Method, device, and program product for predicting extent of cracking of self-piercing rivet joints

Abstract

This application applies to the field of self-piercing riveting technology, providing a method, device, and program product for predicting the cracking degree of self-piercing riveting rivets. The method includes: acquiring the current circular hole punching feature of the sheet metal to be riveted, wherein the sheet metal to be riveted is the lower layer material in the self-piercing riveting connection material, and the current circular hole punching feature is formed after the sheet metal to be riveted is punched with a circular hole; processing the current circular hole punching feature using a target relationship model to predict the predicted cracking degree value of the rivet when the sheet metal to be riveted is self-pierced riveted, wherein the target relationship model is determined based on multiple historical circular hole punching features and multiple historical rivet cracking degree values ​​corresponding to the sheet metal to be riveted, and the target relationship model is used to characterize the correspondence between the circular hole punching feature of the sheet metal to be riveted and the rivet cracking degree value. Through the above method, the cracking degree of the rivet can be predicted without completely destroying the sheet metal.

Description

Technical Field

[0001] This application belongs to the field of self-piercing riveting technology, and in particular relates to a method, equipment and program product for predicting the degree of cracking of self-piercing riveting rivets. Background Technology

[0002] Self-piercing riveting is a cold joining technique used to join two or more sheet metals. A specially designed rivet penetrates the top sheet metal, and under the action of a riveting die, the hollow structure at the rivet's tail expands and pierces the bottom sheet metal without penetrating it, thus forming a strong joint. Self-piercing riveting technology can be applied in various fields. For example, it can be used in vehicle manufacturing.

[0003] To improve the lightweighting of the body-in-white and increase the overall vehicle range, steel-aluminum hybrid body designs are gradually becoming the mainstream. Self-piercing riveting technology can be used to achieve safe and effective connections between pure aluminum parts and steel-aluminum hybrid parts. During the self-piercing riveting process, a semi-hollow self-piercing rivet pierces through the upper sheet metal and then quantitatively penetrates into the lower sheet metal. During penetration into the lower sheet metal, significant localized plastic deformation occurs. Due to the insufficient mechanical properties of the lower sheet metal material, some degree of material cracking may occur during rivet penetration.

[0004] Material cracking can adversely affect the mechanical properties, corrosion resistance, and sealing performance of joints. To ensure the safety of the entire vehicle, material cracking caused by self-piercing riveting should be avoided during the body-in-white manufacturing process. If the extent of cracking after self-piercing riveting can be predicted, material cracking caused by self-piercing riveting can be avoided.

[0005] Currently, when determining the degree of rivet cracking corresponding to a self-piercing riveting scheme, a preset number of self-piercing riveting operations can be performed according to the scheme. Based on the actual riveting results, the effectiveness of the self-piercing riveting scheme can be determined. However, this method requires performing self-piercing riveting itself during the process of obtaining the degree of rivet cracking, which can lead to overall damage to the riveted material, resulting in waste of the riveted material. Evaluating the effectiveness of self-piercing riveting schemes using this method is relatively costly. Summary of the Invention

[0006] In view of this, embodiments of this application provide a method, device and program product for predicting the degree of cracking of self-piercing riveting rivets, so as to predict the degree of cracking of rivets without destroying the entire sheet material.

[0007] The first aspect of this application provides a method for predicting the degree of cracking in self-piercing riveting rivets, including:

[0008] Obtain the current round hole punching feature of the plate to be riveted, wherein the plate to be riveted is the lower plate material in the self-punching riveting connection material, and the current round hole punching feature is formed after the plate to be riveted is punched with a round hole;

[0009] The target relationship model is used to process the current circular hole punching feature to predict the predicted rivet cracking degree value when the plate to be riveted is self-punched. The target relationship model is determined based on multiple historical circular hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted. The target relationship model is used to characterize the correspondence between the circular hole punching feature and the rivet cracking degree value of the plate to be riveted.

[0010] In one possible implementation, before obtaining the current hole punching feature of the sheet metal to be riveted, the method further includes:

[0011] Obtain multiple historical round hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted, wherein the historical round hole punching features and the historical rivet cracking degree values ​​correspond one-to-one;

[0012] The target relationship model is determined based on the historical hole punching characteristics and the historical rivet cracking degree values.

[0013] In one possible implementation, obtaining the multiple historical circular hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted includes:

[0014] Obtain the historical round hole punching features of the target plate after it has been punched with round holes, wherein the target plate is a plate with the same thickness and material as the plate to be riveted;

[0015] Obtain a rivet feature image of the target sheet after self-piercing riveting, wherein the target sheet is used as the lower layer material in self-piercing riveting, and the rivet feature image is obtained by scanning the lower side of the target sheet;

[0016] Based on the rivet feature image, the cracking degree value of the historical rivet is determined.

[0017] In one possible implementation, after the target sheet is punched with a circular hole, a circular hole is formed on the target sheet, and a cylindrical fragment separate from the target sheet is obtained. The historical circular hole punching features include at least one of historical circular hole features and historical fragment features. Obtaining the historical circular hole punching features of the target sheet after it has been punched with a circular hole includes:

[0018] The characteristics of the historical circular hole are determined by at least one of the following: the length of the rounded corner band, the length of the bright band, the length of the fracture band, and the length of the burr. The historical circular hole features are characterized by at least one of these three parameters; and / or,

[0019] The length of the rounded corner band, the length of the bright band, the length of the fracture band, and the length of the burr of the cylindrical fragment are determined. The characteristics of the historical fragment are characterized by at least one of the length of the rounded corner band, the length of the bright band, the length of the fracture band, and the length of the burr.

[0020] In one possible implementation, determining the historical rivet cracking degree value based on the rivet feature image includes:

[0021] The feature values ​​of the target plate are obtained from the rivet feature image. The feature values ​​are used to characterize the cracking features of the rivet. The feature values ​​include one or more of the following: number of cracks, crack area, and area of ​​crack-free region.

[0022] The degree of cracking of the historical rivets is determined based on the characteristic value.

[0023] In one possible implementation, determining the historical rivet cracking degree value based on the feature value includes:

[0024] Calculate the ratio of the crack area to the area of ​​the crack-free region;

[0025] The product of the ratio and the number of cracks is used as the historical rivet cracking degree value.

