Arc additive manufacturing weld bead forming interlayer regulation and control method and system

Abstract

The invention discloses an electric arc additive manufacturing weld bead forming interlayer regulation and control method and system, relates to the technical field of electric arc additive manufacturing, solves the technical problem that interlayer error accumulation greatly influences electric arc additive manufacturing structural part forming, and is characterized in that high-precision point cloud data is obtained by scanning the surface of a current cladding layer. The neural network prediction module uses the welding speed sequence of the target cladding layer as input, combines the trained neural network model, predicts feature point data of the target cladding layer and constructs a three-dimensional model of the target cladding layer. And the interlayer regulation and control module adjusts process parameters according to the deviation between the prediction result and the target result and a set threshold value so as to realize accurate interlayer form regulation and control. Compared with the prior art, the method has the advantages that the process adjusting capacity is high, the forming quality of each layer in the additive manufacturing process can be obviously optimized, and the manufacturing precision of the whole component is improved.

Description

Technical Field

[0001] The present invention relates to the fields of robot path planning, additive manufacturing (AM) and intelligent manufacturing technology, and in particular to a method and system for interlayer control of arc additive manufacturing weld bead forming. Background Art

[0002] Arc additive manufacturing technology is one of the metal additive manufacturing methods that has developed rapidly in recent years. This technology discretizes complex metal structures into simple planar stacking forms by layering and slicing the three-dimensional model of the metal component and planning the path. It then uses an arc heat source to melt the metal wire layer by layer for stacking and forming, which significantly reduces the difficulty of forming high-performance metal structural parts. Compared with other metal additive technologies, arc additive manufacturing has the outstanding advantages of short production cycle, low manufacturing cost and high deposition efficiency, and the formed components have the characteristics of uniform chemical composition, high density and excellent mechanical properties. At present, this technology has become an important technological driving force in the aerospace, shipbuilding, chemical and vehicle industries, and its application is gradually developing in the direction of large-scale and integrated metal structural parts.

[0003] However, the arc additive manufacturing process is affected by a variety of factors (such as surface topography deviations of single-layer deposits, surface deformation caused by high temperatures, and random flow in the molten pool). The shape errors between the deposited layers and the ideal model after multi-layer deposition vary in complex ways, making it difficult to achieve large and complex structures simply by optimizing parameters during the design phase. Therefore, effectively controlling interlayer forming accuracy, reducing accumulated deviations, and ensuring the final quality of additive components remain pressing challenges in the current arc additive manufacturing field. Summary of the Invention

[0004] The present application provides a method and system for interlayer control of arc additive manufacturing weld bead forming, the technical purpose of which is to effectively control the interlayer forming accuracy of additive manufacturing weld bead, reduce the accumulation of interlayer deviations and ensure the final quality of additive components.

[0005] The above technical objectives of this application are achieved through the following technical solutions:

[0006] A method for interlayer control of arc additive manufacturing weld bead forming, comprising the following steps:

[0007] Step S1: collecting point cloud data of the current cladding layer;

[0008] Step S2: Design and train a neural network prediction module, input the target cladding layer process parameters into the neural network prediction module, and output the target cladding layer characteristic data; add the target cladding layer characteristic data to the current cladding layer point cloud data to obtain the predicted layer point cloud data;

[0009] Step S3: According to the deviation between the target model and the predicted layer point cloud data, the target cladding layer process parameters are adjusted and optimized, and the optimized process parameters are transmitted to the arc additive equipment to perform target layer deposition.

[0010] Furthermore, the specific steps in step S2 are:

[0011] Step S21: training an artificial neural network model to obtain a prediction module;

[0012] Step S22: inputting the target cladding layer process parameters, i.e., the velocity sequence of the current weld cross section, into the weld cross section prediction unit in the neural network prediction module, and outputting the target cladding layer characteristic data;

[0013] Step S23: correcting the weld overlap portion;

[0014] Step S24: connecting the feature points at corresponding positions of different weld bead sections according to the predicted feature points and the correction results to obtain a three-dimensional model of the weld bead, and obtaining the target cladding layer feature data according to the three-dimensional model of the weld bead.

