A method, device, equipment and computer storage medium for checking powder feeding quality

Abstract

Embodiments of the present application disclose a method, device and equipment for inspecting powder feeding quality and a computer storage medium. The method comprises: collecting profile data of a forming area in real time in a laser stereoscopic forming process; determining an abnormal position in the forming area according to a set judgment condition based on the profile data of the forming area; wherein the abnormal position in the forming area is used to represent a powder feeding defect position.

Description

Technical Field

[0001] The present invention relates to the field of additive manufacturing technology, and in particular to a method, apparatus, equipment and computer storage medium for inspecting powder feeding quality. Background Technology

[0002] Additive manufacturing technology—Laser Solid Forming (LSF)—is a next-generation parts processing technology. Its principle combines automated powder feeding, laser cladding, and rapid prototyping technologies in a bottom-up rapid prototyping process. It primarily utilizes the thermal effect of a laser beam to completely melt metal powder, which then cools and solidifies to form a shape. This technology can quickly, directly, and accurately transform design ideas into functional physical models. The process of laser solid forming of parts includes: 1) 3D modeling; 2) slicing and layering; 3) laser scanning and sintering of metal powder material; 4) layer-by-layer accumulation until the part is formed.

[0003] The existing LSF equipment mainly consists of a laser, powder nozzle, powder feeder, and forming chamber. When processing parts using LSF equipment, the powder feeding accuracy of the powder feeder directly affects the forming quality of the parts. For example, during the printing process, issues such as duct blockage leading to insufficient powder, problems with the powder feeding head causing uneven powder feeding, and uneven powder quantity due to the special path at the "cross" intersection can occur. These abnormalities accumulate and can easily cause parts to collapse and be damaged. Even if the parts are eventually successfully processed, they will have problems such as low precision and many internal defects, failing to meet customer quality requirements. The existing LSF equipment uses a coaxial powder feeding method with open-loop control during the laser stereolithography process. When powder feeding defects occur during printing, there is no warning, requiring manual intervention to handle the powder feeding defects. However, in daily production, even with a large amount of manpower invested, there are still cases where parts are damaged due to powder feeding defects, making it impossible to guarantee the forming quality of the parts. Summary of the Invention

[0004] In view of this, the embodiments of the present invention aim to provide a method, apparatus, device, and computer storage medium for inspecting powder feeding quality; capable of timely and accurate early warning of defects in the powder feeder, and performing process compensation for the laser stereoforming process at the location of powder feeding defects, thus solving the problem of lack of closed-loop control in the laser stereoforming process of existing powder feeding methods.

[0005] The technical solution of this invention is implemented as follows:

[0006] In a first aspect, embodiments of the present invention provide a method for inspecting powder feeding quality, the method comprising:

[0007] During the laser stereolithography process, the contour data of the forming area is acquired in real time;

[0008] Based on the contour data of the forming area, abnormal locations in the forming area are determined according to the set judgment conditions; wherein, the abnormal locations in the forming area are used to characterize the locations of powder feeding defects.

[0009] Secondly, embodiments of the present invention provide an apparatus for inspecting powder delivery quality, the apparatus comprising: a collection part and a determination part; wherein,

[0010] The acquisition unit is configured to acquire contour data of the forming area in real time during the laser stereolithography process;

[0011] The determining part is configured to determine the abnormal position in the forming area based on the contour data of the forming area and according to the set judgment conditions; wherein, the abnormal position in the forming area is used to characterize the position of powder feeding defect.

[0012] Thirdly, embodiments of the present invention provide a device for inspecting powder feeding quality, the device comprising: a data acquisition module, a memory, and a processor disposed on one side of a laser cladding head; wherein...

[0013] The laser contour scanner is used to collect contour data of the forming area in real time during the laser stereolithography process.

[0014] The memory is used to store computer programs that can run on the processor;

[0015] The processor is configured to perform the following steps when running the computer program:

[0016] Based on the contour data of the forming area, abnormal locations in the forming area are determined according to the set judgment conditions; wherein, the abnormal locations in the forming area are used to characterize the locations of powder feeding defects.

[0017] Fourthly, embodiments of the present invention provide a computer storage medium storing a program for inspecting toner feeding quality, wherein the program for inspecting toner feeding quality, when executed by at least one processor, implements the steps of the method for inspecting toner feeding quality described in the first aspect.

