Method and device for detecting quality of a board

Abstract

The application provides a plate quality detection method and device, wherein the plate quality detection method comprises the following steps: collecting plate information of a to-be-detected plate, and adjusting the position of a visual detection module based on the plate information; collecting visual images of all surfaces of the to-be-detected plate by the visual detection module to obtain a to-be-detected image set; performing defect detection, edge sealing detection and size detection on the to-be-detected plate based on the to-be-detected image set and the plate information, and judging the quality information of the to-be-detected plate based on all detection results. The automatic detection of the plate quality is realized.

Description

Technical Field

[0001] This application relates to the field of visual defect detection technology, and in particular to a method for inspecting the quality of sheet metal. This application also relates to a sheet metal quality inspection device, a computing device, and a computer-readable storage medium. Background Technology

[0002] With the development of technology and the improvement of people's living standards, more and more products are in demand, and people are paying more and more attention to the quality of these products. High-quality products often bring people a better experience, which in turn brings a larger market share. Therefore, manufacturers today place particular emphasis on product quality.

[0003] In existing custom furniture production and processing, after the boards are cut to the required dimensions, each side of the board needs to be edge-banded to make it more aesthetically pleasing, sturdy, and waterproof. However, the edge-banding quality may have problems such as loose adhesion or unevenness. In addition, scratches and dents may also appear on the surface of the board during the cutting process. Therefore, defect detection of the board is necessary to determine its quality.

[0004] Currently, most manufacturers in the industry still rely heavily on human inspection to detect defects after edge banding of boards. Human inspection is slow and inefficient, and it cannot promptly relay problems to the upstream processes, often resulting in unnecessary waste and significantly limiting the improvement of product quality. While some automated inspection equipment is available, its accuracy is low, and it cannot assess board quality from multiple perspectives. Summary of the Invention

[0005] In view of this, embodiments of this application provide a method for inspecting the quality of sheet materials to address the technical deficiencies in the prior art. Embodiments of this application also provide a sheet material quality inspection device, a computing device, and a computer-readable storage medium.

[0006] According to a first aspect of the embodiments of this application, a method for testing the quality of sheet metal is provided, comprising:

[0007] Collect the board material information of the board material to be inspected, and adjust the position of the vision inspection module based on the board material information;

[0008] The visual inspection module acquires visual images of all surfaces of the board to be inspected, thus obtaining a set of images to be inspected.

[0009] Based on the set of images to be detected and the information of the board material, defect detection, edge sealing detection and size detection are performed on the board material to be detected, and the quality information of the board material to be detected is determined based on all the detection results.

[0010] Optionally, the step of collecting the board material information of the board material to be inspected and adjusting the position of the visual inspection module based on the board material information includes:

[0011] Collect the board code on the board to be tested;

[0012] The board information of the board to be tested is determined based on the board code.

[0013] Query a preset board material database to determine whether the board material information is contained in the database;

[0014] If so, adjust the position of the vision inspection module according to the board size information contained in the board information;

[0015] If not, the quality inspection of the current board material to be inspected will no longer be carried out, and the board material information will be recorded.

[0016] Optionally, adjusting the position of the vision inspection module based on the board size information contained in the board information includes:

[0017] Based on the material size information, determine the width and thickness of the material to be tested;

[0018] Adjust the positions of the dual side cameras in the vision inspection module according to the width of the sheet material;

[0019] The position of the top camera in the vision inspection module is adjusted according to the thickness of the sheet material.

[0020] Optionally, the step of acquiring visual images of all surfaces of the board material to be inspected through the vision inspection module to obtain an image set to be inspected includes:

[0021] The position of the board to be tested is adjusted using a preset board transport module;

[0022] When the material to be inspected reaches the lower surface detection position, the lower surface image of the material to be inspected is captured by the bottom camera in the vision inspection module;

[0023] When the material to be inspected reaches the head side detection position, the head side image of the material to be inspected is acquired by the head camera in the vision inspection module.

[0024] When the material to be inspected reaches the detection positions of the upper surface and both sides, the top camera in the vision inspection module captures the image of the upper surface of the material to be inspected, and the side cameras in the vision inspection module capture the images of the sides of the material to be inspected.

[0025] When the material to be inspected reaches the rear side detection position, the rear side image of the material to be inspected is acquired by the rear camera in the vision inspection module.

