Additive manufacturing molten pool information acquisition system

Abstract

The embodiment of the invention provides an additive manufacturing molten pool information collection system, and relates to the technical field of information collection, and the system comprises an image collection unit which is used for collecting a molten pool image generated by additive manufacturing equipment in the machining process; the laser light supplementing unit is used for emitting light supplementing laser, and the light supplementing laser is used for irradiating the position of the molten pool; the positioning bracket is used for relatively fixing the image acquisition unit and the laser light supplementing unit with a processing head of the additive manufacturing equipment, and fixing the direction of a lens of the image acquisition unit and the direction of light supplementing laser emitted by the laser light supplementing unit to be towards a molten pool; and the data processing unit is connected with the image acquisition unit and is used for acquiring the molten pool image and extracting molten pool morphology information in the molten pool image. According to the embodiment of the invention, the accuracy of collecting the morphology information of the molten pool is improved.

Description

Technical Field

[0001] This application relates to the technical field of information acquisition, and particularly to an information acquisition system for additive manufacturing molten pool. Background Art

[0002] In additive manufacturing technology, the real-time acquisition and information extraction of the molten pool morphology are crucial for controlling the quality of the formed metal components. As the basic unit in the additive manufacturing process of metal components, the state change of the molten pool can reflect the basic problems and principles of additive manufacturing of metal components, such as the complex interaction between high-energy beams and materials, abnormal metallurgy and unsteady heat and mass transfer, rapid solidification of the moving molten pool melt, and the formation of solidification structures and defects, and thus reflect the internal quality and surface quality of the formed metal components. However, in the related art, there are various deficiencies in the real-time acquisition of the molten pool morphology, and the accuracy of the molten pool morphology information acquisition is relatively low. Summary of the Invention

[0003] Embodiments of this application provide an information acquisition system for additive manufacturing molten pool to alleviate or solve one or more technical problems existing in the prior art.

[0004] Embodiments of this application provide an information acquisition system for additive manufacturing molten pool, including:

[0005] An image acquisition unit, configured to acquire a molten pool image generated during the processing of an additive manufacturing device;

[0006] A laser supplementary light unit, configured to emit supplementary light laser, and the supplementary light laser is used to irradiate the position of the molten pool;

[0007] A positioning bracket, configured to relatively fix the image acquisition unit and the laser supplementary light unit with the processing head of the additive manufacturing device, and make the lens orientation of the image acquisition unit and the direction of the supplementary light laser emitted by the laser supplementary light unit be fixed to face the position of the molten pool;

[0008] A data processing unit, connected to the image acquisition unit, configured to acquire the molten pool image and extract the molten pool morphology information in the molten pool image.

[0009] In some embodiments, the image acquisition unit is configured to acquire an image of light within a preset wavelength band to obtain the molten pool image.

[0010] In some embodiments, the wavelength of the supplementary light laser emitted by the laser supplementary light unit is within the preset wavelength band.

[0011] In some embodiments, the image acquisition unit includes: a lens, a filter, and an image sensor;

[0012] The lens is configured to converge the light entering the lens to the image sensor;

[0013] The image sensor is used for photosensing to generate the molten pool image;

[0014] The filter is disposed outside the image sensor and is used to allow light in the preset wavelength band to pass through the filter.

[0015] In some embodiments, the image acquisition unit further includes:

[0016] A focal length adjustment module is disposed outside the image sensor and is used to adjust the focusing distance of the lens.

[0017] In some embodiments, the focal length adjustment module is disposed between the image sensor and the lens, and the filter is built into the focal length adjustment module.

[0018] In some embodiments, the positioning bracket includes:

[0019] A connecting member fixedly connected to the processing head;

[0020] A first clamping arm fixedly connected to the connecting member. A first adapter fixture is provided at the end of the first clamping arm, and the first adapter fixture is used to clamp the image acquisition unit;

[0021] A second clamping arm fixedly connected to the connecting member. A second adapter fixture is provided at the end of the second clamping arm, and the second adapter fixture is used to clamp the laser supplementary lighting unit.

[0022] In some embodiments, the processing head is a laser processing head that emits processing laser; the second clamping arm is used to make the angle between the direction of the supplementary lighting laser emitted by the laser supplementary lighting unit and the direction of the processing laser an acute angle.

