Fuse fracture detection method based on X-ray images

Abstract

The present application relates to the field of image data processing technology, and in particular to a method for detecting fuse fracture based on X-ray images. The method includes: obtaining an X-ray image of a target fuse to be detected, and determining the gradient direction and gradient magnitude of a pixel in the X-ray image; determining a target parameter value of a target pixel according to the gradient direction and gradient magnitude of other pixels within a target range of the target pixel in the X-ray image; processing the target parameter value using an exponential function to obtain an exponential operation value, and determining a target threshold of the target pixel according to the multiplication of the inverse of the exponential operation value and a first preset gradient threshold; when the gradient magnitude of the target pixel is greater than the target threshold, the target pixel is used as the pixel where the fuse fracture is located to obtain a fracture area. Through the above technical solution, a more accurate fracture area can be determined when the fuse is fractured.

Description

Technical Field

[0001] The present application relates to the technical field of image data processing, and in particular to a method for detecting fuse fracture based on X-ray images. Background Art

[0002] The fuse is a key component of the fuse. It is usually made of metals such as copper, tin, and silver, which makes the fuse have conductive properties and a corresponding melting point. In the case of current overload, the fuse can melt and cut off the circuit to prevent electrical equipment from being damaged due to overload or short circuit. According to different structures, fuses can be divided into plug-in fuses, spiral fuses, unfilled sealed tube fuses, and filled sealed tube fuses.

[0003] In order to detect the fuse, a method for detecting welding defects of a fuse is provided in the related art, such as the Chinese patent application document with the publication number CN117710307A, which includes: obtaining a copper sheet welding image of the fuse; determining an effective welding area in the copper sheet welding image; and obtaining a first defect detection result of the fuse according to the effective welding area. Determining the effective area in the copper sheet welding image includes: determining the copper sheet area and the pad area in the copper sheet welding image; determining the intersection area of ​​the copper sheet area and the pad area; and determining the intersection area as the effective welding area.

[0004] The related art mainly focuses on defect detection of copper sheets produced by welding in fuses, and mainly detects defects in fuses through surface images of fuses. However, internal defects of fuses may be difficult to reflect in surface images. Therefore, the accuracy of related art in detecting fractures in fuses is low. Summary of the invention

[0005] In order to overcome the problem of low accuracy of fuse fracture detection in the related art, the present application provides a fuse fracture detection method based on X-ray images, comprising:

[0006] An X-ray image of a target fuse to be detected is obtained, and a gradient direction and a gradient magnitude of a pixel in the X-ray image are determined; for a target pixel in the X-ray image, a target parameter value of the target pixel is determined according to the gradient directions and gradient magnitudes of other pixels within a target range of the target pixel, wherein the target parameter value is used to characterize the probability that the target pixel is a pixel at a fracture; an exponential function is used to process the target parameter value to obtain an exponential operation value, and a target threshold of the target pixel is determined according to the multiplication of the inverse of the exponential operation value and a first preset gradient threshold; when the gradient magnitude of the target pixel is greater than the target threshold, the target pixel is used as a pixel at a fracture of the fuse, so as to obtain a fracture area composed of a plurality of pixels at the fracture.

[0007] In this way, an X-ray image of the target fuse to be inspected is obtained, and the possible fracture area in the target fuse is determined based on the X-ray image. Compared with defect detection of the fuse using the surface image of the fuse, since the X-ray image can reflect the characteristics of the internal defects of the fuse, it is possible to more accurately detect the fracture of the fuse, thereby determining a more accurate fracture area when the fuse is fractured.

[0008] At the same time, there may be identification information such as manufacturer name, fuse size and applicable melting point on the surface of the fuse. Compared with using the surface image of the fuse to detect fuse defects, since the X-ray image can reflect the characteristics of the internal defects of the fuse, it is possible to avoid the influence of the identification information on the surface of the fuse on the defect detection results, thereby obtaining a more accurate fracture detection result for the fuse.

