In-situ system and method for dimension acquisition of electric arc additive deposition based on binocular vision

Abstract

The application provides a kind of based on binocular vision's electric arc additive deposition size in-situ acquisition system and method, comprising: electric arc additive manufacturing system, image acquisition and processing system, wherein the electric arc additive manufacturing system is configured with robot, intelligent welding machine, wire feeder, welding torch, welding protection gas bottle, the image acquisition and processing system is configured with binocular camera, computer;The binocular camera is installed on the welding torch, for collecting the deposited pass image in deposition process, and the deposited pass image collected is sent to computer for processing, obtains the overall size of current deposition piece.The application can directly monitor the deposition size in deposition process, obtain the size of deposition piece, with good synchronism, not by large workpiece size limitation advantage.And not by size restriction, can realize the size in-situ monitoring in the process of large piece electric arc additive manufacturing, measurement data is more accurate.

Description

Technical Field

[0001] This invention relates to the field of metal additive manufacturing technology, and more specifically, to a system and method for in-situ acquisition of arc additive deposition dimensions based on binocular vision. Background Technology

[0002] Arc additive manufacturing is suitable for the production of large metal components. However, during the deposition process, the metal of the previous layer is repeatedly heated and even melted as the next layer is deposited. With the increase of heat accumulation, the different heating and heat dissipation conditions of each layer, and the existence of unstable factors, the size of the single-layer weld line in arc additive manufacturing changes. If no intervention is taken, the finished product size will deviate from the preset size.

[0003] Currently, common solutions to this problem include:

[0004] (1) Dimensional measurement and post-processing after deposition. That is, after the deposition of the entire part is completed, the finished product is measured or scanned, and then post-processing such as grinding is performed according to the designed dimensions. Although this method can accurately control the dimensions of the workpiece, the increased workload of post-processing and excessive grinding operations make it difficult to give full play to the advantages of additive manufacturing in terms of saving raw materials and high manufacturing efficiency, and excessive post-processing will affect the mechanical properties of the finished product.

[0005] (2) Online monitoring and correction during deposition. This involves measuring or predicting dimensions during manufacturing and adjusting parameters in real time to ensure that the dimensions of the part are close to the design dimensions upon completion of deposition. This method avoids excessive post-processing techniques. Specifically, based on previous monitoring methods, such as those proposed by Song Yajing et al., temperature data is collected in real time using a CCD camera and uploaded to a computer for comparison with pre-stored standard temperature data to adjust working parameters in real time. General Electric Company of the United States proposed: acquiring a melt pool image that includes an array of measurements of at least one physical property for each individual image element, and mapping the melt pool boundary based on the measurements.

[0006] It is evident that current online monitoring methods for additive manufacturing primarily target the molten pool, electric arc, temperature, and spectrum to obtain the deposition state or indirectly determine the size of the deposited layer. However, since the size of the molten pool and the final size of the deposited layer do not strictly correspond, this indirect size monitoring method is not entirely accurate. Direct size monitoring of the deposited layer, such as using methods based on structured light and 3D cameras, is susceptible to arc light interference, resulting in insufficient accuracy and stability in size measurements. Summary of the Invention

[0007] To address the shortcomings of existing technologies, the purpose of this invention is to provide a system and method for in-situ acquisition of arc additive deposition dimensions based on binocular vision.

[0008] In a first aspect, embodiments of this application provide an in-situ acquisition system for arc additive deposition dimensions based on binocular vision, comprising: an arc additive manufacturing system and an image acquisition and processing system, wherein the arc additive manufacturing system is equipped with a robot, an intelligent welding machine, a wire feeder, a welding torch, and a welding shielding gas cylinder, and the image acquisition and processing system is equipped with a binocular camera and a computer;

[0009] The binocular camera is mounted on the welding torch to acquire images of the weld bead during the deposition process and sends the acquired weld bead images to a computer for processing to obtain the overall dimensions of the current deposited part.

[0010] Optionally, the binocular camera uses a visible light-based camera.

[0011] Optionally, during deposition, the welding torch may connect with at most one deposition channel of the same layer and at most one deposition channel of a different layer during each deposition.

[0012] Optionally, the weld path image is a single left-right eye image of the weld path that has just finished deposition and solidified behind the current layer that is being deposited.

[0013] Optionally, the overall size of the currently deposited part is the height and width dimensions of the deposited portion of the workpiece currently being deposited.