[0018] This invention provides a method, apparatus, device, and computer storage medium for inspecting powder feeding quality. The method primarily involves real-time acquisition of contour data of the forming area during laser stereolithography; and, based on this contour data, determining abnormal locations within the forming area according to predefined criteria. This method enables timely and accurate early warning of powder feeding defects in the powder feeder, improving the yield of laser stereolithographic parts and saving process costs. Attached Figure Description

[0019] Figure 1 A schematic diagram of a laser stereolithography (LSF) device provided in an embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram illustrating anomalies in existing laser stereolithography parts provided in an embodiment of the present invention.

[0021] Figure 3 This is a schematic flowchart of a method for inspecting powder feeding quality provided in an embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of the contour image of the forming area provided in an embodiment of the present invention;

[0023] Figure 5 This is a schematic diagram of a local contour image before denoising processing, provided in an embodiment of the present invention.

[0024] Figure 6 This is a schematic diagram of a local contour image after denoising processing, provided in an embodiment of the present invention.

[0025] Figure 7 This invention provides a contour image of a shaped region generated based on collected contour data.

[0026] Figure 8 A schematic diagram of a binarized image converted from a contour image provided in an embodiment of the present invention;

[0027] Figure 9 A schematic diagram of the filtered contour image provided in an embodiment of the present invention;

[0028] Figure 10 This is a schematic diagram of the theoretical segmentation image provided in an embodiment of the present invention;

[0029] Figure 11 This is a schematic diagram of the extracted Region of Interest (ROI) provided in an embodiment of the present invention;

[0030] Figure 12 This is a schematic diagram of the second centerline image obtained after interpolation, provided in an embodiment of the present invention.

[0031] Figure 13 A schematic diagram of the process steps for detecting powder feeding quality provided in an embodiment of the present invention;

[0032] Figure 14 A schematic diagram of a device for inspecting powder feeding quality provided in an embodiment of the present invention;

[0033] Figure 15 A schematic diagram of another device for inspecting powder feeding quality provided in an embodiment of the present invention;

[0034] Figure 16 A schematic diagram of the specific hardware structure of the computing device provided in an embodiment of the present invention. Detailed Implementation

[0035] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0036] The LSF device 1 used in this embodiment of the invention is as follows: Figure 1 As shown, the LSF device 1 mainly includes a laser 101, a powder nozzle 102, a powder feeder 103, a forming chamber 104, a reflective focusing mirror 105, a substrate 106, a CNC system 107, a water-cooled machine tool table 108, a purification system 109, a water-cooling system 110, and a lens 111. It should be noted that the powder nozzle 102, the reflective focusing mirror 105, the substrate 106, the water-cooled machine tool table 108, and the lens 111 are all placed in the forming chamber 104. The system includes a water-cooled machine table 108 for fixing the substrate 106 and performing reciprocating linear motion; a CNC system 107 for controlling the two-dimensional scanning motion of the powder nozzle 102 and the longitudinal lifting motion of the water-cooled machine table 108; a laser 101 for generating a laser beam; a reflecting focusing mirror 105 for focusing the laser beam and irradiating it onto the substrate 106 through a lens 111 to form a molten metal pool; a powder feeder 103 for collecting metal powder through the powder nozzle 102 into the molten pool formed by the laser focal spot; a forming chamber 104 filled with argon gas; a purification system 109 for reducing the oxygen content in the forming chamber 104; and a water-cooling system 110 for cooling the laser 101 and the water-cooled laser table 108. The reflecting focusing mirror 105 and the lens 111 together constitute the laser cladding head 112.

[0037] Specifically, the process of laser stereolithography of parts using the LSF device 1 is as follows: First, the CAD three-dimensional model of the part is sliced ​​using 3D printing slicing software to obtain the layered scanning data of the part; Second, the CNC system 107 loads the layered scanning data of the part and simultaneously controls the movement of the water-cooled machine tool table 108 and the switching of the laser 101 and the powder feeder 102. While the laser beam moves with the water-cooled machine tool table 108, it melts the metal powder delivered by the powder feeder 102 through the powder nozzle 103. The molten metal is deposited on the substrate 106, and the molten metal is accumulated layer by layer until the entire part is formed.

