A hot zone trajectory compensation method, device and equipment for automobile chassis welding and a storage medium

Abstract

The application discloses a hot area track compensation method and device for automobile chassis welding, equipment and a storage medium, relates to the technical field of industrial robot welding control, and comprises the following steps: acquiring a target welding area of a workpiece to be welded; determining a non-heat affected zone of the target welding area, selecting a plurality of cold zone visual reference features on the non-heat affected zone, and acquiring a first position parameter of each cold zone visual reference feature and a second position parameter of each cold zone visual reference feature in a welding process; obtaining a topological distortion variable based on the first position parameter and the second position parameter; if the topological distortion variable is greater than a preset change threshold, a cold zone deformation feature is acquired; a target track point is obtained according to the cold zone deformation feature; a corrected welding track is generated according to the target track point; and the industrial robot is driven to perform a welding operation on the workpiece to be welded along the corrected welding track. The method can improve the stability of compensation.

Description

Technical Field

[0001] This application relates to the field of industrial robot welding control technology, and in particular to a method, apparatus, equipment and storage medium for hot zone trajectory compensation in automotive chassis welding. Background Technology

[0002] Industrial robots have been widely used in manufacturing scenarios such as automotive chassis, frame assembly, and stamping part welding, effectively improving welding efficiency and consistency. However, automotive chassis workpieces typically have characteristics such as large spatial dimensions, uneven local stiffness, and complex weld distribution. Under the action of welding heat input, they are prone to thermal deformation such as thermal expansion, contraction, warping, and torsion, causing the target welding area to deviate from the theoretical trajectory.

[0003] Existing welding trajectory compensation methods mostly employ visual sensors to directly observe features near the weld, molten pool, or welding area, correcting the robot path by identifying weld position deviations. For example, visual markers are placed near the weld or structured light is used to scan the weld contour, acquiring the actual position of the weld in real time and comparing it with a preset trajectory to generate compensation.

[0004] However, the drawback of the above-mentioned traditional solution is that the strong arc light, smoke and spatter during the welding process cause a decrease in the imaging quality of the hot zone and inaccurate compensation. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and storage medium for hot zone trajectory compensation in automotive chassis welding, which can achieve real-time dynamic compensation of the welding trajectory in harsh environments such as arc light, fumes, and spatter, thereby improving the accuracy of the compensation amount.

[0006] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application provides a method for compensating for hot zone trajectories in automotive chassis welding, the method comprising: Obtain the target welding area of ​​the workpiece to be welded; Determine the non-heat-affected zone of the target welding area, select multiple cold zone visual reference features on the non-heat-affected zone, and obtain the first position parameter of each cold zone visual reference feature; wherein, the number of cold zone visual reference features is not less than a preset number; Obtain the second position parameters of the visual reference features of each cold zone during the welding process; Based on the first and second position parameters of the cold zone visual reference features, the topological distortion between the cold zone visual reference features is obtained; If the topological distortion is greater than the preset change threshold, the residual term is obtained by removing the overall rigid body displacement component of the workpiece to be welded, and the cold zone deformation characteristics caused by welding heat input are obtained based on the residual term. The target trajectory point is obtained based on the deformation characteristics of the cold zone; The preset welding trajectory of the industrial robot is corrected based on the target trajectory points to generate a corrected welding trajectory. The industrial robot is driven to perform welding operations on the workpiece to be welded along the corrected welding trajectory.

[0007] In some possible implementations, obtaining the target trajectory point based on the cold zone deformation characteristics includes: The cold zone deformation characteristics and welding process state parameters are input into the hot zone offset mapping model to obtain the real-time offset of the target welding area; based on the real-time offset of the target welding area, the target trajectory point is obtained.

[0008] In some possible implementations, the method further includes: Determine whether the welding operation is completed to obtain a first determination result; if the first determination result indicates that the welding operation is completed, then end the welding operation.

[0009] In some possible implementations, the method further includes: If the first judgment result indicates that the welding operation is not completed, the second position parameter of the cold zone visual reference feature is updated to obtain the third position parameter of the cold zone visual reference feature.

[0010] In some possible implementations, obtaining the topological distortion between the cold zone visual reference features based on the first and second position parameters of the cold zone visual reference features includes: Based on the first and second position parameters of the cold zone visual reference features, calculate the relative distance change and relative angle change between any two cold zone visual reference features; based on the relative distance change and relative angle change, obtain the topological distortion between the cold zone visual reference features.

[0011] In some possible implementations, the method further includes: Determine whether the status parameters of the current welding process meet the abnormal triggering conditions, and obtain the second judgment result; If the second judgment result indicates that the state parameters of the current welding process meet the abnormal triggering conditions, then the abnormal fault tolerance control strategy is triggered; wherein, the abnormal triggering conditions include the number of effectively identified cold zone visual reference features being less than a preset minimum number threshold, or the change rate of cold zone deformation features being greater than a preset deformation rate threshold, or the hot zone offset being greater than a preset compensation upper limit threshold.

[0012] In some possible implementations, the cold zone visual reference feature is in the original geometric features of the workpiece to be welded and an additional reference body; the original geometric features of the workpiece to be welded include one or more of the following: reference hole, process hole, edge of weight reduction hole, locating pin hole, flange corner point and intersection of stamping rib; the additional reference body includes one or more of the following: detachable reference block, sprayed contrast pattern, etched mark or fixed reference part.

