Rigid-flex circuit board patch processing detection method and device

Abstract

The invention provides a rigid-flex circuit board patch processing detection method and device. The method comprises the following steps: acquiring standard coordinates of a chip component and patch processing images in a rigid-flex circuit board patch processing process under focusing light sources in at least four directions; wherein the patch processing image comprises a patch processing image of a flexible circuit board in the rigid-flex circuit board and / or a patch processing image of a rigid circuit board in the rigid-flex circuit board; inputting the patch processing image into an image processing artificial intelligence model to generate an image processing result; wherein the image processing artificial intelligence model is obtained by training a patch processing image training set, and the patch processing image training set comprises a plurality of patch processing image sets of flexible circuit boards and hard circuit boards; determining chip component mounting position coordinates according to an image processing result; and when the coordinates of the mounting position exceed the preset range of the standard coordinates, determining that the patch is unqualified, and otherwise, determining that the patch is qualified. According to the invention, image reflection can be removed, and the surface mounting quality of the rigid-flex circuit board is ensured.

Description

Technical Field

[0001] The present application relates to the field of circuit board patch processing detection, and in particular to a method and device for detecting soft-hard combined circuit board patch processing. Background Art

[0002] A rigid-flexible circuit board refers to a circuit board with the characteristics of both FPC (flexible circuit board) and PCB (rigid circuit board) formed by combining a flexible circuit board and a rigid circuit board through processes such as pressing and other processes according to relevant process requirements. It has the durability of a rigid board and the flexibility of a flexible board, making it light, compact, and resistant to harsh application environments. It is particularly suitable for use in precision electronics such as portable electronic products, medical electronic products, and military equipment.

[0003] The patch processing inspection uses a high-definition camera to capture the actions of the equipment during the patch execution process, thereby collecting images. The system analyzes the collected images to determine the quality of the circuit board patch.

[0004] Chip components are metal sheet structures. Metal reflects light, and rigid-flexible circuit boards have different reflection characteristics under lighting conditions. Complex reflection problems increase the difficulty of image processing. Summary of the invention

[0005] In view of the above problems, the present application is proposed to provide a method and device for detecting patch processing of a soft-hard combined circuit board, which overcomes the above problems or at least partially solves the above problems, including:

[0006] A method for detecting patch processing of a soft-hard combined circuit board, wherein the soft-hard combined circuit board is formed by laminating a flexible circuit board and a rigid circuit board, a camera is arranged above a patch machine, at least four focused light sources with the same light intensity are arranged equidistantly around the shooting direction of the camera, and a plane formed by the focused light sources is perpendicular to the shooting direction of the camera;

[0007] The method comprises:

[0008] Obtaining standard coordinates of chip components and patch processing images of the hard-soft combination circuit board during the patch processing under the focused light sources in at least four directions; wherein the light intensity of each focused light source is consistent, and each focused light source is perpendicular to the shooting direction of the camera; the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board;

[0009] Inputting the patch processing image into an image processing artificial intelligence model to generate an image processing result; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards;

[0010] Determining the mounting position coordinates of the chip component according to the image processing result;

[0011] When the mounting position coordinates exceed the preset range of the standard coordinates, the patch is unqualified, otherwise the patch is qualified.

[0012] Furthermore, the step of training the image processing artificial intelligence model using a patch processing image training set includes:

[0013] Acquire a plurality of patch processing image sets of flexible circuit boards and a plurality of patch processing image sets of rigid circuit boards; wherein the patch processing image sets of the flexible circuit boards include reflective and non-reflective patch processing images of the flexible circuit boards at different distances, different angles, and different light intensities; and the patch processing image sets of the rigid circuit boards include reflective and non-reflective patch processing images of the rigid circuit boards at different distances, different angles, and different light intensities;

[0014] Processing the patch processing image set to obtain the patch processing image training set;

[0015] Annotating the patch processing image training set to obtain corresponding identification information;

[0016] The artificial neural network is trained according to the patch processing image training set and the identification information to obtain the image processing artificial intelligence model; wherein the artificial neural network includes the corresponding relationship between the patch processing image and the image processing result.

