Lightweight aluminum alloy automobile hub friction stir welding feeding method based on visual perception

Abstract

The invention relates to a lightweight aluminum alloy automobile hub friction stir welding feeding method based on visual perception, and relates to the field of hub welding. The light-weight aluminum alloy automobile hub friction stir welding feeding method based on visual perception comprises the steps that image capturing is conducted on a to-be-welded aluminum alloy hub component located in a feeding buffer area, and an initial position image is formed; operation processing is conducted on the initial position image, the position of the aluminum alloy hub component to be welded is determined, and initial positioning information is output; grabbing the to-be-welded aluminum alloy hub part according to the initial positioning information, and outputting an initial grabbing path; the motion path is optimized; and the to-be-welded aluminum alloy hub part is controlled to be placed on a preset processing station according to the optimal grabbing path, and a safe placing signal is output. The feeding device can improve the welding and feeding precision of the light-weight aluminum alloy automobile hub by adjusting the motion path in the welding process, so that the production efficiency is improved, and the production cost is saved.

Description

Technical Field

[0001] The present invention belongs to the field of wheel hub welding, and in particular relates to a lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception. Background Art

[0002] As the automotive industry pursues energy conservation, emission reduction, and performance improvements, lightweight aluminum alloy wheels are becoming increasingly popular. Aluminum alloy wheels typically consist of multiple components that need to be welded together to form a single unit. However, welding processes typically used in aluminum alloy wheel production lines suffer from low automation and inefficient production. The numerous manual operations increase labor costs and lengthen production cycles, making them incapable of meeting the demands for efficient, large-scale production of lightweight aluminum alloy wheels.

[0003] Therefore, a lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception is designed, which can improve the welding feeding accuracy of lightweight aluminum alloy automobile wheel hub, improve production efficiency and save production costs. Summary of the Invention

[0004] Based on this, the present invention aims to overcome the shortcomings of the prior art and provides a visual perception-based method for friction stir welding of lightweight aluminum alloy automotive wheels. The method captures an image of the aluminum alloy wheel component to be welded, located in a loading buffer, to form an initial position image. This initial position image is then processed to determine the position of the aluminum alloy wheel component to be welded, outputting initial positioning information. Based on the initial positioning information, the component to be welded is grasped and an initial grasping path is output. The motion path is then optimized. Finally, the component to be welded is controlled to be placed at a preset processing station along the optimal grasping path, and a safe placement signal is output. This method improves the welding and loading accuracy of lightweight aluminum alloy automotive wheels, increases production efficiency, and reduces production costs.

[0005] The first technical solution provided by the present invention is:

[0006] A lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception, comprising:

[0007] Image recognition: capture the image of the aluminum alloy wheel hub component to be welded in the loading buffer area to form an initial position image;

[0008] Component positioning: perform calculations on the initial position image to determine the position of the aluminum alloy wheel hub component to be welded and output the initial positioning information;

[0009] Component grabbing: grab the aluminum alloy wheel hub component to be welded according to the initial positioning information and the initial grabbing path;

[0010] Path optimization: real-time acquisition of the relative position information between the robotic arm and the aluminum alloy wheel hub component to be welded, and dynamic adjustment of the robotic arm's motion trajectory based on the relative position information to form the optimal grasping path;

[0011] Component placement: controls the aluminum alloy wheel hub components to be welded to the preset processing station according to the optimal grasping path, and outputs a safe placement signal.

[0012] Furthermore, image recognition is performed to capture the image of the aluminum alloy wheel hub component to be welded located in the loading buffer area to form an initial position image, including:

[0013] Perform feature extraction on the captured image of the welded aluminum alloy wheel hub component to extract feature information of the aluminum alloy wheel hub component to be welded;

[0014] The feature information includes the contour shape feature parameter L1, the hole position feature parameter P1 and the edge texture feature parameter T1;

[0015] The extracted feature information is matched and compared with the preset standard model features to determine the shape of the welded aluminum alloy wheel hub component in the loading buffer area.

