Pressing rivet device and method

Abstract

The invention relates to a press riveting device and method, and belongs to the field of stamping equipment, and the press riveting method comprises the steps that stamping data are collected, and the stamping data comprise press riveting device operation state parameters, rivet parameters and stamping environment parameters; constructing a digital twin model of the press riveting process based on the stamping data, and performing multi-objective optimization on the press riveting parameters through a finite element simulation algorithm to generate a recommended press riveting parameter set; and inputting the recommended pressure riveting parameter set into a quality prediction machine learning model trained by historical production data for pressure riveting parameter optimization. According to the pressure riveting device, the stamping data is collected before pressure riveting, the pressure riveting parameters matched with the rivets are generated, the pressure riveting device executes the rivet pressure riveting operation according to the pressure riveting parameters, and the rivets of different qualities are matched with different pressure riveting parameters, so that the pressure riveting quality is stable, the defective rate is reduced, and the pressure riveting quality of the rivets is improved.

Description

Technical Field

[0001] This application relates to the field of stamping equipment, and in particular to a riveting device and method. Background Technology

[0002] In existing technologies, the stamping force and stamping speed during rivet pressing are generally set according to the rivet specifications and models. When the rivet specifications and models remain unchanged, the stamping force and stamping speed are generally not adjusted. However, due to the limitations of the rivet forming process quality, the quality of rivets of the same specifications and models, different batches, and even individual rivets in the same batch are inconsistent. For example, some rivets may have scratches or diameter deviations. In this case, using the same stamping force and stamping speed throughout the stamping process will inevitably affect the stamping quality. Moreover, the state of the stamping equipment and the stamping environment are not constant. Different states of the stamping equipment and different stamping environments will affect the stamping quality. Summary of the Invention

[0003] To improve the quality of rivet pressing, this application provides a pressing device and method.

[0004] The riveting method provided in this application adopts the following technical solution: A riveting method, comprising: Collect stamping data, which includes operating status parameters of the riveting device, rivet parameters, and stamping environment parameters; A digital twin model of the riveting process is constructed based on stamping data, and the riveting parameters are optimized for multiple objectives using finite element simulation algorithms to generate a recommended set of riveting parameters. The recommended set of riveting parameters is input into a quality prediction machine learning model trained on historical production data for riveting parameter optimization; the optimized riveting parameters are then sent to the riveting device, which executes the optimized riveting parameters to perform the riveting operation on the rivets.

[0005] By adopting the above technical solution, stamping data is collected to generate riveting parameters suitable for rivets. The riveting device performs rivet riveting operations according to these riveting parameters. Different riveting parameters are matched with rivets of different qualities to achieve stable riveting quality, reduce the defect rate, and improve the quality of rivet riveting.

[0006] Preferably, during the riveting operation of the rivet by the riveting device using optimized riveting parameters, the force-stroke curve is collected in real time, and the stamping parameters are adjusted through a closed-loop control algorithm to compensate for disturbances.

[0007] By adopting the above technical solutions, the quality of rivet pressing can be further improved.

[0008] Preferably, the closed-loop control algorithm includes: The real-time force-stroke curve is compared with the standard force-stroke curve; If the deviation exceeds a preset threshold, the stamping parameters are adjusted, including the stamping stroke or the stamping speed.

[0009] By adopting the above technical solutions, the quality of rivet pressing can be further improved.

[0010] Preferably, the riveting method further includes: The quality data of the rivets after riveting is obtained and bound to the rivet parameters before riveting to form a data sample for training the digital twin model and the quality prediction machine learning model.

[0011] By adopting the above technical solutions, the accuracy of the model can be improved.

[0012] Preferably, the multi-objective optimization includes optimizing the rivet forming quality, the stamping die life, and the production energy consumption as optimization objectives, and using a genetic algorithm or response surface methodology to collaboratively optimize the die design parameters and stamping process parameters.

[0013] By adopting the above technical solutions, the quality of rivet pressing can be further improved.

[0014] Preferably, the quality prediction machine learning model is a model based on random forest, gradient boosting tree, or neural network.

[0015] By adopting the above technical solutions, the quality of rivet pressing can be further improved.