[0013] Secondly, this application provides a hot zone trajectory compensation device for automotive chassis welding, the device comprising: The acquisition module is used to acquire the target welding area of ​​the workpiece to be welded; determine the non-heat-affected zone of the target welding area, select multiple cold zone visual reference features on the non-heat-affected zone, and acquire the first position parameter of each cold zone visual reference feature; wherein the number of cold zone visual reference features is not less than a preset number; and acquire the second position parameter of each cold zone visual reference feature during the welding process. The calculation module is used to obtain the topological distortion between the visual reference features of the cold area based on the first position parameter and the second position parameter of the visual reference feature of the cold area; The correction module is used to obtain a residual term by removing the overall rigid body displacement component of the workpiece to be welded if the topological distortion is greater than a preset change threshold; obtain the cold zone deformation characteristics caused by welding heat input based on the residual term; obtain the target trajectory point according to the cold zone deformation characteristics; and dynamically correct the preset welding trajectory of the industrial robot according to the target trajectory point to generate the corrected welding trajectory. The execution module is used to drive the industrial robot to perform welding operations on the workpiece to be welded along the corrected welding trajectory.

[0014] Thirdly, this application provides a computing device, including a memory and a processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0015] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0016] Fifthly, this application provides a computer program product comprising one or more computer instructions, wherein when the computer instructions are executed by a computer, the computer performs the method as described in any one of the first aspects.

[0017] As can be seen from the above technical solution, this application has at least the following beneficial effects: In this application, the target welding area of ​​the workpiece to be welded is obtained; the non-heat-affected zone (NAZ) of the target welding area is determined, and multiple cold zone visual reference features are selected in the NAZ, and the first position parameter of each cold zone visual reference feature is obtained; the second position parameter of each cold zone visual reference feature is obtained during the welding process; based on the first and second position parameters of the cold zone visual reference features, the topological distortion between the cold zone visual reference features is obtained; if the topological distortion is greater than a preset change threshold, the residual term is obtained by removing the overall rigid body displacement component of the workpiece to be welded, and the cold zone deformation feature caused by the welding heat input is obtained based on the residual term; the target trajectory point is obtained based on the cold zone deformation feature; the preset welding trajectory of the industrial robot is corrected based on the target trajectory point to generate the corrected welding trajectory; and the industrial robot is driven to perform welding operations on the workpiece to be welded along the corrected welding trajectory.

[0018] In existing technical solutions, visual sensors are often used to directly observe features near the weld, molten pool, or welding area to correct the robot's welding trajectory. However, the strong arc light, fumes, and spatter generated during welding severely degrade the quality of direct imaging of the hot zone, leading to inaccurate compensation. Therefore, this application avoids the interference of the harsh environment of the welding hot zone on visual observation by setting cold zone visual reference features in the non-heat-affected zone of the target welding area, achieving trajectory compensation without directly acquiring clear images of the hot zone. By calculating the topological distortion between the cold zone visual reference features and eliminating the overall rigid body displacement components of the workpiece to be welded, the deformation features of the cold zone caused by welding heat input can be accurately extracted, effectively eliminating interference from non-thermal deformation factors and improving the accuracy of hot zone offset estimation. Based on the cold zone deformation features, the target trajectory points are deduced and the preset welding trajectory of the industrial robot is dynamically corrected, achieving real-time dynamic compensation for welding thermal deformation and improving welding quality.

[0019] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0020] Figure 1A schematic diagram illustrating an application scenario provided in an embodiment of this application; Figure 2 A flowchart illustrating a method for compensating the hot zone trajectory in automotive chassis welding, provided in an embodiment of this application; Figure 3 A schematic diagram of a hot zone trajectory compensation device for automotive chassis welding provided in this application embodiment; Figure 4 This is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0021] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0022] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0023] Currently, industrial robots are widely used in the welding production process of automobile chassis. Existing technologies mostly use vision sensors to directly observe the welding area and adjust the robot's running path based on the observation results.

[0024] The arc smoke and spatter generated during welding can interfere with the visual acquisition process, leading to a decrease in the imaging quality of the hot zone and making it impossible to continuously and stably obtain accurate positional information of the welding area.

[0025] In view of this, embodiments of this application provide a method for hot zone trajectory compensation in automotive chassis welding. This method can be applied to a processing device, which can be a terminal or a server. Terminals include, but are not limited to, smartphones, tablets, laptops, personal digital assistants, or smart wearable devices. Servers can be cloud servers, such as central servers in a central cloud computing cluster or edge servers in an edge cloud computing cluster. Alternatively, servers can be located in a local data center. A local data center refers to a data center directly controlled by the user. Compared to existing technologies, this application selects visual reference features at locations far from the welding hot zone, avoiding interference from the hot zone environment and stably acquiring reference information. Simultaneously, by analyzing the relative positional changes of the reference features, it distinguishes between the overall displacement of the workpiece and the deformation caused by heat input, thereby correcting the welding trajectory and improving the consistency of the welding operation.

[0026] To make the technical solution of this application clearer and easier to understand, the application scenarios of the technical solution of this application are described below with reference to the accompanying drawings. Figure 1 As shown in the figure, this figure is a schematic diagram of an application scenario provided by an embodiment of this application.

[0027] In this application scenario, the automotive chassis welding workstation includes an intelligent control cabinet 1, an industrial robot 21, a workpiece fixture 4, a vision acquisition device 6, and a workpiece 3 to be welded. The industrial robot 21 is mounted on a robot base 22, and its main body 2 has a welding actuator 23 at its end, used to perform welding operations on the target welding area 7 of the workpiece 3. The workpiece 3 is clamped in the workpiece fixture 4, and multiple cold zone visual reference features 5 are selected in the non-heat-affected zone far from the target welding area 7. The vision acquisition device 6 is fixed to the periphery or top of the welding workstation to acquire image information of the cold zone visual reference features 5 in real time. The intelligent control cabinet 1 contains a control unit, which is communicatively connected to both the vision acquisition device 6 and the industrial robot 21. The control unit receives image information transmitted by the vision acquisition device 6, calculates the spatial position parameters of the cold zone visual reference features 5, extracts cold zone deformation features, calculates hot zone offset, and then generates trajectory correction instructions for the industrial robot 21, driving the industrial robot 21 to complete the welding operation along the corrected welding trajectory.

