A welding point detection method and system based on dual manipulator collaboration

Abstract

The present invention provides a solder joint detection method and system based on dual-manipulator collaboration, which relates to the field of solder joint detection technology. The method comprises determining second solder joint parameter information and solder joint feature information based on the digital model of the workpiece to be tested and the first solder joint parameter information; determining a detection area and isolated solder joints by merging adjacent solder joints with similar geometric features based on the solder joint feature information, determining the centroid of the detection area, and defining the centroid and isolated solder joints as path control points; determining node values ​​and basis functions corresponding to the node values ​​based on the path control points, and determining path point coordinates based on the basis functions, path control points, and control point weights; optimizing the path point coordinates to determine a first trajectory, and correcting the first trajectory to determine a second trajectory; controlling one manipulator to clamp the workpiece to be tested and causing the other manipulator to move around the workpiece to be tested along the second trajectory to detect the solder joints. The present invention solves the problem in the prior art of the lack of a solder joint detection method with high welding detection accuracy and efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of solder joint detection, and in particular to a solder joint detection method and system based on dual manipulator collaboration. Background Art

[0002] In some sheet metal processing situations, it is necessary to fix the sheet metal parts to other parts. The fixing method is mostly welding. When welding is completed, the size and shape of the welds need to be inspected to ensure the welding quality.

[0003] In the prior art, to achieve automated manufacturing, solder joints on sheet metal parts are typically inspected using a robotic arm carrying a detection device. This typically generates a corresponding detection path based on a theoretical model of the sheet metal part, and performs scanning inspection using fixed-step infrared, X-ray, or ultrasonic detection equipment. However, when the spacing between solder joints is large, sequential scanning using a fixed path results in a high number of idle strokes, affecting inspection efficiency. When the spacing between solder joints is small, the robotic arm must be moved frequently, causing jitter during movement to affect scanning inspection accuracy, which in turn affects solder joint inspection accuracy. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a welding spot detection method based on dual manipulator collaboration, aiming to solve the problem in the prior art of the lack of a welding spot detection method with high welding detection accuracy and efficiency.

[0005] According to an embodiment of the present invention, a method for detecting solder joints based on dual manipulator collaboration includes:

[0006] Receiving a digital model of a piece to be tested and first solder point parameter information, determining second solder point parameter information according to the digital model of the piece to be tested and the first solder point parameter information, and combining the first solder point parameter information and the second solder point parameter information to determine solder point feature information;

[0007] Determining a detection area and isolated welds by merging adjacent welds with similar geometric features according to the weld feature information, determining a centroid of the detection area, and defining the centroid and the isolated welds as path control points;

[0008] Determining node values ​​and basis functions corresponding to the node values ​​according to the path control points, so as to determine path point coordinates according to the basis functions, the path control points and the control point weights;

[0009] Optimizing the path point coordinates to determine a first trajectory so that the time target and the energy target of the first trajectory are optimized, and correcting the first trajectory to determine a second trajectory so that the second trajectory does not collide with the device under test or the environment;

[0010] A manipulator is controlled to clamp the workpiece to be tested, and another manipulator is controlled to move around the workpiece to be tested according to the second trajectory, so that a detection device on the manipulator detects the solder joints on the workpiece to be tested.

[0011] In addition, the solder joint detection method based on dual manipulator collaboration according to the above embodiment of the present invention may also have the following additional technical features:

[0012] Furthermore, the first solder point parameter information includes a solder point coordinate matrix, and the step of determining the second solder point parameter information according to the DUT digital model and the first solder point parameter information includes:

[0013] Converting the digital model of the test piece into a triangular mesh;

[0014] The local curvature radius of the surface where each welding point is located is calculated by the rate of change of the normal vectors of adjacent triangles;

[0015] The material thickness corresponding to each solder joint area is determined according to the digital model of the test piece and the solder joint coordinate matrix, and the local curvature radius and the material thickness are the second solder joint parameters.

[0016] Furthermore, the step of determining the detection area and isolated solder joints by merging adjacent solder joints with similar geometric features according to the solder joint feature information includes:

[0017] Determine a target distance between each welding point and other welding points according to a preset distance formula, and regard welding points whose target distance is less than a first preset value as neighboring points;

[0018] The welding point having the number of neighboring points greater than a second preset value is set as a core point, and the neighboring points corresponding to the core point are merged starting from the core point to form the detection area, and the welding points outside the detection area are the isolated welding points;

[0019] The preset distance formula is:

[0020]

[0021] in, is the difference between the coordinates of the two welding points, is the difference in curvature radius between the two welding points, is the difference in thickness between the two welding points, is the weight parameter.

