Real-time Defect Detection Method and System for Selective Laser Melting 3D Printing

Abstract

The present invention provides a real-time defect detection method and system for selective laser melting 3D printing, including: retrieving a corresponding defect database based on the material properties of the 3D printed finished product to construct a material defect feature set, determining the image acquisition moment based on the real-time printing progress of the current printing layer by a laser scanning array, obtaining a complete planar image of the current printing layer, identifying a number of current material defects included in the complete planar image, generating defect information of the current printing layer, establishing a 3D stereoscopic image of the 3D printed finished product, using the defect information to identify the defect attributes corresponding to each printed part in the corresponding 3D stereoscopic image, generating a defect report and displaying it, automatically recording the defect type and size during the printing process, and combining with a stereoscopic slicing software for annotation to provide technical reference for users.

Description

Technical Field

[0001] The present invention relates to the field of defect recognition technology, and in particular to a real-time defect detection method and system for selective laser melting 3D printing. Background Art

[0002] SLM technology is developed on the basis of SLS. SLM technology needs to completely melt the metal powder and directly form metal parts. Therefore, a high-power density laser is required. Before the laser beam starts scanning, the horizontal powder roller first spreads the metal powder on the substrate of the processing chamber. Then the laser beam will selectively melt the powder on the substrate according to the contour information of the current layer, process the contour of the current layer, and then the lifting system will drop a layer thickness. The rolling powder roller will spread the metal powder on the processed current layer, and the equipment will be transferred to the next layer for processing. This process is repeated layer by layer until the entire part is processed. However, SLM technology is the same as all 3D printing technologies. Selective laser melting is also processed layer by layer until the entire part is processed. When all the processing work is completed, it is extremely difficult to find out whether there are defects inside the part. For example, since the process of laser melting powder is similar to welding, just like welding will have "false welding", in the process of 3D printing, some powders will not be completely melted. How to detect defects in the printed product during the printing process has become an urgent problem to be solved.

[0003] Therefore, the present invention provides a real-time defect detection method and system for selective laser melting 3D printing. Summary of the invention

[0004] The present invention is a real-time defect detection method and system for selective laser melting 3D printing. By adding a machine vision system to the laser scanning array, a plane image of each layer is quickly captured before the next layer of powder is laid after each layer is printed, and then the image is analyzed to determine the printing defects of the layer. After printing is completed, an internal defect map of each part is generated, and whether the part is usable is determined according to the requirements of the demander.

[0005] The present invention provides a real-time defect detection method for selective laser melting 3D printing, comprising:

[0006] Step 1: Retrieve a corresponding defect database based on the material properties of the 3D printed product, identify the defect features corresponding to each defect data in the defect database, and obtain a material defect feature set;

[0007] Step 2: determining the image acquisition time based on the real-time printing progress of the current printing layer by the laser scanning array, and obtaining a complete plane image of the current printing layer;

[0008] Step 3: Use the material defect feature set to identify several current material defects included in the complete planar image, and respectively perform in-depth identification on each of the current material defects to generate defect information of the current printing layer;

[0009] Step 4: Establish a 3D stereoscopic image of the 3D printed product, use the defect information to identify the defect attributes corresponding to each printed part in the corresponding 3D stereoscopic image, generate a defect report of the 3D printed product and display it.

[0010] In an implementable manner,

[0011] The said Step 1 includes:

[0012] Step 11: Determine the printing raw material of the 3D printed product based on the current printing task, and look up the defect database corresponding to the material attribute in the big data based on the material attribute of the printing raw material;

[0013] Step 12: Use the defect data to draw a defect image of the printing raw material, and determine the defect features corresponding to each defect data;

[0014] Step 13: Perform clustering analysis on the defect features to generate a material defect feature set corresponding to the current printing task and display it.

[0015] In an implementable manner,

[0016] The said Step 12 includes:

[0017] Step 121: Generate a defect-free image of the printing raw material based on the material attribute, and respectively obtain the data differences between each defect data and the defect-free data corresponding to the defect-free image;

[0018] Step 122: Use the data differences to perform corresponding defect adjustment training on the defect-free image to obtain a defect image corresponding to each defect data;

[0019] Step 123: Respectively identify the image presentation features corresponding to each defect image, and generate defect features corresponding to the corresponding defect data.

[0020] In an implementable manner,

[0021] The said Step 13 includes:

[0022] Step 131: Perform clustering analysis on the defect features to obtain several defect clusters, respectively identify the defect weights of each defect feature in the corresponding defect cluster, and recombine the corresponding defect features based on the defect weights to obtain the cluster defect features corresponding to each defect cluster;

[0023] Step 132: Draw a virtual printed finished product diagram according to the current printing task, map each of the cluster defect features in the virtual printed finished product diagram to obtain several material defect features of the current printing task, generate a material defect feature set corresponding to the current printing task and display it.