[0009] Furthermore, the gradient direction and gradient magnitude of the pixel point in the X-ray image are determined, the target parameter value of the target pixel point is determined according to the gradient directions and gradient magnitudes of other pixel points within the target range of the target pixel point in the X-ray image, and the target threshold value corresponding to the target pixel point is determined according to the target parameter value of the target pixel point. When the gradient magnitude of the target pixel point is greater than the target threshold value, the target pixel point is used as the pixel point where the fuse is broken. Compared with determining the pixel point where the fuse is broken in the X-ray image by using a fixed gradient threshold value, the target threshold value corresponding to the pixel point can be determined according to the actual situation of the pixel point, thereby determining a more accurate fracture area.

[0010] Optionally, determining the target parameter value corresponding to the target pixel point according to the gradient direction and gradient magnitude of other pixel points within the target range of the target pixel point includes: , where K is the target parameter value corresponding to the target pixel, norm is the normalization function; P is the first texture feature value of the target pixel, and P is used to characterize the variation range of the grayscale value of the pixel within the target range; M is the number of pixels within the target range, is the gradient size of the mth pixel within the target range, is the average value of the gradient of pixels within the target range, is a preset value greater than 0, S is the second texture feature value of the target pixel, and S is used to characterize the complexity of the gradient direction of the pixel points within the target range.

[0011] In this way, the difference between the gradient size of the pixel points within the target range and the average value of the gradient size of the pixel points within the target range can more comprehensively characterize the texture complexity at the target pixel points, which helps to obtain more accurate fracture detection results for the target fuse.

[0012] Optionally, the first texture feature value is obtained in the following manner: ,in, is the first texture feature value of the target pixel, norm is the normalization function, G is the gradient size of the target pixel, M is the number of pixels within the target range, is the gradient size of the mth pixel within the target range, is the maximum gray value of the pixel within the target range. is the minimum gray value of the pixels within the target range. A preset value greater than 0.

[0013] In this way, the first texture feature value of the target pixel is determined by combining the gradient size of the target pixel and other pixels in the target range except the target pixel, and the texture complexity of the target range can be described by the first texture feature value.

[0014] Optionally, the second texture feature value is obtained in the following manner: , where N is the number of types of gradient directions of pixels within the target range, is the frequency of the nth gradient direction within the target range, and log is the logarithmic function.

[0015] In this way, the more types of gradient directions there are in the target range, the higher the texture complexity of the target range is usually. The second texture eigenvalue is determined by the frequency of occurrence of different gradient directions in the target range. The second texture eigenvalue can better characterize the complexity of the gradient direction of the pixel point in the target range, so as to determine whether the target pixel point is at the fracture point of the fuse.

[0016] Optionally, the target threshold of the target pixel is determined by: , where L is the target threshold of the target pixel, exp is an exponential function with a natural constant as the base, K is the target parameter value of the target pixel, A is a preset adjustment coefficient, and W is the first preset gradient threshold.

[0017] In this way, the exponential operation value is obtained by processing the target parameter value with an exponential function, and the target threshold of the target pixel point is determined according to the inverse of the exponential operation value. A lower target threshold can be set for pixels with higher target parameter values, or a higher target threshold can be set for pixels with lower target parameter values, so as to obtain a more accurate fracture area in the X-ray image.

[0018] Optionally, the method also includes: when the gradient size of the target pixel point is less than the target threshold and the gradient size is greater than a second preset gradient threshold, determining the distance between the target pixel point and the pixel point where the fracture is located; the second preset gradient threshold is less than the first preset gradient threshold; when the distance is less than the preset distance threshold, taking the target pixel point as the pixel point where the fracture is located.

[0019] In this way, according to the gradient size of the target pixel point and the distance between the target pixel point and the pixel point where the fracture area is located, the pixel points in the X-ray image can be further screened, thereby determining a more accurate fracture area in the fuse.

[0020] Optionally, the method also includes: determining the area of ​​the fracture region, and sending a control instruction to a sorting device when the area of ​​the fracture region is greater than a preset area threshold; wherein the control instruction is used to control the sorting device to remove the fuse that passes the target position at the target time from the transportation device, and the transportation device is used to transport the fuse along the target transportation path.

[0021] In this way, the broken fuse determined by fracture detection at the current moment is the fuse that passes the target position at the target moment. The fuse that passes the target position at the target moment is taken out from the transport device, which can not only realize the sorting of broken fuses, but also enable the sorting equipment and fracture monitoring equipment to be more flexibly arranged in different spatial positions.

