Deviation correction compensation identification method for automatic cutting process of film laminating machine

By segmenting and identifying feature points in real-time monitoring images of the automatic cutting process of the lamination machine, deviation correction compensation is achieved, the relative error problem of unstable system coordination is solved, and product quality is improved.

CN118927325APending Publication Date: 2024-11-12SHENZHEN BANGZHENG PRECISION MACHINERY CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410994545.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

During operation, the film coating machine is unstable in system coordination, which leads to the relative error between the conveyor belt and the cutting position, which increases the defective rate of the final product, and requires an effective cutting monitoring and compensation treatment solution.

Method used

By obtaining real-time monitoring images of the automatic cutting process of the lamination machine, initial deviations are identified and bias correction compensation is performed, including image segmentation, feature point extraction and standardized coordinate system establishment, and gradually screening and verification are used to determine the bias correction compensation results.

Benefits of technology

It improves the accuracy and efficiency of deviation correction identification, reduces interference to actual production, and reduces defective rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118927325A_ABST
    Figure CN118927325A_ABST
Patent Text Reader

Abstract

The invention relates to the field of deviation correction identification monitoring of an automatic cutting process production line of a film laminating machine, in particular to a deviation correction compensation identification method for an automatic cutting process of a film laminating machine, which comprises the following steps: S1, acquiring a real-time monitoring image of the automatic cutting process of the film laminating machine; s2, acquiring an initial deviation identification screening result according to the real-time monitoring image of the automatic cutting process of the film laminating machine; and S3, according to the initial deviation identification screening result, obtaining a deviation correction compensation identification result, in actual film coating cutting actual production, carrying out assembly line processing, dividing error identification into a minimum unit interval through step-by-step analysis of a monitoring image, carrying out comprehensive research and judgment on a feature region contour of the segmented image, and carrying out complex problem simplification processing, so as to obtain a film coating cutting result. The accuracy and efficiency of deviation correction identification are improved, and meanwhile interference to actual production is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of deviation correction, recognition and monitoring of an automatic cutting process production line of a laminating machine, and in particular to a deviation correction, compensation and recognition method for an automatic cutting process of a laminating machine. Background Art

[0002] When the laminating machine is working normally, the laminated material is cut by the operation of the conveyor belt. However, due to the unstable factors in the overall coordination between the systems, relative errors are easily generated between the conveyor belt and the cutting position, resulting in an increase in the defective rate of the final product. A practical cutting monitoring and compensation solution is urgently needed. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a correction compensation identification method for the automatic cutting process of a laminating machine. By segmenting and dividing the cutting process production line data, the regional image content is identified one by one, providing a guarantee for the final correction compensation.

[0004] To achieve the above object, the present invention provides a correction compensation identification method for an automatic cutting process of a laminating machine, comprising:

[0005] S1. Obtaining real-time monitoring images of the automatic cutting process of the laminating machine;

[0006] S2, obtaining an initial deviation identification and screening result according to a real-time monitoring image of the automatic cutting process of the laminating machine;

[0007] S3. Obtaining a correction compensation identification result according to the initial deviation identification screening result.

[0008] Preferably, the step of obtaining a real-time monitoring image of the automatic cutting process of the laminating machine includes:

[0009] Obtain the initial real-time monitoring image of the automatic cutting process of the laminating machine;

[0010] Acquire the target area of ​​the automatic cutting process of the laminating machine by using the initial real-time monitoring image;

[0011] The initial real-time monitoring image is marked according to the target area of ​​the automatic cutting process of the laminating machine to obtain the real-time monitoring image of the automatic cutting process of the laminating machine.

[0012] Furthermore, the target area of ​​the automatic cutting process of the laminating machine obtained by using the initial real-time monitoring image includes:

[0013] Extracting a corresponding monitoring area of ​​the automatic cutting process of the laminating machine according to the initial real-time monitoring image;

[0014] Acquire the corresponding monitoring area of ​​the automatic cutting process of the laminating machine as a geometric feature point;

[0015] The geometric feature points are used to obtain standardized geometric feature point coordinates as the target area of ​​the automatic cutting process of the laminating machine.

