Method and system for analyzing abnormal nozzle speed based on image recognition

Abstract

The present invention discloses a nozzle speed anomaly analysis method and system based on image recognition, the method comprising: obtaining multiple material extrusion images of a target printing nozzle when printing a target product; determining the component speeds corresponding to multiple working components of the target printing nozzle based on the material extrusion images and based on a component speed recognition algorithm model; identifying the printing defects corresponding to the target product based on the material extrusion images and based on a recognition algorithm model; analyzing the speed anomaly corresponding to the target printing nozzle based on the preset correspondence between the defect and the speed anomaly according to the printing defect and the component speed corresponding to each of the working components. It can be seen that the present invention can monitor and analyze the speed anomaly of the nozzle more efficiently and accurately, improve the 3D printing accuracy, and reduce printing errors.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for analyzing nozzle velocity anomaly based on image recognition. Background Art

[0002] With the development of 3D printing technology and the increasing demand for 3D printing, more and more 3D printing equipment is being used in various production tasks to improve production efficiency, and the precision requirements for 3D printing are also increasing. Among them, how to accurately identify and correct the working speed of the nozzle has become an important technical issue. However, when the existing technology realizes the monitoring of the speed of 3D printing nozzles, most of them only monitor the speed through simple speed sensors or single image recognition algorithms, and do not fully consider the relationship between the material extrusion image of the nozzle and the working speed of multiple components to accurately correct the speed control of the nozzle. Therefore, the speed monitoring accuracy of the existing technical solution is low and the control accuracy is poor. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for analyzing nozzle speed anomaly based on image recognition, which can monitor and analyze nozzle speed anomaly more efficiently and accurately, improve 3D printing accuracy, and reduce printing errors.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for analyzing nozzle speed anomaly based on image recognition, the method comprising:

[0005] Acquire multiple material extrusion images of a target print head when printing a target product;

[0006] According to the material extrusion image, based on a component speed recognition algorithm model, determining component speeds corresponding to a plurality of working components of the target print head;

[0007] According to the material extrusion image, based on a recognition algorithm model, identifying printing defects corresponding to the target product;

[0008] According to the printing defects and the component speed corresponding to each of the working components, based on a preset corresponding relationship between the defects and the speed anomaly, the speed anomaly corresponding to the target printing nozzle is analyzed.

[0009] As an optional embodiment, in the first aspect of the present invention, the working component is a material extruder or a moving shaft track component in any direction of freedom of movement.

[0010] As an optional embodiment, in the first aspect of the present invention, the printing defects include at least one of material shortage, collapse, misalignment, insufficient line width and insufficient line length.

[0011] As an optional embodiment, in the first aspect of the present invention, determining the component speeds corresponding to the multiple working components of the target print head according to the material extrusion image and based on a component speed recognition algorithm model includes:

[0012] For each material extrusion image, the material extrusion image is input into the trained motion recognition neural network to obtain the nozzle movement direction and working speed corresponding to the material extrusion image; the working speed is the material extrusion speed or the motion axis track movement speed

[0013] Determine the working component corresponding to the moving direction of the nozzle according to the preset association relationship between the moving direction and the component;

[0014] The working speed is determined as the component speed corresponding to the working component corresponding to the moving direction of the nozzle.

[0015] As an optional embodiment, in the first aspect of the present invention, the motion recognition neural network is a RNN neural network, which is trained by a training data set including multiple training material extrusion images and corresponding nozzle movement direction annotations and nozzle working speed annotations.

[0016] As an optional implementation, in the first aspect of the present invention, identifying the printing defects corresponding to the target product based on the material extrusion image and a recognition algorithm model includes:

[0017] Inputting each of the material extrusion images into a trained product region segmentation algorithm to obtain a partial image of the product region corresponding to each of the material extrusion images;

[0018] Inputting each of the product area partial images into a trained print defect recognition neural network to obtain product defects corresponding to each of the product area partial images; the print defect recognition neural network is trained by a training data set including a plurality of training product images and corresponding product defect annotations;

[0019] The printing defects corresponding to the target product are determined according to the product defects corresponding to all the partial images of the product area.

[0020] As an optional implementation, in the first aspect of the present invention, determining the printing defect corresponding to the target product according to the product defects corresponding to all the partial images of the product area includes:

[0021] Sorting the product defects corresponding to all partial images of the product area from early to late according to the corresponding image acquisition time to obtain a defect sequence;

[0022] The product defects whose number continuously appears in the defect sequence exceeds a preset number threshold value are determined as printing defects corresponding to the target product.

