Method and device for predicting cracking degree of self-piercing riveting buckle and program product

Abstract

The embodiment of the invention is suitable for the technical field of self-piercing riveting, and provides a method, equipment and program product for predicting the cracking degree of a self-piercing riveting rivet buckle, and the method comprises the steps: obtaining the current circular hole blanking characteristics of a to-be-riveted plate which is a lower-layer plate material in a self-piercing riveting connecting material, the current circular hole blanking characteristic is formed after the to-be-riveted plate is subjected to circular hole blanking; a target relation model is adopted to process the current circular hole blanking characteristics, a predicted rivet buckle cracking degree value of the to-be-riveted plate during self-piercing riveting is obtained through prediction, and the target relation model is determined based on a plurality of historical circular hole blanking characteristics and a plurality of historical rivet buckle cracking degree values corresponding to the to-be-riveted plate. The target relation model is used for representing the corresponding relation between the circular hole blanking characteristics of the to-be-riveted plate and the rivet buckle cracking degree value. By means of the method, prediction of the cracking degree of the rivet buckle can be achieved under the condition that the whole plate is not damaged.

Description

Technical Field

[0001] The present application belongs to the technical field of self-piercing riveting, and in particular relates to a method, device and program product for predicting the degree of cracking of a self-piercing riveted rivet button. Background Art

[0002] Self-pierce riveting is a cold-joining technique used to connect two or more metal sheets. After a specially designed rivet penetrates the top sheet, the die presses the hollow structure at the end of the rivet, allowing it to expand and penetrate the bottom sheet without piercing the bottom sheet, thus forming a secure joint. Self-pierce riveting technology has applications in various fields. For example, it is used in vehicle manufacturing.

[0003] To improve the lightweighting of body-in-white (BIW) components and enhance vehicle range, steel-aluminum hybrid bodies are becoming the mainstream design approach. Self-pierce riveting technology can be used to safely and effectively connect both pure aluminum and steel-aluminum hybrid parts. During the self-pierce riveting process, a semi-hollow self-piercing rivet pierces the upper sheet and penetrates the lower sheet at a measured depth. During penetration, the lower sheet undergoes significant localized plastic deformation. Due to the insufficient mechanical properties of the lower sheet material, some cracking may occur during penetration.

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

[0005] Currently, determining the degree of rivet button cracking associated with a self-piercing riveting solution involves performing a preset number of self-piercing riveting runs according to the solution. This approach, based on the actual riveting results, can determine the effectiveness of the solution. However, this method requires performing self-piercing riveting to determine the degree of rivet button cracking associated with the solution. This can lead to overall damage to the riveted sheet material, resulting in waste. This method is relatively costly to evaluate the effectiveness of self-piercing riveting solutions. Summary of the Invention

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

[0007] A first aspect of an embodiment of the present application provides a method for predicting the degree of cracking of a self-piercing riveted rivet button, comprising:

[0008] Acquire a current circular hole punching feature of a plate to be riveted, the plate to be riveted being a lower plate material in a self-piercing riveted connection material, the current circular hole punching feature being formed after the plate to be riveted is circular hole punched;

[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 sheet to be riveted is self-piercing riveted. 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 to be riveted. The target relationship model is used to characterize the correspondence between the circular hole punching feature of the sheet to be riveted and the rivet cracking degree value.

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

[0011] Acquire a plurality of the historical circular hole punching features and a plurality of the historical rivet button cracking degree values ​​corresponding to the plate to be riveted, wherein the historical circular hole punching features and the historical rivet button cracking degree values ​​correspond to each other one by one;

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

[0013] In a possible implementation, obtaining the plurality of historical circular hole punching features and the plurality of historical rivet cracking degree values ​​corresponding to the sheet material to be riveted includes:

[0014] Acquiring historical circular hole punching features of a target plate after being circular hole punched, wherein the target plate is a plate having the same thickness and the same material as the plate to be riveted;

[0015] Acquire a rivet feature image of the target plate after self-pierce riveting, wherein the target plate serves as a lower plate material in the self-pierce riveting, and the rivet feature image is obtained by scanning the lower plate side of the target plate;

[0016] The historical rivet button cracking degree value is determined based on the rivet button characteristic image.

[0017] In a possible implementation, after the target plate is punched by the circular hole, a circular hole is formed on the target plate, and a cylindrical fragment separated from the target plate is obtained. The historical circular hole punching feature includes at least one of a historical circular hole feature and a historical fragment feature. The step of obtaining the historical circular hole punching feature of the target plate after the circular hole punching includes:

[0018] Determine at least one of the length of the rounded corner zone of the round hole, the length of the bright zone of the round hole, the length of the broken zone of the round hole, and the length of the burr of the round hole, wherein the historical round hole feature is characterized by at least one of the length of the rounded corner zone of the round hole, the length of the bright zone of the round hole, the length of the broken zone of the round hole, and the length of the burr of the round hole; and / or,

[0019] Determine at least one of the length of the fragment rounded corner band, the length of the fragment bright band, the length of the fragment broken zone, and the length of the fragment burr of the cylindrical fragment, and the historical fragment feature is characterized by at least one of the length of the fragment rounded corner band, the length of the fragment bright band, the length of the fragment broken zone, and the length of the fragment burr.

[0020] In a possible implementation, determining the historical rivet button cracking degree value based on the rivet button characteristic image includes:

[0021] Acquiring characteristic values ​​of the target plate from the rivet feature image, wherein the characteristic values ​​are used to characterize cracking characteristics of the rivet, and the characteristic values ​​include one or more of the number of cracks, the crack area, and the area of ​​a crack-free region;

[0022] The historical rivet cracking degree value is determined according to the characteristic value.

