Robot welding method and device for assisting weld joint locating based on offline programming technology

Abstract

The invention provides a robot welding method and device for assisting welding seam locating based on an off-line programming technology, and the method comprises the steps: firstly building a workpiece three-dimensional model and marking a welding seam position, then carrying out the off-line programming based on the model to generate a welding track, and then extracting the welding seam characteristics of an actual workpiece through a sensor; and matching with a model welding seam position, calculating deviation, correcting a welding track, and finally controlling the robot to perform welding according to the corrected track. According to the method, the welding efficiency can be improved, the labor cost is reduced, and the problem of weld joint position deviation can be effectively solved.

Description

Technical Field

[0001] The invention relates to the technical field of industrial automation, and in particular to a robot welding method and device for assisting weld positioning based on off-line programming technology. Background Art

[0002] In modern industrial production, robot welding technology is widely used due to its high efficiency, stability and precision. However, traditional robot welding methods usually require manual teaching or online programming, which is not only time-consuming and labor-intensive, but also inefficient and error-prone when facing complex workpieces or frequent workpiece changes. In addition, the deviation of the weld position during the welding process will also affect the welding quality.

[0003] At present, some advanced robotic welding systems use visual sensors or laser sensors to locate welds, but these methods usually need to be performed in real time during the welding process, have high hardware requirements, and are easily affected by factors such as ambient light and welding smoke.

[0004] Therefore, there is an urgent need for a robot welding method that can improve robot welding efficiency, reduce labor costs, and effectively solve the problem of weld position deviation. Summary of the invention

[0005] The present invention provides a robot welding method and device for assisting weld location based on offline programming technology. The method first establishes a three-dimensional model of the workpiece and marks the weld position, then generates a welding trajectory based on the model through offline programming, then uses a sensor to extract the weld characteristics of the actual workpiece, matches them with the model weld position, calculates the deviation and corrects the welding trajectory, and finally controls the robot to weld according to the corrected trajectory. The method of the present invention can improve welding efficiency, reduce labor costs, and effectively solve the problem of weld position deviation.

[0006] In a first aspect, an embodiment of the present application provides a robot welding method for assisting weld positioning based on an offline programming technology, comprising:

[0007] 101. Obtain a three-dimensional model corresponding to the workpiece to be welded, wherein the three-dimensional model is marked with a weld position;

[0008] 102. Plan a first welding trajectory of the robot according to the three-dimensional model and the weld position;

[0009] 103. Extracting actual weld features of the workpiece to be welded by scanning the workpiece to be welded;

[0010] 104. Calculate the position deviation between the actual weld feature and the weld position, and correct the first welding trajectory according to the position deviation to obtain a second welding trajectory;

[0011] 105. Control the robot to perform welding according to the second welding trajectory.

[0012] In combination with the first aspect, in an implementation of the embodiment of the present application, step 103 includes:

[0013] 1031. Collecting images or point cloud data of the surface of the workpiece to be welded by a visual sensor or a laser sensor;

[0014] 1032. Perform a preprocessing operation on the image or the point cloud data, where the preprocessing operation includes denoising and filtering;

[0015] 1033. Using an image processing algorithm or a point cloud processing algorithm, extract actual weld features of the workpiece to be welded from the image or the point cloud data after the preprocessing operation, wherein the actual weld features include feature points or feature lines.

[0016] In this implementation, the characteristic points include a weld start point, an end point or an inflection point of the workpiece to be welded, and the characteristic lines include a weld center line of the workpiece to be welded.

[0017] In combination with the first aspect, in an implementation of the embodiment of the present application, step 104 includes:

[0018] 1041. Matching the actual weld feature of the workpiece to be welded with the weld position of the three-dimensional model to obtain a matching relationship between the actual weld and the model weld;

[0019] 1042. Calculate the position deviation between the actual weld feature and the weld position according to the matching relationship;

[0020] 1043. Correct the first welding trajectory according to the position deviation to obtain a second welding trajectory.

[0021] In combination with the first aspect, in an implementation of the embodiment of the present application, step 1041 includes:

[0022] For each feature point of the actual weld feature, perform the following steps:

[0023] Searching the feature point set of the weld position by a nearest neighbor search algorithm for a point closest to the feature point of the actual weld feature as a candidate point;

[0024] If the distance between the feature point of the actual weld feature and the candidate point is within a set threshold range, the candidate point is determined to be a matching point of the feature point of the actual weld feature.