[0028] In actual working conditions, the workpiece 3 to be welded will deform under the action of welding heat input, causing the target welding area to deviate from the preset position. At the same time, the arc smoke and spatter generated during the welding process will interfere with the visual acquisition process. If the target welding area 7 is directly observed, it is impossible to obtain accurate position information stably, thus affecting the effect of welding trajectory correction.

[0029] This application establishes a cold zone visual reference feature 5 in the non-heat-affected zone far from the target welding area 7, enabling the visual acquisition device 6 to avoid interference from the hot zone environment and continuously and stably acquire clear reference images. The control unit compares the initial and real-time positions of the cold zone visual reference feature 5, analyzes the relative positional changes between the features, separates the overall workpiece displacement from the deformation caused by heat input, and then infers the actual offset of the target welding area 7 based on the cold zone deformation characteristics. Based on this, the welding trajectory of the industrial robot 21 is dynamically corrected to ensure the accuracy and consistency of the welding operation.

[0030] To make the technical solution of this application clearer and easier to understand, the following describes a method for hot zone trajectory compensation in automotive chassis welding, based on the above application scenarios. Figure 2 As shown, this figure is a flowchart of a hot zone trajectory compensation method for automotive chassis welding provided in an embodiment of this application. The method includes: S201. The processing equipment acquires the target welding area of ​​the workpiece to be welded, determines the non-heat-affected zone of the target welding area, selects multiple cold zone visual reference features in the non-heat-affected zone, and acquires the first position parameter of each cold zone visual reference feature.

[0031] The target welding area is the area on the workpiece that needs to be welded.

[0032] The non-heat affected zone is the area where the temperature rise is below a preset threshold during welding and is not directly exposed to arc light or continuously attacked by spatter. The preset threshold can be set to 50°C.

[0033] The aforementioned regions are all represented by a set of three-dimensional spatial boundary coordinates in the global coordinate system.

[0034] The visual reference feature for the cold zone is a recognizable geometric feature set in the non-heat-affected zone to reflect the deformation state of the workpiece.

[0035] The first position parameter is the initial spatial position parameter of the visual reference feature of the cold zone in the global coordinate system before welding begins.

[0036] The global coordinate system is a unified spatial reference coordinate system established for the entire welding workstation.

[0037] The processing equipment obtains the target welding area of ​​the workpiece 3 according to the preset welding process document. The processing equipment calculates the welding heat input under the current process based on the welding current, welding voltage, and welding speed. Welding heat input refers to the heat transferred per unit length of weld seam by the welding heat source (such as an electric arc) during the welding process. The calculation formula for the welding heat input under the current process is as follows:

[0038] in, This refers to the welding heat input under the current process, that is, the heat transferred from the welding heat source to a unit length of weld. Let be the thermal efficiency constant. For welding voltage, For welding current, This refers to the welding speed. The greater the welding heat input, the more heat is transferred to the workpiece during the welding process, and the wider the heat-affected zone becomes.

[0039] The processing equipment calculates the theoretical heat-affected zone boundary range by combining the thermophysical parameters of the workpiece material to be welded, including thermal conductivity, specific heat capacity, and coefficient of thermal expansion. For example, for a low-carbon steel workpiece with a thickness of 3mm, when the welding current is 180A, the welding voltage is 20V, and the welding speed is 5mm / s, the theoretical heat-affected zone width is approximately 8mm.

[0040] The processing equipment further modifies the heat-affected zone boundary based on the structural characteristics of the workpiece to be welded. For structures with high stiffness, such as reinforcing ribs and flanges on the workpiece, the heat conduction speed is slow, and the heat-affected zone will expand to one side of the structure; for structures with low stiffness, such as the edges of openings on the workpiece, the heat conduction speed is fast, and the range of the heat-affected zone will be correspondingly reduced.

[0041] The processing equipment uses the corrected heat-affected zone boundary as a reference and extends outward by a certain distance to determine the range of the non-heat-affected zone. In this application, the extension distance can be set to 7mm. In practice, the extension distance can be dynamically adjusted according to the workpiece plate thickness and structural rigidity. For thin-walled parts, the extension dimension is increased, and for high-rigidity thick plates, the extension dimension is reduced to ensure that the non-heat-affected zone is not directly affected by the welding heat input, while avoiding areas affected by arc light irradiation and spatter. Thus, the processing equipment determines the non-heat-affected zone around the target welding area.

[0042] The processing equipment selects multiple cold zone visual reference features 5 in the non-heat-affected zone. These cold zone visual reference features 5 include the original geometric features of the workpiece to be welded and additional reference bodies. The original geometric features of the workpiece to be welded include one or more of the following: reference holes, process holes, weight reduction hole edges, locating pin holes, flange corners, and intersections of stamping ribs. The additional reference bodies include one or more of the following: detachable reference blocks, sprayed comparison patterns, etched marks, or fixed reference parts. The number of cold zone visual reference features 5 is not less than a preset number, for example, the preset number can be set to 3. The reason for choosing to set visual reference features in the non-heat-affected zone is that the target welding area generates a large amount of arc smoke and spatter during the welding process. Directly observing this target welding area will lead to a decrease in imaging quality and an inability to stably obtain accurate positional information. The non-heat-affected zone, however, is not affected by these factors and can continuously provide clear and stable visual reference information.