[0014] Secondly, embodiments of this application provide a method for in-situ acquisition of arc additive deposition dimensions based on binocular vision, applied to the system for in-situ acquisition of arc additive deposition dimensions based on binocular vision as described in the first aspect, the method comprising:

[0015] Step 1: Perform single and dual-target positioning and calibration on the stereo camera;

[0016] Step 2: Obtain the contour range of the deposition layer;

[0017] Step 3: Obtain spatial points based on the sedimentary layer contour range to determine the three-dimensional coordinates of the sedimentary layer contour;

[0018] Step 4: Based on the three-dimensional coordinates of the sedimentary layer outline, correct the size of the single layer to obtain the effective height and effective width of the current sedimentary layer;

[0019] Step 5: Superimpose the effective height and effective width of the current deposition layer with the previous accumulated dimensions to obtain the overall dimensions of the current deposition piece.

[0020] Optionally, step 2 includes:

[0021] The images acquired by the binocular camera are cropped to obtain images near the camera's center point, thus determining the contour of the sedimentary layer.

[0022] Optionally, step 4 includes:

[0023] Step 4.1: Classify the weld lines of the current layer into the starting weld line of the first layer, the non-starting weld line of the first layer, the starting weld line of the subsequent layer, and the non-starting weld line of the subsequent layer;

[0024] Step 4.2: For the initial channel of the first layer, the measured height is taken as the effective height of the current sedimentary layer, and the measured width is taken as the effective width of the current sedimentary layer;

[0025] Step 4.3: For non-initial channels in the first layer, the measured height is taken as the effective height of the current deposition layer. The effective width of the current deposition layer is defined as Δx, where Δx is the set welding torch movement distance. It is half the width of the previous one. It is half the measured width of the track;

[0026] Step 4.4: For the starting channel of the subsequent layer, the corrected height is taken as the effective height of the current sedimentary layer, and the measured width is taken as the effective width of the current sedimentary layer;

[0027] Step 4.5: For non-starting channels in subsequent layers, use the corrected height as the effective height of the current deposition layer. The effective width of the current deposition layer; where Δx is the set welding torch movement distance. It is half the width of the previous one. It is half the measured width of the road.

[0028] Optionally, the formula for calculating the corrected height is as follows:

[0029]

[0030] Among them, h ′ The corrected height is S, the deposition amount is w, and the measured width is w.

[0031] Optionally, step 5 includes:

[0032] During the stacking process, determine whether it is a single-walled component;

[0033] If it is not a single-walled part, the effective height of the single layer is added to the previously accumulated height, and the effective width of the single layer is added to the previously accumulated width to obtain the overall size of the current deposited part;

[0034] If it is a single-walled component, then only the effective height of the single layer is superimposed to obtain the overall size of the current deposited component.

[0035] Thirdly, embodiments of this application provide an in-situ acquisition device for arc additive deposition dimensions based on binocular vision, comprising: a processor and a memory, wherein the memory stores executable program instructions, and when the processor invokes the program instructions in the memory, the processor is used to:

[0036] Perform the steps of the in-situ acquisition method for arc additive deposition dimensions based on binocular vision as described in any of the second aspects.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium for storing a program, which, when executed, implements the steps of the binocular vision-based in-situ acquisition method for arc additive deposition dimensions as described in any one of the second aspects.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The binocular vision-based in-situ size acquisition system and method for arc additive manufacturing provided in this application can directly monitor the deposition size during the deposition process and obtain the size of the deposited part. It has the advantages of good synchronization and is not limited by the size of large workpieces. Furthermore, it is not limited by the size of the workpiece and can realize in-situ size monitoring in the arc additive manufacturing process of large parts, with more accurate measurement data. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort. Other features, objects, and advantages of the present invention will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0041] Figure 1 A schematic diagram of the structure of the in-situ acquisition system for arc additive deposition dimensions based on binocular vision provided in an embodiment of this application;

[0042] Figure 2 A schematic diagram illustrating the principle of the in-situ acquisition method for arc additive deposition dimensions based on binocular vision provided in the embodiments of this application;

[0043] Figure 3 A schematic flowchart illustrating an in-situ acquisition method for arc additive deposition dimensions based on binocular vision, provided for an embodiment of this application;

[0044] Figure 4 This is a schematic diagram showing the installation position of the binocular camera provided in the embodiments of this application;

[0045] Figure 5 This is a schematic diagram illustrating the principle of obtaining the weld bead contour equation in an embodiment of this application.