[0025] In combination with the first aspect, in an implementation of the embodiment of the present application, step 1041 includes:

[0026] Calculating the Hausdorff distance between the characteristic line of the actual weld feature and the characteristic line of the weld position;

[0027] Calculating the shape similarity between the characteristic line of the actual weld feature and the characteristic line of the weld position;

[0028] The characteristic line matching relationship between the actual weld feature and the weld position is calculated according to the Hausdorff distance and the shape similarity.

[0029] In combination with the first aspect, in an implementation of the embodiment of the present application, step 1042 includes:

[0030] Calculate the translation vector between the actual weld feature and the weld position according to the translation vector formula;

[0031] Calculate the average translation vector between the actual weld feature and the weld position according to the average translation vector formula;

[0032] The translation vector formula is: i =(x i -x i ',y i -y i ', z i -z i '), where T j is the translation vector corresponding to the ith feature point, and the ith feature point P of the actual weld feature i (x i ,y i , z i ) and the i-th characteristic point P of the weld position i '(x i ',y i ', z i ') is the corresponding relationship;

[0033] The average translation vector formula is: avg :T avg =(1 / n)*∑T i , i = 1, 2, ..., n, where n is the number of feature points.

[0034] In combination with the first aspect, in an implementation of the embodiment of the present application, step 1042 includes:

[0035] Constructing a first local coordinate system according to the characteristic points of the actual weld characteristics;

[0036] Constructing a second local coordinate system according to the characteristic points of the weld position;

[0037] A rotation matrix is ​​calculated from the first local coordinate system to the second local coordinate system.

[0038] In combination with the first aspect, in an implementation of the embodiment of the present application, step 1042 includes:

[0039] Calculate a first direction vector corresponding to a characteristic line of the actual weld feature;

[0040] Calculate a second direction vector corresponding to the characteristic line of the weld position;

[0041] Calculate the angle between the first direction vector and the second direction vector to obtain a rotation angle;

[0042] A cross product of the first direction vector and the second direction vector is calculated to obtain a rotation axis.

[0043] In combination with the first aspect, in an implementation of the embodiment of the present application, step 1043 includes:

[0044] The second welding trajectory is obtained by calculating through a correction formula;

[0045] The correction formula is: j_corrected =R*P j +T avg , where P j_corrected is the corrected second welding trajectory point, R is the rotation matrix, T avg is the mean translation vector.

[0046] In a second aspect, an embodiment of the present application provides a robot welding device for assisting weld positioning based on an offline programming technology, comprising:

[0047] An acquisition module, used to acquire a three-dimensional model corresponding to the workpiece to be welded, wherein the three-dimensional model is marked with a weld position;

[0048] A processing module, used for planning a first welding trajectory of the robot according to the three-dimensional model and the weld position;

[0049] The processing module is further used to extract the actual weld features of the workpiece to be welded by scanning the workpiece to be welded;

[0050] The processing module is further used to calculate the position deviation between the actual weld feature and the weld position, and correct the first welding trajectory according to the position deviation to obtain a second welding trajectory;

[0051] The processing module is also used to control the robot to perform welding according to the second welding trajectory.

[0052] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of the first aspect when executing the computer program.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method of the first aspect is implemented.

[0054] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the robotic welding method for assisting weld positioning based on offline programming technology as described in any one of the first aspects above.

[0055] It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

[0056] The embodiment of the present invention provides a robot welding method and device for assisting weld location based on offline programming technology. The method first establishes a three-dimensional model of the workpiece and marks the weld position, then generates a welding trajectory based on the model through offline programming, then uses a sensor to extract the weld features of the actual workpiece and matches them with the model weld position, calculates the deviation and corrects the welding trajectory, and finally controls the robot to weld according to the corrected trajectory. The method of the present invention can improve welding efficiency, reduce labor costs, and effectively solve the problem of weld position deviation.

[0057] The beneficial effects of the present invention specifically include the following aspects:

[0058] 1. Improve welding efficiency: Through offline programming, the welding trajectory can be planned in advance, reducing the time of manual teaching or online programming, and improving welding efficiency.

[0059] 2. Reduce labor costs: Reduce manual intervention and lower the skill requirements for operators, thereby reducing labor costs.