[0026] Optionally, the process of performing defect detection and edge banding inspection on the board material to be inspected includes:

[0027] The images to be detected contained in the image set to be detected are segmented into a first board region to obtain a first board image;

[0028] The first board image is segmented into second board regions to obtain a second board image that satisfies the input size conditions of the pre-trained detection model.

[0029] The second board image and the board information are used as inputs to the pre-trained detection model, and the defect detection results and edge sealing detection results of the board to be detected are output.

[0030] Optionally, the process of dimensionally inspecting the sheet material to be inspected includes:

[0031] The black and white color scheme of the images to be detected in the set of images to be detected is determined, and edge extraction is performed based on the determination result to obtain the third board image;

[0032] Based on the third plate image, determine the size information of the plate to be inspected;

[0033] Based on the size information to be tested and the size information of the board material contained in the board material information, the size test result of the board material to be tested is determined.

[0034] Optionally, determining the quality information of the board material to be tested based on all test results includes:

[0035] Based on preset weighting coefficients, the defect detection results, the edge sealing detection results, and the size detection results are weighted and calculated to obtain a quality score;

[0036] The quality information is determined through the quality score based on a preset quality assessment strategy.

[0037] According to a second aspect of the embodiments of this application, a sheet material quality testing device is provided, comprising:

[0038] The acquisition module is configured to acquire information about the board material to be inspected and adjust the position of the vision inspection module based on the board material information.

[0039] The image module is configured to acquire visual images of all surfaces of the board to be inspected through the vision inspection module, thereby obtaining a set of images to be inspected;

[0040] The judgment module is configured to perform defect detection, edge banding detection, and size detection on the board material to be inspected based on the set of images to be inspected and the board material information, and to judge the quality information of the board material to be inspected based on all the detection results.

[0041] According to a third aspect of the embodiments of this application, a computing device is provided, comprising:

[0042] Memory and processor;

[0043] The memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions to implement the steps of the board quality inspection method.

[0044] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the board quality inspection method.

[0045] According to a fifth aspect of the present application, a chip is provided that stores a computer program, which, when executed by the chip, implements the steps of the board quality inspection method.

[0046] The board quality inspection method provided in this application involves collecting board information and adjusting the position of a vision inspection module based on the board information; acquiring visual images of all surfaces of the board through the vision inspection module to obtain an image set; performing defect detection, edge banding detection, and dimensional detection on the board based on the image set and the board information; and determining the quality information of the board based on all the inspection results. This achieves automated inspection of board quality. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of a method for testing the quality of sheet metal according to an embodiment of this application;

[0049] Figure 2 This is a flowchart of a board quality testing method provided in one embodiment of this application;

[0050] Figure 3 This is a visual inspection flowchart of a board quality inspection method provided in one embodiment of this application;

[0051] Figure 4 This is a schematic diagram of the structure of a sheet material quality testing device provided in one embodiment of this application;

[0052] Figure 5 This is a structural block diagram of a computing device provided in one embodiment of this application. Detailed Implementation

[0053] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0054] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” used in one or more embodiments of this application and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0055] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first.

[0056] This application provides a method for inspecting the quality of sheet metal. This application also relates to a sheet metal quality inspection device, a computing device, and a computer-readable storage medium, which will be described in detail in the following embodiments.

[0057] Figure 1 The flowchart illustrates a method for testing the quality of sheet metal according to an embodiment of this application, which specifically includes the following steps:

[0058] Step S102: Collect the board information of the board to be inspected, and adjust the position of the visual inspection module based on the board information;

[0059] Step S104: The visual inspection module acquires visual images of all surfaces of the board to be inspected to obtain a set of images to be inspected;

[0060] Step S106: Based on the image set to be detected and the board information, perform defect detection, edge sealing detection and size detection on the board to be detected, and determine the quality information of the board to be detected based on all the detection results.

[0061] The boards to be inspected are transported via a board transport module, which can take the form of a conveyor belt, robotic arm, etc. However, in practical applications, to ensure the stability of the boards during the inspection process and improve inspection quality, a conveyor belt is preferred. Before the boards are transported to the inspection line, their board information needs to be collected. This information includes the board's color, size, model, etc. The board information can be determined before the board is processed, specifically by its processing model; any processing model has corresponding board information.

