Steel coil collapse defect detection method and system and computer readable storage medium

Abstract

The invention relates to application of point cloud analysis in workpiece defect identification, in particular to a steel coil collapse defect detection method and system and a computer readable storage medium. The steel coil collapse defect detection method comprises the following steps: acquiring a steel coil point cloud; the steel coil end face inner ring contour is extracted through the steel coil point cloud; calculating the vertical height in the inner ring contour; and performing threshold judgment on the vertical height to determine whether a collapse defect exists or not. In the embodiment of the invention, the point cloud data acquired by the end face of the steel coil has certain geometric information and space structure, the inner ring contour and vertical height information of the steel coil can be extracted through a simple point cloud processing algorithm, and a complex deep learning technology is needed when an image recognition technology is used for defect detection. The collected steel coil end face point cloud data does not contain redundant information, the algorithm is simpler, the point cloud processing speed is higher, and real-time detection with higher speed and precision can be realized.

Description

Technical Field

[0001] The present invention relates to the application of point cloud analysis in workpiece defect identification, and in particular to a steel coil collapse defect detection method, system and computer-readable storage medium. Background Art

[0002] The coil collapse defect of steel coil is also called flat coil defect, which means that the end face of the steel coil is elliptical and the vertical radius is shorter than the horizontal radius. It is formed because the steel coil is subjected to a large impact during lifting or the steel coil is placed flat or stacked, resulting in inconsistent forces on both sides and the center, causing the center to sink. The coil collapse defect will affect the correct calculation of the subsequent upper coil centering height, and also affect the yield rate of the strip steel after uncoiling and the final product condition. Discovering the coil collapse defect of steel coil and re-bundling it in time can reduce the risk of miscalculation of the upper coil centering height and improve the yield rate of strip steel.

[0003] The collapse of steel coils is a kind of geometric deformation feature. The extraction of geometric features has always been a difficulty for traditional photoelectric sensor equipment. Due to the different morphologies of collapsed steel coils, they have relied on Summary of the invention

[0004] In order to overcome the above technical problems, the present application provides a steel coil collapse defect detection method, system and computer-readable storage medium.

[0005] In a first aspect of the present application, a method for detecting a steel coil collapse defect is provided, comprising: obtaining a steel coil point cloud; extracting an inner ring contour of a steel coil end face through the steel coil point cloud; calculating a vertical height in the inner ring contour; and performing a threshold judgment on the vertical height to determine whether a coil collapse defect exists.

[0006] In a further scheme of the present application, the inner circle contour of the steel coil end face is extracted through the steel coil point cloud, including: segmenting the target plane equation of the steel coil end face in the steel coil point cloud; segmenting the target point cloud in the steel coil point cloud according to the target plane equation; obtaining the inner circle contour of the steel coil end face in the target point cloud.

[0007] In a further scheme of the present application, a target plane equation of the end face of a steel coil is segmented from a steel coil point cloud, including: randomly selecting a preset number of points from the steel coil point cloud as an initial sample point set; calculating the parameters of the plane equation based on the initial sample point set; substituting the steel coil point cloud into the obtained plane equation, calculating the distance from each point cloud to the plane, and if the distance is less than a preset distance threshold, treating the point cloud as an inner point of the plane equation; and traversing the steel coil point cloud to obtain the target plane equation.

[0008] In a further scheme of the present application, the inner circle contour of the steel coil end face in the target point cloud is obtained, including: projecting the target point cloud onto a reference plane to obtain a front view of the steel coil end face; searching for the contour in the front view of the steel coil end face to obtain multiple steel coil contours; and screening out the inner circle contour of the steel coil end face from the multiple steel coil contours.

[0009] In a further scheme of the present application, the vertical height in the inner ring contour is calculated, including: fitting an ellipse to the inner ring contour of the steel coil end face to obtain the ellipse parametric equation; extracting the short diameter length in the ellipse parametric equation, and calculating the short diameter angle based on the ellipse parametric equation; calculating the vertical height based on the short diameter length and the short diameter angle.