[0017] Furthermore, the step of processing the patch processing image set to obtain the patch processing image training set includes:

[0018] Gaussian smoothing, histogram equalization and / or image filtering are performed on the patch processing image set to obtain the patch processing image training set.

[0019] Furthermore, the step of inputting the patch processing image into the image processing artificial intelligence model to generate the image processing result includes:

[0020] The image processing result corresponding to the current patch processing image is determined by the corresponding relationship pre-established by the artificial neural network.

[0021] Furthermore, the step of determining the mounting position coordinates of the chip component according to the image processing result includes:

[0022] Establishing a coordinate system identical to the standard coordinates of the chip element;

[0023] The mounting position coordinates of the chip component are generated according to the coordinate system and the image processing result.

[0024] Furthermore, when the mounting position coordinates exceed the preset range of the standard coordinates, the step of determining that the patch is unqualified includes:

[0025] A patch defect type result is generated according to the preset range of the mounting position coordinates and the standard coordinates.

[0026] Furthermore, the step of generating a chip defect type result according to a preset range of the mounting position coordinates and the chip component standard coordinates includes:

[0027] Determining the lateral spacing, longitudinal spacing and stacking height of the chip components according to the mounting position coordinates;

[0028] When the mounting coordinates of the chip component as a whole deviate out of the preset range, it is a component overlap deficiency defect;

[0029] When the lateral spacing of the sheet-type components is smaller than the preset range, it is a component side-standing defect;

[0030] When the longitudinal spacing of the chip components is smaller than the preset range, it is a component vertical chip defect;

[0031] When the stacking height of the chip components is greater than the preset range, it is a component stacking defect.

[0032] A soft-hard combined circuit board patch processing detection device, the soft-hard combined circuit board is formed by pressing a flexible circuit board and a rigid circuit board, a camera is arranged above the patch machine, at least four focused light sources with the same light intensity are arranged equidistantly around the shooting direction of the camera, and the plane formed by the focused light sources is perpendicular to the shooting direction of the camera;

[0033] The device comprises:

[0034] An acquisition module, used to acquire the standard coordinates of the chip component and the patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board;

[0035] A processing module, used for inputting the patch processing image into an image processing artificial intelligence model to generate an image processing result; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards;

[0036] A positioning module, used to determine the mounting position coordinates of the chip component according to the image processing result;

[0037] The evaluation module is used to determine that the patch is unqualified when the mounting position coordinate exceeds the preset range of the standard coordinate, and otherwise the patch is qualified.

[0038] A device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the soft-hard combined circuit board patch processing detection method as described above are implemented.

[0039] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the soft-hard combined circuit board patch processing detection method as described above are implemented.

[0040] This application has the following advantages:

[0041] In an embodiment of the present application, in view of the complex reflection problem of the patch processing of the hard-soft combination circuit board in the prior art, which increases the difficulty of image processing, the present application provides a solution through an image processing artificial intelligence model, specifically: obtaining the standard coordinates of the chip component and the patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board; inputting the patch processing images into the image processing artificial intelligence model to generate image processing results; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards; determining the mounting position coordinates of the chip component based on the image processing results; when the mounting position coordinates exceed the preset range of the standard coordinates, the patch is unqualified, otherwise the patch is qualified. The hard-and-soft circuit board patch processing images are processed through the image processing artificial intelligence model to remove the complex reflection problems in the images and obtain high-definition images to facilitate the evaluation of the patch processing and ensure the patch quality of the hard-and-soft circuit board. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the description of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 It is a flowchart of the steps of a method for processing and detecting a soft-hard combined circuit board provided in one embodiment of the present application;

[0044] Figure 2 It is a flowchart of a method for processing and detecting a soft-hard combined circuit board provided in one embodiment of the present application;