[0015] Furthermore, the specific steps of step S2 are as follows:

[0016] Step S221: Initialize parameters j=1, h=1, define j as the weld bead number, j∈{1,2,.j...,J}, J is the total number of weld bead, h is the slice number of each weld bead, h∈{1,2,.h...,H}, H is the total number of slices of each weld bead;

[0017] Step S222: The velocity sequence of the current weld cross section is input into the trained artificial neural network model, and the height axis increments of the corresponding positions of the five feature points relative to the current layer base are output;

[0018] The speed sequence includes: the welding speed parameter V0 corresponding to the current j-th slice of the weld bead, the welding speed parameter V at the position of the first two slices of the predicted weld bead section, and the speed sequence of the weld bead. -2 and V -1 , predict the welding speed parameters V1 and V2 at the two slices after the weld cross section; the height axis increment is defined as

[0019] Step S223: Select the current base contour feature point, add the horizontal coordinate value of the base contour feature point to the horizontal coordinate value of the current welding gun projection point, and obtain the horizontal coordinate value of the predicted point; add the height coordinate value of the base contour feature point to the height axis increment to obtain the height coordinate value of the predicted point, and then obtain the coordinates of the predicted point, and save the data;

[0020] Step S224: h=h+1, repeat steps S222-S223 until h=H;

[0021] Step S225: j=j+1, repeat steps S222-S224 until j=J, thereby obtaining the predicted feature points of the target weld deposit layer of J weld bead and J*H slices.

[0022] Furthermore, in step S223, the welding gun projection point P j,h The absolute coordinates of the intersection point between the target deposited layer additive path and the target deposited layer weld cross-section slice are projected on the current deposited layer. The coordinates of the current welding gun projection point are defined as P j,h (X P ,Z P ), extract the relative welding gun projection point P on the current weld cross section j,h The horizontal coordinate distance is 0. The five points are used as the current base contour feature points and The height direction coordinates of the base contour feature points are defined as Then the coordinates corresponding to the five base contour feature points are Where d is the distance between the additive paths;

[0023] That is, the coordinates of the predicted feature points of the jth layer are

[0024] Furthermore, in step S23, the specific steps of correcting the weld overlap portion are:

[0025] Step S231: Initialize j=1, h=1.

[0026] Step S232: Correct the height coordinate value of the h-th slice section of the overlap portion of the j-th weld bead and the j+1-th weld bead, expressed as:

[0027]

[0028] in, is the height coordinate value of the fifth weld profile feature point in the cross section of the hth weld bead of the jth weld bead, is the height coordinate value of the first weld profile feature point in the cross section of the hth weld bead of the j+1th weld bead, It is the height coordinate value of the junction between the jth and j+1th tracks of the hth slice on the current cladding layer.

[0029] Furthermore, step S3 includes:

[0030] Step S31: The target weld deposition layer height is L, and the deviation θ1 between the target model and the predicted layer point cloud data is calculated and compared with the preset threshold. If the deviation θ1 is less than the preset threshold α1, then go to step S33; if the deviation θ1 is greater than or equal to the preset threshold α1, then the deviation DEV of each weld cross section is calculated. j,h Perform calculations;

[0031] Determine the deviation DEV of each weld cross section j,h , is it greater than the adjustment threshold α2; for the deviation DEV j,h The weld cross-sections that are less than or equal to the adjustment threshold α2 maintain the original welding parameters; the deviation DEV of each weld cross-section j,h The cross section of the weld bead that is larger than the adjustment threshold is calculated according to the deviation DEV. j,h The order from large to small is the welding speed V j,h Make corrections;

[0032] Step S32: Repeat step S2 according to the adjusted welding speed to obtain the predicted layer point cloud data again, and input it into step S31 until the deviation between the target model and the predicted layer point cloud data meets the preset threshold requirement.

[0033] Step S33: inputting the adjusted target cladding layer process parameters into the arc additive equipment to perform target cladding layer deposition.