[0016] Furthermore, this application also proposes a riveting device for pressing rivets, the rivets having a pressing hole, the riveting device comprising: A support base is provided with a lower mold base and a lower fixing clamp for fixing the lower mold base. The lower mold base is provided with a lower template, and the upper surface of the lower template is provided with rivet holes. The frame is equipped with a vision camera, a stamping device, an upper die base, and an upper fixing clamp for fixing the upper die base. The upper die base is equipped with an upper template, a force sensor, and a displacement sensor. A stamping head that is connected to the stamping device is vertically slidably mounted on the lower surface of the upper template. The stamping head is frustum-shaped and vertically arranged. The diameter of the lower surface of the stamping head is smaller than the diameter of the upper surface. The diameter of the stamping hole is between the diameter of the lower surface and the diameter of the upper surface of the stamping head. The lower template and / or upper template are equipped with acoustic emission sensors and vibration sensors, and the support base or frame is equipped with temperature and humidity sensors.

[0017] By adopting the above technical solution, stamping data is collected to generate riveting parameters suitable for rivets. The riveting device performs rivet riveting operations according to these riveting parameters. Different riveting parameters are matched with rivets of different qualities to achieve stable riveting quality, reduce the defect rate, and improve the quality of rivet riveting.

[0018] Preferably, the upper surface of the lower template is provided with a guide hole, and the lower surface of the upper template is provided with a guide pin suitable for extending into the guide hole.

[0019] By adopting the above technical solutions, the quality of rivet pressing can be further improved.

[0020] Preferably, the upper surface of the lower template is provided with a positioning pin.

[0021] By adopting the above technical solutions, the quality of rivet pressing can be further improved.

[0022] Preferably, the riveting device further includes a fixed support frame, the upper surface of which is flush with the upper surface of the lower template.

[0023] By adopting the above technical solution, it is easier to place the material board and improve the quality of rivet pressing.

[0024] In summary, this application includes at least one of the following beneficial technical effects: 1. The riveting device of this application collects stamping data before riveting and generates riveting parameters suitable for the rivet. The riveting device performs rivet riveting operation according to the riveting parameters. Different riveting parameters are matched with rivets of different qualities to achieve stable riveting quality, reduce the defect rate, and improve the riveting quality.

[0025] 2. The riveting device of this application can stamp multiple rivets at one time, with high working efficiency; the stamping head automatically bevels the rivets during the stamping process, which improves the strength of the riveting connection. Attached Figure Description

[0026] Figure 1 This is a flowchart of the riveting method in the embodiments of this application.

[0027] Figure 2 This is a schematic diagram of the riveting device in the embodiments of this application. Figure 1 .

[0028] Figure 3 This is a schematic diagram of the riveting device in the embodiments of this application. Figure 2 .

[0029] Figure 4 This is a schematic diagram of the riveting device in the embodiments of this application. Figure 3 .

[0030] Figure 5 This is a structural diagram of a rivet.

[0031] Explanation of reference numerals in the attached drawings: 1. Support base; 2. Frame; 3. Stamping device; 4. Lower die base; 5. Guide hole; 6. Positioning pin; 7. Rivet; 71. Stamping hole; 8. Material plate; 9. Upper die base; 10. Stamping head; 11. Guide pin; 12. Support frame; 13. Riveting hole; 14. Lower template; 15. Upper template; 16. Lower fixing clamp; 17. Upper fixing clamp; 18. Positioning hole. Detailed Implementation

[0032] The following is in conjunction with the appendix Figure 1-5 This application will be described in further detail.

[0033] This application discloses a riveting method, such as... Figure 1 As shown, it includes: S1. Collect stamping data, construct a digital twin model of the riveting process based on the stamping data, and perform multi-objective optimization of the riveting parameters through finite element simulation algorithm to generate a recommended set of riveting parameters; S2. Input the recommended riveting parameter set into the quality prediction machine learning model trained with historical production data to optimize the riveting parameters. S3. Send the optimized riveting parameters to the riveting device, and the riveting device executes the optimized riveting parameters to perform riveting operation on rivet 7.

[0034] In the riveting method of this embodiment, stamping data is collected to generate riveting parameters that are compatible with the rivet 7. The riveting device performs the riveting operation of the rivet 7 according to the riveting parameters. Different riveting parameters are matched with rivets 7 of different qualities to achieve stable riveting quality, reduce the defect rate, and improve the riveting quality of the rivet 7.