[0045] Figure 3 It is a structural block diagram of a soft-hard combined circuit board patch processing detection device provided by an embodiment of the present application;

[0046] Figure 4 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0048] The inventors have found through analysis of the prior art that the hard-soft circuit board is composed of a flexible circuit board (made of polyimide film, polyester film material) and a rigid circuit board (made of FR-4 and other materials). Both circuit boards are provided with metal foil on their surfaces. The flexible material may produce wrinkles or deformation when bent or folded, while the rigid material remains relatively stable. This difference in surface morphology causes the two circuit boards to have different reflection characteristics under lighting conditions. In addition, the chip components are also metal sheet structures, and the metal will reflect light, making the hard-soft circuit board have complex reflection characteristics under lighting conditions. In order to ensure production, the production workshop usually has very good lighting conditions, which makes it impossible to collect effective hard-soft circuit board patch processing images for patch processing detection. The present invention solves the aforementioned problems by using a trained image processing artificial intelligence model to process hard-soft circuit board patch processing images.

[0049] Reference Figure 1 and Figure 2 , showing a method for processing and detecting a soft-hard combined circuit board patch provided by an embodiment of the present application;

[0050] The method comprises:

[0051] S110, obtaining standard coordinates of the chip component and patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the patch processing images include patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or patch processing images of the rigid circuit board in the hard-soft combination circuit board;

[0052] S120, inputting the patch processing image into an image processing artificial intelligence model to generate an image processing result; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards;

[0053] S130, determining the mounting position coordinates of the chip component according to the image processing result;

[0054] S140. When the mounting position coordinate exceeds the preset range of the standard coordinate, the patch is unqualified, otherwise the patch is qualified.

[0055] In an embodiment of the present application, in view of the complex reflection problem of the patch processing of the hard-soft combination circuit board in the prior art, which increases the difficulty of image processing, the present application provides a solution through an image processing artificial intelligence model, specifically: obtaining the standard coordinates of the chip component and the patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board; inputting the patch processing images into the image processing artificial intelligence model to generate image processing results; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards; determining the mounting position coordinates of the chip component based on the image processing results; when the mounting position coordinates exceed the preset range of the standard coordinates, the patch is unqualified, otherwise the patch is qualified. The hard-and-soft circuit board patch processing images are processed through the image processing artificial intelligence model to remove the complex reflection problems in the images and obtain high-definition images to facilitate the evaluation of the patch processing and ensure the patch quality of the hard-and-soft circuit board.

[0056] Next, a method for detecting patch processing of a rigid-flexible circuit board in this exemplary embodiment will be further described.

[0057] It should be noted that, in any embodiment of the present invention, the rigid-flexible circuit board is formed by laminating a flexible circuit board and a rigid circuit board.

[0058] As an example, the rigid-flexible circuit board can be a single-sided structure, that is, one side is a rigid board and the other side is a flexible board, and the two are electrically connected through plated through holes (PTH) or other connection methods. The rigid-flexible circuit board can also be a multi-layer laminated structure, that is, a complex combination of multiple rigid layers and flexible layers, and electrical connection and structural support are achieved through a lamination process. The rigid-flexible circuit board is not limited to the structure illustrated above. The rigid-flexible circuit board of any structure can be processed and tested using the rigid-flexible circuit board patch processing and testing method of the present invention, which has high applicability.

[0059] As described in step S110, the standard coordinates of the chip component and the patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions are obtained; wherein the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board.

[0060] It should be noted that the standard coordinates of the chip component are the coordinates of a qualified chip component at a standard mounting position.