[0043] In this embodiment, the number of visual reference features for the cold zone is set to be no less than a preset number. This is to ensure that the application can accurately separate the overall rigid body displacement of the workpiece from the local deformation caused by welding heat input. On the other hand, from a mathematical constraint perspective, a rigid body in three-dimensional space has six degrees of freedom of motion. Solving for a unique rigid body transformation relationship requires at least three non-collinear reference points. If the number is insufficient, a definite solution cannot be obtained, and the rigid body displacement components cannot be eliminated. From the deformation detection principle perspective, only when the number of reference points is ≥3 can the relative distance change and relative angle change between features be calculated simultaneously, fully characterizing the topological distortion and avoiding misjudging the overall displacement as thermal deformation. From the perspective of system fault tolerance, setting 3 points initially can trigger an abnormal fault tolerance strategy of "insufficient number of effective recognitions" when one point fails due to occlusion or other reasons, preventing system loss of control. In addition, a sufficient number of reference points can provide more comprehensive information on the cold zone deformation distribution, improve the accuracy of the hot zone offset mapping model, and ultimately ensure the accuracy and reliability of trajectory compensation.

[0044] After completing coordinate registration between the vision acquisition device 6, the industrial robot 21, and the global coordinate system, the processing equipment starts the vision acquisition device 6 to acquire an initial static image containing all cold zone visual reference features 5. The processing equipment performs preprocessing operations such as grayscale conversion, filtering, and noise reduction on the acquired initial image to remove noise interference. The processing equipment uses template matching edge detection or sub-pixel localization algorithms to identify the image coordinates of each cold zone visual reference feature 5 in the preprocessed image. If the vision acquisition device 6 is a binocular or multi-view vision system, the processing equipment will combine images acquired from different perspectives and calculate the three-dimensional spatial coordinates of the cold zone visual reference feature 5 in the vision acquisition device coordinate system using a stereo reconstruction algorithm. If the vision acquisition device 6 is a monocular vision system, the processing equipment will combine the pre-calibrated geometric dimensions and planar constraint relationships of the workpiece 3 to be welded to calculate the relative spatial coordinates of the cold zone visual reference feature 5. The processing equipment then converts the coordinates in the vision acquisition device coordinate system to the coordinates in the global coordinate system according to the pre-completed coordinate registration relationship, finally obtaining the first position parameter of each cold zone visual reference feature 5.

[0045] This step, by setting up visual reference features for the cold zone in the non-heat-affected zone, avoids interference from the welding hot zone environment on visual acquisition, ensuring the clarity and stability of the reference feature images. Using the workpiece's native geometric features as visual reference features for the cold zone eliminates the need for additional complex marking devices, reducing system costs and implementation difficulty.

[0046] S202, The processing equipment acquires the second position parameters of the visual reference features of each cold zone during the welding process.

[0047] The second position parameter is the real-time spatial position parameter of the visual reference feature of the cold zone in the global coordinate system at a certain moment during the welding process.

[0048] After the welding operation starts, the processing equipment controls the vision acquisition device 6 to continuously acquire real-time images containing all cold zone visual reference features 5 at a preset sampling frequency, which can be set to twenty frames per second. The processing equipment performs preprocessing operations such as grayscale conversion, filtering, and noise reduction on each frame of the real-time image to eliminate environmental noise and minor interference in the image. The processing equipment uses the same template matching edge detection or sub-pixel localization algorithm as the initial image to identify the real-time image coordinates of each cold zone visual reference feature 5 in the preprocessed real-time image.

[0049] If the visual acquisition device 6 is a binocular or multi-view vision system, the processing device combines real-time images from different perspectives and uses a stereo reconstruction algorithm to calculate the real-time three-dimensional spatial coordinates of the cold zone visual reference feature 5 in the coordinate system of the visual acquisition device. If the visual acquisition device 6 is a monocular vision system, the processing device combines the pre-calibrated geometric dimensions and planar constraints of the workpiece 3 to be welded to calculate the real-time relative spatial coordinates of the cold zone visual reference feature 5. Based on the pre-completed coordinate registration relationship, the processing device converts the real-time coordinates in the coordinate system of the visual acquisition device into coordinates in the global coordinate system, and finally obtains the second position parameter of each cold zone visual reference feature 5 at the current moment.

[0050] S203. The processing equipment obtains the topological distortion between the visual reference features of the cold zone based on the first position parameter and the second position parameter of the visual reference features of the cold zone.

[0051] Topological distortion is the change in the relative position and relative angle between visual reference features in the cold zone relative to the initial state, used to characterize the degree of deformation of the local structure of the workpiece.

[0052] After acquiring the second position parameters of all cold zone visual reference features at the current moment, the processing device sequentially calculates the relative distance change between any two cold zone visual reference features, i.e., the topological distortion between the cold zone visual reference features. The formula for calculating the relative distance change is:

[0053] in, Indicates the first The visual reference features of the cold zone at time The spatial coordinates, i.e., the first The second location parameter of the visual reference feature of the cold zone; Indicates the first The visual reference features of the cold zone at time The spatial coordinates, i.e., the first The second location parameter of the visual reference feature of the cold zone; Indicates the first The first position parameter of the visual reference feature of the cold zone; Indicates the first The first position parameter of the visual reference feature of the cold zone; Indicates the first The and the first The relative distance change between visual reference features in the cold zone.