[0026] In one possible implementation, obtaining the feature values ​​of the target sheet from the rivet feature image includes:

[0027] After edge detection and noise reduction processing of the rivet feature image, cracked and crack-free areas are identified from the rivet feature image;

[0028] Based on the identified cracked and crack-free areas, the number of cracks, the area of ​​the cracks, and the area of ​​the crack-free areas are determined.

[0029] In one possible implementation, determining the target relationship model based on the historical circular hole punching features and the historical rivet cracking degree values ​​includes:

[0030] Using the historical round hole punching features and the historical rivet cracking degree values, multiple relational models are obtained by fitting them to multiple preset algorithm models.

[0031] The target relation model is determined from the plurality of relation models.

[0032] In one possible implementation, determining the target relation model from the plurality of relation models includes:

[0033] Determine the fitting accuracy for each of the aforementioned relationship models;

[0034] Based on the fitting accuracy, the target relation model is determined from the multiple relation models.

[0035] In one possible implementation, the method further includes:

[0036] If the predicted cracking degree of the rivet is greater than the preset threshold, the self-piercing riveting scheme will be adjusted.

[0037] A second aspect of this application provides a device for predicting the degree of cracking of self-piercing riveting rivets, comprising:

[0038] The acquisition module is used to acquire the current circular hole punching feature of the plate to be riveted, wherein the plate to be riveted is the lower plate material in the self-punching riveting connection material, and the current circular hole punching feature is formed after the plate to be riveted is punched with a circular hole.

[0039] The prediction module is used to process the current circular hole punching feature using a target relationship model to predict the predicted rivet cracking degree value when the plate to be riveted is self-punched. The target relationship model is determined based on multiple historical circular hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted. The target relationship model is used to characterize the correspondence between the circular hole punching feature of the plate to be riveted and the rivet cracking degree value.

[0040] A third aspect of this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in the first aspect or any possible implementation thereof.

[0041] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0042] A fifth aspect of this application provides a computer program product that, when run on a computer device, causes the computer device to perform the method described in the first aspect or any possible implementation thereof.

[0043] Compared with the prior art, the embodiments of this application may include at least the following advantages:

[0044] The method described in this application allows for the prediction of cracking degree in self-piercing riveting rivets based on the punching characteristics of the circular hole after the sheet metal to be riveted is punched. When predicting the cracking degree of self-piercing riveting rivets, it is only necessary to punch a small circular hole in the sheet metal to be riveted, thereby obtaining the punching characteristics. This method avoids completely destroying the sheet metal to be riveted, and the sheet metal after punching can still be used in production, thus preventing material waste. Based on the method described in this application, during process design, the cracking degree of self-piercing riveting rivets can be predicted without actual self-piercing riveting, thereby reducing the investment cost of process development and improving process development efficiency. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0046] Figure 1 This is a schematic diagram of a self-piercing riveting material overlap provided in an embodiment of this application;

[0047] Figure 2 This is a flowchart illustrating the steps of a method for predicting the cracking degree of a self-piercing riveting rivet according to an embodiment of this application.

[0048] Figure 3 This is a schematic diagram of a process for determining the target relationship model provided in an embodiment of this application;

[0049] Figure 4 This is a schematic diagram of a circular hole punching method provided in an embodiment of this application;

[0050] Figure 5 This is a schematic diagram of a circular hole and a cylindrical fragment formed after punching a circular hole, as provided in an embodiment of this application.

[0051] Figure 6 This is a schematic diagram of a circular hole punching feature value provided in an embodiment of this application;

[0052] Figure 7 This is a schematic diagram of a self-piercing riveting connection provided in an embodiment of this application;

[0053] Figure 8 This is a schematic diagram of a rivet feature image provided in an embodiment of this application;

[0054] Figure 9This is a schematic diagram of a rivet feature image after edge recognition provided in an embodiment of this application;

[0055] Figure 10 This is a schematic diagram of a rivet feature image after noise reduction provided in an embodiment of this application;

[0056] Figure 11 This is a schematic diagram of a rivet cracking feature provided in an embodiment of this application;

[0057] Figure 12 This is a flowchart illustrating another method for predicting the cracking degree of self-piercing riveting rivets provided in this application embodiment;

[0058] Figure 13 This is an illustration of the effect of punching and self-punching riveting of the same set of sheet metal in an embodiment of this application;

[0059] Figure 14 These are photographs of a circular hole punching fragment and a self-punching riveting buckle, both original and processed, provided in the embodiments of this application.

[0060] Figure 15 This is a scatter plot showing the cracking degree of a rivet and the proportion of bright bands in the fragments, provided in an embodiment of this application.

[0061] Figure 16 This is a schematic diagram of a device for predicting the degree of cracking of self-piercing riveting rivets provided in an embodiment of this application;

[0062] Figure 17 This is a schematic diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0063] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0064] To ensure the safety of the entire vehicle, material cracking caused by self-piercing riveting should be avoided during the body-in-white manufacturing process. Existing solutions aim to reduce the risk of joint cracking by optimizing the riveting die size to match the material flow of the lower plate during riveting. However, while optimizing the riveting die size can reduce material cracking, it also affects the interlocking of the joints. Therefore, this method cannot guarantee a comprehensive improvement in connection quality.

[0065] Furthermore, the plastic deformation properties of materials can be optimized to avoid material cracking caused by self-piercing riveting without affecting the joint quality. For example, infrared halogen and ultrasonic vibration can be used to heat the connecting metal plates to improve the plastic forming ability of the metal materials, thereby reducing cracking caused by self-piercing riveting and improving riveting quality when using traditional riveting dies. Heat-assisted riveting is an effective method to reduce joint cracking, but its application is limited due to the long heating process. When dealing with the needs of mass production, the self-piercing riveting technology should be selected and its material properties adapted and optimized from the material design and production stages to avoid material cracking at its source. To achieve this goal, it is necessary to accurately understand the correlation between material properties and the degree of cracking in self-piercing riveting.

[0066] In view of this, embodiments of this application provide a method for predicting the cracking degree of rivet threads in self-piercing riveting joints based on the circular hole punching information of the connecting material. By obtaining the mechanical property information of the material through circular hole punching, and utilizing the established correspondence between the circular hole punching features and the cracking degree of rivet threads in self-piercing riveting joints, the cracking degree of self-piercing riveting of the parts can be predicted by using the circular hole punching of the parts before self-piercing riveting is implemented, thereby allowing for targeted optimization of the part's design and performance.