[0038] It should be noted that the LSF equipment 1 described above uses a coaxial powder feeding method. During the part forming process, defects may occur in the powder feeder 103, resulting in abnormal positions in the laser-formed parts. Specifically, for example... Figure 2As shown in the black rectangle, the current LSF device 1 lacks an early warning system when a powder feeding defect occurs, requiring manual intervention to resolve the powder feeding defect in the powder feeder 103. Therefore, this invention provides a method for inspecting powder feeding quality, which can be applied to... Figure 1 The LSF device 1 shown is specifically as follows: Figure 3 As shown, it includes:

[0039] S301. During the laser stereolithography process, the contour data of the forming area is collected in real time;

[0040] S302. Based on the contour data of the forming area, determine the abnormal position in the forming area according to the set judgment conditions; wherein, the abnormal position in the forming area is used to characterize the position of powder feeding defect.

[0041] like Figure 1 As shown, in this embodiment of the invention, a data acquisition module 113 is provided on one side of the laser cladding head 112. For example, the data acquisition module 113 can be a laser scanning profiler, a point laser rangefinder, or a ranging sensor, etc., used to acquire the contour data of the forming area of ​​the laser-formed part on the substrate 106 in real time. It should be noted that in this embodiment of the invention, the data acquisition module 113 can acquire a segment of the contour data of the entire forming area, or it can acquire the contour data of the entire forming area. In this embodiment of the invention, both the contour data of a segment of the forming area and the contour data of the entire forming area are referred to as "contour data of the forming area".

[0042] It should be noted that, in the embodiments of the present invention, the aforementioned contour data are all collected based on a Cartesian coordinate system. It should be understood that, as Figure 1 As shown, the origin O of the Cartesian coordinate system is the vertex of the upper surface of the substrate 106. The X-axis extends along the length of the substrate 106, the Y-axis extends along the width of the substrate 106, and the Z-axis extends along the height of the substrate 106.

[0043] It should be noted that during the laser stereolithography process, the scanning light of the data acquisition module 113 moves along with the focal point of the laser cladding head 112; preferably, the focal point of the laser cladding head 112 coincides with the scanning light of the data acquisition module 113.

[0044] exist Figure 3 In the illustrated technical solution, contour data of the forming area is acquired in real time during the laser stereoforming process; and based on the acquired contour data, abnormal positions in the forming area are determined according to set judgment conditions. This method enables timely and accurate early warning of powder feeding defects in the powder feeder 103, improving the yield of laser stereoforming parts and saving process costs.

[0045] As some possible implementation methods, the real-time acquisition of contour data of the forming area during the laser stereolithography process includes:

[0046] During the laser stereolithography process, data from N collection points in the forming area are acquired in real time as contour data.

[0047] Specifically, during the laser stereolithography process, the contour data of the forming area acquired in real time by the data acquisition module 113 includes N acquisition point data, where the coordinates of the kth acquisition point are (X... k Y k Z k ), 1≤k≤N.

[0048] As some possible implementations, the abnormal locations in the forming region are determined based on the contour data of the forming region and according to set judgment conditions; wherein, the abnormal locations in the forming region are used to characterize the locations of powder feeding defects, including:

[0049] Fit the contour image of the forming region based on the contour data, and extract the first centerline image from the contour image;

[0050] Interpolate the first centerline image to obtain a continuously distributed second centerline image;

[0051] By comparing the second centerline image with the theoretical sliced ​​image, the abnormal locations in the forming region are determined; wherein, the abnormal locations in the forming region are used to characterize the locations of powder feeding defects.

[0052] Specifically, such as Figure 4 As shown, the aforementioned contour image is a single-channel image with bright stripes against a dark background. Therefore, the contour data of the aforementioned formed area is the coordinate data of each point on the contour line of the bright stripes in the single-channel image acquired in real time.

[0053] It should be understood that in this embodiment of the invention, the contour images are all located in the XOZ plane. It can be understood that the pixel coordinate data on the contour image are the orthographic projection coordinates of the corresponding acquisition point coordinates in the XOZ plane.

[0054] Optionally, due to the relatively harsh industrial environment, the generated contour image may contain some noise. Therefore, in the actual implementation process, it is necessary to denoise the contour image to ensure the clarity of the contour image and the preservation of contour image boundary data while suppressing salt-and-pepper noise and speckle noise. Specifically, median filters, mean filters, Gaussian filters, or bilateral filters can be used to denoise the contour image. In this embodiment of the invention, a median filter is preferably used to denoise the contour image. The local contour image before denoising is shown below. Figure 5 As shown, the local contour image after denoising is as follows: Figure 6 As shown, the clarity of the contour image is significantly increased after denoising, and the boundary data of the local contour image is not lost.

