Intelligent defect detecting and marking system and method

Abstract

The invention relates to an intelligent defect detection and marking system and method, which is applied to the field of defect detection, and comprises an X-ray detection module used for scanning a to-be-detected package and generating a package X-ray image in real time; the image processing module is connected to the X-ray detection module and is used for receiving the X-ray image of the packaging part and carrying out defect detection on the packaging part to be detected according to the X-ray image of the packaging part; the control module is connected to the image processing module and is used for outputting a control instruction according to the defect detection result and controlling the laser marking module to mark the packaging piece; and the laser marking module is connected to the control module and is used for receiving the control instruction and carrying out marking treatment on the packaging piece subjected to defect detection according to the control instruction. The method has the technical effects that the defect detection is completed before the marking process of the packaging piece, the operation process is simplified, and the production efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of defect detection technology, and in particular to an intelligent defect detection and marking system and method. Background Art

[0002] Laser marking equipment is mainly used to mark the surface of packages, but this type of equipment cannot detect defects that are invisible to the naked eye without destroying the packages, reflect the internal information of the product, and screen out good and bad products.

[0003] On the production line, the existing laser marking system cannot effectively handle the detected internal defects of the package. It is inevitable that operational errors such as missed detection and wrong detection will occur during screening and rejection. There will also be unstable factors, resulting in unqualified products still flowing into downstream processes after marking, affecting subsequent production and thus reducing production efficiency. Summary of the invention

[0004] In order to help solve the problem that the existing laser marking system cannot effectively handle the detected internal defects of the package, and that the screening and rejection work will inevitably lead to operational errors such as missed detection and wrong detection, and there will also be unstable factors, resulting in unqualified products still flowing into the downstream process after marking, affecting subsequent production, thereby reducing production efficiency, the present application provides an intelligent defect detection and marking system and method.

[0005] In a first aspect, the present application provides an intelligent defect detection and marking system, which adopts the following technical solution: the intelligent defect detection and marking system includes an X-ray detection module, an image processing module, a control module and a laser marking module;

[0006] The X-ray detection module is used to scan the package to be detected and generate an X-ray image of the package in real time;

[0007] The image processing module is connected to the X-ray detection module, and is used to receive the package X-ray image, and perform defect detection on the package to be detected according to the package X-ray image;

[0008] The control module is connected to the image processing module and is used to output control instructions according to the defect detection results to control the laser marking module to mark the package;

[0009] The laser marking module is connected to the control module, and is used for receiving control instructions and marking the packaged parts after defect detection according to the control instructions.

[0010] In a specific possible implementation scheme, the X-ray detection module includes an X-ray source, a detector and an imaging unit;

[0011] The X-ray source is used to emit X-rays to penetrate the package to be inspected;

[0012] The detector is used to receive the X-rays emitted by the X-ray source and convert the received X-rays into digital image signals;

[0013] The imaging unit is used to receive the digital image signal, process the digital image signal and generate an X-ray image of the package;

[0014] Wherein, the X-ray source and the detector operate synchronously.

[0015] In a specific possible implementation scheme, the control instruction output by the control module includes a qualified part mark and a failed part mark;

[0016] When the control instruction output by the control module is a qualified part mark, the laser marking module is controlled to perform a qualified mark on the packaged part;

[0017] When the control instruction output by the control module is a non-conforming part mark, the laser marking module is controlled to mark the package as non-conforming.

[0018] In a specific implementation scheme, controlling the laser marking module to mark the package as unqualified includes:

[0019] The laser marking module is controlled to skip marking or perform a failure marking on the package.

[0020] In a specific possible implementation scheme, the laser marking module includes a laser source, a marking platform and a control interface;

[0021] The laser source is used to emit a laser beam to mark the surface of the package after defect detection according to the marking path;

[0022] The marking platform is used to control the laser beam to cover the area of ​​the package where defect detection is completed;

[0023] The control interface is used to receive the control instruction and generate a marking path of the laser beam according to the control instruction.

[0024] In a second aspect, the present application provides an intelligent defect detection and marking method, which adopts the following technical solution: the method comprises:

[0025] The X-ray detection module receives a package to be detected, scans the package to be detected and generates an X-ray image of the package in real time;

[0026] The image processing module receives the package X-ray image, performs defect detection on the package X-ray image and generates a defect detection result;

[0027] The control module outputs corresponding control instructions according to the defect detection result;

[0028] The laser marking module receives the control instruction and performs marking processing on the packaged component that has completed defect detection according to the control instruction.