[0016] Further, using the geometric feature points to obtain standardized geometric feature point coordinates as the target area of ​​the automatic cutting process of the laminating machine includes:

[0017] Using the centroid projection point of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine as the coordinate origin;

[0018] According to the coordinate origin, a front view horizontal line of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine is used as a standardized coordinate X axis;

[0019] According to the coordinate origin, a vertical line of the horizontal line of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine is used as the standardized coordinate Y axis;

[0020] The geometric feature points are used to obtain a target area of ​​the automatic cutting process of the laminating machine according to the coordinate origin, the standardized coordinate X axis and the standardized coordinate Y axis.

[0021] Furthermore, obtaining the initial deviation identification and screening results based on the real-time monitoring image of the automatic cutting process of the laminating machine includes:

[0022] S2-1, obtaining historical real-time monitoring images of the real-time monitoring images of the automatic cutting process of the laminating machine to establish an image comparison set;

[0023] S2-2, performing a rough screening according to the image comparison set to obtain a first initial deviation identification and screening result;

[0024] S2-3. Perform fine screening according to the first initial deviation identification and screening result to obtain an initial deviation identification and screening result.

[0025] Furthermore, the first initial deviation identification screening result obtained by performing rough screening according to the image comparison set includes:

[0026] S2-2-1. Obtain the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine;

[0027] S2-2-2. Determine whether the difference ratio between the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine and the horizontal projection area of ​​any subset in the image comparison set is greater than 50%. If so, directly output the first initial deviation identification and screening result as abnormal. Otherwise, the first initial deviation identification and screening result is normal, and output the historical real-time monitoring image with the highest similarity between the horizontal projection area of ​​each subset in the image comparison set and the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine as the historical individual similarity identification image.

[0028] Further, the initial deviation identification and screening results obtained by performing fine screening according to the first initial deviation identification and screening results include:

[0029] S2-3-1, determine whether the first initial deviation identification and screening result is normal, if so, obtain the similarity between the horizontal projection area of ​​the real-time monitoring image of the current laminating machine automatic cutting process and the horizontal projection area of ​​the historical individual similar identification image as the fine screening threshold, and execute S2-3-2, otherwise, output the initial deviation identification and screening result as abnormal;

[0030] S2-3-2, using the individual similarity recognition image to obtain the coordinates of the standardized geometric feature points corresponding to the historical individual similarity recognition image according to the coordinate origin, the standardized coordinate X axis and the standardized coordinate Y axis;

[0031] S2-3-3, obtaining the similarity between the standardized geometric feature point coordinates of the real-time monitoring image of the current laminating machine automatic cutting process and the standardized geometric feature point coordinates corresponding to the historical individual similarity recognition image as the fine screening similarity;

[0032] S2-3-4. Determine whether the fine screening similarity is the same as the fine screening threshold. If so, the initial deviation identification and screening result is normal; otherwise, the initial deviation identification and screening result is abnormal.

[0033] Furthermore, obtaining the correction compensation identification result according to the initial deviation identification screening result includes:

[0034] S3-1, when the initial deviation identification screening result is abnormal, the correction compensation identification result is abnormal, and a real-time monitoring image of the current automatic cutting process of the laminating machine is output;

[0035] S3-2: When the initial deviation identification and screening result is normal, coordinate self-verification processing is performed using the real-time monitoring image of the automatic cutting process of the laminating machine to obtain a correction compensation identification result.

[0036] Furthermore, the coordinate self-verification processing is performed using the real-time monitoring image of the automatic cutting process of the laminating machine to obtain the correction compensation identification result, including:

[0037] S3-2-1. Obtain the horizontal projection area of ​​the real-time monitoring image of the automatic cutting process of the laminating machine as the standard area;

[0038] S3-2-2, obtaining the calculated value area of ​​the real-time monitoring image of the automatic cutting process of the laminating machine according to the standardized geometric feature point coordinates of the real-time monitoring image of the automatic cutting process of the laminating machine;

[0039] S3-2-3, determine whether the standard area is larger than the calculated area, if so, the correction compensation recognition result is abnormal, otherwise, execute S3-2-4;

[0040] S3-2-4. Determine whether the perimeter of the graphic corresponding to the standard area is greater than the sum of the geometric feature distances of the real-time monitoring image of the automatic cutting process of the laminating machine. If so, the correction compensation recognition result is abnormal; otherwise, the correction compensation recognition result is normal.