[0035] Specifically, the stamping data mentioned in S1 includes the operating status parameters of the riveting device, the parameters of the rivet 7, and the stamping environment parameters.

[0036] More specifically, the operating parameters of the riveting device include the punching force of the punching head 10, the punching stroke, the air pressure of the punching device 3 (when the punching device 3 is a cylinder), the vibration signal and acoustic emission signal during the punching operation of the riveting device.

[0037] More specifically, the parameters of rivet 7 include constitutive parameters such as rivet 7 surface quality, specifications and dimensions, and stress-strain curve.

[0038] More specifically, stamping environment parameters include the temperature and humidity of the environment surrounding the riveting device.

[0039] In this embodiment, the stamping data of S1 is collected and transmitted to the control center of the riveting device for analysis and processing. Specifically, after the stamping data is collected and uploaded to the control center, the control center calls the built-in finite element analysis engine to automatically generate a digital twin model of the riveting process. With the optimization objectives of optimal rivet 7 forming quality, longest stamping die life and lowest production energy consumption, the genetic algorithm or response surface methodology is used to collaboratively optimize the die design parameters and stamping process parameters to obtain a set of recommended riveting parameters.

[0040] In this embodiment, the historical production data of S2 is the data obtained from previous riveting operations on rivets 7. After being trained on this historical production data, the quality prediction machine learning model can predict the quality of riveting under a specific equipment condition using this set of parameters, and optimize the riveting parameters based on this.

[0041] In this embodiment, the quality prediction machine learning model is a model based on random forest, gradient boosting tree, or neural network.

[0042] In this embodiment, the optimized riveting parameters of S3 are transmitted to the controller in the control center. The controller controls the riveting device to perform riveting operation on the rivet 7 according to the optimized riveting parameters, thereby improving the riveting quality of the rivet 7, reducing the defect rate, and achieving stable riveting quality.

[0043] In this embodiment, during the riveting operation of the rivet 7 by the riveting device described in S3, the force-stroke curve is collected in real time, and the stamping parameters are adjusted by the closed-loop control algorithm to compensate for disturbances and ensure the riveting quality of the rivet 7.

[0044] Specifically, the closed-loop control algorithm includes: S31. Compare the real-time force-stroke curve with the standard force-stroke curve. The force-stroke curve is obtained by collecting the punching force and punch stroke of the punching head 10. The standard force-stroke curve is theoretically obtained by the punching force and punch stroke of the punching head 10 during the riveting process of a riveting device in good condition. S32. If the deviation between the two curves exceeds a preset threshold, the stamping parameters are actively adjusted. The stamping parameters include stamping stroke or stamping speed to ensure stable riveting quality and improve the riveting quality of rivet 7.

[0045] In this embodiment, the riveting method further includes: S4. Obtain the quality data of rivet 7 after riveting is completed, and bind it with the parameters of rivet 7 before riveting to form a data sample for secondary training of the digital twin model and the quality prediction machine learning model to improve the accuracy of the model.

[0046] Specifically, the quality data of the rivet 7 after pressing in S4 includes the shape and surface quality of the rivet 7 after pressing. These data are bound with the parameters of the rivet 7 before pressing to form a data sample. Then, a large number of data samples are built into a database. The digital twin model and the quality prediction machine learning model are retrained and updated every once in a while to make the model more and more accurate, thereby improving the pressing quality of the rivet 7.

[0047] In this embodiment, the riveting method further includes: S5. Determine whether the stamping die has malfunctioned based on the vibration and acoustic emission signals during the stamping operation of the riveting device.

[0048] Specifically, the method of determining whether a stamping die has malfunctioned based on vibration signals and acoustic emission signals during the stamping operation of the riveting device includes: S51. Monitor vibration and acoustic emission signals during the stamping operation of the riveting device; S52. Analyze vibration signals and acoustic emission signals. When it is found that the energy value of a specific frequency band in the vibration signal shows an upward trend for several consecutive times, the timing prediction model is used to determine that the stamping die may have micro-cracks or loosening. Then, the control center sends an early warning and a suggestion to stop the machine for maintenance based on this judgment, thereby realizing predictive maintenance, extending the service life of the riveting device, and avoiding production delays.