[0054] This step, by calculating the topological distortion between visual reference features in the cold zone, effectively reflects the local deformation state of the workpiece, avoiding interference from overall workpiece translation or rotation on deformation judgment. By combining relative distance changes and relative angle changes, the deformation characteristics of the workpiece can be comprehensively characterized, improving the accuracy of deformation detection.

[0055] S204. If the topological distortion is greater than the preset change threshold, the residual term is obtained by removing the overall rigid body displacement component of the workpiece to be welded, and the cold zone deformation characteristics caused by the welding heat input are obtained based on the residual term.

[0056] The cold zone deformation characteristic is the local displacement of the visual reference feature of the cold zone caused only by the welding heat input after removing the overall rigid body displacement component.

[0057] The processing equipment compares the calculated topological distortion with a preset change threshold, which can be set to 0.5 mm. If the topological distortion is greater than the preset change threshold, it indicates that the workpiece to be welded has undergone detectable structural deformation. At this time, the processing equipment initiates a rigid body displacement rejection process to remove the overall rigid body displacement component. During clamping and welding, the workpiece may experience overall translation or rotation due to factors such as loose fixtures or equipment vibration. This type of displacement is not due to deformation caused by welding heat input and needs to be removed from the total displacement. The overall rigid body displacement component refers to the overall translational and rotational displacement of the workpiece to be welded, excluding local structural deformation within the workpiece.

[0058] The processing device determines the optimal rigid body transformation relationship between the initial reference feature coordinate set and the real-time reference feature coordinate set, so that the objective function... Minimum, where R represents the optimal rotation matrix, T represents the optimal translation vector, and n represents the total number of visual reference features in the cold zone.

[0059] The processing equipment calculates the residual term corresponding to the visual reference feature of each cold zone. The formula for calculating the residual term is as follows: ,in, This represents the residual term of the i-th cold zone visual reference feature. Each residual term is a three-dimensional vector containing the local displacement components of the corresponding cold zone visual reference feature in the x-axis, y-axis, and z-axis directions in the global coordinate system.

[0060] The processing equipment arranges the residual terms of all cold zone visual reference features in a preset order and combines them into a one-dimensional vector form of cold zone deformation features. The processing equipment can normalize the combined vector according to actual needs, unifying the numerical range of each component.

[0061] This step, by eliminating the overall rigid body displacement component of the workpiece to be welded, accurately separates the local deformation caused by welding heat input from the overall displacement caused by other factors, avoiding interference from non-thermal deformation factors in subsequent hot zone offset calculations. Using the optimal rigid body transformation method to calculate the residual terms effectively extracts the cold zone deformation characteristics that reflect the true thermal deformation state, improving the accuracy of deformation analysis.

[0062] S205. The processing equipment obtains the target trajectory point based on the deformation characteristics of the cold zone.

[0063] The processing equipment inputs the cold zone deformation characteristics and welding process status parameters into the hot zone offset mapping model to obtain the real-time offset of the target welding area; based on the real-time offset of the target welding area, the target trajectory point is obtained.

[0064] Specifically, the processing equipment inputs the obtained cold zone deformation characteristics into the hot zone offset mapping model to calculate the real-time offset of the target welding area. The hot zone offset mapping model is used to establish the functional relationship between the cold zone deformation characteristics and the offset of the target welding area, and its expression is: ,in, This indicates the real-time offset of the target welding area. The cold zone deformation characteristics are represented by q, which represents the welding process parameters, including welding current, welding voltage, welding speed, welding sequence, and clamping status.

[0065] Furthermore, considering the computational constraints of real-time control in industrial settings, under local linearization conditions, the thermal zone offset mapping model can be simplified to the following:

[0066] in, The transformation matrix is ​​dynamically changed with the welding process state parameters. The transformation matrix can be obtained through offline experimental calibration or finite element simulation fitting.

[0067] After obtaining the real-time offset of the target welding area, the processing equipment calculates the target trajectory point by combining it with the preset welding trajectory points of the industrial robot. The formula for calculating the target trajectory point is:

[0068] in, This represents the corrected target trajectory point. This indicates the preset welding trajectory points of the industrial robot.

[0069] This step establishes a mapping relationship between the deformation characteristics of the cold zone and the offset of the hot zone. It allows for the deduction of the actual offset of the hot zone based on stable visual information of the cold zone, without the need for direct observation of the disturbed welding hot zone. Dynamically correcting the preset welding trajectory based on the real-time offset enables the industrial robot's welding path to follow changes in the target welding area, ensuring the accuracy and consistency of the welding operation.

[0070] S206. The processing equipment corrects the preset welding trajectory of the industrial robot based on the target trajectory points and generates the corrected welding trajectory.

[0071] After acquiring the target trajectory point corresponding to the current moment, the processing device locates the corresponding position of the target trajectory point within the preset welding trajectory. The preset welding trajectory is composed of multiple discrete preset trajectory points connected sequentially according to the welding order, with each preset trajectory point corresponding to a welding moment and spatial position. The processing device replaces the preset trajectory point at the corresponding moment with the calculated target trajectory point.

[0072] To ensure the smoothness of the industrial robot's movement, the processing equipment smooths the sequence of replaced trajectory points. The equipment uses cubic spline interpolation to calculate the target trajectory point and its adjacent points, generating a continuous transition path with continuous velocity and acceleration. The equipment only corrects welding trajectory segments that have not yet been executed after the current moment; completed welding segments remain unchanged.

[0073] The processing equipment repeats the above correction process at preset time intervals. Each correction updates the remaining welding trajectory based on the latest calculated target trajectory point, and finally generates a complete corrected welding trajectory.