[0041] Compared with the closest prior art, the present invention has the following beneficial effects:

[0042] In the actual production of lamination and cutting, the assembly line processing, through the step-by-step analysis of the monitoring image, divides the error recognition into the smallest unit interval, conducts a comprehensive analysis of the feature area contours of the segmented image, simplifies the processing of complex problems, improves the accuracy and efficiency of correction recognition, and reduces interference with actual production. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 The present invention provides a flow chart of a deviation correction compensation identification method for an automatic cutting process of a laminating machine. DETAILED DESCRIPTION

[0044] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0046] Embodiment 1:

[0047] The present invention provides a correction compensation identification method for the automatic cutting process of a laminating machine, such as Figure 1 As shown, including:

[0048] S1. Obtaining real-time monitoring images of the automatic cutting process of the laminating machine;

[0049] S2, obtaining an initial deviation identification and screening result according to a real-time monitoring image of the automatic cutting process of the laminating machine;

[0050] S3. Obtaining a correction compensation identification result according to the initial deviation identification screening result.

[0051] S1 specifically includes:

[0052] S1-1, obtaining an initial real-time monitoring image of the automatic cutting process of the laminating machine;

[0053] S1-2, using the initial real-time monitoring image to obtain the target area of ​​the automatic cutting process of the laminating machine;

[0054] S1-3, marking the initial real-time monitoring image according to the target area of ​​the automatic cutting process of the laminating machine to obtain a real-time monitoring image of the automatic cutting process of the laminating machine.

[0055] S1-2 specifically includes:

[0056] S1-2-1, extracting the corresponding monitoring area of ​​the automatic cutting process of the laminating machine according to the initial real-time monitoring image;

[0057] S1-2-2, obtaining the corresponding monitoring area of ​​the automatic cutting process of the laminating machine as a geometric feature point;

[0058] S1-2-3. Use the geometric feature points to obtain standardized geometric feature point coordinates as the target area of ​​the automatic cutting process of the laminating machine.

[0059] S1-2-3 specifically includes:

[0060] S1-2-3-1, using the centroid projection point of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine as the coordinate origin;

[0061] S1-2-3-2, using the horizontal line of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine as the standardized coordinate X-axis according to the coordinate origin;

[0062] S1-2-3-3, using the vertical line of the horizontal line of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine as the standardized coordinate Y axis according to the coordinate origin;

[0063] S1-2-3-4. Utilize the geometric feature points to obtain the target area of ​​the automatic cutting process of the laminating machine according to the coordinate origin, the standardized coordinate X-axis and the standardized coordinate Y-axis.

[0064] S2 specifically includes:

[0065] S2-1, obtaining historical real-time monitoring images of the real-time monitoring images of the automatic cutting process of the laminating machine to establish an image comparison set;

[0066] S2-2, performing a rough screening according to the image comparison set to obtain a first initial deviation identification and screening result;

[0067] S2-3. Perform fine screening according to the first initial deviation identification and screening result to obtain an initial deviation identification and screening result.

[0068] S2-2 specifically includes:

[0069] S2-2-1. Obtain the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine;

[0070] S2-2-2. Determine whether the difference ratio between the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine and the horizontal projection area of ​​any subset in the image comparison set is greater than 50%. If so, directly output the first initial deviation identification and screening result as abnormal. Otherwise, the first initial deviation identification and screening result is normal, and output the historical real-time monitoring image with the highest similarity between the horizontal projection area of ​​each subset in the image comparison set and the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine as the historical individual similarity identification image.

[0071] S2-3 specifically includes:

[0072] S2-3-1, determine whether the first initial deviation identification and screening result is normal, if so, obtain the similarity between the horizontal projection area of ​​the real-time monitoring image of the current laminating machine automatic cutting process and the horizontal projection area of ​​the historical individual similar identification image as the fine screening threshold, and execute S2-3-2, otherwise, output the initial deviation identification and screening result as abnormal;

[0073] S2-3-2, using the individual similarity recognition image to obtain the coordinates of the standardized geometric feature points corresponding to the historical individual similarity recognition image according to the coordinate origin, the standardized coordinate X axis and the standardized coordinate Y axis;

[0074] S2-3-3, obtaining the similarity between the standardized geometric feature point coordinates of the real-time monitoring image of the current laminating machine automatic cutting process and the standardized geometric feature point coordinates corresponding to the historical individual similarity recognition image as the fine screening similarity;

[0075] S2-3-4. Determine whether the fine screening similarity is the same as the fine screening threshold. If so, the initial deviation identification and screening result is normal; otherwise, the initial deviation identification and screening result is abnormal.