[0024] In an implementable manner,

[0025] It further includes:

[0026] Obtain the indoor environment information of the 3D printing processing chamber;

[0027] When the indoor environment information meets the specified printing requirements, control the laser scanning array to perform printing work.

[0028] In an implementable manner,

[0029] The step 2 includes:

[0030] Step 21: Determine several printing layers to be printed of the 3D printed finished product according to the current printing task, and determine the printing contour corresponding to each printing layer to be printed, generate several printing guiding instructions to control the laser scanning array to perform real-time printing, and determine the current printing layer according to the real-time printing data of the laser scanning array;

[0031] Step 22: Determine the complete printing state of the current printing layer based on the current printing contour corresponding to the current printing layer, construct the real-time printing state of the current printing layer by using the real-time printing data, and determine the real-time printing progress of the current printing layer;

[0032] Step 23: When the real-time printing progress is 100% and the displayed printing state of the current printing layer is consistent with the complete printing state, determine that the current printing layer has completed the printing work, control the preset liquid lens to collect the complete planar image of the current printing layer and display it.

[0033] In an implementable manner,

[0034] The step 3 includes:

[0035] Step 31: Perform gray-scale enhancement on the printing contour included in the complete planar image to obtain the enhanced contour information of the current printing layer, perform straight-line fitting on the enhanced contour information in the complete planar image, and locate several contour key points in the printing contour according to the fitting result;

[0036] Step 32: Divide the printing contour into several contour regions, establish the regional contour features corresponding to each contour region based on the distribution of contour key points corresponding to each contour region, and respectively search for the relevant material defect features corresponding to each regional contour feature in the material defect feature set;

[0037] Step 33: Map each of the relevant material defect features in the corresponding contour region respectively to obtain the point coincidence ratio between each contour key point and the corresponding relevant material defect feature, and screen the target relevant material defects with a point coincidence ratio higher than the specified ratio as the current material defects corresponding to the contour region;

[0038] Step 34: Perform feature recognition on the complete plane image based on the point coincidence ratio corresponding to each current material defect to obtain the defect interference information of each current material defect on the printing contour, obtain several defect appearances of the complete plane image and the defect specifications corresponding to each defect appearance, and generate the defect information of the current printing layer.

[0039] In an implementable manner,

[0040] The said step 4 includes:

[0041] Step 41: Establish a 3D stereoscopic image according to several complete plane images corresponding to the 3D printed finished product, and respectively match each defect information with a corresponding stereoscopic image region based on the correspondence between the defect information and the complete plane image;

[0042] Step 42: Identify several printed parts included in the 3D stereoscopic image, determine the stereoscopic image region corresponding to each printed part, and respectively mark each defect information in the corresponding stereoscopic image region to obtain the part defect features corresponding to each printed part;

[0043] Step 43: Respectively mark each part defect feature in the 3D stereoscopic image to obtain the complete part information corresponding to each printed part, analyze the defect interference information between different printed parts in the 3D stereoscopic image, and establish the defect attribute corresponding to each printed part in combination with the part position corresponding to each printed part;

[0044] Step 44: Conduct an overall defect evaluation on the 3D printed finished product according to the defect attribute corresponding to each printed part, conduct an overall function evaluation on the 3D printed finished product according to the part function corresponding to each printed part, generate a defect report of the 3D printed finished product and display it.

[0045] In an implementable manner,

[0046] It further includes:

[0047] Screening defective 3D printed finished products that fail the overall defect evaluation or the overall function evaluation;

[0048] Respectively marking several defect attributes corresponding to the defective 3D printed finished products in the corresponding defective 3D stereoscopic images, generating a multi-dimensional defect map of the defective 3D printed finished products and displaying it.

[0049] The present invention provides a real-time defect detection system for selective laser melting 3D printing, including:

[0050] A defect preset module for retrieving a corresponding defect database based on the material attributes of the 3D printed finished product, identifying the defect characteristics corresponding to each defect data in the defect database, and obtaining a material defect characteristic set;

[0051] A synchronous supervision module for determining the image acquisition moment based on the real-time printing progress of the current printing layer by means of a laser scanning array, and obtaining a complete planar image of the current printing layer;

[0052] A defect identification module for identifying several current material defects included in the complete planar image by using the material defect characteristic set, respectively performing in-depth identification on each of the current material defects, and generating defect information of the current printing layer;

[0053] A report generation module for establishing a 3D stereoscopic image of the 3D printed finished product, identifying the defect attributes corresponding to each printed part in the corresponding 3D stereoscopic image by using the defect information, generating a defect report of the 3D printed finished product and displaying it.