[0034] Furthermore, the deviation DEV of each weld cross section in step S31 j,h The calculation formula is:

[0035]

[0036] in, Indicates the height coordinate value of the i-th characteristic point in the cross section of the j-th weld, Z target Indicates the target cladding layer height direction coordinate value, DEV j,h Indicates the deviation between the cross section of the jth weld pass and the target deposited layer.

[0037] Furthermore, the welding speed V j,h The correction formula is:

[0038] V′ j,h =V j,h ±DEV j,h *α

[0039] Among them, V' j,h V represents the adjusted welding speed of the jth and hth weld sections, j,h It represents the original welding speed of the jth and hth weld sections, and α represents the correction coefficient.

[0040] A neural network-based interlayer control system for additive manufacturing weld bead forming, comprising:

[0041] Scanning module, to obtain point cloud data of the current cladding layer surface;

[0042] A neural network prediction module outputs target cladding layer characteristic data based on input target cladding layer process parameters;

[0043] The accumulation module adds the target cladding layer feature data and the current cladding layer point cloud data to obtain the predicted layer point cloud data;

[0044] The interlayer control module calculates the deviation between the target model and the predicted layer point cloud data. If the deviation exceeds the preset threshold, the target cladding layer process parameters are adjusted until the deviation meets the preset threshold requirements. The adjusted target cladding layer process parameters are input into the arc additive equipment to execute the target cladding layer deposition.

[0045] A robotic arc additive manufacturing device includes a welding robot, an argon arc welding gun fixed to the end of the welding robot, a three-dimensional scanner, an industrial computer, an electric welder, and a robot controller. The three-dimensional scanner collects current point cloud data of arc additive manufacturing structural parts, and the industrial computer receives and processes the data.

[0046] The beneficial effects of this application are:

[0047] (1) Realizing interlayer control of the deposited layer height during arc additive manufacturing: This application predicts the interlayer morphology during the additive manufacturing process, obtains three-dimensional weld bead morphology prediction data, and adjusts the welding speed corresponding to each cross-section of each weld bead in real time, thereby reducing the morphology deviation caused by the cumulative effect of interlayer errors. Through this precise interlayer control, the loss of accuracy caused by layer-by-layer stacking in traditional methods can be effectively avoided, thereby improving the overall quality and reliability of the formed component.

[0048] (2) Using the welding speed sequence as input, the spatial influence of the target deposit process parameters is considered: This application innovatively uses the welding speed sequence of each cross-section of each weld bead as the neural network input, and fully considers the spatial correlation of the target deposit process parameters in the same weld bead. This allows for fine-tuning of the welding speed process parameters at multiple locations along the additive manufacturing path, thereby improving the flexibility and adaptability of the additive manufacturing process and further enhancing manufacturing accuracy.

[0049] (3) Combining neural network prediction with three-dimensional model construction to accurately predict weld bead morphology: Unlike traditional technologies that only predict the height and width of the weld section, this application proposes a strategy that combines neural network prediction and three-dimensional modeling to more accurately simulate and reconstruct the true three-dimensional morphology of the weld. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a schematic structural diagram of a robot arc additive manufacturing device in an embodiment of the present application;

[0051] Figure 2 This is a schematic diagram of the structure of the neural network prediction module in the embodiment of the present application;

[0052] Figure 3 This is a flow chart of inter-layer control of additive manufacturing weld bead forming in an embodiment of the present application;

[0053] Figure 4 This is a schematic diagram of the welding gun projection point selection in the embodiment of this application;

[0054] Figure 5 This is a schematic diagram of the structural component planning path in the embodiment of this application;

[0055] Figure 6 This is a schematic diagram of the three-dimensional modeling process of the cladding layer in an embodiment of the present application;

[0056] Figure 7 This is a flow chart of the inter-layer control module in an embodiment of the present application.

[0057] Among them, 1-welding robot, 2-argon arc welding gun, 3-arc additive manufacturing platform, 4-arc additive manufacturing structural parts, 5-3D scanner, 6-industrial computer, 7-electric welding machine, 8-robot controller. DETAILED DESCRIPTION

[0058] In order to deepen the understanding of the present invention, the following Figure 1-7 The present invention is further described in detail. This embodiment is only used to explain the present invention and does not constitute a limitation on the scope of protection of this application.

