Detection method, device and equipment based on 3D printing equipment and storage medium

Abstract

The invention provides a detection method and device based on 3D printing equipment, equipment and a storage medium, and the detection method comprises the steps that in the printing process of the 3D printing equipment, multiple pieces of printing data of a spray head within a preset duration are obtained; a label association value of each piece of printing data and a preset label set is calculated, the preset label set comprises multiple labels, the label association value is used for representing the association degree between the printing data and each label, and the multiple labels at least comprise empty printing labels and non-empty printing labels; determining the label corresponding to each piece of printing data according to the label association value; and obtaining a detection result of the 3D printing equipment according to the label corresponding to each piece of printing data. According to the method, whether the nozzle has an abnormal printing condition or not can be detected in time, so that the precision and quality of 3D printing are improved.

Description

Technical Field

[0001] The present application relates to the field of 3D printing technology, and in particular to a detection method, apparatus, device and storage medium based on 3D printing equipment. Background Art

[0002] 3D printing is a technology that uses digital model files as the basis and uses bondable materials such as powdered metal or plastic to construct objects by printing layer by layer. Its main technologies include stereolithography, selective laser sintering and fused deposition modeling.

[0003] In the related art, 3D printing equipment uses detection software or additionally installs detection tools on the 3D printing equipment, and uses the data detected by the detection tools to detect whether there are any abnormalities in the printing process. Most 3D printing detection software uses third-party APPs for online detection, and the data is stored in the cloud, which may cause risks such as user video data leakage and cannot effectively protect user privacy and security; installing additional detection tools makes the detection cost higher. Summary of the invention

[0004] In view of this, the present application provides a detection method, apparatus, device and storage medium based on a 3D printing device, which can accurately detect whether abnormal printing occurs during the printing process of the 3D printing device and can reduce the detection cost.

[0005] A first aspect of the present application provides a detection method based on a 3D printing device, wherein the 3D printing device includes a nozzle and a hot bed, wherein the nozzle is used to spray printing material onto the hot bed; the detection method based on the 3D printing device includes: during the printing process of the 3D printing device, obtaining multiple printing data of the nozzle within a preset time length; calculating a label association value between each of the printing data and a preset label set, wherein the preset label set includes multiple labels, and the multiple labels include at least an empty label and a non-empty label, and the label association value is used to characterize the association between the printing data and each of the labels; according to the label association value, determining the label corresponding to each of the printing data; and according to the label corresponding to each of the printing data, obtaining the detection result of the 3D printing device.

[0006] Compared with the related art, the embodiments of the present application have at least the following advantages:

[0007] By calculating the label association between each print data and multiple labels, the relationship between the print head and multiple labels when printing each print data is determined, so as to obtain the label corresponding to each print data and determine the printing status of the print head when printing each print data. Then, the detection result of the 3D printing device is determined based on the label, and the printing status of the print head during the 3D printing process is obtained based on the detection result, so as to determine whether abnormal printing occurs during the 3D printing process.

[0008] In some possible implementations, the calculating of the label association value between each of the print data and a preset label set includes: performing convolution on multiple print data to obtain convolution feature data; and performing forward feature processing and backward feature processing on the convolution feature data based on the preset label set to obtain the label association value.

[0009] In some possible implementations, determining the label corresponding to each of the print data based on the label association value includes: obtaining the label association value with the greatest correlation between the current print data among the multiple print data and the multiple labels; and determining the label corresponding to each of the print data based on the label association value with the greatest correlation.

[0010] In some possible implementations, obtaining the detection result of the 3D printing device according to the label corresponding to each of the printing data includes: classifying the multiple printing data according to the label corresponding to each of the printing data to obtain the classified multiple printing data; and determining the detection result of the 3D printing device based on the classified multiple printing data.