[0046] Figure 6 A schematic diagram illustrating the distinction between starting and non-starting weld lines provided in the embodiments of this application;

[0047] Figure 7 A schematic diagram illustrating the modification of subsequent layers provided in the embodiments of this application. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] It should be noted that when a component is said to be "fixed" to another component, it can be directly on the other component or it can be in a middle component. When a component is said to be "connected" to another component, it can be directly connected to the other component or it may be in a middle component.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0051] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0052] The technical solutions of the present invention and how they solve the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0053] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0054] Figure 1 This is a schematic diagram of the structure of the in-situ acquisition system for arc additive deposition dimensions based on binocular vision provided in the embodiments of this application, as shown below. Figure 1 As shown, the system in this embodiment may include: an electric arc additive manufacturing system and an image acquisition and processing system. The electric arc additive manufacturing system is equipped with a robot, an intelligent welding machine, a wire feeder, a welding torch, and a welding shielding gas cylinder. The image acquisition and processing system is equipped with a binocular camera and a computer.

[0055] In this embodiment, the robot can be a FANUC M-20iA multi-joint robot, the wire feeder can be a Fronius WF 25i wire feeder, and the welding torch can be a Fronius CMT welding torch.

[0056] In this embodiment, a binocular camera based on visible light can be used. For example, the binocular camera is mounted on the welding torch to acquire images of the weld bead during the deposition process, and the acquired weld bead images are sent to a computer for processing to obtain the overall dimensions of the current deposited part.

[0057] In this embodiment, the binocular camera is mounted on the welding torch rather than fixed outside the additive manufacturing system, so it is not limited by the size of the part and can realize in-situ dimensional monitoring during the arc additive manufacturing process of large parts.

[0058] The camera used in this embodiment does not rely on structured light and infrared light, so it has good robustness when used in the manufacturing process, even in the case of strong arc light during workpiece deposition.

[0059] In this embodiment, the arc additive manufacturing deposition method meets the actual requirements of additive manufacturing industrial applications.

[0060] For example, the size difference between the deposited layers in contact with each other is small; the center distance between the deposited layers in the same layer meets the requirement of achieving a small undulating surface; each deposit is connected to at most one deposited channel in the same layer and at most one deposited channel in a different layer.

[0061] Optionally, the camera's monocular and binocular functions need to be calibrated and adjusted before image acquisition.

[0062] In this embodiment, the number of chessboard images to be acquired can be set to 20-30. During the calibration process, in order to ensure the effect, the allowable error range is <0.1. If it exceeds this range, the camera should be readjusted and calibrated to ensure the effect.

[0063] For example, the weld channel image is a single left- and right-eye image of the weld channel that has just finished deposition and solidified behind the current layer that is being deposited.

[0064] Figure 2 This is a schematic diagram illustrating the principle of the binocular vision-based in-situ acquisition method for arc additive deposition dimensions provided in the embodiments of this application, as shown below. Figure 2 As shown, the method in this embodiment may include: binocular camera calibration, image acquisition at the start of deposition, acquisition of the deposition layer contour range, acquisition of three-dimensional coordinates, acquisition of the current layer measurement size, classification of the current layer, corresponding correction to obtain the effective size, and superposition to obtain the overall size.

[0065] For example, the contour range of the weld bead can be obtained by combining epipolar constraints and boundary recognition. The three-dimensional coordinates can be obtained using the least squares method.

[0066] For example, the weld path classification includes: the starting path of the first layer, the non-starting path of the first layer, the starting path of the subsequent layer, and the non-starting path of the subsequent layer.

[0067] For example, in this embodiment, the overall size obtained by superposition refers to the height and width dimensions of the already deposited portion of the workpiece currently being deposited.

[0068] Figure 3 A flowchart illustrating an in-situ acquisition method for arc additive deposition dimensions based on binocular vision, as provided in this application embodiment, is shown below. Figure 3 As shown, the method in this embodiment may include:

[0069] Step S301: Perform single and dual-target positioning and calibration on the binocular camera.

[0070] In this embodiment, the binocular camera is first mounted on the welding torch as required, and the calibration plate is placed on the worktable. The camera focal length is adjusted so that the calibration plate is clearly visible in the view. 20-30 checkerboard images of the left and right views are acquired. The rotation matrix and translation vector of the left camera relative to the marker points are obtained. The rotation matrix and translation vector of the right camera relative to the left camera are obtained through stereo calibration. The rotation matrix and translation vector of the right camera relative to the object point are obtained from the transformation relationship of the right camera relative to the object point. The images are reconstructed to obtain the mapping matrix used for distortion correction and stereo correction, as well as the reprojection matrix used to calculate the pixel spatial coordinates.