[0023] In some embodiments, the laser supplementary lighting unit includes:

[0024] A laser generator for generating parallel laser;

[0025] A laser focusing lens connected to the laser generator through an optical fiber. The laser focusing lens is fixed on the positioning bracket and is used to converge the parallel laser transmitted by the optical fiber into the supplementary lighting laser.

[0026] In some embodiments, the data processing unit is used to execute:

[0027] Obtain the molten pool image;

[0028] Extract the contour of the molten pool from the molten pool image;

[0029] Perform an elliptical fitting process on the contour to obtain a fitted ellipse of the contour of the molten pool;

[0030] Calculate the morphology information of the molten pool according to the geometric information of the fitted ellipse; the geometric information includes at least one of the following: center coordinates, major axis, minor axis, rotation angle, area.

[0031] In some embodiments, the data processing unit is further configured to perform:

[0032] Control the image acquisition unit to acquire molten pool images generated by the additive manufacturing equipment during the processing at a preset time interval;

[0033] For each of the molten pool images, after calculating the morphology information of the molten pool, store the morphology information of the molten pool in a target data format in a database.

[0034] Based on the above additive manufacturing molten pool information acquisition system, the present application has at least the following beneficial effects or advantages:

[0035] The additive manufacturing molten pool information acquisition system provided by the embodiments of the present application includes: an image acquisition unit for acquiring molten pool images generated by the additive manufacturing equipment during the processing; a laser supplementary lighting unit for emitting supplementary lighting laser, and the supplementary lighting laser is used to irradiate the position of the molten pool; a positioning bracket for relatively fixing the image acquisition unit and the laser supplementary lighting unit to the processing head of the additive manufacturing equipment, and making the lens orientation of the image acquisition unit and the direction of the supplementary lighting laser emitted by the laser supplementary lighting unit fixed to be towards the position of the molten pool; a data processing unit connected to the image acquisition unit for acquiring the molten pool images and extracting the morphology information of the molten pool in the molten pool images. The additive manufacturing molten pool information acquisition system provided by the embodiments of the present application relatively fixes the image acquisition unit and the laser supplementary lighting unit to the processing head of the additive manufacturing equipment through the positioning bracket, ensuring that the relative position between the image acquisition unit and the molten pool remains unchanged during the processing of additive manufacturing, thereby improving the stability of the molten pool image acquisition perspective. At the same time, by using the supplementary lighting laser to supplement light to the position of the molten pool, the recognition rate of the morphology of the molten pool in the image is significantly improved, and further, the accuracy of the acquisition of the morphology information of the molten pool is generally improved.

[0036] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically given below. Description of the Drawings

[0037] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the several views denote the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments in accordance with the present application and should not be regarded as limiting the scope of the present application.

[0038] Figure 1 Fig. 4 shows a schematic block diagram of an additive manufacturing molten pool information acquisition system provided by an embodiment of the present application;

[0039] Figure 2 Fig. 8 shows a schematic structural diagram of an image acquisition unit in an additive manufacturing molten pool information acquisition system provided by an embodiment of the present application;

[0040] Figure 3 Fig. 12 shows a schematic structural diagram of a focal length adjustment module in an additive manufacturing molten pool information acquisition system provided by an embodiment of the present application;

[0041] Figure 4 Fig. 16 shows a schematic structural diagram of a positioning bracket in an additive manufacturing molten pool information acquisition system provided by an embodiment of the present application;

[0042] Figure 5 Fig. 20 shows a schematic structural diagram of an additive manufacturing molten pool information acquisition system provided by an embodiment of the present application;

[0043] Figure 6 Fig. 24 shows a molten pool image acquired by an additive manufacturing molten pool information acquisition system provided by an embodiment of the present application;

[0044] Figure 7 Fig. 28 shows a schematic diagram of an extraction result interface of a molten pool image acquired by an additive manufacturing molten pool information acquisition system provided by an embodiment of the present application.

[0045] At least some of the reference numerals involved in the drawings are as follows:

[0046] 1. Image acquisition unit; 20. Supplementary light laser unit; 2. Laser focusing lens of the supplementary light laser unit; 3. Laser generator of the supplementary light laser unit; 4. Data processing unit; 5. Positioning bracket; 6. Processing head; 7. Laser generator of the processing head; 8. Additive manufacturing forming member; 11. Protective lens; 12. Lens of the image acquisition unit; 13. Focal length adjustment module; 14. Image sensor; 131. Fixed clamping ring; 132. Filter sheet; 133. Focal length extension tube; 51. Connecting member; 52. Second clamping arm; 53. First clamping arm; 54. Second adapter fixture; 55. First adapter fixture. Detailed implementation manners

[0047] In the following text, only some exemplary embodiments are briefly described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the concept or scope of the present application. Therefore, the accompanying drawings and the description are considered to be exemplary in nature and not restrictive.

