A method, apparatus, device, and storage medium for generating welding paths.

Abstract

This invention discloses a welding path generation method, apparatus, device, and storage medium, comprising: establishing a welding finite element simulation model for the part to be welded, and obtaining parameter information for each analysis step from the simulation results of the model; obtaining the planned point cloud cluster and the active point cloud cluster of the activated units in each analysis step based on the parameter information; obtaining the offset rotation matrix for each analysis step based on the planned point cloud cluster and the active point cloud cluster; and generating the welding path for the part to be welded based on the offset rotation matrix. By collecting the planned coordinates, active coordinates, and activation temperature of the active units in each analysis step, and obtaining the offset rotation matrix for each analysis step based on the activation temperature, the planned path in the welding process is adjusted according to the offset rotation matrix, thereby taking into account the temperature-induced deformation during the welding process, making the generated welding path more consistent with the actual production scenario and improving the accuracy of part welding.

Description

Technical Field

[0001] This invention relates to the field of welding technology, and in particular to a welding path generation method, apparatus, equipment, and storage medium. Background Technology

[0002] Currently, robotic welding mainly uses teach programming or offline programming to program the welding trajectory path. Teach programming is based on the actual weld seam of the part; offline programming is based on the geometric model of the part.

[0003] However, during the actual welding process, the temperature rise at the welding position can cause deformation of the welded parts, resulting in a shift in the weld position. This leads to a mismatch between the program path and the weld of the part, causing weld deviation and affecting the quality of the part product. Summary of the Invention

[0004] This invention provides a welding path generation method, apparatus, device, and storage medium for generating accurate welding paths.

[0005] According to a first aspect of the present invention, a welding path generation method is provided, comprising: establishing a welding finite element simulation model for the parts to be welded, and obtaining parameter information for each analysis step from the simulation results of the model, wherein the parameter information includes the planned coordinates, activation coordinates and activation temperature of the element nodes in the activated element;

[0006] Based on the parameter information, obtain the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step;

[0007] For each analysis step, an offset rotation matrix is ​​obtained based on the planned point cloud cluster and the activated point cloud cluster;

[0008] The welding path of the part to be welded is generated based on the offset rotation matrix.

[0009] Optionally, the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step are obtained based on the parameter information, including:

[0010] For each node in the activated unit, the activation temperature is converted to obtain a grayscale value according to a specified method, wherein the specified method includes single-channel conversion or three-channel conversion;

[0011] The grayscale value of each node in the activated unit is combined with its own planned coordinates to obtain the planned point cloud cluster;

[0012] The activation point cloud cluster is obtained by combining the grayscale value of each node in the activated unit with its own activation coordinates.

[0013] Optionally, for each analysis step, an offset rotation matrix is ​​obtained based on the planned point cloud cluster and the activated point cloud cluster, including:

[0014] For each analysis step, coarse registration is performed between the planned point cloud cluster and the activated point cloud cluster to obtain coarse registration results;

[0015] The offset rotation matrix is ​​obtained by performing fine registration on the coarse registration result using an iterative nearest-point algorithm based on color.

[0016] Optionally, after obtaining the offset rotation matrix based on the planned point cloud cluster and the activated point cloud cluster for each analysis step, the method further includes:

[0017] The current offset rotation matrix of the current analysis step is obtained by traversing each analysis step;

[0018] Obtain the adjacent offset rotation matrices of a specified number of analysis steps adjacent to the current analysis step, and construct an offset rotation matrix set based on the adjacent offset rotation matrices and the current offset rotation matrix;

[0019] The current offset rotation matrix is ​​smoothed according to the set of offset rotation matrices.

[0020] Optionally, the current offset rotation matrix is ​​smoothed according to the set of offset rotation matrices, including:

[0021] Extract the Euler angles of each rotation matrix in the offset rotation matrix set, and calculate the average Euler angle by averaging all Euler angles. Obtain the average rotation matrix based on the average Euler angle.

[0022] Extract each offset vector from the offset rotation matrix set, and calculate the average offset vector by averaging all offset vectors.

[0023] The smoothed current offset rotation matrix is ​​obtained based on the average rotation matrix and the average offset vector.

[0024] Optionally, generating the welding path for the part to be welded based on the offset rotation matrix includes:

[0025] Extract the welding torch pose information for each analysis step from the simulation results;

[0026] For each analysis step, the welding torch pose information is corrected according to the offset rotation matrix to obtain the corrected welding torch pose information;

[0027] The welding path is generated based on the corrected welding torch pose information from each analysis step.