[0055] Optionally, to further remove interference information from the contour image and improve subsequent detection accuracy and efficiency, feature filtering of the contour image can be performed using area feature filtering, roundness feature filtering, convexity feature filtering, or inertia rate feature filtering. Of course, feature filtering of contour images is essentially a denoising process, used to remove potential interference information from the contour image. Simultaneously, to improve the processing speed for large amounts of data during contour image feature filtering, threshold segmentation can be used beforehand to convert the contour image into a binary image to distinguish between foreground and background. For example, such as... Figure 7 To generate the contour image, a thresholding method is used to convert the contour image into a binary image, as shown below. Figure 8 As shown, the final contour image obtained after area feature filtering is as follows: Figure 9 As shown.

[0056] Understandably, since the laser beam stripes of the data acquisition module 113 have a certain width, the contour lines in the acquired contour image also have a certain width. In this embodiment of the invention, the theoretically sliced ​​image obtained based on the laser stereoforming path and parameters, such as... Figure 10 As shown, the theoretically segmented image is a straight line. Therefore, to facilitate comparison with the theoretically segmented image for anomaly detection, it is necessary to extract the center line of the contour lines in the contour image. In this embodiment of the invention, the method for extracting the center line of the contour lines in the contour image can be a centroid-based skeleton thinning algorithm. Specifically, this involves removing some data points from the acquired contour image through layer-by-layer stripping, while still maintaining the original shape of the contour lines. Of course, the extraction of the center line of the contour lines in the contour image can also be achieved using the extreme value method or the gray-scale centroid method; this embodiment of the invention does not specifically limit this approach.

[0057] For example, fitting a contour image of the formed region based on the contour data and extracting a first centerline image from the contour image includes:

[0058] Fit the contour image of the formed area based on the contour data, and obtain the region of interest (ROI) in the contour image;

[0059] Based on the region of interest (ROI), the first centerline image is extracted from the ROI.

[0060] It should be noted that, in order to reduce the amount of pixel data that needs to be processed subsequently and further improve the processing efficiency of the contour image, the Region of Interest (ROI) in the contour image can be further extracted in the actual implementation process. In this embodiment of the invention, the ROI in the contour image represents the smallest bounding rectangle corresponding to the N pixels contained in the contour image, that is, the smallest bounding rectangle corresponding to the contour lines in the contour image, such as... Figure 4 The white dashed rectangle is shown in the image. Specifically, the location of the ROI is determined using column projection or row projection of the contour image. The ROI in the final contour image is shown below. Figure 11 As shown, this method of extracting ROI can reduce the amount of pixel data. For example, by extracting ROI in the contour image, the amount of pixel data to be processed can be reduced from 1024×768 to 78×768, which is 1 / 13 of the original.

[0061] Understandably, the contour lines in a ROI also have a certain width. Therefore, to facilitate comparison with the theoretically segmented image for anomaly detection, it is necessary to extract... Figure 11 The center line of the contour lines in the ROI shown. Of course, the center line of the contour lines in the ROI can also be extracted using centroid-based skeleton thinning algorithms, extremum methods, or grayscale centroid methods.

[0062] It should be noted that, in the embodiments of the present invention, the image containing the center line of the contour line in the contour image or the image containing the center line of the contour line in the ROI is collectively referred to as the "first center line image".

[0063] Furthermore, since the extracted first centerline image may be discontinuous, to ensure its continuity, this embodiment employs a cubic spline interpolation algorithm to interpolate the first centerline image. Of course, the nearest neighbor method or bilinear interpolation can also be used for interpolation of the first centerline image; this embodiment does not specifically limit the method. The second centerline image obtained after interpolating the first centerline image is as follows: Figure 12 As shown.

[0064] For example, determining the abnormal location in the forming region by comparing the second centerline image with the theoretical dicing image includes:

[0065] Within the same XOZ plane, select the first pixel point (X) on the second centerline image. k Z k1 ) and the second pixel point (X) on the theoretically segmented image k Z k2And obtain the first height difference ΔZ1 = |Z_i| between the first pixel and the second pixel. k2 -Z k1 |;where 1≤k≤N;

[0066] When the first height difference ΔZ1 is less than the set first threshold, it is determined that there is no abnormality at the position corresponding to the first pixel in the second center image.

