Methods, apparatus, and equipment for controlling slippage defects in stamped parts based on coating evaluation
By obtaining the strain and die fillet radius after stamping, and using a machine learning model to evaluate the appearance quality of the slip line after coating, the problem of inaccurate evaluation in the prior art is solved, achieving higher evaluation accuracy and reducing waste.
Patent Information
- Application Number
- CN202510736985.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-04
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2045-06-04
AI Technical Summary
In the existing technology, the accuracy of assessing the impact of slip line defects on the appearance quality of stamped parts after coating is low, resulting in the waste of defective products.
By obtaining the strain and die fillet radius after stamping, a machine learning model is used to predict the quality, determine whether the slip line affects the appearance quality after coating, and decide whether to coat the product based on the prediction results.
It improves the accuracy of assessing the appearance quality of stamped parts after coating by increasing the severity of slip lines, reducing the possibility of defective products, and reducing material waste.
Smart Images

Figure CN120421389B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of sheet metal stamping technology, and particularly relates to a method, device and equipment for controlling slippage defects in stamped parts based on coating evaluation. Background Technology
[0002] In the metal sheet stamping process, slip line defects are one of the main quality defects in stamped parts, directly affecting the visual effect after coating. If the slip line can be covered by the paint film without affecting the appearance quality, the stamped part is considered a qualified product. If the slip line defect cannot be completely covered by the paint film, the coated stamped part is considered a defective product.
[0003] In existing technologies, the impact of slip lines on the appearance quality of stamped parts after coating is judged solely by manual experience before painting. This leads to low accuracy in assessing the impact of slip line severity on the appearance quality of the stamped parts after coating, resulting in a high probability of the coated stamped parts being unqualified and unusable, thus wasting materials. Therefore, the low accuracy of assessing the impact of slip line severity on the appearance quality of stamped parts after coating is a technical problem that urgently needs to be solved. Summary of the Invention
[0004] This invention provides a method, apparatus, and equipment for controlling slippage defects in stamped parts based on coating evaluation, which solves the technical problem of low accuracy in evaluating the impact of slippage severity on the appearance quality of stamped parts after coating.
[0005] In a first aspect, embodiments of the present invention provide a method for controlling slippage defects in stamped parts based on coating evaluation, comprising: after a target die stamps a target stamped part, if slippage lines exist in the stamped target stamped part, obtaining the strain of the target stamped part after stamping; inputting the strain of the target stamped part after stamping and the fillet radius of the target die into a preset quality prediction model to obtain a first prediction result; the quality prediction model is obtained by training a machine learning model based on multiple sets of samples, each set of samples including the strain of historical sample stamped parts after stamping, the fillet radius of the sample die, and the actual result; if the first prediction result is normal, coating the stamped target stamped part; the first prediction result being normal indicates that the slippage lines do not affect the appearance quality of the target stamped part after coating.
[0006] In conjunction with the first aspect of the present invention, in some embodiments, obtaining the strain of the target stamped part after stamping includes: obtaining the maximum height of the contour of the sliding line of the target stamped part after stamping, wherein the maximum height of the contour of the sliding line is the maximum distance between a point on the sliding line and the plane containing the sliding line; inputting the maximum height of the contour of the sliding line and the fillet radius of the target mold into a preset first correspondence relationship to obtain the strain of the target stamped part after stamping; wherein the first correspondence relationship is the correspondence between the maximum height of the contour of the sliding line, the fillet radius of the mold, and the strain of the stamped part after stamping.
[0007] In conjunction with the first aspect of the present invention, in some embodiments, obtaining the maximum height of the sliding line profile of the target stamped part after stamping includes: obtaining the maximum height of the sliding line profile of the target stamped part after stamping by means of a roughness tester.
[0008] In conjunction with the first aspect of the present invention, in some embodiments, the quality prediction model is pre-established through the following steps: acquiring the multiple sets of samples; inputting the strain of the stamped sample part after stamping and the fillet radius of the sample mold of each set of samples into the machine learning model to obtain a second prediction result; determining the loss function of the second prediction result and the actual result; and iteratively optimizing the machine learning model based on the loss function of the second prediction result and the actual result to obtain the quality prediction model.