[0010] In a further scheme of the present application, a threshold judgment is performed on the vertical height to determine whether there is a roll collapse defect, including: when the vertical height is greater than a preset height threshold, it is determined that there is a roll collapse defect; when the vertical height is less than the preset height threshold, it is determined that there is no roll collapse defect.

[0011] In a further scheme of the present application, the inner circle contour of the steel coil end face is screened out from multiple steel coil contours, including: obtaining bounding boxes of multiple steel coil contours, where one bounding box is completely contained in another bounding box, indicating that the enclosed contour is the inner contour; extracting the innermost contour as the inner circle contour of the steel coil end face; extracting the inner circle contour of the steel coil end face and cropping it.

[0012] In the second aspect of the present application, a steel coil collapse defect detection system is also provided, including: an acquisition module, which acquires a steel coil point cloud; an extraction module, which extracts the inner circle contour of the steel coil end face through the steel coil point cloud; a calculation module, which calculates the vertical height in the inner circle contour; and a determination module, which performs a threshold judgment on the vertical height to determine whether there is a collapse defect.

[0013] Furthermore, the inner circle contour of the steel coil end face is extracted through the steel coil point cloud, including: segmenting the target plane equation of the steel coil end face in the steel coil point cloud; segmenting the target point cloud in the steel coil point cloud according to the target plane equation; and obtaining the inner circle contour of the steel coil end face in the target point cloud.

[0014] Finally, the present application also provides a computer-readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the 3D roll-up centering method as described above.

[0015] In summary, the embodiment of the present invention provides a method for detecting collapsed coil defects. After obtaining the point cloud of the steel coil, the point cloud of the steel coil is processed and the inner circle contour of the end face of the steel coil is extracted, the vertical height in the inner circle contour is calculated, and a threshold judgment is made on the vertical height to determine whether the steel coil has a tower coil defect. The point cloud data collected from the end face of the steel coil in the embodiment of the present invention already has certain geometric information and spatial structure, and the inner circle contour and vertical height information of the steel coil can be extracted through a simple point cloud processing algorithm, while the use of image recognition technology for defect detection requires complex deep learning technology. Since the collected point cloud data of the end face of the steel coil does not contain redundant information, and the algorithm is simpler, the point cloud processing speed is faster, and real-time detection with relatively fast speed and accuracy can be achieved.

[0016] Other features and advantages of the embodiments of the present invention will be described in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A flow chart of a method for detecting a steel coil collapse defect provided by an embodiment of the present invention;

[0019] Figure 2 A flow chart of step S20 in the method for detecting coil collapse defects provided by an embodiment of the present invention;

[0020] Figure 3 A flow chart of step S21 in the method for detecting a steel coil collapse defect provided in an embodiment of the present invention;

[0021] Figure 4 A flow chart of step S23 in the method for detecting a coil collapse defect provided by an embodiment of the present invention;

[0022] Figure 5 A flow chart of step S233 in the method for detecting a steel coil collapse defect provided in an embodiment of the present invention;

[0023] Figure 6 A flow chart of step S30 in the method for detecting a coil collapse defect provided by an embodiment of the present invention;

[0024] Figure 7 A flowchart of step S40 in the method for detecting a coil collapse defect provided by an embodiment of the present invention; and

[0025] Figure 8 This is a module schematic diagram of a steel coil collapse defect detection system provided in an embodiment of the present invention.

[0026] Marking Description

[0027] 100. Centering system;

[0028] 10. Laser radar; 20. Transportation device;

[0029] 30. Controller. DETAILED DESCRIPTION

[0030] In order to make the above and other features and advantages of the present application more clear, the present application is further described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments given herein are for the purpose of explaining to those skilled in the art and are only exemplary and not restrictive.

[0031] In the following description, many specific details are set forth to provide a thorough understanding of the present application. However, it is apparent to those skilled in the art that specific details need not be adopted to practice the present application. In other cases, well-known steps or operations are not described in detail to avoid blurring the present application.

[0032] The 3D roll-up centering method based on point cloud fitting provided in the embodiment of the present application can be executed by the data detection device provided in the embodiment of the present application, and the device can be configured in an electronic device.

