A method and system for online quality inspection in aluminum rod production

Abstract

This application relates to the field of quality inspection technology, and in particular to an online quality inspection method and system for aluminum rod production. The method includes: acquiring a set of polarized images of the side of an electrical aluminum rod of the model to be inspected using a polarization camera, and acquiring a set of structured light images of the side of the electrical aluminum rod using a structured light camera; matching and fusing the polarization image set and the structured light image set to obtain a three-dimensional surface image of the target aluminum rod region; determining the initial quality inspection result of the target aluminum rod region based on the height and color information of the position points in the target aluminum rod region within the three-dimensional surface image, thereby determining the target quality inspection result of the electrical aluminum rod output by the production equipment during a target time period. Through the above technical solution, quality inspection of aluminum rods during the production process can be achieved.

Description

Technical Field

[0001] This application relates to the field of quality inspection technology, and in particular to an online inspection method and system for aluminum rod production quality. Background Technology

[0002] Electrical aluminum rods are mainly used in the manufacture of wires and cables. Through further processing such as wire drawing, electrical aluminum rods can be made into aluminum conductors or cables; for example, electrical aluminum rods can be used to make steel-cored aluminum stranded wires and all-aluminum stranded wires.

[0003] Because aluminum has a lower density and is less expensive than copper, aluminum conductors are more advantageous for long-distance or large-span power transmission; electrical aluminum poles can also be used to make electrical wiring inside buildings, such as power cables and control cables.

[0004] The main production process of electrical aluminum rods can include: refining molten aluminum is kept at a constant temperature in a holding furnace and then injected into the crystallizer of a continuous casting machine. The molten aluminum is rapidly cooled and solidified in the crystallizer to form a continuous aluminum billet rod with a certain cross-sectional shape; the continuous aluminum billet rod is processed into an electrical aluminum rod of the required diameter by multiple passes of rolling mills and then output; the output electrical aluminum rod is wound and packaged to obtain the required electrical aluminum rod product.

[0005] The output electrical aluminum rods may have defects such as uneven diameter, surface cracks, and scratches due to equipment failures such as continuous casting machines or rolling mills. These defects will affect the structural strength and conductivity of the electrical aluminum rods, as well as the subsequent processing. For example, drawing defective electrical aluminum rods will increase the wire breakage rate and affect the processing efficiency. Therefore, it is necessary to inspect the quality of the aluminum rods during the production process. Summary of the Invention

[0006] To inspect the quality of aluminum rods during the production process, this application provides an online inspection method and system for aluminum rod production quality.

[0007] According to a first aspect of the embodiments of this application, an online quality inspection method for aluminum rod production is provided, comprising: acquiring a set of polarized images of the side of an electrical aluminum rod of a certain model to be inspected using a polarization camera, and acquiring a set of structured light images of the side of the electrical aluminum rod using a structured light camera; matching the set of polarized images and the set of structured light images to obtain a polarized image and a structured light image matching a target aluminum rod region for the electrical aluminum rod, and performing image fusion on the matching polarized image and the structured light image to obtain a three-dimensional surface image; determining an initial quality inspection result for the target aluminum rod region based on the height information and color information of the position points in the target aluminum rod region in the three-dimensional surface image; and determining a target quality inspection result for the electrical aluminum rod output by the production equipment in a target time period based on multiple initial quality inspection results for multiple consecutive aluminum rod regions.

[0008] This enables online quality inspection of the electrical aluminum rods output from the production equipment, thereby ensuring the quality of the electrical aluminum rods.

[0009] Optionally, the initial quality inspection result is determined in the following way: based on the height information of the position points in the target aluminum rod region in the three-dimensional surface image, the diameter defect information and height defect information of the target aluminum rod region are determined; the height defect information is used to characterize the degree of difference in height of the position points in the same row in the target aluminum rod region; the diameter defect information is used to characterize the degree of difference in cross-sectional diameter of different columns in the target aluminum rod region; based on the color information of the position points in the target aluminum rod region in the three-dimensional surface image, the color difference information of the target aluminum rod region is determined, and based on the color difference information, the diameter defect information, and the height defect information, the initial quality inspection result of the target aluminum rod region is determined.

[0010] Optionally, the initial quality inspection result for the target aluminum rod area is determined based on the color difference information, the diameter defect information, and the height defect information, including: determining the maximum defect depth and the continuous defect length of the target aluminum rod area based on the height defect information of different rows in the target aluminum rod area; normalizing the color difference information, diameter defect information, maximum defect depth, and continuous defect length, and determining the defect severity value based on the sum of the normalized color difference information, diameter defect information, maximum defect depth, and continuous defect length; and determining the initial quality inspection result for the target aluminum rod area based on the relationship between the defect severity value and a preset defect threshold.

[0011] Optionally, the polarization image set is acquired in the following way: multiple polarization image samples are acquired using a polarization camera on an electrical aluminum rod sample with a predetermined defect location; different polarization image samples are acquired at different preset polarization angles; the contrast of the defect of the electrical aluminum rod sample in the polarization image samples is determined, and the preset polarization angle of the polarization image sample with the largest contrast among multiple preset polarization angles is taken as the target polarization angle; the polarization camera is controlled to acquire the polarization image set according to the target polarization angle.