[0071] Figure 4This is a schematic diagram of the installation position of the binocular camera provided in the embodiments of this application, as shown below. Figure 4 As shown, install the binocular camera at the designated position on the welding torch and adjust the angle to determine the required range that can be captured.

[0072] For example, Zhang's calibration method can be used for single and dual-camera calibration and correction to determine the intrinsic and extrinsic parameters and relative pose of the left and right cameras. The robot arm is adjusted to position the welding torch at the distance during deposition. The robot pose is adjusted to capture 25 images of a calibration board with sides of 10mm × 10mm and a checkerboard pattern of 6 × 7 squares at different angles. The corner response threshold is adjusted to detect checkerboard feature points in the images, and the extrinsic and extrinsic parameters of the left and right cameras are initially calculated. The radial distortion coefficient is solved using the least squares method. The objective function is established using the maximum likelihood method, and the Levenberg-Marquardt algorithm is used to optimize the calibration parameters and improve accuracy.

[0073] Step S302: Obtain the contour range of the deposition layer.

[0074] In this embodiment, the images acquired by the binocular camera are cropped to determine the contour of the deposition layer. To reduce computational load and ensure real-time performance, the images can be cropped, taking only the area near the camera center point while discarding points with excessive grayscale values ​​that will not be used for subsequent calculations.

[0075] For example, in the process of arc additive manufacturing, a binocular camera is kept in operation to obtain binocular images of the weld lines corresponding to the solidified portion of the layer being deposited during the workpiece deposition process.

[0076] Step S303: Obtain spatial object points based on the sedimentary layer contour range and determine the three-dimensional coordinates of the sedimentary layer contour.

[0077] In this embodiment, the coordinates of the spatial object point can be solved using the least squares method.

[0078] Figure 5 A schematic diagram illustrating the principle of obtaining the weld bead contour equation as provided in an embodiment of this application. See also... Figure 5The Bonguet algorithm can be used for stereo correction. Edge detection is performed on the left and right camera images, spiraling outwards from the image center to determine the workpiece range, generating left and right mask matrices (workpiece range is 1, other areas are 0). Subsequent steps involving traversal are based on this mask matrix to reduce unnecessary calculations in areas outside the workpiece. Due to the characteristics of the camera mounting position, a straight line perpendicular to the weld channel is taken in the left camera image. Pixels are traversed along this line, and gradients are obtained based on the Sobel operator. Points between the two detected edge points O1 and O2 are points located on the same cross-sectional contour of this weld channel. Based on epipolar constraints, the two endpoints O1' and O2' of the contour line are found in the right camera image in the same way. A semi-global matching method is used to match the corresponding points between O1' and O2' and between O1 and O2, and the 3D coordinates are recovered using triangulation. The obtained sparse point 3D coordinates are used to fit an approximate parabolic equation for the cross-sectional contour of the weld channel. This step adds a step to determine the range of points belonging to the same cross section for the left and right camera images before matching. Only points on the same cross section in the image and their nearby points are included in the calculation, which reduces the amount of calculation.

[0079] Step S304: Based on the three-dimensional coordinates of the sedimentary layer outline, correct the single-layer size to obtain the effective height and effective width of the current sedimentary layer.

[0080] In this embodiment, the measurement dimensions are obtained by using extreme values ​​based on the obtained three-dimensional coordinates of the sedimentation layer profile.

[0081] For example, before stacking, because the previous layer has melted or covered portions, it is necessary to obtain the effective dimensions from the measured dimensions, i.e., the increased dimensions compared to before this layer was deposited. The distinction between the four types of weld lines is based on whether the edge of the weld line is a discontinuity.

[0082] For example, during correction, the deposition is divided into the first layer and subsequent layers, as well as the starting channel and non-starting channels. For the starting channel of the first layer, h and [other parameters] are directly obtained. The effective height and width dimensions of the current sedimentary layer are used. For the non-initial channel of the first layer, the measured h is used as the effective height of the current sedimentary layer. The effective width of the current deposition layer is defined as Δx, where Δx is the set welding torch movement distance. It is half the width of the previous one. It is half the measured width of this channel.

[0083] Furthermore, for the initial path of subsequent layers, with The effective width of the current sedimentary layer is taken as h', and the corrected h' is taken as the effective height of the current sedimentary layer. The calculation process for h' is as follows:

[0084] Approximating the surface of the current pass as a parabola, we fit the equation of this parabola. We then approximate two adjacent passes as identical parabolas. The deposition amount of this layer at each moment is then S. S is obtained from the set wire feed speed and moving speed. Therefore, the deposition amount of the current pass at each moment can be considered as a curvilinear quadrilateral.