[0067] When the first height difference ΔZ1 is greater than or equal to the set first threshold, it is determined that there is an anomaly at the position corresponding to the first pixel in the second center image.

[0068] Specifically, in order to obtain the exact location of the abnormal position in the forming region, in this embodiment of the invention, the second centerline image and the theoretical segmentation image are placed in the same XOZ plane, in which the same abscissa X can be calculated. k The first height difference corresponding to the vertical coordinates is ΔZ1. By comparing the relationship between the first height difference ΔZ1 and a set first threshold, the abnormal image corresponding to the first pixel position in the second center image is determined. Figure 12 The location is at the position of the white dashed rectangle in the image.

[0069] Based on the examples above, detecting powder delivery quality can include, for example: Figure 13 The process steps shown are as follows:

[0070] S1301. Obtain the contour data of the forming area and fit it to obtain the contour image of the forming area;

[0071] S1302. Denoise the contour image of the formed area;

[0072] S1303. The contour image is converted into a binary image using the threshold segmentation method;

[0073] S1304. Filter the segmented contour image;

[0074] S1305. Extract the region of interest (ROI) from the filtered contour image;

[0075] S1306. Extract the center line of the contour image or the contour line in the ROI using the centroid-based skeleton thinning method to form the first center line image.

[0076] S1307. The first center image is interpolated using cubic spline interpolation to obtain the second centerline image;

[0077] S1308. Compare the second centerline image with the theoretical dicing image to determine the location of anomalies in the forming region.

[0078] Following the above example, as some possible implementations, the abnormal locations in the forming region are determined based on the contour data of the forming region and according to set judgment conditions; wherein, the abnormal locations in the forming region are used to characterize the locations of powder feeding defects, including:

[0079] Set within the same XOZ plane, based on the region of interest (ROI), by sequentially comparing adjacent first pixels (X) on the contour lines of the second central image. k Z k ) and the third pixel (X) k+1 Z k+1 ), obtain the second height difference ΔZ2 = |Z| between the first pixel and the third pixel. k+1 -Z k |;where 1≤k≤N;

[0080] Based on the second height difference ΔZ2, the abnormal location in the forming region is determined; wherein, the abnormal location in the forming region is used to characterize the location of powder feeding defects.

[0081] For example, determining the abnormal location in the forming region based on the second height difference ΔZ2 includes:

[0082] When the second height difference ΔZ2 is less than the set second threshold, it is determined that there is no abnormality in the second center image;

[0083] When the second height difference ΔZ2 is greater than or equal to the set second threshold, it is determined that there is an anomaly in the second center image.

[0084] On the other hand, abnormal locations can also be determined solely through the interpolated second center image without needing to refer to the theoretically segmented image. Specifically, in the XOZ plane, the second height difference ΔZ2 between adjacent first and third pixels in the second center line image can be calculated sequentially. After the sequential calculations are completed, if ΔZ2 is greater than or equal to a set second threshold, it indicates that the height of the forming plane corresponding to the adjacent first and third pixels has changed significantly, and the forming plane has protrusions or depressions. Therefore, there may be an abnormal location in the forming area, meaning there is a powder feeding defect at this location. If ΔZ2 is less than the set second threshold, it indicates that the height of the forming plane corresponding to the adjacent first and third pixels has not changed significantly, and it can be considered that there is no abnormal location in the forming area, meaning there is no powder feeding defect at this location. Specifically, in the specific implementation of this invention, during the sequential calculation of ΔZ2, when ΔZ2′ is greater than or equal to the set second threshold, the third pixel participating in the calculation of ΔZ2′ can be taken as the starting point of the abnormal location, and when ΔZ2″ is less than the set second threshold, the first pixel participating in the calculation of ΔZ2″ can be taken as the ending point of the abnormal location. Therefore, it can be understood that the abnormal position in the forming region is the area between the first pixel point involved in the calculation of ΔZ2″ and the third pixel point involved in the calculation of ΔZ2′.

[0085] As some possible implementations, the abnormal locations in the forming region are determined based on the contour data of the forming region and according to set judgment conditions; wherein, the abnormal locations in the forming region are used to characterize the locations of powder feeding defects, including:

[0086] By sequentially comparing adjacent first acquisition points (X) in the contour data k Y k Z k ) and the second acquisition point (X) k+1 Y k+1 Z k+1 ), obtain the third height difference ΔZ3 = |Z_0.05| ... k+1 -Z k |;where 1≤k≤N;

[0087] The abnormal location in the forming region is determined based on the third height difference ΔZ3; wherein, the abnormal location in the forming region is used to characterize the location of powder feeding defects.