[0023] In a possible implementation, determining the historical rivet cracking degree value according to the characteristic value includes:

[0024] Calculating a ratio of the crack area divided by the crack-free area;

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

[0026] In a possible implementation, obtaining the characteristic value of the target plate from the rivet characteristic image includes:

[0027] After performing edge detection and noise reduction processing on the rivet button feature image, identifying crack and non-crack areas from the rivet button feature image;

[0028] The number of cracks, the area of ​​the cracks and the area of ​​the non-crack region are determined based on the identified cracks and non-crack region.

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

[0030] Using the historical circular hole punching characteristics and the historical rivet cracking degree values, fitting is performed in multiple preset algorithm models to obtain multiple relationship models;

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

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

[0033] Determining the fitting accuracy corresponding to each of the relationship models;

[0034] Based on the fitting accuracy, the target relationship model is determined from the plurality of relationship models.

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

[0036] If the predicted rivet button cracking degree value is greater than a preset threshold, the self-piercing riveting scheme is adjusted.

[0037] A second aspect of the embodiments of the present application provides a device for predicting the degree of cracking of a self-piercing riveted rivet button, comprising:

[0038] an acquisition module, configured to acquire a current circular hole punching feature of a plate to be riveted, wherein the plate to be riveted is a lower plate material in a self-piercing riveted connection material, and the current circular hole punching feature is formed after the plate to be riveted is circular hole punched;

[0039] A prediction module is configured to process the current circular hole punching feature using a target relationship model to predict a predicted rivet button cracking degree value when the sheet to be riveted is subjected to self-piercing riveting, wherein the target relationship model is determined based on a plurality of historical circular hole punching features and a plurality of historical rivet button cracking degree values ​​corresponding to the sheet to be riveted, and the target relationship model is configured to characterize a correspondence between the circular hole punching feature of the sheet to be riveted and the rivet button cracking degree value.

[0040] A third aspect of an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in the first aspect or any possible implementation of the first aspect is implemented.

[0041] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect or any possible implementation of the first aspect is implemented.

[0042] A fifth aspect of the embodiments of the present application provides a computer program product. When the computer program product is run on a computer device, the computer device executes the method described in the first aspect or any possible implementation of the first aspect.

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

[0044] By applying the method in the embodiment of the present application, the degree of cracking of the self-piercing riveted rivets can be predicted based on the circular hole punching characteristics of the sheet to be riveted after the circular hole punching. When predicting the degree of cracking of the self-piercing riveted rivets, it is only necessary to perform circular hole punching on the sheet to be riveted to form a small circular hole on the sheet to be riveted, thereby obtaining the circular hole punching characteristics. When predicting the degree of cracking of the self-piercing riveted rivets, the sheet to be riveted can be not destroyed as a whole, and the sheet to be riveted after the circular hole punching can continue to be used in production, thereby not causing waste of sheet materials. Based on the method in the embodiment of the present application, when performing process design, for the designed self-piercing riveting scheme, the degree of cracking of the self-piercing riveted rivets can be predicted without performing actual self-piercing riveting, thereby reducing the investment cost of process development and improving process development efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art.

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

[0047] Figure 2 This is a schematic flow chart of the steps of a method for predicting the degree of cracking of a self-piercing riveted rivet provided in an embodiment of the present application;

[0048] Figure 3 is a flowchart of determining the target relationship model provided by an embodiment of the present application;

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

[0050] Figure 5 This is a schematic diagram of a circular hole and a cylindrical fragment formed after a circular hole is punched, as provided in an embodiment of the present application;

[0051] Figure 6 This is a schematic diagram of a circular hole punching characteristic value provided by an embodiment of the present application;

[0052] Figure 7 This is a schematic diagram of a self-piercing riveted connection provided by an embodiment of the present application;

[0053] Figure 8 This is a schematic diagram of a rivet feature image provided by an embodiment of the present application;

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

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

[0056] Figure 11 This is a schematic diagram of a rivet cracking characteristic provided by an embodiment of the present application;

[0057] Figure 12 1 is a flow chart of another method for predicting the degree of cracking of self-piercing riveted rivets provided in an embodiment of the present application;

[0058] Figure 13 This is a rendering of the circular hole punching and self-piercing riveting effect of the same set of sheets provided in an embodiment of the present application;

[0059] Figure 14 This is a photo of a circular hole punching fragment and an original photo and a processed photo of a self-piercing riveted rivet provided in an embodiment of the present application;

[0060] Figure 15 This is a scatter plot of the corresponding values ​​of the cracking degree of a rivet button and the proportion of the bright band of the debris provided in an embodiment of the present application;

[0061] Figure 16 Schematic diagram of a device for predicting the degree of cracking of a self-piercing riveted rivet provided in an embodiment of the present application;

[0062] Figure 17 This is a schematic diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present application with unnecessary details.

[0064] To ensure vehicle safety, material cracking caused by self-piercing riveting must be avoided during body-in-white manufacturing. Existing solutions can reduce the risk of joint cracking by optimizing the rivet die size to match the material flow of the underlying panel during the riveting process. While optimizing the die size can reduce material cracking, it also affects the interlocking of the joint, so this approach cannot guarantee a comprehensive improvement in joint quality.