[0085] For non-starting channels in subsequent layers, The effective width of the current deposition layer is defined as Δx, where Δx is the set welding torch movement distance. It is half the width of the previous one. To measure half the width of this section, the half that does not connect with the previous section is considered a curvilinear quadrilateral. Right now As the effective height of the current sedimentary layer.

[0086] Figure 6 This diagram illustrates the distinction between starting and non-starting weld lines in an embodiment of this application. After obtaining the height and width dimensions, the weld lines can be classified accordingly.

[0087] Step S305: Superimpose the effective height and effective width of the current deposition layer with the previous accumulated dimensions to obtain the overall dimensions of the current deposition piece.

[0088] In this embodiment, the effective height and width dimensions of a single layer obtained in the previous step are superimposed on the previously accumulated dimensions to obtain the overall dimensions of the current deposited part. During the superposition process, if it is a single-walled part, only the height is superimposed.

[0089] Figure 7 This is a schematic diagram illustrating the correction of subsequent layers provided in an embodiment of this application. The effective size is obtained using a corresponding correction algorithm, and then superimposed on the previously accumulated size to obtain the overall size of the portion of the deposited part at this point.

[0090] In this embodiment, by correcting the measurement dimensions, the measurement error of each layer is reduced, and the overall dimension after stacking is significantly more accurate.

[0091] In this embodiment, real-time dimensions are obtained by processing the acquired process images, enabling online correction and closed-loop control of the dimensions of the wire arc additive manufacturing process. During deposition, local images of the deposited portion of the workpiece are acquired using a binocular camera to obtain the overall dimensions of the deposited portion. Optionally, the dimensions of the deposited portion of the workpiece are obtained by performing cross-sectional profile range acquisition based on epipolar constraints and the Sobel operator, semi-global matching, cross-sectional profile parabolic fitting, dimension correction, and superposition on the acquired left and right camera images. The method in this embodiment has the advantages of being usable during the deposition process, having good synchronization, and not being limited by the size of large workpieces in obtaining the dimensions of the workpiece.

[0092] This application embodiment also provides a device for in-situ acquisition of arc additive deposition dimensions based on binocular vision, which may include a processor and a memory.

[0093] Memory is used to store programs. Memory can include volatile memory, such as random-access memory (RAM), including static random-access memory (SRAM) and double data rate synchronous dynamic random-access memory (DDR SDRAM); it can also include non-volatile memory, such as flash memory. Memory is used to store computer programs (such as application programs and functional modules that implement the above methods), computer instructions, etc., which can be partitioned and stored in one or more memory locations. Furthermore, these computer programs, instructions, and data can be accessed by the processor.

[0094] The aforementioned computer programs, computer instructions, etc., can be stored in partitions within one or more memory locations. Furthermore, the aforementioned computer programs, computer instructions, data, etc., can be accessed by a processor.

[0095] A processor is used to execute a computer program stored in memory to implement the various steps in the methods described in the above embodiments.

[0096] For details, please refer to the relevant descriptions in the preceding method embodiments.

[0097] The processor and memory can be separate structures or integrated structures. When the processor and memory are separate structures, they can be coupled together via a bus.

[0098] The binocular vision-based in-situ acquisition device for arc additive deposition dimensions in this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principle are described in the relevant description in the above method, and will not be repeated here.

[0099] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "platform."

[0100] Furthermore, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions, wherein when at least one processor of a user device executes the computer-executable instructions, the user device performs the various possible methods described above.

[0101] Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transfer of computer programs from one place to another. Storage media can be any available medium accessible to a general-purpose or special-purpose computer. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a user device. Of course, the processor and storage medium can also exist as discrete components in a communication device.