[0028] Optionally, after generating the welding path for the part to be welded based on the offset rotation matrix, the method further includes:

[0029] The welding path is inspected;

[0030] When the welding path is deemed to be qualified, the parts to be welded are welded according to the welding path.

[0031] According to another aspect of the present invention, a welding path generation device is provided, the device comprising: a model simulation module for establishing a welding finite element simulation model for the part to be welded, and obtaining parameter information for each analysis step from the simulation results of the model, wherein the parameter information includes the planned coordinates, activation coordinates and activation temperature of the element nodes in the activated element;

[0032] The point cloud cluster acquisition module is used to acquire the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step based on the parameter information.

[0033] The offset rotation matrix acquisition module is used to acquire the offset rotation matrix for each analysis step based on the planned point cloud cluster and the activated point cloud cluster.

[0034] The welding path generation module is used to generate the welding path of the part to be welded based on the offset rotation matrix.

[0035] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: one or more processors;

[0036] Storage device for storing one or more programs.

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any embodiment of the present invention.

[0038] According to another aspect of the present invention, a storage medium for computer-executable instructions is provided, on which a computer program is stored, which, when executed by a processor, implements the method as described in any of the embodiments of the present invention.

[0039] The technical solution of the present invention collects the planned coordinates, activation coordinates and activation temperature of the activation unit in each analysis step, and obtains the offset rotation matrix of each analysis step according to the activation temperature. The planned path in the welding process is adjusted according to the offset rotation matrix, thereby taking into account the deformation caused by temperature in the welding process, making the generated welding path more in line with the actual production scenario and improving the accuracy of part welding.

[0040] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of a welding path generation method provided in Embodiment 1 of the present invention;

[0043] Figure 2 This is a schematic diagram of the welding finite element simulation model provided in Embodiment 1 of the present invention;

[0044] Figure 3 This is a schematic diagram of the welding simulation results provided in Embodiment 1 of the present invention;

[0045] Figure 4 This is a schematic diagram of the temperature distribution at the unit planning position and the activation position according to Embodiment 1 of the present invention;

[0046] Figure 5 This is a schematic diagram of a planned point cloud cluster and an activated point cloud cluster according to Embodiment 1 of the present invention;

[0047] Figure 6 This is a flowchart of a welding path generation method provided in Embodiment 2 of the present invention;

[0048] Figure 7 This is a schematic diagram of a welding path generation device according to Embodiment 3 of the present invention;

[0049] Figure 8 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0050] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0051] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or terminal device that includes 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 terminal devices.

[0052] Example 1

[0053] Figure 1 This is a flowchart of a welding path generation method provided in Embodiment 1 of the present invention. This embodiment is applicable to welding path generation. The method can be executed by a welding path generation device, which can be implemented in hardware and / or software, and can be integrated into an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0054] S101. Establish a welding finite element simulation model for the parts to be welded, and obtain the parameter information for each analysis step from the simulation results of the model.

[0055] Specifically, in this embodiment, after obtaining the basic parameters of the parts to be welded, a welding finite element simulation model based on birth and death elements will be established, such as... Figure 2 The diagram shows a schematic of a welding finite element simulation model. The specific requirements for creating the simulation model include: birth and death elements, material model, and boundary conditions. Birth and death elements mainly include the elements corresponding to the weld filler material of the welding process. The material model includes the mechanical and thermal properties of the part to be welded. The boundary condition constraints should also be consistent with the constraints of the actual welding process of the part.

[0056] In this embodiment, a welding finite element simulation model is simulated and simulation results are obtained, such as... Figure 3 The diagram shown illustrates the welding simulation results. After obtaining the simulation results, they are calibrated. The calibration is considered successful when the deformation during the simulation largely matches the actual welding process. Figure 3The simulation results show that the part underwent significant deformation, consistent with the actual welding process. In this embodiment, parameter information for each analysis step is obtained from the simulation results. This parameter information includes the planned coordinates, activation coordinates, and activation temperature of the element nodes in the activated unit. For example, when the analysis steps include N steps, each analysis step corresponds to an activated dead element, i.e., an activated unit. Each activated unit includes multiple element nodes. The analysis results include the planned coordinates, activation coordinates, and activation temperature of each element node. The planned coordinates are (x... 规划 ,y 规划 ,z 规划 ), refers to the original planned coordinates before deformation; the active coordinate is (x 激活 ,y 激活 ,z 激活 The coordinates of the element node are determined by deformation when it is activated. The temperature at activation is T, which refers to the actual temperature when the element node is in the activated state, i.e., during simulated welding. Figure 4 The diagram shows the temperature distribution at the planned and activated locations of the unit. Of course, this embodiment is only an example and does not limit the planned and activated locations.