[0067] Self-piercing riveting can connect two or more metal sheets. Figure 1 This is a schematic diagram of a self-piercing riveting material overlap provided in an embodiment of this application. Figure 1 The diagram shows self-piercing riveting of two types of sheet metal and self-piercing riveting of three types of sheet metal. Figure 1 In this embodiment, 11 represents a two-layer overlapping upper plate, 12 represents a two-layer overlapping lower plate, 21 represents a three-layer overlapping upper plate, 22 represents a three-layer overlapping middle plate, and 23 represents a three-layer overlapping lower plate. The plates to be riveted in this embodiment are the lower plate material in a self-piercing riveting connection material, i.e. Figure 1 12 or 23. For example... Figure 1 As shown, after self-piercing riveting, the lower layer material can form rivets. A rivet refers to a protrusion formed on the back of the connection position after riveting with rivets. The rivet is a result of plastic deformation of the lower layer material. The degree of cracking of the rivet can characterize the connection effect of self-piercing riveting. This application uses two-layer overlap and single-layer overlap as examples to illustrate the scheme. Those skilled in the art should understand that the method in this application can be applied to other multi-layer overlap scenarios.

[0068] The methods described in this application can be applied to computer devices, which may include, but are not limited to, personal computers (PCs), smartphones, netbooks, tablets, smart cameras, handheld computers, personal digital assistants (PDAs), portable multimedia players (PMPs), augmented reality (AR) / virtual reality (VR) devices, mixed reality (MR) devices, smartwatches, smart glasses, in-vehicle terminals, servers, and other terminal devices. This application does not limit the specific type of computer device.

[0069] The method in this application embodiment can be applied before self-piercing riveting to predict the riveting effect after self-piercing riveting; the method in this application embodiment can be applied in process design to evaluate the self-piercing riveting scheme in the process design.

[0070] The technical solution of this application will be described below through specific embodiments.

[0071] Reference Figure 2 The diagram illustrates a step-by-step flowchart of a method for predicting the cracking degree of a self-piercing riveting rivet according to an embodiment of this application, which may specifically include the following steps:

[0072] S201, Obtain the current round hole punching feature of the plate to be riveted, wherein the plate to be riveted is the lower plate material in the self-punching riveting connection material, and the current round hole punching feature is formed after the plate to be riveted is punched with a round hole.

[0073] The aforementioned sheet metal to be riveted can serve as the lower layer material in a self-piercing riveting connection scheme, where the material and thickness of each layer can be specified. The sheet metal to be riveted has a specified material and thickness. As an example, the sheet metal to be riveted can be a part in the process design. For instance, the sheet metal to be riveted can be a body-in-white.

[0074] The aforementioned circular hole punching feature can be achieved by punching a circular hole in the sheet metal to be riveted using a specified circular hole punching tool before self-punching, thereby obtaining the circular hole punching feature. The specified circular hole punching tool can be a punch or die of a specified size.

[0075] After punching a circular hole in the sheet metal to be riveted, a circular hole can be formed on the sheet metal, resulting in a cylindrical fragment separated from the sheet metal. Based on the characteristics of the circular hole and the cylindrical fragment, the current circular hole punching feature can be obtained. The current circular hole punching feature can include the current circular hole feature and / or the current fragment feature. The current circular hole feature can be characterized by at least one of the following: rounded corner feature, bright band feature, fracture band feature, and burr feature. The current fragment feature can be characterized by at least one of the following: rounded corner feature, bright band feature, fracture band feature, and burr feature. The rounded corner feature, bright band feature, fracture band feature, and burr feature can be characterized by defined parameters. For example, the feature values ​​of the rounded corner feature, bright band feature, fracture band feature, and burr feature can be divided into rounded corner length, bright band length, fracture band length, and burr length.

[0076] After punching a circular hole in the sheet metal to be riveted, the current circular hole punching feature can be obtained. This feature can be measured by a worker using specialized measuring tools and then input into a computer. Alternatively, the feature can be obtained by image processing of the circular hole and the remaining sheet using computer equipment. No specific limitations are specified here.

[0077] S202, the target relationship model is used to process the current round hole punching feature to predict the predicted rivet cracking degree value when the plate to be riveted is self-punched. The target relationship model is determined based on multiple historical round hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted. The target relationship model is used to characterize the correspondence between the round hole punching feature and the rivet cracking degree value of the plate to be riveted.

[0078] The aforementioned target relationship model can be a pre-established correspondence between the circular hole punching features of the sheet metal to be riveted and the cracking degree values ​​of the rivets. The target relationship model can be obtained by fitting multiple historical circular hole punching features and multiple historical rivet cracking degree values ​​corresponding to the sheet metal to be riveted. Specifically, when collecting the aforementioned historical circular hole punching features, the punch and die tool library used is consistent with the punch and die parameters in step S201; the sheet metal used has the same material and thickness as the sheet metal to be riveted; and when collecting the aforementioned historical rivet cracking degree values, the material and thickness of each layer of sheet metal used are consistent with the material and thickness of each layer of sheet metal in the aforementioned self-punching riveting scheme.

[0079] In one possible implementation, a relational model database can be included, which may contain multiple relational models. These models can be used to characterize the correspondence between the punching features of the round holes and the cracking degree values ​​of the self-piercing riveting rivets of plates to be riveted, including plates of different materials, thicknesses, and lap joint methods. Based on the material, thickness, and lap joint method of the plates to be riveted, a target relational model can be determined from the relational model database.

[0080] As an example, the target relationship model can be a trained deep learning algorithm. Inputting the current circular hole punching features into the deep learning algorithm can output the corresponding predicted rivet cracking degree value.

[0081] As another example, the target relational model can be a relational expression in which the circular hole punching feature is the independent variable and the rivet cracking degree value is the dependent variable. Substituting the current circular hole punching feature into this relational expression, the corresponding predicted rivet cracking degree value can be obtained.