[0011] In some possible implementations, the method uses a deep learning model to detect the printing status of the 3D printing device; the training process of the deep learning model includes: determining a first time duration, a second time duration, a first label, and a second label, wherein the first label at least includes the empty printing label, and the second label at least includes the non-empty printing label; controlling the nozzle to perform abnormal printing within the first time duration, and obtaining the first printing data of the nozzle within the first time duration, wherein the abnormal printing indicates that the nozzle performs empty printing; marking the first printing data as the first label; controlling the nozzle to perform normal printing within the second time duration, and obtaining the second printing data of the nozzle within the second time duration, wherein the normal printing indicates that the nozzle performs non-empty printing; marking the second printing data as the second label; and training the deep learning model based on the first printing data and the second printing data.

[0012] In some possible implementations, the training of the deep learning model based on the first print data and the second print data includes: using part of the data in the first print data and part of the data in the second print data to train the deep learning model; obtaining historical gradient information; inputting another part of the data in the first print data and another part of the data in the second print data into the trained deep learning model; determining a loss value of the trained deep learning model based on the historical gradient information; and updating all parameters of the deep learning model based on the loss value until the deep learning model converges to obtain the trained deep learning model.

[0013] The second aspect of the present application discloses a detection method based on a 3D printing device, wherein the 3D printing device includes a nozzle and a feed pipe, wherein the feed pipe is used to feed printing material to the nozzle; the detection method based on the 3D printing device includes: during the printing process of the 3D printing device, obtaining multiple feed length data of the feed pipe within a preset time length; obtaining a label association value between each feed length data and the preset label set, wherein the preset label set includes multiple labels, and the label association value is used to characterize the association between the feed length data and each label, and the multiple labels at least include empty labels and non-empty labels; according to the label association value, determining the label corresponding to each feed length data; according to the label corresponding to each printing data, obtaining the detection result of the 3D printing device.

[0014] The third aspect of the present application discloses a detection device based on a 3D printing device, including: an acquisition module: used to acquire multiple printing data of the nozzle within a preset time period during the printing process of the 3D printing device; a calculation module: used to calculate the label association value between each of the printing data and a preset label set, wherein the preset label set includes multiple labels, and the multiple labels include at least empty labels and non-empty labels, and the label association value is used to characterize the association between the printing data and each of the labels; a determination module: used to determine the label corresponding to each of the printing data according to the label association value; a detection module: used to obtain the detection result of the 3D printing device according to the label corresponding to each of the printing data.

[0015] In a fourth aspect, the present application discloses an electronic device, which includes a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the above-mentioned detection method based on the 3D printing device.

[0016] A fifth aspect of the present application discloses a computer storage medium, including computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned detection method based on a 3D printing device.

[0017] It can be understood that the detection device based on the 3D printing device of the third aspect provided above, the electronic device of the fourth aspect, and the computer storage medium of the fifth aspect all correspond to the method of the first aspect mentioned above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A flowchart of the steps of a detection method based on a 3D printing device provided in one embodiment of the present application.

[0020] Figure 2 A flowchart of the steps for training a deep learning model provided in one embodiment of the present application.

[0021] Figure 3 A schematic diagram of the structure of a detection device based on a 3D printing device provided in one embodiment of the present application.

[0022] Figure 4 A schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application.

[0023] Main component symbols

[0024] Detection device based on 3D printing equipment 200

[0025] Acquisition module 210

[0026] Computing module 220

[0027] Determination module 230

[0028] Detection module 240

[0029] Electronic equipment 1000

[0030] Processor 1001

[0031] Memory 1002

[0032] Computer Programs 1003 DETAILED DESCRIPTION

[0033] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the implementation methods of the present application and the features in the implementation methods can be combined with each other without conflict.

[0034] In the following description, many specific details are set forth to facilitate a full understanding of the present application. The described implementations are only part of the implementations of the present application, rather than all the implementations.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0036] It should be further noted that, in this article, the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0037] In this application, "at least one" means one or more, and "more" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0038] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0039] To facilitate understanding, some illustrations of concepts related to the embodiments of the present application are given by way of example for reference.