[0022] Furthermore, the steps of determining the centroid of the detection area and defining the centroid and the isolated weld as path control points, and determining the path point coordinates according to the basis function, the path control points and the control point weights include:

[0023] Calculating the centroid of the detection area by a preset centroid formula, and defining the centroid and the isolated welding point as path control points;

[0024] Determine the node vector and the corresponding node value according to the path control point using a preset parameter formula;

[0025] Recursively calculating the third-order NURBS basis function corresponding to the node value;

[0026] Determine the path point coordinates using a preset trajectory point formula according to the basis function, the path control points and the control point weights;

[0027] The preset centroid formula is:

[0028]

[0029] in, is the coordinate of the path control point;

[0030] The preset parameter formula is:

[0031]

[0032] For the The value of the node, For the The coordinates of the path control points corresponding to the nodes, For adjacent control points nodes and The Euclidean distance between nodes, is the sum of the Euclidean distances between all adjacent control points;

[0033] The preset trajectory point formula is:

[0034]

[0035] in, is the basis function corresponding to the node value, is the weight parameter, are the coordinates of the control points.

[0036] Furthermore, the step of optimizing the path point coordinates to determine the first trajectory so as to optimize the time target and the energy target of the first trajectory includes:

[0037] Randomly sorting the path point coordinates to determine a first preset number of candidate paths and energy targets and time targets corresponding to the candidate paths;

[0038] Performing non-dominated sorting on the candidate paths according to the time target and the energy target to determine the corresponding ranks of the candidate paths;

[0039] Determine a high-quality path based on the level and congestion corresponding to the candidate path, and then determine a child path based on the high-quality path by performing path intersection at a preset intersection rate;

[0040] The high-quality path and the child path are fine-tuned according to a preset mutation rate and screened according to the level and congestion to determine a second preset number of first trajectories.

[0041] Furthermore, the step of correcting the first trajectory to determine the second trajectory includes:

[0042] Performing hierarchical encirclement and detection on the first track to determine whether the distance between a track point in the first track and the digital model of the device to be tested is less than a preset distance;

[0043] If a local obstacle avoidance trajectory is determined according to the first trajectory and the digital model of the device under test, the first trajectory is adjusted, and the adjusted first trajectory is screened to determine the second trajectory.

[0044] Furthermore, the step of the detection device on the manipulator detecting the solder joints on the workpiece to be tested includes:

[0045] Determining the type of the target to be measured; if the target to be measured is an isolated weld spot, determining an arcuate area with a preset radius centered on the isolated weld spot, determining a corresponding real-time step length according to a preset step length calculation formula based on the real-time curvature of the arcuate area, and scanning and detecting the arcuate area according to the real-time step length and a preset speed;

[0046] If the target to be detected is the detection area, scanning and detecting the detection area according to the real-time step size and the preset speed;

[0047] The preset step length calculation formula is:

[0048]

[0049] Among them, R is the real-time curvature, is the real-time step size.

[0050] Another object of an embodiment of the present invention is to provide a solder joint detection system based on dual manipulator collaboration, the system comprising:

[0051] a solder joint characteristic information determination module, configured to receive a digital model of a piece to be tested and first solder joint parameter information, determine second solder joint parameter information based on the digital model of the piece to be tested and the first solder joint parameter information, and combine the first solder joint parameter information and the second solder joint parameter information to determine solder joint characteristic information;

[0052] a path control point determination module, configured to determine a detection area and isolated welds by merging adjacent welds with similar geometric features according to the weld feature information, determine the centroid of the detection area, and define the centroid and the isolated welds as path control points;

[0053] a path point coordinate determination module, configured to determine a node value and a basis function corresponding to the node value according to the path control point, so as to determine the path point coordinates according to the basis function, the path control point and the control point weight;

[0054] a second trajectory determination module, configured to optimize the path point coordinates to determine a first trajectory so as to optimize the time target and the energy target of the first trajectory, and to correct the first trajectory to determine a second trajectory so as to prevent the second trajectory from colliding with the object under test or the environment;

[0055] The detection module is used to control a manipulator to clamp the test piece, and control another manipulator to move around the test piece according to the second trajectory, so that the detection device on the manipulator detects the solder joints on the test piece.