[0082] Understandably, when performing round hole punching and self-piercing riveting on sheet metal with the same properties, the material properties are identical, resulting in similar deformation characteristics. The round hole punching feature reflects the sheet metal's deformation characteristics, and the self-piercing riveting buckle cracking degree value also reflects these characteristics. Since the deformation characteristics of the corresponding sheet metals are consistent, a model can be built based on the round hole punching feature and the self-piercing riveting buckle cracking degree value to obtain a target relationship model between them. Based on this established target relationship model, round hole punching can be performed on the sheet metal to be riveted without implementing self-piercing riveting. Based on the round hole punching feature and the target relationship model, the predicted buckle cracking degree value can be obtained. The predicted buckle cracking degree value characterizes the cracking risk of the sheet metal to be riveted. That is, after obtaining the predicted buckle cracking degree value, the riveting personnel can determine whether the risk of cracking after performing self-piercing riveting based on the current self-piercing riveting scheme is too high, thus determining whether to adjust the self-piercing riveting scheme.

[0083] In one possible implementation, a preset threshold can be determined. When the predicted cracking degree of the rivet exceeds this threshold, it indicates that the predicted cracking degree is too high, the cracking risk of the riveted sheet metal is too great, and the connection effect of the self-piercing riveting is poor. In this case, the self-piercing riveting scheme can be adjusted to reduce the cracking risk and improve the connection effect. When the predicted cracking degree is less than or equal to the threshold, the cracking risk of the current self-piercing riveting scheme can be considered low, and the riveting effect meets the requirements. The preset threshold can be determined according to the riveting requirements in the process design.

[0084] The above target relationship model can be followed as follows Figure 3 The method shown is used to determine this. (Refer to...) Figure 3 The diagram illustrates a flowchart of determining the target relationship model according to an embodiment of this application, which may specifically include the following steps:

[0085] S301, obtain multiple historical round hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted, wherein the historical round hole punching features and the historical rivet cracking degree values ​​correspond one-to-one.

[0086] The computer equipment can acquire the historical punching features of the target plate after it has been punched with a round hole. The target plate is a plate with the same thickness and material as the plate to be riveted.

[0087] Figure 4 This is a schematic diagram of a circular hole punching method provided in an embodiment of this application. Figure 4 In this diagram, 41 represents the punch, 412 is the punch diameter; 42 represents the die, 421 is the die inner diameter, and 422 is the die outer diameter. For example... Figure 4 As shown, a die and punch combination can be used with the aid of a press to punch round holes in a target sheet metal. In this embodiment, the parameters of the die and punch can be set. For example, the inner diameter of the die D2 is greater than the diameter of the punch D1; the diameter of the punch D1 is ≤ 1.5 * the thickness of the target sheet metal t; the punching clearance d = a * the thickness of the target sheet metal t, where a = 10% to 20%.

[0088] After the target sheet is punched with a round hole, a round hole is formed on the target sheet, and a cylindrical fragment is obtained that is separated from the target sheet. Figure 5 This is a schematic diagram of a circular hole and a cylindrical fragment formed after punching a circular hole, as provided in an embodiment of this application. Figure 5 In the diagram, 51 represents the rounded corner band of the round hole, 52 represents the bright band of the round hole, 53 represents the fracture band of the round hole, 54 represents the burr of the round hole, 55 represents the rounded corner band of the fragment, 56 represents the bright band of the fragment, 57 represents the fracture band of the fragment, 58 represents the burr of the fragment, and 59 represents the diameter of the round hole. The historical round hole punching characteristics include at least one of the historical round hole characteristics and historical fragment characteristics. The historical round hole characteristics are characterized by at least one of the following: the length of the rounded corner band of the round hole, the length of the bright band of the round hole, the length of the fracture band of the round hole, and the length of the burr of the round hole. The historical fragment characteristics are characterized by at least one of the following: the length of the rounded corner band of the fragment, the length of the bright band of the fragment, the length of the fracture band of the fragment, and the length of the burr of the fragment.

[0089] In one possible implementation, a predetermined number of parameters can be selected in advance from the following to characterize historical round hole punching features: round hole fillet length, round hole bright band length, round hole fracture band length, round hole burr length, fragment roundet length, fragment bright band length, fragment fracture band length, and fragment burr length. For example, the fragment bright band length can be selected as the historical round hole punching feature. The computer device can acquire only the fragment bright band length.

[0090] In another possible implementation, the computer device can acquire the value of each parameter among the following: the length of the rounded corner band of the rounded hole, the length of the bright band of the rounded hole, the length of the fracture band of the rounded hole, the length of the burr of the rounded hole, the length of the rounded corner band of the fragment, the length of the bright band of the fragment, the length of the fracture band of the fragment, and the length of the burr of the fragment, thereby enabling multiple modeling based on the parameters.

[0091] The lengths of the rounded corner band, bright band, fracture band, burr, rounded corner band, bright band, fracture band, and burr of the fragment can be measured using measuring instruments or identified from acquired images. The determined maximum length can be the average of the maximum and minimum lengths. For example, the average of the maximum and minimum bright band values ​​can be used as the bright band length. Similarly, the average of the maximum and minimum fracture band values ​​can be used as the fracture band length.

[0092] Figure 6 This is a schematic diagram of a circular hole punching feature value provided in an embodiment of this application; Figure 6 In the diagram, 621 represents the minimum value of the bright band, 622 represents the maximum value of the bright band, 631 represents the maximum value of the fracture band, and 632 represents the minimum value of the fracture band.

[0093] Figure 7 This is a schematic diagram of a self-piercing riveting connection provided in an embodiment of this application. Figure 7 In this diagram, 70 represents the rivet, 71 the head height, 72 the interlocking value, 73 the minimum bottom thickness, 74 the upper plate thickness, 75 the lower plate thickness, and 76 the riveting die. Figure 7 As shown, after self-piercing riveting, deformation occurs on the lower plate side, and this deformation can characterize the cracking features of the rivets. Therefore, when obtaining historical rivet cracking feature values, rivet feature images can be acquired.

[0094] Computer equipment can scan the lower side of the target sheet metal using a camera or optical scanning device to acquire a rivet feature image after self-piercing riveting. The rivet feature image can also be input by the user or sent to the computer equipment from other devices.

