Metal foreign matter detection system, method, device and equipment and storage medium

Abstract

The invention provides a metal foreign matter detection system, method, device and equipment and a storage medium, and relates to a machine vision detection technology. The system comprises a photographing unit and a detection unit, the photographing unit comprises photographing equipment and a light source, and the photographing equipment is used for carrying out image acquisition on the surface of a to-be-detected product to obtain an image of the to-be-detected product and sending the image to the detection unit; the light source is used for providing infrared light within a preset wavelength when the photographing equipment performs image acquisition; the detection unit is used for determining whether metal foreign matters exist on the surface of the to-be-detected product according to the image. According to the invention, the detection efficiency can be improved.

Description

Technical Field

[0001] The present application relates to machine vision detection technology, and in particular to a metal foreign body detection system, method, device, equipment and storage medium. Background Art

[0002] During the battery production process, in order to ensure that the quality and performance of the battery meet the standards, it is necessary to detect metal foreign matter on the surface of the core.

[0003] Currently, known technologies rely on machine vision to detect metallic foreign matter on the surface of the electrode core. Specifically, this is typically accomplished using a camera coupled with deep learning software. The camera captures an image of the electrode core surface and performs preprocessing, edge detection, texture analysis, and feature matching to generate the detection result.

[0004] In the above process, the image of the pole core surface needs to be processed in a complex manner before the detection result can be obtained, which has the defect of low detection efficiency. Summary of the Invention

[0005] The present application provides a metal foreign body detection system, method, apparatus, device and storage medium for improving the efficiency of metal foreign body detection.

[0006] In a first aspect, the present application provides a metal foreign body detection system, the system comprising a photographing unit and a detection unit, wherein:

[0007] The photographing unit includes a photographing device and a light source. The photographing device is used to capture an image of the surface of the product to be inspected, so as to obtain an image of the product to be inspected and send it to the inspection unit. The light source is used to provide infrared light within a preset wavelength when the photographing device is performing image capture.

[0008] The detection unit is used to determine whether there is a metal foreign object on the surface of the product to be detected based on the image.

[0009] In one possible implementation, the system further includes a servo unit; and the detection unit is further configured to:

[0010] When the product to be inspected arrives at the inspection station, a control instruction is sent to the servo unit and the camera device;

[0011] The servo unit is specifically configured to: drive the camera unit to move along a preset direction of movement in response to the control instruction;

[0012] The photographing device is specifically used to capture an image of the surface of the product to be inspected in response to the control instruction.

[0013] In one possible implementation, the system further includes a servo unit; and the detection unit is further configured to:

[0014] When the product to be inspected arrives at the inspection station, a control instruction is sent to the servo unit and the camera device;

[0015] The servo unit is specifically configured to: drive the product to be inspected to move along a preset movement direction in response to the control instruction;

[0016] The photographing device is specifically used to capture an image of the surface of the product to be inspected in response to the control instruction.

[0017] In a possible implementation, the photographing device is specifically configured to: capture an image of the surface of the product to be inspected at intervals of a preset time in response to the control instruction;

[0018] The preset duration is related to the field of view of the photographing device in a first target direction and the movement speed of the product to be inspected, and the first target direction is parallel to the preset movement direction.

[0019] In one possible implementation, the detection unit is specifically configured to:

[0020] When the photographing device completes image acquisition of the product to be inspected, a plurality of images acquired during the image acquisition process are stitched together to obtain an overall image of the product to be inspected;

[0021] Determine whether there is metal foreign matter on the surface of the product to be inspected based on the overall image.

[0022] In one possible implementation, the detection unit is specifically configured to:

[0023] During the process of the photographing device capturing an image of the product to be inspected, each time an image is acquired, determining whether there is a metal foreign object on the surface of the product to be inspected based on the image;

[0024] The detection unit is further configured to: when it is determined based on any one of the images that there is a metal foreign body on the surface of the product to be detected, feed back an early warning message.

[0025] In one possible implementation, the detection unit is specifically configured to:

[0026] A trained neural network model is used to determine whether a target area exists in the image, so as to determine whether a metal foreign body exists on the surface of the product to be inspected; the target area is the area where the metal foreign body is located.

[0027] In one possible implementation, the product to be tested is a pole core to be tested; and the detection unit is specifically configured to:

[0028] Inputting the image into a trained first network model to obtain first detection information; the first network model is trained to identify damaged areas and oil-stained areas in the image;

[0029] When the first detection information indicates that the damaged area and the oily area do not exist on the surface of the pole core to be detected, the image is input into the trained second network model to obtain second detection information; the second network model is trained with the identification of the target area as the training goal.