[0088] Alternatively, without generating a contour image or a second centerline image, the adjacent first acquisition points (X) in the contour data acquired by the data acquisition module 113 can be calculated sequentially. n Y n Z n ) and the second acquisition point (X)n+1 Y n+1 Z n+1 ), to obtain the third height difference ΔZ3=|Z n+1 -Z n When the calculations are completed sequentially, if the third height difference ΔZ3 is greater than or equal to the set third threshold, it indicates that the height of the forming plane corresponding to the adjacent first and second sampling points has changed significantly, and the forming plane has protrusions or depressions, possibly indicating an abnormal position, meaning there is a powder feeding defect at this position. If the third height difference ΔZ3 is less than the set second threshold, it indicates that the height of the forming plane corresponding to the adjacent first and second sampling points has not changed significantly, and it can be considered that there is no abnormal position, meaning there is no powder feeding defect at this position. Specifically, in the specific implementation of this invention, during the sequential calculation of ΔZ3, when ΔZ3′ is greater than or equal to the set third threshold, the second sampling point involved in calculating ΔZ3′ can be taken as the starting point of the abnormal position, and when ΔZ3″ is less than the set second threshold, the first sampling point involved in calculating ΔZ3″ can be taken as the ending point of the abnormal position. Therefore, it can be understood that the abnormal position in the forming area is the area between the second sampling point involved in calculating ΔZ3″ and the first sampling point involved in calculating ΔZ3′.

[0089] As some possible implementations, the method further includes:

[0090] After determining the location of the powder feeding defect, when the laser cladding head moves to the location of the powder feeding defect, the power of the laser or the movement speed of the laser cladding head is adjusted for process compensation.

[0091] Understandably, once the abnormal powder feeding location is determined, a warning can be issued to the user or compensation measures can be taken based on the obtained abnormal location. For example, when the laser cladding head 112 moves to the abnormal location again, the power of the laser 101 or the movement speed of the laser cladding head 112 can be adjusted to perform process compensation, thereby realizing closed-loop control of the powder feeding equipment in the laser stereolithography process.

[0092] It should be noted that the method for detecting powder feeding quality described in the aforementioned technical solution can also be applied to detecting wire feeding quality during arc welding. Specifically, the process of arc welding using metal welding wire involves feeding a metal welding wire specifically designed for part forming directly into the molten pool formed by an electric arc or argon arc through a wire feeding mechanism. The wire melts and solidifies together with the base material of the part to form an arc weld cladding layer. Therefore, it can be understood that during arc welding, the contour data of the arc weld cladding layer can be collected in real time by the data acquisition module 113. Based on the contour data of the arc weld cladding layer and according to the set judgment conditions, abnormal locations within the arc weld cladding layer can be determined.

[0093] Based on the same inventive concept as the aforementioned technical solutions, the apparatus 140 for inspecting powder feeding quality provided in this embodiment of the invention, such as... Figure 14 As shown, the device 140 includes: a data acquisition section 1401 and a determination section 1402; wherein,

[0094] The acquisition unit 1401 is configured to acquire contour data of the forming area in real time during the laser stereolithography process;

[0095] The determining part 1402 is configured to determine abnormal positions in the forming region based on the contour data of the forming region and according to set judgment conditions; wherein, the abnormal positions in the forming region are used to characterize the powder feeding defect positions.

[0096] For example, the acquisition section 1401 is configured as follows:

[0097] During the laser stereolithography process, data from N collection points in the forming area are acquired in real time as contour data.

[0098] For example, the determining portion 1402 is configured as follows:

[0099] Fit the contour image of the forming region based on the contour data, and extract the first centerline image from the contour image;

[0100] Interpolate the first centerline image to obtain a continuously distributed second centerline image;

[0101] By comparing the second centerline image with the theoretical sliced ​​image, the abnormal locations in the forming region are determined; wherein, the abnormal locations in the forming region are used to characterize the locations of powder feeding defects.

[0102] For example, the determining portion 1402 is configured as follows:

[0103] Fit the contour image of the shaped region based on the contour data to obtain the region of interest (ROI) in the contour image;

[0104] Based on the region of interest (ROI), the first centerline image is extracted from the ROI.