[0033] In a general inventive concept of the present application, a steel coil point cloud is used to extract the end face contour and analyze the inner circle contour of the steel coil end face. Compared with visual equipment, it has significant advantages in extracting and processing geometric features. The point cloud data collected based on the lidar can accurately depict the three-dimensional shape of the steel coil, and the degree of steel coil collapse can be depicted by quantitatively analyzing the degree of deformation of the steel coil column on the end face compared to the standard column, thereby providing a basis for judging whether the collapse phenomenon exists.

[0034] See also Figure 1 , Figure 1 This is a flow chart of a method for detecting a steel coil collapse defect provided in an embodiment of the present invention.

[0035] A first aspect of an embodiment of the present invention provides a method for detecting a steel coil collapse defect, comprising:

[0036] Step S10, obtaining the steel coil point cloud;

[0037] Step S20, extracting the inner circle contour of the steel coil end surface through the steel coil point cloud;

[0038] Step S30, calculating the vertical height of the inner circle contour;

[0039] Step S40: Perform a threshold judgment on the vertical height to determine whether there is a roll collapse defect.

[0040] It can be understood that the steel coil is scanned using a laser radar or optical camera to obtain the three-dimensional point cloud data of the steel coil. The point cloud data can be saved in standard PLY, STL, OBJ and other formats. The point cloud data is then converted into an image on a two-dimensional plane, and the circular contour (also called the inner contour) on the end face of the steel coil is extracted through image processing technology. Algorithms such as Hough transform, edge detection, and segmentation can be used.

[0041] For each point, the vertical distance of the plane where the inner contour is located is calculated, that is, the vertical height of the entire coil end surface. The vertical height is judged by the threshold value: according to the preset threshold, the vertical height is compared with the threshold. If the height is less than the threshold, it is judged as a coil collapse defect. Finally, the results are output: the test results are output and the area with coil collapse defects is marked.

[0042] In traditional methods, manual measurement or touch measurement using mechanical equipment is usually required. However, the non-contact measurement method of obtaining the point cloud of the steel coil can avoid physical operations of direct contact with the steel coil, reduce potential risks of injury, and improve work efficiency. Compared with traditional manual observation or judgment using limited image information, defect detection using steel coil point cloud data has higher data processing efficiency. The inner ring contour of the end face of the steel coil can be automatically extracted and the vertical height can be calculated through computer algorithms to quickly and accurately perform defect detection. More comprehensive data is obtained, covering the entire end face profile information of the steel coil. This helps to improve the comprehensiveness and consistency of defect detection and reduce the possibility of missed detection and misjudgment. This helps to improve the level of automation on the production line, reduce manual intervention and operating errors, and can optimize algorithms and intelligent upgrades as needed.

[0043] See also Figure 2 , Figure 2 This is a flow chart of step S20 in the steel coil collapse defect detection method provided in an embodiment of the present invention.

[0044] In step S20, the inner circle contour of the steel coil end face is extracted through the steel coil point cloud, including:

[0045] Step S21, fitting the target plane equation of the end surface of the steel coil in the steel coil point cloud;

[0046] Step S22, segmenting the target point cloud in the steel coil point cloud according to the target plane equation;

[0047] Step S23, obtaining the inner circle contour of the steel coil end face in the target point cloud.

[0048] In step S21, the target plane equation of the end face of the steel coil can be obtained by plane fitting the steel coil point cloud. This target plane equation can provide geometric information about the end face of the steel coil, such as the tilt angle, offset, etc. The shape of the steel coil can be more accurately described and analyzed by the fitted target plane equation. The steel coil point cloud is processed using a plane segmentation algorithm in the point cloud, such as the least squares method, RANSAC, etc., to obtain the target plane equation describing the end face of the steel coil.

[0049] In step S22, the target point cloud in the steel coil point cloud is segmented according to the target plane equation. By segmenting the target point cloud, the effective extraction and screening of the steel coil end surface point cloud can be achieved. This helps to remove irrelevant noise or interference points and improve the accuracy of subsequent processing and analysis.

[0050] In step S23, the inner circle contour of the steel coil end face in the target point cloud is obtained, and the circular contour of the inner circle of the steel coil end face is extracted through edge detection, curve fitting or other image processing technology. This inner circle contour can provide specific shape information about the steel coil, such as diameter, roundness, etc. By extracting the inner circle contour of the steel coil end face, the geometric characteristics of the steel coil can be more accurately analyzed and evaluated, providing basic data for subsequent defect detection and quality assessment.

