Notebook computer shell surface defect detection method and device and storage medium

Abstract

The invention relates to the field of shell defect detection, in particular to a notebook shell surface defect detection method and device and a storage medium. The method is applied to defect detection of the surface of a notebook computer shell. The device comprises a conveying mechanism, a first detection mechanism and a second detection mechanism, the first detection mechanism comprises a first image acquisition unit; the second detection mechanism comprises a second image acquisition unit and a visual angle adjustment unit; the method comprises the steps of determining a first instruction set of a conveying mechanism and a second instruction set of a visual angle adjusting unit according to model parameters; based on the first instruction set, the conveying mechanism is controlled to convey the shell to the detection stations of the first detection mechanism and the second detection mechanism; controlling the visual angle adjusting unit based on the second instruction set, so that the to-be-detected side face of the shell is completely or partially located in the collection range of the second image collection unit; and performing defect identification on the image in real time. The detection speed is improved, the remodeling time is reduced, and the detection precision and the overall detection efficiency are both considered.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of shell defect detection, and in particular to a notebook shell surface defect detection method, device and storage medium. BACKGROUND

[0002] With the high popularity and accelerated update iteration of consumer electronics products, notebook computers as core mobile computing devices, their appearance quality directly affects the first impression and brand reputation of users. The notebook shell as an important part of the overall structure not only bears the function of protecting internal components, but also plays a key role in the overall texture, aesthetics and user experience of the product. Therefore, efficient and accurate detection of shell surface defects (such as scratches, dents, color differences, dirt, assembly gaps, etc.) has become an integral part of the manufacturing process.

[0003] In recent years, automatic detection technology based on machine vision has gradually become the mainstream research direction. This technology collects shell images or three-dimensional point cloud data through high-resolution industrial cameras, structured light or laser scanning, and combines image processing algorithms (such as edge detection, template matching) for defect recognition.

[0004] For example, patent application publication No. CN114705693A discloses an AI vision detection device and system for shell structure defect detection. The AI vision detection device includes a transmission structure, one end of the transmission structure is a feeding position, the other end of the transmission structure is a discharging position, the transmission structure has a transmission position for product movement, the transmission position includes a first transmission section and a second transmission section with different transmission directions; at least two first side vision detection devices are respectively arranged on both sides of the first transmission section; at least two second side vision detection devices are respectively arranged on both sides of the second transmission section; a structure surface vision detection device is arranged below the transmission position; and an appearance surface vision detection device is arranged above the transmission position. The AI vision detection device of the present application realizes rapid visual detection of products in all directions.

[0005] For example, patent application CN118937332A discloses a method, controller, and device for detecting surface defects in a laptop casing. The method includes: sequentially capturing images of six surfaces of the laptop casing using the imaging component and the light source component; deploying corresponding AI detection models on the casing surfaces corresponding to the images captured by the imaging component; performing defect identification on the images using the AI ​​detection models to obtain image defect identification results; and determining the identification result of the casing surface based on the image defect identification results belonging to the same casing surface. This application embodiment improves the fault tolerance and stability of the detection device by performing regional detection using multiple images, achieving efficient and accurate detection and identification of defect information on the laptop casing surface.

[0006] However, in actual production, manufacturers usually need to perform different models of shell testing on the same production line. Existing testing technologies are inefficient and impractical in complex situations involving mixed testing of multiple models. Summary of the Invention

[0007] The main objective of this application is to provide a method, device, and storage medium for detecting defects on the surface of a notebook computer casing. To solve the aforementioned technical problems, this application specifically adopts the following technical solution: A first aspect of this application is to provide a method for detecting defects on the surface of a notebook casing. The method is applied to a defect detection device, which includes: a conveying mechanism in a conveying path and a first detection mechanism and a second detection mechanism spaced apart. The conveying mechanism is used to carry and convey the casing. The first detection mechanism includes a first image acquisition unit with a fixed viewing angle. The second detection mechanism includes a second image acquisition unit and a viewing angle adjustment unit that drives the second image acquisition unit to move. The method includes: S101, Obtain the model parameters of the housing, and determine the first instruction set of the transmission mechanism and the second instruction set of the viewing angle adjustment unit based on the model parameters; S102, based on the first instruction set, control the conveying mechanism to transport the housing to the detection stations of the first detection mechanism and the second detection mechanism respectively; S103, based on the second instruction set, control the viewing angle adjustment unit so that all or part of the side of the housing to be detected is within the acquisition range of the second image acquisition unit; S105, perform real-time defect identification on the large-area image acquired by the first image acquisition unit and the side image acquired by the second image acquisition unit.

[0008] In some embodiments, the viewing angle adjustment unit includes a displacement driving component; the side of the housing includes a first type of side parallel to the conveying path and a second type of side perpendicular to the conveying path; the first instruction set includes a first cooperative instruction segment for controlling the conveying mechanism to move the first type of side so that the first type of side completely passes through the acquisition range of the second image acquisition unit at least once; the second instruction set includes a second cooperative instruction segment for controlling the displacement driving component to move the second type of side along the vertical direction of the conveying path so that the acquisition range of the second image acquisition unit completely covers the second type of side at least once; the method includes: S104, while executing the first cooperative instruction segment or the second cooperative instruction segment, controlling the second image acquisition unit to acquire at least one side image.

[0009] In some embodiments, the first instruction set includes a housing delivery instruction segment; the housing delivery instruction segment is used to implement step S102; the viewing angle adjustment unit includes a rotation drive component; the second instruction set includes a viewing angle rotation instruction segment; S103 further includes: controlling the rotation drive component based on the viewing angle rotation instruction segment to adjust the shooting direction of the second image acquisition unit to face the side to be detected.

[0010] In some embodiments, the method includes: when performing defect identification on the large-area image, if a defect is identified as being located within a preset shell edge region, marking the side adjacent to the defect as a risk side; increasing the number of detections in which the risk side is completely passed through or completely covered within the acquisition range of the second image acquisition unit, and / or reducing the movement speed of the conveying mechanism or the displacement driving component when acquiring the risk side image; and updating the cooperative instruction segment corresponding to the risk side in the first instruction set or the second instruction set according to the adjusted number of detections or movement speed.

[0011] In some embodiments, S101 includes: S1011, calling a pre-configured first instruction set and a second instruction set from a preset parameter database according to the model parameters; or, S1012, generating the first instruction set and the second instruction set according to the housing geometry corresponding to the model parameters, the field of view parameters of the second image acquisition unit, and the first preset number of detections and the first preset motion speed.

[0012] In some embodiments, S101 further includes: S1013, acquiring historical defect data of the model parameters, and determining a risk side based on the historical defect data; the risk side includes: a side with a high incidence of defects, and / or, a local area within the side with a high incidence of defects; S1014, generating a collaborative instruction segment corresponding to the risk side based on the housing geometry corresponding to the model parameters, the field of view parameters of the second image acquisition unit, and a second preset number of detections and a second preset movement speed; wherein, the second preset number of detections is greater than the first preset number of detections, or the first preset movement speed is greater than the second preset movement speed.

[0013] In some embodiments, the apparatus further includes a marking mechanism; the method further includes controlling the marking mechanism to mark the housing surface according to the target coordinates of the identified defect on the housing surface.