[0012] In this way, by testing electrical aluminum samples with predetermined defect locations, the polarization angle that best matches the actual situation can be obtained, thereby improving the contrast of the defects in the obtained polarization image.

[0013] Optionally, matching the polarization image set and the structured light image set to obtain a polarization image and a structured light image matching the target aluminum rod region of the electrical aluminum rod includes: acquiring the correlation relationship obtained by pre-calibrating the polarization camera and the structured light camera; the correlation relationship is used to characterize the relationship between the polarization camera and the structured light camera in terms of spatial position and sampling time; acquiring the motion information of the electrical aluminum rod moving along the axial direction, and determining the corresponding aluminum rod region and the polarization image and structured light image matching the time from the polarization image set and the structured light image set based on the motion information and the correlation relationship.

[0014] Optionally, the association relationship is determined in the following way: obtaining the first spatial position of the polarization camera in the spatial coordinate system and the second spatial position of the structured light camera in the spatial coordinate system to obtain positional difference information between the first spatial position and the second spatial position; obtaining the time interval information between the moment when the polarization camera performs image acquisition and the moment when the structured light camera performs image acquisition, and determining the association relationship based on the positional difference information and the time interval information.

[0015] In this way, by determining the relationship between the polarization camera and the structured light camera, the placement of the polarization camera and the structured light camera can be more flexible or diverse.

[0016] Optionally, image fusion is performed on the matched polarization image and the structured light image to obtain a three-dimensional surface image, including: image fusion is performed on the matched polarization image and the structured light image to obtain a three-dimensional surface image, so that the color information of the target aluminum rod region in the polarization image and the three-dimensional height information of the target aluminum rod region in the structured light image are retained in the three-dimensional surface image.

[0017] In this way, by fusing polarized light images and structured light images, the advantages of both can be combined to enable the quality inspection of aluminum rod areas using three-dimensional surface images.

[0018] Optionally, based on multiple initial quality inspection results for multiple consecutive aluminum rod areas, the target quality inspection result for the electrical aluminum rods output by the production equipment during the target time period is determined, including: determining the continuous qualified length of the electrical aluminum rods output by the aluminum rod production equipment during the target time period based on multiple initial quality inspection results for multiple consecutive aluminum rod areas; and determining whether the target quality inspection result for the electrical aluminum rods output by the production equipment during the target time period is qualified or unqualified based on the relationship between the continuous qualified length and the target qualified length of the model to be inspected.

[0019] Optionally, the method further includes: winding the inspected electrical aluminum rod at the output end of the electrical aluminum rod; if the target quality test result of the electrical aluminum rod output during the target time period is unqualified, determining a candidate model whose minimum allowable continuous length is less than the continuous qualified length; and transporting the electrical aluminum rod coil obtained after winding the electrical aluminum rod output during the target time period of the production equipment to the production area where the candidate model is located.

[0020] This allows for full utilization of the qualified portion of the electrical aluminum rods produced by the production equipment within the target time period, thereby reducing the production cost of electrical aluminum rods.

[0021] According to a second aspect of the present application, an online inspection system for aluminum rod production quality is provided, comprising: a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions, when executed by the processor, implement the steps of the online inspection method for aluminum rod production quality provided in the first aspect of the present application.

[0022] The technical solutions provided by the embodiments of this application can include the following beneficial effects: For the same aluminum rod area of ​​the electrical aluminum rod output by the production equipment, by acquiring the polarization image and structured light image of the side of the aluminum rod area, the height information and color information of different positions in the same aluminum rod area can be obtained more completely. Compared with using RGB images for defect detection, it can avoid the influence of light reflection on the aluminum rod surface on the detection results, and can better detect defects such as pits and cracks on the aluminum rod surface that are difficult to show in RGB images. Therefore, by using the initial detection results of multiple consecutive aluminum rod areas, the quality inspection of the electrical aluminum rods output by the production equipment within the target time period can be better achieved, so as to ensure the quality of the electrical aluminum rods.

[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0024] Figure 1This is a flowchart illustrating an online quality inspection method for aluminum rod production according to an exemplary embodiment;

[0025] Figure 2 This is a schematic diagram of an online quality inspection system for aluminum rod production, according to an exemplary embodiment. Detailed Implementation

[0026] First, a brief introduction to the application scenario of the embodiments of this application will be given. In the application scenario of this application, the quality of electrical aluminum rods can be detected by using the RGB image of the surface of the electrical aluminum rod. However, defects such as local cracks or dents on the surface of the electrical aluminum rod are difficult to be reflected in the RGB image. Moreover, when using the RGB image for defect detection, the surface reflection effect of the aluminum rod may cause the defects on the surface of the electrical aluminum rod to be missed. Therefore, the related technology is difficult to accurately detect the production quality of electrical aluminum rods.

[0027] To address the aforementioned technical problems, embodiments of this application provide an online inspection method and system for aluminum rod production quality. Figure 1 This is a flowchart illustrating an online quality inspection method for aluminum rod production according to an exemplary embodiment, such as... Figure 1 As shown, the method includes the following steps.