[0061] As an example, before collecting the image of the soft-hard circuit board patch processing, a coordinate system is established, and a high-precision measuring instrument is used to directly measure the boundaries of the chip components accurately, and the standard coordinates of the components are calculated based on the measurement results. Or, a coordinate system is established according to the drawing, the size and position information of the component is extracted, and converted into standard coordinates; or other methods are used to establish a coordinate system to obtain the standard coordinates of the chip component. This application does not limit the method of obtaining the standard coordinates of the standard mounting position. As long as the technical solution can achieve the technical effect of obtaining the standard coordinates of the standard mounting position, it is within the scope of protection of this application. The camera and light source arrangement are designed, and the light source is preferably a white light source. The layout of the light source can be equidistantly distributed around the axis of the camera, or it can be customized according to the shape of the target area and the detection requirements to improve the image quality and detection accuracy. During the image acquisition process, each light source is individually lit for shooting.

[0062] In a specific implementation, with the shooting direction of the camera lens as the axis, four light sources with the same light intensity are arranged equidistantly around the axis to ensure that the plane formed by the four light sources is perpendicular to the axis. And the irradiation directions of the four light sources form a convergence point on the optical axis. The four light sources surround the axis of the camera lens, so that a 360-degree patch processing image can be obtained. Then, light up a certain light source, turn off the other light sources, and light up the four light sources separately in turn. Each time the light is turned on, the same target is photographed, so as to obtain four patch processing images of the flexible circuit board in the soft-hard combination circuit board and the patch processing image of the rigid circuit board in the soft-hard combination circuit board illuminated by different light sources. At the same time, an automatic calibration and light source intensity monitoring mechanism is introduced to improve the stability and accuracy of the detection and ensure that the state of the light source is consistent every time the light is taken.

[0063] As described in step S120, the patch processing image is input into the image processing artificial intelligence model to generate an image processing result; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards.

[0064] It should be noted that the image processing artificial intelligence model is deployed on a cloud server, and the collected images are uploaded to the cloud for efficient recognition and processing to obtain the required image processing results.

[0065] In one embodiment of the present invention, the specific process of the step "the image processing artificial intelligence model is trained by the patch processing image training set" can be further explained in combination with the following description.

[0066] As described in the following steps, a plurality of patch processing image sets of flexible circuit boards and a plurality of patch processing image sets of rigid circuit boards are obtained; wherein the patch processing image sets of the flexible circuit boards include reflective and non-reflective patch processing images of the flexible circuit boards at different distances, different angles and different light intensities; the patch processing image sets of the rigid circuit boards include reflective and non-reflective patch processing images of the rigid circuit boards at different distances, different angles and different light intensities;

[0067] As described in the following steps, the patch processing image set is processed to obtain the patch processing image training set;

[0068] As described in the following steps, the patch processing image training set is labeled to obtain corresponding identification information;

[0069] As described in the following steps, an artificial neural network is trained based on the patch processing image training set and the identification information to obtain the image processing artificial intelligence model; wherein the artificial neural network includes the corresponding relationship between the patch processing image and the image processing result.

[0070] As an example, patch processing images of flexible circuit boards and rigid circuit boards at different distances, angles and light intensities are collected; specifically, at least four light sources are set, and the layout of the light sources is equidistantly distributed or randomly distributed around the axis of the camera, and the plane determined by each light source is perpendicular to the axis, so as to obtain patch processing images at different angles. Then adjust the distance between the light source and the camera to obtain patch processing images at different shooting distances. When using light sources of different wattages, or changing the type of light source, or multiple light sources for irradiation, in addition to lighting each light source separately to take images, you can also try to light up multiple light sources at the same time to obtain patch processing images with different light intensities. Then, patch processing images of circuit boards with various degrees of reflectivity and non-reflectivity are obtained as training sets for the model. Within the scope of computer processing capabilities, the more samples in the training set, the more accurate the recognition model trained will be. After obtaining the training set, the training set is annotated to obtain identification information. The annotation can make the data readable and usable, providing a "teaching material" for learning for the model. The patch processing image training set and the corresponding identification information are used as the input data of the artificial neural network for training. After the network converges, the image processing artificial intelligence model, that is, the network structure and parameters, is obtained. The artificial neural network can be a deep convolutional artificial neural network, FasterR-CNN, YOLO or SSD, etc. By using the artificial neural network algorithm, by adjusting the network structure and the weights between the network nodes, the artificial neural network fits the relationship between the patch processing images corresponding to different regions and the image processing results, and finally the artificial neural network can accurately fit the corresponding relationship between the patch processing images and the image processing results.