[0057] S102, based on parameter information, obtain the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step.

[0058] Optionally, the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step are obtained based on the parameter information, including: converting the activation temperature of each unit node in the activated unit according to a specified method to obtain grayscale values, wherein the specified method includes single-channel conversion or three-channel conversion; combining the grayscale values ​​of each unit node in the activated unit with its own planned coordinates to obtain the planned point cloud cluster; and combining the grayscale values ​​of each unit node in the activated unit with its own activation coordinates to obtain the activated point cloud cluster.

[0059] Specifically, when a dead cell is activated and becomes an active cell, the heat source of the welded body is applied to these cells. The cell nodes on these activated cells are assigned corresponding temperature values. Therefore, in this embodiment, the temperature values ​​are converted into single-channel or three-channel values ​​and assigned to the corresponding cell nodes. Thus, each cell node, in addition to containing (x, y, z) coordinate values, can also contain three-channel (R, G, B) or single-channel Gray values, thereby converting the cell nodes into colored point cloud data. Since a cell contains multiple cell nodes, the grayscale values ​​of each cell node in the activated cell are combined with its own planned coordinates to obtain the planned point cloud cluster (PointCloud). 规划The grayscale value of each node in the activated unit is combined with its own activation coordinates to obtain the PointCloud cluster. 激活 ,like Figure 5 The diagram shows the planning and activation of point cloud clusters. Of course, this embodiment is only an example and does not limit the size of the point cloud clusters.

[0060] S103, for each analysis step, obtain the offset rotation matrix based on the planned point cloud cluster and the activated point cloud cluster.

[0061] Optionally, for each analysis step, an offset rotation matrix is ​​obtained based on the planned point cloud cluster and the active point cloud cluster, including: performing coarse registration between the planned point cloud cluster and the active point cloud cluster for each analysis step to obtain a coarse registration result; and performing fine registration on the coarse registration result based on the color-based iterative nearest point algorithm to obtain the offset rotation matrix.

[0062] Optionally, after obtaining the offset rotation matrix for each analysis step based on the planned point cloud cluster and the activated point cloud cluster, the method further includes: traversing each analysis step to obtain the current offset rotation matrix of the current analysis step; obtaining the adjacent offset rotation matrices of a specified number of analysis steps adjacent to the current analysis step, and constructing an offset rotation matrix set based on the adjacent offset rotation matrices and the current offset rotation matrix; and smoothing the current offset rotation matrix based on the offset rotation matrix set.

[0063] Optionally, the current offset rotation matrix is ​​smoothed according to the offset rotation matrix set, including: extracting the Euler angles of each rotation matrix in the offset rotation matrix set, and calculating the average Euler angle by averaging all Euler angles, and obtaining the average rotation matrix based on the average Euler angle; extracting each offset vector in the offset rotation matrix set, and calculating the average offset vector by averaging all offset vectors; and obtaining the smoothed current offset rotation matrix based on the average rotation matrix and the average offset vector.

[0064] Specifically, in this embodiment, after obtaining the planned point cloud cluster and the active point cloud cluster in each analysis step, the two point cloud clusters are coarsely registered, and then finely registered based on the iterative nearest point algorithm of color to obtain the active point cloud cluster PointCloud. 激活 Compared to planning point cloud clusters (PointCloud) 规划 The offset rotation matrix, since it includes N analysis steps, will form an offset rotation matrix sequence set {Z1, Z2, ..., Zn} based on the offset rotation matrix corresponding to each analysis step. 2.。。。 Z N Furthermore, after obtaining the offset rotation matrix for each analysis step, this embodiment performs smoothing processing on the offset rotation matrix to further improve its accuracy. For the current offset rotation matrix Z corresponding to the current analysis step i... iDuring smoothing, the first k and last k offset rotation matrices are collected from the offset rotation matrix sequence set. The offset rotation matrix set is formed by 2k+1 offset rotation matrices. Since the offset rotation matrix Z contains both the rotation matrix R and the offset vector T, smoothing operations will be performed on them separately in this embodiment.