[0065] In addition, the plastic deformation properties of the material can be optimized, thereby avoiding material cracking caused by self-piercing riveting without affecting the connection quality. For example, infrared halogen and ultrasonic vibration can be used to heat the connected metal plates to improve the plastic forming ability of the metal material, thereby reducing the cracking caused by self-piercing riveting and improving the riveting quality when using traditional riveting dies. Thermal assistance is an effective method to reduce joint cracking, but due to the long heating process, the use scenarios of this method have certain limitations. When responding to large-scale production needs, the material properties are adapted and optimized for the selected self-piercing riveting technology from the material design and production links, thereby avoiding material cracking from the root. In order to achieve this goal, it is necessary to accurately grasp the correspondence between material properties and the degree of self-piercing riveting cracking.

[0066] In light of this, embodiments of the present application provide a method for predicting the degree of rivet cracking in self-piercing riveted joints based on circular hole punching information of the connecting material. By understanding the mechanical properties of the material through circular hole punching and utilizing the established correspondence between circular hole punching characteristics and the degree of rivet cracking in self-piercing riveted joints, the degree of self-piercing riveted cracking can be predicted using circular hole punching of the part before self-piercing riveting is performed, thereby enabling targeted optimization of the part's design and performance.

[0067] Self-pierce riveting can connect two or more metal sheets. Figure 1 This is a schematic diagram of material overlap of self-piercing riveting provided in an embodiment of the present application. Figure 1 , the self-pierce riveting of two sheet materials and the self-pierce riveting of three sheet materials are shown. Figure 1 11 is a two-layer lapped upper plate, 12 is a two-layer lapped lower plate; 21 is a three-layer lapped upper plate, 22 is a three-layer lapped middle plate, and 23 is a three-layer lapped lower plate. The plate to be riveted in the embodiment of the present application is the lower plate material in the self-piercing riveting connection material, that is, Figure 1 12 or 23 in. Figure 1 As shown, after self-piercing riveting, the lower plate material can form a rivet. The rivet refers to the protrusion formed on the back of the connection position after riveting is completed using rivets. The rivet is a result of plastic deformation of the lower plate material. The degree of cracking of the rivet can characterize the connection effect of the self-piercing riveting. The embodiments of this application use 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 method in the embodiments of the present application can be applied to computer devices, which may include but are not limited to personal computers (PCs), smart phones, netbooks, tablet computers, smart cameras, PDAs, personal digital assistants (PDAs), portable multimedia players (PMPs), augmented reality (AR) / virtual reality (VR) devices, mixed reality (MR) devices, smart watches, smart glasses, vehicle-mounted terminals, servers, and other terminal devices. The embodiments of the present application do not limit the specific type of computer devices.

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

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

[0071] Reference Figure 2 , shows a schematic flow chart of the steps of a method for predicting the degree of cracking of a self-piercing riveted rivet button provided in an embodiment of the present application, which may specifically include the following steps:

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

[0073] The sheet to be riveted can serve as the lower sheet material in a self-pierce riveting scheme. The self-pierce riveting scheme specifies the sheet material and thickness for each layer. The sheet to be riveted has a specified material and thickness. For example, the sheet to be riveted can be a part in a process design. For example, the sheet to be riveted can be a body-in-white.

[0074] The current circular hole punching feature can be obtained by punching a circular hole in the sheet to be riveted using a specified circular hole punching tool before self-piercing riveting. The specified circular hole punching tool can be a punch or die of a specified size.

[0075] After the circular hole punching is performed on the sheet to be riveted, a circular hole can be formed on the sheet to be riveted, and a cylindrical fragment separated from the sheet to be riveted can be obtained. Based on the characteristics of the circular hole and the cylindrical fragment, the current circular hole punching characteristics can be obtained. The current circular hole punching characteristics can include the current circular hole characteristics and / or the current fragment characteristics. The current circular hole characteristics can be characterized by at least one of the rounded corner band characteristics, bright band characteristics, fracture band characteristics, and burr characteristics of the circular hole. The current fragment characteristics can be characterized by at least one of the rounded corner band characteristics, bright band characteristics, fracture band characteristics, and burr characteristics of the fragment. Among them, the rounded corner band characteristics, bright band characteristics, fracture band characteristics, and burr characteristics can be characterized by formulating parameters respectively. For example, the characteristic values ​​of the rounded corner band characteristics, bright band characteristics, fracture band characteristics, and burr characteristics can be divided into the rounded corner band length, the bright band length, the fracture band length, and the burr length.

[0076] After punching a circular hole in the sheet to be riveted, the current circular hole punching characteristics can be obtained. These characteristics can be measured by a professional measuring tool and input into a computer. Alternatively, the current circular hole punching characteristics can be obtained by performing image processing on the computer based on images of the circular hole and the residual piece. This is not limited here.

[0077] S202: Process the current circular hole punching feature using a target relationship model to predict a predicted rivet button cracking degree value when the sheet to be riveted undergoes self-piercing riveting. The target relationship model is determined based on multiple historical circular hole punching features and multiple historical rivet button cracking degree values ​​corresponding to the sheet to be riveted. The target relationship model is used to characterize the corresponding relationship between the circular hole punching feature of the sheet to be riveted and the rivet button cracking degree value.

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

[0079] In one possible implementation, a relational model database may be provided, which may include multiple relational models. These multiple relational models may be used to characterize the correspondence between the circular hole punching characteristics of the sheets to be riveted and the cracking degree values ​​of the self-piercing riveted buttons, including those of different materials, thicknesses, and overlap configurations. Based on the material, thickness, and overlap configuration of the sheets to be riveted, a target relational model may be determined from the relational model database.