[0048] To facilitate the understanding of the technical solutions of the embodiments of the present application, the related technologies of the embodiments of the present application are described below. The following related technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.

[0049] The technical solutions of the present application and how the technical solutions of the present application solve the foregoing technical problems will be described in detail below with specific embodiments. The several specific embodiments listed can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0050] The additive manufacturing technology for high-performance metal components uses alloy powders or wires as raw materials, and through high-power heat sources (such as lasers / electron beams / arcs, etc.) for in-situ metallurgical melting / rapid solidification layer-by-layer deposition, directly completes the direct near-net shaping manufacturing technology of fully dense and high-performance large and complex metal structural components from the part digital model in one step. The rapid development and application of additive manufacturing technology provide a transformative technical method for the processing and manufacturing of large key metal components of high-end major equipment such as marine ships, special vehicles, aerospace, and bridge construction.

[0051] During the long-term cyclic and reciprocating point-by-point and layer-by-layer local high-energy beam melting and deposition forming process of metal components, process parameters such as material parameters, high-energy beam processing parameters, processing technology parameters, and environmental parameters will all affect the temperature field and thermal stress field during the forming process, and thus affect the chemical composition uniformity, rapid solidification nucleation and growth process, and residual internal stress distribution of additive manufacturing components, etc., and ultimately affect the tissue characteristics, defect formation, and deformation and cracking of additive manufacturing components. At the same time, the continuous change of boundary conditions (such as the fluctuations and changes in the molten state of the moving molten pool, the transformation of scanning filling trajectories, etc., which are discontinuous and unstable) also increases the uncertainty and complexity of the internal tissue, defects, and residual internal stress of the component.

[0052] The molten pool is the basic unit in the additive manufacturing process of metal components. The change of its state can reflect the basic problems and principles of additive manufacturing of metal components, such as the complex interaction between high-energy beam and materials, abnormal metallurgy and unsteady heat and mass transfer, rapid solidification of the moving molten pool melt, and the formation of solidification microstructure and defects. Furthermore, it can reflect the internal quality (such as defects) and surface quality (roughness and surface topography, etc.) of the formed metal components. If an industrial camera, a laser supplementary light source, and a high-precision filter can be integrated, and combined with machine vision recognition algorithms, a real-time acquisition and information extraction system for the additive manufacturing molten pool morphology can be established, and a database of the molten pool state change during the additive manufacturing process can be obtained, which can provide a basis and dataset for revealing the correlation between the process parameters of additive manufacturing of high-performance metal components and the quality performance of components, and for mastering the intelligent prediction and autonomous decision-making control technology of the quality performance of additive manufacturing components.

[0053] Currently, foreign additive manufacturing processing head design and production manufacturers such as PRECITEC Company and TRUMPF Company in Germany have achieved the connection and integration of industrial cameras with additive manufacturing processing heads through the internal optical path transformation of the processing heads, and have carried out subsequent development work in aspects such as imaging, acquisition, and information extraction. However, the research and development of additive manufacturing processing heads in China are still in an immature stage. At present, most domestic additive manufacturing processing heads on the market only have optical lens group modules, powder feeding modules, and cooling modules that can meet the basic needs of additive manufacturing of metal components, and cannot install or integrate industrial cameras, lacking the hardware foundation for real-time acquisition of the morphology characteristics of the molten pool during the additive manufacturing process. At the same time, in the commercial field, even additive manufacturing processing heads that can install industrial cameras generally lack filtering and supplementary light functions, and are often affected by the high-energy beam source and the light emission and heat generation of the formed metal components during the real-time acquisition of the molten pool morphology characteristics, greatly reducing the acquisition effect and the quality of information extraction. Finally, the current efficiency of additive manufacturing molten pool morphology acquisition and extraction is low, the speed is slow, the accuracy is poor, and the amount of information is small, which cannot meet the requirements of real-time monitoring of the additive manufacturing molten pool. The above problems limit the design and development of the real-time acquisition and information extraction system for the additive manufacturing molten pool morphology, and seriously affect the control of the quality consistency and stability of high-performance metal components in additive manufacturing. Based on the above problems, the embodiment of this application provides an additive manufacturing molten pool information acquisition system.