[0056] Another object of an embodiment of the present invention is to provide a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned solder joint detection method based on dual-manipulator collaboration.

[0057] Another object of an embodiment of the present invention is to provide an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the above-mentioned solder joint detection method based on dual-manipulator collaboration are implemented.

[0058] The present invention classifies and merges the welds according to their distribution on the digital model of the test piece, so that adjacent and relatively close test points constitute the test area, and other welds become isolated welds. The centroids of each test area and the isolated welds, i.e., the path control points, which are the points that the manipulator must pass through, are then sorted to determine multiple paths, and the multiple paths are iterated to determine the path with the best time and energy targets, i.e., the path that consumes less time and energy. The path is then adjusted according to the actual state to avoid the situation where the manipulator's stroke collides and interferes with the test piece or the environment, and the manipulator is controlled to move by the second trajectory that is finally determined, so that when the manipulator moves to the isolated weld, the galvanometer on the manipulator performs an area scan with the isolated weld as the center, thereby ensuring the detection accuracy. When the manipulator moves to the detection area, the galvanometer rotates to scan the detection area. Furthermore, by merging points with smaller spacing, the distance between the two points is larger when the manipulator moves, and the manipulator can move with a larger stroke and acceleration to improve detection efficiency. Moreover, for points with smaller spacing, the galvanometer is controlled to detect an area, thereby avoiding the influence of vibration caused by frequent movement of the manipulator on detection accuracy. Moreover, the movement path of the manipulator is adjusted and optimized according to the actual distribution of solder joints, the test pieces and the environmental conditions, so as to further ensure the movement effect of the manipulator. Furthermore, through the large displacement positioning of the manipulator and the small displacement precision scanning of the galvanometer, the efficiency and effect of solder joint detection are significantly improved. Therefore, the present invention solves the problem in the prior art of the lack of a solder joint detection method with high welding detection accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Flowchart of a solder joint detection method based on dual manipulator collaboration in the first embodiment of the present invention;

[0060] Figure 2 4 is a structural block diagram of a welding spot detection system based on dual manipulator collaboration in a second embodiment of the present invention;

[0061] Figure 3 A schematic diagram of the structure of an electronic device in an embodiment of the present invention;

[0062] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0063] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0065] Example 1

[0066] See also Figure 1 , which shows a solder joint detection method based on dual manipulator collaboration in the first embodiment of the present invention, and the method specifically includes S01-S05.

[0067] S01, receiving a digital model of a piece to be tested and first solder point parameter information, determining second solder point parameter information according to the digital model of the piece to be tested and the first solder point parameter information, and combining the first solder point parameter information and the second solder point parameter information to determine solder point feature information.

[0068] Specifically, the first solder joint parameter information includes a solder joint coordinate matrix. The steps of determining the second solder joint parameter information based on the DUT digital model and the first solder joint parameter information include: converting the DUT digital model into a triangular mesh; calculating the local curvature radius of the surface where each solder joint is located using the rate of change of the normal vectors of adjacent triangular facets; and determining the material thickness corresponding to each solder joint area based on the DUT digital model and the solder joint coordinate matrix, where the local curvature radius and the material thickness are the second solder joint parameters. Based on the existing input data, the solder joint data and the DUT data are processed to determine the required solder joint feature information.

[0069] S02: Determine a detection area and isolated welds by merging adjacent welds with similar geometric features according to the weld feature information, determine the centroid of the detection area, and define the centroid and the isolated welds as path control points.

[0070] Specifically, a target distance between each weld point and other weld points is determined according to a preset distance formula, and weld points whose target distance is less than a first preset value are regarded as neighboring points; a weld point whose number of neighboring points is greater than a second preset value is set as a core point, and the neighboring points corresponding to the core point are merged starting from the core point to form the detection area, and weld points located outside the detection area are regarded as isolated weld points;

[0071] The preset distance formula is:

[0072]

[0073] in, is the difference between the coordinates of the two welding points, is the difference in curvature radius between the two welding points, is the difference in thickness between the two welding points, is the weight parameter.