[0095] In this process, the target sheet material serves as the lower layer material in self-piercing riveting. The riveting feature image includes the rivet cracking features formed on the target sheet material after self-piercing riveting. The rivet cracking features can be characterized by feature values, which may include one or more of the following: the number of cracks, the crack area, and the area of ​​the crack-free region.

[0096] Figure 8 This is a schematic diagram of a rivet feature image provided in an embodiment of this application, wherein, Figure 8In the image, 801 represents a crack and 802 represents noise. To facilitate the processing of the rivet feature image, image processing can be performed, such as edge recognition and noise reduction.

[0097] Edge detection can utilize the principle of Gaussian difference, achieving edge detection by calculating the difference between Gaussian blurred images at different scales. Figure 8 ).

[0098] The expression for the Difference of Gaussians (DoG) is:

[0099] DoG(x,y)=G(x,y,σ1)-G(x,y,σ2)

[0100] Where σ1 and σ2 are the standard deviations at two different scales. The expression for the Gaussian function is:

[0101]

[0102] Where (x, y) are the coordinates in the image, and σ is the standard deviation of the Gaussian kernel.

[0103] Furthermore, edge operators can be convolved with the image to calculate the gradient of each pixel, and then compared with a threshold to identify edge information. Edge operators include, but are not limited to, the Sobel operator, Prewitt operator, Laplace operator, and Roberts operator. Taking the Sobel operator as an example, the formula for calculating the gradient magnitude is:

[0104]

[0105] The gradient direction is calculated as follows:

[0106]

[0107] in, X is the gradient magnitude threshold, and Y is the gradient direction threshold. When the gradient magnitude and direction exceed the threshold, the pixel is defined as an edge point.

[0108] Noise reduction can employ methods including, but not limited to, mean filtering, median filtering, Gaussian filtering, and bilateral filtering. Noise reduction removes features irrelevant to the crack from the image after edge recognition, thereby improving the accuracy of crack information. Figure 9 Taking mean filtering as an example, the noise reduction calculation formula is:

[0109]

[0110] Where I(x,y) is the pixel value of the original image at point (x,y), N(x,y) is the square neighborhood of point (x,y), N is the number of pixels in the neighborhood, and I'(x,y) is the pixel value of the denoised image at point (x,y).

[0111] Figure 9 This is a schematic diagram of a rivet feature image after edge recognition provided in an embodiment of this application; Figure 10 This is a schematic diagram of a rivet feature image after noise reduction processing, provided in an embodiment of this application.

[0112] After edge recognition and noise reduction, cracked and crack-free areas can be identified from the rivet feature image, such as... Figure 11 As shown. Figure 11 This is a schematic diagram of a rivet cracking feature provided in an embodiment of this application.

[0113] Figure 11 In the diagram, 801 represents a crack, 803 represents the bottom of the rivet, and 804 represents the area at the bottom of the rivet without a crack. Figure 11 The crack-free region in this embodiment is the largest circle excluding cracks. In this example, a circle is used as the crack-free region for illustration; however, the shape of the crack-free region can be, but is not limited to, a circle.

[0114] Based on the identified cracked and crack-free areas, determine the number of cracks, the crack area, and the area of ​​the crack-free area.

[0115] Computer equipment determines the historical rivet cracking degree value based on rivet cracking characteristics. The historical rivet cracking degree value can be determined based on the number of cracks, the crack area, and the area of ​​the crack-free region. As an example, the computer equipment can calculate the ratio of the crack area to the area of ​​the crack-free region; then, the product of this ratio and the number of cracks is used as the historical rivet cracking degree value. For example, the consensus for calculating the rivet cracking degree value (fracture grad) can be as follows:

[0116] Fracture grad = n * s1 / s2

[0117] Where Fracture grad is the cracking degree of the rivet, n is the number of cracks, s1 is the crack area, and s2 is the area of ​​the crack-free region. The crack area and the crack-free region at the bottom of the rivet can be calculated using pixels.

[0118] S302, Based on the historical round hole punching features and the historical rivet cracking degree values, determine the target relationship model.

[0119] The computer equipment can use historical round hole punching features and historical rivet cracking degree values ​​to fit multiple preset algorithm models, resulting in multiple relational models. Then, a target relational model is determined from these multiple relational models. For example, the fitting accuracy corresponding to each relational model can be determined; based on the fitting accuracy, the target relational model is determined from the multiple relational models.

[0120] The process of fitting data on round hole punching and self-piercing riveting and establishing a target relationship model involves collecting a certain amount of characteristic data on round hole punching (independent variables) and data on the cracking degree of self-piercing riveting rivets (dependent variables) to establish a linear or nonlinear relationship between the independent and dependent variables. This is done to obtain the fitting accuracy value R. 2 If the value is greater than 0.9, the independent and dependent variables can undergo appropriate mathematical transformations such as reciprocals, exponents, and logarithms.

[0121] {L1, L2, L3, L4, L5, L6, L7, L8}~{Fracture grad}

[0122] Wherein, L1 is the length of the rounded corner of the fragment, L2 is the length of the bright band of the fragment, L3 is the length of the fracture band of the fragment, L4 is the length of the burr of the fragment, L5 is the length of the rounded corner of the hole, L6 is the length of the bright band of the hole, L7 is the length of the fracture band of the hole, and L8 is the length of the burr of the hole.

[0123] In another possible implementation, neural networks, such as convolutional networks, can be used. The historical round hole punching features can be defined as feature vectors based on the lengths of the rounded corner band, bright band, fracture band, burr, rounded corner band, bright band, fracture band, and burr. Training and testing datasets are determined based on these historical round hole punching features and historical rivet cracking severity values. A prediction model is then obtained based on these training and testing datasets; this prediction model is the aforementioned target relationship model. An attention mechanism can also be used in this prediction model to determine the weights corresponding to each feature. These weights represent the degree of influence of each feature on the prediction of the rivet cracking severity value.

[0124] The above methods can be used to determine the influence of the lower plate material properties on the degree of rivet cracking under standard self-piercing riveting processes for a material overlap combination. By changing the grade, thickness, and thickness of the upper and lower plate materials, a comprehensive analysis can be performed using the disclosed methods. This allows for the determination of the correspondence between the lower plate's circular hole punching characteristic value and the degree of rivet cracking under standard self-piercing riveting processes for different material overlap combinations. Using this result, when assessing the risk of self-piercing riveting cracking, the degree of rivet cracking can be predicted by punching the circular hole in the lower plate material, avoiding complex and tedious self-piercing riveting experiments and improving process development efficiency.