[0040] 3D printing equipment, also known as three-dimensional printers, is a rapid prototyping process equipment, usually using digital technology to print materials. 3D printing equipment is often used to manufacture models or parts in the fields of mold manufacturing, industrial design, etc.

[0041] Please refer to Figure 1 , is a step flow chart of a detection method based on a 3D printing device provided in one embodiment of the present application. This embodiment is applied to a 3D printing device. The 3D printing device includes a nozzle, a first acquisition component and a hot bed. The nozzle is used to spray printing material onto the hot bed, and the first acquisition component is used to collect printing data of the nozzle under the extrusion force of the printing material. The detection method based on the 3D printing device uses a pre-trained deep learning model to detect the printing situation of the 3D printing device, so as to timely determine whether the 3D printing device has an abnormal printing situation. In this embodiment, the first acquisition component is a pressure sensor. This embodiment only uses the pressure sensor that is often set in the 3D printing device, and uses the pressure sensor to obtain the printing data of the nozzle. The cost of data acquisition is reduced. The detection method includes the following steps:

[0042] Step 101: During the printing process of the 3D printing device, a plurality of printing data of the nozzle within a preset time period are obtained.

[0043] In some embodiments, the preset duration can be set to 1 minute, 2 minutes, etc.

[0044] It should be noted that during the process of 3D printing equipment printing 3D models, empty printing may occur. Empty printing is a common problem in printing. There are many reasons, such as running out of printing materials, unclean or poor quality printing materials, inappropriate printing temperature, printing speed, etc., which lead to nozzle blockage during printing and cause empty printing. The occurrence of empty printing not only wastes user time and affects user experience, but long-term empty printing may even cause serious damage to the 3D printing equipment.

[0045] It should also be noted that during the process of 3D printing equipment printing 3D models, nozzle blob may occur. The occurrence of nozzle blob is due to the continuous accumulation of molten plastic during the printing process due to nozzle blockage or unstable material temperature. A large amount of molten plastic gathers around the nozzle, which may cause irregular protrusions or lumps on the surface of the printed object, or stick to the extruder head, which is called "blob", causing defects in the quality of the printed object, affecting the quality of the printed object, and may even cause serious damage to the printer.

[0046] Therefore, by acquiring multiple printing data of the nozzle during the process of 3D printing of the 3D model by the 3D printing device, and performing abnormality detection based on the multiple printing data in the subsequent steps, it is possible to immediately stop 3D printing when the nozzle is abnormally printed during the process of the 3D printing device printing the object to be printed, thereby further improving the reliability of the 3D printing device.

[0047] Step 102: Calculate the label association value between each print data and the preset label set.

[0048] In some embodiments, the preset label set includes multiple labels. In the present embodiment, the multiple labels include at least non-empty labels and empty labels. In other embodiments, the multiple labels may also include nozzle wrapped labels and nozzle unwrapped labels. The label association value is used to characterize the association between the print data and each label. In other embodiments, if other abnormal printing situations need to be detected, the preset label set may also include other labels in addition to non-empty labels, empty labels, nozzle wrapped labels and nozzle unwrapped labels.

[0049] Specifically, the association degree between each print data and multiple labels is calculated respectively. The association data between each print data and multiple labels is used as the label association value. For example, the association degree between each print data and a non-empty label is calculated, the association degree between each print data and an empty label is calculated, the association degree between each print data and a non-printer package is calculated, and the association degree between each print data and a printhead package is calculated.

[0050] In some embodiments, a pre-trained deep learning model is used to calculate the label association value of each print data and a preset label set. The deep learning model includes a convolution layer, a bidirectional long short-term memory network, and a fully connected layer. Among them, multiple print data are convolved based on the convolution layer to obtain convolution feature data. The convolution feature data is forward feature processed and backward feature processed based on the preset label set to obtain a label association value. The training steps of the deep learning model are described in detail below and will not be repeated here.

