Bicycle part girth welding method, system and device

Abstract

The invention relates to the technical field of girth welding, in particular to a girth welding method, system and device for bicycle parts. The method comprises the following steps: acquiring a thermal imaging image of a bicycle part in a welding process, and carrying out graying processing to obtain a grayscale image; according to the gray level distribution characteristics of the gray level image, a welding pool area, a heat influence area and a splashing hot spot are determined; radiating outwards from the central point of the welding pool area, and determining a gradient characteristic sequence of temperature change of the heat affected area in different edge pixel point directions; determining the deviation degree of the pipe diameter of the workpiece according to the length difference and the gray scale distribution of the gradient feature sequence; analyzing gray level change characteristics of welding pool areas in the gray level images of the current frame and the previous frame, and evaluating a stability index in combination with the area and distribution characteristics of splashing hot spots of the current frame; and according to the stability index and the workpiece pipe diameter deviation degree, parameters of the current welding process are adjusted in real time. Real-time regulation and control of the welding process can be effectively achieved, and the welding stability is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of circumferential seam welding, and particularly relates to a method, a system and a device for circumferential seam welding of bicycle parts. Background Art

[0002] With the improvement of the requirements for the aesthetics and mechanical strength of bicycles, the requirements for the welding quality of bicycle parts during welding processing are getting higher and higher. In order to ensure the welding quality, it is necessary to adjust the welding parameters in real time according to the data change characteristics of the circumferential seam area of the parts during the welding process, so as to improve the welding quality of bicycle parts.

[0003] In the related art, some automatic welding systems integrate a process parameter library, and automatically retrieve the preset parameters of PID control according to the input material type and thickness. However, most current welding equipment does not have the ability to sense the real-time state of parts such as the temperature during the welding process, the state of the molten pool, and the deformation trend. Once the process parameters are set, they are fixed values, and it is impossible to dynamically adjust automatically with material changes or welding fluctuations, lacking the ability of automatic adjustment during the welding process, resulting in uneven welding heat, which affects the stability of the overall welding control. Summary of the Invention

[0004] In order to solve the technical problem that in the related art, through fixed values, it is impossible to dynamically adjust automatically with material changes or welding fluctuations, resulting in uneven welding heat, which affects the stability of the overall welding control, the present invention provides a method, a system and a device for circumferential seam welding of bicycle parts, and the specific technical solutions adopted are as follows: The present invention proposes a method for circumferential seam welding of bicycle parts, and the method includes: Obtain the thermal imaging image of the bicycle part during the welding process, and perform grayscale processing to obtain a grayscale image; Determine the welding molten pool area, the heat affected area and the spatter hot spots according to the grayscale distribution characteristics of different areas in the grayscale image; Radiate from the center point of the welding molten pool area to the outside, and determine the gradient feature sequence of the temperature change in the direction of different edge pixels in the heat affected area; determine the workpiece pipe diameter deviation degree of the current welding area according to the length difference and grayscale distribution of the gradient feature sequence; Analyze the grayscale change characteristics of the welding molten pool area in the current frame and the previous frame of grayscale images, and combine the area and distribution characteristics of the spatter hot spots in the current frame to evaluate the stability index of the current welding process; Adjust the parameters of the current welding process in real time according to the stability index and the workpiece pipe diameter deviation degree.

[0005] Further, the determining the welding molten pool area, the heat affected area and the spatter hot spots according to the grayscale characteristics of different areas in the grayscale image includes: Perform gray clustering on the pixel points within the welding influence area based on the density clustering algorithm to determine different clustering regions, calculate the average gray value of the pixel points in each clustering region, and use it as the gray index for the corresponding clustering region; Combine the clustering regions with gray indexes greater than the preset first index threshold as the welding molten pool region; In the other clustering regions except the welding molten pool region, calculate the average of the gray index differences between each clustering region and all other adjacent clustering regions. The clustering region with the average gray index difference greater than the preset difference threshold and a larger gray index value compared to all other adjacent clustering regions is used as the spatter hot spot; Use the region except the welding molten pool region and the spatter hot spot as the heat affected region.

[0006] Furthermore, radiating outward from the center point of the welding molten pool region to determine the gradient feature sequence of the temperature change in different edge pixel point directions of the heat affected region, including: Use the morphological center point of the welding molten pool region as the radiation point and make ray connections to different edge pixel points of the heat affected region; Take the difference between the gray value of each pixel point on the ray and the gray value of the corresponding previous pixel point as the gray gradient of the pixel point, and sort them in the order from near to far from the radiation point to obtain the gradient feature sequence of the temperature change in the corresponding edge pixel point direction.