[0054] Reference Figure 1 As shown in, the embodiment of this application provides an additive manufacturing molten pool information acquisition system, including: an image acquisition unit 1, a laser supplementary light unit 20, a positioning bracket 5, and a data processing unit 4.

[0055] The image acquisition unit 1 is used to acquire the molten pool image generated during the processing of the additive manufacturing equipment. Specifically, the image acquisition unit 1 can use a COMS industrial camera, a CCD industrial camera, an area array camera, etc. The lens of the image acquisition unit 1 faces the molten pool to capture the image of the molten pool. The image acquisition unit 1 can be connected to the data processing unit 4 through a wired or wireless communication connection method to send the acquired molten pool image to the data processing unit 4. The image acquisition unit 1 can be fixedly connected to the positioning bracket 5 by means such as welding, threaded connection, and clamping connection.

[0056] The laser supplementary lighting unit 20 is used to emit supplementary lighting laser, and the supplementary lighting laser is used to irradiate the position of the molten pool. The role of the supplementary lighting laser is to supplement the necessary light intensity for the image acquisition process of the image acquisition unit 1, so that the image acquisition unit 1 can obtain a clear and high-quality molten pool image, and enhance the image features of the molten pool morphology in the molten pool image.

[0057] The positioning bracket 5 is used to relatively fix the image acquisition unit 1 and the laser supplementary lighting unit 20 with the processing head of the additive manufacturing equipment, and make the direction of the lens of the image acquisition unit 1 and the supplementary lighting laser emitted by the laser supplementary lighting unit 20 fixed to face the position of the molten pool. The positioning bracket 5 can be relatively fixed to the processing head by means such as welding, threaded connection, and clamping connection, and can be specifically fixed on the moving mechanism of the processing head. For example, the moving mechanism includes but is not limited to: multi-axis robotic arm, three-axis moving mechanism, side-axis wire feeding mechanism, fuse pressing mechanism, and guide groove, etc.

[0058] The data processing unit 4 is connected to the image acquisition unit 1 and is used to execute the following algorithm steps: acquire the molten pool image and extract the molten pool morphology information in the molten pool image. The main body for the data processing unit 4 to execute the algorithm steps can be an electronic device, such as a computer, a mobile phone, a tablet computer and other terminal devices, a server, etc. The specific implementation manner of the algorithm steps of the data processing unit 4 can be a computer program, which can be implemented in forms such as a client, an application program, an APP, a cloud service, etc., and the embodiments of the present application do not make any limitations in this regard.

[0059] The additive manufacturing molten pool information acquisition system provided by the embodiments of the present application relatively fixes the image acquisition unit and the laser supplementary lighting unit with the processing head of the additive manufacturing equipment through the positioning bracket, ensuring that the relative position between the image acquisition unit and the molten pool remains unchanged during the processing of additive manufacturing, thereby improving the stability of the molten pool image acquisition perspective. At the same time, by using the supplementary lighting laser to supplement light to the position of the molten pool, the recognition rate of the molten pool morphology in the image is significantly improved, and thus the accuracy of the molten pool morphology information acquisition is generally improved.

[0060] In some embodiments, with reference to Figure 2 , the image acquisition unit 1 may specifically include: a lens 12, a filter Figure 2(not shown in the figure) and an image sensor 14. The lens 12 is used to converge the light entering the lens to the image sensor 14, and the image sensor 14 is used to sense light to generate a molten pool image.

[0061] A filter is disposed outside the image sensor 14 and is used to allow light in a preset wavelength band to pass through the filter. The filter can filter out interfering light rays, improving the clarity and contrast of the molten pool morphology imaging. The filter can be disposed in front of the lens 12 or between the lens 12 and the image sensor 14.

[0062] In some embodiments, the image acquisition unit 1 may also be configured with a highly transparent protective lens 11 as shown before the lens 12. The protective lens 11 is used to prevent damage to the lens 12 caused by raw material splashing during the additive manufacturing process. Figure 2 shown, and the protective lens 11 is used to prevent damage to the lens 12 caused by raw material splashing during the additive manufacturing process.