[0062] Based on this, by acquiring the information about the board material, the visual inspection module is moved to avoid continuously inspecting the board material, whose height and width vary greatly. This is because the lens cannot achieve rapid autofocus, and the depth of field cannot meet the needs of large changes in working distance. Therefore, to acquire clear images, the position of the visual inspection module needs to be dynamically adjusted. Subsequently, as the board material transport module continuously moves the board material to be inspected, when it reaches the designated position, the visual inspection module acquires images of the entire surface of the board material.

[0063] Since the board information contains information such as the board color, size, and model of the board to be tested under ideal conditions, the actual quality of the board to be tested can be determined by comparing the collected set of images with the board information, that is, by comparing the actual situation of the board to be tested with the ideal situation.

[0064] Furthermore, in step S102, the process of collecting the board information of the board to be inspected and adjusting the position of the visual inspection module based on the board information is specifically implemented as follows in this embodiment:

[0065] Collect the board code on the board to be inspected; determine the board information of the board to be inspected based on the board code; query the preset board database to determine whether the board information is contained in the board database; if yes, adjust the position of the vision inspection module according to the board size information contained in the board information; if no, stop quality inspection of the current board to be inspected and record the board information.

[0066] The board material code can be a barcode or a QR code. However, in actual use cases, since there are thousands of types of boards and the incoming materials are unordered, the method of identifying and matching the board size information through QR codes can meet the requirements of multiple categories and unordered rules.

[0067] Specifically, such as Figure 2 The provided board quality inspection method includes a board inspection flowchart. First, a QR code is identified. The CAD drawing of the board to be inspected is determined by the identified QR code. The board information, including board color and size, can be obtained by acquiring the CAD drawing. The subsequent process of checking for the presence of the board information can be understood as follows: the board information is stored in a preset board database. The board information is retrieved to determine whether the board information corresponding to the board to be inspected is stored in the database. If it is, the subsequent steps can be executed; otherwise, the board is prohibited from entering the inspection line.

[0068] In practical applications, since the performance parameters of the testing line are fixed, such as volume and weight, boards that are too large in size or weight cannot be tested by the testing line. If there are no size or weight restrictions, the testing line may be damaged. However, the board information entered into the board database in advance corresponds to boards that have been determined to be able to be tested by the testing line.

[0069] It should be noted that if the barcode of the board to be tested is damaged, contaminated, or otherwise unidentifiable, the board will not be tested. However, if the board model does not exist in the board database, its information can be recorded. Later, it will be determined whether the board can be tested by the testing line. If so, the recorded board information will be entered into the board database. Figure 2 As shown, enter the missing information about the board material.

[0070] Furthermore, in step S102, the process of adjusting the position of the visual inspection module based on the board size information contained in the board information is specifically implemented as follows in this embodiment:

[0071] Based on the material size information, determine the width and thickness of the material to be inspected; based on the material width, adjust the positions of the bilateral side cameras in the vision inspection module; based on the material thickness, adjust the position of the top camera in the vision inspection module.

[0072] The visual inspection module includes a bottom camera, a head camera, a top camera, dual side cameras, and a tail camera. During the inspection of the sheet material, the top camera moves vertically according to the sheet thickness, while the dual side cameras move horizontally according to the sheet width. It should be noted that the top camera's vertical movement can be non-vertical, and the dual side cameras' horizontal movement can be non-horizontal. Furthermore, the movement distance of the top and dual side cameras can be set with position limits, restricting the camera positions within a certain range to prevent collisions with the sheet material due to excessive movement.

[0073] Specifically, such as Figure 2 The provided flowchart illustrates a board quality inspection method. If the board information exists in the board database, the board begins to flow into the inspection line. The camera position is dynamically adjusted in real-time based on the different board widths and thicknesses. Specifically, the board type and its specified dimensions (length, width, and height) are obtained through QR code recognition, and this dimensional information is fed back to the equipment control program PLC. Based on the board dimensions, the servo drive module adjusts the camera position.

[0074] Furthermore, in step S104, the process of acquiring visual images of all surfaces of the board to be inspected through the visual inspection module to obtain the image set to be inspected is specifically implemented as follows in this embodiment:

[0075] The position of the board to be inspected is adjusted using a preset board transport module. When the board reaches the lower surface inspection position, the bottom camera in the vision inspection module captures an image of the lower surface of the board. When the board reaches the head side inspection position, the head camera in the vision inspection module captures an image of the head side of the board. When the board reaches the upper surface and bilateral side inspection positions, the top camera in the vision inspection module captures an image of the upper surface of the board, and the bilateral side cameras in the vision inspection module capture images of the bilateral side of the board. When the board reaches the tail side inspection position, the tail camera in the vision inspection module captures an image of the tail side of the board.