[0074] This step, by replacing the corresponding preset trajectory points with target trajectory points, enables the welding trajectory to follow the thermal deformation offset of the target welding area in real time. Smoothing the trajectory avoids sudden impacts during the industrial robot's movement, ensuring the stability of the welding process. Correcting only unexecuted trajectory segments reduces computational load and improves the real-time performance of trajectory correction.

[0075] S207. The processing equipment drives an industrial robot to perform welding operations on the workpiece to be welded along the corrected welding trajectory.

[0076] The processing equipment converts the generated, corrected welding trajectory into drive instructions that the industrial robot 21 can recognize. These drive instructions include angle instructions for each joint of the industrial robot 21, pose instructions for the end effector, and motion speed instructions. Simultaneously, the processing equipment generates corresponding welding process instructions, which are synchronized with the drive instructions in time.

[0077] The processing equipment sends drive commands and welding process commands to the controller of the industrial robot 21. After receiving the commands, the controller of the industrial robot 21 controls the coordinated movement of each joint, causing the welding actuator 23 to move along the corrected welding trajectory. At the same time, the controller sends welding process commands to the welding power source and wire feeding mechanism, controlling the parameter output of the welding process.

[0078] During the welding operation, the processing equipment continuously collects image information of the visual reference feature 5 of the cold zone according to the preset sampling frequency, repeatedly executes the process of position parameter solution, topological distortion calculation, rigid body displacement elimination, hot zone offset calculation and trajectory correction, and updates the drive instructions in real time to ensure that the welding actuator 23 always follows the actual position movement of the target welding area 7.

[0079] This step, by driving an industrial robot to perform the operation along the corrected welding trajectory, ensures that the welding actuator is accurately aligned with the actual target welding area, improving the weld formation quality. Synchronously sending welding process commands ensures the stability of welding process parameters. Continuous real-time trajectory updates dynamically compensate for thermal deformation throughout the welding process, enhancing the consistency of the welding operation.

[0080] In some embodiments, the processing device further determines whether the welding operation has been completed and obtains a first determination result; if the first determination result indicates that the welding operation has been completed, the welding operation is terminated.

[0081] If the first judgment result indicates that the welding operation has not been completed, the second position parameter of the cold zone visual reference feature is updated to obtain the third position parameter of the cold zone visual reference feature.

[0082] Specifically, after the processing equipment completes the welding trajectory correction and execution for the current compensation cycle, it immediately determines whether the welding operation is completed and obtains the first judgment result. The processing equipment compares the currently executed trajectory point number with the total trajectory point number of the preset welding trajectory and receives the arc extinguishing completion signal sent by the welding power source. When the executed trajectory point number is equal to the total trajectory point number and the arc extinguishing completion signal sent by the welding power source is received, the processing equipment determines that the welding operation is completed.

[0083] If the first judgment result indicates that the welding operation has been completed, the processing equipment sends a stop motion command to the industrial robot 21 and a shut-off output command to the welding power source to end the welding operation.

[0084] If the first judgment result indicates that the welding operation is not completed, the processing equipment controls the vision acquisition device 6 to acquire a real-time image containing all cold zone visual reference features 5 at the next moment. Following the same calculation method as the second position parameter, the second position parameter is updated to obtain the third position parameter for each cold zone visual reference feature 5. The processing equipment compares the first and third position parameters of the cold zone visual reference feature 5 and, following the same calculation method as S203, obtains the topological distortion between the cold zone visual reference features at the current moment. It then continues to execute subsequent rigid body displacement removal, cold zone deformation feature extraction, hot zone offset calculation, and trajectory correction processes, forming a continuous dynamic compensation process.

[0085] This step, by setting a welding operation completion judgment node, can promptly stop equipment operation after all welding tasks are completed, avoiding unnecessary resource consumption. By automatically entering the next compensation cycle when welding is not yet complete, continuous thermal deformation compensation can be performed throughout the welding process, ensuring the welding quality of all weld segments. Employing multiple methods to determine the welding operation completion status can improve the reliability of the judgment results and avoid welding interruptions or over-welding caused by misjudgments.

[0086] In some embodiments, the processing device further determines whether the state parameters of the current welding process meet the abnormal triggering conditions and obtains a second determination result; if the second determination result indicates that the state parameters of the current welding process meet the abnormal triggering conditions, then the abnormal fault tolerance control strategy is triggered; wherein, the abnormal triggering conditions include the number of effectively identified cold zone visual reference features being less than a preset minimum number threshold, or the rate of change of cold zone deformation features being greater than a preset deformation rate threshold, or the hot zone offset being greater than a preset compensation upper limit threshold.

[0087] During the execution of each compensation cycle, the processing equipment synchronously determines whether the status parameters of the current welding process meet the abnormal triggering conditions, and obtains a second judgment result. There are three abnormal triggering conditions: First, the number of effectively identified cold zone visual reference features is less than a preset minimum threshold, which can be set to 1. Second, the rate of change of cold zone deformation features is greater than a preset deformation rate threshold, which can be set to 2 mm per second. Third, the hot zone offset is greater than a preset compensation upper limit threshold, which can be set to 5 mm.