[0063] In some embodiments, referring to Figure 2 , the image acquisition unit 1 may further include a focal length adjustment module 13 for adjusting the focusing distance of the lens 12. The focal length adjustment module 13 is disposed outside the image sensor 14. In some applications, the focal length adjustment module 13 may use a focal length extension ring with different focal length lengths to adjust the focal length and field of view.

[0064] In some embodiments, the focal length adjustment module 13 may be disposed in front of the lens 12, for example, between the protective lens 11 and the lens 12. In still other embodiments, referring to Figure 2 , the focal length adjustment module 13 may be disposed between the lens 12 and the image sensor 14. Further, the filter may be built into the focal length adjustment module 13. For example, referring to Figure 3 , the focal length adjustment module 13 may include: a fixed retaining ring 131, a filter 132, and a focal length extension tube 133. The fixed retaining ring 131 is used to fix the focal length adjustment module 13 to the image sensor 14. The image sensor 14 is one of the main components of the image acquisition unit 1 and is internally configured with a photosensitive unit and an acquisition unit for converting the physical quantity of light into a digital quantity.

[0065] In some embodiments, the wavelength of the supplementary light laser emitted by the laser supplementary light unit 20 is within the preset wavelength band. In this way, the filter can filter out interfering light rays outside the preset wavelength band, and the wavelength of the supplementary light laser is within the preset wavelength band. The supplementary light laser can efficiently supplement light to the molten pool, allowing the light rays of the supplementary light laser to enter the image acquisition unit 1, ensuring clear and good-contrast imaging of the molten pool morphology.

[0066] In some embodiments, referring to Figure 4, the positioning bracket 5 includes: a connecting member 51, a first clamping arm 52, a second clamping arm 53, a first adapter fixture 54, and a second adapter fixture 55. The connecting member 51 is fixedly connected to the processing head of the additive manufacturing equipment, for example, by fixing methods such as welding, threaded connection, and clamping connection. The first clamping arm 52 is fixedly connected to the connecting member 51, and a first adapter fixture 54 is provided at the end of the first clamping arm 52. The first adapter fixture 54 is used to clamp the image acquisition unit 1. The second clamping arm 53 is fixedly connected to the connecting member 51, and a second adapter fixture 55 is provided at the end of the second clamping arm 53. The second adapter fixture 55 is used to clamp the laser supplementary lighting unit 20. In some embodiments, referring to Figure 4 and Figure 5 , the first clamping arm 52 of the positioning bracket 5 is used to make the lens 12 of the image acquisition unit 1 face at an acute angle to the emission direction of the processing laser, and the second clamping arm 53 is used to make the angle between the direction of the supplementary lighting laser emitted by the laser supplementary lighting unit 20 and the direction of the processing laser be an acute angle.

[0067] Optionally, the connecting member 51 can use a central flange as shown in Figure 4 . In some embodiments, the laser processing head installation point on the central flange can be set to have a certain inclination angle with the vertical direction. For example, the value of the inclination angle can be set between 5 - 10°, so as to avoid the error reporting problem caused by most lasers reflecting into the processing head.

[0068] In some embodiments, referring to Figure 5 , the laser supplementary lighting unit 20 includes a laser generator 3 and a laser focusing lens 2. The laser generator 3 is used to generate parallel laser, the laser focusing lens 2 is connected to the laser generator 3 through an optical fiber, and the laser focusing lens 2 is fixed on the positioning bracket 5 and is used to converge the parallel laser generated by the laser generator 3 transmitted through the optical fiber into supplementary lighting laser and irradiate it to the molten pool position.

[0069] In some embodiments, the data processing unit 4 is used to perform the following steps 101 to 104:

[0070] Step 101, acquire the molten pool image;

[0071] Step 102, extract the contour of the molten pool in the molten pool image;

[0072] Step 103, perform ellipse fitting processing on the contour to obtain the fitting ellipse of the contour of the molten pool;

[0073] Step 104, calculate the molten pool morphology information according to the geometric information of the fitting ellipse; the geometric information includes at least one of the following: center coordinates, major axis, minor axis, rotation angle, area.

[0074] In some embodiments, the data processing unit 4 can also control the image acquisition unit 1 to acquire the molten pool images generated during the processing of the additive manufacturing equipment at a preset time interval. For each molten pool image, after calculating the molten pool topography information, the molten pool topography information is stored in the database in a target data format.