[0022] Optionally, the target time is determined in the following manner: obtaining the first position of the target fuse at the current moment on the target transport path, and obtaining the second position corresponding to the sorting device on the target transport path; obtaining the transport speed of the fuse by the transport device, and determining the target time based on the first position, the second position and the transport speed.

[0023] The technical solution provided by the embodiments of the present application may include the following beneficial effects: obtaining an X-ray image of the target fuse to be inspected, and determining the possible fracture area in the target fuse based on the X-ray image. Compared with using the surface image of the fuse to perform defect detection on the fuse, since the X-ray image can reflect the characteristics of the internal defects of the fuse, it is possible to more accurately detect the fracture of the fuse, thereby determining a more accurate fracture area when the fuse is fractured.

[0024] At the same time, there may be identification information such as manufacturer name, fuse size and applicable melting point on the surface of the fuse. Compared with using the surface image of the fuse to detect fuse defects, since the X-ray image can reflect the characteristics of the internal defects of the fuse, it is possible to avoid the influence of the identification information on the surface of the fuse on the defect detection results, thereby obtaining a more accurate fracture detection result for the fuse.

[0025] Furthermore, the gradient direction and gradient magnitude of the pixel point in the X-ray image are determined, the target parameter value of the target pixel point is determined according to the gradient directions and gradient magnitudes of other pixel points within the target range of the target pixel point in the X-ray image, and the target threshold value corresponding to the target pixel point is determined according to the target parameter value of the target pixel point. When the gradient magnitude of the target pixel point is greater than the target threshold value, the target pixel point is used as the pixel point where the fuse is broken. Compared with determining the pixel point where the fuse is broken in the X-ray image by using a fixed gradient threshold value, the target threshold value corresponding to the pixel point can be determined according to the actual situation of the pixel point, thereby determining a more accurate fracture area.

[0026] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] 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.

[0028] Figure 1 The present invention is a flow chart showing a method for detecting fuse fracture based on X-ray images according to an exemplary embodiment. DETAILED DESCRIPTION

[0029] Here, exemplary embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application.

[0030] First, the application scenario of the embodiment of the present application is briefly introduced. In the application scenario of the present application, if the fuse link of the fuse is partially broken, the contact resistance of the fuse may increase, thereby generating more heat at the fuse and accelerating the aging of the fuse, and even blowing prematurely before reaching its rated current, threatening the safety of the electrical equipment connected to the fuse.

[0031] In order to ensure the reliability of the fuse, the fuse can be inspected for defects before it is installed inside the fuse. For example, the fuse produced on the fuse transportation line can be inspected for defects to prevent broken fuses from being installed in fuses connected to electrical equipment, thereby ensuring the safety of the electrical equipment.

[0032] In the related art, defect detection of the fuse is mainly performed through the surface image of the fuse link. However, there may be identifying text information on the surface of the fuse link, or the defects of the fuse link may be difficult to obtain from the surface image, making it difficult to detect the fracture of the fuse link through the surface image of the fuse link, and the accuracy of fuse fracture detection is low.

[0033] In response to the above technical problems, an embodiment of the present application provides a method for detecting fuse fractures based on X-ray images, which obtains an X-ray image of a target fuse to be detected, and determines a possible fracture area in the target fuse based on the X-ray image. Compared with using a surface image of the fuse to perform defect detection on the fuse, since the X-ray image can reflect the characteristics of the internal defects of the fuse, it is possible to more accurately detect the fracture of the fuse, thereby determining a more accurate fracture area when the fuse is fractured.

[0034] At the same time, there may be identification information such as manufacturer name, fuse size and applicable melting point on the surface of the fuse. Compared with using the surface image of the fuse to detect fuse defects, since the X-ray image can reflect the characteristics of the internal defects of the fuse, it is possible to avoid the influence of the identification information on the surface of the fuse on the defect detection results, thereby obtaining a more accurate fracture detection result for the fuse.