[0065] This involves obtaining the rotation matrix from each offset rotation matrix in the offset rotation matrix set. Euler angles [ϕ,θ,ψ], for example, the offset rotation matrix Z in the current analysis step. i The rotation matrix part included in At that time, R i The corresponding Euler angles They are respectively Of course, this embodiment is only for obtaining R. i Taking Euler angles as an example, the method for obtaining Euler angles for other rotation matrices is roughly the same, and this implementation does not limit it. After obtaining the Euler angles corresponding to the previous K and next K analysis steps of the current analysis step, the average Euler angle is obtained by averaging all Euler angles. For example... The average Euler angles are converted into the corresponding average rotation matrix R. 平均 Of course, this embodiment is only an example and does not limit the specific method of obtaining the average rotation matrix.

[0066] In addition, this embodiment will decompose each offset rotation matrix in the offset rotation matrix set to obtain the offset vector. For example, the offset rotation matrix Z in the current analysis step i The corresponding offset vector Of course, this embodiment is only an example; the format of other offset vectors is the same as T. i The general principles are similar, and this implementation does not limit the specifics. After obtaining the offset vectors corresponding to the K preceding and K following analysis steps of the current analysis step, the average offset vector T is calculated by averaging all offsets. i平均 Of course, this embodiment is merely an example and does not limit the specific method for obtaining the average offset vector. The average rotation matrix R is obtained through the above solution process. i平均 and average offset vector T i平均 Next, the average rotation matrix R will be... i平均 and average offset vector T i平均 Recombining the components yields the offset rotation matrix Z corresponding to the current analysis step i. i Smoothed current offset rotation matrix Z i平均 =[Ri平均 ,T i平均 Of course, this embodiment only takes the current analysis step i as an example for explanation. The smoothing process of the offset rotation matrix for other analysis steps is roughly the same, and will not be described in detail in this embodiment.

[0067] S104, Generate the welding path of the part to be welded based on the offset rotation matrix.

[0068] Optionally, the welding path of the part to be welded is generated based on the offset rotation matrix, including: extracting the welding gun pose information of each analysis step from the simulation results; correcting the welding gun pose information of each analysis step based on the offset rotation matrix to obtain the corrected welding gun pose information; and generating the welding path based on the corrected welding gun pose information of each analysis step.

[0069] Specifically, since the simulation results include the welding torch pose information for each analysis step, for example, the welding torch pose information for the i-th analysis step is POS. i And in POS i Specifically, this includes the position and orientation of the welding torch in the i-th analysis step. Therefore, for each sub-analysis step, the offset rotation matrix Z will be... i平均 =[R i平均 ,T i平均 By correcting the welding torch pose information POSi, the corrected welding torch pose information POS can be obtained. i校正 Once the welding position information of each analysis step has been corrected, the welding path is generated based on the corrected welding gun position information of each analysis step.

[0070] The technical solution of this invention collects the planned coordinates, activation coordinates, and activation temperature of the activation unit in each analysis step, and obtains the offset rotation matrix of each analysis step based on the activation temperature. The planned path in the welding process is adjusted based on the offset rotation matrix, thereby taking into account the temperature-induced deformation in the welding process. This makes the generated welding path more consistent with the actual production scenario and improves the accuracy of part welding.

[0071] Example 2

[0072] Figure 6 This is a flowchart of another welding path generation method provided by an embodiment of the present invention. Based on the above embodiment, after generating the welding path of the part to be welded according to the offset rotation matrix, the method further includes: detecting the welding path; when the welding path is determined to be qualified, welding is performed on the part to be welded according to the welding path, such as... Figure 6 As shown, the method includes:

[0073] S201. Establish a welding finite element simulation model for the parts to be welded, and obtain the parameter information for each analysis step from the simulation results of the model.

[0074] S202, based on parameter information, obtain the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step.

[0075] Optionally, the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step are obtained based on the parameter information, including: converting the activation temperature of each unit node in the activated unit according to a specified method to obtain grayscale values, wherein the specified method includes single-channel conversion or three-channel conversion; combining the grayscale values ​​of each unit node in the activated unit with its own planned coordinates to obtain the planned point cloud cluster; and combining the grayscale values ​​of each unit node in the activated unit with its own activation coordinates to obtain the activated point cloud cluster.