[0009] In conjunction with the first aspect of the present invention, in some embodiments, the data of each group of samples in the plurality of samples is obtained in advance through the following steps: stamping the sample stamping part using the sample mold of the sample group so that the strain of the sample stamping part after stamping reaches the target strain, and the sample stamping part after stamping has slip lines; applying a coating to the sample stamping part after stamping to obtain the coated sample stamping part; performing a surface visual analysis on the coated sample stamping part to obtain actual results for characterizing the appearance quality of the sample stamping part after coating; and obtaining the data of the sample group based on the target strain of the sample stamping part after stamping, the fillet radius of the sample mold, and the actual results characterizing the appearance quality of the sample stamping part after coating.
[0010] In conjunction with the first aspect of the present invention, in some embodiments, the step of stamping the sample stamping part using the sample die of the set of samples to make the strain of the sample stamping part after stamping reach the target strain includes: inputting the target strain into a preset second correspondence relationship to obtain a target forming height; the second correspondence relationship is the correspondence between the forming height and the strain of the sample stamping part when stamping the sample stamping part; based on the target forming height, controlling the sample die to stamp the sample stamping part to make the strain of the sample stamping part after stamping reach the target strain.
[0011] In conjunction with the first aspect of the present invention, in some embodiments, the step of performing surface visual analysis on the coated sample stamping to obtain actual results characterizing the appearance quality of the sample stamping after coating includes: performing surface visual analysis on the coated sample stamping using a visual analysis system to determine whether there are slip lines on the surface of the coated sample stamping; if there are no slip lines on the surface of the coated sample stamping, the actual result is determined to be normal; if there are slip lines on the surface of the coated sample stamping, the actual result is determined to be abnormal.
[0012] In conjunction with the first aspect of the present invention, in some embodiments, the method further includes: if the first prediction result is abnormal, marking the profile height of the sliding line on the surface of the target stamped part after stamping as abnormal.
[0013] Secondly, embodiments of the present invention provide a stamping part slippage defect control device based on coating evaluation, comprising: a strain acquisition unit, used to acquire the strain of the target stamping part after stamping by a target mold if slippage lines exist in the stamped target stamping part; a prediction unit, used to input the strain of the target stamping part after stamping and the fillet radius of the target mold into a preset quality prediction model to obtain a first prediction result; the quality prediction model is obtained by training a machine learning model based on multiple sets of samples, each set of samples including the strain of historical sample stamping parts after stamping, the fillet radius of the sample mold, and the actual result; and a coating unit, used to coat the stamped target stamping part if the first prediction result is normal; the first prediction result being normal indicates that the slippage lines do not affect the appearance quality of the target stamping part after coating.
[0014] Thirdly, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any of the first aspects.
[0015] The embodiments of the present invention provide one or more technical solutions that achieve at least the following technical effects or advantages: In this embodiment of the invention, after stamping a target stamped part using a target mold, if slip lines exist in the stamped part, the strain of the stamped part after stamping is obtained. The strain of the stamped part and the fillet radius of the target mold are input into a preset quality prediction model to obtain a first prediction result. The quality prediction model is obtained by training a machine learning model based on multiple sets of samples. Each set of samples includes the strain of historical sample stamped parts after stamping, the fillet radius of the sample mold, and the actual result. If the first prediction result is normal, the stamped part is coated. A normal first prediction result indicates that slip lines do not affect the appearance quality of the stamped part after coating. Since the strain of the stamped part and the fillet radius of the target mold are strongly correlated with the deformation of the stamped part, and the deformation of the stamped part affects the degree of slip of the slip lines. Therefore, based on the dependent variable, fillet radius, and quality prediction model, a first prediction result can be determined to characterize whether the slip line affects the appearance quality of the target stamped part after painting. This allows for judging appearance quality based on actual data, avoiding judgment solely based on human experience, and thus achieving the beneficial effect of improving the accuracy of assessing the impact of slip line severity on the appearance quality of stamped parts after painting.
[0016] In addition, determining whether to paint the target stamped part based on the first prediction result reduces the possibility that the painted target stamped part will be a defective product, thereby achieving the beneficial effect of reducing material waste. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart of a stamping part slippage defect control method based on coating evaluation in an embodiment of the present invention; Figure 2 This is a schematic diagram of the mold in an embodiment of the present invention; Figure 3 This is a schematic diagram of the sample stamping part in an embodiment of the present invention; Figure 4 This is a schematic diagram of the measurement direction of the roughness meter in an embodiment of the present invention; Figure 5This is a schematic diagram of the contour curve data of the slip line before correction in an embodiment of the present invention; Figure 6 This is a schematic diagram showing the corrected contour curve data of the slip line in an embodiment of the present invention; Figure 7 This is a curve showing the relationship between the maximum height of the profile and the strain under different fillet radii in an embodiment of the present invention; Figure 8 This is a functional block diagram of the stamping part slippage defect control device based on coating evaluation in an embodiment of the present invention; Figure 9 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation
[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0020] In this invention, descriptions involving "first," "second," etc., are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination should be considered non-existent and not within the scope of protection claimed by this invention.