[0054] The achievable beneficial effects of the above technical solutions are:

[0055] In order to solve the defects in the prior art, a method for real-time defect detection is constructed. Before the printing work is carried out, the corresponding defect database is screened according to the material attributes of the raw materials used in this time, so as to construct the material defect characteristic set of this printing. Then, after one layer of printing work is completed, its complete planar image is collected. By identifying the current material defects in the complete planar image and performing in-depth identification on them, the defect information of the current printing layer is determined. Finally, by constructing a 3D stereoscopic image, the defect attributes of each printed part are analyzed, so as to generate a defect report of the 3D printed finished product. In this way, real-time detection can be carried out during the printing process, the defects existing in the finished product are determined, and a defect report is generated for the demander to refer to. The demander can perform different treatments on the printed finished product according to actual needs. Various printing defects can be identified during the printing process, which is convenient for the manufacturer to timely discover production problems and deal with them, promoting the development of productivity.

[0056] Other features and advantages of the present invention will be described in the following specification, and in part will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained by the structure specifically pointed out in the written specification and the accompanying drawings.

[0057] The technical solution of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0058] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings:

[0059] Figure 1 is a schematic diagram of the working process of the real-time defect detection method for selective laser melting 3D printing in the embodiment of the present invention;

[0060] Figure 2 is a schematic diagram of the composition of the real-time defect detection system for selective laser melting 3D printing in the embodiment of the present invention. Detailed Embodiments

[0061] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0062] Embodiment 1

[0063] This embodiment provides a real-time defect detection method for selective laser melting 3D printing, as Figure 1 shown, including:

[0064] Step 1: Retrieve the corresponding defect database based on the material properties of the 3D printed finished product, identify the defect features corresponding to each defect data in the defect database, and obtain a set of material defect features;

[0065] Step 2: Determine the image acquisition moment based on the real-time printing progress of the current printing layer by the laser scanning array, and obtain a complete planar image of the current printing layer;

[0066] Step 3: Use the set of material defect features to identify several current material defects included in the complete planar image, and perform depth identification on each of the current material defects to generate defect information of the current printing layer;

[0067] Step 4: Establish a 3D stereoscopic image of the 3D printed finished product, use the defect information to identify the defect attributes corresponding to each printed part in the corresponding 3D stereoscopic image, generate a defect report of the 3D printed finished product and display it.

[0068] In this example, the material property represents the property of the raw material used during printing, generally a powdery raw material.

[0069] In this example, the defect database represents the data information of the possible defects that may occur after constructing a finished product using this raw material.

[0070] In this example, the material defect feature set represents the features of the possible defects that may occur after constructing a 3D printed finished product using this raw material.

[0071] In this example, the current printing layer represents the layer that is currently being 3D printed.

[0072] In this example, the image acquisition time is: the time corresponding to when the real-time printing progress of a current printing layer reaches 100%.

[0073] In this example, the complete planar image represents the result of collecting all the image information of the current printing layer.

[0074] In this example, the current material defect represents the defect existing in the complete planar image.

[0075] In this example, the printed part represents an individual part used to compose the 3D printed finished product.

[0076] In this example, the defect attribute represents the attribute of the defect presented by the printed part.

[0077] The working principle and beneficial effects of the above technical solution: To solve the defects in the prior art, a method for real-time defect detection is constructed. Before starting the printing work, the corresponding defect database is screened according to the material property of the raw material used in this time, so as to construct the material defect feature set for this printing. Then, after completing one layer of printing work, its complete planar image is collected. By identifying the current material defect in the complete planar image and performing in-depth identification on it, the defect information of the current printing layer is determined. Finally, by constructing a 3D stereoscopic image, the defect attributes of each printed part are analyzed, so as to generate a defect report of the 3D printed finished product. In this way, real-time detection can be carried out during the printing process to determine the defects existing in the finished product, and a defect report is generated for the requester to refer to. The requester can perform different treatments on the printed finished product according to actual needs. Various printing defects can be identified during the printing process, which is convenient for the manufacturer to timely discover production problems and handle them, promoting the development of productivity.

[0078] Embodiment 2

[0079] Based on Example 1, for the real-time defect detection method for selective laser melting 3D printing, Step 1 includes:

[0080] Step 11: Determine the printing raw material of the 3D printing finished product based on the current printing task. Based on the material properties of the printing raw material, search for the defect database corresponding to the material properties in the big data;

[0081] Step 12: Use the defect data to draw the defect image of the printing raw material, and determine the defect characteristics corresponding to each defect data;

[0082] Step 13: Perform clustering analysis on the defect characteristics to generate a material defect characteristic set corresponding to the current printing task and display it.

