A groove path and welding speed planning method and system

Abstract

The present application provides a groove path and welding speed planning method and system, the method comprising scanning the groove of a workpiece by a line laser sensor according to a preset travel speed and a preset travel direction of the line laser to obtain first groove data of the workpiece groove; filtering the first groove data to obtain second groove data; obtaining a three-dimensional groove model according to the second groove data; and determining welding parameters based on the three-dimensional groove model and the preset travel direction.

Description

Technical Field

[0001] The present invention relates to the field of groove welding, and in particular to a groove path and welding speed planning method and system. Background Art

[0002] Groove welding usually relies on industrial robots. During the process of robot groove welding, the robot system is used for multi-layer and multi-pass offline programming to plan the groove path. However, the welding gun position, welding speed, welding gun posture, etc. often require manual intervention, resulting in low efficiency and poor welding quality.

[0003] In order to solve the above problems, CN108188548B discloses a robot multi-layer multi-pass welding method, which performs multi-layer multi-pass welding by scanning the bottom width of the groove with a laser line multiple times to match the process database, thus solving the problem of inaccurate paths caused by too many layers in traditional multi-layer multi-pass automatic welding. However, this method requires the construction of a process database in advance, and the flexibility of the method is reduced when non-standard or complex welds appear.

[0004] Therefore, it is hoped to provide a groove path and welding speed planning method to help improve welding efficiency and ensure groove welding quality. Summary of the invention

[0005] One or more embodiments of the present specification provide a groove path and welding speed planning method, characterized in that the method includes: scanning the groove of the workpiece by a line laser sensor according to a preset travel speed and a preset travel direction of the line laser to obtain first groove data of the workpiece groove; filtering the first groove data to obtain second groove data; obtaining a three-dimensional groove model based on the second groove data; and determining welding parameters based on the three-dimensional groove model and the preset travel direction.

[0006] One or more embodiments of the present specification provide a groove path and welding speed planning system, characterized in that the system includes: a scanning module, which is used to scan the groove of a workpiece through a line laser sensor according to a preset travel speed and a preset travel direction of the line laser to obtain first groove data of the workpiece groove; a filtering module, which is used to filter the first groove data to obtain second groove data; a three-dimensional model construction module, which is used to obtain a three-dimensional model of the groove according to the second groove data; and a parameter determination module, which is used to determine the welding parameters based on the three-dimensional model of the groove and the preset travel direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0008] Figure 1 is an exemplary flow chart of a groove path and welding speed planning method according to some embodiments of this specification;

[0009] Figure 2 is an exemplary flow chart for determining welding parameters according to some embodiments of the present specification;

[0010] Figure 3 is an exemplary schematic diagram of an evaluation model according to some embodiments of this specification;

[0011] Figure 4 is an exemplary schematic diagram of a method for determining a model according to some embodiments of this specification;

[0012] Figure 5 It is an exemplary schematic diagram of the division of the groove sub-segments shown in some embodiments of this specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] Using multi-layer and multi-pass offline programming of the robot system to plan the groove path requires manual intervention in the welding gun position, welding speed, welding gun posture, etc., resulting in low welding efficiency, poor welding quality and other problems. CN108188548B discloses a robot multi-layer and multi-pass welding method, which performs multi-layer and multi-pass welding by scanning the groove bottom width with multiple line lasers to match the process database, which improves the welding efficiency and welding quality to a certain extent, but the method requires the construction of the process database in advance, and when non-standard or complex-shaped welds appear, the flexibility of the method is reduced.

[0018] In view of this, in some embodiments of this specification, a groove path and welding speed planning system and method are disclosed. The system and method use an industrial robot and a laser to continuously scan the groove to establish a three-dimensional point cloud model. By separating and allocating the identified contour point cloud, and calculating the filling section and welding cladding amount, the system can automatically determine the position, posture and speed of the welding gun. Subsequently, a welding control program module is generated and sent to the robot for execution. This system and method effectively improves welding efficiency and ensures welding quality.