[0021] This invention provides a method for controlling slippage defects in stamped parts based on coating evaluation, with reference to... Figure 1 As shown, the method includes the following steps S101 to S103: S101: After the target die stamps the target stamping part, if there is a slip line in the stamped part, obtain the strain of the target stamping part after stamping.
[0022] In some embodiments, obtaining the strain of the target stamped part after stamping may include: obtaining the maximum height of the contour of the sliding line of the target stamped part after stamping, wherein the maximum height of the contour of the sliding line is the maximum distance between a point on the sliding line and the plane containing the sliding line; inputting the maximum height of the contour of the sliding line and the fillet radius of the target mold into a preset first correspondence relationship to obtain the strain of the target stamped part after stamping; the first correspondence relationship is the correspondence between the maximum height of the contour of the sliding line, the fillet radius of the mold, and the strain of the stamped part after stamping.
[0023] It should be noted that the strain can be obtained indirectly by measuring the maximum height of the profile, or it can be obtained by direct calculation. However, direct calculation of the strain is more complex and time-consuming. In this case, obtaining the strain indirectly by measuring the maximum height of the slip line profile improves the convenience of obtaining this data.
[0024] In some implementations, obtaining the maximum height of the sliding line profile of the target stamped part after stamping may include: obtaining the maximum height of the sliding line profile of the target stamped part after stamping by means of a roughness tester.
[0025] S102: Input the strain of the target stamped part after stamping and the fillet radius of the target die into the preset quality prediction model to obtain the first prediction result; the quality prediction model is obtained by training the machine learning model based on multiple sets of samples. Each set of samples includes the strain of the historical sample stamped part after stamping, the fillet radius of the sample die, and the actual result.
[0026] It should be noted that the actual results are used to characterize whether slip lines affect the appearance quality of the stamped sample after coating. Specifically, the actual results indicate that normal slip lines do not affect the appearance quality of the stamped sample after coating, while abnormal slip lines do affect the appearance quality of the stamped sample after coating.
[0027] In some implementations, the quality prediction model can be pre-established through the following steps: acquiring multiple sets of samples; inputting the strain of the stamped sample part after stamping and the fillet radius of the sample die of each set of samples into the machine learning model to obtain a second prediction result; determining the loss function between the second prediction result and the actual result; and iteratively optimizing the machine learning model based on the loss function between the second prediction result and the actual result to obtain the quality prediction model.
[0028] In some implementations, the data for each of the multiple sample groups can be obtained in advance through the following steps, including steps A through D: Step A: The sample stamping part is stamped using the sample mold of the sample group so that the strain of the sample stamping part after stamping reaches the target strain. The sample stamping part after stamping has slip lines.
[0029] In some embodiments, stamping the sample stamping part using the sample die of the sample set to make the strain of the sample stamping part reach the target strain after stamping may include: inputting the target strain to a preset second correspondence to obtain a target forming height; the second correspondence is the correspondence between the forming height and the strain of the sample stamping part when stamping the sample stamping part; based on the target forming height, controlling the sample die to stamp the sample stamping part to make the strain of the sample stamping part reach the target strain after stamping.
[0030] It should be noted that directly calculating the strain during the stamping process of this sample is quite complex. However, the strain is related to the forming height. By controlling the forming height, the strain of the sample can be accurately controlled, thereby improving the data accuracy of each sample in multiple samples.
[0031] Step B: Apply a coating to the stamped sample to obtain a coated stamped sample.
[0032] Step C: Perform a surface visual analysis on the coated stamped part to obtain actual results characterizing the appearance quality of the stamped part after coating.
[0033] In some embodiments, performing a surface visual analysis on the coated sample stamping to obtain actual results characterizing the appearance quality of the sample stamping after coating may include: performing a surface visual analysis on the coated sample stamping using a visual analysis system to determine whether there are slip lines on the surface of the coated sample stamping; if there are no slip lines on the surface of the coated sample stamping, the actual result is determined to be normal; if there are slip lines on the surface of the coated sample stamping, the actual result is determined to be abnormal.