[0074] Specifically, the distance is calculated to determine whether two welds are physically adjacent, and then the curvature and thickness difference between the two welds are calculated to determine whether the two welds are in the same area and whether the detection parameters are consistent. Thus, it is determined through multiple dimensions whether it is appropriate to merge the two welds into the same detection area, and then multiple welds are merged to simplify the movement path of the robot. It is also ensured that after the merger, when the welds in the merged area are inspected, the parameters that need to be inspected for the welds in the area are consistent or close, thereby ensuring the efficiency and effectiveness of the weld detection in the area.

[0075] S03, determining a node value and a basis function corresponding to the node value according to the path control point, so as to determine the path point coordinates according to the basis function, the path control point and the control point weight.

[0076] Specifically, the centroid of the detection area is calculated using a preset centroid formula, and the centroid and the isolated weld are defined as path control points; a node vector and a corresponding node value are determined based on the path control point using a preset parameter formula; a third-order NURBS basis function corresponding to the node value is recursively calculated; and the coordinates of the path point are determined using a preset trajectory point formula based on the basis function, the path control point, and the control point weight.

[0077] The preset centroid formula is:

[0078]

[0079] in, is the coordinate of the path control point;

[0080] The preset parameter formula is:

[0081]

[0082] For the The value of the node, For the The coordinates of the path control points corresponding to the nodes, For adjacent control points nodes and The Euclidean distance between nodes, is the sum of the Euclidean distances between all adjacent control points;

[0083] The preset trajectory point formula is:

[0084]

[0085] in, is the basis function corresponding to the node value, is the weight parameter, are the coordinates of the control points.

[0086] Specifically, the center of mass of the detection area is calculated to determine the optimal point for scanning and inspecting the detection area. That is, it is easier to scan and inspect other welds at the center of mass. Then, each center of mass and isolated weld is a necessary point on the path. Then, by determining the node value and basis function, the influence weight of each necessary point on the path shape is determined. Then, by combining the basis function and the coordinates of the necessary points on the path, the corresponding path point coordinates are generated to determine a smooth and efficient path. In addition, the path formed by the path points needs to be optimized and verified. By calculating the curvature of the path points, it is determined whether it is less than the allowable value of the manipulator curvature to ensure that the motion constraints of the manipulator are met. And the smoothness of the trajectory is ensured by detecting whether the derivatives of adjacent path points are connected.

[0087] S04: Optimize the path point coordinates to determine a first trajectory so that the time target and energy target of the first trajectory are optimized, and correct the first trajectory to determine a second trajectory so that the second trajectory does not collide with the device under test or the environment.

[0088] Specifically, the pathpoint coordinates are randomly sorted to determine a first preset number of candidate paths and their corresponding energy and time targets. The candidate paths are then non-dominatedly sorted based on the time and energy targets to determine their corresponding ranks. High-quality paths are determined based on the candidate paths' corresponding ranks and congestion levels. These high-quality paths are then cross-pollinated using a preset crossover rate to determine descendant paths. The high-quality paths and descendant paths are fine-tuned based on a preset mutation rate and screened based on their ranks and congestion levels to determine a second preset number of first trajectories. In specific implementations, all pathpoint coordinates are randomly sorted to determine a large number of candidate paths. These candidate paths are then non-dominatedly sorted based on time and energy targets. The dominance relationship is: Path 1 is superior to Path 2 if and only if Path 1 is not inferior to Path 2 in both time and energy consumption and is superior in at least one objective. The hierarchy is divided into the following: the first level comprises individuals that are not dominated by any other path. The second level comprises individuals that are dominated only by individuals in the first level. The remaining levels are similar. Paths are then screened based on their hierarchy. When the hierarchy is the same, the path is determined based on congestion. Specifically, if Path 1 and Path 2 are at the same hierarchy, the individual with the more sparse target space distribution is selected. The selected high-quality paths are then intersected. This involves randomly selecting two intersection points for segmentation and swapping the intermediate segments to create new paths, known as offspring paths. A random perturbation is then added to a randomly selected control point in each of the identified offspring and high-quality paths to fine-tune the paths, preventing the algorithm from falling into local optima and increasing diversity. Finally, the fine-tuned paths are screened based on hierarchy and congestion to determine the first trajectory for the target number.

