Welding parameter adjusting method for automobile part welding device

Abstract

The invention relates to the technical field of automobile part production, in particular to a welding parameter adjusting method for an automobile part welding device.The welding parameter adjusting method comprises the following steps that an image of a workpiece welding position is obtained through a high-resolution camera, image preprocessing is conducted, and an image of a welding area is obtained; extracting an edge contour set of the crack by using an edge detection algorithm; and traversing pixel points of each element in the edge contour set. According to the welding parameter adjusting method for the automobile part welding device, an image of a workpiece welding position is obtained through a high-resolution camera, and after image information is uploaded to a microprogram controller, a parameter adjusting amount set is obtained through a parameter adjusting method; and the microprogram controller takes out values in the parameter adjustment amount set and correspondingly adjusts the advancing speed of the linear module, the power of the induction coil and the power of the welding gun, so that the welding of the workpiece achieves the optimal effect, and the purpose of automatically adjusting the welding parameters is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of automobile parts production, in particular to a welding parameter adjustment method for an automobile parts welding device. Background Art

[0002] The stator is one of the main parts of the automotive generator. The main function of the stator is to generate a magnetic field. In the automotive generator, the stator converts the mechanical energy generated by the rotation of the rotor into electrical energy by generating a magnetic field, thereby achieving the function of generating electricity. Welding is required during the stator production process.

[0003] Chinese patent 202410020785.2 proposes a stator welding device for automobile motor production, which realizes automatic assembly of insulating sheets and silicon steel sheets into the stator frame through a plurality of loading racks cooperating with the feeding structure inside thereof, and does not require manual stacking of silicon steel sheets inside the stator frame, thereby reducing manual labor intensity. In the process of welding the stator, it is necessary to rely on manual experience to adjust relevant welding parameters so that the stator welding effect can be optimized. However, relying on manual experience to adjust welding parameters is not only time-consuming and labor-intensive, but also has errors. Therefore, an automatic welding device and a welding method for automobile parts production are proposed to solve the above problems. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a welding parameter adjustment method for an automobile parts welding device, which has the advantages of automatically adjusting welding parameters, etc., and solves the problem that adjusting welding parameters relying on manual experience is not only time-consuming and labor-intensive, but also has errors.

[0005] To achieve the above object, the present invention provides the following technical solution: a welding parameter adjustment method for an automobile parts welding device, comprising the following steps: S4.1. Obtain an image of the welding portion of the workpiece by using a high-resolution camera, perform image preprocessing, and obtain an image of the welding area; S4.2. Extract a set of edge contours of the crack using an edge detection algorithm; S4.3. traverse the pixel points of each element in the edge contour set and calculate the crack length value set; S4.4. Determine whether the crack length value set is empty. If yes, jump to S4.5. If no, jump to S4.6. S4.5. End the program without adjusting the welding parameters; S4.6. Obtain a welding parameter adjustment amount set according to the crack length value set; S4.7. Determine whether the welding parameter adjustment set is empty. If so, jump to S4.5. If not, the microprogram controller takes out the value in the parameter adjustment set and adjusts the linear module travel speed, induction coil power and welding grab power accordingly to achieve the best welding effect of the workpiece.

[0006] Furthermore, the image preprocessing described in step S4.1 to obtain the welding area image also includes the following sub-steps: S4.1.1. Convert the original image into a grayscale image. Select a suitable threshold value according to the grayscale distribution characteristics of the image. The specific formula for converting the original image into a grayscale image is: ; in, Represents the value of the red channel, represents the value of the green channel, Represents the value of the blue channel; S4.1.2. Use a Gaussian filter to smooth the image to reduce noise and detail interference. The specific formula is: ; in, is the coordinate, σ is the standard deviation of the Gaussian distribution; S4.1.3. Use thresholding to segment the image and separate the weld area from the background.