[0035] Furthermore, the gradient direction and gradient magnitude of the pixel point in the X-ray image are determined, the target parameter value of the target pixel point is determined according to the gradient directions and gradient magnitudes of other pixel points within the target range of the target pixel point in the X-ray image, and the target threshold value corresponding to the target pixel point is determined according to the target parameter value of the target pixel point. When the gradient magnitude of the target pixel point is greater than the target threshold value, the target pixel point is used as the pixel point where the fuse is broken. Compared with determining the pixel point where the fuse is broken in the X-ray image by using a fixed gradient threshold value, the target threshold value corresponding to the pixel point can be determined according to the actual situation of the pixel point, thereby determining a more accurate fracture area.

[0036] Figure 1 is a flow chart showing a method for detecting fuse fracture based on X-ray images according to an exemplary embodiment. Figure 1 As shown, the method includes the following steps.

[0037] In step S101, an X-ray image of a target fused sheet to be inspected is acquired, and a gradient direction and a gradient magnitude of pixels in the X-ray image are determined.

[0038] X-ray imaging is an imaging technology that uses X-rays to penetrate objects and record their internal structures. When X-rays pass through the target object, due to differences in density and thickness of the target object's internal structure, materials of different densities absorb X-rays to different degrees, and an X-ray image reflecting the internal characteristics of the target object can be generated.

[0039] For example, an X-ray image acquisition device can be set up to capture X-ray images of the completed fused sheet; the completed fused sheet can be transported by transportation equipment so that the completed fused sheet is transported along the target transportation path; the transportation equipment can be, for example, a conveying equipment such as a belt conveyor belt, and the X-ray image acquisition device can be an X-ray imaging system, an X-ray detector and other equipment.

[0040] X-ray images are usually presented as grayscale images. The gradient size of pixels in grayscale images can reflect the edge information in the image. The gradient size of pixel values ​​can be determined by the horizontal gradient and vertical gradient of pixels. The horizontal gradient and vertical gradient of pixels in grayscale images can be obtained by using Sobel operator, Prewitt operator, Roberts operator, Laplacian operator and Scharr operator.

[0041] In step S102, for a target pixel in the X-ray image, a target parameter value of the target pixel is determined according to the gradient directions and gradient magnitudes of other pixels within a target range of the target pixel.

[0042] Among them, the target parameter value is used to characterize the probability that the target pixel is a pixel at a fracture site. The larger the target parameter value of the pixel is, the higher the probability that the target pixel is at a fracture site. On the contrary, the smaller the target parameter value of the pixel is, the lower the probability that the target pixel is at a fracture site.

[0043] In the case where fractures exist in the fuse, the region where the fractures exist in the fuse will appear as random cracks in the X-ray image, and the trajectories of these cracks are more dispersed and irregular than the edges of the fuse, for example, the texture complexity of the region where the cracks exist is higher than the texture complexity of the region where the cracks do not exist.

[0044] Therefore, the target parameter value of the target pixel can be determined by the gradient direction and gradient magnitude of other pixels within the target range of the target pixel, so that the probability that the target pixel is a pixel at the fracture can be represented by the target parameter value.

[0045] The target range may be a range of a preset size centered on the target pixel point, for example, the target range may be a 5×5 pixel area centered on the target pixel point, or the target range may be a 7×7 pixel area centered on the target pixel point.

[0046] In one embodiment, determining the target parameter value corresponding to the target pixel point according to the gradient direction and gradient magnitude of other pixel points within the target range of the target pixel point includes: , where K is the target parameter value corresponding to the target pixel, norm is the normalization function; P is the first texture feature value of the target pixel, and P is used to characterize the variation range of the grayscale value of the pixel within the target range; M is the number of pixels within the target range, is the gradient size of the mth pixel within the target range, is the average value of the gradient of pixels within the target range, is a preset value greater than 0, S is the second texture feature value of the target pixel, and S is used to characterize the complexity of the gradient direction of the pixel points within the target range.

[0047] Here, the first texture eigenvalue is used to characterize the variation amplitude of the grayscale value of the pixel point within the target range, and the second texture eigenvalue is used to characterize the complexity of the gradient direction of the pixel point within the target range. Combining the first texture eigenvalue and the second texture eigenvalue can better characterize the texture complexity at the target pixel point, thereby better characterizing the probability that the target pixel point is a pixel point at the fracture through the target parameter value.