[0060] 3. Improve welding quality: Through weld position correction, the problem of weld position deviation can be effectively solved and welding accuracy and quality can be improved.

[0061] 4. Strong adaptability: The method of the present invention is suitable for welding various complex workpieces and has strong adaptability.

[0062] 5. Reduce hardware cost: The method of the present invention has relatively low hardware requirements and can reduce system costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0064] Figure 1 A flowchart of a robot welding method for assisting weld positioning based on off-line programming technology provided in an embodiment of the present application;

[0065] Figure 2 A schematic diagram of a three-dimensional model provided in an embodiment of the present application;

[0066] Figure 3 A schematic diagram of weld feature extraction provided in an embodiment of the present application;

[0067] Figure 4 A schematic diagram of a robot welding device for assisting weld seam positioning based on off-line programming technology provided in an embodiment of the present application;

[0068] Figure 5 A schematic diagram of a data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The embodiment of the present invention provides a robot welding method and device for assisting weld location based on offline programming technology. The method first establishes a three-dimensional model of the workpiece and marks the weld position, then generates a welding trajectory based on the model through offline programming, then uses a sensor to extract the weld features of the actual workpiece and matches them with the model weld position, calculates the deviation and corrects the welding trajectory, and finally controls the robot to weld according to the corrected trajectory. The method of the present invention can improve welding efficiency, reduce labor costs, and effectively solve the problem of weld position deviation.

[0070] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] Figure 1 A flowchart of a robot welding method for assisting weld positioning based on offline programming technology is provided in an embodiment of the present application. The method comprises the following steps:

[0072] 101. Obtain a three-dimensional model corresponding to the workpiece to be welded, where the weld position is marked on the three-dimensional model;

[0073] Figure 2 This is a schematic diagram of a three-dimensional model provided in the embodiment of this application. Please refer to Figure 2 In an embodiment of the present application, a three-dimensional scanner or CAD software can be used to create a three-dimensional model of the workpiece to be welded and mark the weld position.

[0074] In practical applications, other new technologies or software may emerge to implement three-dimensional modeling, which is not limited in the embodiments of the present application.

[0075] 102. Plan a first welding trajectory of the robot according to the three-dimensional model and the weld position;

[0076] In an embodiment of the present application, based on the three-dimensional model and weld position generated in step 101, the robot welding trajectory (ie, the first welding trajectory) can be planned in the offline programming software, and a corresponding robot motion program can be generated.

[0077] Specifically, the robot's welding trajectory can be planned based on data such as the coordinate points of the weld position or the fitting curve. This technology is a common technology in robot welding and will not be described in detail here.

[0078] 103. Extracting actual weld features of the workpiece to be welded by scanning the workpiece to be welded;

[0079] Figure 3 This is a schematic diagram of weld feature extraction provided in the embodiment of the present application. Please refer to Figure 3 In the embodiment of the present application, a visual sensor or a laser sensor can be used to scan the actual workpiece to extract the characteristic points or characteristic lines of the weld. In this embodiment, the characteristic points include the starting point, the end point or the inflection point of the weld of the workpiece to be welded, and the characteristic lines include the center line of the weld of the workpiece to be welded.

[0080] In some embodiments, this step is divided into the following detailed steps:

[0081] 1031. Collecting images or point cloud data of the surface of the workpiece to be welded by a visual sensor or a laser sensor;

[0082] Specifically, this step is called an image acquisition step, and a visual sensor or a laser sensor can be used to acquire images or point cloud data of the workpiece surface.

[0083] 1032. Perform preprocessing operations on the image or point cloud data, where the preprocessing operations include denoising and filtering;

[0084] Specifically, this step is called an image preprocessing step, and preprocessing operations such as denoising and filtering can be performed on the collected image or point cloud data in order to optimize the processing.

[0085] 1033. Using an image processing algorithm or a point cloud processing algorithm, extract the actual weld features of the workpiece to be welded from the image or point cloud data after the preprocessing operation, and the actual weld features include feature points or feature lines.

[0086] Specifically, this step is called a feature extraction step, and the characteristic points or characteristic lines of the weld, such as the starting point, the ending point, the inflection point, etc. of the weld, can be extracted using an image processing algorithm or a point cloud processing algorithm.