[0075] Reference Figure 5 This is a specific implementation of an additive manufacturing molten pool information acquisition system provided by an embodiment of the present application. As Figure 5 The additive manufacturing molten pool information acquisition system shown includes the following components: an image acquisition unit 1, a laser focusing lens 2 of the supplementary light laser unit 20, a laser generator 3 of the supplementary light laser unit 20, a data processing unit 4, a positioning bracket 5, a laser processing head 6 of the additive manufacturing equipment, a laser generator 7 of the processing head, and an additive manufacturing formed component 8.

[0076] Next, in combination with Figures 1 to 4 , for Figure 5 the specific structure and implementation of the additive manufacturing molten pool information acquisition system shown will be described in detail.

[0077] The image acquisition unit 1 uses a high-definition CMOS industrial camera. The function of the high-definition CMOS industrial camera is to perform real-time imaging and acquisition of the molten pool topography during the additive manufacturing process. Exemplarily, the maximum frame rate of the selected camera is ≥50 frames per second, and the resolution is ≥1280 (H) x 1024 (V) pixels. The camera will output the brightness values of each point in the field of view as relative values after taking the logarithm to reduce the influence of the high-brightness laser beam on the molten pool topography imaging during the additive manufacturing process. The lens of the camera is specially designed. In addition to the usual focusing and imaging functions, a high-transmission protection lens is configured at the front end of the lens. Referring to Figure 2 the protection lens 11 shown, it can prevent the damage of the lens caused by the splashing of raw materials during the additive manufacturing process. A focal length extension ring with different lengths and a high-precision filter 132 built-in is installed between the lens 12 and the image sensor 14 of the image acquisition unit 1. On the one hand, it can filter out the interfering light other than the supplementary light laser to ensure clear and good-contrast imaging of the molten pool topography. On the other hand, it can realize the adjustment of the focal length and the field of view of the camera.

[0078] The laser generator 3 and the laser focusing lens 2 are components of the laser supplementary lighting unit 20 in the additive manufacturing molten pool information acquisition system. The laser generator 3 is used to generate low-energy laser that matches the transmission wavelength of the high-precision filter 132 built into the camera lens 12, serving as the illumination light source for the molten pool during the additive manufacturing process. It has advantages such as high brightness, high purity, and no stroboscopic effect that conventional light sources like LEDs do not possess. The laser focusing lens 2 is connected to the laser generator 3 through an optical fiber and fixed on the second clamping arm 52 of the positioning bracket 5. Its function is to converge the parallel laser generated by the laser generator 3 into a circular light spot suitable for the system. The focusing distance is approximately 25 - 30 cm, and the light spot diameter is approximately 8 - 15 mm, which can meet the usage requirements of most real-time acquisition scenarios of the additive manufacturing molten pool morphology.

[0079] The data processing unit 4 is a high-performance computer, and relevant image acquisition and extraction algorithms are configured in the computer. The role of the high-performance computer is, on the one hand, to control the high-definition CMOS industrial camera to perform real-time acquisition of the additive manufacturing molten pool morphology, and on the other hand, to load the self-developed machine vision algorithm to complete the extraction of the additive manufacturing molten pool morphology information.

[0080] The positioning bracket 5 includes: a connecting piece 51, a second clamping arm 52, a first clamping arm 53, a second adapter fixture 54, and a first adapter fixture 55. The connecting piece 51 is specifically a central flange. The role of the positioning bracket 5 is to integrate the high-definition CMOS industrial camera, the laser focusing lens 2, the laser processing head 6, and the motion mechanism of the additive manufacturing equipment into an overall unit, so as to keep the relative position between the image acquisition unit 1 and the molten pool fixed during the additive manufacturing process. The overall positioning bracket 5 can adopt topological optimization design and is processed from forged aluminum alloy, which can ensure the stability and vibration-free operation of the image acquisition unit 1 while significantly reducing weight. The laser processing head installation point of the central flange has a certain inclination angle with the vertical direction. For example, the inclination angle value is set between 5 - 10°, which can avoid error reporting problems caused by most lasers reflecting into the processing head.

[0081] The specific steps for the data processing unit 4 to extract the additive manufacturing molten pool morphology information are as follows:

[0082] Step 201: Create a suitable Python environment in the high-performance computer and import necessary algorithm libraries such as OpenCV and NumPy.