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

[0081] As another example, the target relationship model may 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 the relational expression, the corresponding predicted rivet cracking degree value can be obtained.

[0082] It can be understood that when performing circular hole punching and self-piercing riveting on sheets with the same characteristics, due to the identical material properties and their identical deformation characteristics, the circular hole punching characteristics can reflect the sheet's deformation characteristics, and the self-piercing riveted rivet cracking degree value can also reflect the sheet's deformation characteristics. Since the corresponding deformation characteristics of the sheets are consistent, a model can be established based on the circular hole punching characteristics and the self-piercing riveted rivet cracking degree value, thereby obtaining a target relationship model between the circular hole punching characteristics and the rivet cracking degree value. Based on the established target relationship model, circular hole punching can be performed on the sheet to be riveted without self-piercing riveting. Based on the circular hole punching characteristics and the target relationship model, a predicted rivet cracking degree value can be obtained. The predicted rivet cracking degree value can represent the cracking risk of the sheet to be riveted. That is, after obtaining the predicted rivet cracking degree value, the riveter can determine whether the risk of cracking after self-piercing riveting based on the current self-piercing riveting scheme is too high, and thus determine whether to adjust the self-piercing riveting scheme.

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

[0084] The above target relationship model can be Figure 3 Determined by the method shown. Figure 3 , shows a schematic diagram of a process for determining the target relationship model provided by an embodiment of the present application, which may specifically include the following steps:

[0085] S301 : Acquire a plurality of historical circular hole punching features and a plurality of historical rivet button cracking degree values ​​corresponding to the sheet material to be riveted, wherein the historical circular hole punching features and the historical rivet button cracking degree values ​​correspond to each other one by one.

[0086] The computer device can obtain the historical round hole punching characteristics of the target plate after the round hole is punched, and the target plate is a plate with the same thickness and the same material as the plate to be riveted.

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

[0088] After the target plate is punched by the circular hole, a circular hole is formed on the target plate, and a cylindrical fragment separated from the target plate is obtained. Figure 5 This is a schematic diagram of a circular hole and cylindrical fragment formed after a circular hole is punched out, as provided in an embodiment of the present application. Figure 5 51 is the round hole fillet band, 52 is the round hole bright band, 53 is the round hole fracture band, 54 is the round hole burr, 55 is the fragment rounded band, 56 is the fragment bright band, 57 is the fragment fracture band, 58 is the fragment burr, and 59 is the round hole diameter. The historical round hole punching feature includes at least one of the historical round hole feature and the historical fragment feature. The historical round hole feature is characterized by at least one of the length of the round hole fillet band, the length of the round hole bright band, the length of the round hole fracture band, and the length of the round hole burr. The historical fragment feature is characterized by at least one of the length of the fragment rounded band, the length of the fragment bright band, the length of the fragment fracture band, and the length of the fragment burr.

[0089] In one possible implementation, a preset number of parameters can be selected from the following: 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 fractured zone of the circular hole, the length of the burr of the circular hole, the length of the rounded corner band of the residual piece, the length of the bright band of the residual piece, the length of the fractured zone of the residual piece, and the length of the burr of the residual piece to represent the historical circular hole punching characteristics. For example, the length of the bright band of the residual piece can be selected as the historical circular hole punching characteristic. The computer device can only obtain the length of the bright band of the residual piece.

[0090] In another possible implementation, the computer device can obtain each parameter value of the round hole fillet band length, the round hole bright band length, the round hole broken band length, the round hole burr length, the fragment fillet band length, the fragment bright band length, the fragment broken band length, and the fragment burr length, so that multiple modeling can be performed based on the parameters.

[0091] The aforementioned lengths of the rounded corner zone, the bright zone, the fracture zone, the burr, the rounded corner zone, the bright zone, the fracture zone, and the burr can be measured using a measuring instrument or identified from an image. The maximum length determined can be the average of the maximum and minimum lengths. For example, the average of the maximum and minimum values ​​of the bright zone can be used as the bright zone length. The average of the maximum and minimum values ​​of the fracture zone can be used as the fracture zone length.

[0092] Figure 6 This is a schematic diagram of a circular hole punching characteristic value provided by an embodiment of the present application; Figure 6 Among them, 621 is the minimum value of the bright zone, 622 is the maximum value of the bright zone, 631 is the maximum value of the fracture zone, and 632 is the minimum value of the fracture zone.

[0093] Figure 7 This is a schematic diagram of a self-piercing riveted connection provided in an embodiment of the present application. Figure 7 70 is the rivet, 71 is the head height, 72 is the interlocking value, 73 is the minimum bottom thickness, 74 is the upper plate thickness, 75 is the lower plate thickness, and 76 is the riveting die. Figure 7 As shown in the figure, after self-pierce riveting, the lower plate side will deform, and this deformation can represent the cracking characteristics of the rivet button. Therefore, when obtaining the historical cracking characteristic values ​​of the rivet button, the rivet button feature image can be collected.

[0094] The computer device can scan the lower side of the target plate using a camera or optical scanning device to capture a characteristic image of the rivet button after self-pierce riveting. The characteristic image of the rivet button can also be input into the computer device by a user or sent to the computer device by other devices.

[0095] The target sheet material is used as the lower sheet material in self-pierce riveting. The rivet feature image includes cracking characteristics of the rivet formed on the target sheet material after self-pierce riveting. The rivet cracking characteristics can be characterized by characteristic values, which can include one or more of the number of cracks, crack area, and crack-free area.