[0087] 104. Calculate the position deviation between the actual weld feature and the weld position, and correct the first welding trajectory according to the position deviation to obtain a second welding trajectory;

[0088] The principle of this step is to match the extracted weld features with the weld positions marked in the 3D model of the workpiece, calculate the deviation between the actual weld position and the model weld position, and correct the welding trajectory generated by offline programming according to the deviation.

[0089] In some embodiments, the step comprises the following steps:

[0090] 1041. Matching the actual weld characteristics of the workpiece to be welded with the weld position of the three-dimensional model to obtain a matching relationship between the actual weld and the model weld;

[0091] This step is feature matching, which matches the extracted weld features with the weld features marked in the workpiece 3D model to determine the correspondence between the actual weld and the model weld. Weld features can be feature points (such as starting points, end points, inflection points, etc.) or feature lines (such as weld center lines).

[0092] In one implementation, for each feature point of an actual weld feature, the following steps are performed:

[0093] The nearest neighbor search algorithm is used to search the point closest to the feature point of the actual weld feature in the feature point set of the weld position as a candidate point; that is, the nearest neighbor search: for each actual weld feature point, the nearest point in the model weld feature point set is searched as a matching point. The nearest neighbor search algorithm is a classic algorithm in the population matching algorithm and will not be described here.

[0094] If the distance between the feature point of the actual weld feature and the candidate point is within a set threshold range, the candidate point is determined to be a matching point of the feature point of the actual weld feature.

[0095] In this implementation, the matching point corresponding to each feature point of the actual weld feature can be searched to determine the matching relationship between the actual weld and the model weld. In the embodiment of the present application, a distance threshold can be set. If the closest distance exceeds the threshold, it is considered that the actual weld feature point has no matching point.

[0096] In one implementation, matching can be performed by following the steps below:

[0097] The Hausdorff distance between the characteristic line of the actual weld feature and the characteristic line of the weld position is calculated; in the embodiment of the present application, the Hausdorff distance is the Hausdorff distance.

[0098] Calculate the shape similarity between the characteristic lines of the actual weld features and the characteristic lines of the weld location;

[0099] The characteristic line matching relationship between the actual weld features and the weld positions is calculated based on the Hausdorff distance and shape similarity.

[0100] In practical applications, there are three ways to achieve matching using Hausdorff distance and similarity. The first is to calculate the Hausdorff distance between the actual weld characteristic line and the model weld characteristic line, and then match them according to the distance. The second is to calculate the shape similarity between the actual weld characteristic line and the model weld characteristic line, and match them according to the similarity. The third is the above-mentioned calculation of the characteristic line matching relationship between the actual weld feature and the weld position based on the Hausdorff distance and shape similarity. The specific implementation method is not limited in the embodiments of this application.

[0101] In the embodiment of the present application, the matching result (the matching relationship between the actual weld and the model weld) is the corresponding relationship between the actual weld features and the model weld features, for example: the actual weld feature point P1 corresponds to the model weld feature point P1', and the actual weld feature line L1 corresponds to the model weld feature line L1'.

[0102] 1042. Calculate the position deviation between the actual weld feature and the weld position according to the matching relationship;

[0103] In the embodiment of the present application, specifically, the position deviation between the actual weld feature and the model weld feature is calculated, including translation deviation and rotation deviation.

[0104] In some implementations, the translation deviation calculation may be implemented by the following steps:

[0105] Calculate the translation vector between the actual weld feature and the weld position according to the translation vector formula;

[0106] Calculate the average translation vector between the actual weld feature and the weld position according to the average translation vector formula;

[0107] The translation vector formula is: T i =(x i -x i ',y i -y i ', z i -z i '), where T i is the translation vector corresponding to the ith feature point, and the ith feature point P of the actual weld feature i (x i ,y i , z i ) and the i-th characteristic point P at the weld position i '(x i ',y i ', z i ') is the corresponding relationship;

[0108] The average translation vector formula is: T avg :T avg =(1 / n)*∑T i , i = 1, 2, ..., n, where n is the number of feature points.

[0109] The average translation vector T avg This is one way to express translational deviation.

[0110] In some implementations, the average translation vector T avg The calculation can also include the following steps:

[0111] The average distance between the actual weld feature line and the model weld feature line can be calculated, or the average distance between the corresponding points on the two feature lines can be calculated to obtain the translation vector as the average translation vector T avg .