[0051] After forward feature processing and backward feature processing are performed on the convolution feature data based on the preset label set, the correlation between each data in the convolution feature data and the non-empty label and the empty label can be obtained.

[0052] Specifically, the convolutional layer uses a convolutional neural network (CNN). CNN can capture key features in the data. That is, CNN extracts local features in the input data through convolution operations. Convolution operations are linear operations that perform point-by-point multiplication and accumulation on the input data to capture key features.

[0053] Furthermore, the convolution feature data is processed forward and backward based on the preset label set and the bidirectional long short-term memory network to obtain the target feature data. The bidirectional long short-term memory network (Bi-directional LongShort-Term Memory, BiLSTM) is an improved recurrent neural network (RNN) specially designed for processing sequence data. BiLSTM can capture the bidirectional dependency in the sequence data by combining the outputs of the forward and reverse long short-term memory networks. BiLSTM runs two independent long short-term memory networks at each time step, one from the beginning to the end of the sequence data (forward long short-term memory network), and the other from the end to the beginning of the sequence data (backward long short-term memory network). The outputs of these two long short-term memory networks are combined, so that BiLSTM considers both past and future information at the same time, so that the model can better capture the contextual information in the sequence data. Thus, accurate time series feature association data is obtained to ensure the accuracy of subsequent classification of time series feature data.

[0054] Step 103: Determine the label corresponding to each print data according to the label association value.

[0055] In some embodiments, the label association value with the greatest association between the current print data and multiple labels in the multiple print data is obtained. According to the label association value with the greatest association, the label corresponding to each print data is determined. For example, if multiple labels include empty labels and non-empty labels, it is determined that the association between the current print data and the empty labels is 0.8, and the association between the current print data and the non-empty labels is 0.2. Since the maximum association between the current print data and multiple labels is 0.8, the label corresponding to the current print data is an empty label. In other embodiments, if multiple labels include empty labels, non-empty labels, nozzle wrapped labels, and nozzle unwrapped labels, it is determined that the association between the current print data and the empty labels is 0.6, the association between the current print data and the non-empty labels is 0.2, the association between the current print data and the nozzle wrapped labels is 0.1, and the association between the current print data and the nozzle unwrapped labels is 0.1. The maximum association between the current print data and multiple labels is 0.6, and the label corresponding to the current print data is an empty label.

[0056] Step 104: Obtain the detection result of the 3D printing device according to the label corresponding to each printing data.

[0057] In some embodiments, based on a preset label set, multiple print data are classified by labels to obtain multiple classified print data. Based on the classified data, the detection result of the 3D printing device is determined. In this embodiment, based on the preset label set, a fully connected layer is used to classify the labels of multiple print data to obtain a classification result. Among them, the fully connected layer uses a Dense layer. The Dense layer connects all neurons in the previous layer and all neurons in the current layer, and can help the deep learning model better understand the input data, thereby improving the accuracy of the deep learning model.

[0058] In some embodiments, the detection result of the 3D printing device includes abnormal printing and normal printing. Based on the classification data, a data set labeled as an empty printing label is obtained from multiple printing data. If the difference between the data in the data set labeled as an empty printing label is relatively small, the nozzle has an empty printing phenomenon during the printing process, and the detection result of the 3D printing device is abnormal printing. Similarly, if the multiple labels also include a nozzle wrapping label and a nozzle unwrapped label, based on the classification data, a data set labeled as a nozzle wrapping label is obtained from multiple printing data. If the difference between the data in the data set labeled as a nozzle wrapping label is relatively small, the nozzle has a nozzle wrapping phenomenon during the printing process, and the detection result of the 3D printing device is also abnormal printing. On the contrary, it is proved that there is no empty printing phenomenon or nozzle wrapping phenomenon in the preset time length, and the detection result of the 3D printing device is normal printing.