[0016] Furthermore, the extracted feature information is matched and compared with the preset standard model features to determine the shape of the welded aluminum alloy wheel hub component in the loading buffer area, including:

[0017] Obtain the standard contour shape feature parameter L0, the standard hole position feature parameter P0, and the standard edge texture feature parameter T0 corresponding to the preset standard model; calculate the similarity S between the welded aluminum alloy wheel hub component and the preset standard model, S = α × (L1 / L0) + β × (P1 / P0) + γ × (T1 / T0), where α, β, and γ are weight coefficients, and α + β + γ = 1;

[0018] Determine whether the similarity S is within a first preset threshold range; if the similarity S is within the first preset threshold range, determine that the feature information of the welded aluminum alloy wheel hub component is valid, output a recognition success signal, and the robotic arm prepares for grasping based on the feature information; if the similarity S is not within the first preset threshold range, output a recognition failure signal, and the robotic arm re-captures the image and re-extracts the features until the recognition is successful.

[0019] Furthermore, component positioning, performing computational processing on the initial position image, determining the position of the aluminum alloy wheel hub component to be welded, and outputting initial positioning information, includes:

[0020] Analyze the contour and characteristic points of the aluminum alloy wheel hub component to be welded, and obtain the center point coordinates (X1, Y1, Z1) and characteristic point coordinates (X2, Y2, Z2) of the contour of the aluminum alloy wheel hub component to be welded;

[0021] Obtain the coordinates (X3, Y3, Z3) of the current grasping point of the robotic arm; calculate the deviations ΔX, ΔY, and ΔZ between the current grasping point and the midpoint of the line connecting the center point and the characteristic point of the aluminum alloy wheel hub component to be welded, where ΔX = (X1 + X2) / 2 - X3, ΔY = (Y1 + Y2) / 2 - Y3, and ΔZ = (Z1 + Z2) / 2 - Z3;

[0022] Determine whether the deviation amounts ΔX, ΔY and ΔZ are within the second preset threshold range; if the deviation amounts ΔX, ΔY and ΔZ are within the second preset threshold range, output the initial positioning information and the positioning of the robotic arm is successful; if the deviation amounts ΔX, ΔY and ΔZ are not within the second preset threshold range, output the positioning adjustment signal and adjust the robotic arm to the position of (X3+ΔX, Y3+ΔY, Z3+ΔZ) to ensure that the positioning of the robotic arm is successful, and then output the initial positioning information.

[0023] Furthermore, component grabbing is performed on the aluminum alloy wheel hub component to be welded according to the initial positioning information and along the initial grabbing path, including:

[0024] Receive initial positioning information; plan the grasping execution path from the coordinates (X3, Y3, Z3) of the current grasping point of the robot arm to the coordinates (X1, Y1, Z1) of the center point of the contour of the aluminum alloy wheel hub component to be welded, and output the initial grasping path;

[0025] The initial grasping path is X(t)=X3+(X1-X3)×t 3 , Y(t)=Y3+(Y1-Y3)×t 3 , Z(t)=Z3+(Z1-Z3)×t 3 , where t is the time parameter.

[0026] Furthermore, path optimization is performed to obtain the relative position information between the robot arm and the aluminum alloy wheel hub component to be welded in real time, and dynamically adjust the motion trajectory of the robot arm based on the relative position information to form the optimal grasping path, including:

[0027] Real-time measurement of the relative distance D and relative angle θ between the robotic arm and the aluminum alloy wheel hub component to be welded; the relative distance D is the straight-line distance from the front end of the robotic arm to the nearest edge of the aluminum alloy wheel hub component to be welded, and the relative angle θ is the angle between the movement direction of the front end of the robotic arm and the center line of the aluminum alloy wheel hub component to be welded;

[0028] Compare the preset relative distance D0 and the preset relative angle θ0; calculate the distance deviation ΔD and the angle deviation Δθ based on the real-time measured relative distance D and relative angle θ, where ΔD = D - D0, Δθ = θ - θ0;

[0029] Determine whether the distance deviation ΔD and the angle deviation Δθ are within a third preset threshold range; if both the distance deviation ΔD and the angle deviation Δθ are within the third preset threshold range, output a trajectory holding signal and the robotic arm maintains the current motion trajectory; if both the distance deviation ΔD and the angle deviation Δθ are not within the third preset threshold range, output a trajectory adjustment signal.