[0083] The working principle and beneficial effects of the above technical solution: By searching for the defect database of the printing raw material in the big data and then drawing the corresponding defect image to analyze the defect characteristics corresponding to each defect data, a material defect characteristic set for the current printing task is constructed. In this way, a highly referential and high-quality defect comparison set can be provided for the current printing work, facilitating subsequent defect identification.

[0084] Example 3

[0085] Based on Example 2, for the real-time defect detection method for selective laser melting 3D printing, Step 12 includes:

[0086] Step 121: Generate a flawless image of the printing raw material based on the material properties, and respectively obtain the data difference between each defect data and the flawless data corresponding to the flawless image;

[0087] Step 122: Use the data difference to perform corresponding defect adjustment training on the flawless image to obtain the defect image corresponding to each defect data;

[0088] Step 123: Respectively identify the image presentation characteristics corresponding to each defect image, and generate the defect characteristics corresponding to the defect data.

[0089] In this example, the flawless image represents an image of an item constructed without defects using the printing raw material, and the flawless image can be generated using AI technology;

[0090] In this example, the data difference represents different data segments between the defect data and the flawless data;

[0091] In this example, the defect adjustment training represents the process of adjusting the flawless data to be consistent with the defect data using the data difference;

[0092] In this example, the image presentation features represent the features related to the defects presented in the defective image.

[0093] The working principle and beneficial effects of the above technical solution: In order to better identify the defect features corresponding to the defect data, a defect-free image is constructed using material properties, and the defect-free image is subjected to defect adjustment training based on the data difference between the defect data and the defect-free data, obtaining the defective image corresponding to each type of defect data. By identifying the image presentation features corresponding to each defective image, the defect features of each type of defect data are determined. In this way, the defect features of multiple defect data can be analyzed simultaneously, improving the generation efficiency and quality of the defect features, and improving the accuracy of subsequent defect detection.

[0094] Example 4

[0095] Based on Example 2, for the real-time defect detection method for selective laser melting 3D printing, step 13 includes:

[0096] Step 131: Perform clustering analysis on the defect features to obtain several defect clusters, respectively identify the defect weights of each defect feature in the corresponding defect cluster, and recombine the corresponding defect features based on the defect weights to obtain the cluster defect features corresponding to each defect cluster;

[0097] Step 132: Draw a virtual printed finished product diagram according to the current printing task, respectively map each cluster defect feature onto the virtual printed finished product diagram to obtain several material defect features of the current printing task, generate a material defect feature set corresponding to the current printing task and display it.

[0098] In this example, the defect cluster represents the result of clustering the defect features, and a defect cluster contains several similar defect features;

[0099] In this example, the defect weight represents the proportion of a defect feature in the defect cluster;

[0100] In this example, the cluster defect feature represents the common feature among several defect features included in a defect cluster;

[0101] In this example, the virtual printed finished product diagram represents the image of the 3D printed finished product drawn in the virtual space.

[0102] Working principle and beneficial effects of the above technical solution: In order to improve the construction efficiency of the material defect feature set and reduce the influence of a single defect on the feature set, the defect features are first divided into several defect clusters by means of cluster analysis, and then the cluster defect features of each defect cluster are analyzed according to the weight of each defect feature in its corresponding defect cluster. The virtual printed finished product drawing is processed using the cluster defect features to determine several material defect features, and then the material defect feature set for this printing task is generated. In this way, not only can the defect features be classified, but also the preliminary identification of defects can be realized according to the common features between different defect features, improving the quality of subsequent defect detection.

[0103] Example 5

[0104] Based on Example 1, the real-time defect detection method for selective laser melting 3D printing further includes:

[0105] Obtain the indoor environment information of the 3D printing processing chamber;

[0106] When the indoor environment information meets the specified printing requirements, control the laser scanning array to perform printing work.

[0107] In this example, the specified printing requirements are one of the following environments: 1. Vacuum environment, 2. Filled with protective gas.

[0108] Working principle and beneficial effects of the above technical solution: The entire processing process is carried out in a processing chamber with vacuum pumping or gas protection to prevent the metal from reacting with other gases at high temperatures.