[0088] If the second judgment result indicates that the current welding process status parameters meet any one of the abnormal triggering conditions, the processing equipment immediately triggers the corresponding abnormal fault-tolerant control strategy. When the number of effectively identified cold zone visual reference features is less than the preset minimum number threshold, the processing equipment pauses trajectory compensation, keeps the current position of the industrial robot 21 and the welding parameters unchanged, and issues a visual recognition abnormality alarm. When the rate of change of cold zone deformation features is greater than the preset deformation rate threshold, the processing equipment continues to observe. If the rate of change of cold zone deformation features is greater than the preset deformation rate threshold for multiple consecutive sampling cycles (e.g., three consecutive sampling cycles), the welding speed is reduced to 50% of the original speed, and the visual acquisition frequency is increased to 40 frames per second to strengthen deformation monitoring. When the hot zone offset is greater than the preset compensation upper limit threshold, the processing equipment controls the welding actuator 23 to detach from the surface of the workpiece 3 to be welded, sends an arc extinguishing command to shut down the welding power supply, issues a compensation over-limit alarm, and stops the machine.

[0089] If the second judgment result indicates that the current welding process status parameters do not meet any abnormal triggering conditions, the processing equipment continues to execute the normal welding trajectory compensation process.

[0090] This step, by setting multi-dimensional anomaly trigger conditions, can promptly detect visual recognition anomalies, sudden deformation changes, and compensation exceeding limits during the welding process. By triggering corresponding anomaly tolerance control strategies, appropriate measures can be taken when anomalies occur, avoiding welding quality defects and equipment damage. By setting different tolerance measures at different levels, unnecessary welding interruptions can be minimized while ensuring safety, thereby improving welding production efficiency.

[0091] The above text combined Figures 1 to 2 The hot zone trajectory compensation method for automotive chassis welding provided in this application embodiment has been described in detail. The apparatus and equipment provided in this application embodiment will be described below with reference to the accompanying drawings.

[0092] This application also provides a hot zone trajectory compensation device for automotive chassis welding, such as... Figure 3 As shown in the figure, this is a schematic diagram of a hot zone trajectory compensation device for automotive chassis welding provided in an embodiment of this application. The device includes: The acquisition module 301 is used to acquire the target welding area of ​​the workpiece to be welded; determine the non-heat-affected zone of the target welding area, select multiple cold zone visual reference features on the non-heat-affected zone, and acquire the first position parameter of each cold zone visual reference feature; wherein the number of cold zone visual reference features is not less than a preset number; and acquire the second position parameter of each cold zone visual reference feature during the welding process. Calculation module 302 is used to obtain the topological distortion between the visual reference features of the cold area based on the first position parameter and the second position parameter of the visual reference features of the cold area; The correction module 303 is used to obtain a residual term by removing the overall rigid body displacement component of the workpiece to be welded if the topological distortion is greater than a preset change threshold; obtain the cold zone deformation characteristics caused by welding heat input based on the residual term; obtain the target trajectory point according to the cold zone deformation characteristics; and dynamically correct the preset welding trajectory of the industrial robot according to the target trajectory point to generate the corrected welding trajectory. The execution module 304 is used to drive the industrial robot to perform welding operations on the workpiece to be welded along the corrected welding trajectory.

[0093] In some possible implementations, the correction module 303 is specifically used to input the cold zone deformation characteristics and welding process state parameters into the hot zone offset mapping model to obtain the real-time offset of the target welding area; and to obtain the target trajectory point based on the real-time offset of the target welding area.

[0094] In some possible implementations, the device further includes: The first judgment module is used to determine whether the welding operation has been completed and obtain a first judgment result; if the first judgment result indicates that the welding operation has been completed, the welding operation is terminated.

[0095] In some possible implementations, the first judgment module is further configured to update the second position parameter of the cold zone visual reference feature if the first judgment result indicates that the welding operation has not been completed, so as to obtain the third position parameter of the cold zone visual reference feature.

[0096] In some possible implementations, the calculation module 302 is specifically used to calculate the relative distance change and relative angle change between any two cold zone visual reference features based on the first position parameter and the second position parameter of the cold zone visual reference feature; and to obtain the topological distortion between the cold zone visual reference features based on the relative distance change and the relative angle change.

[0097] In some possible implementations, the device further includes: The second judgment module is used to determine whether the state parameters of the current welding process meet the abnormal triggering conditions and obtain the second judgment result. If the second judgment result indicates that the state parameters of the current welding process meet the abnormal triggering conditions, the abnormal fault tolerance control strategy is triggered. The abnormal triggering conditions include the number of effectively identified cold zone visual reference features being less than a preset minimum number threshold, or the rate of change of cold zone deformation features being greater than a preset deformation rate threshold, or the hot zone offset being greater than a preset compensation upper limit threshold.

[0098] In some possible implementations, the cold zone visual reference feature is the original geometric feature of the workpiece to be welded and an additional reference body; the original geometric feature of the workpiece to be welded includes one or more of the following: reference hole, process hole, edge of weight reduction hole, locating pin hole, flange corner point and intersection of stamping rib; the additional reference body includes one or more of the following: detachable reference block, sprayed contrast pattern, etched mark or fixed reference part.

[0099] The hot zone trajectory compensation device for automotive chassis welding according to the embodiments of this application can correspondingly execute the method described in the embodiments of this application, and the other operations and / or functions of each module / unit of the hot zone trajectory compensation device for automotive chassis welding are respectively for implementing Figure 2 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0100] This application also provides a computing device. For example... Figure 4 As shown in the figure, this is a schematic diagram of a computing device provided in an embodiment of this application. The computing device 400 includes a bus 401, a processor 402, a communication interface 403, and a memory 404. The processor 402, the memory 404, and the communication interface 403 communicate with each other via the bus 401.

[0101] Bus 401 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0102] Processor 402 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0103] The communication interface 403 is used for communication with external devices. For example, if the computing device is a first switch, the communication interface 403 can be used for communication between the first switch and a first user terminal, or for communication between the first switch and a second switch.