[0007] Furthermore, step S4.2. extracting the crack edge contour using an edge detection algorithm further includes the following sub-steps: S4.2.1. Use the Sobel operator to calculate the horizontal gradient value of the grayscale image , the specific formula is: ; Calculate the vertical gradient value of the grayscale image y, the specific formula is: ; S4.2.2. For each pixel, compare the gradient values ​​of the two adjacent pixels in the gradient direction, and only retain the pixel with the largest gradient value in the gradient direction; S4.2.3. Classify pixels into three categories: strong edge, weak edge and non-edge, and set a higher threshold With a lower threshold , when the gradient value of the pixel is higher than When the gradient value of the pixel point is lower than When the gradient value of the pixel point is between and When the edge is between , it is classified as a weak edge. If the weak edge is connected to the strong edge, it is retained; otherwise, it is discarded; S4.2.4. Through the edge connection step, the weak edge is connected to the surrounding strong edges to form a complete edge.

[0008] Furthermore, the step S4.3 of calculating and obtaining a set of crack length values ​​further includes the following sub-steps: S4.3.1. Calculate the distance between adjacent pixels. The specific formula is: ; Where n is the total number of crack pixels; S4.3.2. The entire crack length is the sum of the distances between all adjacent pixels; S4.3.3. Place the crack length into the set of crack length values.

[0009] Furthermore, the step S4.6 of obtaining a welding parameter adjustment amount set according to a crack length value set further includes the following sub-steps: S4.6.1. Traversing the set of crack length values , get the maximum crack length Max and the total number of cracks , calculate the average crack length and crack length variance , the calculation formula is as follows: ; ; In the formula, Indicates the value of each sample; S4.6.2. Set the maximum crack length threshold to μ, the total number of cracks threshold to θ, and the crack length variance threshold to ω. and and If yes, jump to S4.6.4, otherwise jump to S4.6.3; S4.6.3. Set the parameter adjustment amount set to empty; S4.6.4. Average the crack lengths Substituted as input into the constructed multivariate linear regression model, the welding speed, preheating temperature and welding power are obtained, and the welding speed, preheating temperature and welding power are put into the parameter adjustment set in turn.

[0010] Furthermore, the construction of the multivariate linear regression model in step S4.6.4 further includes the following sub-steps: S4.6.4.1. Based on historical experimental data, establish a historical data set, which contains crack length And its corresponding welding speed , Preheating temperature and welding power ; S4.6.4.2. Clean the data to remove outliers, missing values, etc. to ensure data quality; S4.6.4.3. Set the form of the multivariate linear regression model. The specific formula is as follows: ; In the formula, is the regression constant, also called the intercept term, , are the regression coefficients corresponding to the respective variables , degree of impact.

[0011] Compared with the prior art, the technical solution of this application has the following beneficial effects: The welding parameter adjustment method for an automobile spare parts welding device obtains an image of a workpiece welding point through a high-resolution camera, uploads the image information to a microprogram controller, obtains a parameter adjustment amount set through a parameter adjustment method, and the microprogram controller takes out the value in the parameter adjustment amount set and correspondingly adjusts the linear module travel speed, induction coil power and welding grab power to achieve the best welding effect of the workpiece, thereby achieving the purpose of automatically adjusting the welding parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a schematic diagram of the process of the present invention; DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] See also Figure 1 In this embodiment, a welding parameter adjustment method for an automobile parts welding device includes the following steps: S4.1. Obtain an image of the welding portion of the workpiece by using a high-resolution camera, perform image preprocessing, and obtain an image of the welding area; S4.2. Extract a set of edge contours of the crack using an edge detection algorithm; S4.3. traverse the pixel points of each element in the edge contour set and calculate the crack length value set; S4.4. Determine whether the crack length value set is empty. If yes, jump to S4.5. If no, jump to S4.6. S4.5. End the program without adjusting the welding parameters; S4.6. Obtain a welding parameter adjustment amount set according to the crack length value set; S4.7. Determine whether the welding parameter adjustment set is empty. If so, jump to S4.5. If not, the microprogram controller takes out the value in the parameter adjustment set and adjusts the linear module travel speed, induction coil power and welding grab power accordingly to achieve the best welding effect of the workpiece.