[0089] Furthermore, the first trajectory is hierarchically enclosed and inspected to determine whether the distance between the trajectory points in the first trajectory and the digital model of the DUT is less than a preset distance. If a local obstacle avoidance trajectory is determined based on the first trajectory and the digital model of the DUT, the first trajectory is adjusted, and the adjusted first trajectory is screened to determine the second trajectory. To avoid collisions between the manipulator, the DUT, and the environment, the path needs to be inspected, and then the local path is adjusted based on the inspection results to avoid local obstacles. In specific implementations, the local obstacle avoidance trajectory can be generated using the Bezier obstacle avoidance trajectory generation method.

[0090] S05 , controlling a manipulator to clamp the workpiece to be tested, and controlling another manipulator to move around the workpiece to be tested according to the second trajectory, so that a detection device on the manipulator detects solder joints on the workpiece to be tested.

[0091] Specifically, after the optimal motion trajectory is determined, the workpiece to be tested is clamped by a clamping manipulator, and another detection manipulator is notified to perform motion detection around the workpiece to be tested according to the motion trajectory.

[0092] Furthermore, the step of detecting the solder joints on the workpiece by the detection device on the manipulator includes:

[0093] Determine the type of the target to be measured. If the target to be measured is an isolated weld spot, determine an arcuate area with a preset radius centered on the isolated weld spot, and then determine a corresponding real-time step length based on the real-time curvature of the arcuate area and a preset step length calculation formula, so as to scan and detect the arcuate area according to the real-time step length and the preset speed. If the target to be measured is the detection area, scan and detect the detection area according to the real-time step length and the preset speed.

[0094] The preset step length calculation formula is:

[0095]

[0096] Among them, R is the real-time curvature, is the real-time step size.

[0097] Specifically, when the robot moves to a preset position based on the optimized path, the galvanometer's scanning path is adjusted based on the target to be inspected at that preset position. This combination of large-displacement positioning by the robot and small-displacement precision scanning by the galvanometer significantly improves the efficiency and effectiveness of solder joint inspection. Furthermore, the impact of curvature in different areas on scanning results is taken into account, and the galvanometer's real-time step size is adjusted accordingly.

[0098] By way of example and not limitation, in some optional embodiments, the first weld parameter information also includes a weld normal vector. In a specific implementation, the weld condition is detected by irradiating the weld with a laser, and the laser correction angle can be adjusted according to the weld normal vector to ensure vertical incidence of the laser, i.e., to ensure detection accuracy.

[0099] After the inspection data is collected, it is evaluated using a curve recognition model. The movement path is adjusted for areas with high confidence levels of defects to perform dense scanning to ensure the accuracy of the inspection results. A corresponding quality assessment report and visualization model are then generated.

[0100] In summary, the solder joint detection method based on dual manipulator collaboration in the above embodiment of the present invention classifies and merges the solder joints according to their distribution on the digital model of the test piece, so that adjacent and relatively close test points constitute the detection area, and other solder joints become isolated solder joints. Then, the centroids of each detection area and the isolated solder joints, i.e., the path control points, that is, the points that the manipulator must pass through, are sorted to determine multiple paths, and the multiple paths are iterated to determine the path with the optimal time target and energy target, that is, the path that consumes less time and energy. The path is then adjusted according to the actual state to avoid the situation where the manipulator stroke collides and interferes with the test piece or the environment, and then the manipulator is controlled to move by the second trajectory that is finally determined, so that when the manipulator moves to the isolated solder joint, the galvanometer on the manipulator performs an area scan with the isolated solder joint as the center, thereby ensuring the detection accuracy. When the manipulator moves to the detection area, the galvanometer rotates to scan the detection area. Furthermore, by merging points with smaller spacing, the distance between the two points is larger when the manipulator moves, and the manipulator can move with a larger stroke and acceleration to improve detection efficiency. Moreover, for points with smaller spacing, the galvanometer is controlled to detect an area, thereby avoiding the influence of vibration caused by frequent movement of the manipulator on detection accuracy. Moreover, the movement path of the manipulator is adjusted and optimized according to the actual distribution of solder joints, the test pieces and the environmental conditions, so as to further ensure the movement effect of the manipulator. Furthermore, through the large displacement positioning of the manipulator and the small displacement precision scanning of the galvanometer, the efficiency and effect of solder joint detection are significantly improved. Therefore, the present invention solves the problem in the prior art of the lack of a solder joint detection method with high welding detection accuracy and efficiency.