[0028] In step S101, a polarization image set of the side of the electrical aluminum rod of the model to be detected is obtained using a polarization camera, and a structured light image set of the side of the electrical aluminum rod is obtained using a structured light camera.

[0029] A polarization camera and a structured light camera can be installed on the side of the aluminum pole to be tested. The polarization camera is used to acquire a set of polarization images, and the structured light camera is used to acquire structured light images. Different models of aluminum poles correspond to different minimum allowable lengths, or the different models of aluminum poles may also have differences in composition and cross-sectional diameter.

[0030] A polarization camera selectively filters light rays vibrating in a specific direction using a polarization filter, thereby capturing the polarization information of light. The polarized image obtained by the polarization camera can better reflect the brightness and color of the object itself, and can reduce the impact of surface reflections on the aluminum rod on the quality inspection results of the aluminum rod to a certain extent.

[0031] In the scenario of quality inspection of electrical aluminum rods output by production equipment, compared with the surface RGB image of the electrical aluminum rod, polarized image can improve the contrast of possible defects on the surface of the aluminum rod, making it easier to discover the defects in the electrical aluminum rod.

[0032] Structured light imaging technology can project specific patterns such as stripes, grids, or speckles onto the surface of an object and record the image after the projected pattern is deformed on the object's surface. It can then reconstruct the three-dimensional information of the object using the principle of triangulation, thereby obtaining the three-dimensional height information of the surface of the object to be detected. The specific generation process of structured light images will not be described in detail in the embodiments of this application, but can be implemented by referring to the imaging principles and methods of structured light images in the prior art.

[0033] To achieve quality inspection of the electrical aluminum poles of the model to be tested, sampling inspection or full inspection can be used to inspect the electrical aluminum poles output by the production equipment within the target time period. The sampling ratio can be determined according to the required length of the electrical aluminum poles.

[0034] To better achieve quality inspection of electrical aluminum rods, during quality inspection, the production line of the electrical aluminum rods can be controlled to reduce the output speed of the electrical aluminum rods to below the target speed, and after the quality inspection of the electrical aluminum rods is completed, the production line can be controlled to gradually restore the output speed of the electrical aluminum rods to the preset speed.

[0035] When adjusting the output speed of the electrical aluminum rod on the production line, it can be done according to the preset speed adjustment curve to avoid the impact of the change rate of the output speed of the electrical aluminum rod on the quality of the output electrical aluminum rod. The change rate can be set according to actual needs.

[0036] To avoid the influence of structured light image acquisition on polarization image acquisition, the structured light camera and polarization camera can acquire images at certain intervals. Furthermore, by utilizing the timestamp information of the image acquisition, it is possible to match the structured light image and polarization image of the same area of ​​the electrical aluminum rod.

[0037] In one embodiment, the polarization image set is acquired by: using a polarization camera to acquire multiple polarization image samples of an electrical aluminum rod sample with a predetermined defect location; different polarization image samples are acquired at different preset polarization angles; determining the contrast of the defect of the electrical aluminum rod sample in the polarization image samples, and taking the preset polarization angle of the polarization image sample with the largest contrast among multiple preset polarization angles as the target polarization angle; controlling the polarization camera to acquire the polarization image set according to the target polarization angle.

[0038] During the production of electrical aluminum rods, the illumination angle or intensity at the same location is relatively fixed. The polarization angle of the target can be determined by using electrical aluminum rod samples with predetermined defect locations.

[0039] Since the location of defects in the electrical aluminum rod sample has been determined in advance, the polarization camera acquires polarization images at different preset polarization angles at the set positions. Therefore, by comparing the contrast of defects in the polarization image samples obtained at different preset polarization angles, the target polarization angle that can better reflect the defects in the electrical aluminum rod can be obtained.

[0040] In step S102, the polarization image set and the structured light image set are matched to obtain a polarization image and a structured light image that match the target aluminum rod area of ​​the electrical aluminum rod, and the matched polarization image and structured light image are fused to obtain a three-dimensional surface image.

[0041] When acquiring polarization and structured light images of an electrical aluminum rod, there may not be enough space to simultaneously set up both a polarization camera and a structured light camera at the same location on the side of the rod. Therefore, the polarization camera and the structured light camera can be set at different positions along the axis of the electrical aluminum rod. By utilizing the positional relationship between the polarization camera and the structured light camera, it is possible to match the structured light image and the polarization image of the same area of ​​the aluminum rod.

[0042] In one embodiment, matching a set of polarized images and a set of structured light images to obtain a polarized image and a structured light image matching a target aluminum rod region for an electrical aluminum rod includes: acquiring the correlation relationship obtained by pre-calibrating the polarized camera and the structured light camera; the correlation relationship is used to characterize the relationship between the polarized camera and the structured light camera in terms of spatial position and sampling time; acquiring motion information of the electrical aluminum rod moving along the axial direction; and determining the corresponding aluminum rod region and the polarized image and structured light image matching the time from the set of polarized images and the set of structured light images based on the motion information and the correlation relationship.