[0059] In order to reduce the influence of interlayer error accumulation on the forming of arc additive manufacturing structural parts, the present application provides an arc additive manufacturing weld bead forming interlayer control method, which is as follows: Figure 1 The robotic arc additive manufacturing device shown in the figure comprises a welding robot 1, an argon arc welding torch 2 fixed to the end effector of the welding robot 1, a base plate 3, a 3D scanner 5, an industrial computer 6, an electric welder 7, and a robot controller 8. The 3D scanner 5 collects current point cloud data of the arc additive manufacturing structural component 4. The industrial computer 6 receives and processes the data, obtains a controlled welding speed sequence through the interlayer control method for arc additive manufacturing weld bead formation described in this application, and transmits the corrected additive welding process parameters to the robot controller 8 and the electric welder 7.

[0060] For the arc additive manufacturing structural component 4 (length 80mm * width 80mm * height 80mm), the layer thickness is set to Lmm; XYZ is the Cartesian coordinate system of arc additive manufacturing, where X is the horizontal direction, Y is the vertical direction, and Z is the height direction.

[0061] like Figure 2 As shown, the additive path is divided into J additive paths along the X-axis direction, the additive path interval is dmm, and the additive direction is the positive direction of the Y-axis; ER308L stainless steel with a diameter of 1.0mm is selected as the welding wire, the welding current is 115A, the wire feeding speed is 0.6m / min, and the welding speed control range is set to 20-30cm / min.

[0062] like Figure 3 As shown, the method for interlayer control of arc additive manufacturing weld bead forming described in this application includes:

[0063] Step S1: Collect the point cloud data of the current cladding layer through a 3D scanner.

[0064] The number of slice sections H is calculated according to the weld bead length and the interval distance d of the additive path. Each weld bead is sliced along the additive direction Y axis according to the number of slice sections H, and the cross-sectional profile of each slice is obtained.

[0065] Define j as the weld bead number, j∈{1,2,.j..,J}, J is the total number of weld bead, h is the slice number of each weld bead, h∈{1,2,.h..,H}, H is the total number of slices of each weld bead;

[0066] like Figure 4 As shown, the welding gun projection point P j,h The absolute coordinates of the intersection point between the target deposited layer additive path and the target deposited layer weld cross-section slice projected on the current deposited layer. The welding gun projection point sequence number p∈{P 1,1 , P 1,2 ,...,P j,h ,...,P J,H The set of} is P, and the coordinate data set of all welding gun projection points is defined as The weld cross-section base contour line is the contour line of the weld cross-section slice on the base point cloud data.

[0067] In this embodiment, the number of slices per weld is H, and the target weld deposition layer is J, so the data set of the welding gun projection point data with a total of H*J slices is Read and save. At the same time, obtain the base contour line where the welding gun projection point is located through three-dimensional scanning, which is used for subsequent correction of the weld cross-section feature points. Go to step S2;

[0068] Step S2: design and train a neural network prediction module, input the target cladding layer process parameters into the neural network prediction module, and output the target cladding layer characteristic data.

[0069] Step S21: training an artificial neural network model to obtain a prediction module;

[0070] (1) Sample set construction:

[0071] Select the target cladding layer process parameters to be input into the neural network, including: the welding speed parameter V0 at the location of the predicted weld cross section, the welding speed parameter V at the location of the first two slices of the predicted weld cross section -2 and V -1 , predict the welding speed parameters V1 and V2 of the two slices after the weld cross section (if the current slice does not meet the condition of having two cross-section slices before and after, the welding speed parameters at the position of the missing cross-section slice are filled with 0), and take the spatial influence of the process parameters in the arc additive manufacturing process into consideration, so that the subsequent fine-grained control of the welding speed parameters at the corresponding position of each cross-section slice becomes possible.

