Method for automatically adding curve tolerance judgment window based on AI

Abstract

The invention belongs to the technical field of servo press fitting detection, and discloses an AI-based method for automatically adding a curve tolerance judgment window, which specifically comprises the following steps: step 1, data loading and threshold calculation, step 2, base line determination, step 3, maximum offset calculation, step 4, maximum offset calculation, and step 5, curve tolerance judgment window addition. 5, carrying out iterative simplification; 6, reconstructing the simplified curve; and 7, generating a tolerance window. The invention provides an innovative automatic data processing scheme for solving the problem of complexity in press-fitting monitoring of the servo press. By automatically loading the historical press fitting curve and accurately calculating the tolerance threshold value, the requirement for manual intervention is greatly reduced, and the working efficiency is effectively improved; meanwhile, the maximum distance between the point and the straight line is dynamically compared, the accuracy of a tolerance judgment window is ensured, and the change trend of the press fitting process is reflected more accurately.

Description

Technical Field

[0001] The present invention belongs to the technical field of servo press-fit detection, and specifically is a method for automatically adding a curve tolerance judgment window based on AI. Background Art

[0002] A servo press is a servo press system used to produce different connectors through processes such as pressing, caulking, riveting, stamping, and embossing. Servo presses are widely used in automated production plants as well as manually controlled workplaces. Servo press systems are often used in automation industry production applications, such as engine and transmission system installation, steering systems, chassis, brakes, fuel injection pumps, airbags, and electric motors for components such as wipers in the field of new energy vehicles (NEV). In addition, medical products, the electronics and household appliances industry, and the power tool production industry are also important application areas for servo press systems.

[0003] In the application of servo presses, it is often necessary to add a tolerance judgment window to the press-fitting curve to monitor and evaluate the press-fitting process, thereby accurately ensuring the press-fitting process and effectively controlling the consistency of product press-fitting. Figure 1 , Figure 2 It is the upper and lower envelope tolerance judgment window added to the common press-fitting curve. As can be seen from the figure, the configuration of the upper and lower envelope tolerance judgment window is very complicated, and the coordinate value of each point needs to be accurately input. For on-site process engineers, it is necessary to constantly adjust the coordinate value of the judgment window to achieve accurate monitoring and evaluation of the press-fitting process, which is a waste of time and resources. Therefore, this application makes the following improvements to the inconveniences in the prior art. Summary of the invention

[0004] The purpose of the present invention is to provide an AI-based method for automatically adding a curve tolerance judgment window to solve the problems raised in the above background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a method for automatically adding a curve tolerance judgment window based on AI, the method steps for adding a curve tolerance judgment window are specifically as follows:

[0006] Step 1: Data loading and threshold calculation: Load historical press curve data, calculate Dx and Dy for each press curve respectively; take the maximum value of Dx and Dy as the threshold Dt for curve calculation, and this threshold Dt is also used to generate the tolerance value of the curve tolerance judgment window;

[0007] Step 2: Determine the baseline: hash the points on the curve, select the point with the minimum X-axis coordinate as the starting point, the point with the maximum X-axis coordinate as the end point, and connect the two points to form a straight line as the baseline;

[0008] Step 3, calculate the maximum offset: calculate the maximum distance Dmax from all points of the curve to the baseline (including the starting point and the end point);

[0009] Step 4: Simplify the curve (based on threshold judgment):

[0010] If Dmax is less than Dt, the first and last points are retained, and all the intermediate points are deleted, and the simplification process is completed;

[0011] If Dmax is greater than or equal to Dt, the point corresponding to Dmax is used as the new starting point, and the new baseline is reconnected with the end point, and the original starting point is recorded, and the next step is continued;

[0012] Step 5, iterative simplification: repeat the above steps 3 and 4 until the maximum distance Dmax of all points to the new baseline is less than Dt, at which point the simplification process ends;

[0013] Step 6: Reconstruct the simplified curve: Use all the points passing through the starting point and the end point of the original curve to form the final simplified curve;

[0014] Step 7, generate tolerance window: translate the simplified curve in step 6 by half the distance Dt along the positive and negative directions of the Y axis respectively. The connecting lines formed are the upper tolerance window and the lower tolerance window. The tolerance judgment window of the curve is defined by these two lines.

[0015] Preferably, the calculation formulas for Dx and Dy in step 1 are:

[0016]

[0017] Preferably, the upper tolerance window and the lower tolerance window in step seven are respectively:

[0018]

[0019]

[0020] Preferably, the method further includes step eight, i.e. dynamically adjusting the threshold Dt: after generating the tolerance window, according to the requirements of the actual application scenario, the user is allowed to manually adjust the threshold Dt and re-execute steps two to seven to generate a tolerance judgment window that meets different accuracy requirements.