[0030] Furthermore, path optimization is performed to obtain the relative position information between the robot arm and the aluminum alloy wheel hub component to be welded in real time, and dynamically adjust the motion trajectory of the robot arm based on the relative position information to form the optimal grasping path, including:

[0031] Receive trajectory adjustment signals; replan the motion trajectory of the robotic arm to form the optimal grasping path; the coordinate function of the optimal grasping path is X(t) = X3 + (X1-X3) × t 3 +k1×ΔD×t 2 Y(t)=Y3+(Y1-Y3)×t 3 +k2×Δθ×t 2 and Z(t)=Z3+(Z1-Z3)×t 3 +k3×Δθ×t 2 , where k1, k2 and k3 are trajectory adjustment coefficients, and t is the time parameter.

[0032] Furthermore, component placement controls the aluminum alloy wheel hub component to be welded to be placed at a preset processing station according to the optimal grasping path and outputs a safe placement signal, including:

[0033] Get the gripping force F of the robotic arm g , obtain the mass m and surface roughness μ of the aluminum alloy wheel hub component to be welded; calculate the theoretical gripping force F 理 , F 理 =k×m×g+f×μ, where k is the weight coefficient, f is the friction coefficient, and g is the acceleration due to gravity;

[0034] Calculate the gripping force F of the robotic arm g and theoretical gripping force F 理 The difference ΔF, ΔF=|F g -F 理 |;

[0035] Determine whether ΔF is within the fourth preset threshold range; if ΔF is within the fourth preset threshold range, output a grasping force stabilization signal to maintain the current grasping force of the robot arm; if ΔF is not within the fourth preset threshold range, output a grasping force adjustment signal to adjust the grasping tightness of the robot arm so that the grasping force F of the robot arm is g Adjust to the theoretical gripping force F 理 nearby.

[0036] Furthermore, component placement controls the aluminum alloy wheel hub component to be welded to be placed at a preset processing station according to the optimal grasping path and outputs a safe placement signal, including:

[0037] Receive the grasping force stabilization signal and complete the action of the robotic arm placing the aluminum alloy wheel hub component to be welded; after the robotic arm places the aluminum alloy wheel hub component to be welded on the preset processing station, compare the image of the placed welded aluminum alloy wheel hub component with the preset placement image and output a placement comparison signal.

[0038] Furthermore, component placement controls the aluminum alloy wheel hub component to be welded to be placed at a preset processing station according to the optimal grasping path and outputs a safe placement signal, including:

[0039] Receive a placement comparison signal; analyze the status of the welded aluminum alloy wheel hub component at a preset processing station to determine whether the placement comparison signal is within a fifth preset threshold range; if the placement comparison signal is within the fifth preset threshold range, output a safe placement signal to maintain the current placement state; if the placement comparison signal is not within the fifth preset threshold range, output a placement adjustment signal to adjust the position of the welded aluminum alloy wheel hub component.

[0040] The beneficial effects of the present invention are:

[0041] The system captures an image of the aluminum alloy wheel hub component to be welded, located in the loading buffer, to form an initial position image. This initial position image is then processed to determine the position of the component and output initial positioning information. Based on this initial positioning information, the component is grasped and an initial grasping path is output. The system also optimizes the motion path and controls the placement of the component to be welded at a preset processing station along the optimal grasping path, outputting a safe placement signal. By adjusting the motion path during the welding process, the system improves the welding and loading accuracy of lightweight aluminum alloy automotive wheels, thereby increasing production efficiency and saving production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a step diagram of a lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to an embodiment of the present invention.

[0043] Description of reference numerals:

[0044] S1, image recognition; S2, component positioning; S3, component grasping; S4, path optimization; S5, component placement. DETAILED DESCRIPTION

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0046] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0047] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0048] In the description of the embodiments of the present application, it should be understood that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or are the orientations or positional relationships in which the product of the application is conventionally placed when in use, or are the orientations or positional relationships conventionally understood by those skilled in the art. They are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0049] In the description of the embodiments of this application, it should also be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to direct connections, indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0050] It should be noted that, unless there is any conflict, the embodiments and features in the embodiments of this application can be combined with each other.