[0076] S3 specifically includes:

[0077] S3-1, when the initial deviation identification screening result is abnormal, the correction compensation identification result is abnormal, and a real-time monitoring image of the current automatic cutting process of the laminating machine is output;

[0078] S3-2: When the initial deviation identification and screening result is normal, coordinate self-verification processing is performed using the real-time monitoring image of the automatic cutting process of the laminating machine to obtain a correction compensation identification result.

[0079] S3-2 specifically includes:

[0080] S3-2-1. Obtain the horizontal projection area of ​​the real-time monitoring image of the automatic cutting process of the laminating machine as the standard area;

[0081] S3-2-2, obtaining the calculated value area of ​​the real-time monitoring image of the automatic cutting process of the laminating machine according to the standardized geometric feature point coordinates of the real-time monitoring image of the automatic cutting process of the laminating machine;

[0082] S3-2-3, determine whether the standard area is larger than the calculated area, if so, the correction compensation recognition result is abnormal, otherwise, execute S3-2-4;

[0083] S3-2-4. Determine whether the perimeter of the graphic corresponding to the standard area is greater than the sum of the geometric feature distances of the real-time monitoring image of the automatic cutting process of the laminating machine. If so, the correction compensation recognition result is abnormal; otherwise, the correction compensation recognition result is normal.

[0084] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A correction compensation identification method for the automatic cutting process of a laminating machine, characterized in that: include: S1. Obtaining real-time monitoring images of the automatic cutting process of the laminating machine; S2. Obtaining initial deviation identification and screening results based on the real-time monitoring image of the automatic cutting process of the laminating machine; S3. Obtaining a correction compensation identification result according to the initial deviation identification screening result.

2. A method for correcting and compensating for automatic cutting process of a laminating machine as claimed in claim 1, characterized in that: The real-time monitoring image of the automatic cutting process of the laminating machine is obtained, which includes: Obtain the initial real-time monitoring image of the automatic cutting process of the laminating machine; Acquire the target area of ​​the automatic cutting process of the laminating machine by using the initial real-time monitoring image; The initial real-time monitoring image is marked according to the target area of ​​the automatic cutting process of the laminating machine to obtain the real-time monitoring image of the automatic cutting process of the laminating machine.

3. A method for correcting and compensating for automatic cutting process of a laminating machine as claimed in claim 2, characterized in that: The target areas for obtaining the automatic cutting process of the laminating machine using the initial real-time monitoring image include: Extracting a corresponding monitoring area of ​​the automatic cutting process of the laminating machine according to the initial real-time monitoring image; Acquire the corresponding monitoring area of ​​the automatic cutting process of the laminating machine as a geometric feature point; The geometric feature points are used to obtain standardized geometric feature point coordinates as the target area of ​​the automatic cutting process of the laminating machine.

4. A method for correcting and compensating for automatic cutting process of a laminating machine as claimed in claim 3, characterized in that: The use of the geometric feature points to obtain the standardized geometric feature point coordinates as the target area of ​​the automatic cutting process of the laminating machine includes: Using the centroid projection point of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine as the coordinate origin; According to the coordinate origin, a front view horizontal line of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine is used as a standardized coordinate X axis; According to the coordinate origin, a vertical line of the horizontal line of the corresponding monitoring area of ​​the automatic cutting process of the laminating machine is used as the standardized coordinate Y axis; The geometric feature points are used to obtain a target area of ​​the automatic cutting process of the laminating machine according to the coordinate origin, the standardized coordinate X axis and the standardized coordinate Y axis.

5. A method for correcting and compensating for automatic cutting process of a laminating machine as claimed in claim 4, characterized in that: The initial deviation identification and screening results obtained based on the real-time monitoring image of the automatic cutting process of the laminating machine include: S2-1, obtaining historical real-time monitoring images of the real-time monitoring images of the automatic cutting process of the laminating machine to establish an image comparison set; S2-2, performing a rough screening according to the image comparison set to obtain a first initial deviation identification and screening result; S2-3. Perform fine screening according to the first initial deviation identification and screening result to obtain an initial deviation identification and screening result.