[0019] In some embodiments, a groove path and welding speed planning system includes: a scanning module, which is used to scan the groove of the workpiece through a line laser sensor according to the preset travel speed and preset travel direction of the line laser to obtain the first groove data of the workpiece groove; a filtering module, which is used to filter the first groove data to obtain the second groove data; a three-dimensional model construction module, which is used to obtain a three-dimensional model of the groove according to the second groove data; a parameter determination module, which is used to determine the welding parameters based on the three-dimensional model of the groove and the preset travel direction.

[0020] In some embodiments, the parameter determination module is further used to: determine contour change data based on the groove three-dimensional model; divide the workpiece groove into groove sub-segments based on the contour change data and a preset travel direction; determine the welding coverage amount of the groove sub-segments; and determine the welding parameters based on the welding coverage amount.

[0021] In some embodiments, the parameter determination module is further used to: determine candidate welding parameters; determine the welding effective value through an evaluation model based on the welding coverage amount and the candidate welding parameters; wherein the evaluation model is a machine learning model; and determine the welding parameters based on the welding effective value.

[0022] In some embodiments, a groove path and welding speed planning system also includes: an information determination module, used to determine the groove geometry and groove position based on the groove three-dimensional model; a speed determination module, used to determine the target travel speed based on the groove geometry, groove position, and welding parameters.

[0023] In some embodiments, the speed determination module is further used to: determine the target travel speed by determining a model based on the groove geometry, groove position, and welding parameters; wherein the determination model is a machine learning model.

[0024] In some embodiments, a groove path and welding speed planning system may further include a processor, and the above-mentioned modules may be integrated into the processor to execute the functions of each module based on the processor.

[0025] Figure 1 is an exemplary flow chart of a groove path and welding speed planning method according to some embodiments of the present specification. In some embodiments, process 100 can be executed by a processor.

[0026] In some embodiments, Figure 1 As shown, the processor can scan the workpiece groove through the line laser sensor according to the preset travel speed and preset travel direction of the line laser to obtain the first groove data of the workpiece groove; filter the first groove data to obtain the second groove data; obtain the groove three-dimensional model according to the second groove data; determine the welding parameters based on the groove three-dimensional model and the preset travel direction.

[0027] Step 110 , scanning the groove of the workpiece by a line laser sensor according to a preset travel speed and a preset travel direction of the line laser, and obtaining first groove data of the groove of the workpiece.

[0028] The preset travel speed is the moving speed set before the line laser is scanned. The preset travel direction is the moving direction set before the line laser is scanned. The preset travel speed and the preset travel direction can be manually preset values ​​or determined based on historical experience.

[0029] A line laser sensor is a sensor for emitting a line laser and receiving its reflected light. In some embodiments, the line laser sensor can measure the shape and size of the surface of an object.

[0030] The workpiece groove is a groove with a certain geometric shape that is machined and assembled at the part to be welded. For more information on the groove geometry, see Figure 4 and its related description.

[0031] The first groove data is the point cloud data of the groove of the workpiece. The point cloud is a set of point data of the appearance surface of the object obtained by a measuring instrument. In some embodiments, the point cloud data may include any one or a combination of three-dimensional coordinates (X, Y, Z), color, laser reflection intensity, etc.

[0032] In some embodiments, the processor may obtain the first groove data of the workpiece groove in a variety of ways. For example, the processor may perform a large number of intensive scans on the workpiece groove surface through a line laser sensor to obtain the point cloud data of the workpiece groove, that is, the first groove data.

[0033] Step 120, filtering the first groove data to obtain second groove data.

[0034] The second groove data is the filtered point cloud data of the groove of the workpiece, that is, the filtered first groove data.

[0035] In some embodiments, the processor may filter the first groove data in a variety of ways. For example, the processor may filter the first groove data using a variety of filtering algorithms. The filtering algorithms may include any one or a combination of Gaussian filtering, median filtering, etc.

[0036] Exemplarily, the processor can obtain the contour of the workpiece groove from a picture of a certain angle of the workpiece groove in advance, and align the angle of the picture with the angle of the point cloud by setting the mark point in advance. Use the filtering algorithm to remove the point cloud outside the contour corresponding to the angle on the workpiece groove in the picture, and then remove the point cloud inside the contour and the distance from the contour exceeds the preset distance range. For pictures at different angles, repeat the filtering multiple times, and use the filtered results as the second groove data. Among them, the preset distance range can be a manually preset value, or determined based on historical experience.