[0051] The technical solution in this application will be described below with reference to the accompanying drawings.

[0052] Please refer to Figure 1, an embodiment of the present application provides a lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception. The method is applied to the field of wheel hub welding. The method forms an initial position image by capturing an image of the aluminum alloy wheel hub component to be welded located in a feeding buffer area; performs computational processing on the initial position image to determine the position of the aluminum alloy wheel hub component to be welded, and outputs initial positioning information; grasps the aluminum alloy wheel hub component to be welded based on the initial positioning information, outputs an initial grasping path; and optimizes the motion path; controls the aluminum alloy wheel hub component to be welded to a preset processing station according to the optimal grasping path, and outputs a safe placement signal. It can improve the welding and feeding accuracy of lightweight aluminum alloy automobile wheels by adjusting the motion path of the welding process, thereby improving production efficiency and saving production costs.

[0053] It should be noted that, an image of the aluminum alloy wheel hub component to be welded located in the loading buffer area is captured, and feature extraction is performed on the captured image of the welded aluminum alloy wheel hub component to extract feature information of the aluminum alloy wheel hub component to be welded, including contour shape feature parameter L1, hole position feature parameter P1 and edge texture feature parameter T1; the extracted feature information is matched and compared with the preset standard model feature to determine the shape of the welded aluminum alloy wheel hub component in the loading buffer area to form an initial position image; the contour and feature points of the aluminum alloy wheel hub component to be welded are analyzed, Obtain the center point coordinates and feature point coordinates of the outline of the aluminum alloy wheel hub component to be welded; obtain the coordinates of the current grasping point of the robotic arm; calculate the deviation between the current grasping point and the midpoint of the line connecting the center point and feature point of the aluminum alloy wheel hub component to be welded, determine the position of the aluminum alloy wheel hub component to be welded, and output the initial positioning information; grasp the aluminum alloy wheel hub component to be welded based on the initial positioning information, and output the initial grasping path; optimize the movement path of the robotic arm through the trajectory adjustment signal; finally, control the aluminum alloy wheel hub component to be welded to be placed at the preset processing station according to the optimal grasping path, output a safe placement signal, and complete the grasping process.

[0054] This solution provides a lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception, including the following steps:

[0055] S1: Image recognition, capturing an image of the aluminum alloy wheel hub component to be welded located in the loading buffer area to form an initial position image.

[0056] It can be understood that this step mainly involves recognizing the shape of the aluminum alloy wheel hub component to be welded by the visual recognition system equipped on the robotic arm.

[0057] Step S1 includes: performing feature extraction on the captured image of the welded aluminum alloy wheel hub component to extract feature information of the aluminum alloy wheel hub component to be welded; the feature information is the contour shape feature parameter L1, the hole position feature parameter P1 and the edge texture feature parameter T1; matching and comparing the extracted feature information with the preset standard model features to determine the shape of the welded aluminum alloy wheel hub component in the loading buffer area.

[0058] Preferably, the standard contour shape characteristic parameter L0, the standard hole position characteristic parameter P0, and the standard edge texture characteristic parameter T0 corresponding to the preset standard model are obtained; and the similarity S between the welded aluminum alloy wheel hub component and the preset standard model is calculated, where S = α × (L1 / L0) + β × (P1 / P0) + γ × (T1 / T0), where α, β, and γ are weight coefficients, and α + β + γ = 1. It should be noted that α, β, and γ are coefficients obtained through multiple simulations using big data.

[0059] Determine whether the similarity S is within a first preset threshold range; if the similarity S is within the first preset threshold range, determine that the feature information of the welded aluminum alloy wheel hub component is valid, output a recognition success signal, and the robotic arm prepares for grasping based on the feature information; if the similarity S is not within the first preset threshold range, output a recognition failure signal, and the robotic arm re-captures the image and re-extracts the features until the recognition is successful.

[0060] It can be understood that by identifying the contour shape characteristic parameters L1, hole position characteristic parameters P1 and edge texture characteristic parameters T1 and matching and comparing them with the standard contour shape characteristic parameters L0, standard hole position characteristic parameters P0 and standard edge texture characteristic parameters T0 in the preset standard model, the image information of the aluminum alloy wheel hub component to be welded can be clearly identified.