[0023] As an optional embodiment, in the first aspect of the present invention, the analyzing the speed abnormality corresponding to the target print head according to the printing defect and the component speed corresponding to each of the working components based on a preset correspondence relationship between the defect and the speed abnormality includes:

[0024] According to the preset correspondence between the printing defect and the abnormal component, and the printing defect, a plurality of preset abnormal components and corresponding normal speed reference values ​​are determined;

[0025] Calculating a speed difference between the component speed corresponding to each of the preset abnormal components and the normal speed reference value;

[0026] Determine the preset abnormal component whose speed difference is greater than a preset difference threshold as an abnormal working component;

[0027] The abnormality degree value corresponding to each abnormal working component is determined as an abnormal parameter that is proportional to the corresponding speed difference value.

[0028] A second aspect of an embodiment of the present invention discloses a nozzle speed abnormality analysis system based on image recognition, the system comprising:

[0029] An acquisition module, used to acquire multiple material extrusion images of a target printing nozzle when printing a target product;

[0030] A determination module, configured to determine component speeds corresponding to a plurality of working components of the target print head according to the material extrusion image and based on a component speed recognition algorithm model;

[0031] A recognition module, configured to identify printing defects corresponding to the target product according to the material extrusion image and based on a recognition algorithm model;

[0032] The analysis module is used to analyze the speed abnormality corresponding to the target printing nozzle according to the printing defect and the component speed corresponding to each of the working components and based on a preset corresponding relationship between the defect and the speed abnormality.

[0033] As an optional embodiment, in the second aspect of the present invention, the working component is a material extruder or a moving shaft track component in any direction of freedom of movement.

[0034] As an optional embodiment, in the second aspect of the present invention, the printing defects include at least one of material shortage, collapse, misalignment, insufficient line width and insufficient line length.

[0035] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the component speeds corresponding to the multiple working components of the target print head according to the material extrusion image and based on the component speed recognition algorithm model includes:

[0036] For each material extrusion image, the material extrusion image is input into the trained motion recognition neural network to obtain the nozzle movement direction and working speed corresponding to the material extrusion image; the working speed is the material extrusion speed or the motion axis track movement speed

[0037] Determine the working component corresponding to the moving direction of the nozzle according to the preset association relationship between the moving direction and the component;

[0038] The working speed is determined as the component speed corresponding to the working component corresponding to the moving direction of the nozzle.

[0039] As an optional embodiment, in the second aspect of the present invention, the motion recognition neural network is a RNN neural network, which is trained by a training data set including multiple training material extrusion images and corresponding nozzle movement direction annotations and nozzle working speed annotations.

[0040] As an optional implementation, in the second aspect of the present invention, the specific manner in which the recognition module identifies the printing defects corresponding to the target product based on the material extrusion image and the recognition algorithm model includes:

[0041] Inputting each of the material extrusion images into a trained product region segmentation algorithm to obtain a partial image of the product region corresponding to each of the material extrusion images;

[0042] Inputting each of the product area partial images into a trained print defect recognition neural network to obtain product defects corresponding to each of the product area partial images; the print defect recognition neural network is trained by a training data set including a plurality of training product images and corresponding product defect annotations;

[0043] The printing defects corresponding to the target product are determined according to the product defects corresponding to all the partial images of the product area.

[0044] As an optional implementation, in the second aspect of the present invention, the identification module determines the specific manner in which the printing defect corresponding to the target product corresponds to all the product defects corresponding to the partial images of the product area, including:

[0045] Sorting the product defects corresponding to all partial images of the product area from early to late according to the corresponding image acquisition time to obtain a defect sequence;

[0046] The product defects whose number continuously appears in the defect sequence exceeds a preset number threshold value are determined as printing defects corresponding to the target product.

[0047] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the analysis module analyzes the speed abnormality corresponding to the target print head according to the printing defect and the component speed corresponding to each of the working components and based on a preset correspondence between the defect and the speed abnormality includes:

[0048] According to the preset correspondence between the printing defect and the abnormal component, and the printing defect, a plurality of preset abnormal components and corresponding normal speed reference values ​​are determined;

[0049] Calculating a speed difference between the component speed corresponding to each of the preset abnormal components and the normal speed reference value;

[0050] Determine the preset abnormal component whose speed difference is greater than a preset difference threshold as an abnormal working component;

[0051] The abnormality degree value corresponding to each abnormal working component is determined as an abnormal parameter that is proportional to the corresponding speed difference value.