[0048] The difference between the gradient size of the pixels within the target range and the average value of the gradient size of the pixels within the target range can more comprehensively characterize the texture complexity at the target pixel points, which helps to obtain more accurate fracture detection results for the target fuse.

[0049] By normalizing the calculation results with the normalization function, the target parameter value corresponding to the target pixel point can be within the range of 0 to 1, which is convenient for comparing the target parameter values ​​of different pixels; the existence of a preset value greater than 0 can avoid the situation where the item involved in the multiplication operation is 0 when the gradient size within the target range of the target pixel point is the same, so as to give full play to the influence of each item involved in the calculation of the target parameter value, so as to obtain a more accurate target parameter value; for example, the preset value It can be values ​​such as 0.01, 0.02, and 0.05.

[0050] In one embodiment, the first texture feature value is obtained by: ,in, is the first texture feature value of the target pixel, norm is the normalization function, G is the gradient size of the target pixel, M is the number of pixels within the target range, is the gradient size of the mth pixel within the target range, is the maximum gray value of the pixel within the target range. is the minimum gray value of the pixels within the target range. A preset value greater than 0.

[0051] The difference between the maximum grayscale value of the pixel points in the target range and the minimum grayscale value of the pixel points in the target range can reflect the variation of the pixel values ​​in the target range; when the fuse is broken, the variation of the grayscale value of the pixel points in the broken area is greater than that of the pixel points in the unbroken area. Therefore, determining the variation of the grayscale value of the pixel points in the target range is helpful to determine the fracture area in the X-ray image. Since the X-ray image is a grayscale image, the pixel value of the pixel point in the X-ray image is the grayscale value of the pixel point.

[0052] At the same time, the gradient size of the pixel points within the target range can also reflect the texture characteristics of the target area. Therefore, the first texture feature value of the target pixel point is determined by combining the gradient sizes of the target pixel point and other pixel points except the target pixel point within the target range. The texture complexity of the target range can be described by the first texture feature value.

[0053] In one embodiment, the second texture feature value is obtained by: , where N is the number of types of gradient directions of pixels within the target range, is the frequency of the nth gradient direction within the target range, and log is the logarithmic function.

[0054] The frequencies of occurrence of different gradient directions within the target range are different, so the frequencies of occurrence of different gradient directions are also different. The frequencies of occurrence of gradient directions are between 0 and 1, and the sum of the frequencies of occurrence of all gradient directions is 1. Therefore, the processing result of the logarithmic function on the frequencies of occurrence of gradient directions is a negative number. Therefore, the presence of the negative sign in the calculation formula of the second texture eigenvalue S can ensure that the value of the second texture eigenvalue is positive.

[0055] The more types of gradient directions there are in the target range, the higher the texture complexity of the target range is usually. The second texture eigenvalue is determined by the frequency of occurrence of different gradient directions in the target range. The second texture eigenvalue can better characterize the complexity of the gradient direction of the pixel point in the target range, so as to determine whether the target pixel point is at the fracture point of the fuse.

[0056] In step S103, the target parameter value is processed by using an exponential function to obtain an exponential operation value, and the target threshold of the target pixel point is determined according to the multiplication of the reciprocal of the exponential operation value and the first preset gradient threshold.

[0057] Here, the target parameter value is processed using an exponential function to obtain an exponential operation value, and the inverse of the exponential operation value is multiplied by the first preset gradient threshold, so that the obtained multiplication value is between 0 and 1, thereby realizing normalization processing of the calculation results of the target parameter value and the first preset gradient threshold, and avoiding the influence of different numerical ranges of different parameters on the calculation results.

[0058] In order to achieve the segmentation of the broken area in the X-ray image in the related art, a gradient threshold can be set in advance, and the gradient size of the pixel point can be compared with the gradient threshold. However, it may be difficult to achieve effective segmentation of the broken area through a single gradient threshold; for example, the pixel points that are not in the broken area may be divided into the broken area, or the pixel points in the broken area may be divided into the non-broken area, resulting in an erroneous judgment of the broken area.

[0059] In an embodiment of the present application, a smaller segmentation threshold can be set for target pixel points with larger target parameter values ​​to achieve segmentation of target pixel points with larger target parameter values ​​as much as possible; or, a larger segmentation threshold can be set for target pixel points with smaller target parameter values ​​to avoid the non-fracture area in the X-ray image from being segmented into the fracture area, thereby obtaining a more accurate fracture area.