[0061] S2: Component positioning: perform calculation processing on the initial position image to determine the position of the aluminum alloy wheel hub component to be welded and output the initial positioning information.

[0062] Step S2 includes: analyzing the contour and feature points of the aluminum alloy wheel hub component to be welded, obtaining the center point coordinates (X1, Y1, Z1) and feature point coordinates (X2, Y2, Z2) of the contour of the aluminum alloy wheel hub component to be welded; obtaining the coordinates (X3, Y3, Z3) of the current grasping point of the robotic arm; calculating the deviations ΔX, ΔY and ΔZ between the current grasping point and the midpoint of the line connecting the center point and feature point of the aluminum alloy wheel hub component to be welded, where ΔX = (X1+X2) / 2-X3, ΔY = (Y1+Y2) / 2-Y3, and ΔZ = (Z1+Z2) / 2-Z3.

[0063] It should be noted that it is determined whether the deviation amounts ΔX, ΔY and ΔZ are within the second preset threshold range; if the deviation amounts ΔX, ΔY and ΔZ are within the second preset threshold range, the initial positioning information is output and the positioning of the robotic arm is successful; if the deviation amounts ΔX, ΔY and ΔZ are not within the second preset threshold range, a positioning adjustment signal is output to adjust the robotic arm to the position of (X3+ΔX, Y3+ΔY, Z3+ΔZ) to ensure that the positioning of the robotic arm is successful, and then the initial positioning information is output.

[0064] S3: Component grabbing: grabbing the aluminum alloy wheel hub component to be welded according to the initial grabbing path based on the initial positioning information.

[0065] Step S3 includes: receiving initial positioning information; planning a grasping execution path from the coordinates (X3, Y3, Z3) of the current grasping point of the robotic arm to the center point coordinates (X1, Y1, Z1) of the contour of the aluminum alloy wheel hub component to be welded, and outputting the initial grasping path.

[0066] Optionally, the initial grasping path is X(t)=X3+(X1-X3)×t 3 , Y(t)=Y3+(Y1-Y3)×t 3 , Z(t)=Z3+(Z1-Z3)×t 3 , where t is the time parameter.

[0067] S4: Path optimization: Real-time acquisition of the relative position information between the robotic arm and the aluminum alloy wheel hub component to be welded. Dynamic adjustment of the robotic arm's motion trajectory based on the relative position information to form the optimal grasping path.

[0068] Step S4 includes: measuring in real time the relative distance D and relative angle θ between the robotic arm and the aluminum alloy wheel hub component to be welded; wherein the relative distance D is the straight-line distance from the front end of the robotic arm to the nearest edge point of the aluminum alloy wheel hub component to be welded, and the relative angle θ is the angle between the movement direction of the front end of the robotic arm and the center line of the aluminum alloy wheel hub component to be welded; comparing the preset relative distance D0 and the preset relative angle θ0; and calculating the distance deviation ΔD and the angle deviation Δθ based on the real-time measured relative distance D and relative angle θ, wherein ΔD=D-D0, Δθ=θ-θ0.

[0069] Determine whether the distance deviation ΔD and the angle deviation Δθ are within a third preset threshold range; if both the distance deviation ΔD and the angle deviation Δθ are within the third preset threshold range, output a trajectory holding signal and the robotic arm maintains the current motion trajectory; if both the distance deviation ΔD and the angle deviation Δθ are not within the third preset threshold range, output a trajectory adjustment signal.

[0070] It should be noted that this step also requires receiving a trajectory adjustment signal; replanning the motion trajectory of the robotic arm to form an optimal grasping path; the coordinate function of the optimal grasping path is X(t) = X3 + (X1-X3) × t 3 +k1×ΔD×t 2 Y(t)=Y3+(Y1-Y3)×t 3 +k2×Δθ×t 2 and Z(t)=Z3+(Z1-Z3)×t 3 +k3×Δθ×t 2 , where k1, k2, and k3 are trajectory adjustment coefficients, and t is the time parameter. k1, k2, and k3 are also coefficients obtained through multiple simulations of big data.

[0071] S5: Component placement: controls the aluminum alloy wheel hub components to be welded to be placed in the preset processing station according to the optimal grasping path, and outputs a safe placement signal.