[0021] Preferably, the method also includes step nine, namely, abnormality detection: after generating the tolerance judgment window, the original pressing curve is traversed to determine whether each point on the curve falls within the tolerance judgment window. If there is a point that exceeds the tolerance window range, it is marked as an abnormal point and an abnormality report is output.

[0022] Preferably, the method further includes step ten, namely, data visualization: displaying the original press-fitting curve, the simplified curve and the tolerance judgment window to the user in the form of a graphical interface, so that the user can intuitively understand the curve tolerance and conduct subsequent analysis.

[0023] Preferably, the method also supports simultaneous processing of multiple curves, and can load and process multiple press-fitting curves at the same time, generate respective tolerance judgment windows, and improve processing efficiency and automation level.

[0024] The beneficial effects of the present invention are as follows:

[0025] The present invention effectively solves the complex problem of setting the tolerance judgment window in the servo press press curve monitoring. Through a highly automated data processing method - loading historical curves and automatically calculating the threshold Dt, it significantly reduces manual intervention and improves work efficiency. Its mechanism of dynamically calculating Dmax and comparing it with the threshold Dt ensures the accuracy of the tolerance window, can accurately reflect changes in the press process, and improves monitoring accuracy. The method is highly flexible and suitable for a variety of curve types, and can adapt to different monitoring needs by adjusting the Dt calculation method. At the same time, it saves engineers' time and energy, allowing them to focus more on process optimization and problem solving. The generated simplified curves and tolerance windows are clear and intuitive, making it easy to quickly identify anomalies and take countermeasures. In addition, the method is simple to implement and maintain, easy to integrate into existing systems, and reduces maintenance costs. In summary, this solution brings a new experience of convenience, efficiency, and accuracy to servo press press monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the existing press-fit curve tolerance determination window;

[0027] Figure 2 A schematic diagram of setting parameters for the existing press-fit curve tolerance determination window;

[0028] Figure 3 It is a schematic diagram of the loading and pressing history curve of the present invention;

[0029] Figure 4 Schematic diagram of the process of automatically adding a tolerance judgment window in the present invention Figure 1 ;

[0030] Figure 5 Schematic diagram of the process of automatically adding a tolerance judgment window in the present invention Figure 2 ;

[0031] Figure 6 Schematic diagram of the process of automatically adding a tolerance judgment window in the present invention Figure 3 ;

[0032] Figure 7 Schematic diagram of the process of automatically adding a tolerance judgment window in the present invention Figure 4 ;

[0033] Figure 8 Schematic diagram of the process of automatically adding a tolerance judgment window in the present invention Figure 5 ;

[0034] Fig. 9 This is a schematic diagram of the simplified curve of the present invention after automatically adding a tolerance judgment window;

[0035] Fig.10 This is a schematic diagram of the press-fitting curve of the present invention after automatically adding a tolerance judgment window. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] like Figures 1 to 10 As shown, an embodiment of the present invention provides a method for automatically adding a curve tolerance judgment window based on AI, and the method steps for adding a curve tolerance judgment window are specifically as follows:

[0038] Step 1: Data loading and threshold calculation: Load historical press curve data, calculate Dx and Dy for each press curve respectively; take the maximum value of Dx and Dy as the threshold Dt for curve calculation, and this threshold Dt is also used to generate the tolerance value of the curve tolerance judgment window;

[0039] like Figure 3 As shown, curve 1 (green): Dx = 72.05 Dy = 37.2

[0040] Curve 2 (red): Dx = 71.95 Dy = 36.6

[0041] Curve 3 (blue): Dx = 80.6 Dy = 36.8

[0042] Curve 4 (purple): Dx = 69.55 Dy = 37.45

[0043] Curve 5 (orange): Dx = 68.45 Dy = 37.1

[0044] According to the above data, Dt = 72.05;

[0045] Figure 3The seemingly coherent curve in the figure is actually a series of discrete single points in the underlying data inside the controller. Each point is marked in the order of acquisition. For the convenience of description and calculation, only about 30 points are retained, such as Figure 4 , Figure 5 , Figure 6 , Figure 7 , Figure 8 As shown;

[0046] Step 2: Determine the baseline: hash the points on the curve, select the point with the minimum X-axis coordinate as the starting point, the point with the maximum X-axis coordinate as the end point, and connect the two points to form a straight line as the baseline;

[0047] Step 3, calculate the maximum offset: calculate the maximum distance Dmax from all points of the curve to the baseline (including the starting point and the end point);

[0048] From the calculation results in the table below, it can be concluded that the maximum distance is 323.359 (the 10th point)

[0049]

[0050]

[0051] Take the 10th point as the new starting point, and form a straight line with the last point, and calculate the maximum distance Dmax from the 10th point to the straight line. From the calculation results in the table below, it can be concluded that the maximum distance is 488.272 (the 13th point).