[0043] For example, if the polarization camera corresponds to the first position in the direction of movement of the electrical aluminum rod, and the structured light camera corresponds to the second position in the direction of movement of the electrical aluminum rod, the direction from the first position to the second position is parallel to the direction in which the electrical aluminum rod moves.

[0044] If, based on the motion information of the electrical aluminum rod moving along its axial direction, the time required for the same region of the electrical aluminum rod to move from the first position to the second position is T, and the polarization camera acquires a polarization image of the target aluminum rod region at time t1, then the structured light image acquired by the structured light camera at time t2 corresponds to the target aluminum rod region, t2 = t1 + T; the motion information of the electrical aluminum rod moving along its axial direction can at least include the speed of the electrical aluminum rod moving along its axial direction.

[0045] In this way, by matching the set of polarized images and the set of structured light images, the polarized camera and the structured light camera can be set at different positions in the output direction of the electrical aluminum rod, making the setting of the polarized camera and the structured light more flexible and reducing the requirements for the setting of the polarized camera and the structured light camera.

[0046] In one embodiment, the association is determined by: obtaining a first spatial position of the polarization camera in the spatial coordinate system and a second spatial position of the structured light camera in the spatial coordinate system to obtain positional difference information between the first and second spatial positions; obtaining time interval information between the moment when the polarization camera acquires an image and the moment when the structured light camera acquires an image, and determining the association based on the positional difference information and the time interval information.

[0047] The relationship between the camera coordinate system of the polarization camera and the spatial coordinate system of the real world can be calibrated in advance, as can the relationship between the camera coordinate system of the structured light and the spatial coordinate system of the real world.

[0048] By utilizing the positional difference information between the first and second spatial positions, the relative positions of the polarization camera and the structured light camera in the real world can be reflected. This facilitates the frequency or time interval of image acquisition by the polarization camera and the structured light camera, thereby better enabling the acquisition of polarization images and structured light images of the same area of ​​the electrical aluminum rod.

[0049] Determining the correlation based on positional differences and time intervals facilitates combining the correlation with the motion information of the electrical aluminum rods output from the production line during quality inspection, enabling more accurate matching between polarization images and structured light images of the same aluminum rod region.

[0050] In one embodiment, image fusion of a matched polarization image and a structured light image to obtain a three-dimensional surface image includes: image fusion of a matched polarization image and a structured light image to obtain a three-dimensional surface image, so that the color information of the target aluminum rod region in the polarization image and the three-dimensional height information of the target aluminum rod region in the structured light image are retained in the three-dimensional surface image.

[0051] By matching different types of images in the polarization image set and the structured light image set, the matched polarization image and structured light image are for the same aluminum rod area of ​​the electrical aluminum rod. In the obtained polarization image, the influence of light reflection on the surface color information of the aluminum rod area can be reduced or avoided to a certain extent.

[0052] Because different materials have different light-reflecting abilities, the impurities that may exist in the electrical aluminum rod may differ from the color information of the electrical aluminum rod itself. Alternatively, the color information of areas with uneven distribution of surface components on the electrical aluminum rod may differ from the color information of areas with uniform distribution of surface components. Therefore, polarization images can better reflect the surface color information of the target aluminum rod area, making it easier to identify defects in the target aluminum rod area.

[0053] In the structured light image of the target aluminum rod region, the height information of different points in the target aluminum rod region can be reflected well. However, the color information contained in the structured light image may not be able to reflect the actual color information of the target aluminum rod region. Therefore, by fusing the polarization image and the structured light image of the target aluminum rod region, the obtained three-dimensional surface image can combine the advantages of both polarization and structured light images. This allows the three-dimensional surface image to reflect both the color information and the three-dimensional height information of the target aluminum rod region well.

[0054] In step S103, the initial quality inspection result of the target aluminum rod region is determined based on the height and color information of the location points in the target aluminum rod region in the three-dimensional surface image.

[0055] Since electrical aluminum rods are obtained by continuous rolling of aluminum rod blanks, the consistency of the composition distribution in the axial direction is usually higher than the consistency of the composition distribution in the circumferential direction. The consistency of the composition distribution in electrical aluminum rods is mainly manifested in the color consistency of different local areas of the electrical aluminum rod. Therefore, the consistency of the surface color in the circumferential direction of electrical aluminum rods can be mainly tested.

[0056] The anomalies that may exist in the electrical aluminum rod may manifest as differences in the diameter of different cross sections, resulting in differences in the curvature of different points on the same circular line in the electrical aluminum rod region. Furthermore, the curvature of the points in the electrical aluminum rod region can be determined based on the height information of the points in the three-dimensional surface image. Therefore, the height information of the points in the target aluminum rod region in the three-dimensional surface image can be used to determine whether there are any anomalies in the diameter information of the electrical aluminum rod in the target aluminum rod region.

[0057] In one embodiment, the initial quality inspection result is determined as follows: based on the height information of the position points in the target aluminum rod region in the three-dimensional surface image, the diameter defect information and height defect information of the target aluminum rod region are determined; the height defect information is used to characterize the degree of difference in height between position points in the same row in the target aluminum rod region; the diameter defect information is used to characterize the degree of difference in cross-sectional diameter between different columns in the target aluminum rod region; based on the color information of the position points in the target aluminum rod region in the three-dimensional surface image, the color difference information of the target aluminum rod region is determined, and the initial quality inspection result of the target aluminum rod region is determined based on the color difference information, the diameter defect information, and the height defect information.