[0071] In an embodiment of the present invention, the specific process of “processing the patch-processed image set to obtain the patch-processed image training set” may be further explained in combination with the following description.

[0072] As described in the following steps, Gaussian smoothing, histogram equalization and / or image filtering are performed on the patch processing image set to obtain the patch processing image training set.

[0073] It should be noted that the patch processing image set is enhanced to improve image quality and enhance image recognizability and clarity. In addition to the enhancement methods of Gaussian smoothing, histogram equalization and / or image filtering described in this embodiment, other processing methods that can achieve the same preprocessing effect can also be used, all of which are within the scope of protection of this application.

[0074] In one embodiment of the present invention, the specific process of "inputting the patch processing image into the image processing artificial intelligence model to generate an image processing result" in step S120 can be further explained in combination with the following description.

[0075] As described in the following steps, the image processing result corresponding to the current patch processing image is determined through the corresponding relationship pre-established by the artificial neural network.

[0076] As an example, the patch processing image is input into a trained image processing artificial intelligence model, and the image processing result corresponding to the current patch processing image is determined through the corresponding relationship.

[0077] As described in step S130, the mounting position coordinates of the chip component are determined according to the image processing result.

[0078] In an embodiment of the present invention, the specific process of step S130 of "determining the mounting position coordinates of the chip component according to the image processing result" can be further explained in combination with the following description.

[0079] As described in the following steps, a coordinate system identical to the standard coordinates of the chip element is established;

[0080] As described in the following steps, the mounting position coordinates of the chip component are generated according to the coordinate system and the image processing result.

[0081] As an example, a coordinate system is established, and the method of establishing the coordinate system is consistent with the coordinate system of the standard coordinates of the chip component, and the mounting position coordinates of the chip component are obtained based on the coordinate system.

[0082] As described in step S140, when the mounting position coordinate exceeds the preset range of the standard coordinate, the patch is unqualified, otherwise the patch is qualified.

[0083] As an example, the mounting position coordinates of the chip component are compared with its standard coordinates to obtain a deviation result, and whether the mounting of the chip component is qualified is judged based on the deviation result. When the deviation result exceeds a preset range, it is unqualified, otherwise it is qualified.

[0084] In an embodiment of the present invention, the specific process of step S140 "when the mounting position coordinate exceeds the preset range of the standard coordinate, the mounting is unqualified" can be further explained in combination with the following description.

[0085] As described in the following steps, a patch defect type result is generated according to the preset range of the mounting position coordinates and the standard coordinates.

[0086] It should be noted that the types of patch defects include insufficient component overlap, component sideways, component stand-offs and component stacking. Insufficient overlap means that when a component is mounted on a circuit board, its pins, pads or other contact surfaces fail to fully and accurately contact the corresponding parts of the circuit board (such as pads, sockets, etc.), resulting in a contact area that is smaller than the design requirements or expected values. Component sideways means that the side of the component is mounted, and it flips over during the patch process, causing the pins or faces of the component to face the wrong direction. Component stand-off means that the component tilts or flips over during the patch process, causing one or both ends of the component to lift up and fail to fit the plane of the circuit board. Component stacking means that multiple components overlap during the patch process.

[0087] As an example, the lateral spacing, longitudinal spacing and stacking height of the chip components are determined according to the mounting position coordinates.