[0007] Furthermore, determine the workpiece pipe diameter deviation degree of the current welding region according to the length difference and gray distribution of the gradient feature sequence, including: Take the range of the number of elements included in different gradient feature sequences as the first deviation analysis index; Calculate the standard deviation of all elements in each gradient feature sequence as the sequence fluctuation index; Take the standard deviation of all sequence fluctuation indexes as the second deviation analysis index; Normalize the product value of the first deviation analysis index and the second deviation analysis index as the workpiece pipe diameter deviation degree.

[0008] Furthermore, analyze the gray change characteristics of the welding molten pool region in the current frame and the previous frame of gray images, and combine the area and distribution characteristics of the spatter hot spot in the current frame to evaluate the stability index of the current welding process, including: Pass through the morphological center point of the welding molten pool region and draw a perpendicular line along the welding direction to divide the welding molten pool region into two influence regions; Determine the gray change characteristic index of the welding molten pool region according to the gray change of the pixel points in different influence regions in the welding direction; Calculate the absolute value of the difference between the grayscale change characteristic index of the current frame and that of the previous frame, and normalize the negative value of the absolute value of the difference as the first welding stability coefficient of the current frame; Determine the second welding stability coefficient according to the area of the splash hot spot and the density distribution of the splash hot spot itself; Normalize the sum of the first welding stability coefficient and the second welding stability coefficient as the stability index of the current welding process.

[0009] Furthermore, the determining of the grayscale change characteristic index of the welding molten pool region according to the grayscale change of pixel points in the welding direction in different influence regions includes: Calculate the absolute value of the difference between the grayscale values of each pixel point and the next pixel point in the welding direction to obtain the grayscale change value of the corresponding pixel point; Take the average value of the grayscale change values of all pixel points in each influence region as the regional change value; Take the absolute value of the difference between the regional change values of the two influence regions as the grayscale change characteristic index of the welding molten pool region.

[0010] Furthermore, the determining of the second welding stability coefficient according to the area of the splash hot spot and the density distribution of the splash hot spot itself includes: Within a preset range centered on the morphological center point of the welding molten pool region, determine the number of splash hot spots included as the density analysis index; Normalize the negative value of the product of the total area of all the splash hot spots and the density analysis index as the second welding stability coefficient.

[0011] Furthermore, the real-time adjustment of the parameters of the current welding process according to the stability index and the workpiece pipe diameter deviation includes: Calculate the ratio of the workpiece pipe diameter deviation to the stability index, and linearly map it to the range between (0, 2) as the adjustment index at the current moment; Adjust the proportional gain of the PID controller according to the adjustment index to perform PID control on the welding process.

[0012] On the other hand, a circumferential seam welding system for bicycle parts is also provided, and the system includes: An acquisition module for acquiring the thermal imaging image of the bicycle parts during the welding process and performing grayscale processing to obtain a grayscale image; A partitioning module for determining the welding molten pool region, the heat affected region, and the splash hot spots according to the grayscale distribution characteristics of different regions in the grayscale image; The deviation analysis module is used to radiate from the center point of the welding molten pool area to the outside to determine the gradient feature sequence of the temperature change in the direction of different edge pixel points in the heat affected area; according to the length difference and gray distribution of the gradient feature sequence, the workpiece pipe diameter deviation degree of the current welding area is determined; The stability analysis module is used to analyze the gray change characteristics of the welding molten pool area in the gray image of the current frame and the previous frame, and combine the area and distribution characteristics of the splash hot spots in the current frame to evaluate the stability index of the current welding process; The control module is used to adjust the parameters of the current welding process in real time according to the stability index and the workpiece pipe diameter deviation degree.

[0013] On the other hand, a circumferential seam welding device for bicycle parts is also provided. The device includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method described in any one of the foregoing are realized.

[0014] The present invention has the following beneficial effects: In the embodiment of the present invention, by acquiring the thermal imaging image of the bicycle parts during the welding process, performing graying processing to obtain a gray image, and dividing the welding molten pool area, the heat affected area, and the splash hot spots according to the image features in the gray image. Since welding analysis needs to consider the overall welding effect, through the division of different areas, different areas can be analyzed separately, thereby improving the reliability of the overall welding analysis; according to the heat diffusion effect in different directions of the heat affected area, the workpiece pipe diameter deviation degree of the welding area is analyzed, and the workpiece pipe diameter deviation degree can effectively characterize the heat diffusion deviation effect of the heat affected area presented by the pipe diameter characteristics during the welding process; then, combining the gray change characteristics of the welding molten pool area, the area and distribution characteristics of the splash hot spots, the stability index of the current welding process is determined. The stability index can combine the characteristics of the welding molten pool area and the splash hot spots respectively to perform the stability analysis of the welding process; after that, according to the stability index and the workpiece pipe diameter deviation degree, the parameters of the current welding process are adjusted in real time. The present invention can independently analyze different welding areas, and thus combine the characteristics of all welding areas to realize the control analysis at the current moment, reduce the situation of uneven welding heat, and improve the stability of the overall welding control. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 A flowchart of a circumferential seam welding method for bicycle parts provided by an embodiment of the present invention; Figure 2 A schematic diagram of a grayscale image provided by an embodiment of the present invention. Detailed implementation manners