[0034] It should be noted that the height of the slip line profile can also be obtained through surface visual analysis.
[0035] Step D: Based on the target strain of the stamped part after stamping, the fillet radius of the die, and the actual results characterizing the appearance quality of the stamped part after coating, the data of this set of samples are obtained.
[0036] It should be noted that the data in this sample may also include the height of the slip line profile.
[0037] S103: If the first prediction result is normal, the target stamped part after stamping is coated; the first prediction result being normal indicates that the slip lines do not affect the appearance quality of the target stamped part after coating.
[0038] In some embodiments, the stamping part slip defect control method based on coating evaluation may further include: if the first prediction result is abnormal, marking the slip line profile height of the target stamping part surface after stamping as abnormal.
[0039] It should be noted that the first prediction result is that the abnormal characterization of slip lines affects the appearance quality of the target stamped part after painting.
[0040] Specifically, the slip line not affecting the appearance quality of the target stamped part after painting can mean that the height of the slip line profile does not affect the appearance quality of the target stamped part after painting. Conversely, the slip line affecting the appearance quality of the target stamped part after painting can mean that the height of the slip line profile affects the appearance quality of the target stamped part after painting.
[0041] It should be noted that the above embodiments mainly discuss the situation where the stamped parts have already been produced, and the quality prediction model can be used to determine whether the stamped parts need to be painted. A different approach is to determine process parameters using a quality prediction model before producing the stamped parts. For example, the fillet radius and strain can be input into the quality prediction model. If the first prediction result is normal, then the fillet radius, strain, and other process parameters can be used. If the slip line height of the stamped part exceeds the maximum threshold for painting, the quality prediction model can be used to optimize the die fillet radius and material strain.
[0042] It should be noted that slip lines are a common surface defect in the stamping process of automotive body panels, which can seriously affect the surface quality and appearance of the stamped parts. However, automotive parts have complex shapes and an increasing number of body feature lines, making hardening and slippage inevitable when the die fillets come into contact with the sheet metal. To more accurately assess slip defects, it is necessary to conduct in-depth research on the strain of the sheet metal after slippage, the slip line profile, and the coating results, and establish the correspondence between these three factors to prevent slip defects from flowing into subsequent processes.
[0043] It should be noted that during sheet metal stamping, when the sheet metal flows through the rounded corners of the punch and other punch features, the material undergoes localized hardening and thinning due to bending, reverse bending, and stretching, leaving marks on the sheet surface. With the uneven flow of material on both sides of the die during stamping, these marks can slip and enter the part's surface area, affecting the quality of the final product. Slip line defects are one of the main quality defects in automotive body panels, directly impacting the visual appearance of the finished vehicle. Therefore, measuring and evaluating slip lines in stamped parts during the process design phase, enabling accurate on-site judgment and evaluation, and guiding the optimization of slip defect control, has significant practical value for automotive parts stamping. Furthermore, AutoForm simulation software can determine whether slip line defects affecting product appearance quality will occur when the sheet metal passes through the die rounded corners using three methods: slip distance, maximum contact compressive stress, and reverse bending strain. However, this software cannot quantify the slip line height, and changes in resistance after die wear can cause simulation results to differ from actual stamping conditions. Therefore, simulation evaluation is mainly applied during the product development phase. Human visual inspection is significantly influenced by subjective factors. The skill level of the technicians, ambient lighting, and variations in stamping conditions can all contribute to assessment errors. The severity of slip lines is directly related to the size of the fillet radius of the sheet metal contacting the die, the sheet metal properties, and the strain at the fillet radius. Therefore, establishing a correspondence between die fillet radius, strain, slip line contour values, and appearance quality allows for rapid assessment of slip defects in stamped parts. Furthermore, based on the correspondence between the contour curve and strain, it can guide the production line in optimizing stamping process parameters, thereby reducing the impact of slip lines on painting.