[0052] The third aspect of the present invention discloses another nozzle speed abnormality analysis system based on image recognition, the system comprising:

[0053] A memory storing executable program code;

[0054] a processor coupled to the memory;

[0055] The processor calls the executable program code stored in the memory to execute part or all of the steps in the method for analyzing nozzle velocity anomaly based on image recognition disclosed in the first aspect of the present invention.

[0056] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the nozzle speed anomaly analysis method based on image recognition disclosed in the first aspect of the present invention.

[0057] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0058] The present invention can respectively identify the working speed of the component and the printing defects of the product based on the material extrusion image of the target printing nozzle when printing the target product, and then accurately analyze the speed abnormality corresponding to the target printing nozzle based on the preset correspondence between the defect and the speed abnormality, so as to monitor and analyze the speed abnormality of the nozzle more efficiently and accurately, improve the 3D printing accuracy and reduce printing errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1 It is a flow chart of a method for analyzing nozzle velocity anomaly based on image recognition disclosed in an embodiment of the present invention.

[0061] Figure 2 It is a structural schematic diagram of a nozzle speed anomaly analysis system based on image recognition disclosed in an embodiment of the present invention.

[0062] Figure 3 It is a structural schematic diagram of another nozzle speed anomaly analysis system based on image recognition disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0065] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0066] The present invention discloses a nozzle speed anomaly analysis method and system based on image recognition, which can respectively identify the working speed of a component and the printing defect of a product based on the material extrusion image of a target printing nozzle when printing a target product, and then accurately analyze the speed anomaly corresponding to the target printing nozzle based on the preset corresponding relationship between the defect and the speed anomaly, so as to more efficiently and accurately monitor and analyze the nozzle speed anomaly, improve the 3D printing accuracy, and reduce printing errors. The following are detailed descriptions.

[0067] Embodiment 1

[0068] See also Figure 1 , Figure 1 : is a flow chart of a nozzle speed abnormality analysis method based on image recognition disclosed in an embodiment of the present invention. Figure 1 The described method for analyzing nozzle speed anomaly based on image recognition can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the nozzle speed abnormality analysis method based on image recognition may include the following operations:

[0069] 101. Acquire multiple material extrusion images of a target printing head when printing a target product.

[0070] 102. According to the material extrusion image and based on a component speed recognition algorithm model, component speeds corresponding to a plurality of working components of a target print head are determined.

[0071] 103. According to the material extrusion image, based on the recognition algorithm model, the printing defects corresponding to the target product are identified.

[0072] 104. According to the printing defects and the component speed corresponding to each working component, based on the preset corresponding relationship between the defects and the speed anomaly, the speed anomaly corresponding to the target printing nozzle is analyzed.

[0073] It can be seen that the above-mentioned embodiments of the invention can respectively identify the working speed of the component and the printing defects of the product based on the material extrusion image of the target printing nozzle when printing the target product, and then accurately analyze the speed abnormality corresponding to the target printing nozzle based on the preset correspondence between the defect and the speed abnormality, so as to monitor and analyze the speed abnormality of the nozzle more efficiently and accurately, improve the 3D printing accuracy and reduce printing errors.

[0074] As an optional embodiment, in the above steps, the working component is a material extruder or a moving shaft rail component in any direction of freedom of movement.

[0075] It can be seen that through the above optional embodiments, the type of working parts is clarified, which can more accurately characterize the characteristics of the moving parts corresponding to the nozzle, and assist in more efficient and accurate monitoring and analysis of the speed abnormality of the nozzle, thereby improving 3D printing accuracy and reducing printing errors.

[0076] As an optional embodiment, in the above steps, the printing defects include at least one of material shortage, collapse, misalignment, insufficient line width and insufficient line length.

[0077] It can be seen that through the above optional embodiments, the types of printing defects are clarified, and the possible defect characteristics of the product printing process can be more accurately characterized, so as to facilitate the accurate analysis of speed abnormalities, and assist in more efficient and accurate monitoring and analysis of nozzle speed abnormalities, thereby improving 3D printing accuracy and reducing printing errors.