[0088] When the mounting coordinates of the chip component as a whole deviate from the preset range, it is a defect of insufficient component overlap; when the coordinates of the four corners of the chip component on the plane of the circuit board as a whole deviate from the preset range, it indicates that the contact area between the component and the standard mounting position of the circuit board is insufficient;

[0089] When the lateral spacing of the chip components is smaller than the preset range, it is a component side-standing defect; the lateral spacing refers to the distance of the chip components along the horizontal direction on the plane of the circuit board, and this distance is parallel to the surface of the circuit board. During the patch process, if the lateral spacing is too small, it indicates that the component has a side-standing defect, that is, the side of the component rather than the predetermined surface or pin contacts the circuit board;

[0090] When the longitudinal spacing of the chip components is less than the preset range, it is a component stand-up defect; the longitudinal spacing refers to the distance of the chip components in a direction perpendicular to the lateral spacing on the plane of the circuit board. If the longitudinal spacing is too small, it indicates that the component has a stand-up defect, that is, the component tilts or overturns during the patch process, causing one or both ends to be lifted up and unable to fully fit with the plane of the circuit board;

[0091] When the stacking height of the chip components is greater than the preset range, it is a component stacking defect; the stacking height is a three-dimensional concept, which refers to the distance between the component and the circuit board or other components in the direction perpendicular to the plane of the circuit board. If the stacking height is greater than the preset range, it indicates that a component stacking defect has occurred, that is, multiple components overlap during the patch process.

[0092] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0093] Reference Figure 3, showing a soft-hard combined circuit board patch processing detection device provided by an embodiment of the present application; a camera is provided above the patch machine, and at least four focused light sources with the same light intensity are arranged equidistantly around the shooting direction of the camera, and the plane formed by the focused light sources is perpendicular to the shooting direction of the camera;

[0094] The device specifically comprises:

[0095] The acquisition module 310 is used to acquire the standard coordinates of the chip component and the patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board;

[0096] The processing module 320 is used to input the patch processing image into an image processing artificial intelligence model to generate an image processing result; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards;

[0097] A positioning module 330, used to determine the mounting position coordinates of the chip component according to the image processing result;

[0098] The evaluation module 340 is used to determine that the patch is unqualified when the mounting position coordinate exceeds the preset range of the standard coordinate, and otherwise the patch is qualified.

[0099] In one embodiment of the present invention, the processing module 320 includes:

[0100] An image acquisition submodule, used to acquire a plurality of patch processing image sets of flexible circuit boards and a plurality of patch processing image sets of rigid circuit boards; wherein the patch processing image sets of the flexible circuit boards include reflective and non-reflective patch processing images of the flexible circuit boards at different distances, different angles and different light intensities; the patch processing image sets of the rigid circuit boards include reflective and non-reflective patch processing images of the rigid circuit boards at different distances, different angles and different light intensities;

[0101] An image processing submodule, used for processing the patch processing image set to obtain the patch processing image training set;

[0102] A data annotation submodule is used to annotate the patch processing image training set to obtain corresponding identification information;

[0103] The model training submodule is used to train the artificial neural network based on the patch processing image training set and the identification information to obtain the image processing artificial intelligence model; wherein the artificial neural network includes the corresponding relationship between the patch processing image and the image processing result.

[0104] In one embodiment of the present invention, the image processing submodule includes:

[0105] The enhancement processing unit is used to perform Gaussian smoothing, histogram equalization and / or image filtering processing on the patch processing image set to obtain the patch processing image training set.

[0106] In one embodiment of the present invention, the processing module 320 further includes:

[0107] The image processing submodule is used to determine the image processing result corresponding to the current patch processing image through the corresponding relationship pre-established by the artificial neural network.

[0108] In one embodiment of the present invention, the positioning module 330 includes:

[0109] A coordinate system establishment submodule, used to establish a coordinate system identical to the standard coordinates of the chip element;

[0110] The coordinate generation submodule is used to generate the mounting position coordinates of the chip component according to the coordinate system and the image processing result.

[0111] In one embodiment of the present invention, the evaluation module 340 includes:

[0112] The type determination submodule is used to generate a patch defect type result according to a preset range of the mounting position coordinates and the standard coordinates.