[0014] In some embodiments, the conveying mechanism includes at least two conveying components, and a housing clamp and a lifting mechanism configured one-to-one with each conveying component. The housing clamp is connected to the conveying component via the lifting mechanism. The conveying component is used to drive the housing clamp to reciprocate between a loading position and a unloading position, and the lifting mechanism is used to drive the housing clamp to lift. The method further includes: when one of the housing clamps moves to the unloading position, controlling the other housing clamp to move to the loading position; when two adjacent housing clamps move toward each other on the conveying component to an intersection position, controlling one of the lifting mechanisms to drive the corresponding housing clamp to lift.

[0015] A second aspect of this application is to provide a computer device, the device comprising: Memory, used to store computer programs; A processor is configured to execute the computer program and, in executing the computer program, implement the steps of the defect detection method for the surface of a notebook housing as provided in any embodiment of this application.

[0016] A third aspect of this application is that a computer-readable storage medium is also provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the defect detection method for the surface of a notebook casing provided in any embodiment of this application.

[0017] Beneficial effects: This application provides a method, device, and storage medium for detecting defects on the surface of a notebook casing. Through a relatively simple mechanical structure and high-precision command drive, it achieves a high degree of coordination between the transmission mechanism and the viewing angle adjustment unit. While maintaining high detection accuracy, it improves the overall detection efficiency, enhances the adaptability and reliability in multi-model mixed-line detection environments, and thus enhances production line compatibility and overall production capacity.

[0018] The first inspection unit is equipped with a fixed-view image acquisition unit for large-area inspection of the housing. Since the large-area structure is relatively regular and not sensitive to changes in viewing angle, a fixed installation method can meet the inspection requirements of various housing models, effectively simplifying the structure and improving stability.

[0019] The second detection mechanism is equipped with a dynamic viewing angle image acquisition unit. The viewing angle is adjusted in real time by the viewing angle adjustment unit (including displacement driving component and rotation driving component) to adapt to the side detection requirements of different shells, thereby replacing the complex mechanical structure of traditional solutions that rely on shell rotation or multiple sets of surround cameras.

[0020] For each housing model, a set of time-series coordinated instructions is generated or invoked. The first instruction set controls the operation of the conveyor mechanism to adjust the housing position, and the second instruction set controls the viewing angle adjustment unit to adjust the spatial angle or position of the second image acquisition unit, thereby aligning the position of the housing with the acquisition range of the image acquisition unit in the same time sequence. For example, when one side of the housing moves to a certain position, the second image acquisition unit synchronously adjusts to the corresponding shooting angle, so that part or all of the target side is within the field of view.

[0021] Therefore, the method of abstracting mechanical actions into programmable and reusable instruction sequences allows for automatic model adaptation within minutes when switching housing models, without the need for physical adjustments to the camera or mechanical structure, only requiring updates to the housing parameters, thus reducing the time from hours to minutes.

[0022] Furthermore, side detection can employ a local acquisition strategy. Through precise coordination between the conveying mechanism and the displacement driving component, the side to be inspected is scanned systematically along the vertical or horizontal direction within the field of view of the second image acquisition unit, ensuring full coverage without omissions. Thus, the second image acquisition unit does not require a highly flexible mechanical structure; it only needs to support simple translation and steering adjustments, achieving high-resolution, blind-spot-free side coverage within limited space and cost.

[0023] Furthermore, this application also provides a differentiated detection mechanism based on defect identification results or historical defect data. For high-risk or localized areas, the detection intensity is automatically increased, for example, by increasing the number of data acquisitions or reducing the cooperative movement speed, while maintaining high-speed passage through non-risk areas. Through differentiated resource allocation strategies, the defect detection capability of key areas is specifically enhanced without significantly affecting the overall cycle time, achieving an effective balance between accuracy and efficiency. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. The elements or parts in the drawings are not necessarily drawn to scale. Obviously, the drawings described below are some embodiments of this application; for those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0025] Figure 1 This is a schematic diagram of the structure of a defect detection device for the surface of a notebook casing provided in an embodiment of this application; Figure 2 This is a schematic diagram of the state of the viewing angle adjustment unit when detecting the left side of the housing, provided in an embodiment of this application; Figure 3 This is a schematic diagram of the state of the viewing angle adjustment unit when detecting the rear side of the housing, provided in an embodiment of this application; Figure 4 This is a schematic diagram of the state of the viewing angle adjustment unit when detecting the right side of the housing, provided in an embodiment of this application; Figure 5 This is a schematic flowchart of a defect detection method for the surface of a notebook computer casing provided in an embodiment of this application; Figure 6 This is a schematic diagram of a type of notebook casing provided in an embodiment of this application; Figure 7 This is a schematic block diagram of the structure of a computer device provided in an embodiment of this application.

[0026] Summary of reference numerals in the attached drawings: Defect detection device 10, first detection mechanism 11, first image acquisition unit 111, second detection mechanism 12, second image acquisition unit 121, viewing angle adjustment unit 122, displacement drive component 1221, rotation drive component 1222, lifting drive module 1223, conveying mechanism 13, housing clamp 131, conveying assembly 132, marking mechanism 14. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0028] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0029] In this document, suffixes such as “module,” “part,” or “unit” used to denote elements are used only for illustrative purposes and have no specific meaning in themselves. Therefore, “module,” “part,” or “unit” may be used interchangeably.

[0030] In this document, the terms "upper," "lower," "inner," "outer," "front," "rear," "one end," and "the other end," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0031] In this document, unless otherwise explicitly specified and limited, the terms "installed," "equipped with," and "connected," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0032] In this document, the term “and / or” includes any and all combinations of one or more of the listed related items.

[0033] In this article, the term "multiple" means two or more, that is, it includes two, three, four, five, etc.

[0034] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0035] This application provides a method, device, and storage medium for detecting defects on the surface of a notebook casing. Through a relatively simple mechanical structure and high-precision command drive, it achieves a high degree of coordination between the transmission mechanism and the viewing angle adjustment unit. While maintaining high detection accuracy, it improves the overall detection efficiency, enhances the adaptability and reliability in multi-model mixed-line detection environments, and thus enhances production line compatibility and overall production capacity.

[0036] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0037] Please see Figure 1 To the diagram, Figure 1 This is a schematic diagram of a defect detection device for the surface of a notebook casing provided in an embodiment of this application. Figure 1 As shown in the figure, this application provides a defect detection device for the surface of a notebook casing. The defect detection device 10 includes: a conveying mechanism 13 set in a conveying path and a first detection mechanism 11 and a second detection mechanism 12 set at intervals along the conveying path.

[0038] In some embodiments, the conveying path is set along the X-axis direction, which is the conveying direction. The conveying mechanism 13 can drive the housing to reciprocate in the X-axis direction to carry and convey the housing.

[0039] In some embodiments, the device 10 further includes a loading position and a unloading position; the conveying mechanism 13 includes two conveying components 132, and a housing clamp 131 and a lifting mechanism configured one-to-one with the conveying components 132. The housing clamp 131 is connected to the conveying components 132 through the lifting mechanism. The conveying components 132 are used to drive the housing clamp 131 to reciprocate between the loading position and the unloading position. The lifting mechanism is used to drive the housing clamp 131 to lift.