[0076] S203, for each analysis step, obtain the offset rotation matrix based on the planned point cloud cluster and the activated point cloud cluster.

[0077] Optionally, for each analysis step, an offset rotation matrix is ​​obtained based on the planned point cloud cluster and the active point cloud cluster, including: performing coarse registration between the planned point cloud cluster and the active point cloud cluster for each analysis step to obtain a coarse registration result; and performing fine registration on the coarse registration result based on the color-based iterative nearest point algorithm to obtain the offset rotation matrix.

[0078] Optionally, after obtaining the offset rotation matrix for each analysis step based on the planned point cloud cluster and the activated point cloud cluster, the method further includes: traversing each analysis step to obtain the current offset rotation matrix of the current analysis step; obtaining the adjacent offset rotation matrices of a specified number of analysis steps adjacent to the current analysis step, and constructing an offset rotation matrix set based on the adjacent offset rotation matrices and the current offset rotation matrix; and smoothing the current offset rotation matrix based on the offset rotation matrix set.

[0079] Optionally, the current offset rotation matrix is ​​smoothed according to the offset rotation matrix set, including: extracting the Euler angles of each rotation matrix in the offset rotation matrix set, and calculating the average Euler angle by averaging all Euler angles, and obtaining the average rotation matrix based on the average Euler angle; extracting each offset vector in the offset rotation matrix set, and calculating the average offset vector by averaging all offset vectors; and obtaining the smoothed current offset rotation matrix based on the average rotation matrix and the average offset vector.

[0080] S204, Generate the welding path of the part to be welded based on the offset rotation matrix.

[0081] Optionally, the welding path of the part to be welded is generated based on the offset rotation matrix, including: extracting the welding gun pose information of each analysis step from the simulation results; correcting the welding gun pose information of each analysis step based on the offset rotation matrix to obtain the corrected welding gun pose information; and generating the welding path based on the corrected welding gun pose information of each analysis step.

[0082] S205, inspect the welding path. When the welding path is deemed to be qualified, weld the parts to be welded according to the welding path.

[0083] Specifically, in this embodiment, after obtaining the welding path based on the simulation results, the welding path is checked for compliance. During the check, the deviation coefficient between the welding path and the planned path is obtained. When the deviation coefficient is greater than a specified value, the check is deemed unqualified. The deviation coefficient is calculated by obtaining the error between the welding path and the analysis step at each analysis step, and the average of the errors in N analysis steps is used as the deviation coefficient. Of course, this embodiment is only an example and does not limit the specific calculation method of the deviation coefficient. As long as it can reflect the degree of deviation between the planned path and the welding path, it is within the scope of protection of this application. Although the planned path does not consider the deformation caused by temperature factors, it is still relatively consistent with the actual welding machine situation. When the generated welding path deviates significantly from the planned path, it indicates that the generated welding path does not match the actual welding situation, and therefore the check is deemed unqualified. Of course, this embodiment is only an example and does not limit the specific detection method of the welding path.

[0084] It should be noted that when the welding path is confirmed to be qualified, the welding path will be sent to the welding torch, which will then instruct the welding torch to weld on the part to be welded according to the determined welding path. The welding process of the part will be monitored in real time. When it is determined that the welding torch is not welding according to the planned path, an alarm will be generated to notify the user in a timely manner that an abnormality has occurred in the current welding process, so that the user can promptly oppose the welding process for maintenance and adjustment.

[0085] The technical solution of this invention collects the planned coordinates, activation coordinates, and activation temperature of the activation unit in each analysis step, and obtains the offset rotation matrix of each analysis step based on the activation temperature. The planned path in the welding process is adjusted based on the offset rotation matrix, thereby taking into account the temperature-induced deformation in the welding process. This makes the generated welding path more consistent with the actual production scenario and improves the accuracy of part welding.

[0086] Example 3

[0087] Figure 7 This is a schematic diagram of a welding path generation device provided in an embodiment of the present invention. Figure 7As shown, the device includes: a model simulation module 310, a point cloud cluster acquisition module 320, an offset rotation matrix acquisition module 330, and a welding path generation module 340.

[0088] The model simulation module 310 is used to establish a welding finite element simulation model for the part to be welded, and to obtain the parameter information of each analysis step from the simulation results of the model. The parameter information includes the planned coordinates, activation coordinates and temperature at activation of the element nodes in the activated element.