[0044] It should be noted that, regarding the slip line defects caused by die fillet radius and material flow during stamping, this invention can utilize fillet forming and an online DIC (Digital Image Correlation) measurement system to obtain the surface profile curves of samples with slip lines under different strain values, establishing a correspondence between die fillet radius, steel grade, forming strain, and slip line profile morphology. Simultaneously, a sample coating test is conducted to evaluate the surface defects of the coated samples, establishing a correspondence between strain and slip defects. Based on this, the minimum strain value affecting the surface quality of stamped parts and the slip line profile fluctuation threshold can be obtained, effectively guiding the assessment of slip line defects during forming and providing a basis for slip line optimization control. Specifically, firstly, based on the slip line generation mechanism, tensile bending dies with different fillet radii are developed. The die fillet radius r can range from 1.5 mm to 6.5 mm, with a step size of 1 mm and a die angle ≥ 90°. Secondly, a forming testing machine is used to simulate stamping forming to prepare slip line samples with different fillet radii. Then, cup tensile tests were performed on the existing slipline specimens. Before the test, speckle spray was applied to the specimen surface, and the strain state of the specimens was measured and recorded using a DIC online detection device. The strain was controlled by the forming height. According to the forming height and strain comparison table, the test was repeated on specimens without speckle spray to obtain tensile specimens with different fillet radii and strain. The profile of the strained tensile specimens was analyzed by a roughness tester along the direction perpendicular to the slipline to obtain the profile curve at the slipline. Through data processing, the maximum fluctuation value of the slipline profile after different strains was obtained and denoted as H. max Finally, the surface slip line defect was assessed by spraying with a pre-coated sheet, establishing the correspondence between steel grade, mold fillet radius, strain, and assessment results. When the defect at the slip line of the sample is invisible after spraying, the corresponding strain is the minimum strain ε generated by the slip defect of the sheet metal under the mold fillet radius. min That is, when this type of steel is formed under the fillet radius of this mold, when the strain > ε min At this time, the slip lines generated after the sheet metal contacts the mold can be covered by the paint film and will not affect the surface quality. The slip line profile H corresponding to the unpainted sample at this time... max This can be considered the maximum critical height; when the height of the sliding line profile after the mold impacts the sheet metal is less than H. max In this case, it can be determined that the slip line after the impact will not affect the coating surface.
[0045] To enhance understanding of the determination process for the first correspondence, the second correspondence, and multiple sets of samples, the following examples illustrate steps 1 through 5: Step 1: Development of the sliding line mold and sample preparation. (Reference) Figure 2 As shown, Figure 2This is a schematic diagram of the mold in an embodiment of the present invention. Tension bending molds with different fillet radii and included angles were developed, with fillet radii ranging from 1.5mm to 6.5mm. A slip line perpendicular to the stretching direction was prepared using a forming testing machine. To ensure uniform deformation of the central region of the stamped specimen during the stretching process, the stamped specimen was designed as a "dumbbell shape," referencing... Figure 3 As shown, Figure 3 This is a schematic diagram of the sample stamping part in an embodiment of the present invention, where a=45mm, b=70mm, and d=260mm.
[0046] Step 2: Tensile Strain Measurement and Analysis of Slip Lines. The surface of the stamped sample with slip lines is subjected to speckled spraying, and a cup tensile test is performed using a DIC measurement system. The strain and thinning curves of the slip line region are obtained, and a table corresponding to forming height and strain is established. A second correspondence can be obtained from this table. The table of forming height and strain can be referenced in Table 1, and repeated tests can be performed on samples without speckled lines based on Table 1.
[0047] Table 1:
[0048] Step 3: Slip line height measurement and data fitting correction. Using a roughness tester, measure the height of the tensile stamped sample along the slip line perpendicular to it. The measurement stroke is 15 mm. Obtain the profile curve data for reference. Figure 4 and Figure 5 As shown, Figure 4 This is a schematic diagram of the measurement direction of the roughness meter in an embodiment of the present invention. Figure 5 This is a schematic diagram of the contour curve data of the slip line in an embodiment of the present invention before correction. In order to accurately obtain the maximum height of the contour at the slip line, the original data must be corrected so that the sample plane coincides with or is parallel to the X-axis. The original data of the plane area can be fitted by Excel to obtain the angle between the fitted curve and the X-axis, and the coordinate transformation can be performed by the following formulas (1) and (2) to obtain the optimized contour curve. Figure 6 As shown, Figure 6 This is a schematic diagram of the corrected contour curve data of the slip line in an embodiment of the present invention. The correction method for the contour curve can be as follows: First, calculate the rotation angle; the rotation angle corresponding to the slope 'a' of the fitted curve is: θ = arctan(a); then, calculate the coordinates of the rotated data points. For each data point (X... i ,Y i ), the new coordinates after rotation (X) i ' ,Y i ' ).