[0112] In some implementations, the rotation deviation may be represented by a rotation matrix, and the calculation of the rotation matrix may include the following steps:

[0113] A first local coordinate system is constructed according to the characteristic points of the actual weld characteristics; a second local coordinate system is constructed according to the characteristic points of the weld position; specifically, at least three non-collinear matching characteristic points can be selected to construct local coordinate systems on the actual weld and the model weld respectively.

[0114] Calculate the rotation matrix R from the first local coordinate system to the second local coordinate system. Specifically, the rotation matrix can be calculated using methods such as singular value decomposition (SVD), which will not be described in detail in the embodiment of the present application.

[0115] In some implementations, the rotation deviation may be represented by a rotation angle, a rotation axis, etc., so the calculation of the rotation deviation may further include the following steps:

[0116] Calculate the first direction vector corresponding to the characteristic line of the actual weld feature;

[0117] Calculate the second direction vector corresponding to the characteristic line of the weld position;

[0118] Calculate the angle between the first direction vector and the second direction vector to obtain the rotation angle;

[0119] Calculate the cross product of the first direction vector and the second direction vector to obtain the rotation axis.

[0120] In practical applications, the rotation deviation can also be expressed by rotation matrix R, Euler angles (α, β, γ), quaternion q, etc. The specific calculation method can refer to the conventional calculation method of the corresponding parameters, which will not be repeated in the embodiments of the present application.

[0121] 1043. Correct the first welding trajectory according to the position deviation to obtain a second welding trajectory.

[0122] The main purpose of step 1043 is to perform trajectory correction, that is, to perform translation and rotation correction on the welding trajectory generated by offline programming according to the calculated deviation, so that the corrected welding trajectory is aligned with the actual weld position.

[0123] In some implementations, the following steps may be specifically included:

[0124] The second welding trajectory is obtained by calculating through a correction formula;

[0125] The correction formula is: j_corrected =R*P j +T avg , where P j_corrected is the corrected second welding trajectory point, R is the rotation matrix, T avg is the mean translation vector.

[0126] Specifically, assuming that the welding trajectory generated by offline programming consists of a series of trajectory points, each trajectory point (the trajectory point of the first welding trajectory) can be expressed as P j (x j ,y j , z j ). Therefore, the trajectory of translation correction can be expressed as P j_corrected =P j +T avg , the rotation correction trajectory can be expressed as P j_corrected =R*P j , Combining the above two formulas, we can get the correction formula: Pj_corrected =R*P j +T avg , where P j_corrected is the corrected second welding trajectory point, R is the rotation matrix, T avg is the mean translation vector.

[0127] In practical applications, if the translation deviation and rotation deviation are expressed in other ways, they can be converted into the representation of the average translation vector and the rotation matrix, and then corrected by the above steps. Of course, the corresponding correction formula can also be designed by yourself, and the embodiment of the present application does not limit this.

[0128] 105. Control the robot to perform welding according to the second welding trajectory.

[0129] Specifically, step 105 may include the following steps:

[0130] Program import: determine the robot's motion program according to the corrected second welding trajectory, and then import the motion program into the robot control system;

[0131] Parameter setting: set welding parameters, such as welding current, welding voltage, welding speed, etc.;

[0132] Welding execution: Control the robot to weld according to the corrected welding trajectory and monitor the welding process in real time.

[0133] Beneficial effects of the present invention:

[0134] 1. Improve welding efficiency: Through offline programming, the welding trajectory can be planned in advance, reducing the time of manual teaching or online programming, and improving welding efficiency.

[0135] 2. Reduce labor costs: Reduce manual intervention and lower the skill requirements for operators, thereby reducing labor costs.

[0136] 3. Improve welding quality: Through weld position correction, the problem of weld position deviation can be effectively solved and welding accuracy and quality can be improved.

[0137] 4. Strong adaptability: The method of the present invention is suitable for welding various complex workpieces and has strong adaptability.

[0138] 5. Reduce hardware cost: The method of the present invention has relatively low hardware requirements and can reduce system costs.

[0139] Figure 4 A schematic diagram of a robot welding device for assisting weld seam positioning based on offline programming technology provided in an embodiment of the present application. The internal modules of the robot welding device 400 for assisting weld seam positioning based on offline programming technology include:

[0140] Acquisition module 401, used to execute or implement the above Figure 1 Corresponding to step 101 in each embodiment;

[0141] Processing module 402 is used to execute or implement the above Figure 1 These correspond to step 102, step 103, step 104, and step 105 in each embodiment.