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following combines the accompanying drawings and preferred embodiments to detail the specific implementation manners, structures, features and effects of a circumferential seam welding method, system and device for bicycle parts proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] It should be noted that for the convenience of calculation, all the index data involved in the operations in the embodiments of the present invention have undergone data preprocessing, thereby eliminating the influence of dimension. The specific means for eliminating dimension influence are well-known technical means to those skilled in the art and will not be limited herein.

[0020] The following specifically describes the specific solution of a circumferential seam welding method for bicycle parts provided by the present invention with reference to the accompanying drawings.

[0021] Please refer to Figure 1 , which shows a flowchart of a circumferential seam welding method for bicycle parts provided by an embodiment of the present invention. The method includes: S101: Obtain the thermal imaging image of the bicycle parts during the welding process, and perform grayscale processing to obtain a grayscale image.

[0022] In the embodiments of the present invention, a far-infrared thermal imager can be used as an infrared thermal imaging sensor, and the infrared thermal imaging sensor is installed above or above the side of the welding torch, looking down on the welding area; among them, the infrared thermal imaging sensor is equipped with an air curtain (nitrogen / compressed air, air pressure 0.5 MPa) and a sapphire protection window (temperature resistance > 1500 °C) to prevent soot attachment, and the sampling frequency is set to 30 Hz; during the installation process, it is necessary to pay attention to the safe distance between the infrared thermal imaging sensor and the vision sensor and the welding trajectory to avoid collision.

[0023] In a specific welding scenario, bicycle parts (such as bottom bracket shells, rear fork connecting pipes, etc.) are fixed on a rotating fixture. After clamping, the control system records the welding path parameters, and the welding torch robotic arm enters the position to be welded. Parameters such as the material and thickness of the bicycle parts are input into the welding control system of the welding machine. The welding control system extracts the corresponding process recommended values from the built-in welding process database to obtain the initial welding parameters. The automatic rotation module is started, and the workpiece rotates uniformly at a set speed. The temperature distribution of the current bicycle part during circumferential welding is collected by an infrared thermal imaging sensor to generate a thermal imaging image. After obtaining the original thermal imaging image in the embodiment of the present invention, image preprocessing can also be performed. The Otsu threshold method is used to perform binary segmentation on the thermal image to obtain a binary segmentation map, and the area with heat characteristics is extracted to obtain the thermal imaging image of the bicycle part in the embodiment of the present invention, that is, the thermal imaging image only contains the area affected by the welding temperature, eliminating the background. Then, a filtering algorithm is used to perform noise reduction processing on the thermal image. Among them, non-local means filtering is selected to perform noise reduction processing on the thermal image.

[0024] It should be noted that in the embodiment of the present invention, in order to facilitate image analysis, the thermal imaging image also needs to be grayscale processed to obtain a grayscale image. The grayscale processing can specifically be mean grayscale processing.

[0025] Among them, the grayscale image contains the temperature distribution information of the target surface. The higher the grayscale value of the pixel point, the higher the temperature of the corresponding target object. See Figure 2 , Figure 2 which is a schematic diagram of the grayscale image provided by an embodiment of the present invention.

[0026] S102: Determine the welding molten pool area, heat affected area, and spatter hot spots according to the grayscale distribution characteristics of different areas in the grayscale image.

[0027] During the welding process, the welding molten pool area, heat affected area, and spatter hot spots can be distinguished according to temperature and morphological differences. Among them, the welding molten pool area is the core high-temperature area currently aligned by the welding torch and is the area with the highest temperature; the heat affected area shows a gradient distribution with the temperature gradually decreasing around the welding molten pool area and has a relatively large area; the spatter hot spots fly out from the welding molten pool area and have a relatively high temperature. The area division can be realized by combining the characteristics of different areas.

[0028] Further, in some embodiments of the present invention, according to the gray-scale characteristics of different regions in the gray-scale image, the welding molten pool region, the heat-affected region, and the spatter hot spots are determined, including: performing gray-scale clustering processing on the pixel points in the welding-affected region based on the density clustering algorithm to determine different clustering regions, calculating the mean value of the gray-scale values of the pixel points in each clustering region as the gray-scale index corresponding to the clustering region; combining the clustering regions with gray-scale indexes greater than the preset first index threshold as the welding molten pool region; in the other clustering regions except the welding molten pool region, calculating the mean value of the differences in gray-scale indexes between each clustering region and all other adjacent clustering regions, and taking the clustering region with the mean value of the gray-scale index differences greater than the preset difference threshold and a larger gray-scale index value compared with all other adjacent clustering regions as the spatter hot spot; and taking the region except the welding molten pool region and the spatter hot spot as the heat-affected region.