[0037] In some embodiments, the number of filtering times may be related to the environmental visibility and the environmental granularity. For example, the lower the environmental visibility, the more filtering times; for another example, the higher the environmental granularity, the more filtering times.

[0038] Environmental visibility is the maximum distance at which an object can be seen and recognized at present. In some embodiments, environmental visibility can be obtained by means of a projector, a laser radar, etc.

[0039] The environmental particle size is the concentration of particles in the atmosphere. The particles in the atmosphere may include sulfur dioxide, nitrogen oxides, etc. In some embodiments, the environmental particle size can be obtained by a particle detector, a microbial sampler, etc.

[0040] Step 130, obtaining a groove three-dimensional model according to the second groove data.

[0041] The groove three-dimensional model is a three-dimensional geometric model constructed based on the second groove data. In some embodiments, the groove three-dimensional model may include groove geometry, groove position and other data. For more information about the groove geometry and groove position, see Figure 4 and its related description.

[0042] In some embodiments, the processor may obtain a three-dimensional point cloud model of the workpiece groove, that is, a three-dimensional model of the groove, by fitting the point cloud frame by frame.

[0043] Step 140, determining welding parameters based on the groove three-dimensional model and the preset travel direction.

[0044] Welding parameters are various parameters that need to be set during the workpiece groove welding process. In some embodiments, welding parameters may include welding speed, welding gun position and welding gun posture at at least one time point. Exemplarily, welding parameters may be expressed as: {(time 1, welding speed 1, welding gun position 1, welding gun posture 1), ..., (time n, welding speed n, welding gun position n, welding gun posture n)}.

[0045] In some embodiments, the processor can determine the welding parameters in a variety of ways. For example, the processor can determine the groove geometry based on the groove three-dimensional model, query the default welding parameters under the geometry and in the preset walking direction, and determine the default welding parameters as the welding parameters. The default welding parameters can be determined based on historical experience. For more information about the groove geometry, see Figure 4 and its related description.

[0046] For more information on determining welding parameters, see Figure 2 and its related description.

[0047] In some embodiments of the present specification, redundant invalid point clouds are filtered out to separate the valid point cloud of the workpiece groove, and the valid point cloud is subjected to controllable filtering processing, thereby reducing the calculation time of the processor; the accuracy of the appearance information of the workpiece groove is improved by determining the number of filtering times based on the environmental visibility and environmental granularity; and appropriate welding parameters are formulated according to the geometric shape of the groove to ensure that the welding conforms to the actual situation of the workpiece groove, thereby ensuring the welding quality.

[0048] It should be noted that the above description of the process 100 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 100 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0049] Figure 2 is an exemplary flow chart for determining welding parameters according to some embodiments of this specification. The process is executed by a parameter determination module or a processor, such as Figure 2 As shown, process 200 includes the following steps.

[0050] In some embodiments, Figure 2As shown, the processor can determine the contour change data according to the groove three-dimensional model; based on the contour change data, preset the travel direction and divide the workpiece groove into groove sub-segments; determine the welding cladding amount of the groove sub-segments; and determine the welding parameters based on the welding cladding amount.

[0051] Step 210, determining the profile change data according to the groove three-dimensional model.

[0052] The profile change data refers to the relative ratio of the groove width change to the groove height change. For example, if the groove height increases by 1mm and the width increases by 3mm, the relative ratio of the groove width change to the groove height change is 3, and the profile change data is 3. The increase in height and width can be determined based on the change in height and width of the current point as a cross section compared to the cross section at the preset point (such as the welding start point, etc.).

[0053] In some embodiments, the processor may determine the profile change data based on a width change value and a height change value of the groove in the three-dimensional model of the groove.

[0054] Step 220, based on the profile change data and the preset travel direction, the workpiece groove is divided into groove sub-segments.