[0058] Based on the height information of the location points in the target aluminum rod region in the three-dimensional surface image, the curvature information of the location points in the target aluminum rod region in the three-dimensional surface image can be determined. The degree of difference in curvature information of the location points located on the same ring line in the target aluminum rod region can reflect the roundness information of the location points on the same ring line in the target aluminum rod region.

[0059] Height defect information is used to characterize the degree of height difference between position points in the same row within the target aluminum rod region; the curvature information of electrical aluminum rods with different cross-sectional diameters is different, or the curvature information of electrical aluminum rods with inconsistent cross-sectional diameters is different at different cross-sections. Therefore, the average curvature information of position points located on the same loop line within the target aluminum rod region can reflect the diameter information of the electrical aluminum rod at the same loop line.

[0060] Given that the height information of different points in the target aluminum rod region has been determined, the curvature information of different points in the target aluminum rod region can be determined based on the height information of the points in the target aluminum rod region. Specifically, the steps for determining curvature in the prior art can be referred to, and will not be repeated here in the embodiments of this application.

[0061] The diameter defect information of the target aluminum rod region is used to characterize the degree of difference in the cross-sectional diameter of different sections corresponding to the target aluminum rod region in the electrical aluminum rod, so as to characterize the degree of difference in the cross-sectional diameter of different columns of the target aluminum rod region; since the image of the target aluminum rod region is acquired from the side of the electrical aluminum rod, different cross-sections of the target aluminum rod region can correspond to different columns of the target aluminum rod region.

[0062] The average curvature of the points in the same column of the target aluminum rod region can be used as the column curvature characteristic value. Based on the range or standard deviation of the column curvature characteristic values ​​of different columns of the target aluminum rod region, the diameter defect information of the target aluminum rod region can be determined.

[0063] When there are pits or scratches in the obtained electrical aluminum rod, the height information of the location point with the scratches or pits will differ from the height information of other location points on the axial direction of the electrical aluminum rod without pits. Therefore, the height defect information of the target aluminum rod area can be used to characterize the degree of difference in height information of the location points in the same row in the target aluminum rod area.

[0064] For example, the height defect information of the target aluminum rod area can be determined based on at least one of the range and standard deviation of the height information of the position points located in the same row in the target aluminum rod area.

[0065] Color difference information of the target aluminum rod area is used to characterize the degree of difference in color information between different sub-regions or different rows of the target aluminum rod area; for example, color difference information can be determined based on the differences in different color channels of different sub-regions or different rows of the target aluminum rod area.

[0066] The three-dimensional surface image contains color information from the polarization image of the target aluminum rod region. The different color channels of the location points in the target aluminum rod region can refer to the three channels of red, green and blue, respectively.

[0067] Based on the color difference information, the diameter defect information, and the height defect information, the defects of the target aluminum rod area in different aspects can be combined to determine the initial quality inspection results of the target aluminum rod area, so as to achieve a comprehensive evaluation of the target aluminum rod area.

[0068] In one embodiment, determining the initial quality inspection result for the target aluminum rod area based on color difference information, the diameter defect information, and the height defect information includes: determining the maximum defect depth and the continuous defect length of the target aluminum rod area based on the height defect information of different rows in the target aluminum rod area; normalizing the color difference information, diameter defect information, maximum defect depth, and continuous defect length, and determining the defect severity value based on the sum of the normalized color difference information, diameter defect information, maximum defect depth, and continuous defect length; and determining the initial quality inspection result for the target aluminum rod area based on the relationship between the defect severity value and a preset defect threshold.

[0069] The length of a continuous defect with depth defects can be determined as follows: For a surface location point of the target aluminum rod region in a 3D surface image, if the difference in depth information between the surface location point and other pixels in the same row's neighborhood is greater than a preset ratio, the surface location point can be used as a candidate depth defect point. Then, adjacent surface location points with similar depth information in the row containing the candidate depth defect points are used as candidate depth defect points to obtain all candidate depth defect points in different rows of the target aluminum rod region. The length of the candidate depth defect points that are adjacent to each other and located in the same row is taken as the length of the continuous defect.

[0070] The maximum defect depth of the target aluminum rod area can be determined in the following way: the range of the differences in depth information between the position points in the same row in the target aluminum rod area is taken as the row depth feature value of the same row in the target aluminum rod area; the maximum of the row depth feature values ​​of different rows is taken as the maximum defect depth.

[0071] Normalizing the color difference information, diameter defect information, maximum defect depth, and continuous defect length enables dimensionless processing of different variables, avoiding the influence of the dimensions of different variables on the subsequent comparison process. In the embodiments of this application, the normalization of variables can be achieved by means of min-max standardization, logarithmic transformation, arctangent function, and sigmoid function.