[0078] As an optional embodiment, in the above step, determining the component speeds corresponding to the multiple working components of the target print head according to the material extrusion image and based on the component speed recognition algorithm model includes:

[0079] For each material extrusion image, the material extrusion image is input into the trained motion recognition neural network to obtain the nozzle movement direction and working speed corresponding to the material extrusion image; the working speed is the material extrusion speed or the motion axis track movement speed

[0080] According to the preset association between the moving direction and the components, the working components corresponding to the moving direction of the nozzle are determined;

[0081] The working speed is determined as the component speed corresponding to the working component corresponding to the direction of movement of the nozzle.

[0082] It can be seen that through the above-mentioned optional embodiments, after the nozzle movement direction and working speed corresponding to the extrusion image can be identified through the mobile recognition neural network, the working parts and component speeds can be determined according to the association between the movement direction and the parts, so as to facilitate the subsequent accurate analysis of speed anomalies, and assist in achieving more efficient and accurate monitoring and analysis of nozzle speed anomalies, thereby improving 3D printing accuracy and reducing printing errors.

[0083] As an optional embodiment, in the above steps, the motion recognition neural network is a RNN neural network, which is trained by a training data set including a plurality of training material extrusion images and corresponding nozzle movement direction annotations and nozzle working speed annotations.

[0084] It can be seen that through the above optional embodiments, the algorithm details and training details of the mobile recognition neural network are clarified to facilitate accurate component speed recognition and analysis, assist in more efficient and precise monitoring and analysis of nozzle speed anomalies, improve 3D printing accuracy, and reduce printing errors.

[0085] As an optional embodiment, in the above step, identifying the printing defects corresponding to the target product based on the material extrusion image and the recognition algorithm model includes:

[0086] Input each material extrusion image into a trained product region segmentation algorithm to obtain a partial image of the product region corresponding to each material extrusion image;

[0087] Inputting each product area partial image into a trained print defect recognition neural network to obtain a product defect corresponding to each product area partial image; optionally, the print defect recognition neural network is trained by a training data set including a plurality of training product images and corresponding product defect annotations;

[0088] According to the product defects corresponding to the partial images of all product areas, the printing defects corresponding to the target product are determined.

[0089] It can be seen that through the above-mentioned optional embodiments, after identifying the product area in the image according to the product area segmentation algorithm, the product defects can be identified based on the printing defect recognition neural network to comprehensively determine the printing defects corresponding to the product, facilitate subsequent accurate speed abnormality analysis, and assist in achieving more efficient and accurate monitoring and analysis of the speed abnormality of the nozzle, thereby improving 3D printing accuracy and reducing printing errors.

[0090] As an optional embodiment, in the above step, determining the printing defects corresponding to the target product according to the product defects corresponding to the partial images of all product regions includes:

[0091] The product defects corresponding to the partial images of all product regions are sorted from early to late according to the corresponding image acquisition time to obtain a defect sequence;

[0092] The product defects that appear continuously in the defect sequence in a number exceeding a preset threshold value are determined as printing defects corresponding to the target product.

[0093] It can be seen that through the above-mentioned optional embodiments, it is possible to determine that the defects that appear continuously in the product defects corresponding to multiple images are printing defects, so as to accurately determine the printing defects corresponding to the product, facilitate subsequent accurate speed abnormality analysis, and assist in achieving more efficient and accurate monitoring and analysis of the speed abnormality of the nozzle, thereby improving 3D printing accuracy and reducing printing errors.

[0094] As an optional embodiment, in the above steps, according to the printing defect and the component speed corresponding to each working component, based on the preset corresponding relationship between the defect and the speed abnormality, analyzing the speed abnormality corresponding to the target print head includes:

[0095] According to the preset correspondence between the printing defect and the abnormal component, and the printing defect, a plurality of preset abnormal components and corresponding normal speed reference values ​​are determined;

[0096] Calculate the speed difference between the component speed corresponding to each preset abnormal component and the normal speed reference value;

[0097] Determine a preset abnormal component whose speed difference is greater than a preset difference threshold as an abnormal working component;

[0098] The abnormality degree value corresponding to each abnormal working component is determined as an abnormal parameter that is proportional to the corresponding speed difference value.