[0040] Specifically, the two conveying components 132 are respectively a first conveying component and a second conveying component, the two housing clamps 131 are respectively a first housing clamp and a second housing clamp, and the two lifting mechanisms are respectively a first lifting mechanism and a second lifting mechanism. The first lifting mechanism is fixedly connected to the first conveying component, and the first housing clamp is fixedly connected to the output end of the first lifting mechanism; correspondingly, the second lifting mechanism is fixedly connected to the second conveying component, and the second housing clamp is fixedly connected to the output end of the second lifting mechanism.

[0041] The two conveying components 132 connect the loading and unloading positions. During operation, when the first conveying component drives the first housing clamp to move to the unloading position, it controls the second conveying component to drive the second housing clamp to move to the loading position; similarly, when the first conveying component drives the first housing clamp to move to the loading position, it controls the second conveying component to drive the second housing clamp to move to the unloading position. When the first housing clamp and the second housing clamp move towards each other on the two conveying components 132 to the intersection position, one of the lifting mechanisms is controlled to drive the corresponding housing clamp to lift to avoid collision, thereby achieving continuous loading and unloading and efficient flow.

[0042] In some embodiments, a lifting mechanism is provided between any one of the housing clamps 131 and the conveying assembly 132. In some embodiments, a lifting mechanism is provided between each housing clamp 131 and the conveying assembly 132, and the housing clamp that does not carry a housing is lifted first each time.

[0043] In other embodiments, the conveying mechanism 13 may further include more than two conveying components 132, with the housing clamps 131 and the lifting mechanism still configured one-to-one with the conveying components 132. It should be noted that the number of conveying components 131 is a multiple of two, and two adjacent conveying components 132 form a group, driving the two housing clamps 131 on them to move in opposite directions.

[0044] In some embodiments, the conveying assembly 132 employs existing technology and includes a conveying track and a drive mechanism. The lifting mechanism is slidably connected to the corresponding conveying track and is driven by the corresponding drive mechanism to move along the conveying track. The drive mechanism employs existing technology, such as a structure where a motor drives a synchronous belt via a synchronous pulley, a structure where a motor drives a slider via a lead screw, or a structure where a linear motor drives a slider. The specific structure will not be described in detail in this embodiment. It should be understood that moving from the loading position to the unloading position is forward movement, and moving from the unloading position to the loading position is reverse movement.

[0045] The first lifting mechanism and the second lifting mechanism adopt existing technology, such as lifting cylinders; the first housing clamp and the second housing clamp also adopt existing technology, as long as they can support the laptop housing, and their structure will not be described in detail in this embodiment.

[0046] In some embodiments, the first detection mechanism 11 includes a first image acquisition unit 111 with a fixed viewing angle, used for rapid imaging of a large surface (such as the top or bottom surface) of the housing. Since the large surface structure is relatively regular and insensitive to changes in viewing angle, a fixed installation method can meet the detection requirements of various housing models, effectively simplifying the structure and improving stability. For example, as... Figure 1 As shown, the first detection mechanism 11 includes a first mounting frame and a first image acquisition unit 111 disposed on the first mounting frame.

[0047] In some embodiments, the second detection mechanism 12 includes a second image acquisition unit 121 and a viewing angle adjustment unit 122 for driving the movement of the second image acquisition unit 121. For example, Figure 1 As shown, the second detection mechanism 12 includes a second mounting frame and a second image acquisition unit 121 and a viewing angle adjustment unit 122 disposed on the second mounting frame.

[0048] In some embodiments, the viewing angle adjustment unit 122 includes a displacement driving component 1221 and a rotation driving component 1222. The displacement driving component 1221 slides along the horizontal-vertical direction (i.e., the X-axis direction) of the transmission path (set along the Y-axis direction) to drive the second image acquisition unit 121 to move horizontally; the rotation driving component 1222 is used to adjust the shooting direction. In some embodiments, the viewing angle adjustment unit further includes a lifting driving module 1223 to adjust the shooting height to drive the second image acquisition unit 121 to move vertically (i.e., in the Z-axis direction).

[0049] In some embodiments, the viewing angle adjustment unit 122 includes a displacement driving component 1221 and a rotation driving component 1222. The displacement driving component 1221 slides in the vertical direction (i.e., the X-axis direction) of the transmission path (set along the Y-axis direction) to drive the second image acquisition unit 121 to move horizontally; the rotation driving component 1222 is used to adjust the shooting angle or direction of the second image acquisition unit 121. In some embodiments, the viewing angle adjustment unit further includes a lifting driving module 1223 for adjusting the height of the second image acquisition unit 121 in the vertical direction (i.e., the Z-axis direction).

[0050] In other words, the displacement drive component 1221 supports the movement of the second image acquisition unit 121 in a horizontal direction (i.e., the Y-axis direction) perpendicular to the conveying direction of the conveying mechanism (i.e., the X-axis direction), achieving complete field-of-view coverage through translation along the Y-axis. Simultaneously, the rotation drive component 1222 can adjust the camera angle according to actual needs to adapt to angle changes on different sides. Furthermore, the lifting drive module 1223 supports the vertical lifting movement of the second image acquisition unit 121 in the Z-axis direction, adapting to housings with different height characteristics. Thus, the three-dimensional adjustment mechanism (i.e., horizontal movement along the X-axis, conveying direction along the Y-axis, and vertical lifting along the Z-axis) combined with the rotation adjustment function enables the device to flexibly handle housings with various complex geometries, improving the high precision and efficiency of the detection process to a certain extent, while also simplifying the design complexity of the equipment structure.

[0051] For example, such as Figure 1 As shown, the rotation drive component 1222 can be connected to the output end of the displacement drive component 1221, the lifting drive module 1223 can be connected to the output end of the rotation drive component 1222, and the second image acquisition unit 121 can be connected to the output end of the lifting drive module 1223.

[0052] For example, such as Figure 1 As shown, the displacement drive component 1221 can be a linear motor module, the rotation drive component 1222 can be a rotary cylinder, and the lifting drive module 1223 can be a linear cylinder.

[0053] Please see Figures 2 to 4 , Figure 2 This is a schematic diagram of the state of the viewing angle adjustment unit when detecting the left side of the housing, provided in an embodiment of this application. Figure 3 This is a schematic diagram of the state of the viewing angle adjustment unit when detecting the rear side of the housing, provided in an embodiment of this application; Figure 4 This is a schematic diagram of the state of a viewing angle adjustment unit when detecting the right side of the housing, as provided in an embodiment of this application. Figures 2 to 4 As shown, through the coordinated movement of multiple components, the second image acquisition unit 121 can flexibly adapt to the side of the shell with different heights, thicknesses and edge contours, thereby achieving high coverage and high resolution side imaging.

[0054] In some embodiments, such as Figures 2 to 4As shown, the device also includes a marking mechanism 14 disposed on the second detection mechanism 12. The marking mechanism 14 can move in the Y direction with the displacement driving component and, in conjunction with the conveying mechanism 13, drives the housing to move in the X direction. The marking mechanism 14 can physically mark the defects on the surface of the housing according to the target coordinates, facilitating subsequent sorting or rework. For example, the marking mechanism 14 is connected to the output end of the displacement driving component 1221. The marking mechanism 14 includes a marking lifting unit and a marking pen, with the marking pen connected to the output end of the lifting unit. The lifting unit can, for example, be a lifting cylinder.