[0125] Based on the punching characteristics of the circular hole in the sheet metal to be riveted, the cracking degree of self-piercing riveting rivets is predicted. When predicting the cracking degree of self-piercing riveting rivets, it is only necessary to punch a small circular hole in the sheet metal to be riveted, thus obtaining the punching characteristics. This method avoids completely destroying the sheet metal to be riveted, and the sheet metal after punching can still be used in production, thus preventing material waste. Based on the method in this embodiment, when designing a self-piercing riveting scheme, the cracking degree of the self-piercing riveting rivets can be predicted without actual self-piercing riveting, thereby reducing the investment cost of process development and improving process development efficiency.

[0126] The method described in this embodiment can assess the risk of self-piercing riveting cracking in different parts without destroying the entire part or establishing an actual connection. The tested parts can still be put into normal production, reducing material waste.

[0127] Figure 12 This is a flowchart illustrating another method for predicting the cracking degree of self-piercing riveting rivets provided in this application embodiment. Figure 12 As shown, before making predictions, the connection material overlap combination can be determined, and the material overlap can be tested by round hole punching and self-punching riveting respectively. The round hole punching and self-punching riveting data can be fitted and a target relationship model can be established.

[0128] First, the material overlap combination needs to be determined. Specifically, if it is a two-layer overlap, the material grade and thickness of the upper layer and the thickness of the lower layer can be fixed, and lower layers with different mechanical properties can be selected. If it is a three-layer overlap, the material grades and thicknesses of the upper and middle layers and the thickness of the lower layer can be fixed, and lower layers with different mechanical properties can be selected. The mechanical properties include, but are not limited to, tensile strength and elongation at break.

[0129] The next step is to perform round hole punching, which includes: selecting testing tools, round hole punching testing, and quantifying the round hole punching features.

[0130] The selection of testing tools refers to determining the dimensions of the punch and die required to complete the circular hole punching, based on the thickness of the test plate material. The test plate material refers to the lower plate material in the self-punching riveting connection material overlap. Specifically, the die inner diameter D2 is greater than the punch diameter D1; the punch diameter D1 ≤ 1.5 * test plate thickness t; the punching clearance d = a * test plate thickness t, where a = 10%–20%.

[0131] The circular hole punching test refers to the process of punching a circular hole into a test sheet using a selected combination of punches and dies and a press. This process creates a circular through-hole in the test sheet and produces a cylindrical fragment that detaches from the test sheet.

[0132] Quantitative punching features refer to determining key feature length values ​​such as the rounded corner length L1, bright band length L2, fracture band length L3, and burr length L4 of the scrap, or the rounded corner length L5, bright band length L6, fracture band length L7, and burr length L8 of the through hole, using optical measurement methods.

[0133] The next step is to perform self-piercing riveting, which includes: determining the material overlap combination for self-piercing riveting connection, acquiring rivet feature images, image processing, and quantifying rivet cracking features.

[0134] Self-piercing riveting connection, specifically the determination of material overlap combination, refers to selecting a suitable rivet and riveting die combination based on the overlap characteristics of the connecting materials, and using riveting equipment to complete a self-piercing riveting connection that meets the requirements. The overlap characteristics of the connecting materials include: the thickness and grade of the connecting plates. A self-piercing riveting connection that meets the requirements means that the head height, interlocking value, and minimum bottom thickness satisfy the process standard requirements.

[0135] Acquiring rivet feature images refers to taking pictures or scanning the lower plate side of the material overlap after self-piercing riveting with the help of optical devices to obtain the surface features of the rivet.

[0136] Image processing refers to edge recognition and noise reduction of the acquired rivet feature images.

[0137] Next, we can quantify the cracking characteristics of the rivets, specifically by quantitatively describing the degree of cracking of the rivets through the measurement of rivet cracks.

[0138] Next, we can fit the data of round hole punching and self-piercing riveting and establish a target relationship model. Specifically, this involves collecting a certain amount of characteristic data of round hole punching (independent variable) and data on the cracking degree of self-piercing riveting rivets (dependent variable) to establish a linear or nonlinear relationship between the independent and dependent variables. To obtain the fitting accuracy value R... 2 If the value is greater than 0.9, the independent and dependent variables can undergo appropriate mathematical transformations such as reciprocals, exponents, and logarithms.

[0139] {L1, L2, L3, L4, L5, L6, L7, L8}~{Fracture grad}

[0140] In this embodiment, the material overlap used is CR02 (t = 1.5 mm) - a certain heat-free die-cast aluminum (t = 3.0 mm). Due to the influence of the die-casting process, different batches of the same grade of heat-free die-cast aluminum material exhibit different mechanical properties. The heat-free die-cast aluminum specimen size is 80 x 200 mm, and the CR02 specimen size is 40 x 100 mm. During the test, the round hole punching and self-piercing riveting positions were... Figure 13 As shown.

[0141] When punching round holes, a 6mm diameter punch and a 6.6mm inner diameter die were used, and the punching speed remained constant during different tests. For self-punching riveting, a rivet pattern number of M260468 and a rivet type of C5.3x6.0H2 were used. The head height was set to 0 during self-punching riveting, and the riveting speed remained constant during different tests.

[0142] Images of the cross-section of the fragment produced by round hole punching, images of the rivet after self-punching riveting, and images of the rivet after edge recognition and noise reduction processing are shown below. Figure 14 As shown in the image. The photographs taken from the cross-section of the fragment produced by the circular hole punching are... Figure 14 The photos of the round hole punching fragments and the photos of the rivets after punching and riveting are shown in the image. Figure 14 The self-piercing riveting rivet photo in the image, after edge recognition and noise reduction processing, is the rivet photo. Figure 14 Edge recognition noise reduction processing of photos.

[0143] like Figure 14 As shown, based on the rivet photo after edge recognition and noise reduction processing, information such as the crack area, the area of ​​the crack-free region, and the number of cracks can be obtained. Based on the photo of the circular hole punching fragment, the lengths of the bright band and the fracture band can be obtained.