[0060] In one embodiment, the target threshold of the target pixel is determined by: , where L is the target threshold of the target pixel, exp is an exponential function with a natural constant as the base, K is the target parameter value of the target pixel, A is a preset adjustment coefficient, and W is the first preset gradient threshold.

[0061] For pixel points in a grayscale image with pixel values ​​between 0 and 255, since the gradient size mainly reflects the change in the pixel value of the pixel point, the gradient size of the pixel point can be between 0 and 255. The specific value of the first preset gradient threshold can be determined based on the gradient size of the pixel point in the historical X-ray image of the fused film. For example, the first preset gradient threshold can be between 20 and 50, and the pre-set adjustment coefficient is a positive integer such as 1 or 2.

[0062] In this way, the exponential operation value is obtained by processing the target parameter value with an exponential function, and the target threshold of the target pixel point is determined according to the inverse of the exponential operation value. A lower target threshold can be set for pixels with higher target parameter values, or a higher target threshold can be set for pixels with lower target parameter values, so as to obtain a more accurate fracture area in the X-ray image.

[0063] In step S104, when the gradient magnitude of the target pixel is greater than the target threshold, the target pixel is used as the pixel where the fracture of the fuse is located, so as to obtain a fracture region composed of multiple pixel points where the fracture is located.

[0064] Since the target threshold is determined based on the target parameter value of the target pixel, and the target parameter value is determined based on the gradient direction and gradient magnitude of other pixels within the target range, when the gradient magnitude of the target pixel is greater than the target threshold, it means that the grayscale change at the target pixel is large, or the texture change direction and texture change amplitude at the target pixel are large. Therefore, there is a high probability that the target pixel is at the fracture point of the fuse.

[0065] By taking the target pixel point as the pixel point where the fuse is broken, the fracture area composed of multiple pixel points at the fracture point can be obtained, thereby realizing the fracture detection of the fuse; according to the different areas of the fracture area, it can also be determined whether the target fuse can continue to be used, or the broken fuse can be sorted out to avoid confusion between the broken fuse and the non-broken fuse.

[0066] In one embodiment, the distance between the target pixel point and the pixel point where the fracture is located can also be determined when the gradient magnitude of the target pixel point is smaller than the target threshold and the gradient magnitude is larger than a second preset gradient threshold; the second preset gradient threshold is smaller than the first preset gradient threshold; when the distance is smaller than the preset distance threshold, the target pixel point is taken as the pixel point where the fracture is located.

[0067] For example, a first preset gradient threshold and a second preset gradient threshold may be preset, the second preset gradient threshold is less than the first preset gradient threshold, and for a target pixel in an X-ray image, the target threshold corresponding to the target pixel may be determined based on the first preset gradient threshold according to the target threshold determination process provided in the embodiment of the present application. The second preset gradient threshold may be set according to actual needs, for example, the second preset gradient threshold may be between 10 and 20.

[0068] When the gradient magnitude of the target pixel is greater than the target threshold corresponding to the target pixel, it means that the gradient magnitude of the target pixel is large and the gradient direction is relatively random. The characteristics of the target pixel are consistent with the characteristics of the pixel at the fracture. The target pixel can be used as the pixel at the fracture.

[0069] When the gradient size of the target pixel point is less than the second preset gradient threshold, it means that the change amplitude of the grayscale value at the target pixel point is small, and the characteristics of the target pixel point are relatively consistent with the characteristics of the pixel points in the unbroken area. The target pixel point can be used as the pixel point of the unbroken area.

[0070] When the gradient size of the target pixel point is between the second preset gradient threshold and the target threshold, that is, the gradient size of the target pixel point is smaller than the target threshold, and the gradient size of the target pixel point is larger than the second preset gradient threshold, the characteristics of the target pixel point are between the pixel points in the broken area and the pixel points in the unbroken area, and further judgment of the target pixel point can be achieved based on the distance between the target pixel point and the pixel point at the broken point.

[0071] For example, by comparing the gradient size of the target pixel with the target threshold corresponding to the target pixel, the fracture area in the X-ray image can be determined, and other pixels around the fracture area may also be the location points of the fracture.