[0052] Point number Distance from point to line 10 0 11 211.247 12 445.408 13 488.272 14 488.095 15 461.994 16 432.043 17 381.506 18 357.552 19 351.288 20 348.401 21 255.227 22 231.56 23 135.92 24 129.006 25 107.716 26 80.4352 27 59.1795 28 43.1689 29 30.4594 30 0

[0053] Take the 13th point as the new starting point, and form a straight line with the last point, and calculate the maximum distance Dmax from the 13th point to the straight line. From the calculation results in the table below, if it does not exceed Dt (the preset threshold), then end;

[0054] Point number Distance from point to line 13 0 14 15.8325 15 11.1964 16 1.86702 17 13.9199 18 16.4457 19 18.3711 20 17.1024 21 2.41585 22 4.55965 23 23.0157 24 21.5584 25 15.9894 26 9.42698 27 1.00758 28 4.95055 29 14.112 30 0

[0055] From the above algorithm, we can find the points with serial numbers 1, 10, 13, and 30, and then combine them with the tolerance value Dt of the curve tolerance judgment window. The Y-axis coordinate +Dt / 2 forms the upper tolerance window; the Y-axis coordinate -Dt / 2 forms the lower tolerance window, such as Fig. 9 As shown;

[0056] In the same way, the five historical curves in the first step can be fitted to obtain the final curve tolerance judgment window, such as Fig.10 shown.

[0057] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0058] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for automatically adding a curve tolerance judgment window based on AI, characterized in that: The method steps for adding a curve tolerance judgment window are as follows: Step 1: Data loading and threshold calculation: Load historical press curve data, calculate Dx and Dy for each press curve respectively; take the maximum value of Dx and Dy as the threshold Dt for curve calculation, and this threshold Dt is also used to generate the tolerance value of the curve tolerance judgment window; Step 2: Determine the baseline: hash the points on the curve, select the point with the minimum X-axis coordinate as the starting point, the point with the maximum X-axis coordinate as the end point, and connect the two points to form a straight line as the baseline; Step 3, calculate the maximum offset: calculate the maximum distance Dmax from all points of the curve to the baseline (including the starting point and the end point); Step 4: Simplify the curve (based on threshold judgment): If Dmax is less than Dt, the first and last points are retained, and all the intermediate points are deleted, and the simplification process is completed; If Dmax is greater than or equal to Dt, the point corresponding to Dmax is used as the new starting point, and the new baseline is reconnected with the end point, and the original starting point is recorded, and the next step is continued; Step 5, iterative simplification: repeat the above steps 3 and 4 until the maximum distance Dmax of all points to the new baseline is less than Dt, at which point the simplification process ends; Step 6: Reconstruct the simplified curve: Use all the points passing through the starting point and the end point of the original curve to form the final simplified curve; Step 7, generate tolerance window: translate the simplified curve in step 6 by half the distance Dt along the positive and negative directions of the Y axis respectively. The connecting lines formed are the upper tolerance window and the lower tolerance window. The tolerance judgment window of the curve is defined by these two lines.

2. The method for automatically adding a curve tolerance judgment window based on AI according to claim 1, characterized in that: The calculation formulas of Dx and Dy in step 1 are:

3. The method for automatically adding a curve tolerance judgment window based on AI according to claim 1, characterized in that: The upper tolerance window and the lower tolerance window in step seven are respectively:

4. The method for automatically adding a curve tolerance judgment window based on AI according to claim 1, characterized in that: The method also includes step eight, i.e. dynamically adjusting the threshold Dt: after generating the tolerance window, according to the requirements of the actual application scenario, the user is allowed to manually adjust the threshold Dt and re-execute steps two to seven to generate a tolerance judgment window that meets different accuracy requirements.

5. The method for automatically adding a curve tolerance judgment window based on AI according to claim 1, characterized in that: The method also includes step nine, namely, abnormality detection: after generating the tolerance judgment window, the original pressing curve is traversed to determine whether each point on the curve falls within the tolerance judgment window. If there is a point that exceeds the tolerance window range, it is marked as an abnormal point and an abnormality report is output.

6. The method for automatically adding a curve tolerance judgment window based on AI according to claim 1, characterized in that: The method also includes step ten, namely, data visualization: displaying the original press-fitting curve, the simplified curve and the tolerance judgment window to the user in the form of a graphical interface, so that the user can intuitively understand the curve tolerance and conduct subsequent analysis.

7. The method for automatically adding a curve tolerance judgment window based on AI according to claim 1, characterized in that: The method also supports simultaneous processing of multiple curves, and can load and process multiple pressing curves at the same time, generate respective tolerance judgment windows, and improve processing efficiency and automation level.

Images