[0055] Groove sub-segment refers to a smaller area or segment on the groove. For example, if the groove is divided into three groove sub-segments AB, BC, and CD, then A, B, C, and D are all groove division points or division layers. Figure 5 As shown in the figure, the groove of the workpiece is a V-shaped groove, wherein A, B, C, and D are groove division points from bottom to top. Based on the groove division points, the V-shaped groove can be horizontally segmented from bottom to top (i.e., segmented according to the cross-sectional direction). For example, AB corresponds to a groove sub-segment with a triangular vertical section shape, and BC and CD correspond to groove sub-segments with a trapezoidal vertical section shape, respectively.

[0056] In some embodiments, the processor can divide the workpiece groove in a variety of ways. For example, the processor can determine the groove division point based on the contour change data and the contour change threshold, and according to the preset direction of travel, the area between every two adjacent groove division points constitutes a groove sub-segment. As an example only, the processor can use the point where the contour change data is greater than or equal to the contour change threshold as the groove division point to divide the groove. Among them, the contour change threshold can be set by the processor by default or by the technician based on experience.

[0057] Step 230, determining the welding coverage amount of the groove sub-section.

[0058] Welding coverage refers to the volume or mass of welding materials (such as welding wire, welding rod, etc.) deposited in the weld after melting during the welding process.

[0059] In some embodiments, the processor may determine the welding cladding amount by a variety of methods. For example, the processor may determine the welding cladding amount by querying a first preset table based on the contour change data corresponding to the groove sub-segment. The contour change data corresponding to the groove sub-segment may be a sequence or set of contour change data of points included in the groove sub-segment, and the first preset table includes a plurality of contour change data sequences or sets and their corresponding welding cladding amounts.

[0060] In some embodiments, the first preset table can be constructed based on historical data. For example, the processor can use historical profile change data as sample data, and use the welding coverage amount corresponding to a sample data when performing compliant welding as the sample corresponding label (i.e., the welding coverage amount corresponding to the historical profile change data).

[0061] In some embodiments, the processor may determine the cross-sectional shape of the groove sub-section; and determine the welding cladding amount based on the cross-sectional shape and the content of the protective gas in the processing environment.

[0062] In some embodiments, the processor may determine the cross-sectional shape of the groove sub-segment by a variety of methods. For example, the processor may determine the cross-sectional shape (such as the cross-sectional shape and / or the vertical cross-sectional shape) of the groove sub-segment by querying the position of the groove sub-segment in the three-dimensional model, such as the shape corresponding to the cross section at point B in the groove sub-segment AB is the cross-sectional shape of the groove sub-segment AB.

[0063] Since the larger the area of ​​the cross-sectional shape, the higher the weld deposition amount required. In some embodiments, the weld deposition amount may be positively correlated to the area of ​​the cross-sectional shape.

[0064] In some embodiments, the welding cladding amount may be negatively correlated to the degree of convergence between the actual content of the shielding gas in the processing environment and the standard content of the shielding gas. For example, the closer the shielding gas content in the processing environment is to the standard content, the higher the stability and efficiency during the cladding process, and the lower the required welding cladding amount. The standard content may be set based on relevant experiments or by technicians based on experience.

[0065] In some embodiments of the present specification, the welding coverage amount is adjusted according to the specific cross-sectional shape of each groove sub-segment and the shielding gas content in the processing environment, so as to obtain a more accurate welding coverage amount, reduce material consumption caused by misjudgment, and reduce costs.

[0066] Step 240, determining welding parameters based on the welding coverage.

[0067] In some embodiments of the present specification, by calculating the contour change data through the groove three-dimensional model, the geometric shape of the workpiece can be understood more accurately, and precise path planning and parameter setting can be performed, thereby improving welding reliability; based on the specific conditions of each workpiece groove sub-segment, the welding parameters (such as welding posture, welding speed, etc.) are dynamically adjusted to adapt to the welding requirements of different sub-segments, which can improve the flexibility of the welding process and the welding quality.

[0068] Figure 3 is an exemplary schematic diagram of an evaluation model according to some embodiments of the present specification.