[0144] like Figure 14As shown, in the first image of the circular hole punching fragment, the maximum length of the bright band is 480.2 μm, the minimum length is 56.5 μm, the minimum length of the fracture band is 2401.0 μm, and the maximum length is 2740.1 μm; in the second image, the minimum length of the bright band is 79.1 μm, the maximum length is 576.3 μm, the maximum length of the fracture band is 2638.4 μm, and the minimum length is 2214.7 μm; in the third image, the minimum length of the bright band is 190.9 μm, the maximum length is 627.3 μm, the maximum length of the fracture band is 2536.40 μm, and the minimum length is 1936.4 μm. In the fourth image of the circular hole punching fragment, the maximum length of the bright band is 609.1 μm, the minimum length is 109.1 μm, the minimum length of the fracture band is 2318.2 μm, and the maximum length is 2772.7 μm. In the fifth image of the circular hole punching fragment, the maximum length of the bright band is 245.5 μm, the minimum length is 45.5 μm, the maximum length of the fracture band is 2727.3 μm, and the minimum length is 2609.1 μm. In the sixth image of the circular hole punching fragment, the maximum length of the bright band is 545.5 μm, the minimum length is 63.6 μm, the minimum length of the fracture band is 2190.9 μm, and the maximum length is 2827.3 μm.

[0145] The key parameters and calculated data summarized from the collected photo data are shown in Table 1.

[0146] Table 1

[0147]

[0148] The data reveals the target relationship between the fracture grad (dependent variable y) of the standard self-piercing riveting joint and the proportion of the bright band length of the die-cast aluminum material after round hole punching and the obtained fragments, when the material overlap is CR02 (t = 1.5 mm) - a certain heat-free die-cast aluminum (t = 3.0 mm). This relationship can be represented as follows: Figure 15 As shown. Wherein:

[0149] y = -436.61x + 61.154

[0150] Where y is the degree of cracking of the rivet, and x is the punching feature of the round hole, which is characterized by the length of the bright band of the fragment.

[0151] The method proposed in this embodiment can establish a correlation between the punching features of circular holes and the cracking degree of self-piercing riveting rivets for different material overlap combinations. When assessing the risk of self-piercing riveting cracking in new projects, circular hole punching tests can be performed directly on the materials, and the punching features can be used to predict the cracking degree of self-piercing riveting rivets under different material overlap conditions. This method can eliminate the need for self-piercing riveting experiments, reduce equipment investment, and improve process development efficiency.

[0152] The method described in this embodiment can assess the risk of self-piercing riveting cracking in different parts without destroying the entire part or establishing an actual connection. The tested parts can still be put into normal production, reducing material waste.

[0153] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0154] Reference Figure 16 The diagram illustrates a device for predicting the cracking degree of self-piercing riveting rivets according to an embodiment of this application. Specifically, it may include an acquisition module 1601 and a prediction module 1602, wherein:

[0155] The acquisition module 1601 is used to acquire the current round hole punching feature of the plate to be riveted, wherein the plate to be riveted is the lower plate material in the self-punching riveting connection material, and the current round hole punching feature is formed after the plate to be riveted is punched with a round hole.

[0156] The prediction module 1602 is used to process the current round hole punching feature using a target relationship model to predict the predicted rivet cracking degree value when the plate to be riveted is self-punched. The target relationship model is determined based on multiple historical round hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted. The target relationship model is used to characterize the correspondence between the round hole punching feature and the rivet cracking degree value of the plate to be riveted.

[0157] In one possible implementation, the device further includes:

[0158] The historical data acquisition module is used to acquire multiple historical round hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted, wherein the historical round hole punching features and the historical rivet cracking degree values ​​correspond one-to-one.

[0159] The target relationship model determination module is used to determine the target relationship model based on the historical circular hole punching features and the historical rivet cracking degree values.

[0160] In one possible implementation, the historical data acquisition module includes:

[0161] The historical round hole punching feature acquisition submodule is used to acquire the historical round hole punching features of the target plate after it has been punched with round holes. The target plate is a plate with the same thickness and material as the plate to be riveted.

[0162] The rivet feature image acquisition submodule is used to acquire the rivet feature image of the target sheet after self-piercing riveting, wherein the target sheet is used as the lower layer material in self-piercing riveting, and the rivet feature image includes the rivet cracking feature formed on the target sheet after self-piercing riveting.

[0163] The historical rivet cracking degree value determination submodule is used to determine the historical rivet cracking degree value based on the rivet cracking characteristics.

[0164] In one possible implementation, after the target sheet is punched with a circular hole, a circular hole is formed on the target sheet, and a cylindrical fragment separate from the target sheet is obtained. The historical circular hole punching feature includes at least one of historical circular hole features and historical fragment features. The historical circular hole punching feature acquisition submodule includes:

[0165] The first determining unit is used to determine at least one of the following: the length of the rounded corner band, the length of the bright band, the length of the fracture band, and the length of the burr. The historical circular hole characteristics are characterized by at least one of the following: the length of the rounded corner band, the length of the bright band, the length of the fracture band, and the length of the burr.

[0166] The second determining unit is used to determine at least one of the following: the length of the rounded corner band, the length of the bright band, the length of the fracture band, and the length of the burr of the cylindrical fragment. The characteristics of the historical fragment are characterized by at least one of the following: the length of the rounded corner band, the length of the bright band, the length of the fracture band, and the length of the burr.

[0167] In one possible implementation, the historical rivet cracking degree value determination submodule includes:

[0168] The rivet cracking feature acquisition unit is used to acquire feature values ​​of the target plate from the rivet feature image. The feature values ​​are used to characterize the rivet cracking feature, and the feature values ​​include one or more of the following: number of cracks, crack area, and area of ​​crack-free region.

[0169] The historical rivet cracking degree value determination unit is used to determine the historical rivet cracking degree value based on the characteristic value.

[0170] In one possible implementation, the historical rivet cracking degree value determination unit includes:

[0171] The ratio calculation subunit is used to calculate the ratio of the crack area to the area of ​​the crack-free region;

[0172] The historical rivet cracking degree value determination subunit is used to take the product of the ratio and the number of cracks as the historical rivet cracking degree value.