[0030] In one possible implementation, when the detection unit inputs the image into the trained second network model to obtain the second detection information, it is specifically configured to:

[0031] Inputting the image into a trained third network model to obtain third detection information; the third network model is trained with the identification of a target foreign object as a training goal, and the area of ​​the target foreign object is larger than a preset area;

[0032] When the third detection information indicates that the target foreign matter does not exist on the surface of the pole core to be detected, it is determined to input the image into the trained second network model to obtain the second detection information.

[0033] In one possible implementation, the detection unit is specifically configured to:

[0034] Receive position information transmitted by a carrier device; the carrier device is used to move the product to be inspected to the inspection station, and the position information is used to indicate the distance between the product at the inspection station and the inspection station;

[0035] When the position information indicates that the distance between the product to be inspected and the inspection station is zero, it is determined that the product to be inspected has arrived at the inspection station.

[0036] In one possible implementation, the photographing device includes at least one camera, which is arranged along a second target direction, and the sum of the fields of view of the at least one camera in the second target direction is not less than the length of the product to be inspected in the second target direction, and the second target direction is perpendicular to the preset movement direction.

[0037] In a second aspect, the present application provides a method for detecting metal foreign matter, the method comprising:

[0038] Acquire an image of the product to be inspected; the image is obtained by capturing the image of the product to be inspected by a camera under infrared light conditions within a preset wavelength;

[0039] Determine whether there is metal foreign matter on the surface of the product to be inspected based on the image.

[0040] In a third aspect, the present application provides a metal foreign body detection device, the device comprising:

[0041] An acquisition module is used to acquire an image of the product to be inspected; the image is obtained by capturing the image of the product to be inspected by a camera under infrared light conditions within a preset wavelength;

[0042] A feedback module is used to determine whether there is a metal foreign object on the surface of the product to be inspected based on the image.

[0043] In a fourth aspect, the present application provides an electronic device, comprising a processor, and a memory communicatively connected to the processor;

[0044] The memory stores computer-executable instructions;

[0045] The processor executes the computer-executable instructions stored in the memory to implement the method according to the second aspect.

[0046] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the second aspect.

[0047] In a sixth aspect, the present application provides a computer program product, comprising a computer program, which implements the method described in the second aspect when executed by a processor.

[0048] The present application provides a metal foreign body detection system, method, apparatus, device and storage medium, wherein the system includes a photographing unit and a detection unit. Specifically, the photographing unit includes a photographing device for acquiring an image of the product to be inspected and sending it to the detection unit, and a light source for providing infrared light within a preset wavelength when the photographing device performs image acquisition. The detection unit is used to determine whether there is a metal foreign body on the surface to be inspected based on the received image. Metal foreign bodies are clearly distinguishable from non-metallic substances under infrared light, and the detection unit does not need to perform a complex image processing process. Therefore, the metal foreign body detection system of the present application can more quickly and accurately detect whether there is a metal foreign body on the surface of the product to be inspected. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0050] Figure 1 This is an application scenario diagram of a metal foreign body detection system provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the structure of a metal foreign body detection system provided in an embodiment of the present application Figure 1 ;

[0052] Figure 3 A schematic diagram of the installation of a photographing unit provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of the structure of a metal foreign body detection system provided in an embodiment of the present application Figure 2 ;

[0054] Figure 5 A schematic diagram of a detection process of a detection unit provided in an embodiment of the present application;

[0055] Figure 6 A schematic diagram of a process for detecting metal foreign matter provided in an embodiment of the present application;

[0056] Figure 7 A schematic structural diagram of a metal foreign body detection device provided in an embodiment of the present application;

[0057] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0058] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0059] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0060] In some production scenarios, finished products need to be inspected to determine whether there are any metallic foreign objects on the surface of the product to ensure its performance and safety. For example, during battery production, metallic foreign objects on the surface of the core need to be inspected to ensure battery performance and safety. Therefore, it is very important to develop effective and feasible methods for detecting metallic foreign objects.

[0061] Currently, conventional techniques use a camera to capture an image of the surface of the product to be inspected. This image is then subjected to preprocessing, edge detection, texture analysis, feature matching, and other processing to obtain a test result. This process requires complex processing of the product surface image before obtaining a test result, resulting in low detection efficiency and hindering production efficiency.

[0062] In addition, the known technologies mainly use traditional 2D area array cameras or 3D line scan cameras in combination with deep learning software for detection. Among them, the solution using 2D area array cameras cannot effectively distinguish between metal objects and non-metal objects, resulting in a high detection error rate, which in turn leads to increased waste discharge in the production process and affects production efficiency. In the solution using 3D line scan cameras, the detection results are obtained by detecting the height map and brightness map obtained by the 3D line scan camera. However, there is no obvious difference in height information between metal and non-metal materials. Therefore, this solution cannot accurately distinguish between metal and non-metal materials, which is not conducive to ensuring production efficiency.