[0029] Among them, the density clustering algorithm in the embodiments of the present invention may specifically be the k-means clustering algorithm, and the value of k is obtained by the elbow method. Of course, other unsupervised density clustering algorithms may also be used to form a clustering region with similar and adjacent gray-scale values of pixel points.

[0030] First, based on the characteristics that the welding molten pool region has the highest temperature and the largest gray-scale value, the analysis of the welding molten pool region is carried out, that is, combining the clustering regions with gray-scale indexes greater than the preset first index threshold as the welding molten pool region. The preset first index threshold may specifically be, for example, 200, that is, the region with a gray-scale value above 200 is used as the welding molten pool region. Then, the heat-affected region and the spatter hot spots are specifically divided.

[0031] Among them, the spatter hot spot is caused by the spattering of the molten material in the welding molten pool region. Except for the direct characteristics of the molten pool region, the spatter hot spot is one of the typical welding defect signs during the welding process. Especially in circumferential welding, the amount and distribution of spatter directly reflect the welding stability, the rationality of heat input, and the stability control of the molten pool. When the welding parameters are too large, the metal gasification is more intense, the stable characteristics of the molten pool are worse, and a large number of high-temperature particles, that is, spatter hot spots, are easily formed.

[0032] Therefore, its temperature is higher than that of the heat-affected area. Since the heat-affected area is affected by temperature and distance, its gray-scale change is relatively linear. Therefore, calculate the average value of the gray-scale index differences between each clustering area and all other adjacent clustering areas, and use the clustering area with the average value of the gray-scale index differences greater than the preset difference threshold and a larger gray-scale index value compared to all other adjacent clustering areas as the spatter hot spot. The preset difference threshold represents the gray-scale difference value between the spatter hot spot and the heat-affected area. Optionally, the preset difference threshold can be specifically, for example, 100. That is, when there is a sudden change in heat and there is an obvious high gray-scale feature compared to other surrounding clustering areas, it can be regarded as a spatter hot spot, and the area other than the welding molten pool area and the spatter hot spot is used as the heat-affected area.

[0033] S103: Radiate from the center point of the welding molten pool area to the outside to determine the gradient feature sequence of the temperature change in different edge pixel point directions of the heat-affected area; determine the pipe diameter deviation degree of the workpiece in the current welding area according to the length difference and gray-scale distribution of the gradient feature sequence.

[0034] To ensure the beauty of the weld and maintain the overall load-bearing strength of the bicycle, there are a large number of hollow parts with non-uniform pipe diameters in the bicycle structure. During the circumferential welding of these special-shaped or different-diameter hollow pipe fittings, due to the different wall thicknesses, pipe diameters, and the structure of the area adjacent to the weld at each position, the heat conduction rate during the welding process is different, and heat accumulation is likely to occur at some positions, causing the temperature of the welding molten pool to rise abnormally, thus affecting the welding fusion quality and the consistency of the weld formation.

[0035] Therefore, during the welding process, it is necessary to evaluate the heat conduction situation at the current welding position in real time. In the welding area with uniform pipe diameter and wall thickness, the heat diffusion rate in the heat-affected area after welding heat input is balanced, and on the thermal imaging image, it is manifested as a relatively gentle temperature gradient change along the same pixel distance in the heat-affected area, and the temperature decreases uniformly from the center of the molten pool to the surrounding. When there are sudden changes in pipe diameter, uneven wall thickness, or changes in the joint structure in the welding area, the heat diffusion path changes, resulting in a sudden change in the temperature gradient of the local heat-affected area. To analyze this sudden change in temperature gradient, it is necessary to determine the gradient feature sequence.

[0036] Further, in some embodiments of the present invention, radiating from the center point of the welding molten pool area to the outside to determine the gradient feature sequence of the temperature change in different edge pixel point directions of the heat-affected area includes: using the morphological center point of the welding molten pool area as the radiation point and making ray connections to different edge pixel points of the heat-affected area; taking the difference between the gray-scale value of each pixel point on the ray and the gray-scale value of the corresponding previous pixel point as the gray-scale gradient of the pixel point, and sorting them in the order from near to far from the radiation point to obtain the gradient feature sequence of the temperature change in the corresponding edge pixel point direction.