[0055] In some embodiments, the relative positions of the first detection unit 11 and the second detection unit 12 can be flexibly adjusted according to the production line cycle or spatial layout. For example, the first image acquisition unit 111 is positioned in front of the second image acquisition unit 121 to acquire large-area images first. Alternatively, the first image acquisition unit 111 can be positioned behind the second image acquisition unit 121 to acquire side images first.

[0056] In some embodiments, the defect detection device 10 further includes a protective housing, which is entirely covered outside the conveying mechanism 13, the first detection mechanism 11 and the second detection mechanism 12. The housing is mainly used to block ambient light interference, prevent dust from falling into the surface of the housing, and improve the safety of equipment operation and the accuracy of detection.

[0057] In some embodiments, each image acquisition unit (including the first image acquisition unit 111 and the second image acquisition unit 121) may be equipped with a dedicated light source module. The light source can be adjusted in brightness, angle and color temperature according to the housing material (such as metal, paint, etc.) and surface characteristics to improve the accuracy of subsequent image recognition.

[0058] In some embodiments, an automatic alignment mechanism is provided at the loading position, including pushing mechanisms in the X and Y directions. After the housing is placed in the housing fixture 131, the two pushing mechanisms advance synchronously from both sides towards the center, accurately pushing the housing to the designated position on the fixture. This ensures that the housing remains in a standard posture and within the camera's field of view during transport and inspection, addressing potential issues such as housing misalignment, tilting, or inconsistent positioning that may occur during manual or robotic arm loading. For example, the pushing mechanism can be a cylinder or a linear motor.

[0059] In some embodiments, to prevent collisions between housings during equipment operation, limit protection mechanisms are configured for all moving parts. For example, the main conveyor motor that drives the housing clamp 131 to move along the conveyor assembly 132, the horizontal slide motor used in the displacement drive component 1221 of the viewing angle adjustment unit 122, the vertical lifting motor used in the lifting drive component 1222, and the push rod motor in the loading and straightening mechanism all integrate hardware limit sensors (such as photoelectric switches, micro switches, or magnetic proximity switches). When a moving part reaches a preset travel limit position, the limit sensor immediately feeds back a signal to the control system, forcibly stopping the motor operation to avoid overshoot or structural damage. In addition, limit and speed limits can be set at the software level to achieve dual safety protection.

[0060] It should be noted that, Figures 1 to 4 The specific mechanical structure shown does not constitute a limitation on the scope of protection of this invention. In practical applications, the structural layout, driving method, or safety mechanism can be reasonably adjusted or replaced. For example, the various functions of the viewing angle adjustment unit can also be realized through a multi-axis robotic arm, a sliding table module, or other precision motion platform to achieve adaptive adjustment of the shooting angle.

[0061] Please see Figure 5 , Figure 5 This is a schematic flowchart illustrating a method for detecting defects on the surface of a laptop casing, as provided in an embodiment of this application. Figure 5 As shown in the figure, this application provides a method for detecting defects on the surface of a notebook computer casing. Applied to a defect detection device, the device includes: a conveying mechanism in a transport path and a first detection mechanism and a second detection mechanism spaced apart; the conveying mechanism is used to carry and transport the casing; the first detection mechanism includes a first image acquisition unit with a fixed viewing angle; the second detection mechanism includes a second image acquisition unit and a viewing angle adjustment unit that drives the second image acquisition unit to move; S101, Obtain the model parameters of the housing, and determine the first instruction set of the transmission mechanism and the second instruction set of the viewing angle adjustment unit based on the model parameters; S102, based on the first instruction set, control the conveying mechanism to transport the housing to the detection stations of the first detection mechanism and the second detection mechanism respectively; S103, based on the second instruction set, control the viewing angle adjustment unit so that all or part of the side of the housing to be detected is within the acquisition range of the second image acquisition unit; S105, perform real-time defect identification on the large-area image acquired by the first image acquisition unit and the side image acquired by the second image acquisition unit.

[0062] Specifically, the model parameters of the housing are obtained, and a first instruction set and a second instruction set are generated accordingly. The first instruction set is used to control the operating status of the conveying mechanism (such as start / stop, speed, and positioning) to adjust the position of the housing, and the second instruction set is used to control the viewing angle adjustment unit to adjust the spatial angle or position of the second image acquisition unit. This achieves alignment between the position of the housing and the acquisition range of the image acquisition unit in the same time sequence, so as to complete the complete image acquisition.

[0063] The image acquisition unit refers to the camera device installed in the inspection mechanism, used to acquire images of the shell surface. Specifically, the first image acquisition unit is used to acquire large-area images of the shell, such as the top or bottom surface; the second image acquisition unit is used to acquire side images of the shell, such as the front, back, left, and right sides.

[0064] The first detection mechanism is positioned at a fixed location on the transport path. Its first image acquisition unit uses a fixed viewing angle to acquire image information of the largest surface area (i.e., the large surface) of the shell. The second detection mechanism is located at a distance after or before the first detection mechanism. It includes a second image acquisition unit and a viewing angle adjustment unit connected to it. The viewing angle adjustment unit is used to adjust the spatial posture of the second image acquisition unit, enabling the second image acquisition unit to achieve multi-degree-of-freedom movement, such as rotation around an axis, lifting, or lateral offset. This allows for segmented or continuous imaging of the front, back, left, and right sides of the shell, ensuring that different sides of the shell are effectively covered and photographed.

[0065] After the conveying mechanism delivers the housing to the inspection station, the two image acquisition units sequentially acquire images and send the large-area image and side image to the preset defect recognition algorithm in real time to intelligently identify abnormal defects or flaws such as scratches and dents, thereby achieving efficient and comprehensive automated appearance inspection.

[0066] Laptop casings, as typical multi-surface industrial components, have complex structures and come in various models. Please refer to... Figure 6 , Figure 6 This is a schematic diagram of a type of notebook casing provided in an embodiment of this application, such as... Figure 6 As shown, the casing typically comprises three main components: A) the upper casing, C) the keyboard casing, and D) the lower casing. Each type of casing has one outer surface and four sides, and different product series of laptops exhibit significant differences in size and outline, resulting in highly complex testing conditions.

[0067] In actual production, laptop manufacturers often need to frequently switch between different models of casing inspection tasks on the same automated production line. However, existing automated inspection technologies often rely on manual recalibration of camera positions, adjustment of light source angles, and modification of mechanical positioning parameters when changing models. The entire process takes two to three hours, affecting production line efficiency and limiting practicality.

[0068] It should be understood that this application generates or invokes a set of time-series-related collaborative instructions for each type of housing. The instruction set will precisely plan the control parameters of the defect detection device under different working conditions according to the detection cycle requirements. For example, when a certain side of the housing moves to a certain position, the second image acquisition unit will synchronously adjust to the corresponding shooting angle so that part or all of the target side is within the field of view.

[0069] Therefore, the method of abstracting mechanical actions into programmable and reusable instruction sequences makes model switching unnecessary for cumbersome adjustments to the camera layout. Simply updating the housing parameters can complete the automatic model adaptation within minutes, reducing the time required for model change from hours to minutes, reducing changeover time, and improving overall testing efficiency, production line compatibility, and flexibility.