[0076] Among them, such as Figure 2 The provided board quality inspection method includes a board inspection flowchart. When the board reaches the lower surface inspection position, the head side inspection position, the upper surface and the double side inspection positions, and the tail side inspection position, the corresponding camera acquires images.

[0077] Furthermore, in step S106, the process of defect detection and edge sealing inspection of the board material to be inspected is specifically implemented as follows in this embodiment:

[0078] The first board region segmentation is performed on the images to be detected contained in the image set to obtain a first board image; the first board image is then segmented into a second board region to obtain a second board image that meets the input size conditions of the pre-trained detection model; the second board image and the board information are used as the input of the pre-trained detection model to output the defect detection results and edge sealing detection results of the board to be detected.

[0079] Furthermore, in step S106, the process of dimensional inspection of the material to be inspected is specifically implemented as follows in this embodiment:

[0080] The images to be detected in the set of images to be detected are judged to be black and white, and edge extraction is performed based on the judgment result to obtain a third board image; the size information to be detected of the board to be detected is determined based on the third board image; the size detection result of the board to be detected is determined based on the size information to be detected and the board size information contained in the board information.

[0081] Among them, such as Figure 2 The provided board quality inspection method includes a board inspection flowchart. After the corresponding camera acquires images of each surface of the board to be inspected, the vision inspection system begins inspection, specifically defect detection, size inspection and edge banding inspection.

[0082] Based on this, the testing process for the board material to be tested is as follows: Figure 3 The provided visual inspection flowchart of a board quality inspection method shows that the image acquisition module identifies the images in the image set to be inspected, determines the board area, and then extracts the board area. The image obtained after the board area is extracted is divided into two threads: one thread performs defect detection and edge banding detection, and the other thread performs size detection.

[0083] Regarding the defect detection and edge sealing detection threads, two board region segmentations are performed: a first board region segmentation and a second board region segmentation. The purpose of the first board region segmentation is to remove invalid parts such as the background of the entire image, extracting the board region to obtain the first board image. This can be achieved using techniques such as "blob analysis" and feature analysis. The second board region segmentation is based on the board region extracted in the first step, aiming to match the size during deep learning image preprocessing to obtain a second board image that meets the input size conditions of the pre-trained detection model. Then, through the target detection module and the defect judgment module (i.e., the deep learning algorithm of the pre-trained detection model), feature extraction and target detection are performed on the second board image. Based on the board information, the expected appearance of the corresponding model of the board to be detected is determined. Features are extracted from this expected appearance and compared with the feature extraction and target detection results of the second board image to obtain the defect detection result and the edge sealing detection result. This comparison is implemented through a neural network model, i.e., the pre-trained detection model.

[0084] Regarding the dimension inspection thread, the process first categorizes the board material into two colors—black and white—based on its color scheme. This is to accommodate settings for edge detection, target detection, and other related parameters. Specifically, after extracting the board area, grayscale values ​​are extracted, and the board is classified into black or white according to preset criteria. Then, based on the black-and-white classification, edge extraction is performed using the edge extraction module, followed by dimension calculation to determine the distance from a point to a line or point to a point, thus determining the size of the board. Next, the CAD drawing included in the board information is parsed to obtain contour data. Using the drawing and contour data as a benchmark, the relationship between the measured board size and the drawing size is determined, serving as the dimension inspection result.

[0085] Furthermore, in step S106, the process of determining the quality information of the board material to be tested based on all the test results is specifically implemented as follows in this embodiment:

[0086] The defect detection results, edge sealing detection results, and dimensional detection results are weighted and calculated according to preset weighting coefficients to obtain a quality score; the quality information is determined through the quality score based on a preset quality assessment strategy.

[0087] Among them, such as Figure 3 The provided visual inspection flowchart of a board quality inspection method shows that, based on the defect inspection results, edge banding inspection results, and dimensional inspection results, a comprehensive judgment is made, and the judgment results are displayed as text or sent to a designated device through data transmission mode. The inspection results are also stored through an image / data storage module.