[0096] Figure 8 is a schematic diagram of a rivet feature image provided by an embodiment of the present application, wherein: Figure 8801 is a crack and 802 is a noise point. In order to facilitate processing of the rivet button feature image, the rivet button feature image can be processed, for example, edge recognition and noise reduction processing can be performed.

[0097] Among them, edge recognition can use the Gaussian difference principle to achieve edge detection by calculating the difference between Gaussian blurred images at different scales ( Figure 8 ).

[0098] The expression of Gaussian difference DoG is:

[0099] DoG(x,y)=G(x,y,σ1)-G(x,y,σ2)

[0100] Among them, σ1 and σ2 are standard deviations of two different scales. The expression of Gaussian function is:

[0101]

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

[0103] Furthermore, you can also perform a convolution operation on the image using an edge operator to calculate the gradient of each pixel in the image and identify edge information in the image by comparing it with a threshold. 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:

[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 be achieved by using methods including but not limited to mean filtering, median filtering, Gaussian filtering, and bilateral filtering. By using noise reduction, features not related to cracks are removed 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 by an embodiment of the present application; Figure 10 This is a schematic diagram of a rivet feature image after noise reduction processing provided in an embodiment of the present application.

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

[0113] Figure 11 In the figure, 801 is the crack, 803 is the bottom of the rivet button, and 804 is the crack-free area at the bottom of the rivet button. Figure 11 The crack-free region in is the largest circle that does not include cracks. In this embodiment, a circle is used as the crack-free region to illustrate the solution. The shape of the crack-free region can include but is not limited to a circle.

[0114] Based on the identified cracks and crack-free areas, the number of cracks, crack area and crack-free area are determined.

[0115] The computer device determines a historical rivet button cracking degree value based on the rivet button cracking characteristics. The historical rivet button 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 device can calculate the ratio of the crack area divided by the area of ​​the crack-free region; then, the product of the ratio and the number of cracks is used as the historical rivet button cracking degree value. For example, the calculation consensus of the rivet button cracking degree value (Fracture grad) can be as follows:

[0116] Fracture grad=n*s1 / s2

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

[0118] S302: Determine the target relationship model based on the historical round hole punching features and the historical rivet cracking degree values.

[0119] The computer device can use historical circular hole punching characteristics and historical rivet cracking degree values ​​to fit multiple preset algorithm models to obtain multiple relationship models. A target relationship model can then be determined from the multiple relationship models. For example, the fitting accuracy corresponding to each relationship model can be determined; based on the fitting accuracy, the target relationship model can be determined from the multiple relationship models.

[0120] Among them, fitting the circular hole punching and self-piercing riveting data and establishing the target relationship model means that by collecting a certain amount of circular hole punching feature data (independent variable) and self-piercing riveting rivet cracking degree data (dependent variable), a linear or nonlinear relationship between the independent variable and the dependent variable is established. In order to obtain the fitting accuracy value R 2 >0.9, the independent variable and the dependent variable can be subjected to appropriate mathematical transformations such as reciprocal, exponential, logarithmic, etc.

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

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

[0123] In another possible implementation, a neural network, such as a convolutional network, can also be used. The historical hole punching features can be feature vectors determined based on the length of the hole fillet band, the length of the hole polished band, the length of the hole fractured band, the length of the hole burr, the length of the fragment fillet band, the length of the fragment polished band, the length of the fragment fractured band, and the length of the fragment burr. Based on these historical hole punching features and the historical rivet cracking degree values, a training dataset and a test dataset are determined, thereby generating a prediction model based on the training and test datasets. This prediction model is the target relationship model described above. This prediction model can also use an attention mechanism to determine the weights corresponding to each feature, which represents the degree of influence of each feature on the prediction of the rivet cracking degree value.

[0124] The above method can be used to determine the impact of the lower plate material properties on the degree of rivet cracking in a material overlap combination under the standard self-piercing riveting process. By varying the upper plate material grade, upper plate material thickness, and lower plate material thickness, the above-disclosed method can be used to conduct a full-domain analysis, thereby determining the corresponding relationship between the lower plate circular hole punching characteristic value and the degree of rivet cracking under the standard self-piercing riveting process under different material overlap conditions. Utilizing this result, when determining the risk of self-piercing riveting cracking in a material, the degree of rivet cracking can be predicted by punching the circular hole of the lower plate material, avoiding complex and tedious self-piercing riveting experiments and improving process development efficiency.

[0125] Based on the circular hole punching characteristics of the sheet to be riveted after the circular hole punching, the degree of cracking of the self-piercing riveted rivets is predicted. When predicting the degree of cracking of the self-piercing riveted rivets, it is only necessary to perform circular hole punching on the sheet to be riveted to form a small circular hole on the sheet to be riveted, thereby obtaining the circular hole punching characteristics. When predicting the degree of cracking of the self-piercing riveted rivets, the sheet to be riveted can be not destroyed as a whole, and the sheet to be riveted after the circular hole punching can continue to be used in production, thereby not causing waste of sheet materials. Based on the method in the embodiment of the present application, when performing process design, for the designed self-piercing riveting scheme, the degree of cracking of the self-piercing riveted rivets can be predicted without performing actual self-piercing riveting, thereby reducing the investment cost of process development and improving process development efficiency.

[0126] The method in this embodiment can assess the risk of cracking in self-pierce rivets of different parts without destroying the entire part or actually connecting them. After testing, the parts can still be put into normal production, reducing material waste.