[0029] In a specific implementation scheme, the image processing module performs defect detection on the package X-ray image and generates a defect detection result, including:

[0030] The image processing module pre-processes the X-ray image of the package and generates a clear image of the package;

[0031] The image processing module uses a deep learning algorithm to extract features from the package denoised image, and identifies defects in the package clear image based on the extracted features;

[0032] The image processing module outputs corresponding defect detection results according to the identified defects.

[0033] In a specific implementation manner, the image processing module preprocesses the package X-ray image including:

[0034] The image processing module performs image denoising, image enhancement and image binarization processing on the package X-ray image.

[0035] In a specific implementation scheme, the image processing module outputs corresponding defect detection results according to the identified defects, including:

[0036] The image processing module determines whether a defect is identified;

[0037] If no defect is identified, the package to be inspected is determined to be qualified;

[0038] If a defect is identified, the size of the identified defect is calculated and it is determined whether the size of the defect is within a preset threshold range;

[0039] If the size of the defect is within a preset threshold range, the package to be inspected is determined to be qualified;

[0040] If the size of the defect is not within the preset threshold range, the package to be inspected is determined to be unqualified.

[0041] In a specific implementation scheme, the deep learning algorithm used by the image processing module is a convolutional neural network.

[0042] In summary, this application has the following beneficial technical effects:

[0043] 1. This application integrates X-ray detection and laser marking functions into the same system, so that the package can be inspected for internal and external defects before entering the marking process; the integrated design simplifies the production process and reduces the dependence on multiple devices, thereby reducing the complexity of the production line and equipment costs; in addition, the integrated equipment design reduces the number of equipment on the production line and maintenance costs;

[0044] 2. The system can identify external and internal defects of packages in X-ray inspection scans, including cracks, voids, bubbles, surface scratches, etc. Through the application of deep learning technology, it has efficient feature extraction and defect recognition capabilities, greatly improving the detection accuracy;

[0045] 3. Through the linkage of the image processing module and the control module, it can automatically make marking decisions based on the inspection results of the package; if a serious defect is detected in the package, the system will automatically skip the marking of the package or mark "FAIL" on its surface, thereby preventing unqualified products from entering the downstream links. The intelligent marking function effectively improves the quality control level of the production line;

[0046] 4. Integrate the inspection and marking processes into a continuous workflow, and reduce manual intervention through automated control, greatly reduce operational errors caused by manual labor, save manpower time costs, and significantly improve production efficiency; the packaged parts do not need to be transferred and waited between different devices, which greatly shortens the production cycle and improves the accuracy and production efficiency of the operation process;

[0047] 5. The system is highly flexible and can be adjusted by software to adapt to different types of packages and production requirements; whether it is adjusting the parameters of X-ray inspection or the content of laser marking, it can be achieved through simple software configuration, which enhances the versatility of the system;

[0048] 6. The system can record the inspection results and marking information of each package in real time, forming a closed-loop management of production data. These data not only help to trace quality problems in the production process, but also can be used to optimize the production process and improve overall production efficiency. The equipment is equipped with powerful image processing software, which can perform precise product inspection through the system and support real-time image display, so that the operator can see the operation results and make necessary adjustments in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the framework of the intelligent defect detection and marking system in the embodiment of the present application;

[0050] Figure 2is a schematic diagram of the operation of the X-ray detection module in an embodiment of the present application;

[0051] Figure 3 is a flow chart of an intelligent defect detection and marking method in an embodiment of the present application;

[0052] Reference numerals: 101, X-ray detection module; 102, image processing module; 103, control module; 104, laser marking module. DETAILED DESCRIPTION

[0053] The following combination Figure 1-Figure 3 This application is described in further detail.

[0054] The embodiment of the present application discloses an intelligent defect detection and marking system, which can detect internal and external defects of the package before entering the marking process. In the production line, laser marking can mark the package with relevant information, including conventional serial number, batch number and other information, so that the key information of the package is clear at a glance, allowing users to better understand the information of the package and better find and use these packages. However, it is difficult for laser marking equipment to detect defects that are invisible to the naked eye without destroying the package, reflect the internal information of the product, and screen out good and bad products.