[0037] Taking the morphological center point as the starting point, ray connections are made in the directions of different edge pixel points to obtain corresponding rays, and the difference in grayscale values between the pixel points passed through by the rays and the corresponding previous pixel points is sorted starting from the ray starting point to obtain a gradient feature sequence.

[0038] It should be noted that the grayscale gradient at the radiation point position is its own grayscale value. Thus, a gradient feature sequence for the gradient change in the corresponding direction is determined.

[0039] Further, in some embodiments of the present invention, according to the length difference and grayscale distribution of the gradient feature sequences, the pipe diameter deviation degree of the workpiece in the current welding area is determined, including: taking the range of the number of elements included in different gradient feature sequences as the first deviation analysis index; calculating the standard deviation of all elements in each gradient feature sequence as the sequence fluctuation index; taking the standard deviation of all sequence fluctuation indexes as the second deviation analysis index; and normalizing the product value of the first deviation analysis index and the second deviation analysis index as the pipe diameter deviation degree of the workpiece.

[0040] Among them, the larger the first deviation analysis index, the larger the range of the number of elements, the greater the difference in the lengths of different gradient feature sequences, that is, the greater the difference in the diffusion effects generated during the welding process in different directions, and the more uneven the heating.

[0041] Among them, first calculate the standard deviation of all elements in each gradient feature sequence, and then calculate the standard deviation of the standard deviations of all gradient feature sequences, so as to perform fluctuation analysis on all gradient feature sequences. The larger the value of the second deviation analysis index, the greater the difference in the heat diffusion effects in all directions, and the more uneven the heating.

[0042] Combining the above characteristic analysis, the product value of the first deviation analysis index and the second deviation analysis index is normalized as the pipe diameter deviation degree of the workpiece. The larger its value, the more likely it is that the current welding area has uneven heat reception during the circumferential seam welding due to the pipe diameter of the bicycle parts, and the greater the degree of adjustment required for the welding parameters.

[0043] S104: Analyze the grayscale change characteristics of the welding molten pool area in the current frame and the previous frame of grayscale images, and combine the area and distribution characteristics of the splash hot spots in the current frame to evaluate the stability index of the current welding process.

[0044] After obtaining the welding abnormality caused by the abnormal pipe diameter of bicycle parts, it is necessary to further evaluate the welding quality of the current welding parameters under the influence of the current pipe diameter, and it is also necessary to analyze the state of the welding molten pool. The welding molten pool is a key position during the welding process of bicycle parts and is the part with the highest temperature in the welding area on the workpiece surface. Through the gray-scale changes in the welding molten pool area in different frames, the overall heat stability analysis of the welding is realized.

[0045] Influenced by the application location and structural design, in addition to the pipe diameter differences, there may also be certain differences in the local wall thickness of bicycle parts. This non-uniformity of the geometric structure directly affects the local heat conduction performance during the welding process, causing changes in the heat diffusion rate at different positions, and further affecting the thermal distribution state of the welding molten pool, resulting in local heat accumulation. In infrared thermal imaging, this difference in heat conduction performance is usually manifested as uneven temperature gradients at the boundary of the molten pool area, specifically as a narrower heat diffusion range or a faster temperature decay rate in certain directions, leading to an asymmetric and irregular thermal distribution characteristic of the molten pool.

[0046] In addition to the direct characteristics of the molten pool area, the spatter hot spot is one of the typical signs of welding defects during the welding process. Especially in circumferential seam welding, the amount and distribution of spatter directly reflect the welding stability, the rationality of heat input, and the stability control of the molten pool. When the welding parameters are too large, the metal vaporizes more violently, and the stable characteristics of the molten pool are worse, easily forming a large number of high-temperature particles. The initial molten pool stability index mainly considers the influence of the molten pool stability on the welding parameters from the perspective of heat loss, and it is also necessary to further adjust the stable characteristics of the molten pool from the perspective of excessive heat. In the thermal imaging image, the number of spatter hot spots can directly reflect the intensity of heat input during the welding process. The more the number and the larger the area of the spatter hot spots, the more metal melts and splashes into the molten pool during the welding process, and the more unstable the welding process is.

[0047] Therefore, in the embodiments of the present invention, by analyzing the gray-scale change characteristics of the welding molten pool area in the gray-scale images of the current frame and the previous frame, and combining the area and distribution characteristics of the spatter hot spots in the current frame, the stability index of the current welding process is evaluated, including: passing through the morphological center point of the welding molten pool area, making a perpendicular line along the welding direction, and dividing the welding molten pool area into two influencing areas; determining the gray-scale change characteristic index of the welding molten pool area according to the gray-scale changes of the pixel points in different influencing areas in the welding direction; calculating the absolute value of the difference between the gray-scale change characteristic indexes of the current frame and the previous frame, and normalizing the opposite number of the absolute value of the difference as the first welding stability coefficient of the current frame; determining the second welding stability coefficient according to the area of the spatter hot spots and the density distribution of the spatter hot spots themselves; and normalizing the sum value of the first welding stability coefficient and the second welding stability coefficient as the stability index of the current welding process.