[0105] For example, the determining portion 1402 is configured as follows:

[0106] Within the same XOZ plane, select the first pixel point (X) on the second centerline image. k Z k1 ) and the second pixel point (X) on the theoretically segmented image k Z k2And obtain the first height difference ΔZ1 = |Z_i| between the first pixel and the second pixel. k2 -Z k1 |;where 1≤k≤N;

[0107] When the first height difference ΔZ1 is less than the set first threshold, it is determined that there is no abnormality at the position corresponding to the first pixel in the second center image.

[0108] When the first height difference ΔZ1 is greater than or equal to the set first threshold, it is determined that there is an anomaly at the position corresponding to the first pixel in the second center image.

[0109] For example, the determining portion 1402 is further configured to:

[0110] Set within the same XOZ plane, based on the region of interest (ROI), by sequentially comparing adjacent first pixels (X) on the contour lines of the second central image. k Z k ) and the third pixel (X) k+1 Z k+1 ), obtain the second height difference ΔZ2 = |Z| between the first pixel and the third pixel. k+1 -Z k |;where 1≤k≤N;

[0111] Based on the second height difference ΔZ2, the abnormal location in the forming region is determined; wherein, the abnormal location in the forming region is used to characterize the location of powder feeding defects.

[0112] For example, the determining portion 1402 is further configured to:

[0113] When the second height difference ΔZ2 is less than the set second threshold, it is determined that there is no abnormality in the second center image;

[0114] When the second height difference ΔZ2 is greater than or equal to the set second threshold, it is determined that there is an anomaly in the second center image.

[0115] For example, the determining portion 1402 is further configured to:

[0116] By sequentially comparing adjacent first acquisition points (X) in the contour data k Y k Z k ) and the second acquisition point (X) k+1 Y k+1 Z k+1 ), obtain the third height difference ΔZ3 = |Z_0.05| ... k+1 -Z k|;where 1≤k≤N;

[0117] The abnormal location in the forming region is determined based on the third height difference ΔZ3; wherein, the abnormal location in the forming region is used to characterize the location of powder feeding defects.

[0118] For example, see Figure 15 The device 140 further includes:

[0119] The adjustment part 1403 is configured to, after determining the location of the powder feeding defect, adjust the power of the laser or the movement speed of the laser cladding head to perform process compensation when the laser cladding head moves to the location of the powder feeding defect.

[0120] Understandably, in this embodiment, "part" can be a part of a circuit, a part of a processor, a part of a program or software, etc., or it can be a unit, a module, or a non-modular one.

[0121] Furthermore, in this embodiment, the components can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional module.

[0122] If the integrated unit is implemented as a software functional module and not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the method described in this embodiment. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] Therefore, this embodiment provides a computer storage medium storing a program for inspecting toner feeding quality. When the program for inspecting toner feeding quality is executed by at least one processor, it implements the steps of the method for inspecting toner feeding quality described in the above technical solution.

[0124] Based on the aforementioned device 140 for inspecting powder feeding quality and the computer storage medium, see [link / reference]. Figure 16This illustrates the specific hardware structure of a computing device 160 provided in an embodiment of the present invention, capable of implementing the above-described apparatus 140 for inspecting powder feeding quality. This computing device 160 can be applied to... Figure 1 In the LSF device 1 shown, the computing device 160 may include: a data acquisition module 113, a memory 1601, and a processor 1602 disposed on one side of the laser cladding head 112; the various components are coupled together via a bus system 1603. It is understood that the bus system 1603 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 1603 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 16 The general designated all buses as Bus System 1603. Among them,

[0125] The data acquisition module 113 is used to acquire contour data of the forming area in real time during the laser stereolithography process;

[0126] The memory 1601 is used to store computer programs that can run on the processor;

[0127] The processor 1602 is configured to perform the following steps when running the computer program:

[0128] Based on the contour data of the forming area, abnormal locations in the forming area are determined according to the set judgment conditions; wherein, the abnormal locations in the forming area are used to characterize the locations of powder feeding defects.

[0129] It is understood that the memory 1601 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 1601 of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0130] The processor 1602 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above methods can be completed by the integrated logic circuitry in the hardware of the processor 1602 or by software instructions. The processor 1602 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 1601. Processor 1602 reads the information in memory 1601 and, in conjunction with its hardware, completes the steps of the above method.