[0089] The point cloud cluster acquisition module 320 is used to acquire the planned point cloud clusters and activated point cloud clusters of the activated units in each analysis step based on parameter information.

[0090] The offset rotation matrix acquisition module 330 is used to acquire the offset rotation matrix for each analysis step based on the planned point cloud cluster and the activated point cloud cluster.

[0091] The welding path generation module 340 is used to generate the welding path of the part to be welded based on the offset rotation matrix.

[0092] Optionally, a point cloud cluster acquisition module is used to convert the activation temperature of each unit node in the activated unit to obtain grayscale values ​​according to a specified method, wherein the specified method includes single-channel conversion or three-channel conversion.

[0093] The grayscale value of each node in the activated unit is combined with its own planning coordinates to obtain the planning point cloud cluster;

[0094] The grayscale value of each node in the activated unit is combined with its own activation coordinates to obtain the activation point cloud cluster.

[0095] Optionally, an offset rotation matrix acquisition module is used to perform coarse registration between the planned point cloud cluster and the activated point cloud cluster for each analysis step to obtain coarse registration results;

[0096] The coarse registration result is finely registered using an iterative nearest-point algorithm based on color to obtain the offset rotation matrix.

[0097] Optionally, the device also includes an offset rotation matrix smoothing module, used to traverse each analysis step to obtain the current offset rotation matrix of the current analysis step;

[0098] Obtain the adjacent offset rotation matrices of a specified number of analysis steps adjacent to the current analysis step, and construct an offset rotation matrix set based on the adjacent offset rotation matrices and the current offset rotation matrix;

[0099] The current offset rotation matrix is ​​smoothed based on the set of offset rotation matrices.

[0100] Optionally, an offset rotation matrix smoothing module is used to extract the Euler angles of each rotation matrix in the offset rotation matrix set, calculate the average Euler angles by averaging all Euler angles, and obtain the average rotation matrix based on the average Euler angles.

[0101] Extract each offset vector from the offset rotation matrix set, and calculate the average offset vector by averaging all offset vectors.

[0102] Obtain the smoothed current offset rotation matrix based on the average rotation matrix and the average offset vector.

[0103] Optionally, a welding path generation module is used to extract the welding gun pose information for each analysis step from the simulation results;

[0104] For each analysis step, the welding torch pose information is corrected according to the offset rotation matrix to obtain the corrected welding torch pose information.

[0105] The welding path is generated based on the corrected welding torch pose information from each analysis step.

[0106] Optionally, the device also includes a welding path detection module for detecting the welding path;

[0107] Once the welding path inspection is confirmed to be qualified, the parts to be welded are welded according to the welding path.

[0108] The welding path generation device provided in this embodiment of the invention can execute a welding path generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0109] Example 4

[0110] Figure 8 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0111] The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0112] like Figure 8As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0113] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other electronic devices through computer networks such as the Internet and / or various telecommunications networks.

[0114] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the solder path generation method.

[0115] That is, a welding finite element simulation model is established for the parts to be welded, and the parameter information of each analysis step is obtained from the simulation results of the model. The parameter information includes the planned coordinates, activation coordinates and temperature at activation of the element nodes in the activated element.

[0116] Based on the parameter information, obtain the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step;

[0117] For each analysis step, the offset rotation matrix is ​​obtained based on the planned point cloud cluster and the activated point cloud cluster;

[0118] The welding path of the part to be welded is generated based on the offset rotation matrix.

[0119] In some embodiments, the weld path generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the weld path generation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the weld path generation method by any other suitable means (e.g., by means of firmware).

[0120] Various embodiments of the apparatuses and techniques described above herein can be implemented in digital electronic circuit devices, integrated circuit devices, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), device-on-a-chip (SoC) devices, complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable device including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage device, at least one input device, and at least one output device, and transmitting data and instructions to the storage device, the at least one input device, and the at least one output device.

[0121] Computer programs used to implement the welding path generation method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other non-stop data migration device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution apparatus, device, or electronic device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage electronics, magnetic storage electronics, or any suitable combination thereof.

