D1×d / L; we know that d=D2×L / D1, and substituting into D1=L×cos(α), we get d=D2 / cos(α).

[0208] For example, when the distance L between the object to be measured and the line laser generator 2 is 50 cm and the angle α between the line laser and the horizontal plane is 45 degrees, the calculated projection offset distance d is 2 mm, and thus the line height H of the object to be measured is 2 mm.

[0209] Please refer to Figure 16 This is a schematic diagram of the hardware structure of the electronic device 1000 provided in an embodiment of this application. Figure 16 As shown, the electronic device 1000 may include a processor 1001 and a memory 1002. The memory 1002 is used to store one or more computer programs 1003. The one or more computer programs 1003 are configured to be executed by the processor 1001. The one or more computer programs 1003 include instructions that can be used to implement the methods described above in the electronic device 1000.

[0210] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 1000. In other embodiments, the electronic device 1000 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements.

[0211] Processor 1001 may include one or more processing units, such as application processors (APs), modems, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.

[0212] The processor 1001 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 1001 is a cache memory. This memory can store instructions or data that the processor 1001 has just used or that are used repeatedly. If the processor 1001 needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces the waiting time of the processor 1001, and thus improves the efficiency of the system.

[0213] In some embodiments, the processor 1001 may include one or more interfaces. Interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM interface, and / or a USB interface, etc.

[0214] In some embodiments, memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0215] This embodiment also provides a storage medium storing computer instructions. When the instructions are executed on an electronic device, the electronic device performs the aforementioned method steps to implement the methods described in the above embodiments.

[0216] In this embodiment, the electronic device and computer storage medium are used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0217] In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0218] In the several embodiments provided in this application, the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are illustrative. For instance, the division of modules or units is a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0219] The unit described as a separate component may or may not be physically separate. The component shown as a unit can be one physical unit or multiple physical units, that is, it can be located in one place or distributed in multiple different places. Some or all of the units can be selected to achieve the purpose of the solution in this embodiment according to actual needs.

[0220] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0221] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0222] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method for detecting processing steps in a 3D printing device, characterized in that, The 3D printing equipment includes a nozzle assembly, a printing platform, and a laser light source; the method includes: Obtain working data of the current processing step of the 3D printing equipment, wherein the processing step includes at least the extrusion flow detection of the nozzle assembly, the first layer detection, and the leveling detection of the printing platform; The working data is input into a preset model, wherein the preset model is trained based on the historical working data of the 3D printing equipment; Detect whether the current processing step is abnormal based on the output of the preset model; The leveling test of the printing platform includes: Control the printhead assembly to print at least one preset line in the informal printing area; Obtain the actual line width of the preset line; Compare the actual line width with the preset printing line width of the 3D model to be printed, and determine the adjustment value based on the comparison result; Adjust the relative distance between the printing platform and the printhead assembly according to the adjustment value.

2. The method for detecting processing steps in a 3D printing device as described in claim 1, characterized in that, The preset model is trained in the following manner: The historical working data is input into the initial model to train the initial model; Check whether the performance parameters of the initial model after training meet the preset requirements; When the performance parameters of the initial model after training meet the preset requirements, the initial model after training is used as the preset model. If the performance parameters of the initial model after training do not meet the preset requirements, new historical working data is obtained, and the initial model after training is retrained based on the new historical working data.

3. The method for detecting processing steps in a 3D printing device as described in claim 2, characterized in that, Before inputting the historical working data into the initial model, the following is also included: The historical working data is processed to obtain processed data that meets the model training requirements; The step of inputting the historical working data into the initial model to train the initial model includes: The processed data is input into the initial model to train the initial model.

4. The method for detecting processing steps in a 3D printing device as described in claim 3, characterized in that, The historical work data includes image data, and the data processing of the historical work data includes: The image data is cropped, scaled, and enhanced.

5. The method for detecting processing steps in a 3D printing device as described in claim 3, characterized in that, The historical working data includes point cloud data, and the data processing of the historical working data includes: The point cloud data is filtered and sampled.

6. The method for detecting processing steps in a 3D printing device as described in claim 1, characterized in that, The preset model is one of the following: convolutional neural network model, recurrent neural network model, and autoencoder.

7. The method for detecting processing steps in a 3D printing device as described in claim 1, characterized in that, After detecting an anomaly in the current processing step based on the output of the preset model, the process further includes: Send an alarm signal and / or control the 3D printing equipment to stop working.

8. The method for detecting processing steps of a 3D printing device as described in any one of claims 1 to 7, characterized in that, The historical work data includes first historical work data when the 3D printing equipment is in normal working condition, and second historical work data when the 3D printing equipment is in abnormal working condition.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory being used to store instructions, and the processor being used to invoke the instructions in the memory, causing the electronic device to execute the processing step detection method of the 3D printing device according to any one of claims 1 to 8.

10. A storage medium, characterized in that, The method includes computer instructions that, when executed on an electronic device, cause the electronic device to perform a processing step detection method for a 3D printing device as claimed in any one of claims 1 to 8.

Images