[0088] Based on this, such as Figure 2 The provided board quality inspection method flowchart shows that after the result judgment is completed, the judgment results of good products and defective products are output.

[0089] Specifically, in practical applications, defect detection results, edge banding detection results, and dimensional detection results can all be presented in a scoring format. Then, a quality score is calculated by weighting these results using preset weighting coefficients. Based on the quality score, it is determined whether the corresponding board material to be inspected is defective. It should be noted that the weighting coefficients can be set as a stage function, ensuring that if a certain detection result deviates significantly from the normal board material, the weighting coefficient of that detection result is increased, giving it greater weight.

[0090] For example, if the scoring ranges for defect detection, edge banding detection, and dimensional detection results are all within [0, 1], and the closer the value is to 1, the worse the actual quality of the board being inspected is, then we can set the weighting coefficient to 1 when the value is less than 0.2, to 2 when the value is between 0.2 and 0.5, and to (x+0.5) when the value is between 0.5 and 1. 4 +1, where x is the numerical value. It should be noted that the function for each segment in the piecewise function can be a constant, linear function, power function, exponential function, etc., and the specific function selection depends on the actual application scenario. After calculating the quality score, the quality of the board to be tested is determined based on the specific value of the quality score. It should be noted that the quality of the board can be divided into multiple levels, such as Grade 1 Good, Grade 2 Good, Grade 1 Defective, Grade 2 Defective, etc. Users can select the corresponding quality of board according to their actual usage needs.

[0091] Corresponding to the above method embodiments, this application also provides embodiments of a board quality testing device. Figure 4 A schematic diagram of a sheet material quality testing device according to an embodiment of this application is shown. Figure 4 As shown, the device includes:

[0092] The acquisition module 402 is configured to acquire the board information of the board to be inspected, and adjust the position of the visual inspection module based on the board information;

[0093] Image module 404 is configured to acquire visual images of all surfaces of the board material to be inspected through the vision inspection module to obtain a set of images to be inspected;

[0094] The judgment module 406 is configured to perform defect detection, edge banding detection, and size detection on the board material to be inspected based on the image set to be inspected and the board material information, and to judge the quality information of the board material to be inspected based on all the detection results.

[0095] In an optional embodiment, the acquisition module 402 is further configured to:

[0096] Collect the board code on the board to be inspected; determine the board information of the board to be inspected based on the board code; query the preset board database to determine whether the board information is contained in the board database; if yes, adjust the position of the vision inspection module according to the board size information contained in the board information; if no, stop quality inspection of the current board to be inspected and record the board information.

[0097] In an optional embodiment, the acquisition module 402 is further configured to:

[0098] Based on the material size information, determine the width and thickness of the material to be inspected; based on the material width, adjust the positions of the bilateral side cameras in the vision inspection module; based on the material thickness, adjust the position of the top camera in the vision inspection module.

[0099] In an optional embodiment, the image module 404 is further configured to:

[0100] The position of the board to be inspected is adjusted using a preset board transport module. When the board reaches the lower surface inspection position, the bottom camera in the vision inspection module captures an image of the lower surface of the board. When the board reaches the head side inspection position, the head camera in the vision inspection module captures an image of the head side of the board. When the board reaches the upper surface and bilateral side inspection positions, the top camera in the vision inspection module captures an image of the upper surface of the board, and the bilateral side cameras in the vision inspection module capture images of the bilateral side of the board. When the board reaches the tail side inspection position, the tail camera in the vision inspection module captures an image of the tail side of the board.

[0101] In an optional embodiment, the determining module 406 is further configured to:

[0102] The first board region segmentation is performed on the images to be detected contained in the image set to obtain a first board image; the first board image is then segmented into a second board region to obtain a second board image that meets the input size conditions of the pre-trained detection model; the second board image and the board information are used as the input of the pre-trained detection model to output the defect detection results and edge sealing detection results of the board to be detected.

[0103] In an optional embodiment, the determining module 406 is further configured to:

[0104] The images to be detected in the set of images to be detected are judged to be black and white, and edge extraction is performed based on the judgment result to obtain a third board image; the size information to be detected of the board to be detected is determined based on the third board image; the size detection result of the board to be detected is determined based on the size information to be detected and the board size information contained in the board information.