[0063] To address the above-mentioned issues, the present application provides a metal foreign body detection system, method, apparatus, device, and storage medium. Specifically, the metal foreign body detection system of the present application provides infrared light within a preset wavelength during the image acquisition process to obtain an image of the product to be inspected, and based on the image, determines whether a metal foreign body is present on the surface of the product to be inspected.

[0064] In the above process, since there is a clear difference in the imaging of metal objects and non-metal objects under infrared light within a preset wavelength, it is possible to quickly and accurately detect whether there are metal foreign objects on the surface of the product to be inspected without complicated processing, thereby ensuring production efficiency.

[0065] It can be understood that the system of the present application is applicable to any scenario where there is a need to detect whether there are metal foreign objects, such as the aforementioned battery production process, and some food production processes, which are not limited in this embodiment.

[0066] For example, Figure 1 This is an application scenario diagram of a metal foreign body detection system provided in an embodiment of the present application. Figure 1 As shown, the metal foreign body detection system of the present application is set at the detection station, and the pole core to be detected enters the detection station in sequence according to the preset direction and is detected by the metal foreign body detection system to obtain the detection results.

[0067] It is understood that the preset direction can be Figure 1 The left-to-right direction shown in , in actual application, can also be Figure 1In the direction from top to bottom, in this embodiment, the incoming direction of the pole core to be inspected is not limited, as long as each pole core to be inspected can be moved to the inspection station.

[0068] Based on the above settings, during the battery production process, the metal foreign body detection system can inspect each pole core passing through the inspection station. Through the metal foreign body detection system of this application, the detection results can be determined more quickly and accurately, which is beneficial to ensuring the production efficiency of the battery.

[0069] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflicts between the embodiments, the following embodiments and the features of the embodiments may be combined with each other. It is worth noting that the following content is described in detail using any electronic device as the execution subject.

[0070] The present invention provides a metal foreign body detection system. Figure 2 A schematic diagram of the structure of a metal foreign body detection system provided in an embodiment of the present application Figure 1 ,like Figure 2 As shown, the system provided by the embodiment of the present application includes a photographing unit and a detection unit, wherein the photographing unit specifically includes a photographing device and a light source.

[0071] It is understood that, in this application, the photographing device is an infrared camera capable of capturing infrared radiation invisible to the human eye. More specifically, in this embodiment, the photographing device is an infrared scanning camera, which is used to capture images of the surface of the product to be inspected, thereby obtaining images of the product to be inspected and transmitting them to the inspection unit. The light source is an infrared light source, which is used to provide infrared light within a preset wavelength when the photographing device is performing image capture.

[0072] It is understandable that when capturing images, the camera device needs to obtain a complete image of the surface of the product to be inspected in order to perform a comprehensive inspection of the product, ensure inspection accuracy, and thus improve production efficiency. Therefore, in this embodiment, the light source parameters and camera parameters of the camera unit are not limited, as long as they can achieve a comprehensive inspection of the product to be inspected.

[0073] Specifically, light source parameters include the light source installation location, and camera parameters include installation location, number of cameras, field of view, scanning speed, resolution, camera line frequency, etc. The installation location includes information such as installation angle and installation height.

[0074] It should be understood that the infrared wavelength range is 700-14000nm, of which 1000-3000nm is short-wave infrared, 3000-5000nm is medium-wave infrared, and 7500-14000nm is long-wave infrared. In this embodiment, because the reflectivity of metals and non-metals under short-wave infrared light in the range of 900-1700nm is significantly different, a short-wave infrared wavelength range of 900-1700nm is configured to achieve an easily distinguishable imaging effect.

[0075] Accordingly, when the detection unit receives the image sent by the photographing device, it is used to determine whether there is a metal foreign object on the surface of the product to be detected based on the image.

[0076] It is understood that the detection unit can be any electronic device with computing power, and this embodiment is not limited to this. Since the imaging effects of metal and non-metal materials under the light source conditions of this embodiment are significantly different, the detection unit can determine whether there is a metal foreign object on the surface of the product to be inspected based on the image.

[0077] Specifically, in this embodiment, the detection unit is specifically used to: use a trained neural network model to determine whether there is a target area in the image to determine whether there is a metal foreign matter on the surface of the product to be inspected; the target area is the area where the metal foreign matter is located.

[0078] The neural network model is trained to output a true detection result corresponding to a sample image. Specifically, the true detection result indicates whether the target area exists in the sample image. Upon receiving an image of the product to be inspected, the inspection unit inputs the image into the trained neural network model and obtains a detection result indicating whether the target area exists in the image.

[0079] It can be understood that under the light source conditions within the preset wavelength range, metal substances appear bright white in the image, and non-metallic substances appear dark black in the image. Therefore, the target area is specifically the area that appears bright white, and the neural network model specifically feeds back the detection results based on whether there is a bright white area in the image.