[0055] At present, on the production line, packages are usually inspected by independent X-ray inspection equipment (X-Ray inspection equipment), and then marked by laser marking equipment. This separate process will greatly increase the workload of operators, which not only increases the time cost, but also increases the complexity of operation. In addition, the existing laser marking system cannot effectively handle the detected internal defects of the package. When screening and removing, it will inevitably lead to operational errors such as missed inspections and wrong inspections, and there will also be unstable factors, resulting in unqualified products that may still flow into downstream processes after marking, affecting subsequent production. In order to help detect defects inside packages and improve production efficiency, the present application provides an intelligent defect detection and marking system.

[0056] Reference Figure 1 The intelligent defect detection and marking system includes an X-ray detection module 101, an image processing module 102, a control module 103 and a laser marking module 104; the intelligent defect detection and marking system also includes a feed port and a discharge port, and the package to be inspected enters the intelligent defect detection and marking system through the feed port.

[0057] The X-ray detection module 101, also known as the X-Ray detection module, is used to scan the package to be inspected and generate an X-ray image of the package in real time; the image processing module 102 is connected to the X-ray detection module, and is used to receive the X-ray image of the package, and perform defect detection on the package to be inspected based on the X-ray image of the package; the control module 103 is connected to the image processing module, and is used to output a control instruction based on the defect detection result, and control the laser marking module to mark the package; the laser marking module 104 is connected to the control module, and is used to receive the control instruction, and mark the package that has completed the defect detection according to the control instruction.

[0058] It should be noted that, considering the radiation of X-rays, the overall shell of the system adopts a special operation equipment protective cover, which is a three-layer metal plate processed from steel-lead-steel. The visible glass window is also installed with lead glass with a thickness of 21.6mm, which is used to set up a comprehensive shield between the radiation source and the staff, greatly reducing or eliminating the radiation to avoid harm to the human body.

[0059] Through the above technical solution, X-Ray detection and laser marking functions are integrated into the same system, so that the package can complete the internal and external defect detection before entering the marking process, solving the problem that it is difficult to detect internal and external defects of the package through the standard system in the existing system; the integrated design simplifies the production process and reduces the dependence on multiple equipment, thereby reducing the complexity of the production line and equipment costs. In addition, the entire system reduces human intervention through automated control, greatly reduces operational errors caused by manual labor, saves manpower time costs, and thus improves production efficiency; the package does not need to be transferred and waited between different equipment, shortening the production cycle, reducing material loss, and improving the accuracy of the operation process.

[0060] The X-ray detection module 101, namely the X-ray detection module, includes an X-ray source, a detector and an imaging unit. Figure 2 , the X-ray source tube emits X-rays through the package to be detected, so as to obtain the internal structure image of the package to be detected. The X-ray source is used to emit X-rays to penetrate the package to be detected. In the embodiment of the present application, an X-ray source tube is used; the detector is used to receive the X-rays emitted by the X-ray source and convert the received X-rays into digital image signals. In the embodiment of the present application, an FPD digital flat panel detector is used; the X-ray source and the detector operate synchronously; the imaging unit is used to receive the digital image signal, process the digital image signal and generate an X-ray image of the package. Specifically, the imaging unit includes an industrial control PC host and an imaging display. The industrial control PC host receives the digital image signal, performs image analysis on the received digital image signal, and finally outputs the final X-ray image of the package through the image imaging display.

[0061] The image processing module 102 is mainly used to process and analyze the package X-ray image data provided by the X-Ray detection module, and output corresponding defect detection results.

[0062] The control module 103 is connected to the image processing module 102 and the laser marking module 104. The control instructions output by the control module 103 include qualified part marking and unqualified part marking. When the control instruction output by the control module is a qualified part marking, the laser marking module is controlled to mark the package as qualified. When the control instruction output by the control module is an unqualified part marking, the laser marking module is controlled to mark the package as unqualified. The unqualified marking method includes skipping the mark or performing a failure mark. Skipping the mark means not marking the package that has been inspected. The failure mark means marking a "FAIL" mark on the surface of the package to clearly indicate that the product is unqualified. Among them, the qualified mark refers to controlling the laser marking module to mark the qualified package with conventional serial number, batch number and other information; and the unqualified mark means controlling the laser marking module to skip the mark, or controlling the laser marking module to mark the defective package with a "FAIL" mark.

[0063] The laser marking module 104 includes a laser source, a marking platform and a control interface; the laser source is used to emit a laser beam and mark the surface of the package that has completed defect detection according to the marking path; the marking platform is used to control the laser beam to cover the area of ​​the package that has completed defect detection; the control interface is used to receive control instructions and generate the marking path of the laser beam according to the control instructions. The laser marking module performs corresponding qualified or unqualified marks on the package that has completed detection according to the received instructions.