[0072] Select the cross-sectional feature points of the output neural network: slice each weld along the Y-axis of the additive direction according to the number of slice sections H, and obtain the cross-sectional profile of each slice. Construct a coordinate system and place the welding gun projection point P of the current slice j,h As the origin, select the projection point P on the current base contour relative to the welding gun. j,h Five points with horizontal offsets of -d / 2, -d / 4, 0, d / 4, and d / 2, respectively, are designated as base contour feature points. Five points on the predicted layer's weld cross-section contour corresponding to the base contour feature points' X coordinates are defined as weld cross-section feature points, and the weld height increment, ΔZ, of the weld cross-section feature points relative to the base contour feature points is used as output data. Compared to predicting only the weld height and width parameters, selecting five feature points on the weld cross-section can more accurately characterize the weld cross-section geometry, making the model more consistent with actual additive manufacturing results. Furthermore, using the weld height increment as an output parameter effectively characterizes the correspondence between the target deposited layer and the current layer's point cloud data, thereby accurately reflecting the cumulative effect of interlayer errors.

[0073] (2) Neural network model construction

[0074] The artificial neural network structure includes an input layer, an output layer, and a hidden layer. The hidden layer contains several neurons. The input process parameters and the weld cross-section feature points obtained after point cloud data processing are used as a whole sample set. The sample set is then divided into a training set and a test set. The training set is used to train the artificial neural network, and the test set is used to verify the generalization ability of the constructed artificial neural network model.

[0075] The rationality and accuracy of the artificial neural network structure were verified by the mean square error and determination coefficient R2;

[0076] The structure of the neural network prediction module is as follows Figure 5 As shown, the neural network prediction module includes a weld cross-section prediction unit and a cladding layer three-dimensional modeling unit.

[0077] Step S22: Input the target cladding layer process parameters into the weld cross-section prediction unit in the neural network prediction module, and output the target cladding layer characteristic data:

[0078] Step S221: Initialize parameters, j=1, h=1.

[0079] Step S222: Input the velocity sequence of the current weld bead (the current weld bead is the predicted weld bead) into the trained artificial neural network model, and output the height (Z) axis increment of the corresponding positions of the five feature points relative to the current layer base; the velocity sequence of the current weld bead section includes: the welding velocity parameter V0 corresponding to the position of the hth slice of the current weld bead section, the welding velocity parameter V at the position of the first two slices of the predicted weld bead section, and the corresponding position of the five feature points. -2 and V -1 , predict the welding speed parameters V1 and V2 of the two slices after the weld cross section; (if the current slice does not meet the condition of having two cross-section slices before and after, the welding speed parameters at the position of the missing cross-section slice are filled with 0).

[0080] The velocity sequence of the current weld cross section is input into the trained artificial neural network model, and the height (Z) axis increments of the corresponding positions of the five feature points relative to the current layer base are output, which is defined as

[0081] Step S223: Define the current welding gun projection point coordinates as P j,h (X P ,Z P ), extract the relative welding gun projection point P on the current weld cross section j,h The horizontal (X) coordinate distance is 0. The five points are used as the current base contour feature points, and the Z coordinate of the base contour feature point is defined as The coordinates of each point are Where d is the distance between the additive paths.

[0082] Read welding gun projection point P j,h Coordinates (X P ,Z P )as well as Will and Z P 、 Add the horizontal (X) coordinates of the weld cross-section projection point to the welding gun projection point P j,h The horizontal coordinate (X P ) are added together to get the coordinates of the predicted feature points of the jth layer and the hth layer: The height coordinate value of the i-th predicted feature point in the j-th layer is defined as (i=1,2,3,4,5), save the data.

[0083] Step S224: h=h+1, repeat steps S222-S223 until h=H;

[0084] Step S225: j=j+1, repeat steps S222-S224 until j=J, thereby obtaining the predicted feature points of the target weld deposit layer of J weld bead and J*H slices.

[0085] Step S23: correcting the weld overlap portion;

[0086] Step S231: Initialize j=1, h=1.

[0087] Step S232: Correct the height (Z) coordinate value of the overlapped portion of slices h between slices j and slices j+1, expressed as:

[0088]

[0089] in, is the Z coordinate value of the fifth weld profile feature point in the cross section of the hth weld bead of the jth weld bead, is the Z coordinate value of the first weld profile feature point in the cross section of the hth weld bead of the j+1th weld bead, It is the Z coordinate value of the junction between the jth and j+1th tracks of the hth slice on the current cladding layer.