[0101] Example 2

[0102] See also Figure 2 , which is a block diagram of a solder joint detection system based on dual-manipulator collaboration according to a second embodiment of the present invention, includes: a solder joint feature information determination module 21, a path control point determination module 22, a path point coordinate determination module 23, a second trajectory determination module 24, and a detection module 25, wherein:

[0103] The solder joint characteristic information determining module 21 is configured to receive a digital model of a piece to be tested and first solder joint parameter information, determine second solder joint parameter information based on the digital model of the piece to be tested and the first solder joint parameter information, and combine the first solder joint parameter information and the second solder joint parameter information to determine solder joint characteristic information;

[0104] a path control point determination module 22 for determining an inspection area and isolated welds by merging adjacent welds with similar geometric features according to the weld feature information, determining a centroid of the inspection area, and defining the centroid and the isolated welds as path control points;

[0105] a path point coordinate determination module 23, configured to determine a node value and a basis function corresponding to the node value according to the path control point, so as to determine the path point coordinates according to the basis function, the path control point and the control point weight;

[0106] A second trajectory determination module 24 is configured to optimize the path point coordinates to determine a first trajectory so as to optimize the time target and energy target of the first trajectory, and to correct the first trajectory to determine a second trajectory so as to prevent the second trajectory from colliding with the device under test or the environment;

[0107] The detection module 25 is used to control a manipulator to clamp the test piece, and control another manipulator to move around the test piece according to the second trajectory, so that the detection device on the manipulator detects the solder joints on the test piece.

[0108] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments and will not be repeated here.

[0109] Example 3

[0110] Another aspect of the present invention provides an electronic device, see Figure 3 , shown is a schematic diagram of an electronic device in the current regional embodiment of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, the solder joint detection method based on dual-manipulator collaboration as described above is implemented.

[0111] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0112] The memory 20 includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 20 may be an internal storage unit of the electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Furthermore, the memory 20 may include both an internal storage unit of the electronic device and an external storage device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or is about to be output.

[0113] It should be pointed out that Figure 3 The structure shown does not constitute a limitation to the electronic device. In other embodiments, the electronic device may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0114] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for detecting solder joints based on dual-manipulator collaboration as described above is implemented.

[0115] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0116] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0117] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0118] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0119] The above embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A solder joint detection method based on dual manipulator collaboration, characterized in that: The method comprises: Receiving a digital model of a piece to be tested and first solder point parameter information, determining second solder point parameter information based on the digital model of the piece to be tested and the first solder point parameter information, and combining the first solder point parameter information and the second solder point parameter information to determine solder point feature information, wherein the first solder point parameter information includes a solder point coordinate matrix, the step is specifically as follows: Converting the digital model of the test piece into a triangular mesh; calculating the local curvature radius of the surface where each solder point is located by the rate of change of the normal vectors of adjacent triangular facets; Determine the material thickness corresponding to each solder joint area according to the digital model of the test piece and the solder joint coordinate matrix, wherein the local curvature radius and the material thickness are the second solder joint parameters; The method further includes: determining a detection area and isolated welds by merging adjacent welds with similar geometric features according to the weld feature information, determining a centroid of the detection area, and defining the centroid and the isolated welds as path control points. This step specifically comprises: Determine a target distance between each welding point and other welding points according to a preset distance formula, and regard welding points whose target distance is less than a first preset value as neighboring points; The welding point having the number of neighboring points greater than a second preset value is set as a core point, and the neighboring points corresponding to the core point are merged starting from the core point to form the detection area, and the welding points outside the detection area are the isolated welding points; The preset distance formula is: in, is the difference between the coordinates of the two welding points, is the difference in curvature radius between the two welding points, is the difference in thickness between the two welding points, is the weight parameter; The method further includes: determining a node value and a basis function corresponding to the node value according to the path control point, so as to determine the path point coordinates according to the basis function, the path control point and the control point weight, wherein the step is specifically as follows: Calculating the centroid of the detection area by a preset centroid formula, and defining the centroid and the isolated welding point as path control points; Determine the node vector and the corresponding node value according to the path control point using a preset parameter formula; Recursively calculating the third-order NURBS basis function corresponding to the node value; Determine the path point coordinates using a preset trajectory point formula according to the basis function, the path control points and the control point weights; The preset centroid formula is: in, is the coordinate of the path control point; The preset parameter formula is: For the The value of the node, For the The coordinates of the path control points corresponding to the nodes, For adjacent control points nodes and The Euclidean distance between nodes, is the sum of the Euclidean distances between all adjacent control points; The preset trajectory point formula is: in, is the basis function corresponding to the node value, is the weight parameter, are the coordinates of the control points; The method further includes: optimizing the path point coordinates to determine a first trajectory so that a time target and an energy target of the first trajectory are optimized, and correcting the first trajectory to determine a second trajectory so that the second trajectory does not collide with the device under test or the environment; Controlling a manipulator to clamp the workpiece to be tested, and controlling another manipulator to move around the workpiece to be tested according to the second trajectory, so that the detection device on the manipulator detects the solder joints on the workpiece to be tested, this step is specifically as follows: Determining the type of the target to be measured; if the target to be measured is an isolated weld spot, determining an arcuate region with a preset radius centered on the isolated weld spot, substituting the real-time curvature of the arcuate region into a preset step length calculation formula to determine a corresponding real-time step length, and scanning and detecting the arcuate region according to the real-time step length and a preset speed; If the target to be detected is the detection area, scanning and detecting the detection area according to the real-time step size and the preset speed; The preset step length calculation formula is: Among them, R is the real-time curvature, is the real-time step size.