[0127] Figure 12 This is a flow chart of another method for predicting the degree of cracking of self-piercing riveted rivets provided in an embodiment of the present application. Figure 12 As shown in the figure, before making a prediction, the connection material overlap combination can be determined, the circular hole punching and self-piercing riveting tests can be performed on the material overlap, the circular hole punching and self-piercing riveting data can be fitted, and the target relationship model can be established.

[0128] First, the material combination for the overlap must be determined. Specifically, for a two-layer overlap, the material grade, thickness, and thickness of the upper and lower layers can be fixed, and lower layers with different mechanical properties can be selected. For a three-layer overlap, the material grade, thickness, and thickness of the upper and middle layers, as well as the thickness of the lower layer, can be fixed, and lower layers with different mechanical properties can be selected. These mechanical properties include, but are not limited to, tensile strength and elongation at break.

[0129] The next step is to perform circular hole punching, which includes: test tool selection, circular hole punching testing, and quantifying circular hole punching characteristics.

[0130] Test tool selection involves determining the punch and die dimensions required to punch a circular hole based on the thickness of the test plate. The test plate refers to the lower plate in a self-piercing riveted joint. The die inner diameter D2 must be greater than the punch diameter D1; the punch diameter D1 must be ≤ 1.5 × the test plate thickness t; and the blanking gap d must be equal to a × the test plate thickness t, where a = 10% to 20%.

[0131] The round hole punching test involves punching a round hole in a test sheet using a selected punch and die combination with a press. This process results in a round through-hole being formed in the test sheet and a cylindrical fragment being detached from the sheet.

[0132] Quantifying blanking features means determining key characteristic length values ​​such as the fillet length L1, bright band length L2, fracture band length L3 and burr length L4 of the fragment or the fillet length L5, bright band length L6, fracture band length L7 and burr length L8 of the through hole by means of optical measurement.

[0133] Next, self-pierce riveting can be performed, which specifically includes: determining the material overlap combination of the self-pierce riveted connection, collecting the rivet feature image, image processing, and quantifying the rivet cracking characteristics.

[0134] Determining the material overlap combination for self-pierce riveting involves selecting the appropriate rivet and die combination based on the overlapping characteristics of the materials being joined, and using riveting equipment to achieve a self-pierce riveted connection that meets the requirements. These overlapping characteristics include the thickness and grade of the materials being joined. A satisfactory self-pierce riveted connection means that the head height, interlock value, and minimum base thickness meet the process standards.

[0135] Capturing the rivet feature image means photographing or scanning the lower plate side of the overlapped material after self-pierce riveting with the aid of an optical device to obtain the surface features of the rivet.

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

[0137] Next, the cracking characteristics of the rivet button can be quantified, specifically by quantitatively describing the degree of cracking of the rivet button through the rivet button crack quantification.

[0138] Next, we can fit the circular hole punching and self-piercing riveting data and establish a target relationship model. Specifically, we collect a certain amount of circular hole punching feature data (independent variable) and self-piercing riveting rivet cracking degree data (dependent variable) to establish a linear or nonlinear relationship between the independent variable and the dependent variable. In order to obtain the fitting accuracy value R 2 >0.9, the independent variable and the dependent variable can be subjected to appropriate mathematical transformations such as reciprocal, exponential, logarithmic, etc.

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

[0140] The material overlap used in this embodiment is CR02 (t = 1.5mm) - a heat-free die-cast aluminum (t = 3.0mm). Due to the influence of the material die-casting process, different batches of the same brand of heat-free die-cast aluminum have different mechanical properties. The size of the heat-free die-cast aluminum test piece is 80x200mm, and the size of the CR02 test piece is 40x100mm. In the test, the circular hole punching and self-piercing riveting position are Figure 13 shown.

[0141] For round hole punching, a 6mm diameter punch and a 6.6mm inner diameter die were used, and the punching speed remained constant across all tests. For self-pierce riveting, rivet model M260468 and rivet type C5.3x6.0H2 were used, with the head height set to 0. The riveting speed remained constant across all tests.

[0142] Photos of the fragments produced by round hole punching, photos of the rivet buttons after self-piercing riveting, and photos of the rivet buttons after edge recognition and noise reduction processing are shown below. Figure 14 As shown. Among them, the fragment cross-section photos produced by round hole punching are Figure 14 Photos of the round hole punching fragments and photos of the rivet buttons after self-piercing riveting Figure 14 The self-piercing riveted rivet photos in the image are processed by edge recognition and noise reduction. Figure 14 Edge-aware noise reduction in photos.

[0143] like Figure 14 As shown in the figure, based on the edge recognition and noise reduction processing of the rivet buckle photo, the crack area, the area of ​​the crack-free area, and the number of cracks can be obtained. Based on the circular hole punching fragment photo, the length information of the bright band and the broken 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 480.2um, the minimum length of the bright band is 56.5um, the minimum length of the broken band is 2401.0um, and the maximum length of the broken band is 2740.1um; in the second image of the circular hole punching fragment, the minimum length of the bright band is 79.1um, the maximum length of the bright band is 576.3um, the maximum length of the broken band is 2638.4um, and the minimum length of the broken band is 2214.7um; in the third image of the circular hole punching fragment, the minimum length of the bright band is 190.9um, the maximum length of the bright band is 627.3um, the maximum length of the broken band is 2536.40um, and the minimum length of the broken band is 1936.4 um; in the fourth image of the circular hole punching fragment photo, the maximum length of the bright band is 609.1um, the minimum length of the bright band is 109.1um, the minimum length of the broken band is 2318.2um, and the maximum length of the broken band is 2772.7um; in the fifth image of the circular hole punching fragment photo, the maximum length of the bright band is 245.5um, the minimum length of the bright band is 45.5um, the maximum length of the broken band is 2727.3um, and the minimum length of the broken band is 2609.1um; in the sixth image of the circular hole punching fragment photo, the maximum length of the bright band is 545.5um, the minimum length of the bright band is 63.6um, the minimum length of the broken band is 2190.9um, and the maximum length of the broken band is 2827.3um.