[0049]
[0050] Step 4: Establish the correspondence between strain and the height of slip line profile undulations. Based on the corrected profile, select H as the absolute value of the distance from the highest or lowest point of the profile undulation to the X-axis. max That is, the maximum height of the slip line profile, establishing the relationship between each fillet radius, strain, and H. max The correspondence table is shown in Table 2, from which the first correspondence is obtained, and the corresponding dependent variable is denoted as ε. min To illustrate the first correspondence, Table 2 shows that when the fillet radius is 1.5mm and the maximum profile height is 34mm, the strain is 15%. Additionally, please refer to... Figure 7 As shown, Figure 7 This is a curve showing the correspondence between the maximum profile height and the strain under different fillet radii in an embodiment of the present invention.
[0051] Table 2:
[0052] Step 5: Threshold Determination and Slip Defect Assessment. The measured tensile specimens are coated with a coating film. Under sufficient light, the surface quality of the specimens is assessed by light reflection. A visual analysis system can be used to analyze whether the slip lines on the substrate surface are completely covered by the coating film, and the results are recorded to obtain multiple sets of samples, as shown in Table 3. Finally, the correspondence between mold fillet radius, strain, and assessment results is established.
[0053] Table 3:
[0054] In Table 3, ε represents the strain. A coating assessment of "present" indicates that the slip line contour height affects the appearance quality of the stamped part after coating, corresponding to an abnormal result. A coating assessment of "slight" also indicates that the slip line contour height affects the appearance quality of the stamped part after coating, corresponding to an abnormal result. A coating assessment of "no" indicates that the slip line contour height does not affect the appearance quality of the stamped part after coating, corresponding to a normal result. Specifically, one group of samples had a corner radius of 1.5mm and a strain of 5%, corresponding to an abnormal result. It should be emphasized that Table 3 is only a defect evaluation table for one type of steel after slippage. The evaluation methods for other steel types and strain testing are the same as above and will not be repeated here.
[0055] It should be noted that after obtaining the correspondence table between strain and surface quality assessment at the fillet of specific steel grades after fillet forming with different dies, in actual stamping production, the impact of slip lines on the final coated surface quality can be determined based on the fillet radius of the die and the strain after forming. Furthermore, based on the assessment results in the correspondence table, the stamping process and the strain state of the sheet metal can be adjusted to achieve optimized control of slip defects.
[0056] In this embodiment of the invention, after stamping a target stamped part using a target mold, if slip lines exist in the stamped part, the strain of the stamped part after stamping is obtained. The strain of the stamped part and the fillet radius of the target mold are input into a preset quality prediction model to obtain a first prediction result. The quality prediction model is obtained by training a machine learning model based on multiple sets of samples. Each set of samples includes the strain of historical sample stamped parts after stamping, the fillet radius of the sample mold, and the actual result. If the first prediction result is normal, the stamped part is coated. A normal first prediction result indicates that slip lines do not affect the appearance quality of the stamped part after coating. Since the strain of the stamped part and the fillet radius of the target mold are strongly correlated with the deformation of the stamped part, and the deformation of the stamped part affects the degree of slip of the slip lines. Therefore, based on the dependent variable, fillet radius, and quality prediction model, a first prediction result can be determined to characterize whether the slip line affects the appearance quality of the target stamped part after coating. This allows for judging appearance quality based on actual data, avoiding judgment solely based on human experience, and thus improving the accuracy of assessing the impact of slip line severity on the appearance quality of the stamped part after coating. Furthermore, determining whether to coat the target stamped part based on the first prediction result reduces the likelihood of the coated part being a defective product, thereby reducing material waste.
[0057] Based on the same inventive concept, and referring to Figure 8 As shown, this embodiment of the invention provides a stamping part slippage defect control device 10 based on coating evaluation, comprising: a strain acquisition unit 110, used to acquire the strain of the target stamping part after stamping by a target mold if slippage lines exist in the stamped target stamping part; a prediction unit 120, used to input the strain of the target stamping part after stamping and the fillet radius of the target mold into a preset quality prediction model to obtain a first prediction result; the quality prediction model is obtained by training a machine learning model based on multiple sets of samples, each set of samples including the strain of historical sample stamping parts after stamping, the fillet radius of the sample mold, and the actual result; and a coating unit 130, used to coat the stamped target stamping part if the first prediction result is normal; the first prediction result being normal indicates that slippage lines do not affect the appearance quality of the target stamping part after coating.