[0069] In some embodiments, Figure 3 As shown, the processor may determine candidate welding parameters, determine a welding effective value 340 based on the welding coverage 310 and the candidate welding parameters 320 through an evaluation model 330 , and determine welding parameters based on the welding effective value 340 .

[0070] Candidate welding parameters 320 refer to parameters that may be used for a welding process. In some embodiments, candidate welding parameters 320 may include candidate welding gun positions, candidate welding speeds, candidate welding postures, and the like.

[0071] In some embodiments, the processor may determine one or more candidate welding parameters based on at least one historical welding parameter. For example, the processor may count the number of times each historical welding parameter is used, sort the parameters in order of the number of times used, and use the historical welding parameters with a preset number of parameters in the front as candidate welding parameters. The preset number may be set by the technician based on experience.

[0072] In some embodiments, the preset number is related to the welding requirement. For example, the higher the welding requirement, the higher the preset number.

[0073] The welding effective value 340 refers to a parameter used to evaluate the welding effect. In some embodiments, the welding effective value 340 can be represented by a numerical value. The higher the numerical value, the better the welding effect.

[0074] The evaluation model 330 refers to a model used to determine the effective value of welding. In some embodiments, the evaluation model 330 can be a machine learning model, such as a neural network (NN) model or any combination of other custom model structures.

[0075] In some embodiments, the input of the evaluation model 330 may include the welding coverage amount of at least one section of the workpiece groove sub-section and the candidate welding parameters, and the output may include the welding effective value corresponding to the candidate welding parameter.

[0076] In some embodiments, the input to the evaluation model 330 may also include the groove position of the groove sub-segment.

[0077] The groove position refers to the position of the groove sub-segment compared to the weld. For example, in the middle of the weld, at the corner, etc.

[0078] In some embodiments of the present specification, since the groove position affects the accessibility, operation difficulty and final quality of the weld, considering the welding position when evaluating the effectiveness can make the evaluation result more reasonable.

[0079] In some embodiments, the input of the evaluation model 330 may also include groove material data of the groove sub-section, such as material chemical composition, density, melting point, etc.

[0080] For more information about groove position and groove material data, see Figure 4 Corresponding content.

[0081] In some embodiments of the present specification, due to the different absorption rates of welding energy by different metals and alloys, thicker materials usually require a slower laser travel speed to ensure sufficient heat transfer and melting depth to obtain good welding quality. Therefore, considering the characteristics of the material in evaluating the effectiveness can further improve the welding quality.

[0082] In some embodiments, the evaluation model 330 can be obtained through training in a variety of ways. For example, the evaluation model 330 can be obtained through training of multiple first training samples with first training labels, etc. A set of first training samples may include a sample welding cladding amount and a sample welding parameter of at least one sample workpiece groove sub-segment. The first training label corresponding to the first training sample can be the welding effective value obtained after the sample workpiece groove sub-segment is welded with the sample welding parameter. Among them, the processor and / or technician can determine the welding effective value based on the actual welding quality test results of the groove component after welding, and mark the corresponding label of the sample. The first training sample and the first training label can be obtained based on historical data. Among them, the detection of welding quality can include using non-destructive testing (NDT) methods, destructive testing methods, etc., and taking the ratio of the number of incomplete welds to the number of all welds of the sample workpiece groove sub-segment as the label value.

[0083] In some embodiments, the processor may train the evaluation model based on the first training sample and the first training label. The training method may include, but is not limited to, the gradient descent method, etc. As an example only, the processor may input a plurality of first training samples with the first training label into the initial evaluation model, construct a first loss function through the first training label and the output result of the initial evaluation model, and iteratively update the parameters of the initial evaluation model based on the first loss function. When the first preset condition is met, the model training is completed and a trained evaluation model is obtained. Among them, the first preset condition may be that the first loss function converges, the number of iterations reaches a threshold, etc.

[0084] In some embodiments, the processor can determine the welding parameters by multiple methods based on the welding effective value. For example, the processor can determine the candidate welding parameter with the largest welding effective value as the welding parameter finally used.