[0048] It should be noted that the bicycle parts are continuously welded by rotation. In this way, due to the rotation, the morphological changes will occur between the front and rear frames. This morphological change mainly affects the heat diffusion effect, and during the normal welding process, a symmetric effect with the vertical line as the axis of symmetry is presented. Therefore, in the embodiments of the present invention, the morphological center point passing through the welding molten pool area is used to draw a vertical line along the welding direction, and the welding molten pool area is divided into two influence areas. According to the gray-scale changes of the pixel points in the welding direction in different influence areas, the gray-scale change characteristic index of the welding molten pool area is determined.

[0049] Furthermore, in some embodiments of the present invention, determining the gray-scale change characteristic index of the welding molten pool area according to the gray-scale changes of the pixel points in the welding direction in different influence areas includes: calculating the absolute value of the difference between the gray-scale values of each pixel point and the next pixel point in the welding direction to obtain the gray-scale change value of the corresponding pixel point; taking the average value of the gray-scale change values of all pixel points in each influence area as the area change value; taking the absolute value of the difference between the area change values of the two influence areas as the gray-scale change characteristic index of the welding molten pool area.

[0050] In the embodiments of the present invention, by calculating the area change values of the influence areas, the absolute value of the difference between the area change values of the two influence areas is used as the gray-scale change characteristic index of the welding molten pool area, and this index represents the symmetry effect of the welding molten pool area.

[0051] Taking the absolute value of the difference between the gray-scale change characteristic indexes of the current frame and the previous frame as the change value of the symmetry effect, and normalizing the opposite number of the absolute value of the difference as the first welding stability coefficient of the current frame. That is, the larger the first welding stability coefficient, the smaller the dynamic change of the welding molten pool area in the current frame, and the same symmetry effect is still maintained, and the welding process is more stable.

[0052] Furthermore, in some embodiments of the present invention, determining the second welding stability coefficient according to the area of the splash hot spot and the density distribution of the splash hot spot itself includes: determining the number of splash hot spots included within a preset range centered on the morphological center point of the welding molten pool area as the density analysis index; taking the product of the total area of all splash hot spots and the density analysis index, and normalizing the opposite number of the product value as the second welding stability coefficient.

[0053] Since the number of spatter hot spots can directly reflect the intensity of heat input during the welding process, the more the number of spatter hot spots and the larger the area, it indicates that more metal melts and splashes into the molten pool during the welding process, and the welding process is more unstable. Therefore, a preset range can be determined as a circular range with a diameter of 10 cm, so as to calculate the density information, obtain the density analysis index, and calculate the product value of the density analysis index and the total area of all spatter hot spots. The larger the product value, the higher the density and the larger the area of the spatter hot spots. Therefore, the welding process is more unstable. The negative value of the product value is normalized and used as the second welding stability coefficient.

[0054] Combining the above analysis, the sum value of the first welding stability coefficient and the second welding stability coefficient is normalized and used as the stability index of the current welding process. This stability index can combine the characteristics of the welding molten pool area and the spatter hot spots respectively to analyze the stability of the welding process, and has high accuracy.

[0055] S105: According to the stability index and the workpiece pipe diameter deviation degree, the parameters of the current welding process are adjusted in real time.

[0056] According to the stability index and the workpiece pipe diameter deviation degree, the parameters of the current welding process are adjusted in real time, including: calculating the ratio of the workpiece pipe diameter deviation degree and the stability index, and linearly mapping it to the range between (0, 2) as the adjustment index at the current moment; adjusting the proportional gain of the PID controller according to the adjustment index to perform PID control on the welding process.

[0057] In the embodiment of the present invention, the workpiece pipe diameter deviation degree represents the thermal diffusion deviation effect of the thermal influence area presented due to the pipe diameter characteristics during the welding process, and the stability index represents the stability analysis of the welding process by combining the characteristics of the welding molten pool area and the spatter hot spots respectively.

[0058] Therefore, directly taking the ratio of the workpiece pipe diameter deviation degree and the stability index and linearly mapping it to the range between (0, 2) as the adjustment index at the current moment, that is, the larger the adjustment index value, the greater the thermal diffusion deviation and the more unstable the welding at the current moment, and it is necessary to increase the adjustment effect. Linear mapping to the range between (0, 2) is convenient for subsequent PID control.