[0070] In some embodiments, the shooting strategy of the second image acquisition unit is dynamically adjusted according to the specific working conditions and hardware configuration of the current housing model to adapt to the actual constraints under different structural and degree-of-freedom configurations.

[0071] For example, in the overall acquisition strategy, the entire side of the housing to be detected is within the acquisition range of the second image acquisition unit. A complete side image can be obtained by triggering only one shot, avoiding unnecessary actions and time overhead. It should be understood that in the overall acquisition strategy, the second image acquisition unit can obtain a complete side image with a single shot at a specific position, which is suitable for scenarios with small size or good field of view matching.

[0072] For example, in the local acquisition strategy, the side of the shell to be inspected is within the acquisition range of the second image acquisition unit. At this time, collaborative acquisition is triggered. High-resolution side images are acquired multiple times and in sections by the displacement of the second image acquisition unit or the shell to complete full side coverage. There may be appropriate overlap between the local side images, so that defects in the entire side to be inspected can be completely identified in the later stage.

[0073] It should be understood that the local acquisition strategy is achieved through collaborative acquisition, using multiple shots and coordinated movement to achieve overall coverage. This strategy is suitable for situations where the side dimensions exceed limits, high-precision detection is required, or the degrees of freedom of the viewing angle adjustment unit are limited. For example, when the degrees of freedom or travel of the viewing angle adjustment unit is limited, the field of view of the second image acquisition unit in a single image is also limited. If the side dimension is too large, it may not be possible to completely cover the entire side to be detected with a single image. Furthermore, in scenarios requiring high detection accuracy, the acquisition accuracy can be improved by reducing the shooting distance.

[0074] In some embodiments, based on the differences in their roles during the detection process, the first instruction set may include a housing delivery instruction segment applied before acquisition and a first coordination instruction segment applied during acquisition.

[0075] The housing transport command segment is used to implement step S102, namely: based on the housing transport command segment, the conveying mechanism is controlled to transport the housing to the detection stations of the first detection mechanism and the second detection mechanism respectively. The detection station is usually a fixed physical location area. When a local acquisition strategy is adopted and the acquisition object is a type of side view, the detection station is the initial position for collaborative acquisition, and the conveying mechanism is controlled to move from the starting position. The first collaborative command segment is used to move the housing in the local detection strategy to achieve full side coverage during the acquisition process.

[0076] In some embodiments, based on the differences in their roles or the different action units during the detection process, the second instruction set may include a viewpoint rotation instruction segment and a viewpoint elevation instruction segment applied before acquisition, as well as a second coordination instruction segment applied during acquisition.

[0077] The viewpoint rotation command segment controls the rotation drive component to adjust the shooting direction of the second image acquisition unit to face the side to be detected. The viewpoint elevation command segment controls the elevation drive component to adjust the shooting height of the second image acquisition unit to achieve optimal imaging alignment with the side to be detected in the vertical direction; for example, making the optical axis center of the camera substantially at the same level as the geometric center of the side to be detected. The second coordination command segment moves the second image acquisition unit in a local detection strategy to achieve full-side coverage during the acquisition process.

[0078] It should be understood that, through the three-dimensional adjustment mechanism (i.e., horizontal movement of the X-axis, conveying direction of the Y-axis, and vertical lifting of the Z-axis) plus the rotation adjustment function, the device can flexibly cope with shells of various geometric sizes and complete multi-sided detection, so that the shell detection process does not need to be flipped or moved, which can significantly reduce the complexity of structural and algorithm design.

[0079] In some embodiments, the sides of the housing include a type of side parallel to the conveying path and a type of side perpendicular to the conveying path. Specifically, the sides of the housing are divided into two types according to their direction relative to the conveying path: one type of side is parallel to the conveying path, such as... Figure 2 The middle left side, and as Figure 4 The middle right side, and the second type of side are perpendicular to the conveying path, such as... Figure 3 The rear side of the middle.

[0080] In some embodiments, the viewing angle adjustment unit includes a displacement driving component; the first instruction set includes a first cooperative instruction segment for controlling the conveying mechanism to move the first type of side so that the first type of side completely passes through the acquisition range of the second image acquisition unit at least once; the second instruction set includes a second cooperative instruction segment for controlling the displacement driving component to move the second type of side along the vertical direction of the conveying path so that the acquisition range of the second image acquisition unit completely covers the second type of side at least once.

[0081] Specifically, during the collaborative acquisition process, the conveying mechanism is controlled based on the first collaborative command segment to transport the housing at a preset speed within a specific travel range along the conveying path, i.e., in the case of... Figures 2 to 4 The device moves in the X direction. During the movement, the side of the housing to be detected passes through the fixed field of view of the second image acquisition unit at least once, thereby achieving full-coverage imaging by moving the workpiece and using a stationary camera.

[0082] Alternatively, during collaborative acquisition, the displacement driving component is controlled based on the second collaborative command segment to drive the second image acquisition unit to move along a direction perpendicular to the transport path within a specific travel range at a preset speed, i.e., in the case of... Figures 2 to 4 The camera moves in the Y direction. During the movement, the fixed field of view of the second image acquisition unit completely covers the side of the housing to be detected at least once, thereby ensuring complete acquisition by moving the camera while keeping the workpiece stationary.

[0083] It should be understood that, based on the structural characteristics of the detection device (such as the transmission mechanism supporting X-direction movement) and the regular geometric features of the housing (such as the side surfaces being distributed along the XY direction), this application proposes a classification-based collaborative acquisition mechanism, which divides the side surfaces of the housing into a first-class side parallel to the transmission path and a second-class side perpendicular to it, and matches different motion strategies to each.

[0084] For one type of side view, the side view only needs to be transported in the X direction by the conveying mechanism to completely pass through the fixed field of view of the second image acquisition unit, without adjusting the camera position. For another type of side view, the horizontal movement of the displacement drive component of the viewing angle adjustment unit in the Y direction achieves segment-by-segment coverage of the side view by the camera's field of view. Thus, only the viewing angle adjustment unit needs to have translational capability in the Y-axis direction, eliminating the need for complex multi-degree-of-freedom mechanical structures. This simplifies hardware design and manufacturing costs, while ensuring the integrity of the detection coverage through precise collaborative control.

[0085] In some embodiments, the specific travel range refers to the minimum effective distance that the conveying mechanism or displacement driving component needs to move, calculated based on the actual dimensions of the housing side, so that the field of view of the second image acquisition unit can completely cover the area to be detected. For example, it is dynamically determined based on the length of one type of side or the width of the second type of side of the current housing, so that the first type of side completely passes through the acquisition range of the second image acquisition unit once, or so that the acquisition range of the second image acquisition unit completely covers the second type of side once.

[0086] In some embodiments, the preset motion speed is the pre-set movement speed of the transmission mechanism or displacement driving component during the image acquisition process.

[0087] In some embodiments, the preset number of detections is the number of round trips within a specific travel range. For example, when the preset number of detections is 2, the conveying mechanism moves back and forth once within the specific travel range (i.e., one outbound and one return trip). Or, when the preset number of detections is 1, the displacement driving component moves once in a single trip within the specific travel range (e.g., one outbound trip).