[0090] Step S224: h=h+1, repeat step S232 until h=H;

[0091] Step S225: j=j+1, repeat steps S232-S233 until j=J-1, thereby obtaining the corrected predicted point cloud data of the target cladding layer.

[0092] Step S24: Figure 6 As shown, according to the predicted characteristic points and the correction results, the characteristic points at corresponding positions of different weld cross sections are connected to obtain a three-dimensional model of the weld bead, and the characteristic data of the target weld deposition layer are obtained based on the three-dimensional model of the weld bead. Go to step S3;

[0093] Step S3: By calculating the deviation between the target model and the predicted layer point cloud data, if the deviation exceeds a preset threshold, the system dynamically adjusts the target deposited layer process parameters until the required accuracy is met. The optimized process parameters are then transmitted to the arc additive equipment to deposit the target layer. A control strategy based on weld bead cross-sectional characteristics enables more precise and flexible process parameter adjustments, enabling targeted optimization of specific errors in each weld bead cross section, effectively addressing the problem of insufficient component forming accuracy caused by the accumulation of interlayer errors.

[0094] Specifically, step S3 includes:

[0095] Step S31: The target cladding layer height is L, and the deviation θ1 between the target model and the predicted layer point cloud data is calculated and compared with the preset threshold. If the deviation θ1 is less than the preset threshold α1, the process proceeds to step S33;

[0096] If the deviation θ1 is greater than or equal to the preset threshold α1, such as Figure 7 As shown, the deviation DEV of each weld cross section j,h Calculate the deviation DEV j,h The calculation formula is:

[0097]

[0098] Deviation DEV of each weld cross section j,h If the cross section of the weld bead is less than or equal to the adjustment threshold α2, the original welding parameters are maintained;

[0099] Deviation DEV of each weld cross section j,h The cross section of the weld bead that is larger than the adjustment threshold is calculated according to the deviation DEV. j,h The order from large to small is the welding speed V j,h The correction is expressed as:

[0100] V′ j,h =V j,h ±DEV j,h *α

[0101] in, Indicates the Z value of the i-th characteristic point in the cross section of the j-th weld, Z target Indicates the target deposit layer Z value, DEV j,h Indicates the deviation between the cross section of the jth and hth weld bead and the target deposited layer, V' j,h V represents the adjusted welding speed of the jth and hth weld sections, j,h represents the original welding speed of the jth and hth weld sections, and α represents the correction coefficient;

[0102] Step S32: Repeat step S2 according to the adjusted welding speed to obtain the predicted layer point cloud data again, and input it into step S31 until the deviation between the target model and the predicted layer point cloud data meets the preset threshold requirement.

[0103] Step S33: inputting the adjusted target cladding layer process parameters into the arc additive equipment to perform target cladding layer deposition.

[0104] The arc additive manufacturing weld bead forming interlayer control system described in the present application is used to implement the additive manufacturing weld bead forming interlayer control method described in the present application.

[0105] The control system includes a scanning module, a neural network prediction module, an accumulation module and an inter-layer control module.

[0106] Scanning module, used to obtain point cloud data of the current cladding layer surface;

[0107] A neural network prediction module is used to output target cladding layer characteristic data according to input target cladding layer process parameters;

[0108] The interlayer control module is used to calculate the deviation between the target model and the predicted layer point cloud data. If the deviation exceeds the preset threshold, the target cladding layer process parameters are adjusted until the deviation meets the preset threshold requirements. The adjusted target cladding layer process parameters are input into the arc additive equipment to execute the target cladding layer deposition.