[0142] Figure 5 Schematic diagram of a data processing device provided in an embodiment of the present application. The data processing device 500 includes a memory 502, a processor 501, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, the following is achieved: Figure 1 The corresponding methods of each embodiment.

[0143] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0144] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0146] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0147] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0150] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A robot welding method based on offline programming technology to assist weld positioning, characterized in that: include:

101. Obtain a three-dimensional model corresponding to the workpiece to be welded, wherein the three-dimensional model is marked with a weld position; 102. Plan a first welding trajectory of the robot according to the three-dimensional model and the weld position; 103. Extracting actual weld features of the workpiece to be welded by scanning the workpiece to be welded; 104. Calculate the position deviation between the actual weld feature and the weld position, and correct the first welding trajectory according to the position deviation to obtain a second welding trajectory; 105. Control the robot to perform welding according to the second welding trajectory.

2. The method according to claim 1, characterized in that The step 103 comprises: 1031. Collecting images or point cloud data of the surface of the workpiece to be welded by a visual sensor or a laser sensor; 1032. Perform a preprocessing operation on the image or the point cloud data, where the preprocessing operation includes denoising and filtering; 1033. Using an image processing algorithm or a point cloud processing algorithm, extract actual weld features of the workpiece to be welded from the image or the point cloud data after the preprocessing operation, wherein the actual weld features include feature points or feature lines.

3. The method according to claim 1, characterized in that: The step 104 includes: 1041. Matching the actual weld feature of the workpiece to be welded with the weld position of the three-dimensional model to obtain a matching relationship between the actual weld and the model weld; 1042. Calculate the position deviation between the actual weld feature and the weld position according to the matching relationship; 1043. Correct the first welding trajectory according to the position deviation to obtain a second welding trajectory.

4. The method according to claim 3, characterized in that: The step 1041 includes: For each feature point of the actual weld feature, perform the following steps: Searching the feature point set of the weld position by a nearest neighbor search algorithm for a point closest to the feature point of the actual weld feature as a candidate point; If the distance between the feature point of the actual weld feature and the candidate point is within a set threshold range, the candidate point is determined to be a matching point of the feature point of the actual weld feature.

5. The method according to claim 3, characterized in that: The step 1041 includes: Calculating the Hausdorff distance between the characteristic line of the actual weld feature and the characteristic line of the weld position; Calculating the shape similarity between the characteristic line of the actual weld feature and the characteristic line of the weld position; The characteristic line matching relationship between the actual weld feature and the weld position is calculated according to the Hausdorff distance and the shape similarity.

6. The method according to claim 3, characterized in that The step 1042 includes: Calculate the translation vector between the actual weld feature and the weld position according to the translation vector formula; Calculate the average translation vector between the actual weld feature and the weld position according to the average translation vector formula; The translation vector formula is: i =(x i -x i ',y i -y i ', z i -z i '), where T i is the translation vector corresponding to the ith feature point, and the ith feature point P of the actual weld feature i (x i ,y i , z i ) and the i-th characteristic point P of the weld position i '(x i ',y i ', z i ') is the corresponding relationship; The average translation vector formula is: avg :T avg =(1 / n)*∑T i , i = 1, 2, ..., n, where n is the number of feature points.

7. The method according to claim 3, characterized in that The step 1042 includes: Constructing a first local coordinate system according to the characteristic points of the actual weld characteristics; Constructing a second local coordinate system according to the characteristic points of the weld position; A rotation matrix is ​​calculated from the first local coordinate system to the second local coordinate system.

8. The method according to claim 3, characterized in that The step 1042 includes: Calculate a first direction vector corresponding to a characteristic line of the actual weld feature; Calculate a second direction vector corresponding to the characteristic line of the weld position; Calculate the angle between the first direction vector and the second direction vector to obtain a rotation angle; A cross product of the first direction vector and the second direction vector is calculated to obtain a rotation axis.

9. The method according to claim 3, characterized in that: The step 1043 includes: The second welding trajectory is obtained by calculating through a correction formula; The correction formula is: j_corrected =R*P j +T avg , where P j_corrected is the corrected second welding trajectory point, R is the rotation matrix, T avg is the mean translation vector.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images