[0059] When the detection result of the 3D printing device is abnormal printing, the 3D printing device will stop printing immediately. After the 3D printing device stops printing, it will also send a warning message to the user to remind the user of the abnormal printing so that the user can handle it in time, thereby improving the stability of the 3D printing device. The types of warning information include but are not limited to voice reminders, text reminders, etc. Users can set the type of warning information according to actual needs.

[0060] In some embodiments, the printing status of the 3D printing device can also be detected by other methods. The specific contents are as follows:

[0061] The 3D printing device also includes a second collection member and a feed pipe, the feed pipe is connected to the nozzle, and the feed pipe is used to feed the printing material to the nozzle. The second collection member is used to collect the length of the printing material in the feed pipe. The second collection member can be a distance sensor. In other embodiments, the second collection member can also be arranged in the material trough tray in the 3D printing device. The second collection member is used to collect the length of the printing material in the material trough tray.

[0062] During the printing process of the 3D printing device, multiple material feeding length data of the feeding pipe within a preset time length are obtained. The label association value of each material feeding length data and the preset label set is obtained. The preset label set includes multiple labels, and the label association value is used to characterize the association between the material feeding length data and each label. The multiple labels at least include empty labels and non-empty labels. According to the label association value, the label corresponding to each material feeding length data is determined. According to the label corresponding to each printing data, the detection result of the 3D printing device is obtained.

[0063] When the print head has a blank print, it means that there is no printing material in the print head, and the feed pipe may not contain printing material or the feed pipe does not feed printing material to the print head. Therefore, the feed length data when the print head has a blank print is different from the feed length data when the print head has no blank print.

[0064] Similarly, if multiple labels include labels with and without nozzle wrapping, when the nozzle wrapping occurs, it means that the printing material at the nozzle is piled up, which causes the printing material in the feeding pipe to also pile up. Therefore, the feeding length data when the nozzle wraps and when the nozzle does not wrap are also different.

[0065] Based on multiple material delivery length data of the material delivery pipe within a preset time, the accurate detection result of the 3D printing equipment can also be determined.

[0066] It should be noted that the steps of determining the detection result of the 3D printing device based on multiple material delivery length data of the material delivery pipe within a preset time are the same as steps 101 to 104, and will not be repeated in this application.

[0067] Compared with the related art, the embodiments of the present application have at least the following advantages: only the printing data of the nozzle is obtained through the first acquisition component or only the multiple feed length data of the feed pipe is obtained through the second acquisition component, which reduces the additional acquisition equipment and reduces the cost of data acquisition. The correlation between each printing data or each feed length data and multiple labels is calculated to determine the printing status of the nozzle or feed pipe during the 3D printing process, thereby obtaining the detection result of the 3D printing device. On the one hand, the correlation between each printing data or each feed length data and the preset label set can be accurately calculated through the deep learning model, which is convenient for accurate detection of abnormal printing. On the other hand, it can detect abnormal printing of the nozzle in time, which is convenient for users to deal with abnormal printing in time.

[0068] Please refer to Figure 2 , is a flowchart of the steps for model training of a deep learning model provided in one embodiment of the present application.

[0069] The specific process of this embodiment is as follows Figure 2 As shown, the following steps are included:

[0070] Step 201: Determine a first duration, a second duration, a first label, and a second label.

[0071] In some embodiments, the first label at least includes a blank-printed label, and the second label at least includes a non-blank-printed label. In other embodiments, the first label may also include a nozzle-wrapped label, and the second label may also include a nozzle-unwrapped label.

[0072] In order to ensure accurate detection of abnormal printing conditions during 3D printing, it is necessary to train the deep learning model before formal printing. The first duration may be equal to the second duration, or the first duration may not be equal to the second duration. For example, the first duration may be 1 minute, the second duration may be 1 minute, or the second duration may be 70 seconds.

[0073] Step 202: Control the print head to perform abnormal printing within a first time period, and obtain first printing data of the print head within the first time period.