[0088] In some embodiments, a preset motion speed and a preset number of checks can be pre-set according to the detection accuracy and the overall production line cycle time. The slower the preset motion speed and the more preset checks, the more complete the image coverage, but the longer the required detection time. For example, if high detection accuracy is required, the motion speed can be set to a lower value or the number of checks can be set to a higher value to extend the image acquisition time window or to increase the number of images and overlapping areas through reciprocating motion, thereby improving the acquisition accuracy of local details. Conversely, if the production line pursues rapid turnover, the motion speed can be appropriately increased or the number of checks can be reduced to shorten the single-piece inspection cycle.

[0089] It should be understood that specific parameters can be flexibly configured according to different working conditions. For Class I and Class II sides, the same or different parameters can be preset. For example, multiple round-trip scans can be set in the quality inspection process with high precision requirements, while single-pass acquisition is preferred in the scenario of large-volume rapid sorting, so as to take into account both product quality and production capacity targets.

[0090] In some embodiments, the method includes: S104, while executing the first cooperative instruction segment or the second cooperative instruction segment, controlling the second image acquisition unit to acquire at least one side image, thereby achieving full side coverage. It should be understood that the image acquisition mode of the second image acquisition unit is precisely controlled by the second instruction set, and can flexibly adopt one or a combination of preset acquisition point triggering, preset frequency acquisition, or continuous acquisition according to actual detection needs.

[0091] For example, in the preset acquisition point trigger mode, several key positions (such as Y-axis coordinates) are predefined on the movement path based on the side dimensions of the housing, the field of view, and the preset number of detections. When the displacement driving component or the conveying mechanism moves to this position, an image acquisition is automatically triggered. For instance, if the side length is 20cm and the field of view of the second image acquisition unit covers 5cm, then an image acquisition is triggered when the housing moves to the starting point (0cm) and the midpoint (such as 4cm, 8cm, 12cm, 16cm, 20cm) of the field of view, respectively, ensuring that the side is completely covered and that there is partial overlap between local side images.

[0092] For example, in the preset frequency acquisition mode, the second image acquisition unit takes pictures at fixed time intervals (such as every 10 milliseconds), which is suitable for scenarios with uniform motion and uniform sampling required, and can simplify the control logic.

[0093] For example, in continuous acquisition mode, the camera continuously images throughout the entire movement, and the effective area is subsequently extracted through image filtering or stitching.

[0094] It should be understood that the side detection employs a local acquisition strategy. Through the precise coordination of the conveying mechanism and the displacement driving component, the side to be inspected is scanned systematically along the vertical or horizontal direction within the field of view of the second image acquisition unit, ensuring full coverage without omissions. Therefore, the second image acquisition unit does not require a highly flexible mechanical structure; it only needs to support simple translation and steering adjustments, achieving high-resolution, blind-spot-free side coverage within limited space and cost.

[0095] In some embodiments, the housing model parameters may include housing geometry, such as length, width, side height, chamfer radius, etc. In some embodiments, the model parameters may be issued by a higher-level control system, obtained through barcode scanning or RFID identification, or manually entered by the operator.

[0096] In other embodiments, the second detection mechanism is located a distance after the first detection mechanism along the conveying path. At this time, the first image acquisition unit first performs image acquisition, extracts the shell outline, edge features or key structural points of the large-area image, and performs matching and recognition in combination with the pre-stored template to predict the model parameters of the current shell, so as to adapt to production line scenarios where model information has not been pre-entered or where there is mixed detection.

[0097] In some embodiments, S101 includes: S1011, calling a pre-configured first instruction set and a second instruction set from a preset parameter database according to the model parameters. The parameter database can be constructed through preliminary engineering verification and manual calibration, and supports the input of new models and the updating and maintenance of existing entries. It stores the model parameters, their corresponding first instruction set, second instruction set, light source configuration parameters, historical defect data, and the judgment rules and model parameters of the defect identification algorithm. Therefore, when changing models, the control mode of the defect detection device can be quickly switched without real-time calculation.

[0098] In other embodiments, when the parameter database does not store the instruction set corresponding to the current housing model, S101 includes: S1012, generating the first instruction set and the second instruction set according to the housing geometry corresponding to the model parameter, the field of view parameters of the second image acquisition unit, the first preset number of detections, and the first preset movement speed.

[0099] Specifically, based on the input model parameters, the first preset number of detections, the first preset movement speed, and the field-of-view parameters of the second image acquisition unit (such as field of view, imaging range, resolution, etc.), an adapted first instruction set and second instruction set are dynamically generated. For example, if the side of the housing is high, the stroke of the lifting drive component needs to be set accordingly; if a certain side is long, the specific stroke range of the conveying mechanism or displacement drive component needs to be adjusted accordingly; if the current model is a high-end production line, the detection accuracy requirements for the housing are higher, and the overall cycle time is slower, the moving speed of the conveying mechanism or displacement drive component can be slowed down, i.e., the first preset movement speed, or the number of round trips within a specific stroke range can be increased, i.e., the first preset number of detections.

[0100] In some embodiments, S101 further includes: S1013, acquiring historical defect data of the model parameters, and determining a risk side based on the historical defect data; the risk side includes: a side with a high incidence of defects, and / or, a local area within the side with a high incidence of defects; S1014, generating a collaborative instruction segment corresponding to the risk side based on the housing geometry corresponding to the model parameters, the field of view parameters of the second image acquisition unit, and a second preset number of detections and a second preset movement speed; wherein, the second preset number of detections is greater than the first preset number of detections, or the first preset movement speed is greater than the second preset movement speed.

[0101] Specifically, after obtaining the parameters of the current housing model, the system further retrieves the historical defect data corresponding to the model from the preset parameter database. The historical defect data refers to the defect information recorded for a specific housing model in past production batches, including the defect location (such as the specific side and coordinate area), type (such as scratches, dents, color difference), frequency of occurrence, and severity.

[0102] By analyzing historical defect data, the frequency and type of defects on each side or in local areas can be identified, thereby identifying risky sides. These risky sides can be complete sides with a high incidence of defects, or local areas on a particular side where defects are concentrated. For example, if scratches frequently appear on the rear side of a certain model's housing, then the rear side is a risky side. Or, if the charging port on the right side of a certain model's housing is prone to protrusions due to its structural design, then the charging port area is a local area on the side with a high incidence of defects.

[0103] Based on the housing geometry, the field of view of the second image acquisition unit, and a higher second preset detection count and / or a lower second preset motion speed, a coordinated command segment is generated for the risky side. It should be noted that when no preset detection count is selected, the second preset detection count is equal to or slightly less than the first preset detection count; when no reduction in preset motion speed is selected, the second preset motion speed can be equal to or slightly greater than the first preset motion speed to balance the overall rhythm.

[0104] It should be understood that the first preset number of inspections and the first preset movement speed apply to the non-risk side, representing the default number of image acquisition passes and baseline transport speed in the standard inspection process. The second preset number of inspections and the second preset movement speed apply to the risk side, allowing for the selection of controlling the conveyor mechanism or displacement drive components to reduce the travel speed and / or increase the number of passes within a specific travel range in the risk area. This achieves denser and more detailed local image acquisition, reducing the probability of defect omission. Thus, without significantly slowing down the overall cycle time, inspection resources are precisely focused on high-risk areas, achieving a dynamic balance between efficiency and accuracy.