[0083] Step 202: Use the cv2.imread() function of OpenCV to complete the reading of the molten pool image.

[0084] Step 203: Preprocess the read molten pool image, including but not limited to the following processing methods:

[0085] (1) Grayscale processing: Convert the color image of the molten pool image into a grayscale image.

[0086] The grayscale value of each pixel in the grayscale image after grayscale processing is given by the following formula:

[0087] Gray(x,y) = 0.299R(x,y) + 0.587G(x,y) + 0.114B(x,y)

[0088] where R(x,y), G(x,y), and B(x,y) are the pixel values of the red, green, and blue channels at each position in the color molten pool image, and Gray(x,y) is the pixel value at the corresponding position in the grayscale image. Refer to Figure 6 Figure

[0089] (2) Noise removal processing: Filters can be used to remove noise in the image. Filters such as Gaussian filtering and median filtering can be used.

[0090] Gaussian filtering: The calculation formula of Gaussian filtering is as follows:

[0091]

[0092] where I(x,y) is the pixel value after filtering, w(i,j) is the weight of the Gaussian kernel, and r is the radius of the kernel. By applying the Gaussian filter kernel to each pixel of the image, the image can be smoothed and noise can be reduced.

[0093] Median filtering: The calculation formula of median filtering is to use the median pixel of the image as the filtering threshold.

[0094] (3) Binarization processing: Binarize the image for feature extraction.

[0095] Binarization processing divides the pixel points in the image into two categories: pixel points higher than the preset threshold Threshold and pixel points lower than the preset threshold Threshold. It can be implemented according to the following calculation formula:

[0096]

[0097] where Binary(x,y) is the pixel value at position (x,y) in the binarized image, Image(x,y) is the pixel value at the corresponding position in the original image, and Threshold is the selected threshold.

[0098] Step 204: Use the developed algorithm to complete the extraction of molten pool morphology information, including but not limited to: molten pool contour, ellipse fitting, and calculation of molten pool morphology information. Call the cv2.findContours() function to extract the contours in the molten pool. For example, to extract the contours, the contours can be drawn manually or, an already trained artificial intelligence model can be used to extract the contours in the molten pool image. Call the cv2.fitEllipse() function to perform ellipse fitting on the contours, and the molten pool morphology information can be calculated. A schematic diagram of the interface of an example result of molten pool morphology information extraction is as shown in Figure 7 which shows the fitted ellipse in the molten pool image and displays the specific data of the molten pool morphology information. The molten pool morphology information includes but is not limited to: the center coordinates center, major axis major_axis, minor axis minor_axis, and rotation angle angle of the fitted ellipse. Among them, the molten pool area can be calculated through the ellipse area formula S = π / 4·major_axis·minor_axis.

[0099] Step 205: Store the extracted molten pool morphology information into a suitable data structure or file to complete the real-time acquisition and information extraction process of the additive manufacturing molten pool morphology. For example, the data structure can be in the form of a dictionary, and the file can be a text file.

[0100] # Store the areas of the contours in the form of a dictionary

[0101] features = {'contour_areas': [cv2.contourArea(contour) for contour in contours]}

[0102] # Or write the feature information to a text file

[0103] with open('features.txt', 'w') as file:

[0104] for area in features['contour_areas']:

[0105] file.write(f'Contour Area: {area}\n')

[0106] In the embodiments of the present application, by reforming the internal optical path layout of the laser processing head, the hardware basis required for real-time acquisition of the additive manufacturing molten pool morphology is integrated inside the processing head, and a dedicated algorithm is developed to realize the extraction of real-time information of the additive manufacturing molten pool morphology, solving the problem that the additive manufacturing equipment in the related art does not have the hardware basis for real-time acquisition and information extraction of the molten pool morphology during the additive manufacturing process. The additive manufacturing molten pool morphology monitoring systems in the related art generally lack the functions of light filtering and light supplementing, and are usually interfered by the laser beam and the light emission and heat generation of the formed metal component during the real-time acquisition of the morphology. The embodiments of the present application greatly reduce the interference of the laser beam and the light emission and heat generation of the formed metal component during the real-time acquisition of the molten pool morphology through high-precision light filtering and laser light source light supplementing. The machine vision and artificial neural network algorithms can be combined to improve the efficiency, speed, accuracy and information volume of the acquisition and extraction of the additive manufacturing molten pool morphology, providing a criterion for improving the performance stability and quality consistency during the additive manufacturing process of metal components.