[0109] Examples

[0110] like Figure 1-7 As shown, in this embodiment, the number of slices per weld is H = 9, and the target weld deposition layer is J = 8, so the data set of the welding gun projection point data of the additive path is 72 slices in total. Read and save. At the same time, the base contour line where the welding gun projection point is located is obtained through 3D scanning, which is used for subsequent correction of weld cross-section feature points;

[0111] The X-coordinate distances of the weld cross section relative to the welding gun projection point P are selected as -5, -2.5, 0, 2.5, and 5 (i.e., d is 10), and the current welding speed is uniformly set to v = 20 cm / min. Therefore, the initial speed sequence of the first weld cross section is defined as (V -2 , V -1 , V0, V2, V1) = (0, 0, 20, 20, 20); the target deposition layer height is L = 5 mm.

[0112] The above specific implementation methods are only for illustrating the technical concept and structural features of the present invention, and the purpose is to enable relevant persons familiar with this technology to implement them accordingly. However, the above content does not limit the scope of protection of the present invention. Any equivalent changes or modifications made according to the spirit of the present invention should fall within the scope of protection of the present invention.

Claims

1. A method for controlling interlayers of arc additive manufacturing weld bead forming, characterized in that: The specific steps are: Step S1: collecting point cloud data of the current cladding layer; Step S2: Design and train a neural network prediction module, input the target cladding layer process parameters into the neural network prediction module, and output the target cladding layer characteristic data; add the target cladding layer characteristic data to the current cladding layer point cloud data to obtain the predicted layer point cloud data; Step S3: According to the deviation between the target model and the predicted layer point cloud data, the target cladding layer process parameters are adjusted and optimized, and the optimized process parameters are transmitted to the arc additive equipment to perform target layer deposition.

2. The arc additive manufacturing weld bead interlayer control method according to claim 1, characterized in that: The specific steps in step S2 are: Step S21: training an artificial neural network model to obtain a prediction module; Step S22: inputting the target cladding layer process parameters, i.e., the velocity sequence of the current weld bead cross section, into the weld bead cross section prediction unit in the neural network prediction module, and outputting the target cladding layer characteristic data; Step S23: correcting the weld overlap portion; Step S24: connecting the feature points at corresponding positions of different weld bead sections according to the predicted feature points and the correction results to obtain a three-dimensional model of the weld bead, and obtaining the target cladding layer feature data according to the three-dimensional model of the weld bead.

3. The arc additive manufacturing weld bead interlayer control method according to claim 2, characterized in that: The specific steps of step S22 are as follows: Step S221: Initialize parameters j=1, h=1, define j as the weld bead number, j∈{1,2,.j...,J}, J is the total number of weld bead, h is the slice number of each weld bead, h∈{1,2,.h...,H}, H is the total number of slices of each weld bead; Step S222: The velocity sequence of the current weld cross section is input into the trained artificial neural network model, and the height axis increments of the corresponding positions of the five feature points relative to the current layer base are output; The speed sequence includes: the welding speed parameter V0 corresponding to the position of the hth slice of the current jth weld bead, the welding speed parameter V at the position of the first two slices of the predicted weld bead section, and the speed sequence of the current jth weld bead. -2 and V -1 , predict the welding speed parameters V1 and V2 at the two slices after the weld cross section; the height axis increment is defined as Step S223: Select the current base contour feature point, add the horizontal coordinate value of the base contour feature point to the horizontal coordinate value of the current welding gun projection point, and obtain the horizontal coordinate value of the predicted point; add the height coordinate value of the base contour feature point to the height axis increment to obtain the height coordinate value of the predicted point, and then obtain the coordinates of the predicted point, and save the data; Step S224: h=h+1, repeat steps S222-S223 until h=H; Step S225: j=j+1, repeat steps S222-S224 until j=J, thereby obtaining the predicted feature points of the target weld deposit layer of J weld bead and J*H slices.