[0059] In the embodiment of the present invention, a PID controller can be used to adjust and control the size of the welding gun current during the current welding process. The adjustment index is input into the PID controller as the proportional gain coefficient to adjust the size of the welding gun current in real time, so as to reduce the situation that the welding heat of bicycle parts is uneven due to uneven pipe diameters during the circumferential welding process, and common problems such as excessive / insufficient heat input of the weld, excessive spatter, and penetration deviation can be avoided.

[0060] In the embodiment of the present invention, by acquiring the thermal imaging image of the bicycle part during the welding process, performing grayscale processing to obtain a grayscale image, and dividing the welding molten pool area, heat-affected area, and splash hot spots according to the image features in the grayscale image. Since welding analysis needs to consider the overall welding effect, through the division of different areas, different areas can be analyzed separately, thereby improving the reliability of the overall welding analysis; according to the heat diffusion effect of the heat-affected area in different directions, the pipe diameter deviation degree of the workpiece in the welding area is analyzed. The pipe diameter deviation degree of the workpiece can effectively represent the heat diffusion deviation effect of the heat-affected area presented due to the pipe diameter characteristics during the welding process; then, combining the grayscale change characteristics of the welding molten pool area, the area and distribution characteristics of the splash hot spots, the stability index of the current welding process is determined. The stability index can combine the characteristics of the welding molten pool area and the splash hot spots respectively to perform the stability analysis of the welding process; after that, according to the stability index and the pipe diameter deviation degree of the workpiece, the parameters of the current welding process are adjusted in real time. The present invention can independently analyze different welding areas, thereby combining the characteristics of all welding areas to achieve the control analysis at the current moment, reducing the situation of uneven welding heat, and improving the stability of the overall welding control.

[0061] On the other hand, the present invention also provides a circumferential seam welding system for bicycle parts, the system includes: An acquisition module, configured to acquire the thermal imaging image of the bicycle part during the welding process and perform grayscale processing to obtain a grayscale image; A division module, configured to determine the welding molten pool area, heat-affected area, and splash hot spots according to the grayscale distribution characteristics of different areas in the grayscale image; A deviation analysis module, configured to radiate from the center point of the welding molten pool area to the outside to determine the gradient feature sequence of the temperature change in the direction of different edge pixels of the heat-affected area; according to the length difference and grayscale distribution of the gradient feature sequence, determine the pipe diameter deviation degree of the workpiece in the current welding area; A stability analysis module, configured to analyze the grayscale change characteristics of the welding molten pool area in the current frame and the previous frame of grayscale images, and combine the area and distribution characteristics of the splash hot spots in the current frame to evaluate the stability index of the current welding process; A control module, configured to adjust the parameters of the current welding process in real time according to the stability index and the pipe diameter deviation degree of the workpiece.

[0062] Each item in the circumferential seam welding system for bicycle parts in the embodiment of the present invention implements the steps of any one of the methods as described above when executed.

[0063] On the other hand, the present invention also provides a circumferential seam welding device for bicycle parts. The device includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the foregoing methods.

[0064] It should be noted that: the above-mentioned sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A circumferential seam welding method for bicycle parts, characterized in that, The method includes: Obtaining a thermal imaging image of a bicycle component during the welding process and performing grayscale processing to obtain a grayscale image; Determining the welding molten pool area, the heat affected area, and the spatter hotspots according to the grayscale distribution characteristics of different regions in the grayscale image; Radiating from the center point of the welding molten pool area to the outside, determining the gradient feature sequence of the temperature change in the direction of different edge pixels in the heat affected area; determining the workpiece pipe diameter deviation degree of the current welding area according to the length difference and grayscale distribution of the gradient feature sequence; Analyzing the grayscale change characteristics of the welding molten pool area in the current frame and the previous frame of grayscale images, and combining the area and distribution characteristics of the spatter hotspots in the current frame to evaluate the stability index of the current welding process; According to the stability index and the workpiece pipe diameter deviation degree, adjusting the parameters of the current welding process in real time.

2. The circumferential seam welding method for a bicycle component according to claim 1, characterized in that, The determining the welding molten pool area, the heat affected area, and the spatter hotspots according to the grayscale characteristics of different regions in the grayscale image includes: Performing grayscale clustering processing on the pixel points in the welding affected area based on the density clustering algorithm, determining different clustering regions, and calculating the average grayscale value of the pixel points in each clustering region as the grayscale index corresponding to the clustering region; Combining the clustering regions with the grayscale index greater than the preset first index threshold as the welding molten pool area; In the other clustering regions except the welding molten pool area, calculating the average value of the grayscale index differences between each clustering region and all other adjacent clustering regions, and taking the clustering region with the average value of the grayscale index differences greater than the preset difference threshold and a larger grayscale index value compared with all other adjacent clustering regions as the spatter hotspot; Taking the region except the welding molten pool area and the spatter hotspots as the heat affected area.