2. The solder joint detection method based on dual manipulator collaboration according to claim 1 is characterized in that: The step of optimizing the path point coordinates to determine a first trajectory so as to optimize the time target and the energy target of the first trajectory includes: Randomly sorting the path point coordinates to determine a first preset number of candidate paths and energy targets and time targets corresponding to the candidate paths; Performing non-dominated sorting on the candidate paths according to the time target and the energy target to determine the corresponding ranks of the candidate paths; Determine a high-quality path based on the level and congestion corresponding to the candidate path, and then determine a child path based on the high-quality path by performing path intersection at a preset intersection rate; The high-quality path and the child path are fine-tuned according to a preset mutation rate and screened according to the level and congestion to determine a second preset number of first trajectories.

3. The solder joint detection method based on dual manipulator collaboration according to claim 2 is characterized in that: The step of correcting the first trajectory to determine the second trajectory includes: Performing hierarchical encirclement and detection on the first track to determine whether the distance between a track point in the first track and the digital model of the device to be tested is less than a preset distance; If a local obstacle avoidance trajectory is determined according to the first trajectory and the digital model of the device under test, the first trajectory is adjusted, and the adjusted first trajectory is screened to determine the second trajectory.

4. A solder joint detection system based on dual manipulator collaboration, characterized in that: For implementing the solder joint detection method based on dual manipulator collaboration according to any one of claims 1 to 3, the system comprises: a solder joint characteristic information determination module, configured to receive a digital model of a piece to be tested and first solder joint parameter information, determine second solder joint parameter information based on the digital model of the piece to be tested and the first solder joint parameter information, and combine the first solder joint parameter information and the second solder joint parameter information to determine solder joint characteristic information; a path control point determination module, configured to determine a detection area and isolated welds by merging adjacent welds with similar geometric features according to the weld feature information, determine the centroid of the detection area, and define the centroid and the isolated welds as path control points; a path point coordinate determination module, configured to determine a node value and a basis function corresponding to the node value according to the path control point, so as to determine the path point coordinates according to the basis function, the path control point and the control point weight; a second trajectory determination module, configured to optimize the path point coordinates to determine a first trajectory so as to optimize the time target and the energy target of the first trajectory, and to correct the first trajectory to determine a second trajectory so as to prevent the second trajectory from colliding with the object under test or the environment; The detection module is used to control a manipulator to clamp the test piece, and control another manipulator to move around the test piece according to the second trajectory, so that the detection device on the manipulator detects the solder joints on the test piece.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by the processor, the steps of the solder joint detection method based on dual-manipulator collaboration as described in any one of claims 1 to 3 are implemented.

6. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for detecting solder joints based on dual-manipulator collaboration as claimed in any one of claims 1 to 3 is implemented.

Images