[0080] In this embodiment, the detection unit, based on a neural network model, determines whether a metal foreign object exists on the surface of a product to be inspected. The result can be obtained by simply inputting the captured image into the trained neural network model, without involving complex real-time calculations. This improves detection efficiency, thereby ensuring the production efficiency of the product to be inspected. Furthermore, it reduces the performance requirements of the detection unit, thereby saving costs.

[0081] It is understood that the detection unit may also compare each pixel in the image with the bright white pixel one by one and determine the detection result based on the comparison results. Specifically, when at least one pixel matches the bright white pixel, the detection result is determined to indicate the presence of a metallic foreign object on the surface of the product being inspected. Furthermore, contextual information may be incorporated into the comparison process to improve detection accuracy.

[0082] In practical applications, the detection unit may also use other means to determine the detection result based on the image, which is not limited in this embodiment.

[0083] When a product needs to be inspected for metal foreign matter, the system of this embodiment uses a camera to capture an image of the product's surface under a light source providing infrared light within a preset wavelength, and transmits the image to a detection unit. Based on this image, the detection unit can quickly and accurately determine whether a metal foreign matter is present on the product's surface without requiring complex image processing, thereby improving production efficiency of the product.

[0084] As an example, when the product to be inspected is a pole core with a width of 110 mm, Table 1 is a parameter table of a photographing unit provided in an embodiment of the present application.

[0085]

[0086] As shown in Table 1, in this example, a 2K infrared line scan camera is used. The core chip material of this infrared camera is indium gallium arsenide (InGaAs), which is very sensitive to shortwave infrared light. Only infrared light can be imaged on the chip. The highest resolution of infrared line scans available on the market is 2048 pixels, so a 2K line scan camera is selected. To meet the 100µm foreign object detection standard, the camera's field of view is set to 61mm, with a single pixel accuracy of 0.029mm / pixel. With a maximum line frequency of 25kHz, the maximum scanning speed of this line scan camera is 740mm / s.

[0087] More specifically, as shown in Table 1, the camera installation height is 235 ± 10 mm. This example specifically uses two infrared light sources to illuminate the product to be inspected from the left and right sides. Each light source is installed at a height of 10-20 mm and an angle of 45°.

[0088] Furthermore, in this example, an infrared lens is selected as the lens, which only allows infrared light to pass through the lens.

[0089] On this basis, in order to conduct a comprehensive inspection of the product to be inspected, the number of cameras in this example is two. The two cameras are installed side by side, and the center distance between the two cameras is 61mm, so that the camera field of view can cover the entire surface of the product to be inspected.

[0090] Figure 3 This is a schematic diagram of the installation of a camera unit provided in an embodiment of the present application. Specifically, Figure 3 The left half is used to show the positional relationship between the camera and the light source. In the left half, the horizontal line at the bottom is used to represent the product to be inspected, the two symmetrical polygons in the middle are used to represent the two light sources, and the figure above the light source is used to represent the camera. It can be understood that the camera installation height is specifically used to indicate the distance between the camera body and the product to be inspected, rather than the distance between the camera lens and the product to be inspected. Figure 3 The right half is used to show the positional relationship between the two cameras. In the right half, the horizontal line at the bottom is used to represent the product to be inspected, and the two images at the top are used to represent the cameras.

[0091] Based on the aforementioned embodiments, the present application provides an embodiment for enabling a photographing device to obtain a complete image of the surface of a product to be inspected during image acquisition, so as to perform a comprehensive inspection of the product to be inspected.

[0092] Specifically, Figure 4 A schematic diagram of the structure of a metal foreign body detection system provided in an embodiment of the present application Figure 2 , understandably, Figure 4 The two marks in the figure are used to indicate the camera installation height and the light source installation height. Figure 4 For the specific installation angle, please refer to Figure 3 .like Figure 4 As shown, in one possible implementation, the metal foreign body detection system further includes a servo unit. On this basis, the detection unit is further configured to send control instructions to the servo unit and the camera when the product to be detected arrives at the detection station.

[0093] Specifically, when determining whether the product to be inspected has arrived at the inspection station, the inspection unit is specifically used to:

[0094] Receive location information transmitted by a carrier device; the carrier device is used to move the product to be inspected to the inspection station, and the location information is used to indicate the distance between the product to be inspected and the inspection station;

[0095] When the position information indicates that the distance between the product to be inspected and the inspection station is zero, it is determined that the product to be inspected has arrived at the inspection station.

[0096] It can be understood that in this embodiment, the product to be inspected is moved to the inspection station by a carrier device, and the carrier device transmits its corresponding position information to the inspection unit in real time during the movement. When the inspection unit monitors that the position information indicates that the distance between the product to be inspected and the inspection station is zero, it determines that the product to be inspected has arrived at the inspection station.

[0097] Through this arrangement, the detection unit can timely and accurately monitor whether the product to be detected will arrive at the detection station, thereby facilitating timely and accurate detection results for the product to be detected.