[0099] It can be seen that through the above-mentioned optional embodiments, multiple preset abnormal components corresponding to the printing defects can be determined through the correspondence between the preset printing defects and abnormal components, and then the abnormal working components can be screened out and the degree of abnormality can be determined according to the difference between the component speed and the reference speed, so as to achieve more efficient and accurate monitoring and analysis of the speed abnormality of the nozzle, improve 3D printing accuracy and reduce printing errors.

[0100] Embodiment 2

[0101] See also Figure 2 , Figure 2 Schematic diagram of a nozzle speed abnormality analysis system based on image recognition disclosed in an embodiment of the present invention. Figure 2 The nozzle speed abnormality analysis system based on image recognition described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2As shown, the nozzle speed abnormality analysis system based on image recognition may include:

[0102] The acquisition module 201 is used to acquire a plurality of material extrusion images of a target printing head when printing a target product.

[0103] The determination module 202 is used to determine the component speeds corresponding to the multiple working components of the target printing nozzle according to the material extrusion image and based on the component speed recognition algorithm model.

[0104] The recognition module 203 is used to recognize the printing defects corresponding to the target product according to the material extrusion image and based on the recognition algorithm model.

[0105] The analysis module 204 is used to analyze the speed abnormality corresponding to the target print head according to the printing defect and the component speed corresponding to each working component, based on the preset corresponding relationship between the defect and the speed abnormality.

[0106] It can be seen that the above-mentioned embodiments of the invention can respectively identify the working speed of the component and the printing defects of the product based on the material extrusion image of the target printing nozzle when printing the target product, and then accurately analyze the speed abnormality corresponding to the target printing nozzle based on the preset correspondence between the defect and the speed abnormality, so as to monitor and analyze the speed abnormality of the nozzle more efficiently and accurately, improve the 3D printing accuracy and reduce printing errors.

[0107] As an optional embodiment, the working component is a material extruder or a moving axis track component in any direction of freedom of movement.

[0108] It can be seen that through the above optional embodiments, the type of working parts is clarified, which can more accurately characterize the characteristics of the moving parts corresponding to the nozzle, and assist in more efficient and accurate monitoring and analysis of the speed abnormality of the nozzle, thereby improving 3D printing accuracy and reducing printing errors.

[0109] As an optional embodiment, the printing defect includes at least one of material shortage, collapse, misalignment, insufficient line width and insufficient line length.

[0110] It can be seen that through the above optional embodiments, the types of printing defects are clarified, and the possible defect characteristics of the product printing process can be more accurately characterized, so as to facilitate the accurate analysis of speed abnormalities, and assist in more efficient and accurate monitoring and analysis of nozzle speed abnormalities, thereby improving 3D printing accuracy and reducing printing errors.

[0111] As an optional embodiment, the specific manner in which the determination module determines the component speeds corresponding to the multiple working components of the target print head according to the material extrusion image and based on the component speed recognition algorithm model includes:

[0112] For each material extrusion image, the material extrusion image is input into the trained motion recognition neural network to obtain the nozzle movement direction and working speed corresponding to the material extrusion image; the working speed is the material extrusion speed or the motion axis track movement speed

[0113] According to the preset association between the moving direction and the components, the working components corresponding to the moving direction of the nozzle are determined;

[0114] The working speed is determined as the component speed corresponding to the working component corresponding to the direction of movement of the nozzle.

[0115] It can be seen that through the above-mentioned optional embodiments, after the nozzle movement direction and working speed corresponding to the extrusion image can be identified through the mobile recognition neural network, the working parts and component speeds can be determined according to the association between the movement direction and the parts, so as to facilitate the subsequent accurate analysis of speed anomalies, and assist in achieving more efficient and accurate monitoring and analysis of nozzle speed anomalies, thereby improving 3D printing accuracy and reducing printing errors.

[0116] As an optional embodiment, the motion recognition neural network is a RNN neural network, which is trained by a training data set including a plurality of training material extrusion images and corresponding nozzle movement direction annotations and nozzle working speed annotations.

[0117] It can be seen that through the above optional embodiments, the algorithm details and training details of the mobile recognition neural network are clarified to facilitate accurate component speed recognition and analysis, assist in more efficient and precise monitoring and analysis of nozzle speed anomalies, improve 3D printing accuracy, and reduce printing errors.