[0173] In one possible implementation, the rivet crack feature acquisition unit includes:

[0174] An edge detection subunit is used to perform edge detection on the rivet feature image to obtain an image of the deformation region of the target sheet material.

[0175] An identification subunit is used to identify cracked and crack-free areas from the deformed area image;

[0176] A sub-unit is defined for determining the number of cracks, the area of ​​the cracks, and the area of ​​the crack-free regions based on the identified crack and crack-free areas.

[0177] In one possible implementation, the target relation model determination module includes:

[0178] The fitting submodule is used to fit the historical circular hole punching features and the historical rivet cracking degree values ​​into multiple preset algorithm models to obtain multiple relationship models.

[0179] A determination submodule is used to determine the target relation model from among the multiple relation models.

[0180] In one possible implementation, the determining submodule includes:

[0181] A fitting accuracy determination unit is used to determine the fitting accuracy corresponding to each of the relationship models;

[0182] A determining unit is used to determine the target relation model from among the multiple relation models based on the fitting accuracy.

[0183] In one possible implementation, the device further includes:

[0184] An anomaly handling module is used to adjust the self-piercing riveting scheme if the predicted rivet cracking degree value is greater than a preset threshold.

[0185] As the apparatus embodiments are basically similar to the method embodiments, they are described in a relatively simple manner. For relevant details, please refer to the description in the method embodiment section.

[0186] Figure 17 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 17 As shown, the computer device 170 of this embodiment includes: at least one processor 1700 ( Figure 17 (Only one is shown in the diagram), memory 1701, and computer program 1702 stored in said memory 1701 and executable on said at least one processor 1700, which, when executing said computer program 1702, implements the steps in any of the above method embodiments.

[0187] The computer device 170 may be a desktop computer, laptop, handheld computer, or cloud computing device, etc. This computer device may include, but is not limited to, a processor 1700 and a memory 1701. Those skilled in the art will understand that... Figure 17 The computer device 170 is merely an example and does not constitute a limitation on the computer device 170. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0188] The processor 1700 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0189] In some embodiments, the memory 1701 may be an internal storage unit of the computer device 170, such as a hard disk or memory of the computer device 170. In other embodiments, the memory 1701 may be an external storage device of the computer device 170, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 170. Further, the memory 1701 may include both internal and external storage units of the computer device 170. The memory 1701 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 1701 can also be used to temporarily store data that has been output or will be output.

[0190] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0191] This application provides a computer program product that, when run on a computer device, enables the computer device to perform the steps described in the above-described method embodiments.

[0192] The embodiments described above are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method of predicting the extent of cracking of a self-piercing riveted rivet, characterized by, include: Obtain the historical round hole punching features of the target plate after it has been punched with round holes, wherein the target plate is a plate with the same thickness and material as the plate to be riveted. Obtain a rivet feature image of the target sheet after self-piercing riveting, wherein the target sheet is used as the lower layer material in self-piercing riveting, and the rivet feature image is obtained by scanning the lower side of the target sheet; Based on the rivet feature image, the historical rivet cracking degree value is determined, and the historical round hole punching feature and the historical rivet cracking degree value correspond one-to-one; Based on the historical circular hole punching characteristics and the historical rivet cracking degree values, a target relationship model is determined. Obtain the current round hole punching feature of the plate to be riveted, wherein the plate to be riveted is the lower plate material in the self-punching riveting connection material, and the current round hole punching feature is formed after the plate to be riveted is punched with a round hole; The target relationship model is used to process the current round hole punching feature to predict the predicted rivet cracking degree value when the plate to be riveted is self-punched. The target relationship model is determined based on multiple historical round hole punching features and multiple historical rivet cracking degree values ​​corresponding to the plate to be riveted. The target relationship model is used to characterize the correspondence between the round hole punching feature and the rivet cracking degree value of the plate to be riveted. Wherein, after the target sheet is punched with a circular hole, a circular hole is formed on the target sheet, and a cylindrical fragment separated from the target sheet is obtained. The historical circular hole punching feature includes at least one of the historical circular hole feature and the historical fragment feature. The historical circular hole feature is characterized by at least one of the length of the rounded corner band of the circular hole, the length of the bright band of the circular hole, the length of the fracture band of the circular hole, and the length of the burr of the circular hole. The historical fragment feature is characterized by at least one of the length of the rounded corner band of the fragment, the length of the bright band of the fragment, the length of the fracture band of the fragment, and the length of the burr of the fragment.

2. The method as described in claim 1, characterized in that, The step of determining the historical rivet cracking degree value based on the rivet feature image includes: The feature values ​​of the target plate are obtained from the rivet feature image. The feature values ​​are used to characterize the cracking features of the rivet. The feature values ​​include one or more of the following: number of cracks, crack area, and area of ​​crack-free region. The degree of cracking of the historical rivets is determined based on the characteristic value.

3. The method as described in claim 2, characterized in that, Determining the historical rivet cracking degree value based on the feature value includes: Calculate the ratio of the crack area to the area of ​​the crack-free region; The product of the ratio and the number of cracks is used as the historical rivet cracking degree value.

4. The method as described in claim 2, characterized in that, The step of obtaining the feature values ​​of the target sheet from the rivet feature image includes: After edge detection and noise reduction processing of the rivet feature image, cracked and crack-free areas are identified from the rivet feature image; Based on the identified cracked and crack-free areas, the number of cracks, the area of ​​the cracks, and the area of ​​the crack-free areas are determined.

5. The method according to any one of claims 2-4, characterized in that, The determination of the target relationship model based on the historical circular hole punching characteristics and the historical rivet cracking degree values ​​includes: Using the historical round hole punching features and the historical rivet cracking degree values, multiple relational models are obtained by fitting them to multiple preset algorithm models. The target relation model is determined from the plurality of relation models.

6. The method as described in claim 5, characterized in that, The step of determining the target relation model from the plurality of relation models includes: Determine the fitting accuracy for each of the aforementioned relationship models; Based on the fitting accuracy, the target relation model is determined from the multiple relation models.

7. The method as described in claim 1, characterized in that, The method further includes: If the predicted cracking degree of the rivet is greater than the preset threshold, the self-piercing riveting scheme will be adjusted.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-7.

9. A computer program product, characterized in that, When the computer program product is run on a computer device, the computer device performs the method as described in claims 1-7.

Images