[0064] Through the linkage of the image processing module and the control module, the marking decision can be automatically made according to the defect detection results of the package; if a defect is detected in the package, the system will automatically skip the marking of the package, or mark "FAIL" on its surface, so as to prevent unqualified products from entering the downstream links. The intelligent marking function can effectively improve the quality control level of the production line. In addition, the system can record the inspection results and marking information of each package in real time to form a closed-loop management of production data. This data not only helps to trace quality problems in the production process, but also can be used to optimize the production process and improve overall production efficiency; the system is equipped with powerful image processing software, which can perform accurate product defect detection through the system and support real-time image display, so that the operator can see the operation results and make necessary adjustments in time to ensure the yield of the final product.

[0065] Through this intelligent defect detection and marking system, the package to be inspected first enters the X-Ray inspection module for external and internal scanning; then, the image data generated by the scan is transmitted to the image processing module for analysis, defect identification and classification; the control module controls the operation of the laser marking module according to the received defect detection results, specifically, the qualified package is marked normally, the unqualified package is skipped or marked with "FAIL"; finally, the laser marking module performs the corresponding marking operation to complete the marking process of the package.

[0066] Based on the above system, an embodiment of the present application also discloses an intelligent defect detection and marking method.

[0067] Reference Figure 3 , the method comprises the following steps:

[0068] S10, the X-ray detection module receives the package to be detected, scans the package to be detected and generates an X-ray image of the package in real time.

[0069] Specifically, the package to be inspected enters the defect detection and marking system through the feed port, and is first received and scanned by the X-ray detection module. The X-ray detection module can generate an X-ray image of the package corresponding to the package to be inspected in real time.

[0070] S20, the image processing module receives the X-ray image of the package, performs defect detection on the X-ray image of the package and generates a defect detection result.

[0071] Specifically, the image processing module performs image processing on the received X-ray image of the package and uses a deep learning algorithm to analyze the image data to achieve defect detection of the package. After the defect detection is completed, the image processing module outputs the corresponding defect detection result.

[0072] S30, the control module outputs corresponding control instructions according to the defect detection result.

[0073] Specifically, the control module receives the defect detection result output by the image processing module, and outputs corresponding control instructions according to the defect detection result to control the laser marking module to complete the corresponding standard-reaching operation.

[0074] S40, the laser marking module receives the control instruction, and performs marking processing on the packaged component after defect detection according to the control instruction.

[0075] Specifically, the laser marking module receives the control instructions from the control module and completes the corresponding marking process according to the control instructions. The marking process mainly includes qualified marking and unqualified marking. The qualified marking is to control the laser marking module to mark the conventional serial number, batch number and other information on the qualified package; the unqualified marking is to control the laser marking module to skip the marking, or to control the laser marking module to mark the defective package with the "FAIL" mark.

[0076] In the present application scheme, defect detection and laser marking functions are integrated, so that the internal and external defects of the package can be detected before entering the marking process, which simplifies the operation process, reduces the complexity of the production line and equipment costs, and improves production efficiency.

[0077] In one embodiment, the step of the image processing module performing defect detection on the package X-ray image and generating defect detection results can be specifically performed as follows:

[0078] The image processing module preprocesses the X-ray image of the package and generates a clear image of the package; the image preprocessing methods include image denoising, image enhancement and image binarization processing to improve the clarity and recognizability of the original acquired image, which is helpful for subsequent defect detection based on the image. After that, the image processing module uses a deep learning algorithm to extract features from the denoised image of the package. The deep learning algorithm used can be a convolutional neural network (CNN). Users can also choose other neural networks for image recognition and defect detection according to actual conditions; then identify defects in the clear image of the package based on the extracted features. The identified defects include internal and external defects of the package. Internal defects include internal structural defects such as cracks, cavities, bubbles, etc., and external defects include surface scratches, edge defects, etc. Finally, the image processing module outputs the corresponding defect detection results based on the identified defects.

[0079] Specifically, the image processing module outputs the corresponding defect detection result according to the identified defect and outputs the corresponding defect detection result according to the severity of the identified defect. The specific implementation steps include:

[0080] The image processing module first determines whether a defect is recognized; if no defect is recognized, the package to be inspected is determined to be qualified; if a defect is recognized, the size of the recognized defect is calculated, and it is determined whether the size of the defect is within a preset threshold range; if the size of the defect is within the preset threshold range, the package to be inspected is determined to be qualified; if the size of the defect is not within the preset threshold range, the package to be inspected is determined to be unqualified.