[0118] As an optional embodiment, the recognition module identifies the specific manner of the printing defects corresponding to the target product according to the material extrusion image and based on the recognition algorithm model, including:

[0119] Input each material extrusion image into a trained product region segmentation algorithm to obtain a partial image of the product region corresponding to each material extrusion image;

[0120] Inputting each product area partial image into a trained print defect recognition neural network to obtain a product defect corresponding to each product area partial image; optionally, the print defect recognition neural network is trained by a training data set including a plurality of training product images and corresponding product defect annotations;

[0121] According to the product defects corresponding to the partial images of all product areas, the printing defects corresponding to the target product are determined.

[0122] It can be seen that through the above-mentioned optional embodiments, after identifying the product area in the image according to the product area segmentation algorithm, the product defects can be identified based on the printing defect recognition neural network to comprehensively determine the printing defects corresponding to the product, facilitate subsequent accurate speed abnormality analysis, and assist in achieving more efficient and accurate monitoring and analysis of the speed abnormality of the nozzle, thereby improving 3D printing accuracy and reducing printing errors.

[0123] As an optional embodiment, the recognition module determines the specific manner in which the printing defect corresponding to the target product corresponds to the product defects corresponding to the partial images of all product regions, including:

[0124] The product defects corresponding to the partial images of all product regions are sorted from early to late according to the corresponding image acquisition time to obtain a defect sequence;

[0125] The product defects that appear continuously in the defect sequence in a number exceeding a preset threshold value are determined as printing defects corresponding to the target product.

[0126] It can be seen that through the above-mentioned optional embodiments, it is possible to determine that the defects that appear continuously in the product defects corresponding to multiple images are printing defects, so as to accurately determine the printing defects corresponding to the product, facilitate subsequent accurate speed abnormality analysis, and assist in achieving more efficient and accurate monitoring and analysis of the speed abnormality of the nozzle, thereby improving 3D printing accuracy and reducing printing errors.

[0127] As an optional embodiment, the analysis module analyzes the specific manner of the speed abnormality corresponding to the target print head according to the printing defect and the component speed corresponding to each working component based on the preset corresponding relationship between the defect and the speed abnormality, including:

[0128] According to the preset correspondence between the printing defect and the abnormal component, and the printing defect, a plurality of preset abnormal components and corresponding normal speed reference values ​​are determined;

[0129] Calculate the speed difference between the component speed corresponding to each preset abnormal component and the normal speed reference value;

[0130] Determine a preset abnormal component whose speed difference is greater than a preset difference threshold as an abnormal working component;

[0131] The abnormality degree value corresponding to each abnormal working component is determined as an abnormal parameter that is proportional to the corresponding speed difference value.

[0132] It can be seen that through the above-mentioned optional embodiments, multiple preset abnormal components corresponding to the printing defects can be determined through the correspondence between the preset printing defects and abnormal components, and then the abnormal working components can be screened out and the degree of abnormality can be determined according to the difference between the component speed and the reference speed, so as to achieve more efficient and accurate monitoring and analysis of the speed abnormality of the nozzle, improve 3D printing accuracy and reduce printing errors.

[0133] Embodiment 3

[0134] See also Figure 3 , Figure 3 It is another nozzle speed abnormality analysis system based on image recognition disclosed in an embodiment of the present invention. Figure 3 The described nozzle speed abnormality analysis system based on image recognition is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the nozzle speed abnormality analysis system based on image recognition may include:

[0135] A memory 301 storing executable program codes;

[0136] a processor 302 coupled to the memory 301;

[0137] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the nozzle speed abnormality analysis method based on image recognition described in the first embodiment.

[0138] Embodiment 4

[0139] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the nozzle velocity abnormality analysis method based on image recognition described in the first embodiment.

[0140] Embodiment 5

[0141] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the nozzle speed abnormality analysis method based on image recognition described in the first embodiment.

[0142] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0143] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0144] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0145] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0146] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0147] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0149] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0150] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0151] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0152] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0153] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0154] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0155] Finally, it should be noted that the method and system for analyzing nozzle speed anomaly based on image recognition disclosed in the embodiment of the present invention disclose only the preferred embodiments of the present invention, which are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical schemes described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the various embodiments of the present invention.