[0098] It is understood that in actual applications, the product to be inspected may be conveyed to the inspection station via a conveyor belt. Accordingly, a proximity switch is provided at each position on the conveyor belt where the product to be inspected is placed. Based on this, the inspection unit determines whether the product to be inspected has arrived at the inspection station by specifically detecting the proximity switch. In this embodiment, the method for determining whether the product to be inspected has arrived at the inspection station is not limited.

[0099] On this basis, as a design, such as Figure 4 As shown in the first case, the servo unit is specifically used to: respond to the control instruction to drive the camera unit to move along the preset movement direction; the camera device is specifically used to: respond to the control instruction to capture the image of the surface of the product to be inspected.

[0100] As another design, Figure 4 As shown in the second case, the servo unit is specifically used to: respond to the control instruction to drive the product to be inspected to move along the preset movement direction; the camera device is specifically used to: respond to the control instruction to capture the image of the surface of the product to be inspected.

[0101] In the first design described above, the camera unit, including the camera and light source, is mounted on a servo unit. The servo unit responds to control commands to drive the camera unit in a preset direction. In the second design described above, the product to be inspected is placed on a tray at the inspection station. The tray is mounted on the servo unit. The servo unit responds to control commands to drive the tray, and thus the product to be inspected, in a preset direction.

[0102] Among them, the servo unit includes components such as a motor and a screw. Specifically, the input end of the motor is connected to the detection unit for receiving control instructions, and the output end of the motor is connected to other components such as a screw for outputting control instructions to other components such as the screw, and executing the control instructions to drive the camera unit or the tray where the product to be detected is located to move along the preset direction of movement.

[0103] It is understood that the control instructions are used to indicate information such as the start position, end position, and speed of movement. After the product to be inspected is determined, the length of the product to be inspected in the preset direction of movement is a known quantity. This quantity can be input by the user into the inspection unit or obtained by the inspection unit from a preset database for storing product information, which is not limited in this embodiment. Based on this, the start position and end position of the movement can be obtained. The speed of movement can be determined by referring to the camera parameters of the camera device, which is not limited in this embodiment.

[0104] In this embodiment, the preset motion direction is any longitudinal direction of the product to be inspected. For example, for the aforementioned core, which has a longer length (length) and a shorter length (width) in a horizontal plane, the preset motion direction can specifically be the longitudinal direction. Accordingly, the camera's field of view should be no less than its width to capture a complete image of the product to be inspected. It should be understood that this embodiment does not specify the shape of the product to be inspected; as long as the camera unit is configured to capture a complete image of the product to be inspected, it is sufficient.

[0105] In the metal foreign body detection system provided in this embodiment, the servo unit and the method for enabling the camera to capture a complete image of the product to be inspected are not limited. The specific settings can be made according to the actual production environment, thereby improving the applicability of the metal foreign body detection system of this application.

[0106] Correspondingly, when the servo unit drives the photographing unit or the product to be inspected to move along the preset movement direction, the photographing device responds to the control instruction to capture images of the product to be inspected.

[0107] More specifically, the camera is configured to capture images of the surface of the product to be inspected at predetermined intervals in response to a control command. The predetermined interval is related to the camera's field of view in a first target direction, which is parallel to the predetermined direction of motion, and the speed of the product to be inspected.

[0108] It is understandable that the movement speed of the product to be inspected is specifically input by the user or freely set, and is not limited in this embodiment. It is sufficient to update the preset time accordingly to achieve complete image acquisition of the product to be inspected.

[0109] In this embodiment, to avoid repeated or missed acquisitions of large areas, the preset duration is determined based on the camera's field of view in the first target direction. Specifically, the preset duration can be set to (the camera's field of view in the first target direction - the preset value) / the motion speed. The preset value is used to avoid missed acquisitions, and to avoid repeated acquisitions of large areas, it can be appropriately small. This embodiment does not limit its specific value. It is understood that to avoid areas of repeated acquisition, the preset value can be set to zero.

[0110] Through the above settings, during the image acquisition process, the photographing device can obtain an accurate preset duration based on its own parameters and the movement speed of the product to be inspected or the photographing device in the corresponding scene. Image acquisition based on the preset duration can obtain a complete image of the product to be inspected.

[0111] Furthermore, as a possible implementation method, the photographing device includes at least one camera, at least one camera is arranged along the second target direction, and the sum of the fields of view of at least one camera in the second target direction is not less than the length of the product to be inspected in the second target direction, and the second target direction is perpendicular to the preset movement direction.

[0112] In this embodiment, at least one camera is set up for each product to be inspected based on its corresponding product information to capture its corresponding image. Specifically, the number of cameras is determined based on the product's length in a second target direction and the camera's field of view in that second target direction. Furthermore, a corresponding number of cameras are arranged along the second target direction, such that the sum of the fields of view of the corresponding number of cameras in the second target direction is no less than the length of the product to be inspected in that second target direction.