[0109] Example 6

[0110] Based on Example 1, in the real-time defect detection method for selective laser melting 3D printing, step 2 includes:

[0111] Step 21: Determine several printing layers to be printed of the 3D printed finished product according to this printing task, and determine the printing contour corresponding to each printing layer to be printed, generate several printing guiding instructions to control the laser scanning array for real-time printing, and determine the current printing layer according to the real-time printing data of the laser scanning array;

[0112] Step 22: Determine the complete printing state of the current printing layer based on the current printing contour corresponding to the current printing layer, construct the real-time printing state of the current printing layer using the real-time printing data, and determine the real-time printing progress of the current printing layer;

[0113] Step 23: When the real-time printing progress is 100% and the display printing state of the current printing layer is the same as the complete printing state, it is determined that the current printing layer has completed the printing work, and the preset liquid lens is controlled to collect and display the complete planar image of the current printing layer.

[0114] In this example, the layer to be printed means that multiple prints are required to complete a 3D printed product, and the printing surface corresponding to each print is a printing layer;

[0115] In this example, the contour to be printed means the contour generated during printing on a layer to be printed when completing a 3D printed product;

[0116] In this example, the printing guidance instruction means the instruction used to guide the laser scanning array for printing, and one layer to be printed corresponds to one printing guidance instruction;

[0117] In this example, the complete printing state means the state presented when all the contours to be printed in the current printing layer are printed;

[0118] In this example, the real-time printing state means the state presented by the current printing layer at the current moment;

[0119] In this example, the preset liquid lens is set in the printing processing chamber and is used to collect images.

[0120] The working principle and beneficial effects of the above technical solution: In order to perform effective defect detection and ensure the real-time nature of the detection results, first determine several layers to be printed for this printing task according to this printing task, as well as the contours to be printed corresponding to each layer to be printed, and then generate a printing guidance instruction to control the laser scanning array to perform the corresponding printing work. Furthermore, determine the real-time printing progress of the printing work according to the contour printing completion state of the current printing layer. After the current printing layer is printed, the preset liquid lens takes a picture of the current printing layer to obtain a complete planar image. In this way, both image acquisition can be completed, and image acquisition can be performed in a timely manner after printing, avoiding unnecessary damage to the printed product caused by long-term video monitoring, and performing corresponding detection on the basis of the quality of the printed product.

[0121] Embodiment 7

[0122] Based on Embodiment 1, the real-time defect detection method for selective laser melting 3D printing, Step 3 includes:

[0123] Step 31: Perform grayscale enhancement on the printing contour contained in the complete planar image to obtain the enhanced contour information of the current printing layer. Perform linear fitting on the enhanced contour information in the complete planar image, and locate a number of contour key points in the printing contour according to the fitting result;

[0124] Step 32: Divide the printing contour into several contour regions, establish the region contour features corresponding to each contour region based on the distribution of the contour key points corresponding to each contour region, and respectively search for the relevant material defect features corresponding to each region contour feature in the material defect feature set;

[0125] Step 33: Map each of the relevant material defect features onto the corresponding contour region respectively to obtain the point coincidence ratio between each contour key point and the corresponding relevant material defect feature, and screen out the target relevant material defects with a point coincidence ratio higher than the specified ratio as the current material defects corresponding to the contour region;

[0126] Step 34: Perform feature recognition on the complete planar image based on the point coincidence ratio corresponding to each current material defect to obtain the defect interference information of each current material defect on the printing contour, obtain several defect appearances of the complete planar image and the defect specifications corresponding to each defect appearance, and generate the defect information of the current printing layer.

[0127] In this example, the enhanced contour information represents the result of enhancing the contour contained in the current printing layer. The purpose of the enhancement is to: improve the contrast and obtain the detailed information in the contour;

[0128] In this example, the contour key point represents the intersection point between two or more straight lines;

[0129] In this example, the relevant material feature defect represents the material defect feature related to the region contour feature;

[0130] In this example, the coincidence ratio represents the ratio between the number of coincidences and the number of non - coincidences between the contour key point and the relevant material defect feature;

[0131] In this example, the specified ratio is 90%;

[0132] In this example, the defect interference information represents the interference caused by the current material defect to the printing contour;

[0133] In this example, the defect specification represents the specification size of the defect appearance;

[0134] In this example, the defect appearance represents the appearance presented by the defects contained in the complete planar image.

[0135] Working principle and beneficial effects of the above technical solution: By enhancing the grayscale of the printing contour on the complete planar image and performing linear fitting to determine several contour key points included in the printing contour, then dividing the printing contour into several contour regions, performing feature recognition on each contour region, and searching for relevant material defect features corresponding to each regional contour. Further, by analyzing the coincidence ratio between the relevant material defect features and the contour key points to determine the current material defect of the regional contour. Finally, analyzing the defect interference information of each current material defect on the printing contour to determine the defect appearance and its defect specifications contained in the complete planar image. Finally, the defect information of the current printing layer is determined. In this way, the defect appearance in the current printing layer can be uniformly recognized and processed, the position and its specifications of each defect appearance are determined, and an accurate defect information is obtained, providing strong data reference for the demand side.