[0072] In this way, according to the gradient size of the target pixel point and the distance between the target pixel point and the pixel point where the fracture area is located, the pixel points in the X-ray image can be further screened, thereby determining a more accurate fracture area in the fuse.

[0073] By using the X-ray image-based fuse fracture detection method provided in the embodiment of the present application, an X-ray image of the target fuse to be detected is obtained, and a fracture area that may exist in the target fuse is determined based on the X-ray image. Compared with using the surface image of the fuse to perform defect detection on the fuse, since the X-ray image can reflect the characteristics of the internal defects of the fuse, it is possible to more accurately detect the fracture of the fuse, thereby determining a more accurate fracture area when the fuse is fractured.

[0074] At the same time, there may be identification information such as manufacturer name, fuse size and applicable melting point on the surface of the fuse. Compared with using the surface image of the fuse to detect fuse defects, since the X-ray image can reflect the characteristics of the internal defects of the fuse, it is possible to avoid the influence of the identification information on the surface of the fuse on the defect detection results, thereby obtaining a more accurate fracture detection result for the fuse.

[0075] Furthermore, the gradient direction and gradient magnitude of the pixel point in the X-ray image are determined, the target parameter value of the target pixel point is determined according to the gradient directions and gradient magnitudes of other pixel points within the target range of the target pixel point in the X-ray image, and the target threshold value corresponding to the target pixel point is determined according to the target parameter value of the target pixel point. When the gradient magnitude of the target pixel point is greater than the target threshold value, the target pixel point is used as the pixel point where the fuse is broken. Compared with determining the pixel point where the fuse is broken in the X-ray image by using a fixed gradient threshold value, the target threshold value corresponding to the pixel point can be determined according to the actual situation of the pixel point, thereby determining a more accurate fracture area.

[0076] In one embodiment, the area of ​​the fracture region can also be determined, and when the area is greater than a preset area threshold, a control instruction can be sent to a sorting device; wherein the control instruction is used to control the sorting device to remove the fuse that passes the target position at the target time from the transport device, and the transport device is used to transport the fuse along the target transport path.

[0077] The preset area threshold may be set according to the actual situation of the fuse. For example, the preset area threshold may be between 0.1% and 0.3% of the surface area of ​​the fuse.

[0078] When the area of ​​the broken region of the fuse is larger than the preset area threshold, it means that the broken fuse may affect the use of the fuse and pose a threat to the use of the fuse. Therefore, the fuses can be sorted to avoid fuses with broken regions having an area larger than the preset area threshold from being installed in the fuse.

[0079] Here, the fuses can be sorted according to the scenario of fuse transportation. For example, on the production line of completed fuses, since the transportation equipment has a certain transportation speed for the fuses and it is not convenient to sort the fuses near the X-ray image acquisition equipment, in order to take into account the sorting of the fuses and avoid re-inspection of the fuses, the sorting equipment can be set downstream of the fuse fracture detection.

[0080] In this way, the broken fuse determined by fracture detection at the current moment is the fuse that passes the target position at the target moment. The fuse that passes the target position at the target moment is taken out from the transport device, which can not only realize the sorting of broken fuses, but also enable the sorting equipment and fracture monitoring equipment to be more flexibly arranged in different spatial positions.

[0081] In one embodiment, the target time is determined in the following manner: obtaining the first position of the target fuse on the target transport path at the current moment, and obtaining the second position corresponding to the sorting device on the target transport path; obtaining the transport speed of the fuse by the transport device, and determining the target time based on the first position, the second position and the transport speed.

[0082] For example, the fracture monitoring of the fuse piece can be implemented upstream of the target transportation path, and the fuse pieces with fracture can be sorted by the sorting equipment arranged downstream of the target transportation path.

[0083] Acquiring the transport speed of the transport device for the fuse and determining the target time according to the first position, the second position and the transport speed can facilitate the sorting of broken fuses by the sorting equipment arranged downstream of the target transport path.

[0084] It should be understood that the features of some embodiments of the various applications described herein may be combined with each other, unless specifically stated otherwise.