[0107] In the above embodiments, the "unit" can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0108] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0109] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality" means two or more, unless otherwise specifically defined.

[0110] Any process or method described in the method flow or otherwise described herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of the present application includes additional implementations, where functions may be performed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed.

[0111] The logic and / or steps described in the method flow or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatus, or devices.

[0112] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above-described example methods can be completed by a program instructing relevant hardware. This program can be stored in a computer-readable storage medium. When this program is executed, it includes one or a combination of the steps of the method embodiments.

[0113] In addition, in each embodiment of the present application, each functional unit can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above-integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a magnetic disk, an optical disc, etc.

[0114] As described above, only the exemplary embodiments of the present application are provided, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope recorded in the present application can easily think of various changes or substitutions, and these should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An additive manufacturing molten pool information acquisition system, characterized in that: include: An image acquisition unit, used to acquire a molten pool image generated by the additive manufacturing device during the processing; A laser fill light unit, used for emitting a fill light laser, wherein the fill light laser is used for irradiating the position of the molten pool; A positioning bracket, used for fixing the image acquisition unit and the laser fill light unit relative to the processing head of the additive manufacturing device, and fixing the direction of the lens of the image acquisition unit and the direction of the fill light laser emitted by the laser fill light unit to a position facing the molten pool; The data processing unit is connected to the image acquisition unit and is used to obtain the molten pool image and extract the molten pool morphology information in the molten pool image.

2. The additive manufacturing molten pool information acquisition system according to claim 1, characterized in that: The image acquisition unit is used to acquire the imaging of light within a preset wavelength band to obtain the molten pool image.

3. The additive manufacturing molten pool information acquisition system according to claim 2, characterized in that: The wavelength of the fill light laser emitted by the laser fill light unit is within the preset wavelength band.

4. The additive manufacturing molten pool information acquisition system according to claim 2, characterized in that: The image acquisition unit includes: a lens, a filter and an image sensor; The lens is used to focus the light entering the lens onto the image sensor; The image sensor is used for sensing light to generate the molten pool image; The filter is arranged outside the image sensor and is used to allow the light of the preset wavelength band to pass through the filter.

5. The additive manufacturing molten pool information acquisition system according to claim 4, characterized in that: The image acquisition unit also includes: The focus adjustment module is arranged outside the image sensor and is used to adjust the focus distance of the lens.

6. The additive manufacturing molten pool information acquisition system according to claim 5, characterized in that: The focus adjustment module is arranged between the image sensor and the lens, and the filter is built in the focus adjustment module.

7. The additive manufacturing molten pool information acquisition system according to claim 1, characterized in that: The positioning bracket comprises: A connecting piece, fixedly connected to the processing head; A first clamping arm is fixedly connected to the connecting member, a first adapter fixture is provided at the end of the first clamping arm, and the first adapter fixture is used to clamp the image acquisition unit; The second clamping arm is fixedly connected to the connecting member. A second adapter fixture is disposed at the end of the second clamping arm. The second adapter fixture is used to clamp the laser fill light unit.

8. The additive manufacturing molten pool information acquisition system according to claim 1, characterized in that: The laser light supplement unit comprises: A laser generator, used for generating parallel laser light; A laser focusing lens is connected to the laser generator via an optical fiber. The laser focusing lens is fixed on the positioning bracket and is used to converge the parallel lasers transmitted by the optical fiber into the fill light lasers.

9. The additive manufacturing molten pool information acquisition system according to claim 1, characterized in that: The data processing unit is used to perform: Acquire the molten pool image; extracting the contour of the molten pool in the molten pool image; Performing ellipse fitting processing on the contour to obtain a fitting ellipse of the contour of the molten pool; The molten pool morphology information is calculated according to the geometric information of the fitted ellipse; the geometric information includes at least one of the following: center coordinates, major axis, minor axis, rotation angle, and area.

10. The additive manufacturing molten pool information acquisition system according to claim 9, characterized in that: The data processing unit is also used to execute: Controlling the image acquisition unit to acquire the molten pool image generated by the additive manufacturing device during the processing at a preset time interval; For each of the molten pool images, after calculating the molten pool morphology information, the molten pool morphology information is stored in a database in a target data format.

Images