[0015] In this embodiment, step S4.1 performs image preprocessing to obtain the welding area image, and further comprises the following sub-steps: S4.1.1. Convert the original image into a grayscale image. Select a suitable threshold value according to the grayscale distribution characteristics of the image. The specific formula for converting the original image into a grayscale image is: ; in, Represents the value of the red channel, represents the value of the green channel, Represents the value of the blue channel; S4.1.2. Use a Gaussian filter to smooth the image to reduce noise and detail interference. The specific formula is: ; in, is the coordinate, σ is the standard deviation of the Gaussian distribution; S4.1.3. Use thresholding to segment the image and separate the weld area from the background.

[0016] In this embodiment, step S4.2. extracting the crack edge contour using an edge detection algorithm also includes the following sub-steps: S4.2.1. Use the Sobel operator to calculate the horizontal gradient value of the grayscale image , the specific formula is: ; Calculate the vertical gradient value of the grayscale image y, the specific formula is: ; S4.2.2. For each pixel, compare the gradient values ​​of the two adjacent pixels in the gradient direction, and only retain the pixel with the largest gradient value in the gradient direction; S4.2.3. Classify pixels into three categories: strong edge, weak edge and non-edge, and set a higher threshold With a lower threshold , when the gradient value of the pixel is higher than When the gradient value of the pixel point is lower than When the gradient value of the pixel point is between and When the edge is between , it is classified as a weak edge. If the weak edge is connected to the strong edge, it is retained; otherwise, it is discarded; S4.2.4. Through the edge connection step, the weak edge is connected to the surrounding strong edges to form a complete edge.

[0017] In this embodiment, step S4.3 of calculating and obtaining a set of crack length values ​​further includes the following sub-steps: S4.3.1. Calculate the distance between adjacent pixels. The specific formula is: ; Where n is the total number of crack pixels; S4.3.2. The entire crack length is the sum of the distances between all adjacent pixels; S4.3.3. Place the crack length into the set of crack length values.

[0018] In this embodiment, step S4.6 of obtaining a welding parameter adjustment value set according to a crack length value set also includes the following sub-steps: S4.6.1. Traversing the set of crack length values , get the maximum crack length Max and the total number of cracks , calculate the average crack length and crack length variance , the calculation formula is as follows: ; ; In the formula, Indicates the value of each sample; S4.6.2. Set the maximum crack length threshold to μ, the total number of cracks threshold to θ, and the crack length variance threshold to ω. and and If yes, jump to S4.6.4, otherwise jump to S4.6.3; S4.6.3. Set the parameter adjustment amount set to empty; S4.6.4. Average the crack lengths Substituted as input into the constructed multivariate linear regression model, the welding speed, preheating temperature and welding power are obtained, and the welding speed, preheating temperature and welding power are put into the parameter adjustment set in turn.

[0019] In this embodiment, step S4.6.4 of constructing a multivariate linear regression model further includes the following sub-steps: S4.6.4.1. Based on historical experimental data, establish a historical data set, which contains crack length And its corresponding welding speed , Preheating temperature and welding power ; S4.6.4.2. Clean the data to remove outliers, missing values, etc. to ensure data quality; S4.6.4.3. Set the form of the multivariate linear regression model. The specific formula is as follows: ; In the formula, is the regression constant, also called the intercept term, , are the regression coefficients corresponding to the respective variables , degree of impact.

[0020] The estimation steps of the regression coefficients are as follows: 1) Substitute the historical data set into the model and calculate the predicted value of each observation ; 2) Calculate the residual for each observation, that is, the difference between the actual observation and the predicted value ,in, is the actual observed data value; 3) Add the squares of all residuals to get the residual sum of squares ; 4) For each regression coefficient, the RSS , Find the partial derivative and set it to 0, thus obtaining a system of equations; 5) Solve this system of equations to get the estimated values ​​of the regression coefficients .

[0021] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0022] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A welding parameter adjustment method for an automobile parts welding device, characterized in that: The following steps are involved: S4.

1. Obtain an image of the welding portion of the workpiece by using a high-resolution camera, perform image preprocessing, and obtain an image of the welding area; S4.

2. Extract a set of edge contours of the crack using an edge detection algorithm; S4.

3. traverse the pixel points of each element in the edge contour set and calculate the crack length value set; S4.