[0072] It should be noted that step S5 includes: obtaining the gripping force F of the robotic arm g , obtain the mass m and surface roughness μ of the aluminum alloy wheel hub component to be welded; calculate the theoretical gripping force F 理 , F 理 =k×m×g+f×μ, where k is the weight coefficient, f is the friction coefficient, and g is the acceleration due to gravity; calculate the gripping force F of the robot arm g and theoretical gripping force F 理 The difference ΔF, ΔF=|F g -F 理 |.

[0073] Determine whether ΔF is within the fourth preset threshold range; if ΔF is within the fourth preset threshold range, output a grasping force stabilization signal to maintain the current grasping force of the robot arm; if ΔF is not within the fourth preset threshold range, output a grasping force adjustment signal to adjust the grasping tightness of the robot arm so that the grasping force F of the robot arm is g Adjust to the theoretical gripping force F 理 nearby.

[0074] Optionally, a grasping force stabilization signal is received, and the action of the robotic arm placing the aluminum alloy wheel hub component to be welded is completed; after the robotic arm places the aluminum alloy wheel hub component to be welded on a preset processing station, the image of the placed welded aluminum alloy wheel hub component is compared with the preset placement image, and a placement comparison signal is output.

[0075] It can be understood that this step also requires receiving a placement comparison signal; analyzing the status of the welded aluminum alloy wheel hub component in the preset processing station, and determining whether the placement comparison signal is within the fifth preset threshold range; if the placement comparison signal is within the fifth preset threshold range, outputting a safe placement signal to maintain the current placement state; if the placement comparison signal is not within the fifth preset threshold range, outputting a placement adjustment signal to adjust the position of the welded aluminum alloy wheel hub component.

[0076] The following describes the principles of the visual perception-based lightweight aluminum alloy automobile wheel friction stir welding feeding method provided in this embodiment:

[0077] The image of the aluminum alloy wheel hub component to be welded located in the loading buffer area is captured, and features are extracted from the captured image of the welded aluminum alloy wheel hub component to extract feature information of the aluminum alloy wheel hub component to be welded, including contour shape feature parameter L1, hole position feature parameter P1 and edge texture feature parameter T1; the extracted feature information is matched and compared with the preset standard model features to determine the shape of the welded aluminum alloy wheel hub component in the loading buffer area and form an initial position image; the contour and feature points of the aluminum alloy wheel hub component to be welded are analyzed to obtain the contour and feature points of the aluminum alloy wheel hub component to be welded The center point coordinates and feature point coordinates of the contour of the welded aluminum alloy wheel hub component; obtain the coordinates of the current grasping point of the robotic arm; calculate the deviation between the current grasping point and the midpoint of the line connecting the center point and feature point of the aluminum alloy wheel hub component to be welded, determine the position of the aluminum alloy wheel hub component to be welded, and output the initial positioning information; grasp the aluminum alloy wheel hub component to be welded based on the initial positioning information, and output the initial grasping path; optimize the movement path of the robotic arm through the trajectory adjustment signal; finally, control the aluminum alloy wheel hub component to be welded to be placed at the preset processing station according to the optimal grasping path, output the safe placement signal, and complete the grasping process.

[0078] In summary, the embodiments provided by the present invention have the following main effective effects:

[0079] The system captures an image of the aluminum alloy wheel hub component to be welded, located in the loading buffer, to form an initial position image. This initial position image is then processed to determine the position of the component and output initial positioning information. Based on this initial positioning information, the component is grasped and an initial grasping path is output. The system also optimizes the motion path and controls the placement of the component to be welded at a preset processing station along the optimal grasping path, outputting a safe placement signal. By adjusting the motion path during the welding process, the system improves the welding and loading accuracy of lightweight aluminum alloy automotive wheels, thereby increasing production efficiency and saving production costs.