[0136] Example 8

[0137] Based on Example 1, for the real-time defect detection method for selective laser melting 3D printing, step 4 includes:

[0138] Step 41: Establish a 3D stereoscopic image based on several complete planar images corresponding to the 3D printed finished product, and match each defect information with a corresponding stereoscopic image region based on the correspondence between the defect information and the complete planar image;

[0139] Step 42: Identify several printed parts included in the 3D stereoscopic image, determine the stereoscopic image region corresponding to each printed part, and mark each defect information in the corresponding stereoscopic image region to obtain the part defect feature corresponding to each printed part;

[0140] Step 43: Mark each part defect feature in the 3D stereoscopic image to obtain the complete part information corresponding to each printed part, analyze the defect interference information between different printed parts in the 3D stereoscopic image, and establish the defect attribute corresponding to each printed part in combination with the part position corresponding to each printed part;

[0141] Step 44: Perform an overall defect evaluation on the 3D printed finished product according to the defect attribute corresponding to each printed part, perform an overall function evaluation on the 3D printed finished product according to the part function corresponding to each printed part, generate a defect report of the 3D printed finished product and display it.

[0142] In this example, the 3D stereoscopic image refers to a three-dimensional image generated by combining several complete planar images corresponding to a 3D printed finished product in the layer order;

[0143] In this example, the three-dimensional image area represents the area of the 3D printed finished product corresponding to a defect information;

[0144] In this example, the part defect feature represents the feature of the defect presented on a printed part;

[0145] In this example, the part complete information represents the integrity of each position of the printed part;

[0146] In this example, the defect attribute represents the attribute of the defect presented by a printed part, such as: the attribute of virtual soldering, the attribute of missed soldering, etc.

[0147] The working principle and beneficial effects of the above technical solution: By using a complete planar image to construct a 3D stereoscopic image of the 3D printed finished product to process the defect information, determining the part defect features of each printed part, and then analyzing various information presented in the 3D stereoscopic image to determine the defect attributes of each printed part. Finally, the 3D printed finished product is evaluated multiple times to generate its defect report. In this way, the defects of the 3D printed finished product can be analyzed comprehensively and multi-angularly, improving the accuracy of defect capture and providing a well-founded defect report for the demander.

[0148] Example 9

[0149] Based on Example 8, the real-time defect detection method for selective laser melting 3D printing further includes:

[0150] Screening defective 3D printed finished products with unqualified overall defect evaluation or unqualified overall function evaluation;

[0151] Marking the respective defective defect attributes corresponding to the defective 3D printed finished product in the corresponding defective 3D stereoscopic image, generating a multi-dimensional defective map of the defective 3D printed finished product and displaying it.

[0152] The working principle and beneficial effects of the above technical solution: By generating an exploded view of the defective 3D printed finished product to show all its defects, it is convenient for the demander to understand the working mistakes of this printing and helps them with technical improvement.

[0153] Example 10

[0154] This example provides a real-time defect detection system for selective laser melting 3D printing, as Figure 2 shown, including:

[0155] A defect preset module for retrieving a corresponding defect database based on the material attributes of the 3D printed finished product, identifying the defect features corresponding to each defect data in the defect database, and obtaining a material defect feature set;

[0156] A synchronous monitoring module, which is used to determine the image acquisition moment based on the laser scanning array for the real-time printing progress of the current printing layer, and obtain the complete planar image of the current printing layer;

[0157] A defect recognition module, which is used to identify a number of current material defects included in the complete planar image by using the material defect feature set, and perform depth recognition on each of the current material defects respectively to generate the defect information of the current printing layer;

[0158] A report generation module, which is used to establish a 3D stereoscopic image of the 3D printed finished product, identify the defect attributes corresponding to each printed part in the corresponding 3D stereoscopic image by using the defect information, generate a defect report of the 3D printed finished product and display it.

[0159] In this example, the material property represents the property of the raw material used during printing, generally a powdery raw material;

[0160] In this example, the defect database represents the data information of the possible defects generated after constructing a finished product by using this raw material;

[0161] In this example, the material defect feature set represents the features of the possible defects generated after constructing a 3D printed finished product by using this raw material;

[0162] In this example, the current printing layer represents the layer that is currently undergoing 3D printing;

[0163] In this example, the image acquisition moment is: the moment corresponding to when the real-time printing progress of a current printing layer reaches 100%;

[0164] In this example, the complete planar image represents the result of collecting all the image information of the current printing layer;

[0165] In this example, the current material defect represents the defect existing in the complete planar image;

[0166] In this example, the printed part represents an individual part used to form a 3D printed finished product;

[0167] In this example, the defect attribute represents the attribute of the defect presented by the printed part.