[0074] In some embodiments, abnormal printing indicates that the nozzle performs empty printing or the nozzle wraps during printing. In this embodiment, the two situations of the nozzle performing empty printing and the nozzle performing non-empty printing are explained.

[0075] Specifically, the nozzle is controlled to perform dry printing, and first printing data of the nozzle within a first time period is obtained.

[0076] It should be noted that the printing situation when the nozzle wraps during printing is the same as the printing situation when the nozzle is empty printing, and this application will not go into details.

[0077] Step 203: Mark the first printing data as a first label.

[0078] In this embodiment, the first printing data is marked as an empty print label. When the nozzle wrapping phenomenon occurs during printing, the first printing data is marked as a nozzle wrapping label.

[0079] Step 204: Control the print head to perform normal printing within the second time period, and obtain second printing data of the print head within the second time period.

[0080] In some embodiments, normal printing indicates that the nozzle does not perform empty printing or the nozzle does not wrap during printing.

[0081] In this embodiment, the nozzle is controlled to perform non-empty printing, and second printing data when the nozzle is performing non-empty printing is obtained.

[0082] Step 205: Mark the second printing data as a second label.

[0083] In this embodiment, the second printing data is marked as non-empty label printing. When the nozzle does not wrap around the nozzle during printing, the second printing data is marked as the nozzle does not wrap around the label.

[0084] The first print data and the second print data are stored. For example, the first print data and the second print data can be stored in a DataFrame data structure. DataFrame is a tabular data structure that contains a set of ordered columns, each of which can be a different value type (numerical value, string, Boolean value). At the same time, various functions are provided to perform operations such as data access, filtering, segmentation, merging, reshaping, aggregation, and conversion. In other embodiments, the first print data and the second print data can also be stored in other data structures, which is not limited by the present application.

[0085] Step 206: Train a deep learning model based on the first printing data and the second printing data.

[0086] In some embodiments, part of the data of the first print data and part of the data of the second print data are used as training data, and another part of the data of the first print data and another part of the data of the second print data are used as test data. For example, 70% of the data in the first print data and 70% of the data in the second print data are used as training data, and 30% of the data in the first print data and 30% of the data in the second print data are used as test data. Alternatively, 80% of the data in the first print data and 80% of the data in the second print data are used as training data, and 20% of the data in the first print data and 20% of the data in the second print data are used as test data. Alternatively, 70% of the data in the first print data and 80% of the data in the second print data are used as training data, and 30% of the data in the first print data and 20% of the data in the second print data are used as test data.

[0087] In some embodiments, a deep learning model is trained based on training data. Test data is input into the trained deep learning model to determine a loss value of the trained deep learning model. All parameters of the deep learning model are updated based on the loss value until the deep learning model converges to obtain a trained deep learning model.

[0088] Specifically, after training the deep learning model based on the training data, the historical gradient information of the deep learning model when the training data is trained is obtained. The test data is input into the trained deep learning model, and the loss value of the trained deep learning model is determined based on the historical gradient information. Then all the parameters of the deep learning model are updated based on the loss value until the deep learning model converges to obtain a trained deep learning model. Among them, the BCE loss function (BinaryCrossEntropy) is used to determine the loss value of the trained deep learning model. The BCE loss function is a prior art and will not be described in detail in this application.

[0089] In this embodiment, after the deep learning model is trained based on the training data, the adaptive optimizer (Adaptive Moment Estimation, Adam) is used to obtain the historical gradient information when the training data is trained on the deep learning model. The test data is input into the trained deep learning model, and the loss value of the trained deep learning model is determined based on the historical gradient information.

[0090] It should be noted that the Adam optimizer can adaptively adjust the learning rate of the model based on historical gradient information. A larger learning rate is used in the early stage of model training so that the model can converge quickly. A smaller learning rate is used in the later stage of model training to more accurately find the minimum loss value. The deep learning model optimized by the Adam optimizer can improve the accuracy of the deep learning model in detecting abnormal printheads.