[0058] Understandably, the strain acquisition unit 110 is specifically used to: acquire the maximum height of the sliding line contour of the target stamped part after stamping, where the maximum height of the sliding line contour is the maximum distance between a point on the sliding line and the plane containing the sliding line; input the maximum height of the sliding line contour and the fillet radius of the target die into a preset first correspondence relationship to obtain the strain of the target stamped part after stamping; the first correspondence relationship is the correspondence between the maximum height of the sliding line contour, the fillet radius of the die, and the strain of the stamped part after stamping. Acquiring the maximum height of the sliding line contour of the target stamped part after stamping includes: acquiring the maximum height of the sliding line contour of the target stamped part after stamping using a roughness tester.
[0059] Understandably, the stamping part slippage defect control device 10 based on coating evaluation also includes: a model building unit, used to pre-build a quality prediction model, including the following steps: acquiring multiple sets of samples; inputting the strain of the sample stamping part after stamping and the fillet radius of the sample mold of each set of samples into the machine learning model to obtain a second prediction result; determining the loss function between the second prediction result and the actual result; and iteratively optimizing the machine learning model based on the loss function between the second prediction result and the actual result to obtain a quality prediction model.
[0060] Understandably, the stamping part slippage defect control device 10 based on coating evaluation further includes: a sample acquisition unit for pre-acquiring multiple sets of samples, wherein the sample acquisition unit includes: a stamping subunit for stamping the sample stamping part using the sample mold of the sample set, so that the strain of the sample stamping part after stamping reaches the target strain, and the sample stamping part after stamping has slip lines; a spraying subunit for applying a coating to the sample stamping part after stamping to obtain the coated sample stamping part; an analysis subunit for performing surface visual analysis on the coated sample stamping part to obtain actual results characterizing the appearance quality of the sample stamping part after coating; and an acquisition subunit for obtaining the data of the sample set based on the target strain of the sample stamping part after stamping, the fillet radius of the sample mold, and the actual results characterizing the appearance quality of the sample stamping part after coating.
[0061] It is understandable that the stamping subunit is specifically used to: input the target strain variable into a preset second correspondence relationship to obtain the target forming height; the second correspondence relationship is the correspondence between the forming height and the strain variable of the sample stamping part when the sample stamping part is stamped; based on the target forming height, control the sample die to stamp the sample stamping part so that the strain variable of the sample stamping part after stamping reaches the target strain variable.
[0062] Understandably, the analysis subunit is specifically used to: perform surface visual analysis on the coated sample stamping part through a visual analysis system to determine whether there are slip lines on the surface of the coated sample stamping part; if there are no slip lines on the surface of the coated sample stamping part, the actual result is judged to be normal; if there are slip lines on the surface of the coated sample stamping part, the actual result is judged to be abnormal.
[0063] Understandably, the stamping part slippage defect control device 10 based on coating evaluation also includes: a marking unit, used to mark the target stamping part after stamping as an abnormal stamping part if the first prediction result is abnormal.
[0064] It should be understood that further implementation details of the stamping part slippage defect control device 10 based on coating evaluation in the embodiments of the present invention are as described in the foregoing method for controlling stamping part slippage defects based on coating evaluation, and will not be repeated here for the sake of brevity.
[0065] Based on the same inventive concept, embodiments of the present invention also provide an electronic device, such as... Figure 9 As shown, it includes a memory 904, a processor 902, and a computer program stored in the memory 904 and executable on the processor 902. The processor 902 executes the program to implement the steps described in any embodiment of the method for controlling slippage defects in stamped parts based on coating evaluation.
[0066] Among them, Figure 9 In this document, a bus architecture (represented by bus 900) is used. Bus 900 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 902 and memory represented by memory 904. Bus 900 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 905 provides an interface between bus 900 and receiver 901 and transmitter 903. Receiver 901 and transmitter 903 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 902 is responsible for managing bus 900 and general processing, while memory 904 can be used to store data used by processor 902 during operation.
[0067] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.
[0068] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.
[0069] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.
[0070] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0071] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.