[0168] Working principle and beneficial effects of the above technical solution: To address the deficiencies in the prior art, a method for real-time defect detection is constructed. Before starting the printing work, a corresponding defect database is screened according to the material properties of the raw materials used in this instance, thereby constructing a material defect feature set for this printing. Then, after completing one layer of printing work, a complete planar image is collected. By identifying the current material defects in the complete planar image and performing in-depth identification on them, the defect information of the current printing layer is determined. Finally, by constructing a 3D stereoscopic image, the defect attributes of each printed part are analyzed, thereby generating a defect report for the 3D printed finished product. In this way, real-time detection can be carried out during the printing process to determine the defects existing in the finished product and generate a defect report for the requester's reference. The requester can perform different treatments on the printed finished product according to actual needs, and various printing defects can be identified during the printing process, facilitating the manufacturer to promptly discover and handle production problems, and promoting the development of productivity.

[0169] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A real-time defect detection method for selective laser melting 3D printing, characterized in that: include: Step 1: Retrieve a corresponding defect database based on the material properties of the 3D printed product, identify the defect features corresponding to each defect data in the defect database, and obtain a material defect feature set; Step 2: determining the image acquisition time based on the real-time printing progress of the current printing layer by the laser scanning array, and obtaining a complete plane image of the current printing layer; Step 3: using the material defect feature set to identify a number of current material defects contained in the complete plane image, performing depth identification on each of the current material defects, and generating defect information of the current printing layer; Step 4: creating a 3D stereoscopic image of the 3D printed product, identifying defect attributes corresponding to each printed part in the corresponding 3D stereoscopic image using the defect information, generating a defect report of the 3D printed product and displaying it; The step 3 comprises: Step 31: grayscale enhancement is performed on the print contour contained in the complete plane image to obtain enhanced contour information of the current print layer, straight line fitting is performed on the enhanced contour information in the complete plane image, and a plurality of contour key points are located in the print contour according to the fitting result; Step 32: Divide the printed contour into a plurality of contour regions, establish a regional contour feature corresponding to each contour region based on the distribution of contour key points corresponding to each contour region, and search for relevant material defect features corresponding to each regional contour feature in the material defect feature set; Step 33: Map each of the relevant material defect features in the corresponding contour area, obtain the point overlap ratio between each contour key point and the corresponding relevant material defect feature, and select the target relevant material defects with a point overlap ratio higher than a specified ratio as the current material defects corresponding to the contour area; Step 34: Based on the point overlap ratio corresponding to each current material defect, feature recognition is performed on the complete plane image to obtain defect interference information of each current material defect on the printing contour, obtain several defect appearances of the complete plane image and defect specifications corresponding to each defect appearance, and generate defect information of the current printing layer.

2. The real-time defect detection method for selective laser melting 3D printing according to claim 1, characterized in that: The step 1 comprises: Step 11: Determine the printing raw material of the 3D printed product based on the current printing task, and search for a defect database corresponding to the material property in big data based on the material property of the printing raw material; Step 12: Draw a defect image of the printing raw material using the defect data, and determine defect features corresponding to each defect data; Step 13: Perform cluster analysis on the defect features to generate a material defect feature set corresponding to this printing task and display it.

3. The real-time defect detection method for selective laser melting 3D printing according to claim 2, characterized in that: The step 12 comprises: Step 121: generating a flawless image of the printing raw material based on the material properties, and obtaining a data difference between each defect data and the flawless data corresponding to the flawless image; Step 122: performing corresponding defect adjustment training on the flawless image using the data difference to obtain a defect image corresponding to each defect data; Step 123: Identify the image presentation features corresponding to each of the defective images respectively, and generate defect features corresponding to the defect data.

4. The real-time defect detection method for selective laser melting 3D printing according to claim 2, characterized in that: The step 13 comprises: Step 131: performing cluster analysis on the defect features to obtain a plurality of defect clusters, identifying the defect weight of each defect feature in the corresponding defect cluster, and reorganizing the corresponding defect features based on the defect weight to obtain a cluster defect feature corresponding to each defect cluster; Step 132: Draw a virtual print product map according to the current print task, map each cluster defect feature in the virtual print product map to obtain several material defect features of the current print task, generate a material defect feature set corresponding to the current print task and display it.