[0113] In one embodiment of the present invention, the type determination submodule includes:

[0114] A spacing calculation unit, comprising determining the lateral spacing, longitudinal spacing and stacking height of the chip components according to the mounting position coordinates;

[0115] A first judgment unit includes: when the mounting coordinates of the chip component are offset from the preset range as a whole, it is a component overlap deficiency defect;

[0116] The second judgment unit includes: when the lateral spacing of the chip-type components is smaller than the preset range, it is a component side-standing defect;

[0117] The third judgment unit includes: when the longitudinal spacing of the chip-type components is smaller than the preset range, it is a component standing defect;

[0118] The fourth judgment unit includes: when the stacking height of the chip components is greater than the preset range, it is a component stacking defect.

[0119] Reference Figure 4 , showing a computer device of a soft-hard combined circuit board patch processing detection method of the present invention, which may specifically include the following:

[0120] The computer device 12 is in the form of a general-purpose computing device, and the components of the computer device 12 may include but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0121] The bus 18 represents one or more of several types of bus 18 structures, including a memory bus 18 or memory controller, a peripheral bus 18, an accelerated graphics port, a processor or a local bus 18 using any of a variety of bus 18 architectures. These architectures include, by way of example, but are not limited to, an Industry Standard Architecture (ISA) bus 18, a Micro Channel Architecture (MAC) bus 18, an Enhanced ISA bus 18, an Audio Video Electronics Standards Association (VESA) local bus 18, and a Peripheral Component Interconnect (PCI) bus 18.

[0122] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0123] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, which are configured to perform the functions of various embodiments of the present invention.

[0124] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0125] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, cameras, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs)), wide area networks (WANs), and / or public networks (e.g., the Internet) via a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

[0126] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing a method for processing and detecting a soft-hard combined circuit board provided in an embodiment of the present invention.

[0127] That is, when the processing unit 16 executes the program, it realizes: obtaining the standard coordinates of the chip component and the patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board; inputting the patch processing images into the image processing artificial intelligence model to generate image processing results; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards; determining the mounting position coordinates of the chip component based on the image processing results; when the mounting position coordinates exceed the preset range of the standard coordinates, the patch is unqualified, otherwise the patch is qualified.

[0128] In an embodiment of the present invention, the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, a method for detecting patch processing of a soft-hard combined circuit board provided in all embodiments of the present application is implemented:

[0129] That is, when the program is executed by the processor, it is implemented as follows: obtaining the standard coordinates of the chip component and the patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the light intensity of each focused light source is consistent, and each focused light source is perpendicular to the shooting direction of the camera; the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board; inputting the patch processing images into the image processing artificial intelligence model to generate image processing results; wherein the image processing artificial intelligence model is trained by the patch processing image training set, and the patch processing image training set includes the patch processing image sets of multiple flexible circuit boards and the patch processing image sets of multiple rigid circuit boards; determining the mounting position coordinates of the chip component based on the image processing results; when the mounting position coordinates exceed the preset range of the standard coordinates, the patch is unqualified, otherwise the patch is qualified.

[0130] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0131] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0132] The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0133] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0134] Finally, 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 terminal 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 terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0135] The above is a detailed introduction to a method and device for processing and detecting a soft-hard combined circuit board provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for detecting patch processing of a soft-hard combined circuit board, wherein the soft-hard combined circuit board is formed by laminating a flexible circuit board and a rigid circuit board, characterized in that: A camera is provided above the placement machine, and at least four focused light sources with the same light intensity are arranged equidistantly around the shooting direction of the camera, and the plane formed by the focused light sources is perpendicular to the shooting direction of the camera; The method comprises: Acquire standard coordinates of chip components and patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the patch processing images include patch processing images of flexible circuit boards in hard-soft combination circuit boards and / or patch processing images of rigid circuit boards in hard-soft combination circuit boards; Inputting the patch processing image into an image processing artificial intelligence model to generate an image processing result; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards; Determining the mounting position coordinates of the chip component according to the image processing result; When the mounting position coordinates exceed the preset range of the standard coordinates, the patch is unqualified, otherwise the patch is qualified.