[0080] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] The above embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception, characterized in that: include: Image recognition: capture the image of the aluminum alloy wheel hub component to be welded in the loading buffer area to form an initial position image; Component positioning: performing calculation processing on the initial position image to determine the position of the aluminum alloy wheel hub component to be welded, and outputting initial positioning information; Component grabbing, grabbing the aluminum alloy wheel hub component to be welded according to the initial grabbing path based on the initial positioning information; Path optimization: obtaining the relative position information between the robotic arm and the aluminum alloy wheel hub component to be welded in real time, and dynamically adjusting the motion trajectory of the robotic arm according to the relative position information to form an optimal grasping path; Component placement: controls the aluminum alloy wheel hub component to be welded to be placed at a preset processing station according to the optimal grasping path, and outputs a safe placement signal.

2. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 1 is characterized in that: The image recognition captures the image of the aluminum alloy wheel hub component to be welded located in the loading buffer area to form an initial position image, including: Performing feature extraction on the captured image of the welded aluminum alloy wheel hub component to extract feature information of the aluminum alloy wheel hub component to be welded; The characteristic information includes the contour shape characteristic parameter L1, the hole position characteristic parameter P1 and the edge texture characteristic parameter T1; The extracted feature information is matched and compared with the preset standard model features to determine the shape of the welded aluminum alloy wheel hub component in the loading buffer area.

3. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 2 is characterized in that: The step of matching and comparing the extracted feature information with preset standard model features to determine the shape of the welded aluminum alloy wheel hub component in the loading buffer area includes: Obtaining a standard contour shape feature parameter L0, a standard hole position feature parameter P0, and a standard edge texture feature parameter T0 corresponding to a preset standard model; calculating a similarity S between the welded aluminum alloy wheel hub component and the preset standard model, where S = α × (L1 / L0) + β × (P1 / P0) + γ × (T1 / T0), where α, β, and γ are weight coefficients, and α + β + γ = 1; Determine whether the similarity S is within a first preset threshold range; if the similarity S is within the first preset threshold range, determine that the feature information of the welded aluminum alloy wheel hub component is valid, output a recognition success signal, and the robotic arm prepares for grasping according to the feature information; if the similarity S is not within the first preset threshold range, output a recognition failure signal, and the robotic arm re-captures the image and re-extracts the feature until the recognition is successful.

4. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 1 is characterized in that: The component positioning, performing calculation processing on the initial position image, determining the position of the aluminum alloy wheel hub component to be welded, and outputting initial positioning information, includes: Analyze the contour and characteristic points of the aluminum alloy wheel hub component to be welded, and obtain the center point coordinates (X1, Y1, Z1) and characteristic point coordinates (X2, Y2, Z2) of the contour of the aluminum alloy wheel hub component to be welded; Obtain the coordinates (X3, Y3, Z3) of the current grasping point of the robotic arm; calculate the deviations ΔX, ΔY, and ΔZ between the current grasping point and the midpoint of the line connecting the center point and the characteristic point of the aluminum alloy wheel hub component to be welded, where ΔX = (X1 + X2) / 2 - X3, ΔY = (Y1 + Y2) / 2 - Y3, and ΔZ = (Z1 + Z2) / 2 - Z3; Determine whether the deviation amounts ΔX, ΔY and ΔZ are within a second preset threshold range; if the deviation amounts ΔX, ΔY and ΔZ are within the second preset threshold range, output the initial positioning information and the positioning of the robotic arm is successful; if the deviation amounts ΔX, ΔY and ΔZ are not within the second preset threshold range, output a positioning adjustment signal to adjust the robotic arm to move to the position of (X3+ΔX, Y3+ΔY, Z3+ΔZ) to ensure that the positioning of the robotic arm is successful, and then output the initial positioning information.

5. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 4 is characterized in that: The component grabbing is to grab the aluminum alloy wheel hub component to be welded according to the initial grabbing path based on the initial positioning information, including: Receive the initial positioning information; plan a grasping execution path from the coordinates (X3, Y3, Z3) of the current grasping point of the robotic arm to the coordinates (X1, Y1, Z1) of the center point of the contour of the aluminum alloy hub component to be welded, and output the initial grasping path; The initial grasping path is X(t)=X3+(X1-X3)×t 3 , Y(t)=Y3+(Y1-Y3)×t 3 , Z(t)=Z3+(Z1-Z3)×t 3 , where t is the time parameter.

6. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 5 is characterized in that: The path optimization acquires the relative position information between the robotic arm and the aluminum alloy wheel hub component to be welded in real time, and dynamically adjusts the motion trajectory of the robotic arm according to the relative position information to form an optimal grasping path, including: Measure the relative distance D and relative angle θ between the robotic arm and the aluminum alloy wheel hub component to be welded in real time; wherein the relative distance D is the straight-line distance from the front end of the robotic arm to the nearest edge point of the aluminum alloy wheel hub component to be welded, and the relative angle θ is the angle between the movement direction of the front end of the robotic arm and the center line of the aluminum alloy wheel hub component to be welded; Comparing a preset relative distance D0 and a preset relative angle θ0; calculating a distance deviation ΔD and an angle deviation Δθ based on the relative distance D and the relative angle θ measured in real time, wherein ΔD=D-D0, Δθ=θ-θ0; Determine whether the distance deviation ΔD and the angle deviation Δθ are within a third preset threshold range; if both the distance deviation ΔD and the angle deviation Δθ are within the third preset threshold range, output a trajectory keeping signal so that the robotic arm maintains the current motion trajectory; if neither the distance deviation ΔD nor the angle deviation Δθ is within the third preset threshold range, output a trajectory adjustment signal.

7. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 6 is characterized in that: The path optimization acquires the relative position information between the robotic arm and the aluminum alloy wheel hub component to be welded in real time, and dynamically adjusts the motion trajectory of the robotic arm according to the relative position information to form an optimal grasping path, including: Receive the trajectory adjustment signal; re-plan the motion trajectory of the robot arm to form the optimal grasping path; the coordinate function of the optimal grasping path is X(t)=X3+(X1-X3)×t 3 +k1×ΔD×t 2 Y(t)=Y3+(Y1-Y3)×t 3 +k2×Δθ×t 2 and Z(t)=Z3+(Z1-Z3)×t 3 +k3×Δθ×t 2 , where k1, k2 and k3 are trajectory adjustment coefficients, and t is the time parameter.

8. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 1 is characterized in that: The component placement controls the aluminum alloy wheel hub component to be welded to be placed at a preset processing station according to the optimal grasping path and outputs a safe placement signal, including: Get the gripping force F of the robotic arm g , obtain the mass m and surface roughness μ of the aluminum alloy wheel hub component to be welded; calculate the theoretical gripping force F 理 , F 理 =k×m×g+f×μ, where k is the weight coefficient, f is the friction coefficient, and g is the acceleration due to gravity; Calculate the gripping force F of the robotic arm g With the theoretical gripping force F 理 The difference ΔF, ΔF=|F g -F 理 |; Determine whether ΔF is within a fourth preset threshold range; if ΔF is within the fourth preset threshold range, output a grasping force stabilization signal to maintain the current grasping force of the robotic arm; if ΔF is not within the fourth preset threshold range, output a grasping force adjustment signal to adjust the grasping tightness of the robotic arm so that the grasping force F of the robotic arm is g Adjust to the theoretical gripping force F 理 nearby.

9. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 8, characterized in that: The component placement controls the aluminum alloy wheel hub component to be welded to be placed at a preset processing station according to the optimal grasping path and outputs a safe placement signal, including: The grasping force stabilization signal is received, and the action of the robotic arm placing the aluminum alloy wheel hub component to be welded is completed; after the robotic arm places the aluminum alloy wheel hub component to be welded at a preset processing station, the image of the placed welded aluminum alloy wheel hub component is compared with the preset placement image, and a placement comparison signal is output.

10. The lightweight aluminum alloy automobile wheel hub friction stir welding feeding method based on visual perception according to claim 9, characterized in that: The component placement controls the aluminum alloy wheel hub component to be welded to be placed at a preset processing station according to the optimal grasping path and outputs a safe placement signal, including: Receive the placement comparison signal; analyze the status of the welded aluminum alloy wheel hub component at the preset processing station, and determine whether the placement comparison signal is within a fifth preset threshold range; if the placement comparison signal is within the fifth preset threshold range, output a safe placement signal to maintain the current placement state; if the placement comparison signal is not within the fifth preset threshold range, output a placement adjustment signal to adjust the position of the welded aluminum alloy wheel hub component.

Images