[0085] In some embodiments of this specification, a model is used to determine the effective value of welding, which significantly improves the intelligent level of welding parameter determination, thereby improving welding efficiency. With the help of the model's advanced algorithm and data analysis capabilities, a more accurate effective value of welding can be obtained, thereby improving welding quality.

[0086] Figure 4 It is an exemplary schematic diagram of a method for determining a model according to some embodiments of the present specification.

[0087] In some embodiments, the processor may determine the groove geometry 420 and the groove position 422 based on the groove three-dimensional model 410 ; and determine the target travel speed 440 based on the groove geometry 420 , the groove position 422 , and the welding parameters 424 .

[0088] The groove geometry 420 is the cross-sectional or end-face shape of the groove of the workpiece, such as the shape of the vertical cross-section, etc. In some embodiments, the groove geometry can be any one of U-shaped, J-shaped, K-shaped, etc.

[0089] The groove position 422 is the specific position of the groove on the workpiece.

[0090] In some embodiments, the processor may determine the groove geometry and groove position in a variety of ways. For example, the processor may determine the groove geometry and groove position by querying a groove three-dimensional model.

[0091] The target travel speed is the speed at which the line laser needs to move during scanning.

[0092] In some embodiments, the processor can determine the target travel speed in a variety of ways based on the groove geometry, groove position, and welding parameters. For example, the processor can determine the target travel speed through sample matching based on the groove geometry, groove position, and welding parameters.

[0093] In some embodiments, the processor may filter data having a welding effectiveness value greater than a effectiveness threshold from historical data as sample data.

[0094] In some embodiments, the processor may determine the sample groove geometry, sample groove position, sample welding parameter, and sample target travel speed corresponding to the sample data in the sample data as cluster vectors and perform clustering, thereby forming a preset number of cluster centers, determining the sample groove geometry, sample groove position, and sample welding parameter corresponding to the cluster center as standard vectors, and determining the sample target travel speed corresponding to the cluster center as a label of the standard vector. The preset number may be a preset value.

[0095] In some embodiments, the processor can construct a vector to be matched based on groove geometry, groove position, and welding parameters, and calculate the vector similarity between the vector to be matched and the standard vector, and determine the label corresponding to the standard vector with the highest similarity as the target travel speed.

[0096] In some embodiments, the processor may determine a target travel speed 440 based on the groove geometry 420 , the groove position 422 , and the welding parameters 424 by determining a model 430 .

[0097] The determination model 430 is a model for determining the target travel speed. In some embodiments, the determination model may be a machine learning model. For example, the determination model may be a neural network model (NN).

[0098] In some embodiments, the inputs to the determination model 430 may include groove geometry 420 , groove location 422 , welding parameters 424 , and the outputs may include a target travel speed 440 .

[0099] In some embodiments, Figure 4 As shown, the input of the determination model 430 also includes the contour change data 426. For more information about the contour change data, see Figure 2 Related description.

[0100] In some embodiments of the present specification, by adding contour change data as input, for example, the scanning speed can be slowed down at the location where the contour suddenly changes, so that more detailed data can be obtained.

[0101] In some embodiments, Figure 4 As shown, the input of the determination model 430 also includes groove material data 428. The groove material data 428 includes: groove material flatness and groove material type.

[0102] The groove material flatness is the smoothness of the groove material surface. The groove material type is the type of the groove material. In some embodiments, the groove material type may include any one or a combination of glass, polished metal, etc.

[0103] In some embodiments, the processor can determine the groove material data in a variety of ways. For example, the processor can photograph or scan the groove surface through a high-resolution camera or other equipment to determine the groove material flatness. For another example, the processor can perform component analysis on the groove material through spectral analysis, X-ray diffraction, etc. to determine the groove material type.

[0104] In some embodiments of the present specification, by adding groove material data as input, noise data caused by the material during the scanning process can be considered, making the obtained data more detailed.

[0105] In some embodiments, the determination model can be obtained by training based on a large number of second training samples with second labels through various feasible methods. For example, the parameters can be updated based on the gradient descent method. The training process of the determination model is similar to the training process of the evaluation model. For details, see Figure 3 Related description.