4. The arc additive manufacturing weld bead interlayer control method according to claim 3, characterized in that: In step S223, the welding gun projection point P j,h The absolute coordinates of the intersection point between the target deposited layer additive path and the target deposited layer weld cross-section slice are projected on the current deposited layer. The coordinates of the current welding gun projection point are defined as P j,h (X P ,Z P ), extract the relative welding gun projection point P on the current weld cross section j,h The horizontal coordinate distance is 0. The five points are used as the current base contour feature points and The height direction coordinates of the base contour feature points are defined as Then the coordinates corresponding to the five base contour feature points are Where d is the distance between the additive paths; That is, the coordinates of the predicted feature points of the jth layer are 5. The arc additive manufacturing weld bead interlayer control method according to claim 4, characterized in that: In step S23, the specific steps of correcting the overlapped portion of the weld are: Step S231: Initialize j=1, h=1. Step S232: Correct the height coordinate value of the h-th slice section of the overlap portion of the j-th weld bead and the j+1-th weld bead, expressed as: in, is the height coordinate value of the fifth weld profile feature point in the cross section of the hth weld bead of the jth weld bead, is the height coordinate value of the first weld profile feature point in the cross section of the hth weld bead of the j+1th weld bead, It is the height coordinate value of the junction between the jth and j+1th tracks of the hth slice on the current cladding layer.

6. The arc additive manufacturing weld bead interlayer control method according to claim 1, characterized in that: Step S3 includes: Step S31: The target weld deposition layer height is L, and the deviation θ1 between the target model and the predicted layer point cloud data is calculated and compared with the preset threshold. If the deviation θ1 is less than the preset threshold α1, then go to step S33; if the deviation θ1 is greater than or equal to the preset threshold α1, then the deviation DEV of each weld cross section is calculated. j,h Perform calculations; Determine the deviation DEV of each weld cross section j,h , is it greater than the adjustment threshold α2; for the deviation DEV j,h The weld cross-sections that are less than or equal to the adjustment threshold α2 maintain the original welding parameters; the deviation DEV of each weld cross-section j,h The weld cross-section that is larger than the adjustment threshold is calculated according to the deviation DEV. j,h The order of welding speed V from large to small j,h Make corrections; Step S32: Repeat step S2 according to the adjusted welding speed to obtain the predicted layer point cloud data again, and input it into step S31 until the deviation between the target model and the predicted layer point cloud data meets the preset threshold requirement; Step S33: inputting the adjusted target cladding layer process parameters into the arc additive equipment to perform target cladding layer deposition.

7. The arc additive manufacturing weld bead interlayer control method according to claim 6, characterized in that: Deviation DEV of each weld cross section in step S31 j,h The calculation formula is: in, Indicates the height coordinate value of the i-th characteristic point in the cross section of the j-th weld, Z target Indicates the target cladding layer height direction coordinate value, DEV j,h Indicates the deviation between the cross section of the jth weld pass and the target deposited layer.

8. The arc additive manufacturing weld bead interlayer control method according to claim 7, characterized in that: Butt welding speed V j,h The correction formula is: V′ j,h =V j,h ±DEV j,h *α Among them, V' j,h V represents the adjusted welding speed of the jth and hth weld sections, j,h It represents the original welding speed of the jth and hth weld sections, and α represents the correction coefficient.

9. A neural network-based arc additive manufacturing weld bead interlayer control system, used in the additive manufacturing weld bead interlayer control method according to any one of claims 1 to 8, characterized in that: include: Scanning module, to obtain point cloud data of the current cladding layer surface; A neural network prediction module outputs target cladding layer characteristic data based on input target cladding layer process parameters; The accumulation module adds the target cladding layer feature data and the current cladding layer point cloud data to obtain the predicted layer point cloud data; The interlayer control module calculates the deviation between the target model and the predicted layer point cloud data. If the deviation exceeds the preset threshold, the target cladding layer process parameters are adjusted until the deviation meets the preset threshold requirements. The adjusted target cladding layer process parameters are input into the arc additive equipment to execute the target cladding layer deposition.

10. A robotic arc additive manufacturing device equipped with the additive manufacturing weld bead forming interlayer control system of claim 9, used to implement the additive manufacturing weld bead forming interlayer control method of any one of claims 1 to 8, characterized in that: It includes a welding robot, an argon arc welding gun fixed at the end of the welding robot, a 3D scanner, an industrial computer, an electric welder, and a robot controller. The 3D scanner collects the current point cloud data of arc additive manufacturing structural parts, and the industrial computer receives and processes the data.

Images