2. The method according to claim 1, characterized in that: The steps of training the image processing artificial intelligence model with the patch processing image training set include: Acquire a plurality of patch processing image sets of flexible circuit boards and a plurality of patch processing image sets of rigid circuit boards; wherein the patch processing image sets of the flexible circuit boards include reflective and non-reflective patch processing images of the flexible circuit boards at different distances, different angles, and different light intensities; and the patch processing image sets of the rigid circuit boards include reflective and non-reflective patch processing images of the rigid circuit boards at different distances, different angles, and different light intensities; Processing the patch processing image set to obtain the patch processing image training set; Annotating the patch processing image training set to obtain corresponding identification information; The artificial neural network is trained according to the patch processing image training set and the identification information to obtain the image processing artificial intelligence model; wherein the artificial neural network includes the corresponding relationship between the patch processing image and the image processing result.

3. The method according to claim 2, characterized in that The step of processing the patch processing image set to obtain the patch processing image training set includes: Gaussian smoothing, histogram equalization and / or image filtering are performed on the patch processing image set to obtain the patch processing image training set.

4. The method according to claim 2, characterized in that: The step of inputting the patch processing image into the image processing artificial intelligence model to generate an image processing result includes: The image processing result corresponding to the current patch processing image is determined by the corresponding relationship pre-established by the artificial neural network.

5. The method according to claim 1, characterized in that The step of determining the mounting position coordinates of the chip component according to the image processing result comprises: Establishing a coordinate system identical to the standard coordinates of the chip element; The mounting position coordinates of the chip component are generated according to the coordinate system and the image processing result.

6. The method according to claim 1, characterized in that The step of determining that the patch is unqualified when the mounting position coordinate exceeds the preset range of the standard coordinate includes: A patch defect type result is generated according to the preset range of the mounting position coordinates and the standard coordinates.

7. The method according to claim 6, characterized in that The step of generating a chip defect type result according to the preset range of the mounting position coordinates and the chip component standard coordinates includes: Determining the lateral spacing, longitudinal spacing and stacking height of the chip components according to the mounting position coordinates; When the mounting coordinates of the chip component as a whole deviate out of the preset range, it is a component overlap deficiency defect; When the lateral spacing of the sheet-type components is smaller than the preset range, it is a component side-standing defect; When the longitudinal spacing of the chip components is smaller than the preset range, it is a component vertical chip defect; When the stacking height of the chip components is greater than the preset range, it is a component stacking defect.

8. A device for detecting patch processing of a soft-hard combined circuit board, wherein the soft-hard combined circuit board is formed by laminating a flexible circuit board and a rigid circuit board, characterized in that: A camera is provided above the placement machine, and at least four focused light sources with the same light intensity are arranged equidistantly around the shooting direction of the camera, and the plane formed by the focused light sources is perpendicular to the shooting direction of the camera; The device comprises: An acquisition module, used to acquire the standard coordinates of the chip component and the patch processing images of the hard-soft combination circuit board during the patch processing under the focused light source in at least four directions; wherein the patch processing images include the patch processing images of the flexible circuit board in the hard-soft combination circuit board and / or the patch processing images of the rigid circuit board in the hard-soft combination circuit board; A processing module, used for inputting the patch processing image into an image processing artificial intelligence model to generate an image processing result; wherein the image processing artificial intelligence model is trained by a patch processing image training set, and the patch processing image training set includes a patch processing image set of multiple flexible circuit boards and a patch processing image set of multiple rigid circuit boards; A positioning module, used to determine the mounting position coordinates of the chip component according to the image processing result; The evaluation module is used to determine that the patch is unqualified when the mounting position coordinate exceeds the preset range of the standard coordinate, and otherwise the patch is qualified.

9. A device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the method for detecting patch processing of a soft-hard combined circuit board as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for detecting the processing of soft-hard combined circuit board patches according to any one of claims 1 to 7 is implemented.

Images