[0106] In some embodiments, the second training sample may include a sample groove geometry, a sample groove position, and a sample welding parameter, and the second label may be a sample target travel speed. The second training sample may be determined based on historical data. For example, the processor may filter the sample groove geometry, sample groove position, and sample welding parameter in the sample welding whose welding effective value is greater than the effective threshold from the historical data as the second training sample, wherein the effective threshold may be a manually preset value or determined based on historical experience. The second label may be the actual line laser travel speed of the sample welding corresponding to the second training sample.

[0107] In some embodiments, when the input to the determination model 430 also includes the profile variation data 426, the training samples may include sample profile variation data corresponding to the sample welding.

[0108] In some embodiments, when the input of the determination model 430 further includes the groove material data 428 , the training sample may include sample groove material data corresponding to the sample welding.

[0109] In some embodiments of this specification, the self-learning ability of the machine learning model can be used to continuously optimize and adjust according to the data in the actual welding process, so that the determination of the target travel speed is more in line with actual needs, thereby improving the welding quality and stability.

[0110] In some embodiments of the present specification, the quality of the obtained groove data can be effectively controlled by adjusting the travel speed of the line laser.

[0111] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0112] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0113] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0114] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0115] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0116] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0117] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A groove path and welding speed planning method, characterized in that: The method comprises: Scanning the groove of the workpiece by the line laser sensor according to the preset travel speed and the preset travel direction of the line laser to obtain the first groove data of the groove of the workpiece; Filtering the first groove data to obtain second groove data; Obtaining a groove three-dimensional model according to the second groove data; Based on the groove three-dimensional model and the preset moving direction, determining welding parameters includes: Determining contour change data according to the groove three-dimensional model; Based on the profile change data and the preset travel direction, the workpiece groove is divided into groove sub-segments; Determining the welding coverage amount of the groove subsection; The welding parameters are determined based on the welding coverage amount.

2. The method according to claim 1, characterized in that Determining the welding parameters based on the welding cladding amount includes: determining candidate welding parameters; Based on the welding cladding amount and the candidate welding parameters, a welding effective value is determined through an evaluation model; wherein the evaluation model is a machine learning model; The welding parameters are determined based on the welding effective values.

3. The method according to claim 1, characterized in that The method further comprises: Based on the groove three-dimensional model, determine the groove geometry and groove position; A target travel speed is determined based on the groove geometry, the groove position, and the welding parameters.

4. The method according to claim 3, characterized in that: The determining of the target travel speed based on the groove geometry, the groove position, and the welding parameters comprises: Based on the groove geometry, the groove position, and the welding parameters, the target travel speed is determined by determining a model; wherein the determination model is a machine learning model.

5. A groove path and welding speed planning system, characterized in that: The system comprises: A scanning module is used to scan the groove of the workpiece through a line laser sensor according to a preset travel speed and a preset travel direction of the line laser to obtain first groove data of the groove of the workpiece; A filtering module, used for filtering the first groove data to obtain second groove data; A three-dimensional model building module, used for obtaining a three-dimensional model of the groove according to the second groove data; A parameter determination module is used to determine welding parameters based on the groove three-dimensional model and the preset travel direction, and the parameter determination module is also used to: Determining contour change data according to the groove three-dimensional model; Based on the profile change data and the preset travel direction, the workpiece groove is divided into groove sub-segments; Determining the welding coverage amount of the groove subsection; The welding parameters are determined based on the welding coverage amount.

6. The system according to claim 5, characterized in that The parameter determination module is further used for: determining candidate welding parameters; Based on the welding cladding amount and the candidate welding parameters, a welding effective value is determined through an evaluation model; wherein the evaluation model is a machine learning model; The welding parameters are determined based on the welding effective values.

7. The system according to claim 5, characterized in that The system further comprises: An information determination module, used for determining the groove geometry and groove position based on the groove three-dimensional model; The speed determination module is used to determine the target travel speed based on the groove geometry, the groove position, and the welding parameters.

8. The system according to claim 7, characterized in that The speed determination module is further used for: Based on the groove geometry, the groove position, and the welding parameters, the target travel speed is determined by determining a model; wherein the determination model is a machine learning model.

Images