[0072] The defect severity value is determined by summing the normalized color difference information, diameter defect information, maximum defect depth, and continuous defect length. This allows for the combination of different defect manifestations in the target aluminum rod area, enabling a more comprehensive evaluation of the target aluminum rod area.

[0073] In one embodiment, determining the initial quality inspection result for the target aluminum rod area based on color difference information, diameter defect information, and height defect information includes: determining the maximum defect depth and the continuous defect length of the target aluminum rod area based on the height defect information of different rows in the target aluminum rod area; normalizing the color difference information, diameter defect information, maximum defect depth, and continuous defect length, and taking the largest of the normalized color difference information, diameter defect information, maximum defect depth, and continuous defect length as the defect severity value; and determining the initial quality inspection result for the target aluminum rod area based on the relationship between the defect severity value and a preset defect threshold.

[0074] By using the maximum of the normalized color difference information, diameter defect information, maximum defect depth, and continuous defect length as the defect severity value, the abnormality in the target aluminum rod area can be detected in time when at least one of the multiple evaluation indicators is abnormal, thus preventing the abnormal electrical aluminum rod from flowing into the next processing stage.

[0075] The preset defect threshold can be set according to actual needs. For example, when the defect severity value is normalized to 0 to 1, the preset defect threshold value can be between 0.5 and 0.8.

[0076] If the defect severity value is greater than or equal to the preset defect threshold, it indicates that the target aluminum rod area has an anomaly in at least one of the diameter, color, and height information, and the initial quality inspection result of the target aluminum rod area can be determined to be unqualified.

[0077] Conversely, if the defect severity value is less than the preset defect threshold, it indicates that there are no abnormalities in the target aluminum rod area in terms of diameter, color, and height information, and the initial quality inspection result of the target aluminum rod area can be determined to be qualified.

[0078] To detect different circumferential positions of an electrical aluminum rod, a polarization camera and a structured light camera corresponding to the same aluminum rod area can be used as a camera group. The aluminum rod areas covered by different camera groups can have a certain overlap (e.g., 20%), so as to obtain the polarization image and structured light image of the entire circumferential region of the same aluminum rod.

[0079] Alternatively, the quality inspection results obtained from different camera groups can be summarized to obtain the total quality inspection results for the same area of ​​the electrical aluminum pole.

[0080] In one possible implementation, the vibration intensity information in the vertical direction of the electrical aluminum rod production equipment at the current moment when outputting the electrical aluminum rod can be used to adjust the height information of the surface position point of the target aluminum rod area, so as to avoid the influence of the vibration of the electrical aluminum rod production equipment on the height information when outputting the electrical aluminum rod.

[0081] Accelerometers, distance sensors, or image sensors can be used to acquire the vertical vibration intensity and frequency information of the electrical aluminum rod production equipment when it is outputting electrical aluminum rods at the current moment. Using the vibration intensity and frequency information, the adjustment amount of the height information of the surface position point of the target aluminum rod area at the current moment can be determined, so as to adjust the height information of the surface position point of the target aluminum rod area using the adjustment amount.

[0082] In step S104, the target quality test result of the electrical aluminum rods output by the production equipment in the target time period is determined based on the initial quality test results of multiple consecutive aluminum rod areas.

[0083] Since electrical aluminum rods are mainly used to form aluminum wires in the subsequent wire drawing process and to cooperate with steel cores to form steel-cored aluminum stranded wires, the continuity of electrical aluminum rod production needs to be ensured to avoid stopping the subsequent wire drawing process and affecting the processing efficiency of electrical aluminum rods. Furthermore, the presence of defects in multiple consecutive aluminum rod areas is highly likely due to impurities in the molten aluminum raw material or abnormal rolling parameters of the aluminum rod billet. Therefore, the target quality inspection result of electrical aluminum rods output by the production equipment in the target time period can be determined based on multiple initial quality inspection results of multiple consecutive aluminum rod areas.

[0084] When an abnormality exists in one continuous section of an electrical aluminum rod, there is a high probability that an abnormality will also exist in another continuous section. Therefore, based on multiple initial quality inspection results of multiple continuous aluminum rod areas, it is beneficial to avoid electrical aluminum rods with abnormalities from flowing into the subsequent wire drawing process, and also to avoid the impact of occasional defects or defects with minor impact on the quality inspection results.

[0085] In one embodiment, determining the target quality inspection result of the electrical aluminum rods output by the production equipment during a target time period based on multiple initial quality inspection results for multiple consecutive aluminum rod regions includes: determining the continuous qualified length of the electrical aluminum rods output by the aluminum rod production equipment during the target time period based on multiple initial quality inspection results for multiple consecutive aluminum rod regions; and determining whether the target quality inspection result of the electrical aluminum rods output by the production equipment during the target time period is qualified or unqualified based on the relationship between the continuous qualified length and the target qualified length of the model to be inspected.

[0086] Multiple aluminum rod areas refer to different aluminum rod areas along the axial direction of the electrical aluminum rod. There can be a certain degree of overlap between multiple aluminum rod areas to ensure the accuracy of quality inspection of electrical aluminum rods; or, multiple aluminum rod areas can be adjacent without overlap to balance the efficiency of quality inspection of electrical aluminum rods.