[0105] In some embodiments, the instruction set includes control instructions arranged in a time sequence. Each control instruction defines at least one of the target position, target velocity, and target direction at a specific moment, so as to ensure strict synchronization between mechanical actions and image acquisition, achieving efficient and complete surface coverage. For example, during collaborative acquisition, the target velocity is either a first preset motion velocity or a second preset motion velocity.

[0106] This application embodiment also provides a dynamic risk response mechanism based on large-area detection results. The method includes: when performing defect identification on the large-area image, if a defect is identified within a preset shell edge region, the side adjacent to the defect is marked as a risk side; increasing the number of detections in which the risk side is completely passed through or completely covered within the acquisition range of the second image acquisition unit, and / or reducing the movement speed of the conveying mechanism or the displacement driving component when acquiring the risk side image; and updating the cooperative instruction segment corresponding to the risk side in the first instruction set or the second instruction set according to the adjusted number of detections or movement speed.

[0107] Specifically, when performing defect identification on the large-area image acquired by the first image acquisition unit, if it is determined that the identified defect is located within a preset shell edge area (e.g., within 5 mm of the shell boundary), the side adjacent to the defect is automatically marked as a risk side, and the detection intensity of the risk side is increased accordingly.

[0108] For example, the number of times a risk is fully covered in the field of view of the second image acquisition unit can be increased, i.e., the number of detections can be preset (e.g., from 1 to 2 or 3), thereby increasing the probability of defect detection through multiple imaging. For example, the movement speed of the camera by the conveyor housing or displacement drive component can be reduced, i.e., the movement speed can be preset, to extend the image acquisition time window, thereby acquiring more images with higher resolution and less motion blur.

[0109] Furthermore, parameter updates only apply to the collaborative instruction segment corresponding to the risk aspect. If a type-one aspect is involved, the first collaborative instruction segment in the first instruction set is updated in real time; if a type-two aspect is involved, the second collaborative instruction segment in the second instruction set is updated in real time. This avoids redundant scanning of the entire casing, allowing limited detection resources to be precisely targeted at high-risk areas without significantly slowing down the overall cycle time, effectively balancing detection accuracy and efficiency.

[0110] In some embodiments, the apparatus further includes a marking mechanism; the method further includes controlling the marking mechanism to mark the housing surface according to the target coordinates of the identified defect on the housing surface.

[0111] Specifically, after identifying a defect, the defect recognition algorithm generates a corresponding marking control command based on the physical location obtained by mapping the image coordinate system to the machine coordinate system. This command then drives the marking mechanism to perform a marking action at a precise position on the shell surface. Marking methods may include dotting with a marker pen, applying labels, etc., with the specific form selected according to the shell material and process requirements.

[0112] In some embodiments, the marking mechanism may be located downstream of the inspection station, near the unloading position, to physically mark the shell after it is determined to have a defect, so as to facilitate subsequent sorting, rework or quality traceability.

[0113] In some embodiments, to verify the reliability of the instruction set in actual operation, a verification mechanism is introduced in the initial preset number of tests after the first application of new parameters or the switch to a new model. For example, after the side image is acquired, based on the image recognition algorithm, it is analyzed whether the image completely includes the key structures of each side (such as corners, seams, screw holes, etc.), and it is determined whether there are any acquisition anomalies such as occlusion, missed shots, or viewing angle deviations. If it is found that the key structures on the side are not completely covered, the displacement stroke and shooting angle of the fine-tuning viewing angle adjustment unit or the conveying mechanism are triggered, and the corresponding instruction set is updated. The correction effect is verified in the next round of testing. If multiple corrections still cannot meet the requirements, manual intervention can be prompted for review, and the operator can confirm whether the housing placement or parameter configuration is reasonable to avoid the risk of missed detection due to instruction deviations.

[0114] In some embodiments, the method further includes: obtaining the model parameters of the housing, and managing and updating the judgment rules and model parameters of the defect identification algorithm according to the model parameters, so as to make the defect identification algorithm match the structural features and quality standards of the current product.

[0115] It should be noted that defect detection algorithms can refer to relevant technologies, such as those based on template matching, edge contour comparison, or geometric feature extraction. Most algorithms heavily rely on stable positioning benchmarks and reference models. Changes in product shape, such as offsets in opening positions or updates to logo layouts, will render the original image templates or coordinate system mappings invalid, easily leading to false positives or false negatives. Furthermore, different product models have varying tolerances for appearance defects; for example, high-end models and entry-level products have different levels of tolerance for imperfections.

[0116] Therefore, by updating the defect judgment threshold, classification rules, and processing logic (such as whether to trigger a flag, whether to judge as unqualified, etc.) of the defect identification algorithm according to the model, the sensitivity can be dynamically adjusted during the detection process, improving the adaptability and reliability in multi-model mixed-line detection environments.

[0117] For example, based on Figures 1 to 4 The present application describes the process of a defect detection device for the surface of a laptop casing, and the method for detecting defects on the surface of a laptop casing provided in the embodiments of this application.

[0118] The product is placed at the loading position by a person or an external robot; the shell is precisely pushed to the specified position on the shell clamp 131 by an automatic straightening mechanism, so that it is always in a standard posture and within the camera's field of view during the conveying and inspection process.

[0119] The conveying mechanism 13 is controlled by an X-axis motor. Based on the housing clamp 131, it drives the housing to move forward. When it passes the detection station of the first image acquisition unit 111, the first image acquisition unit 111 starts to acquire large-area images and analyzes and processes the large-area images in real time based on the defect recognition algorithm. If a defect is detected, the coordinate value of the defect is recorded.

[0120] The X-axis motor controls the conveyor mechanism 13 to continue moving forward, transporting the housing to the first detection station of the second image acquisition unit 121. Figure 1 As shown, the second image acquisition unit 121 does not face the housing to be inspected. The acquisition range of the second image acquisition unit 121 is adjusted by the viewing angle adjustment unit 122, such as by rotating the second image acquisition unit 121 90 degrees to the left side based on the rotation drive component 1222. Figure 2 As shown, at this time, the shooting direction of the second image acquisition unit 121 is facing the left side of the housing, completing the alignment of the side with the acquisition range. At this time, multiple partial side images of the left side begin to be acquired. The left side is a type of side parallel to the conveying path. The X-axis motor controls the conveying mechanism 13 to drive the housing to move, completing the collaborative acquisition process.

[0121] Furthermore, the X-axis motor controls the conveying mechanism 13 to continue moving, transporting the housing to the second detection station of the second image acquisition unit 121. At this time, the adaptation angle adjustment unit 122 can move forward or backward. Simultaneously, the angle adjustment unit 122 adjusts the acquisition range of the second image acquisition unit 121, such as rotating the second image acquisition unit 121 90 degrees in the direction of the rear side based on the rotation drive component 1222. Figure 3 As shown, the second image acquisition unit 121 is now facing the rear side of the housing. At this time, it begins to acquire multiple partial side images of the rear side, which is a type II side perpendicular to the transport path. The Y-axis motor controls the displacement drive component 1221 to move the second image acquisition unit 121, completing the collaborative acquisition process.

[0122] Furthermore, the detection process for the left and rear sides is referenced to complete the detection of the right and front sides. Additionally, while acquiring side images, the side images are analyzed and processed in real time based on a defect recognition algorithm; if a defect is detected, its coordinates are recorded.