[0104] Memory 404 may include volatile memory, such as random access memory (RAM). Memory 404 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0105] The memory 404 stores executable code, and the processor 402 executes the executable code to perform the aforementioned hot zone trajectory compensation method for automotive chassis welding.

[0106] Specifically, in achieving Figure 3 In the case of the illustrated embodiment, and Figure 3 When the modules or units of the hot zone trajectory compensation device for automotive chassis welding described in the embodiments are implemented by software, the execution... Figure 3 The software or program code required for the functions of each module / unit can be partially or entirely stored in memory 404. Processor 402 executes the program code corresponding to each unit stored in memory 404, and executes the aforementioned hot zone trajectory compensation method for automotive chassis welding.

[0107] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct a computing device to execute the aforementioned hot-zone trajectory compensation method for automotive chassis welding.

[0108] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0109] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0110] When the computer program product is executed by a computer, the computer performs any of the aforementioned methods of the hot zone trajectory compensation method for automotive chassis welding. The computer program product can be a software installation package; when any of the aforementioned methods of the hot zone trajectory compensation method for automotive chassis welding is required, the computer program product can be downloaded and executed on the computer.

[0111] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0112] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method for compensating for hot zone trajectory in automotive chassis welding, characterized in that, The method includes: Obtain the target welding area of ​​the workpiece to be welded; Determine the non-heat-affected zone of the target welding area, select multiple cold zone visual reference features on the non-heat-affected zone, and obtain the first position parameter of each cold zone visual reference feature; wherein, the number of cold zone visual reference features is not less than a preset number; Obtain the second position parameters of the visual reference features of each cold zone during the welding process; Based on the first and second position parameters of the cold zone visual reference features, the topological distortion between the cold zone visual reference features is obtained; If the topological distortion is greater than the preset change threshold, the residual term is obtained by removing the overall rigid body displacement component of the workpiece to be welded, and the cold zone deformation characteristics caused by welding heat input are obtained based on the residual term. The target trajectory point is obtained based on the deformation characteristics of the cold zone; The preset welding trajectory of the industrial robot is corrected based on the target trajectory points to generate a corrected welding trajectory. The industrial robot is driven to perform welding operations on the workpiece to be welded along the corrected welding trajectory.

2. The method according to claim 1, characterized in that, The step of obtaining the target trajectory point based on the deformation characteristics of the cold zone includes: The cold zone deformation characteristics and welding process state parameters are input into the hot zone offset mapping model to obtain the real-time offset of the target welding area. The target trajectory point is obtained based on the real-time offset of the target welding area.

3. The method according to claim 1, characterized in that, The method further includes: Determine whether the welding operation has been completed to obtain a first determination result; If the first determination result indicates that the welding operation has been completed, then the welding operation is terminated.

4. The method according to claim 3, characterized in that, The method further includes: If the first judgment result indicates that the welding operation is not completed, the second position parameter of the cold zone visual reference feature is updated to obtain the third position parameter of the cold zone visual reference feature.

5. The method according to claim 1, characterized in that, The step of obtaining the topological distortion between the visual reference features of the cold zone based on the first and second position parameters of the visual reference features of the cold zone includes: Based on the first and second position parameters of the cold zone visual reference features, calculate the relative distance change and relative angle change between any two cold zone visual reference features. Based on the relative distance change and the relative angle change, the topological distortion between the visual reference features of the cold zone is obtained.

6. The method according to claim 1, characterized in that, The method further includes: Determine whether the status parameters of the current welding process meet the abnormal triggering conditions, and obtain the second judgment result; If the second judgment result indicates that the state parameters of the current welding process meet the abnormal triggering conditions, then the abnormal fault tolerance control strategy is triggered; wherein, the abnormal triggering conditions include the number of effectively identified cold zone visual reference features being less than a preset minimum number threshold, or the change rate of cold zone deformation features being greater than a preset deformation rate threshold, or the hot zone offset being greater than a preset compensation upper limit threshold.

7. The method according to claim 1, characterized in that, The visual reference features of the cold zone are the original geometric features of the workpiece to be welded and an additional reference body; the original geometric features of the workpiece to be welded include one or more of the following: reference hole, process hole, edge of weight reduction hole, positioning pin hole, flange corner point and intersection of stamping rib; the additional reference body includes one or more of the following: detachable reference block, sprayed contrast pattern, etched mark or fixed reference part.

8. A thermal trajectory compensation device for welding on an automobile chassis, characterized in that, The device includes: The acquisition module is used to acquire the target welding area of ​​the workpiece to be welded; determine the non-heat-affected zone of the target welding area, select multiple cold zone visual reference features on the non-heat-affected zone, and acquire the first position parameter of each cold zone visual reference feature; wherein the number of cold zone visual reference features is not less than a preset number; and acquire the second position parameter of each cold zone visual reference feature during the welding process. The calculation module is used to obtain the topological distortion between the visual reference features of the cold area based on the first position parameter and the second position parameter of the visual reference feature of the cold area; The correction module is used to obtain a residual term by removing the overall rigid body displacement component of the workpiece to be welded if the topological distortion is greater than a preset change threshold; obtain the cold zone deformation characteristics caused by welding heat input based on the residual term; obtain the target trajectory point according to the cold zone deformation characteristics; and dynamically correct the preset welding trajectory of the industrial robot according to the target trajectory point to generate the corrected welding trajectory. The execution module is used to drive the industrial robot to perform welding operations on the workpiece to be welded along the corrected welding trajectory.

9. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 7.

Images