[0049] In addition, this application also proposes a riveting device for pressing rivets 7, such as... Figure 5 As shown, the rivet 7 has a stamped hole 71, as... Figures 2-4 As shown, the riveting device includes: a support base 1 and a frame 2. The support base 1 is provided with a lower die base 4 and a lower fixing clamp 16 for fixing the lower die base 4. The lower die base 4 is provided with a lower template 14. The upper surface of the lower template 14 is constructed with riveting holes 13 for placing... Figure 5 The rivet 7 is shown.

[0050] In this embodiment, as Figures 2-4 As shown, the frame 2 is equipped with a vision camera, a stamping device 3, an upper die base 9, and an upper fixing clamp 17 for fixing the upper die base 9. The vision camera is used to photograph the surface quality, specifications, and dimensions of the rivet 7 before riveting, as well as the shape and surface quality of the rivet 7 after riveting. The upper die base 9 is equipped with an upper template 15, a force sensor, and a displacement sensor. The force sensor is used to detect the stamping force of the stamping head 10, and the displacement sensor is used to detect the stroke of the stamping head. The stamping head 10, which is connected to the stamping device 3, is vertically slidably mounted on the lower surface of the upper template 15. The stamping device 3 drives the stamping head 10 to stamp the rivet 7.

[0051] In this embodiment, preferably, such as Figures 2-5 As shown, the stamping head 10 is frustum-shaped and vertically arranged. The diameter of the lower surface of the stamping head 10 is smaller than the diameter of the upper surface. The diameter of the stamping hole 71 is between the diameter of the lower surface and the diameter of the upper surface of the stamping head 10. With this design, the stamping head 10 automatically bevels the rivet 7 during the stamping process, which improves the strength of the press-fit connection.

[0052] In this embodiment, the lower template 14 and / or the upper template 15 are provided with an acoustic emission sensor and a vibration sensor. The acoustic emission sensor is used to detect acoustic emission signals during the stamping operation of the riveting device, and the vibration sensor is a vibration acceleration sensor used to detect vibration signals during the stamping operation of the riveting device to determine whether the stamping die has malfunctioned. The stamping die includes at least the lower template 14 and the upper template 15.

[0053] In this embodiment, the support base 1 or frame 2 is equipped with a temperature and humidity sensor to detect the ambient temperature and humidity around the riveting device.

[0054] By adopting the above technical solution, stamping data is collected to generate riveting parameters that are compatible with rivets 7. The riveting device performs the riveting operation of rivets 7 according to the riveting parameters. Different riveting parameters are matched with rivets 7 of different qualities to achieve stable riveting quality, reduce the defect rate, and improve the riveting quality of rivets 7.

[0055] In this embodiment, as Figure 2 As shown, the upper surface of the lower template 14 is provided with guide holes 5, such as... Figure 3 As shown, the lower surface of the upper template 15 is provided with a guide pin 11 suitable for extending into the guide hole 5, thereby achieving precise fit between the lower template 14 and the upper template 15 and ensuring the quality of the rivet 7. Further, as... Figure 4 As shown, the upper surface of the lower template 14 is provided with a positioning pin 6, which is used for positioning the material plate 8. The riveting device also includes a fixed support frame 12, the upper surface of which is flush with the upper surface of the lower template 14. This design facilitates the placement of large material plates 8 and improves the riveting quality of the rivets 7.

[0056] In this embodiment, during riveting, the rivet 7 is placed inside the riveting hole 13, and then... Figure 2 The metal material plate 8 is placed as shown, so that the upper part of the rivet 7 passes through the corresponding opening on the metal material plate 8, and the rivet 7 protrudes upward from the opening by a certain length. The stamping device 3 drives the lower die base 4 to move downward, the guide pin 11 is inserted into the guide hole 5, the positioning rod is inserted into the positioning hole 18, and finally the stamping device 3 drives the stamping head 10 to extend and insert into the stamping hole 71 of the rivet 7. After stamping, the rivet 7 is chamfered so that the rivet 7 is firmly fixed in the hole of the metal material plate 8.

[0057] In this embodiment, as Figure 4As shown, the two riveting holes 13 can punch two rivets 7 at once, which improves work efficiency.