[0087] The length of the target aluminum rod area can be set according to actual needs. For example, the length of the target aluminum rod area can be between 30 cm and 40 cm, which can be determined based on the width of the field of view of the polarization camera and the structured light camera.

[0088] The continuous qualified length of electrical aluminum rods output by the aluminum rod production equipment within the target time period can be determined based on the number of aluminum rod regions that passed the initial quality inspection and are adjacent to each other along the axial direction of the electrical aluminum rod, as well as the length of the aluminum rod regions.

[0089] For example, if multiple aluminum rod areas are adjacent to each other and do not overlap, the number of aluminum rod areas with initial quality inspection results that are qualified and adjacent to each other among the electrical aluminum rods output by the production equipment within the target time period is at most 5, and the length of the aluminum rod area is 40 centimeters, then the continuous qualified length is equal to 2 meters.

[0090] Because different models of electrical aluminum poles require different lengths, the acceptable lengths for different models also differ. Therefore, when inspecting the quality of electrical aluminum poles, the minimum continuous acceptable length that different models of electrical aluminum poles must achieve varies. In particular, the larger the length of the electrical aluminum pole indicated by the model, the larger the continuous acceptable length that must be achieved during inspection.

[0091] If the continuous qualified length of the model to be tested within the target time period is greater than the target qualified length of the model to be tested, then the target quality test result of the electrical aluminum rod output by the production equipment within the target time period can be determined to be qualified.

[0092] Conversely, if the continuous qualified length of the model to be tested within the target time period is less than or equal to the target qualified length of the model to be tested, then the target quality test result of the electrical aluminum rod output by the production equipment within the target time period can be determined to be unqualified.

[0093] The target time period can be output to correspond to the total length and duration required for the model to be tested, so as to complete the quality inspection of the complete electrical aluminum rod required for the model to be tested.

[0094] When conducting quality inspection on electrical aluminum poles of the specified model, if there is an area of ​​aluminum pole that initially failed the quality inspection, the section containing the area that initially failed the quality inspection can be cut off at the output end of the electrical aluminum pole to avoid the presence of unqualified sections in the complete electrical aluminum pole.

[0095] If the target quality test results of the electrical aluminum rods output by the production equipment within the target time period are unqualified, the supervisory personnel can be prompted to investigate the production line of electrical aluminum rods to avoid waste caused by continuing to produce electrical aluminum rods with unqualified quality test results.

[0096] In one embodiment, the inspected electrical aluminum rod can be wound at the output end of the electrical aluminum rod. If the target quality test result of the electrical aluminum rod output during the target time period is unqualified, a candidate model with a minimum allowable continuous length less than the continuous qualified length is determined. The electrical aluminum rod coil obtained after winding the electrical aluminum rod output during the target time period of the production equipment is transported to the production area where the candidate model is located.

[0097] The target quality test result of the electrical aluminum poles output during the target time period is unqualified, indicating that the length requirement of the electrical aluminum poles output during the target time period does not meet the length requirement of the model to be tested. However, the continuous qualified length of the electrical aluminum poles output during the target time period may be sufficient to meet the length requirements of other models besides the model to be tested. For example, it may meet the length requirement of at least one other model whose total length is less than that of the model to be tested.

[0098] To prevent substandard electrical aluminum rods from entering the subsequent wire drawing process and to make full use of the electrical aluminum rods produced, when the quality inspection result of a complete electrical aluminum rod is substandard due to the substandard quality inspection result of some sections, the sections with satisfactory quality inspection results can be fully utilized.

[0099] The winding of the electrical aluminum rod is performed at the output end of the electrical aluminum rod. After processing the initial section of the obtained electrical aluminum rod coil, what remains is the qualified electrical aluminum rod, and the qualified part can continue to be used.

[0100] The electrical aluminum rods output from the production equipment during the target time period are wound into coils, which are then transported to the production area of ​​the candidate model. This facilitates the use of the formed electrical aluminum rods and avoids confusion between coils of electrical aluminum rods that are not up to standard for the model being tested and coils that have passed inspection for the model being tested.

[0101] The inspected electrical aluminum rods can be wound at the output end of the electrical aluminum rods. If the target quality test result of the electrical aluminum rods output during the target time period is qualified, the coil of electrical aluminum rods obtained after winding the electrical aluminum rods output during the target time period of the production equipment can be transported to the packaging area of ​​the model to be tested.

[0102] The coils of electrical aluminum rods produced by the production equipment during the target time period are transported to the packaging area for the model to be tested. This ensures continuous operation of the electrical aluminum rods produced by the production equipment and improves the processing efficiency of the electrical aluminum rods.

[0103] Figure 2 This is a schematic diagram illustrating the structure of an online quality inspection system 1000 for aluminum rod production, according to an exemplary embodiment. (Refer to...) Figure 2 The online quality inspection system 1000 for aluminum rod production includes a processor 1100 and a memory 1200. The memory 1200 stores computer program instructions, which, when executed by the processor 1100, implement all or part of the steps of the online quality inspection method for aluminum rod production in this application.