[0091] It should also be noted that the framework used by the deep learning model is the pytorch framework. The pytorch framework is an open source deep learning framework for machine learning and deep learning. When designing a model, the structure of the model can be dynamically modified at runtime, providing greater flexibility for the model. The deep learning model is converted into an ONNX format file through the ONNX open source library, which helps to better deploy the model and quickly exchange and transplant between different frameworks and platforms, improving the utility and usability of the model. The ONNX format file is then converted into the inference file format required by the embedded end of the 3D printing device through NCNN or ONNXRunTime. For example, the inference file format can be in bin format. Finally, the converted deep learning model is deployed to the 3D printing device.

[0092] Compared with the related art, the embodiment of the present application has at least the following advantages: by controlling the nozzle to perform abnormal printing within a first time period and to perform non-abnormal printing within a second time period, accurate first printing data under abnormal printing and second printing data under non-abnormal printing are obtained. The first printing data and the second printing data are then used to train the deep learning model, and at the same time, during the training process, the Adam optimizer is used to optimize the training process. A model with accurate detection effect is obtained, thereby improving the accuracy of abnormal printing detection.

[0093] Please refer to Figure 3 , is a schematic diagram of the structure of a detection device based on a 3D printing device provided in one embodiment of the present application.

[0094] The detection device 200 based on 3D printing equipment is applied to the 3D printing equipment. The detection device 200 based on the 3D printing equipment includes an acquisition module 210, a calculation module 220, a determination module 230 and a detection module 240. The acquisition module 210 is used to obtain multiple printing data of the nozzle within a preset time length during the printing process of the 3D printing device. The calculation module 220 is used to calculate the label association value of each printing data and the preset label set, wherein the preset label set includes multiple labels, and the multiple labels include at least empty labels and non-empty labels, and the label association value is used to characterize the association between the printing data and each label. The determination module 230 is used to obtain the detection result of the 3D printing device according to the label corresponding to each printing data.

[0095] Please refer to Figure 4 , is a schematic diagram of the hardware structure of the electronic device 1000 provided in the embodiment of the present application. Figure 4 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, and the above instructions can be used to implement the above-mentioned detection method based on the 3D printing device in the electronic device 1000.

[0096] It is understandable that the structure shown 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 shown, or combine or separate some components, or arrange the components differently.

[0097] The processor 1001 may include one or more processing units, for example, the processor 1001 may include an application processor (AP), a modem, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0098] The processor 1001 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 1001 is a cache memory. The memory may store instructions or data that the processor 1001 has just used or circulated. If the processor 1001 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 1001, and thus improves the efficiency of the system.

[0099] In some embodiments, the processor 1001 may include one or more interfaces. The interface 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.

[0100] In some embodiments, memory 1002 may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0101] This embodiment further provides a computer-readable storage medium, in which computer instructions are stored. When the instructions are executed on an electronic device, the electronic device executes the above-mentioned related method steps to implement the detection method based on the 3D printing device in the above-mentioned embodiment.

[0102] Among them, the detection device, electronic device, and storage medium based on the 3D printing device provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0103] In practical applications, the above functions can be distributed 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.

[0104] In several embodiments provided in the present application, the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are schematic. For example, the division of the modules or units is a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0105] The unit described as a separate component may or may not be physically separated, and the component shown as a unit may be one physical unit or multiple physical units, that is, it may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0106] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0107] If the integrated unit is implemented in the form of 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 solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0108] The above description is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application.

Claims

1. A detection method based on 3D printing equipment, characterized in that: The 3D printing device comprises a nozzle and a heated bed, wherein the nozzle is used to spray printing material onto the heated bed; The detection method based on 3D printing equipment includes: During the printing process of the 3D printing device, a plurality of printing data of the nozzle within a preset time period are obtained; Calculating a label association value between each of the print data and a preset label set, wherein the preset label set includes a plurality of labels, the plurality of labels include at least a blank label and a non-blank label, and the label association value is used to characterize the degree of association between the print data and each of the labels; Determining the label corresponding to each of the print data according to the label association value; According to the label corresponding to each of the printing data, a detection result of the 3D printing device is obtained.