[0131] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0132] For software implementation, the techniques described herein can be achieved through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented within the processor or externally.

[0133] Specifically, the processor 1602 is also configured to execute the steps of the method for checking powder feeding quality described in the aforementioned technical solution when running the computer program, which will not be repeated here.

[0134] It should be noted that the technical solutions described in the embodiments of the present invention can be combined arbitrarily without conflict.

[0135] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method of verifying the quality of a powder feed, characterized in that The method includes: During the laser stereolithography process, the contour data of the forming area is acquired in real time; Based on the contour data, abnormal locations in the forming area are determined according to the set judgment conditions; wherein, the abnormal locations are used to characterize the locations of powder feeding defects. After determining the location of the powder feeding defect, when the laser cladding head moves to the location of the powder feeding defect, the power of the laser or the movement speed of the laser cladding head is adjusted for process compensation. The step of determining abnormal locations in the forming area based on the contour data and according to set judgment conditions includes: Fit the contour image of the shaped region based on the contour data to obtain the region of interest in the contour image; Extract the first centerline image from the region of interest; Interpolate the first centerline image to obtain a continuously distributed second centerline image; Within the same XOZ plane, based on the region of interest, the second height difference between the first and third pixels is obtained by sequentially comparing the first and third pixels on the contour lines in the second centerline image. The location of the anomaly is determined based on the second height difference.

2. The method for inspecting powder feeding quality according to claim 1, characterized in that, The real-time acquisition of contour data of the forming area during the laser stereolithography process includes: During the laser stereolithography process, data from N collection points in the forming area are acquired in real time as the contour data.

3. The method for inspecting powder feeding quality according to claim 1, characterized in that, The step of determining the abnormal location in the forming area based on the second height difference includes: When the second height difference is less than the set second threshold, it is determined that there is no abnormality in the second centerline image; When the second height difference is greater than or equal to the set second threshold, it is determined that there is an anomaly in the second centerline image.

4. A device for inspecting the quality of powder feeding, characterized in that, The device includes: a data acquisition section, a determination section, and an adjustment section; wherein... The acquisition unit is configured to acquire contour data of the forming area in real time during the laser stereolithography process; The determining part is configured to determine the abnormal position in the forming area based on the contour data and according to the set judgment conditions; wherein the abnormal position is used to characterize the position of powder feeding defect; The adjustment section is configured to, after determining the location of the powder feeding defect, adjust the power of the laser or the movement speed of the laser cladding head to perform process compensation when the laser cladding head moves to the location of the powder feeding defect. The determining part is configured as follows: Fit the contour image of the shaped region based on the contour data to obtain the region of interest in the contour image; Extract the first centerline image from the region of interest; Interpolate the first centerline image to obtain a continuously distributed second centerline image; Within the same XOZ plane, based on the region of interest, the second height difference between the first pixel and the third pixel is obtained by sequentially comparing adjacent first and third pixels on the contour lines in the second centerline image. The location of the anomaly is determined based on the second height difference.

5. A device for inspecting powder feeding quality, characterized in that, The device includes: a data acquisition module, a memory, and a processor disposed on one side of the laser cladding head; wherein... The data acquisition module is used to acquire the contour data of the forming area in real time during the laser stereolithography process; The memory is used to store computer programs that can run on the processor; The processor is configured to perform the following steps when running the computer program: Based on the contour data, abnormal locations in the forming area are determined according to the set judgment conditions; wherein, the abnormal locations are used to characterize the locations of powder feeding defects. After determining the location of the powder feeding defect, when the laser cladding head moves to the location of the powder feeding defect, the power of the laser or the movement speed of the laser cladding head is adjusted for process compensation. The step of determining abnormal locations in the forming area based on the contour data and according to set judgment conditions includes: Fit the contour image of the shaped region based on the contour data to obtain the region of interest in the contour image; Extract the first centerline image from the region of interest; Interpolate the first centerline image to obtain a continuously distributed second centerline image; Within the same XOZ plane, based on the region of interest, the second height difference between the first pixel and the third pixel is obtained by sequentially comparing adjacent first and third pixels on the contour lines in the second centerline image. The location of the anomaly is determined based on the second height difference.

6. A computer storage medium, characterized in that, The computer storage medium stores a program for inspecting the powder feeding quality, which, when executed by at least one processor, implements the steps of the method for inspecting the powder feeding quality according to any one of claims 1 to 3.

Images