[0113] Based on the above configuration, on the one hand, when the servo unit drives the product to be inspected or the camera unit to move in a preset direction, the camera device can obtain a complete image of the product to be inspected. On the other hand, it can enable the metal foreign body detection system of the present application to detect products of any size.

[0114] Based on the aforementioned embodiments, the present application provides an embodiment for determining whether there is a metal foreign object on the surface of a product to be inspected based on an image.

[0115] Specifically, as a design, the detection unit is specifically used to: when the photographing device completes image acquisition of the product to be inspected, stitch the multiple images obtained during the image acquisition process to obtain an overall image of the product to be inspected; and determine whether there are metal foreign objects on the surface of the product to be inspected based on the overall image.

[0116] As another design, the detection unit is specifically used to: in the process of the photographing device capturing images of the product to be inspected, whenever an image is obtained, determine whether there is metal foreign matter on the surface of the product to be inspected based on the image; the detection unit is also used to: when it is determined that there is metal foreign matter on the surface of the product to be inspected based on any image, feedback warning information.

[0117] It is understood that, based on the aforementioned embodiment, the camera device captures multiple images and sends multiple images to the detection unit during the image acquisition process. For example, for the aforementioned embodiment, upon completion of image acquisition, the two cameras each send 11 images to the detection unit, for a total of 22 images.

[0118] In this embodiment, after the camera completes the image acquisition process, the detection unit can stitch the multiple images captured to obtain a single integrated image. This integrated image is then fed into the trained neural network model to obtain the detection result. This setup allows the detection unit to perform only one detection using the neural network model, effectively conserving computing resources.

[0119] The detection unit can also input each image captured by the camera into a trained neural network model for detection during image acquisition. Furthermore, multiple images can be detected in parallel, thereby improving detection efficiency. Furthermore, the detection unit can provide feedback warning information when any image indicates the presence of a metal foreign object on the surface of the product being inspected, allowing for the timely termination of the detection process, and even the image acquisition process. This not only helps save computing resources and improves detection efficiency, but also allows for the timely termination of the image acquisition process if a metal foreign object is present on the surface of the product being inspected but image acquisition is not complete, thereby saving costs.

[0120] When the metal foreign body detection system of this application is used to detect metal foreign bodies on the battery core, other foreign bodies may exist on the surface of the battery core, which may also affect the performance and safety of the battery. Therefore, this application provides an embodiment for scenarios where other foreign bodies need to be detected at the same time.

[0121] For example, for the aforementioned pole core to be detected, in one possible implementation, the detection unit is specifically configured to:

[0122] Inputting the image into the trained first network model to obtain first detection information; during training, the first network model takes identifying damaged areas and oil-stained areas in the image as a training goal;

[0123] When the first detection information indicates that there are no damaged areas and oily areas on the surface of the pole core to be detected, the image is input into the trained second network model to obtain second detection information; the second network model is trained with the identification of the target area as the training goal.

[0124] Specifically, the first network model and the second network model are both segmentation models. The detection unit first inputs the image into the segmentation model for identifying damaged areas and oily areas to determine whether there are damaged areas or oily areas on the surface of the pole core to be detected.

[0125] Furthermore, when there is no damaged area or oily area on the pole core to be inspected, the inspection unit inputs the image into a segmentation model for identifying the target area to determine whether there is a metal foreign body on the surface of the product to be inspected.

[0126] It is understandable that when the first detection information indicates that there are damaged areas and / or oily areas on the surface of the pole core to be detected, the detection unit feeds back the first detection information and stops the detection.

[0127] It is understandable that, in practical applications, the first network model and the second network model may also be any other neural network model, which is not limited in this embodiment.

[0128] During the inspection process, any core to be inspected, regardless of whether it has damaged areas, oily areas, or metal foreign matter on its surface, will be considered a substandard product. Furthermore, the process of inspecting the core to be inspected for damaged areas and / or oily areas is more efficient and reliable. Therefore, in this embodiment, damaged areas and oily areas are first inspected, and if the aforementioned areas are not present, subsequent inspection for the presence of metal foreign matter is performed. This not only meets the production standards for the core, but also allows for timely termination of inspection when damaged areas and / or oily areas are found, effectively saving computing power, thereby improving inspection and ensuring the production efficiency of the core.

[0129] Further, Figure 5 A schematic diagram of a detection process of a detection unit provided in an embodiment of the present application, such as Figure 5 As shown in FIG. 1 , as a possible implementation method, when the detection unit inputs the image into the trained second network model to obtain the second detection information, it is specifically configured to:

[0130] Inputting the image into a trained third network model to obtain third detection information; during training, the third network model is trained to identify a target foreign object, where the area of ​​the target foreign object is larger than a preset area;

[0131] When the third detection information indicates that there is no target foreign matter on the surface of the pole core to be detected, the image is input into the trained second network model to obtain second detection information.