5. The real-time defect detection method for selective laser melting 3D printing according to claim 1, characterized in that: Also includes: Obtain the indoor environment information of the 3D printing processing room; When the indoor environment information meets the specified printing requirements, the laser scanning array is controlled to perform printing.

6. The real-time defect detection method for selective laser melting 3D printing according to claim 1, characterized in that: The step 2 comprises: Step 21: determining a number of layers to be printed of the 3D printed product according to the current printing task, and determining the contour to be printed corresponding to each of the layers to be printed, generating a number of printing guidance instructions to control the laser scanning array to perform real-time printing, and determining the current printing layer according to the real-time printing data of the laser scanning array; Step 22: determining the complete printing state of the current printing layer based on the current contour to be printed corresponding to the current printing layer, constructing the real-time printing state of the current printing layer using the real-time printing data, and determining the real-time printing progress of the current printing layer; Step 23: When the real-time printing progress is 100%, and the displayed printing status of the current printing layer is consistent with the complete printing status, it is determined that the current printing layer has completed printing, and the preset liquid lens is controlled to collect and display the complete plane image of the current printing layer.

7. The real-time defect detection method for selective laser melting 3D printing according to claim 1, characterized in that: The step 4 comprises: Step 41: establishing a 3D stereoscopic image according to a plurality of complete plane images corresponding to the 3D printed product, and matching a corresponding stereoscopic image area for each defect information based on the corresponding relationship between the defect information and the complete plane image; Step 42: identifying a plurality of printed parts contained in the 3D stereoscopic image, determining a stereoscopic image region corresponding to each of the printed parts, and marking each of the defect information in the corresponding stereoscopic image region to obtain a part defect feature corresponding to each of the printed parts; Step 43: Mark each of the part defect features in the 3D stereoscopic image to obtain complete part information corresponding to each of the printed parts, analyze defect interference information between different printed parts in the 3D stereoscopic image, and establish defect attributes corresponding to each of the printed parts in combination with the part position corresponding to each of the printed parts; Step 44: Perform an overall defect evaluation on the 3D printed product according to the defect attributes corresponding to each of the printed parts, perform an overall function evaluation on the 3D printed product according to the part functions corresponding to each of the printed parts, generate a defect report for the 3D printed product, and display it.

8. The real-time defect detection method for selective laser melting 3D printing according to claim 7, characterized in that: Also includes: Screening defective 3D printed products that fail the overall defect evaluation or the overall function evaluation; Several defect attributes corresponding to the defective 3D printed product are respectively marked in the corresponding 3D stereoscopic image, and a multi-dimensional defect map of the defective 3D printed product is generated and displayed.

9. A real-time defect detection system for selective laser melting 3D printing, characterized in that: include: A defect presetting module is used to retrieve a corresponding defect database based on the material properties of the 3D printed product, identify the defect features corresponding to each defect data in the defect database, and obtain a material defect feature set; A synchronous monitoring module, used to determine the image acquisition time based on the real-time printing progress of the current printing layer by the laser scanning array, and obtain a complete plane image of the current printing layer; A defect recognition module, used to use the material defect feature set to identify a plurality of current material defects contained in the complete plane image, perform depth recognition on each of the current material defects, and generate defect information of the current printing layer; a report generation module, configured to create a 3D stereoscopic image of the 3D printed product, identify defect attributes corresponding to each printed part in the corresponding 3D stereoscopic image using the defect information, generate a defect report of the 3D printed product and display it; The process in which the defect recognition module uses the material defect feature set to recognize a plurality of current material defects contained in the complete plane image, performs depth recognition on each of the current material defects, and generates defect information of the current printing layer includes: Performing grayscale enhancement on the print contour contained in the complete plane image to obtain enhanced contour information of the current print layer, performing straight line fitting on the enhanced contour information in the complete plane image, and locating a plurality of contour key points in the print contour according to the fitting result; Divide the printed contour into a plurality of contour regions, establish a regional contour feature corresponding to each contour region based on the distribution of contour key points corresponding to each contour region, and search for relevant material defect features corresponding to each regional contour feature in the material defect feature set; Mapping each of the related material defect features in the corresponding contour area respectively, obtaining the point overlap ratio between each of the contour key points and the corresponding related material defect feature, and screening target related material defects with a point overlap ratio higher than a specified ratio as current material defects corresponding to the contour area; Based on the point overlap ratio corresponding to each of the current material defects, feature recognition is performed on the complete plane image to obtain defect interference information of each of the current material defects on the printing contour, and several defect appearances of the complete plane image and defect specifications corresponding to each of the defect appearances are obtained to generate defect information of the current printing layer.

Images