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

[0146] Table 1

[0147]

[0148] Through the data, we can get the corresponding target relationship model between the rivet buckle fracture degree Fracture grad (dependent variable y) of the standard self-piercing riveting and the length ratio of the bright band of the die-cast aluminum material obtained after the circular hole punching (independent variable x) when the material overlap is CR02 (t = 1.5mm) - a heat-treatment-free die-cast aluminum (t = 3.0mm). Figure 15 As shown. Among them:

[0149] y=-436.61x+61.154

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

[0151] The method proposed in this embodiment establishes a correlation between the circular hole punching characteristics and the degree of cracking in self-piercing rivets for different material overlap combinations. When assessing the risk of self-piercing rivet cracking in new projects, circular hole punching tests can be performed directly on the materials. The circular hole punching characteristics can be used to predict the degree of cracking in self-piercing rivets for different material overlap conditions. This method eliminates the need for self-piercing rivet testing, reduces equipment investment, and improves process development efficiency.

[0152] The method in this embodiment can assess the risk of cracking in self-pierce rivets of different parts without destroying the entire part or actually connecting them. After testing, the parts can still be put into normal production, reducing material waste.

[0153] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean 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 , which shows a schematic diagram of a device for predicting the cracking degree of a self-piercing riveted rivet button provided by an embodiment of the present application, which may specifically include an acquisition module 1601 and a prediction module 1602, wherein:

[0155] An acquisition module 1601 is configured to acquire a current circular hole punching feature of a plate to be riveted, wherein the plate to be riveted is a lower plate material in a self-piercing riveted connection material, and the current circular hole punching feature is formed after the plate to be riveted is circular hole punched;

[0156] Prediction module 1602 is configured to process the current circular hole punching feature using a target relationship model to predict a predicted rivet button cracking degree value when the sheet to be riveted is subjected to self-piercing riveting. The target relationship model is determined based on multiple historical circular hole punching features and multiple historical rivet button cracking degree values ​​corresponding to the sheet to be riveted. The target relationship model is configured to characterize the correspondence between the circular hole punching feature of the sheet to be riveted and the rivet button cracking degree values.

[0157] In a possible implementation, the apparatus further includes:

[0158] a historical data acquisition module, configured to acquire a plurality of historical circular hole punching features and a plurality of historical rivet button cracking degree values ​​corresponding to the sheet material to be riveted, wherein the historical circular hole punching features and the historical rivet button cracking degree values ​​correspond to each other in a one-to-one manner;

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

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

[0161] A historical circular hole punching feature acquisition submodule is used to acquire the historical circular hole punching features of the target plate after the circular hole is punched, wherein the target plate is a plate having the same thickness and the same material as the plate to be riveted;

[0162] a rivet feature image acquisition submodule, configured to acquire a rivet feature image of the target plate after self-pierce riveting, wherein the target plate serves as the lower plate material in the self-pierce riveting, and the rivet feature image includes rivet cracking features formed on the target plate after the self-pierce riveting;

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

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

[0165] a first determining unit, configured to determine at least one of a length of a rounded corner zone, a length of a bright zone, a length of a fracture zone, and a length of a burr of the round hole, wherein the historical round hole feature is characterized by at least one of the length of the rounded corner zone, the length of the bright zone, the length of the fracture zone, and the length of the burr of the round hole; and / or

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

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

[0168] a rivet cracking feature acquisition unit, configured to acquire a feature value of the target plate from the rivet feature image, wherein the feature value is used to characterize the rivet cracking feature, and the feature value includes one or more of the number of cracks, the crack area, and the area of ​​a crack-free region;

[0169] The historical rivet button cracking degree value determining unit is used to determine the historical rivet button cracking degree value according to the characteristic value.

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

[0171] a ratio calculation subunit, configured to calculate a ratio of the crack area divided by the crack-free area;

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

[0173] In a possible implementation, the rivet cracking feature acquisition unit includes:

[0174] The edge detection subunit is used to perform edge detection on the rivet feature image to obtain the deformation area image of the target plate.

[0175] an identification subunit, configured to identify cracked and crack-free areas from the deformed area image;

[0176] The determination subunit is used to determine the number of cracks, the crack area and the area of ​​the crack-free area based on the identified cracks and crack-free area.

[0177] In a possible implementation, the target relationship model determination module includes:

[0178] A fitting submodule, configured to use the historical circular hole punching characteristics and the historical rivet button cracking degree values ​​to perform fitting in a plurality of preset algorithm models to obtain a plurality of relationship models;

[0179] The determination submodule is used to determine the target relationship model from the multiple relationship models.

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

[0181] A fitting accuracy determination unit, configured to determine a fitting accuracy corresponding to each of the relationship models;

[0182] A determining unit is configured to determine the target relationship model from the plurality of relationship models based on the fitting accuracy.

[0183] In a possible implementation, the apparatus further includes:

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

[0185] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment part.