2. The detection method based on 3D printing equipment according to claim 1, characterized in that: The calculating of the label association value between each of the printing data and the preset label set includes: Convolving the plurality of print data to obtain convolution feature data; Based on the preset label set, forward feature processing and backward feature processing are performed on the convolution feature data to obtain the label association value.

3. The detection method based on 3D printing equipment according to claim 1, characterized in that: The step of determining the label corresponding to each of the print data according to the label association value includes: Acquire the tag association value having the greatest association degree between the current print data among the plurality of print data and the plurality of tags; The label corresponding to each of the printing data is determined according to the label association value with the greatest association degree.

4. The detection method based on 3D printing equipment according to claim 1, characterized in that: The step of obtaining the detection result of the 3D printing device according to the label corresponding to each of the printing data includes: Classify the plurality of printing data by labels according to the labels corresponding to each of the printing data to obtain the plurality of printing data after classification; Based on the classified plurality of printing data, a detection result of the 3D printing device is determined.

5. The detection method based on 3D printing equipment according to claim 1, characterized in that: The method uses a deep learning model to detect the printing status of the 3D printing device; The training process of the deep learning model includes: Determine a first duration, a second duration, a first label, and a second label, wherein the first label at least includes the empty label, and the second label at least includes the non-empty label; Controlling the nozzle to perform abnormal printing within the first time period, and obtaining first printing data of the nozzle within the first time period, wherein the abnormal printing indicates that the nozzle performs empty printing; marking the first print data as the first label; Controlling the nozzle to perform normal printing within the second time period, and obtaining second printing data of the nozzle within the second time period, wherein the normal printing indicates that the nozzle performs non-empty printing; marking the second print data as the second label; The deep learning model is trained based on the first printing data and the second printing data.

6. The detection method based on 3D printing equipment according to claim 5, characterized in that: The training of the deep learning model based on the first printing data and the second printing data includes: Training the deep learning model using part of the first print data and part of the second print data; Get historical gradient information; Inputting another portion of the first printing data and another portion of the second printing data into the trained deep learning model; Based on the historical gradient information, determining a loss value of the deep learning model after training; All parameters of the deep learning model are updated based on the loss value until the deep learning model converges to obtain the trained deep learning model.

7. A detection method based on 3D printing equipment, characterized in that: The 3D printing device comprises a nozzle and a material delivery pipe, wherein the material delivery pipe is used to deliver printing material to the nozzle; The detection method based on 3D printing equipment includes: During the printing process of the 3D printing device, a plurality of material feeding length data of the material feeding pipe within a preset time length are obtained; Obtaining a label association value between each of the feed length data and a preset label set, wherein the preset label set includes a plurality of labels, the plurality of labels at least include an empty label and a non-empty label, and the label association value is used to characterize the degree of association between the feed length data and each of the labels; Determine the label corresponding to each of the feeding length data according to the label association value; According to the label corresponding to each of the printing data, a detection result of the 3D printing device is obtained.

8. A detection device based on 3D printing equipment, characterized in that: include: An acquisition module: used for acquiring a plurality of printing data of a nozzle within a preset time period during the printing process of the 3D printing device; A calculation module: used for calculating a label association value between each of the printing data and a preset label set, wherein the preset label set includes a plurality of labels, and the label association value is used for representing the association degree between the printing data and each of the labels, and the plurality of labels include at least a blank label and a non-blank label; A determination module: used for determining the label corresponding to each of the printing data according to the label association value; Detection module: used to obtain the detection result of the 3D printing device according to the label corresponding to each printing data.

9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the detection method based on a 3D printing device according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The method comprises computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the detection method based on a 3D printing device as claimed in any one of claims 1 to 7.

Images