[0105] In an optional embodiment, the determining module 406 is further configured to:

[0106] The defect detection results, edge sealing detection results, and dimensional detection results are weighted and calculated according to preset weighting coefficients to obtain a quality score; the quality information is determined through the quality score based on a preset quality assessment strategy.

[0107] The board material quality inspection device provided in this application collects board material information and adjusts the position of the vision inspection module based on the board material information; the vision inspection module collects visual images of all surfaces of the board material to be inspected, obtaining a set of images to be inspected; based on the set of images to be inspected and the board material information, defect detection, edge banding detection, and dimensional detection are performed on the board material to be inspected, and the quality information of the board material to be inspected is determined based on all the detection results. This achieves automated inspection of board material quality.

[0108] The above is a schematic scheme of a board quality inspection device according to this embodiment. It should be noted that the technical solution of this board quality inspection device and the technical solution of the aforementioned board quality inspection method belong to the same concept. Details not described in detail in the technical solution of the board quality inspection device can be found in the description of the technical solution of the aforementioned board quality inspection method. Furthermore, each component in the device embodiment should be understood as a functional module necessary to implement each step of the program flow or each step of the method; these functional modules are not actual functional divisions or separations. The device claim defined by such a set of functional modules should be understood as a functional module architecture that primarily implements the solution through the computer program described in the specification, and not as a physical device that primarily implements the solution through hardware.

[0109] Figure 5 A structural block diagram of a computing device 500 according to an embodiment of this application is shown. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and a database 550 is used to store data.

[0110] The computing device 500 also includes an access device 540, which enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of wired or wireless network interface (e.g., a Network Interface Card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) interface, a Wi-MAX interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0111] In one embodiment of this application, the aforementioned components of the computing device 500 and Figure 5 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 5 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this application. Those skilled in the art can add or replace other components as needed.

[0112] The computing device 500 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs. The computing device 500 can also be a mobile or stationary server.

[0113] The processor 520 is used to execute computer-executable instructions for each step of the board quality inspection method.

[0114] The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the above-described board quality inspection method belong to the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the above-described board quality inspection method.

[0115] An embodiment of this application also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, are used to perform the steps of the board quality inspection method.

[0116] The above is an illustrative embodiment of a computer-readable storage medium. It should be noted that the technical solution of this storage medium and the technical solution of the aforementioned board quality inspection method belong to the same concept. Details not described in detail in the technical solution of the storage medium can be found in the description of the technical solution of the aforementioned board quality inspection method.

[0117] An embodiment of this application also provides a chip that stores a computer program, which, when executed by the chip, implements the steps of the board quality inspection method.

[0118] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0119] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0120] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0121] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0122] The preferred embodiments disclosed above are merely illustrative of this application. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this application. These embodiments are selected and specifically described in this application to better explain the principles and practical applications of this application, thereby enabling those skilled in the art to better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. A method for inspecting the quality of sheet materials, characterized in that, include: The system collects information about the board material to be inspected and adjusts the position of the vision inspection module based on this information. Specifically, it collects the board material code on the board material to be inspected, determines the board material information based on the board material code, queries a preset board material database to determine whether the database contains the board material information, and if so, determines the board material width and thickness based on the board material size information contained in the board material information, adjusts the positions of the two side cameras in the vision inspection module based on the board material width, and adjusts the position of the top camera in the vision inspection module based on the board material thickness; otherwise, it stops quality inspection of the current board material to be inspected and records the board material information. The visual inspection module acquires visual images of all surfaces of the board to be inspected, thus obtaining a set of images to be inspected. Based on the set of images to be detected and the board information, defect detection, edge banding detection, and size detection are performed on the board to be detected. Based on all the detection results, the quality information of the board to be detected is determined. Specifically, the defect detection and edge banding detection process involves: segmenting the images in the set of images to be detected into a first board region to obtain a first board image; segmenting the first board image into a second board region to obtain a second board image that meets the input size conditions of the pre-trained detection model; using the second board image and the board information as input to the pre-trained detection model; and outputting the defect detection results and edge banding detection results of the board to be detected. Specifically, the deep learning algorithm of the pre-trained detection model is used to extract features and detect targets in the second board image. Based on the board information, the expected appearance of the corresponding model of the board to be detected is determined. Features are extracted from this expected appearance and compared with the feature extraction and target detection results of the second board image to obtain... The process of performing dimensional inspection on the board to be inspected involves determining the black and white color scheme of the images in the image set to be inspected, extracting edges based on the determination results to obtain a third board image, determining the board's dimensions based on the third board image, and determining the board's dimensions based on the board's dimensions and the board's dimensions contained in the board information. The process of judging the quality information of the board to be inspected based on all inspection results involves weighting the defect inspection results, the edge sealing inspection results, and the dimensional inspection results according to a preset weighting coefficient to obtain a quality score. Based on a preset quality assessment strategy, the quality information is determined through the quality score. The weighting coefficient is set as a piecewise function, increasing the weight coefficient of a certain inspection result when it deviates from the normal board. The function in each segment of the piecewise function is one of a constant, a linear function, a power function, or an exponential function.