Claims
1. A method for controlling slippage defects in stamped parts based on coating evaluation, characterized in that, include: After the target mold stamps the target stamping part, if the stamped target stamping part has a slip line, the strain of the target stamping part after stamping is obtained. The strain of the target stamped part after stamping and the fillet radius of the target die are input into a preset quality prediction model to obtain a first prediction result. The quality prediction model is obtained by training a machine learning model based on multiple sets of samples. Each set of samples includes the strain of the historical sample stamped part after stamping, the fillet radius of the sample die, and the actual result. If the first prediction result is normal, the target stamped part after stamping is coated; the first prediction result being normal indicates that the slip line does not affect the appearance quality of the target stamped part after coating. The quality prediction model is established in advance through the following steps: acquiring the multiple sets of samples; inputting the strain of the stamped sample part after stamping and the fillet radius of the sample mold of each set of samples into the machine learning model to obtain a second prediction result; determining the loss function of the second prediction result and the actual result; and iteratively optimizing the machine learning model based on the loss function of the second prediction result and the actual result to obtain the quality prediction model.
2. The method for controlling slippage defects in stamped parts based on coating evaluation according to claim 1, characterized in that, The process of obtaining the strain of the target stamped part after stamping includes: The maximum height of the contour of the sliding line of the target stamped part after stamping is obtained. The maximum height of the contour of the sliding line is the maximum distance between a point on the sliding line and the plane on which the sliding line is located. The maximum height of the sliding line contour and the fillet radius of the target mold are input into a preset first correspondence to obtain the strain of the target stamped part after stamping; the first correspondence is the correspondence between the maximum height of the sliding line contour, the fillet radius of the mold, and the strain of the stamped part after stamping.
3. The method for controlling slippage defects in stamped parts based on coating evaluation according to claim 2, characterized in that, Obtaining the maximum height of the slip line contour of the target stamped part after stamping includes: The maximum height of the slip line profile of the target stamped part after stamping is obtained by using a roughness tester.
4. The method for controlling slippage defects in stamped parts based on coating evaluation according to claim 1, characterized in that, The data for each of the multiple sample groups was obtained in advance through the following steps: The sample stamping part is formed by stamping the sample using the sample mold of this group of samples, so that the strain of the sample stamping part after stamping reaches the target strain. The sample stamping part after stamping has slip lines. The stamped sample is coated with a coating material by applying a coating sheet to the stamped sample. A surface visual analysis was performed on the coated sample stamping to obtain actual results characterizing the appearance quality of the sample stamping after coating. The data for this set of samples are obtained based on the target strain of the stamped part after stamping, the fillet radius of the mold, and the actual results characterizing the appearance quality of the stamped part after coating.
5. The method for controlling slippage defects in stamped parts based on coating evaluation according to claim 4, characterized in that, The process of stamping the sample part using the sample die of the sample group to achieve the target strain after stamping includes: The target strain is input into a preset second correspondence to obtain the target forming height; the second correspondence is the correspondence between the forming height and the strain of the stamped part when the stamped part is stamped. Based on the target forming height, the sample die is controlled to stamp the sample stamping part so that the strain of the sample stamping part after stamping reaches the target strain.
6. The method for controlling slippage defects in stamped parts based on coating evaluation according to claim 4, characterized in that, The surface visual analysis of the coated stamped sample to obtain actual results characterizing the appearance quality of the stamped sample after coating includes: The surface of the coated sample stamping was visually analyzed using a visual analysis system to determine whether there were slip lines on the surface of the coated sample stamping. If no slip lines are found on the surface of the stamped part of the coated sample, the actual result is considered normal. If slip lines are present on the surface of the stamped part of the coated sample, the actual result is considered abnormal.
7. The method for controlling slippage defects in stamped parts based on coating evaluation according to claim 6, characterized in that, Also includes: If the first prediction result is abnormal, the height of the sliding line profile on the surface of the target stamped part after stamping is marked as abnormal.
8. A stamping part slippage defect control device based on coating evaluation, applied to the method of any one of claims 1-7, characterized in that, include: The strain acquisition unit is used to acquire the strain of the target stamping part after stamping the target stamping part by the target mold, if there is a slip line in the stamped target stamping part; The prediction unit is used to input the strain of the target stamped part after stamping and the fillet radius of the target die into a preset quality prediction model to obtain a first prediction result. The quality prediction model is obtained by training a machine learning model based on multiple sets of samples. Each set of samples includes the strain of the historical sample stamped part after stamping, the fillet radius of the sample die, and the actual result. A coating unit is used to coat the target stamped part after stamping if the first prediction result is normal; the first prediction result being normal indicates that the slip line does not affect the appearance quality of the target stamped part after coating.
9. An electronic device, characterized in that, include: 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 of any one of claims 1-7.
Citation Information
Patent Citations
Intelligent detection method for judging forming defect of stamping part blank contour deviation
CN115906557A