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

[0187] The computer device 170 may be a desktop computer, a notebook computer, a PDA, a cloud computing device, etc. The computer device may include, but is not limited to, a processor 1700 and a memory 1701. It will be understood by those skilled in the art that Figure 17 This is merely an example of the computer device 170 and does not constitute a limitation on the computer device 170 . The computer device 170 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0188] The processor 1700 may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. 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 also be an external storage device of the computer device 170, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 170. Furthermore, the memory 1701 may also include both an internal storage unit of the computer device 170 and an external storage device. The memory 1701 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 1701 may also be used to temporarily store data that has been output or is about to be output.

[0190] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0191] An embodiment of the present application provides a computer program product. When the computer program product is run on a computer device, the computer device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0192] The above embodiments are intended only to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they may still modify the technical solutions described in the above embodiments or replace some of the technical features therein with equivalents; and such modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application and should be included within the scope of protection of the present application.

Claims

1. A method for predicting the cracking degree of self-piercing riveted rivets, characterized in that: include: Acquire a current circular hole punching feature of a plate to be riveted, the plate to be riveted being a lower plate material in a self-piercing riveted connection material, the current circular hole punching feature being formed after the plate to be riveted is circular hole punched; The target relationship model is used to process the current circular hole punching feature to predict the predicted rivet cracking degree value when the sheet to be riveted is self-piercing riveted. 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 to be riveted. The target relationship model is used to characterize the correspondence between the circular hole punching feature of the sheet to be riveted and the rivet cracking degree value.

2. The method according to claim 1, wherein Before obtaining the current circular hole punching feature of the plate to be riveted, the method further includes: Acquire a plurality of the historical circular hole punching features and a plurality of the historical rivet button cracking degree values ​​corresponding to the plate to be riveted, wherein the historical circular hole punching features and the historical rivet button cracking degree values ​​correspond to each other one by one; The target relationship model is determined based on the historical round hole punching features and the historical rivet cracking degree values.

3. The method according to claim 2, wherein The obtaining of the plurality of historical circular hole punching features and the plurality of historical rivet cracking degree values ​​corresponding to the plate to be riveted includes: Acquiring historical circular hole punching features of a target plate after being circular hole punched, wherein the target plate is a plate having the same thickness and the same material as the plate to be riveted; Acquire a rivet feature image of the target plate after self-pierce riveting, wherein the target plate serves as a lower plate material in the self-pierce riveting, and the rivet feature image is obtained by scanning the lower plate side of the target plate; The historical rivet button cracking degree value is determined based on the rivet button characteristic image.

4. The method according to claim 3, wherein After the target plate is punched by the circular hole, a circular hole is formed on the target plate, and a cylindrical fragment separated from the target plate is obtained. The historical circular hole punching feature includes at least one of a historical circular hole feature and a historical fragment feature. The step of obtaining the historical circular hole punching feature of the target plate after the circular hole punching includes: Determine at least one of the length of the rounded corner zone of the round hole, the length of the bright zone of the round hole, the length of the broken zone of the round hole, and the length of the burr of the round hole, wherein the historical round hole feature is characterized by at least one of the length of the rounded corner zone of the round hole, the length of the bright zone of the round hole, the length of the broken zone of the round hole, and the length of the burr of the round hole; and / or, Determine at least one of the length of the fragment rounded corner band, the length of the fragment bright band, the length of the fragment broken zone, and the length of the fragment burr of the cylindrical fragment, and the historical fragment feature is characterized by at least one of the length of the fragment rounded corner band, the length of the fragment bright band, the length of the fragment broken zone, and the length of the fragment burr.

5. The method according to claim 3, wherein The determining of the historical rivet button cracking degree value based on the rivet button characteristic image includes: Acquiring characteristic values ​​of the target plate from the rivet feature image, the characteristic values ​​being used to characterize cracking characteristics of the rivet, the characteristic values ​​including one or more of the number of cracks, the crack area, and the area of ​​a crack-free region; The historical rivet cracking degree value is determined according to the characteristic value.

6. The method according to claim 5, wherein Determining the historical rivet cracking degree value according to the characteristic value includes: Calculating a ratio of the crack area divided by the crack-free area; The product of the ratio and the number of cracks is used as the historical rivet cracking degree value.

7. The method according to claim 5, wherein The acquiring the characteristic value of the target plate from the rivet characteristic image includes: After performing edge detection and noise reduction processing on the rivet button feature image, identifying crack and non-crack areas from the rivet button feature image; The number of cracks, the area of ​​the cracks and the area of ​​the non-crack region are determined based on the identified cracks and non-crack region.

8. The method according to any one of claims 2 to 7, wherein: The determining of the target relationship model based on the historical round hole punching features and the historical rivet cracking degree values ​​includes: Using the historical circular hole punching characteristics and the historical rivet cracking degree values, fitting is performed in multiple preset algorithm models to obtain multiple relationship models; The target relational model is determined from the plurality of relational models.

9. The method according to claim 8, wherein Determining the target relationship model from the plurality of relationship models includes: Determining the fitting accuracy corresponding to each of the relationship models; Based on the fitting accuracy, the target relationship model is determined from the plurality of relationship models.

10. The method according to claim 1, wherein The method further comprises: If the predicted rivet button cracking degree value is greater than a preset threshold, the self-piercing riveting scheme is adjusted.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 10 is implemented.

12. A computer program product, characterized in that When the computer program product is run on a computer device, the computer device is caused to perform the method according to claims 1 to 10.

Images