[0081] Through the image recognition algorithm, external defects and internal defects of the package can be identified in the X-Ray scanned images, including cracks, voids, bubbles, surface scratches, etc. The algorithm uses deep learning technology to have efficient feature extraction and defect recognition capabilities, greatly improving the detection accuracy.

[0082] Figure 3 FIG. 1 is a flow chart of an intelligent defect detection and marking method in one embodiment. It should be understood that although Figure 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but the steps are not necessarily executed in the order indicated by the arrows; unless otherwise specified in this document, there is no strict order restriction for the execution of the steps, and the steps may be executed in other orders; and Figure 3 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0083] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. An intelligent defect detection and marking system, characterized in that: The intelligent defect detection and marking system includes an X-ray detection module, an image processing module, a control module and a laser marking module; The X-ray detection module is used to scan the package to be detected and generate an X-ray image of the package in real time; The image processing module is connected to the X-ray detection module, and is used to receive the package X-ray image, and perform defect detection on the package to be detected according to the package X-ray image; The control module is connected to the image processing module and is used to output control instructions according to the defect detection results to control the laser marking module to mark the package; The laser marking module is connected to the control module, and is used for receiving control instructions and marking the packaged parts after defect detection according to the control instructions.

2. The intelligent defect detection and marking system according to claim 1, characterized in that: The X-ray detection module includes an X-ray source, a detector and an imaging unit; The X-ray source is used to emit X-rays to penetrate the package to be inspected; The detector is used to receive the X-rays emitted by the X-ray source and convert the received X-rays into digital image signals; The imaging unit is used to receive the digital image signal, process the digital image signal and generate an X-ray image of the package; Wherein, the X-ray source and the detector operate synchronously.

3. The intelligent defect detection and marking system according to claim 1, characterized in that: The control instructions output by the control module include a qualified part mark and a failed part mark; When the control instruction output by the control module is a qualified part mark, the laser marking module is controlled to perform a qualified mark on the packaged part; When the control instruction output by the control module is a non-conforming part mark, the laser marking module is controlled to mark the package as non-conforming.

4. The intelligent defect detection and marking system according to claim 3, characterized in that: The controlling the laser marking module to mark the package as unqualified comprises: The laser marking module is controlled to skip marking or perform a failure marking on the package.

5. The intelligent defect detection and marking system according to claim 1, characterized in that: The laser marking module includes a laser source, a marking platform and a control interface; The laser source is used to emit a laser beam to mark the surface of the package after defect detection according to the marking path; The marking platform is used to control the laser beam to cover the area of ​​the package where defect detection is completed; The control interface is used to receive the control instruction and generate a marking path of the laser beam according to the control instruction.

6. An intelligent defect detection and marking method, applied to the intelligent defect detection and marking system according to claims 1-5, the system comprising an X-ray detection module, an image processing module, a control module and a laser marking module, characterized in that: The method comprises: The X-ray detection module receives a package to be detected, scans the package to be detected and generates an X-ray image of the package in real time; The image processing module receives the package X-ray image, performs defect detection on the package X-ray image and generates a defect detection result; The control module outputs corresponding control instructions according to the defect detection result; The laser marking module receives the control instruction and performs marking processing on the packaged component that has completed defect detection according to the control instruction.

7. The method according to claim 6, characterized in that: The image processing module performs defect detection on the package X-ray image and generates a defect detection result, including: The image processing module pre-processes the X-ray image of the package and generates a clear image of the package; The image processing module uses a deep learning algorithm to extract features from the package denoised image, and identifies defects in the package clear image based on the extracted features; The image processing module outputs corresponding defect detection results according to the identified defects.

8. The method according to claim 7, characterized in that: The image processing module preprocesses the X-ray image of the package including: The image processing module performs image denoising, image enhancement and image binarization processing on the package X-ray image.

9. The method according to claim 7, characterized in that: The image processing module outputs corresponding defect detection results according to the identified defects, including: The image processing module determines whether a defect is identified; If no defect is identified, the package to be inspected is determined to be qualified; If a defect is identified, the size of the identified defect is calculated and it is determined whether the size of the defect is within a preset threshold range; If the size of the defect is within a preset threshold range, the package to be inspected is determined to be qualified; If the size of the defect is not within the preset threshold range, the package to be inspected is determined to be unqualified.

10. The method according to claim 7, characterized in that: The deep learning algorithm adopted by the image processing module is a convolutional neural network.

Images