[0123] Based on the X-axis motor and Y-axis motor respectively controlling the transmission mechanism 13 and the displacement drive component 1221, the defect of the housing is aligned with the marking mechanism 14. The marking mechanism 14 performs physical marking on the target coordinates on the housing surface, such as the cylinder pressing down to drive the marker pen to complete the marking.

[0124] The X-axis motor controls the conveyor mechanism 13 to continue moving forward until it reaches the unloading position. Meanwhile, during this process, the housing fixture 131, which is not currently loading a housing for inspection, moves towards the loading position and completes the housing loading process for the next round of housing inspection.

[0125] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the above-described apparatus and its modules and units can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0126] The method described in this application can be used in a wide variety of general-purpose or special-purpose computing system environments or configurations to control a defect detection device. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer terminal devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices.

[0127] Please see Figure 7 , Figure 7 This is a schematic block diagram illustrating the structure of a computer device according to an embodiment of this application. The computer device may be a terminal device, a server, or a defect detection device.

[0128] For example, the above method can be implemented as a computer program, which can be used in, for example... Figure 7 It runs on the computer device shown.

[0129] like Figure 7 As shown, the computer device includes a processor, memory, and network interface connected via a system bus, wherein the memory may include non-volatile storage media and internal memory.

[0130] The non-volatile storage medium can store an operating system and a computer program. The computer program includes instructions that, when executed, cause a processor to perform the steps of the methods provided in any of the foregoing embodiments.

[0131] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0132] The internal memory provides an environment for the execution of a computer program in a non-volatile storage medium, which, when executed by a processor, causes the processor to perform the steps of the methods provided in any of the foregoing embodiments.

[0133] This network interface is used for network communication, such as sending assigned tasks.

[0134] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0135] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps: S101, Obtain the model parameters of the housing, and determine the first instruction set of the transmission mechanism and the second instruction set of the viewing angle adjustment unit based on the model parameters; S102, based on the first instruction set, control the conveying mechanism to transport the housing to the detection stations of the first detection mechanism and the second detection mechanism respectively; S103, based on the second instruction set, control the viewing angle adjustment unit so that all or part of the side of the housing to be detected is within the acquisition range of the second image acquisition unit; S105, perform real-time defect identification on the large-area image acquired by the first image acquisition unit and the side image acquired by the second image acquisition unit.

[0136] For example, the processor is used to run a computer program stored in a memory, and is also used to implement the steps of the method provided in any embodiment of this application, which will not be repeated here.

[0137] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the processor executing the program instructions to implement the steps of the method provided in any embodiment of this application.

[0138] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0139] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting defects on the surface of a laptop casing, characterized in that, The method is applied to a defect detection device, which includes: a conveying mechanism in a conveying path and a first detection mechanism and a second detection mechanism set at intervals; the conveying mechanism is used to carry and convey the housing; the first detection mechanism includes a first image acquisition unit with a fixed viewing angle; the second detection mechanism includes a second image acquisition unit and a viewing angle adjustment unit that drives the second image acquisition unit to move; The method includes: S101, Obtain the model parameters of the housing, and determine the first instruction set of the transmission mechanism and the second instruction set of the viewing angle adjustment unit based on the model parameters; S102, based on the first instruction set, control the conveying mechanism to transport the housing to the detection stations of the first detection mechanism and the second detection mechanism respectively; S103, based on the second instruction set, control the viewing angle adjustment unit so that all or part of the side of the housing to be detected is within the acquisition range of the second image acquisition unit; S105, perform defect identification in real time on the large-area image acquired by the first image acquisition unit and the side image acquired by the second image acquisition unit.

2. The method according to claim 1, characterized in that, The viewing angle adjustment unit includes a displacement driving component; the side of the housing includes a first type of side parallel to the conveying path and a second type of side perpendicular to the conveying path; The first instruction set includes a first cooperative instruction segment, used to control the transmission mechanism to move the first type of side so that the first type of side completely passes through the acquisition range of the second image acquisition unit at least once; The second instruction set includes a second cooperative instruction segment, used to control the displacement driving component to move the second type of side along the vertical direction of the conveying path, so that the acquisition range of the second image acquisition unit completely covers the second type of side at least once; The method includes: S104, while executing the first collaborative instruction segment or the second collaborative instruction segment, controlling the second image acquisition unit to acquire at least one side image.

3. The method according to claim 1 or 2, characterized in that, The first instruction set includes a housing delivery instruction segment; the housing delivery instruction segment is used to implement step S102; The viewing angle adjustment unit includes a rotation drive component; the second instruction set includes a viewing angle rotation instruction segment; S103 further includes: Based on the perspective rotation command segment, the rotation drive component is controlled to adjust the shooting direction of the second image acquisition unit to face the side to be detected.

4. The method according to claim 2, characterized in that, The method includes: When performing defect identification on the large-area image, if a defect is identified within a preset shell edge area, the side adjacent to the defect is marked as a risk side. Increase the number of detections that the risk side completely passes through or is completely covered within the acquisition range of the second image acquisition unit, and / or reduce the movement speed of the transmission mechanism or the displacement driving component when acquiring images of the risk side; Based on the adjusted number of detections or movement speed, update the collaborative instruction segment corresponding to the risk aspect described in the first instruction set or the second instruction set.

5. The method according to claim 1 or 4, characterized in that, S101 includes: S1011, based on the model parameters, retrieve the pre-configured first instruction set and second instruction set from the preset parameter database; or, S1012, based on the housing geometry corresponding to the model parameters, the field of view parameters of the second image acquisition unit, the first preset number of detections, and the first preset motion speed, generate the first instruction set and the second instruction set.

6. The method according to claim 5, characterized in that, S101 further includes: S1013, Obtain historical defect data of the model parameters, and determine risk aspects based on the historical defect data; the risk aspects include: sides with high defect incidence, and / or, local areas with high defect incidence within the sides; S1014, based on the housing geometry corresponding to the model parameters, the field of view parameters of the second image acquisition unit, the second preset number of detections, and the second preset movement speed, generate the collaborative instruction segment corresponding to the risk side; wherein, the second preset number of detections is greater than the first preset number of detections, or the first preset movement speed is greater than the second preset movement speed.

7. The method according to claim 1, characterized in that, The device further includes a marking mechanism; the method further includes: controlling the marking mechanism to mark the housing surface according to the target coordinates of the identified defect on the housing surface.

8. The method according to claim 1, characterized in that, The conveying mechanism includes at least two conveying components, and a housing clamp and a lifting mechanism configured one-to-one with each conveying component. The housing clamp is connected to the conveying component through the lifting mechanism. The conveying component is used to drive the housing clamp to reciprocate between the loading position and the unloading position, and the lifting mechanism is used to drive the housing clamp to lift. The method further includes: When one of the housing clamps moves to the lower loading position, it controls the other housing clamp to move to the upper loading position. When two adjacent housing clamps move toward each other on the conveying assembly to an intersection position, one of the lifting mechanisms is controlled to drive the corresponding housing clamp to lift.

9. A computer device, characterized in that, The device includes: Memory, used to store computer programs; A processor for executing the computer program and, in executing the computer program, implementing the defect detection method for the surface of a notebook housing as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to implement a defect detection method for the surface of a notebook casing as described in any one of claims 1 to 8.

Images