[0058] In this embodiment, the manufacturing process of rivet 7 includes the following steps: 1. Add aluminum, zinc, copper, magnesium, and zirconium raw materials to a melting furnace in a certain amount and melt them at 700-760℃ for 5-6 hours to obtain an alloy solution; 2. The alloy solution is poured into the mold for casting, and the mold is cooled down. After demolding, a semi-finished product is obtained. 3. Post-process the semi-finished product, such as polishing, shaping, and surface spraying, to obtain the finished rivet 7.

[0059] In this embodiment, the rivet 7 manufactured using the above process has high structural strength.

[0060] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," "third," and similar terms used in this application specification and claims do not indicate any order, quantity, or importance, but are merely used to distinguish different components. The terms "an" or "a" and similar terms do not indicate a quantity limitation, but rather indicate the presence of at least one. The terms "comprising" or "including" and similar terms mean that the elements or objects preceding "comprising" or "including" encompass the elements or objects listed following "comprising" or "including" and their equivalents, and do not exclude other elements or objects. "Above," "below," "left," "right," etc., are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0061] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A riveting method, characterized in that: include: Collect stamping data, construct a digital twin model of the riveting process based on the stamping data, and perform multi-objective optimization of the riveting parameters through finite element simulation algorithm to generate a recommended set of riveting parameters; The recommended set of riveting parameters is input into a quality prediction machine learning model trained on historical production data for riveting parameter optimization; the optimized riveting parameters are then sent to the riveting device, which executes the optimized riveting parameters to perform the riveting operation on the rivets.

2. The riveting method according to claim 1, characterized in that: During the riveting operation of the rivet by the riveting device, the force-stroke curve is collected in real time, and the stamping parameters are adjusted by the closed-loop control algorithm to compensate for the disturbance. The stamping data includes the operating status parameters of the riveting device, rivet parameters, and stamping environment parameters.

3. The riveting method according to claim 2, characterized in that: The closed-loop control algorithm includes: The real-time force-stroke curve is compared with the standard force-stroke curve; If the deviation exceeds a preset threshold, the stamping parameters are adjusted, including the stamping stroke or the stamping speed.

4. The riveting method according to claim 1, characterized in that: Also includes: The quality data of the rivets after riveting is obtained and bound to the rivet parameters before riveting to form a data sample for training the digital twin model and the quality prediction machine learning model.

5. The riveting method according to claim 1, characterized in that: The multi-objective optimization includes optimizing the rivet forming quality, the stamping die life, and the production energy consumption as optimization objectives, and using genetic algorithms or response surface methodology to collaboratively optimize the die design parameters and stamping process parameters.

6. The riveting method according to claim 1, characterized in that: The quality prediction machine learning model is based on random forest, gradient boosting tree, or neural network.

7. A riveting device, implementing the riveting method of any one of claims 1-6, wherein the riveting device is used to press a rivet, the rivet having a punching hole, characterized in that: The riveting device includes: A support base is provided with a lower mold base and a lower fixing clamp for fixing the lower mold base. The lower mold base is provided with a lower template, and the upper surface of the lower template is provided with rivet holes. The frame is equipped with a vision camera, a stamping device, an upper die base, and an upper fixing clamp for fixing the upper die base. The upper die base is equipped with an upper template, a force sensor, and a displacement sensor. A stamping head that is connected to the stamping device is vertically slidably mounted on the lower surface of the upper template. The stamping head is frustum-shaped and vertically arranged. The diameter of the lower surface of the stamping head is smaller than the diameter of the upper surface. The diameter of the stamping hole is between the diameter of the lower surface and the diameter of the upper surface of the stamping head. The lower template and / or upper template are equipped with acoustic emission sensors and vibration sensors, and the support base or frame is equipped with temperature and humidity sensors.

8. The riveting device according to claim 7, characterized in that: The upper surface of the lower template is provided with a guide hole, and the lower surface of the upper template is provided with a guide pin suitable for extending into the guide hole.

9. The riveting device according to claim 7, characterized in that: The upper surface of the lower template is provided with positioning pins.

10. The riveting device according to claim 7, characterized in that: It also includes a fixed support frame, the upper surface of which is flush with the upper surface of the lower template.

Images