6. A method for correcting and compensating for automatic cutting process of a laminating machine as claimed in claim 5, characterized in that: The first initial deviation identification screening result obtained by performing rough screening according to the image comparison set includes: S2-2-1. Obtain the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine; S2-2-2. Determine whether the difference ratio between the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine and the horizontal projection area of ​​any subset in the image comparison set is greater than 50%. If so, directly output the first initial deviation identification and screening result as abnormal. Otherwise, the first initial deviation identification and screening result is normal, and output the historical real-time monitoring image with the highest similarity between the horizontal projection area of ​​each subset in the image comparison set and the horizontal projection area of ​​the real-time monitoring image of the current automatic cutting process of the laminating machine as the historical individual similarity identification image.

7. A method for correcting and compensating for automatic cutting process of a laminating machine as claimed in claim 6, characterized in that: The initial deviation identification and screening results obtained by performing fine screening according to the first initial deviation identification and screening results include: S2-3-1, determine whether the first initial deviation identification and screening result is normal, if so, obtain the similarity between the horizontal projection area of ​​the real-time monitoring image of the current laminating machine automatic cutting process and the horizontal projection area of ​​the historical individual similar identification image as the fine screening threshold, and execute S2-3-2, otherwise, output the initial deviation identification and screening result as abnormal; S2-3-2, using the individual similarity recognition image to obtain the coordinates of the standardized geometric feature points corresponding to the historical individual similarity recognition image according to the coordinate origin, the standardized coordinate X axis and the standardized coordinate Y axis; S2-3-3, obtaining the similarity between the standardized geometric feature point coordinates of the real-time monitoring image of the current laminating machine automatic cutting process and the standardized geometric feature point coordinates corresponding to the historical individual similarity recognition image as the fine screening similarity; S2-3-4. Determine whether the fine screening similarity is the same as the fine screening threshold. If so, the initial deviation identification and screening result is normal; otherwise, the initial deviation identification and screening result is abnormal.

8. A method for correcting and compensating for automatic cutting process of a laminating machine as claimed in claim 7, characterized in that: Obtaining the correction compensation identification result according to the initial deviation identification screening result includes: S3-1, when the initial deviation identification screening result is abnormal, the correction compensation identification result is abnormal, and a real-time monitoring image of the current automatic cutting process of the laminating machine is output; S3-2: When the initial deviation identification and screening result is normal, coordinate self-verification processing is performed using the real-time monitoring image of the automatic cutting process of the laminating machine to obtain a correction compensation identification result.

9. A method for correcting and compensating for automatic cutting process of a laminating machine as claimed in claim 8, characterized in that: The coordinate self-verification processing is performed using the real-time monitoring image of the automatic cutting process of the laminating machine to obtain the correction compensation recognition results including: S3-2-1. Obtain the horizontal projection area of ​​the real-time monitoring image of the automatic cutting process of the laminating machine as the standard area; S3-2-2, obtaining the calculated value area of ​​the real-time monitoring image of the automatic cutting process of the laminating machine according to the standardized geometric feature point coordinates of the real-time monitoring image of the automatic cutting process of the laminating machine; S3-2-3, determine whether the standard area is larger than the calculated area, if so, the correction compensation recognition result is abnormal, otherwise, execute S3-2-4; S3-2-4. Determine whether the perimeter of the graphic corresponding to the standard area is greater than the sum of the geometric feature distances of the real-time monitoring image of the automatic cutting process of the laminating machine. If so, the correction compensation recognition result is abnormal; otherwise, the correction compensation recognition result is normal.

Citation Information

Patent Citations

  • Size measurement method of corrugated board and paper separation pressure line control method and system

    CN104999504A

  • Laminating die cutting equipment for flexible material and die cutting method of laminating die cutting equipment

    CN115139368A

  • Die cutting automatic compensation method and device, electronic equipment and storage medium

    CN115816552A

  • Error identification method for irregular bumper surface shape

    CN117128888A

  • Method for making composite parts with a surface which cannot be unrolled

    EP4074495A1