[0123] To provide interaction with a user, the devices and techniques described herein can be implemented on an electronic device having: a display device (e.g., a touchscreen) for displaying information to the user; and buttons through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0124] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0125] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating welding paths, characterized in that, The method includes: A welding finite element simulation model is established for the parts to be welded, and the parameter information of each analysis step is obtained from the simulation results of the model. The parameter information includes the planned coordinates, activation coordinates and activation temperature of the element nodes in the activated element. Based on the parameter information, obtain the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step; For each analysis step, an offset rotation matrix is ​​obtained based on the planned point cloud cluster and the activated point cloud cluster; The welding path of the part to be welded is generated based on the offset rotation matrix; After obtaining the offset rotation matrix for each analysis step based on the planned point cloud cluster and the activated point cloud cluster, the method further includes: traversing each analysis step to obtain the current offset rotation matrix of the current analysis step; obtaining the adjacent offset rotation matrices of a specified number of analysis steps adjacent to the current analysis step; constructing an offset rotation matrix set based on the adjacent offset rotation matrices and the current offset rotation matrix; and smoothing the current offset rotation matrix based on the offset rotation matrix set. Smoothing the current offset rotation matrix based on the offset rotation matrix set includes: extracting the Euler angles of each rotation matrix in the offset rotation matrix set, and calculating the average Euler angles by averaging all Euler angles to obtain the average Euler angles; obtaining the average rotation matrix based on the average Euler angles; extracting each offset vector in the offset rotation matrix set, and calculating the average offset vector by averaging all offset vectors to obtain the average offset vector; and obtaining the smoothed current offset rotation matrix based on the average rotation matrix and the average offset vector.

2. The method according to claim 1, characterized in that, The step of obtaining the planned point cloud cluster and activated point cloud cluster of the activated unit in each analysis step based on the parameter information includes: For each node in the activated unit, the activation temperature is converted to obtain a grayscale value according to a specified method, wherein the specified method includes single-channel conversion or three-channel conversion; The grayscale value of each node in the activated unit is combined with its own planned coordinates to obtain the planned point cloud cluster; The activation point cloud cluster is obtained by combining the grayscale value of each node in the activated unit with its own activation coordinates.

3. The method according to claim 1, characterized in that, The step of obtaining the offset rotation matrix for each analysis step based on the planned point cloud cluster and the activated point cloud cluster includes: For each analysis step, coarse registration is performed between the planned point cloud cluster and the activated point cloud cluster to obtain coarse registration results; The offset rotation matrix is ​​obtained by performing fine registration on the coarse registration result using an iterative nearest-point algorithm based on color.

4. The method according to claim 1, characterized in that, The step of generating the welding path for the part to be welded based on the offset rotation matrix includes: Extract the welding torch pose information for each analysis step from the simulation results; For each analysis step, the welding torch pose information is corrected according to the offset rotation matrix to obtain the corrected welding torch pose information; The welding path is generated based on the corrected welding torch pose information from each analysis step.

5. The method according to claim 1, characterized in that, After generating the welding path for the part to be welded based on the offset rotation matrix, the method further includes: The welding path is inspected; When the welding path is deemed to be qualified, the parts to be welded are welded according to the welding path.

6. A welding path generation device, characterized in that, The device includes: The model simulation module is used to establish a welding finite element simulation model for the parts to be welded, and to obtain parameter information for each analysis step from the simulation results of the model. The parameter information includes the planned coordinates, activation coordinates and activation temperature of the element nodes in the activated element. The point cloud cluster acquisition module is used to acquire the planned point cloud cluster and the activated point cloud cluster of the activated unit in each analysis step based on the parameter information. The offset rotation matrix acquisition module is used to acquire the offset rotation matrix for each analysis step based on the planned point cloud cluster and the activated point cloud cluster. A welding path generation module is used to generate a welding path for the part to be welded based on the offset rotation matrix. The device further includes an offset rotation matrix smoothing module, which is used to traverse each analysis step to obtain the current offset rotation matrix of the current analysis step; obtain the adjacent offset rotation matrices of a specified number of analysis steps adjacent to the current analysis step; construct an offset rotation matrix set based on the adjacent offset rotation matrices and the current offset rotation matrix; and perform smoothing processing on the current offset rotation matrix based on the offset rotation matrix set. The offset rotation matrix smoothing module is further configured to extract the Euler angles of each rotation matrix in the offset rotation matrix set, calculate the average Euler angle by averaging all Euler angles, and obtain the average rotation matrix based on the average Euler angle; extract each offset vector in the offset rotation matrix set, calculate the average offset vector by averaging all offset vectors; and obtain the smoothed current offset rotation matrix based on the average rotation matrix and the average offset vector.

7. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

8. A storage medium for computer-executable instructions, wherein a computer program is stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

Images