4. Determine whether the crack length value set is empty. If yes, jump to S4.

5. If no, jump to S4.

6. S4.

5. End the program without adjusting the welding parameters; S4.

6. Obtain a welding parameter adjustment amount set according to the crack length value set; S4.

7. Determine whether the welding parameter adjustment set is empty. If so, jump to S4.

5. If not, the microprogram controller takes out the value in the parameter adjustment set and adjusts the linear module travel speed, induction coil power and welding grab power accordingly to achieve the best welding effect of the workpiece.

2. A welding parameter adjustment method for an automobile parts welding device according to claim 1, characterized in that: The image preprocessing described in step S4.1 to obtain the welding area image also includes the following sub-steps: S4.1.

1. Convert the original image into a grayscale image. Select an appropriate threshold value based on the grayscale distribution characteristics of the image. The specific formula for converting the original image into a grayscale image is: ； in, Represents the value of the red channel, represents the value of the green channel, Represents the value of the blue channel; S4.1.

2. Use a Gaussian filter to smooth the image to reduce noise and detail interference. The specific formula is: ； in, is the coordinate, σ is the standard deviation of the Gaussian distribution; S4.1.

3. Use thresholding to segment the image and separate the weld area from the background.

3. A welding parameter adjustment method for an automobile parts welding device according to claim 2, characterized in that: Step S4.

2. The method of extracting the crack edge contour using an edge detection algorithm further includes the following sub-steps: S4.2.

1. Use the Sobel operator to calculate the horizontal gradient value of the grayscale image , the specific formula is: ； Calculate the vertical gradient value of the grayscale image y, the specific formula is: ； S4.2.

2. For each pixel, compare the gradient values ​​of the two adjacent pixels in the gradient direction, and only retain the pixel with the largest gradient value in the gradient direction; S4.2.

3. Classify pixels into three categories: strong edge, weak edge and non-edge, and set a higher threshold With a lower threshold , when the gradient value of the pixel is higher than When the gradient value of the pixel point is lower than When the gradient value of the pixel point is between and When the edge is between , it is classified as a weak edge. If the weak edge is connected to the strong edge, it is retained; otherwise, it is discarded; S4.2.

4. Through the edge connection step, the weak edge is connected to the surrounding strong edges to form a complete edge.

4. The welding parameter adjustment method for automobile parts welding device according to claim 1, characterized in that: The step S4.3 of calculating the crack length value set further includes the following sub-steps: S4.3.

1. Calculate the distance between adjacent pixels. The specific formula is: ； Where n is the total number of crack pixels; S4.3.

2. The entire crack length is the sum of the distances between all adjacent pixels; S4.3.

3. Place the crack length into the set of crack length values.

5. A welding parameter adjustment method for an automobile parts welding device according to claim 4, characterized in that: The step S4.6 of obtaining a welding parameter adjustment value set according to a crack length value set also includes the following sub-steps: S4.6.

1. Traversing the set of crack length values , get the maximum crack length Max and the total number of cracks , calculate the average crack length and crack length variance , the calculation formula is as follows: ； ； In the formula, Indicates the value of each sample; S4.6.

2. Set the maximum crack length threshold to μ, the total number of cracks threshold to θ, and the crack length variance threshold to ω. and and If yes, jump to S4.6.4, otherwise jump to S4.6.3; S4.6.

3. Set the parameter adjustment amount set to empty; S4.6.

4. Average the crack lengths Substituted as input into the constructed multivariate linear regression model, the welding speed, preheating temperature and welding power are obtained, and the welding speed, preheating temperature and welding power are put into the parameter adjustment set in turn.

6. A welding parameter adjustment method for an automobile parts welding device according to claim 5, characterized in that: The construction of the multivariate linear regression model in step S4.6.4 also includes the following sub-steps: S4.6.4.

1. Based on historical experimental data, establish a historical data set, which contains crack length And its corresponding welding speed , Preheating temperature and welding power ; S4.6.4.

2. Clean the data to remove outliers, missing values, etc. to ensure data quality; S4.6.4.

3. Set the form of the multivariate linear regression model. The specific formula is as follows: ； In the formula, is the regression constant, also called the intercept term, , are the regression coefficients corresponding to the respective variables , degree of impact.

Images