[0085] Although terms such as "first", "second", and "third" may be used herein to describe various components, parts, regions, layers, or sections, these components, parts, regions, layers, or sections are not limited to these terms. Instead, these terms are only used to distinguish one component, part, region, layer, or section from another component, part, region, layer, or section. Therefore, without departing from the teachings of the examples described herein, the first component, part, region, layer, or section mentioned in the examples may also be referred to as the second component, part, region, layer, or section.

[0086] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description herein, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0087] In addition, the word "exemplary" is used herein to mean serving as an example, instance, or diagram. Any aspect or design described herein as "exemplary" is not necessarily to be understood as being advantageous over other aspects or designs. Instead, the use of the word exemplary is intended to present concepts in a concrete manner. As used herein, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or".

[0088] Likewise, although the present application has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. With particular regard to the various functions performed by the components (e.g., elements, resources, etc.) described above, unless otherwise noted, the terms used to describe such components are intended to correspond to any component (functionally equivalent) that performs the specific functions of the described components, even if not structurally equivalent to the disclosed structures.

[0089] Additionally, while particular features of the present application may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations as may be desired and advantageous for any given or particular application.

[0090] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application, and the specification and embodiments are only considered as exemplary.

[0091] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A method for detecting fuse fracture based on X-ray images, characterized in that: include: Acquire an X-ray image of the target fused film to be detected, and determine the gradient direction and gradient magnitude of the pixel points in the X-ray image; For a target pixel in the X-ray image, a target parameter value of the target pixel is determined according to the gradient direction and gradient magnitude of other pixels within a target range of the target pixel, wherein the target parameter value is used to characterize the probability that the target pixel is a pixel at a fracture; The target parameter value is processed by using an exponential function to obtain an exponential operation value, and a target threshold value of the target pixel point is determined according to a multiplication value of the reciprocal of the exponential operation value and a first preset gradient threshold value; When the gradient magnitude of the target pixel point is greater than the target threshold, the target pixel point is used as the pixel point where the fracture of the fuse is located, so as to obtain a fracture area composed of multiple pixel points where the fracture is located; Among them, the target parameter value corresponding to the target pixel point , norm is the normalization function; P is the first texture feature value of the target pixel, P is used to characterize the variation of the gray value of the pixel within the target range; M is the number of pixels within the target range, is the gradient size of the mth pixel within the target range, is the average value of the gradient of pixels within the target range, is a preset value greater than 0, S is the second texture feature value of the target pixel, and S is used to characterize the complexity of the gradient direction of the pixel within the target range; The first texture feature value of the target pixel , G is the gradient size of the target pixel, is the maximum gray value of the pixel within the target range. is the minimum gray value of the pixels within the target range. is a preset value greater than 0; The second texture feature value of the target pixel , N is the number of types of gradient directions of pixels within the target range, is the frequency of the nth gradient direction within the target range, and log is the logarithmic function; The target threshold of the target pixel , exp is an exponential function with a natural constant as the base, K is the target parameter value of the target pixel, A is a preset adjustment coefficient, and W is the first preset gradient threshold.

2. The method for detecting fuse fracture based on X-ray images according to claim 1, characterized in that: The method further comprises: When the gradient magnitude of the target pixel point is smaller than the target threshold and the gradient magnitude is larger than a second preset gradient threshold, determining the distance between the target pixel point and the pixel point where the fracture is located; the second preset gradient threshold is smaller than the first preset gradient threshold; When the distance is less than a preset distance threshold, the target pixel point is taken as the pixel point where the fracture is located.

3. The method for detecting fuse fracture based on X-ray images according to claim 1, characterized in that: The method further comprises: Determine the area of ​​the fractured region, and send a control instruction to the sorting device if the area of ​​the fractured region is greater than a preset area threshold; The control instruction is used to control the sorting device to take out the fuse that passes the target position at the target time from the transportation device, and the transportation device is used to transport the fuse along the target transportation path.

4. The method for detecting fuse fracture based on X-ray images according to claim 3, characterized in that: The target time is determined by: Acquire a first position of a target fuse on the target transport path at the current moment, and acquire a second position corresponding to the sorting device on the target transport path; The transport speed of the transport device for the fusible sheet is obtained, and the target time is determined according to the first position, the second position and the transport speed.

Images