[0132] Specifically, the third network model can also be a segmentation model. When the first detection information indicates the absence of damaged areas and oil-stained areas, the detection unit first inputs the image into the segmentation model for identifying target foreign objects to obtain third detection information. When the third detection information indicates the absence of target foreign objects on the surface of the electrode core to be inspected, the image is further input into the second network model to determine whether there is a metal foreign object on the surface of the electrode core to be inspected.

[0133] Among them, in this embodiment, Figure 5As shown, the target foreign object is a foreign object at least 1mm in size. If no target foreign object is present, the system further determines whether there is a metal foreign object larger than 0.1mm. During any judgment process, if the corresponding detection information indicates the presence of a corresponding area, an NG result is output, indicating that the electrode core to be tested is unqualified. If no metal foreign object is finally detected, an OK result is output, indicating that the electrode core to be tested is qualified.

[0134] It can be understood that any pole core to be tested that has any of the following: damaged areas, oily areas, target foreign objects, and metal foreign objects is an unqualified product. In this embodiment, when there are no damaged areas and oily areas, further detection is first performed to determine whether there are target foreign objects. When there are no target foreign objects, subsequent detection is performed to meet the pole core production standards and to ensure the production efficiency of the pole core.

[0135] The present application also provides a metal foreign body detection method, which is specifically used with the detection unit in the aforementioned metal foreign body detection system. It is understandable that the detection unit is specifically any electronic device with computing power. Figure 6 A schematic diagram of a metal foreign body detection method provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the method of this embodiment includes:

[0136] S601, obtaining an image of the product to be inspected.

[0137] The image is obtained by capturing the image of the product to be inspected by a photographic device under infrared light conditions within a preset wavelength range.

[0138] It is understood that when the product to be inspected arrives at the inspection station, the inspection unit sends a control instruction to the camera device, causing the camera device to capture an image of the product to be inspected. In this embodiment, after the inspection unit sends the control instruction to the camera device, it begins to capture an image of the product to be inspected. The specific limitations of the method for determining whether the product to be inspected has arrived at the inspection station and the method for image capture by the camera device can be found in the aforementioned embodiments and will not be repeated here.

[0139] S602: Determine whether there is any metal foreign matter on the surface of the product to be inspected based on the image.

[0140] Among them, the detection unit can determine whether there is metal obligation on the surface of the product to be detected through a trained neural network model, or it can determine it through other methods mentioned in the above embodiments. This embodiment does not limit this and will not be repeated.

[0141] In the method provided in this embodiment, the detection unit determines whether there is metal foreign matter on the surface of the product to be inspected based on the image of the product to be inspected under infrared light conditions within a preset wavelength range. The detection result can be accurately obtained without performing complex image processing on the image, which effectively ensures the efficiency of metal foreign matter detection and is conducive to ensuring the production efficiency of the product to be inspected.

[0142] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0143] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0144] The above embodiments introduce a metal foreign body detection method from the perspective of method flow. The following embodiments introduce a metal foreign body detection device from the perspective of a virtual module or a virtual unit. Please refer to the following embodiments for details.

[0145] Figure 7 A schematic diagram of the structure of a metal foreign body detection device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, in this embodiment, the metal foreign body detection device may include:

[0146] The acquisition module 71 is used to acquire an image of the product to be inspected; the image is obtained by capturing the image of the product to be inspected by a camera under infrared light conditions within a preset wavelength;

[0147] The feedback module 72 is used to determine whether there is any metal foreign matter on the surface of the product to be inspected based on the image.

[0148] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0149] An electronic device is provided in an embodiment of the present application. Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, Figure 8 The electronic device shown includes a processor 81 and a memory 82. The processor 81 and the memory 82 are connected, for example, via a bus 83. Optionally, the electronic device may further include a transceiver 84. It should be noted that in actual applications, the number of transceivers 84 is not limited to one, and the structure of the electronic device does not constitute a limitation on the embodiments of the present application.

[0150] The processor 81 may be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 81 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0151] Bus 83 may include a path for transmitting information between the above components. Bus 83 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. Bus 83 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0152] The memory 82 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0153] The memory 82 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 81. The processor 81 is used to execute the application code stored in the memory 82 to implement the content shown in the above method embodiment.

[0154] The present application also provides a computer-readable storage medium, which may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes. Specifically, the computer-readable storage medium stores program instructions, and the program instructions are used to implement the service message processing methods in the above-mentioned embodiments.

[0155] A computer program product is also provided in an embodiment of the present application, including a computer program. When the computer program is executed by a processor, the technical solution of the above-mentioned method embodiment is implemented. Its implementation principle and technical effect are similar and will not be repeated here.