2. The method according to claim 1, characterized in that, The step involves acquiring visual images of all surfaces of the material to be inspected through the visual inspection module to obtain an image set to be inspected, including: The position of the board to be tested is adjusted using a preset board transport module; When the material to be inspected reaches the lower surface detection position, the lower surface image of the material to be inspected is captured by the bottom camera in the vision inspection module; When the material to be inspected reaches the head side detection position, the head side image of the material to be inspected is acquired by the head camera in the vision inspection module. When the material to be inspected reaches the detection positions of the upper surface and both sides, the top camera in the vision inspection module captures the image of the upper surface of the material to be inspected, and the side cameras in the vision inspection module capture the images of the sides of the material to be inspected. When the material to be inspected reaches the rear side detection position, the rear side image of the material to be inspected is acquired by the rear camera in the vision inspection module.

3. A board material quality testing device, characterized in that, include: The acquisition module is configured to acquire board information of the board to be inspected and adjust the position of the vision inspection module based on the board information. Specifically, it acquires the board code on the board to be inspected, determines the board information of the board to be inspected based on the board code, queries a preset board database to determine whether the board information is contained in the board database. If so, it determines the board width and board thickness of the board to be inspected based on the board size information contained in the board information, adjusts the position of the two side cameras in the vision inspection module based on the board width, and adjusts the position of the top camera in the vision inspection module based on the board thickness. If not, it stops quality inspection of the current board to be inspected and records the board information. The image module is configured to acquire visual images of all surfaces of the board to be inspected through the vision inspection module, thereby obtaining a set of images to be inspected; The judgment module is configured to perform defect detection, edge banding detection, and size detection on the board material to be inspected based on the set of images to be inspected and the board material information, and to judge the quality information of the board material to be inspected based on all the detection results. The process of defect detection and edge banding detection on the board material to be inspected involves: performing a first board material region segmentation on the images to be inspected contained in the set of images to be inspected to obtain a first board material image; performing a second board material region segmentation on the first board material image to obtain a second board material image that meets the input size conditions of the pre-trained detection model; using the second board material image and the board material information as input to the pre-trained detection model; and outputting the defect detection results and edge banding detection results of the board material to be inspected. Specifically, the deep learning algorithm of the pre-trained detection model is used to extract features and detect targets on the second board material image, and based on the board material information, the expected appearance of the board material of the corresponding model to be inspected is determined. Features are extracted from this expected appearance and compared with the feature extraction and target detection results of the second board material image. The process of comparing the defect detection results and the edge banding detection results is as follows: The process of dimensional detection of the board to be inspected involves determining the black and white color scheme of the images to be inspected within the image set, extracting edges based on the determination results to obtain a third board image, determining the dimensional information of the board to be inspected based on the third board image, and determining the dimensional detection result of the board to be inspected based on the dimensional information and the board dimensional information contained in the board information. The process of judging the quality information of the board to be inspected based on all the detection results involves weighting the defect detection results, the edge banding detection results, and the dimensional detection results according to a preset weighting coefficient to obtain a quality score. Based on a preset quality assessment strategy, the quality information is determined through the quality score. The weighting coefficient is set as a piecewise function, which increases the weight coefficient of a detection result when it deviates from the normal board. The function of each segment in the piecewise function is one of a constant, a linear function, a power function, or an exponential function.

4. A computing device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the steps of the board quality testing method according to any one of claims 1 to 2.

5. A computer-readable storage medium storing computer instructions, characterized in that, When executed by the processor, this instruction implements the steps of the board quality inspection method according to any one of claims 1 to 2.

Images