[0102] The various embodiments described in this specification are presented in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0103] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various modifications or variations within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. A system for in-situ acquisition of arc additive deposition dimensions based on binocular vision, characterized in that, include: An electric arc additive manufacturing system and an image acquisition and processing system are provided. The electric arc additive manufacturing system is equipped with a robot, an intelligent welding machine, a wire feeder, a welding torch, and a welding shielding gas cylinder. The image acquisition and processing system is equipped with a binocular camera and a computer. The binocular camera is mounted on the welding torch to acquire images of the weld bead during the deposition process. These images are then sent to a computer for processing to obtain the overall dimensions of the current deposited part. When processing the weld bead images, the computer uses different correction algorithms based on the type of weld bead to calculate the effective height and effective width of the current deposition layer. The effective dimensions of the current deposition layer are then superimposed with the previous accumulated dimensions to obtain the overall dimensions of the current deposited part. The types of weld bead include first-layer initiation bead, first-layer non-initiation bead, subsequent-layer initiation bead, and subsequent-layer non-initiation bead. For the first-layer initiation bead, the measured height is used as the effective height of the current deposition layer, and the measured width is used as the effective width. For the first-layer non-initiation bead, the measured height is used as the effective height, and ∆x - w1 / 2 + w2 / 2 is used as the effective width, where ∆x is the set welding torch movement distance, w1 / 2 is half the width of the previous bead, and w2 / 2 is half the measured width of the current bead. For the subsequent-layer initiation bead, the effective height h' is calculated based on the deposition amount S by fitting a parabolic equation. S / w, using the measured width as the effective width of the current deposition layer. The measured width is Δx - w1 / 2 + w2 / 2 for subsequent non-starting channels, and S / w is the effective height.

2. The in-situ size acquisition system for arc additive deposition based on binocular vision according to claim 1, characterized in that, Binocular cameras use visible light-based cameras.

3. The in-situ size acquisition system for arc additive deposition based on binocular vision according to claim 1, characterized in that, When the welding torch is depositing, each deposition pass can connect with at most one deposition pass of the same layer and at most one deposition pass of a different layer.

4. The in-situ size acquisition system for arc additive deposition based on binocular vision according to claim 1, characterized in that, The weld channel image is a single left-right image of the weld channel behind the current layer that has just finished deposition and solidified.

5. The in-situ size acquisition system for arc additive deposition based on binocular vision according to claim 1, characterized in that, The overall dimensions of the currently deposited part are the height and width dimensions of the already deposited portion of the workpiece currently being deposited.

6. A method for in-situ acquisition of arc additive deposition dimensions based on binocular vision, applied to the in-situ acquisition system for arc additive deposition dimensions based on binocular vision as described in any one of claims 1-5, characterized in that, The method includes: Step 1: Perform single and dual-target positioning and calibration on the stereo camera; Step 2: Obtain the contour range of the deposition layer; Step 3: Obtain spatial points based on the sedimentary layer contour range to determine the three-dimensional coordinates of the sedimentary layer contour; Step 4: Based on the three-dimensional coordinates of the sedimentary layer outline, correct the single-layer size to obtain the effective height and effective width of the current sedimentary layer; Step 4 includes: Step 4.1: Classify the weld lines of the current layer into the starting weld line of the first layer, the non-starting weld line of the first layer, the starting weld line of the subsequent layer, and the non-starting weld line of the subsequent layer; Step 4.2: For the initial channel of the first layer, the measured height is taken as the effective height of the current sedimentary layer, and the measured width is taken as the effective width of the current sedimentary layer; Step 4.3: For non-initial channels in the first layer, the measured height is taken as the effective height of the current deposition layer. As the effective width of the current deposition layer, where, The set welding torch movement distance, It is half the width of the previous one. It is half the measured width of the track; Step 4.4: For the starting channel of the subsequent layer, the corrected height is taken as the effective height of the current sedimentary layer, and the measured width is taken as the effective width of the current sedimentary layer; Step 4.5: For non-starting channels in subsequent layers, use the corrected height as the effective height of the current deposition layer. As the effective width of the current deposition layer; where, The set welding torch movement distance, It is half the width of the previous one. The corrected height is calculated as half the measured lane width; the formula for calculating the corrected height is as follows: in, The corrected height. For sedimentation amount, The width to be measured; Step 5: Superimpose the effective height and effective width of the current deposition layer with the previously accumulated dimensions to obtain the overall dimensions of the current deposition piece; Step 5 includes: During the stacking process, determine whether it is a single-walled component; If it is not a single-walled part, the effective height of the single layer is added to the previously accumulated height, and the effective width of the single layer is added to the previously accumulated width to obtain the overall size of the current deposited part; If it is a single-walled component, then only the effective height of the single layer is superimposed to obtain the overall size of the current deposited component.

7. The method for in-situ acquisition of arc additive deposition dimensions based on binocular vision according to claim 6, characterized in that, Step 2 includes: The images acquired by the binocular camera are cropped to obtain images near the camera's center point, thus determining the contour of the sedimentary layer.

Images