3. A circumferential seam welding method for bicycle parts as claimed in claim 1, characterized in that, The radiating from the center point of the welding molten pool area to the outside and determining the gradient feature sequence of the temperature change in the direction of different edge pixels in the heat affected area includes: Taking the morphological center point of the welding molten pool area as the radiation point and making ray connections to different edge pixels in the heat affected area; Taking the difference between the grayscale value of each pixel point on the ray and the grayscale value of the corresponding previous pixel point as the grayscale gradient of the pixel point, and sorting them in the order from near to far from the radiation point to obtain the gradient feature sequence of the temperature change in the direction of the corresponding edge pixel point.

4. A circumferential seam welding method for a bicycle component as claimed in claim 1, wherein, The determining the workpiece pipe diameter deviation degree of the current welding area according to the length difference and grayscale distribution of the gradient feature sequence includes: Taking the range of the number of elements included in different gradient feature sequences as the first deviation analysis index; Calculating the standard deviation of all elements in each gradient feature sequence as the sequence fluctuation index; Taking the standard deviation of all sequence fluctuation indexes as the second deviation analysis index; Normalizing the product value of the first deviation analysis index and the second deviation analysis index as the workpiece pipe diameter deviation degree.

5. A circumferential seam welding method for bicycle parts according to claim 1, characterized in that, The analyzing the grayscale change characteristics of the welding molten pool area in the current frame and the previous frame of grayscale images, and combining the area and distribution characteristics of the spatter hotspots in the current frame to evaluate the stability index of the current welding process includes: Passing through the morphological center point of the welding molten pool area and making a perpendicular line along the welding direction to divide the welding molten pool area into two affected areas; Determine the gray-scale change characteristic index of the welding molten pool area according to the gray-scale changes of the pixel points in different affected areas in the welding direction; Calculate the absolute value of the difference between the gray-scale change characteristic indexes of the current frame and the previous frame, and normalize the negative value of the absolute value of the difference as the first welding stability coefficient of the current frame; Determine the second welding stability coefficient according to the area of the splash hot spot and the density distribution of the splash hot spot itself; Normalize the sum value of the first welding stability coefficient and the second welding stability coefficient as the stability index of the current welding process.

6. The circumferential seam welding method for a bicycle component according to claim 5, characterized in that, The step of determining the gray-scale change characteristic index of the welding molten pool area according to the gray-scale changes of the pixel points in different affected areas in the welding direction includes: Calculate the absolute value of the gray-scale value difference between each pixel point and the next pixel point in the welding direction to obtain the gray-scale change value of the corresponding pixel point; Take the average value of the gray-scale change values of all pixel points in each affected area as the area change value; Take the absolute value of the difference between the area change values of the two affected areas as the gray-scale change characteristic index of the welding molten pool area.

7. A circumferential seam welding method for a bicycle component according to claim 5, characterized in that, The step of determining the second welding stability coefficient according to the area of the splash hot spot and the density distribution of the splash hot spot itself includes: Within a preset range centered on the morphological center point of the welding molten pool area, determine the number of splash hot spots included as the density analysis index; Normalize the negative value of the product value of the total area of all the splash hot spots and the density analysis index as the second welding stability coefficient.

8. The circumferential seam welding method for a bicycle component according to claim 1, characterized in that, The step of adjusting the parameters of the current welding process in real time according to the stability index and the workpiece pipe diameter deviation degree includes: Calculate the ratio of the workpiece pipe diameter deviation degree and the stability index, and linearly map it to the range between (0, 2) as the adjustment index at the current moment; Adjust the proportional gain of the PID controller according to the adjustment index to perform PID control on the welding process.

9. A circumferential seam welding system for bicycle parts, characterized in that, The system includes: An acquisition module for acquiring the thermal imaging image of the bicycle parts during the welding process and performing gray-scale processing to obtain a gray-scale image; A division module for determining the welding molten pool area, the heat affected area, and the splash hot spot according to the gray-scale distribution characteristics of different areas in the gray-scale image; A deviation analysis module for radiating outward from the center point of the welding molten pool area to determine the gradient characteristic sequence of the temperature change in the direction of different edge pixel points in the heat affected area; and determining the workpiece pipe diameter deviation degree of the current welding area according to the length difference and gray-scale distribution of the gradient characteristic sequence; A stability analysis module for analyzing the gray-scale change characteristics of the welding molten pool area in the gray-scale images of the current frame and the previous frame, and evaluating the stability index of the current welding process in combination with the area and distribution characteristics of the splash hot spots in the current frame; A control module for adjusting the parameters of the current welding process in real time according to the stability index and the workpiece pipe diameter deviation degree.

10. A circumferential seam welding device for bicycle parts, the device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

Images