Claims

1. A nozzle speed abnormality analysis method based on image recognition, characterized in that: The method comprises: Acquire multiple material extrusion images of a target print head when printing a target product; According to the material extrusion image, based on a component speed recognition algorithm model, determining component speeds corresponding to a plurality of working components of the target print head; According to the material extrusion image, based on the recognition algorithm model, the printing defects corresponding to the target product are identified, including: Inputting each of the material extrusion images into a trained product region segmentation algorithm to obtain a partial image of the product region corresponding to each of the material extrusion images; Inputting each of the product area partial images into a trained print defect recognition neural network to obtain product defects corresponding to each of the product area partial images; the print defect recognition neural network is trained by a training data set including a plurality of training product images and corresponding product defect annotations; Sorting the product defects corresponding to all partial images of the product area from early to late according to the corresponding image acquisition time to obtain a defect sequence; Determine the product defects that appear continuously in the defect sequence in a number exceeding a preset number threshold as printing defects corresponding to the target product; According to the printing defects and the component speed corresponding to each of the working components, based on a preset corresponding relationship between the defects and the speed anomaly, the speed anomaly corresponding to the target printing nozzle is analyzed.

2. The method for analyzing nozzle velocity anomaly based on image recognition according to claim 1, characterized in that: The working component is a material extruder or a moving shaft rail component in any direction of freedom of movement.

3. The method for analyzing nozzle velocity anomaly based on image recognition according to claim 1, characterized in that: The printing defects include at least one of material shortage, collapse, misalignment, insufficient line width and insufficient line length.

4. The method for analyzing nozzle velocity anomaly based on image recognition according to claim 2, characterized in that: The determining, according to the material extrusion image and based on a component speed recognition algorithm model, component speeds corresponding to a plurality of working components of the target print head comprises: For each material extrusion image, the material extrusion image is input into the trained motion recognition neural network to obtain the nozzle movement direction and working speed corresponding to the material extrusion image; the working speed is the material extrusion speed or the motion axis track movement speed Determine the working component corresponding to the moving direction of the nozzle according to the preset association relationship between the moving direction and the component; The working speed is determined as the component speed corresponding to the working component corresponding to the moving direction of the nozzle.

5. The method for analyzing nozzle velocity anomaly based on image recognition according to claim 4, characterized in that: The movement recognition neural network is a RNN neural network, which is trained by a training data set including a plurality of training material extrusion images and corresponding nozzle movement direction annotations and nozzle working speed annotations.

6. The method for analyzing nozzle velocity anomaly based on image recognition according to claim 1, characterized in that: The analyzing the speed abnormality corresponding to the target print head according to the printing defect and the component speed corresponding to each of the working components based on a preset corresponding relationship between the defect and the speed abnormality includes: According to the preset correspondence between the printing defect and the abnormal component, and the printing defect, a plurality of preset abnormal components and corresponding normal speed reference values ​​are determined; Calculating a speed difference between the component speed corresponding to each of the preset abnormal components and the normal speed reference value; Determine the preset abnormal component whose speed difference is greater than a preset difference threshold as an abnormal working component; The abnormality degree value corresponding to each abnormal working component is determined as an abnormal parameter that is proportional to the corresponding speed difference value.

7. A nozzle speed abnormality analysis system based on image recognition, characterized in that: The system comprises: An acquisition module, used to acquire multiple material extrusion images of a target printing nozzle when printing a target product; A determination module, configured to determine component speeds corresponding to a plurality of working components of the target print head according to the material extrusion image and based on a component speed recognition algorithm model; The recognition module is used to identify the printing defects corresponding to the target product according to the material extrusion image and based on the recognition algorithm model, including: Inputting each of the material extrusion images into a trained product region segmentation algorithm to obtain a partial image of the product region corresponding to each of the material extrusion images; Inputting each of the product area partial images into a trained print defect recognition neural network to obtain product defects corresponding to each of the product area partial images; the print defect recognition neural network is trained by a training data set including a plurality of training product images and corresponding product defect annotations; Sorting the product defects corresponding to all partial images of the product area from early to late according to the corresponding image acquisition time to obtain a defect sequence; Determine the product defects that appear continuously in the defect sequence in a number exceeding a preset number threshold as printing defects corresponding to the target product; The analysis module is used to analyze the speed abnormality corresponding to the target printing nozzle according to the printing defect and the component speed corresponding to each of the working components and based on a preset corresponding relationship between the defect and the speed abnormality.

8. A nozzle speed abnormality analysis system based on image recognition, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the nozzle speed abnormality analysis method based on image recognition as described in any one of claims 1-6.

Images