[0156] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0157] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0158] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A metal foreign body detection system, characterized in that: The system comprises a photographing unit and a detection unit, wherein: The photographing unit includes a photographing device and a light source. The photographing device is used to capture images of the surface of the product to be inspected, so as to obtain images of the product to be inspected and send them to the inspection unit. The light source is used to provide infrared light within a preset wavelength when the photographing device is performing image acquisition. The detection unit is used to determine whether there is a metal foreign body on the surface of the product to be detected according to the image.

2. The system according to claim 1, characterized in that The system further comprises a servo unit; the detection unit is further used for: When the product to be inspected arrives at the inspection station, a control instruction is sent to the servo unit and the camera device; The servo unit is specifically used to: drive the camera unit to move along a preset movement direction in response to the control instruction; The photographing device is specifically used for: collecting images of the surface of the product to be inspected in response to the control instruction.

3. The system according to claim 1, characterized in that The system further comprises a servo unit; the detection unit is further used for: When the product to be inspected arrives at the inspection station, a control instruction is sent to the servo unit and the camera device; The servo unit is specifically used to: drive the product to be detected to move along a preset movement direction in response to the control instruction; The photographing device is specifically used for: collecting images of the surface of the product to be inspected in response to the control instruction.

4. The system according to claim 2 or 3, characterized in that: The photographing device is specifically used to: in response to the control instruction, collect images of the surface of the product to be inspected at intervals of a preset time; The preset duration is related to the field of view of the photographing device in the first target direction and the movement speed of the product to be inspected, and the first target direction is parallel to the preset movement direction.

5. The system according to claim 2 or 3, characterized in that: The detection unit is specifically used for: When the camera device completes image acquisition of the product to be inspected, multiple images acquired during the image acquisition process are stitched together to obtain an overall image of the product to be inspected; Determine whether there is metal foreign matter on the surface of the product to be inspected based on the overall image.

6. The system according to claim 2 or 3, characterized in that: The detection unit is specifically used for: In the process of the photographing device collecting images of the product to be inspected, whenever an image is obtained, determining whether there is a metal foreign body on the surface of the product to be inspected according to the image; The detection unit is also used to feed back warning information when it is determined according to any one of the images that there is a metal foreign body on the surface of the product to be detected.

7. The system according to any one of claims 1 to 3, characterized in that: The detection unit is specifically used for: A trained neural network model is used to determine whether there is a target area in the image, so as to determine whether there is a metal foreign body on the surface of the product to be inspected; the target area is the area where the metal foreign body is located.

8. The system according to any one of claims 1 to 3, characterized in that: The product to be tested is a pole core to be tested; the detection unit is specifically used for: Inputting the image into a trained first network model to obtain first detection information; the first network model is trained to identify damaged areas and oily areas in the image as a training target; When the first detection information indicates that the damaged area and the oily area do not exist on the surface of the pole core to be detected, the image is input into the trained second network model to obtain second detection information; The second network model is trained with identifying the target area as a training goal.

9. The system according to claim 8, characterized in that When the detection unit inputs the image into the trained second network model to obtain the second detection information, it is specifically used to: Inputting the image into a trained third network model to obtain third detection information; the third network model is trained with identification of target foreign matter as a training goal, and the area of ​​the target foreign matter is greater than a preset area; When the third detection information indicates that the target foreign matter does not exist on the surface of the pole core to be detected, the image is input into the trained second network model to obtain the second detection information.

10. The system according to claim 2 or 3, characterized in that: The detection unit is specifically used for: Receiving position information transmitted by a carrier device; the carrier device is used to move the product to be inspected to the inspection station, and the position information is used to indicate the distance between the product to be inspected and the inspection station; When the position information indicates that the distance between the product to be inspected and the inspection station is zero, it is determined that the product to be inspected has arrived at the inspection station.

11. The system according to claim 2 or 3, characterized in that: The photographing device includes at least one camera, which is arranged along a second target direction, and the sum of the fields of view of the at least one camera in the second target direction is not less than the length of the product to be inspected in the second target direction, and the second target direction is perpendicular to the preset movement direction.

12. A method for detecting metallic foreign matter, characterized in that: The method comprises: Acquire an image of the product to be inspected; the image is obtained by capturing the image of the product to be inspected by a camera under infrared light conditions within a preset wavelength; Determine whether there is metal foreign matter on the surface of the product to be inspected according to the image.

13. A metal foreign body detection device, characterized in that: The device comprises: An acquisition module is used to acquire an image of the product to be inspected; the image is obtained by capturing the image of the product to be inspected by a camera under infrared illumination conditions within a preset wavelength; The feedback module is used to determine whether there is a metal foreign body on the surface of the product to be inspected according to the image.

14. An electronic device, characterized in that: The electronic device comprises a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to claim 12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to claim 12 when executed by a processor.

16. A computer program product, characterized in that The method comprises a computer program which, when executed by a processor, implements the method as claimed in claim 12.

Images