[0104] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for online quality inspection of aluminum rod production, characterized in that, include: A polarization image set of the side of the electrical aluminum rod of the model to be tested is obtained using a polarization camera, and a structured light image set of the side of the electrical aluminum rod is obtained using a structured light camera. The polarization image set and the structured light image set are matched to obtain a polarization image and a structured light image that match the target aluminum rod region of the electrical aluminum rod. The matched polarization image and the structured light image are then fused to obtain a three-dimensional surface image. This includes: fusing the matched polarization image and the structured light image to obtain a three-dimensional surface image, so that the color information of the target aluminum rod region in the polarization image and the three-dimensional height information of the target aluminum rod region in the structured light image are retained in the three-dimensional surface image. Based on the height and color information of the location points in the target aluminum rod region in the 3D surface image, the initial quality inspection results for the target aluminum rod region are determined: Based on the height information of the location points in the target aluminum rod region in the three-dimensional surface image, determine the diameter defect information and height defect information of the target aluminum rod region, including: determining the height defect information of the target aluminum rod region based on at least one of the range and standard deviation of the height information of the location points in the same row of the target aluminum rod region; taking the average curvature of the location points in the same column of the target aluminum rod region as the column curvature feature value of the column, and determining the diameter defect information of the target aluminum rod region based on the range or standard deviation of the column curvature feature values ​​of different columns of the target aluminum rod region; Height defect information is used to characterize the degree of difference in height between position points in the same row in the target aluminum rod region; diameter defect information is used to characterize the degree of difference in cross-sectional diameter between different columns in the target aluminum rod region; based on the color information of position points in the target aluminum rod region in the three-dimensional surface image, the color difference information of the target aluminum rod region is determined, and based on the color difference information, the diameter defect information, and the height defect information, the initial quality inspection result of the target aluminum rod region is determined; Based on the initial quality inspection results of multiple consecutive aluminum rod areas, the target quality inspection results for the electrical aluminum rods output by the production equipment during the target time period are determined, including: Based on the initial quality inspection results of multiple consecutive aluminum rod areas, the continuous qualified length of electrical aluminum rods output by the aluminum rod production equipment within the target time period is determined. Based on the relationship between the continuous qualified length and the target qualified length of the model to be tested, the target quality test result of the electrical aluminum rods output by the production equipment in the target time period is determined to be qualified or unqualified.

2. The online quality inspection method for aluminum rod production according to claim 1, characterized in that, Based on the color difference information, the diameter defect information, and the height defect information, the initial quality inspection results for the target aluminum rod area are determined, including: Based on the height defect information of different rows in the target aluminum rod area, determine the maximum defect depth and the continuous defect length of the target aluminum rod area where the depth defect exists; The color difference information, diameter defect information, maximum defect depth, and continuous defect length are normalized, and the defect severity value is determined based on the sum of the normalized color difference information, diameter defect information, maximum defect depth, and continuous defect length. The initial quality inspection results for the target aluminum rod area are determined based on the relationship between the defect severity value and the preset defect threshold.

3. The online quality inspection method for aluminum rod production according to claim 1, characterized in that, The set of polarization images was obtained in the following way: Multiple polarization images of an electrical aluminum rod sample with a predetermined defect location were acquired using a polarization camera; the different polarization images were acquired at different preset polarization angles. Determine the contrast of the defects of the electrical aluminum rod sample in the polarization image sample, and take the preset polarization angle of the polarization image sample with the highest contrast among multiple preset polarization angles as the target polarization angle. Control the polarization camera to acquire a set of polarization images according to the target polarization angle.

4. The online quality inspection method for aluminum rod production according to claim 1, characterized in that, Matching the sets of polarization images and structured light images yields polarization and structured light images that match the target aluminum rod region for the electrical aluminum rod, including: Obtain the correlation between the polarization camera and the structured light camera obtained through pre-calibration; the correlation is used to characterize the relationship between the polarization camera and the structured light camera in terms of spatial location and sampling time; The motion information of the electrical aluminum rod moving along the axial direction is obtained, and based on the motion information and the correlation, the corresponding aluminum rod region and the polarization image and structured light image that match the time are determined from the polarization image set and the structured light image set.

5. The online quality inspection method for aluminum rod production according to claim 4, characterized in that, The association is determined in the following ways: The first spatial position of the polarization camera in the spatial coordinate system and the second spatial position of the structured light camera in the spatial coordinate system are obtained to obtain the positional difference information between the first spatial position and the second spatial position; The time interval information between the moment when the polarization camera acquires an image and the moment when the structured light camera acquires an image is obtained, and the correlation is determined based on the position difference information and the time interval information.

6. The online quality inspection method for aluminum rod production according to claim 1, characterized in that, The method further includes: The inspected electrical aluminum rod is wound at the output end of the electrical aluminum rod. If the target quality test result of the output electrical aluminum rod during the target time period is unqualified, a candidate model with a minimum allowable continuous length that is less than the continuous qualified length is determined. The electrical aluminum rods produced by the production equipment during the target time period are wound into coils and transported to the production area where the candidate model is located.

7. An online quality inspection system for aluminum rod production, characterized in that, include: A processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement the online inspection method for aluminum rod production quality according to any one of claims 1-6.

Images