[0051] See also Figure 3 , Figure 3 This is a flow chart of step S21 in the steel coil collapse defect detection method provided in an embodiment of the present invention.

[0052] In a specific embodiment, the target plane equation of the end face of the steel coil is segmented from the steel coil point cloud in step S21, including:

[0053] Step S211, randomly selecting a preset number of points from the steel coil point cloud as an initial sample point set;

[0054] Step S212, calculating the parameters of the plane equation according to the initial sample point set;

[0055] Step S213, substituting the steel coil point cloud into the obtained plane equation, calculating the distance from each point cloud to the plane, and if the distance is less than a preset distance threshold, the point cloud is regarded as an interior point of the plane equation;

[0056] Step S214, traverse the steel coil point cloud to obtain the target plane equation.

[0057] It can be understood that the initial sample point set selection: in step S211, a preset number of points are randomly selected from the steel coil point cloud as the initial sample point set. This helps to obtain representative sample points and can better cover the features of the entire steel coil end surface. By reasonably selecting the initial sample point set, the accuracy and stability of the plane fitting can be improved; in step S212, the parameters of the plane equation are calculated according to the initial sample point set. By mathematically calculating and optimizing the sample point set, the parameters of the plane equation, namely the normal vector of the plane and the offset from the origin, can be determined. This plane equation can accurately describe the geometric shape of the steel coil end surface and provide a basis for subsequent point cloud segmentation and contour extraction; in step S213, the steel coil point cloud is substituted into the plane equation to calculate the distance from each point cloud to the plane. By setting a preset distance threshold, it can be determined whether each point cloud is an inner point or an outer point of the plane equation. In this way, the inner points that meet the plane characteristics can be effectively screened out, noise and abnormal points can be removed, and the accuracy and stability of plane fitting can be improved. In step S214, the steel coil point cloud is traversed to obtain the target plane equation. Through iterative calculation and optimization, the final target plane equation can be determined, which can more accurately describe the geometric characteristics of the steel coil end surface. This target plane equation is the basis for subsequent segmentation and contour extraction, providing reliable geometric information for further analysis and processing.

[0058] For example, 10 initial sample points are selected from the point cloud data of the steel coil as the initial sample point set and a plane is fitted to obtain the parameters of the plane equation. Assume that the plane equation after fitting is: ax+by+cz+d=0, where (a, b, c) is the normal vector, (x, y, z) is the coordinate of the point, and d is the distance constant. Next, substitute each point in the steel coil point cloud into the plane equation and calculate the distance from each point to the plane. Assuming that the coordinates of a point P are (xp, yp, zp), the distance from point P to the plane is: distance=|axp+byp+c*zp+d| / sqrt(a^2+b^2+c^2). Assume that the distance threshold is set to 0.5 (that is, when the distance from the point to the plane is less than 0.5, it is considered to be a point in the plane). By traversing the point cloud data of the entire steel coil, calculating the distance from each point to the plane, and screening out the inner points with a distance less than 0.01, the final target plane equation can be obtained.

[0059] According to the previous calculation, the equation parameters describing the target plane are obtained: ax+by+cz+d=0. Through the target plane equation, all target point clouds in the steel coil point cloud are segmented with the plane as the boundary.

[0060] See also Figure 4 , Figure 4 This is a flow chart of step S23 in the steel coil collapse defect detection method provided in an embodiment of the present invention.

[0061] In step S23, the inner circle contour of the steel coil end face in the target point cloud is obtained, including:

[0062] Step S231, projecting the target point cloud onto the reference plane to obtain a front view of the end face of the steel coil;

[0063] Step S232, searching for contours in the front view of the steel coil end surface to obtain multiple steel coil contours;

[0064] Step S233: select the inner circle contour of the steel coil end face from the multiple steel coil contours.

[0065] Step S231: Project the target point cloud onto the reference plane to obtain a front view of the steel coil end face.

[0066] Combined with the above, the three-dimensional coordinates (x, y, z) of the target point cloud are projected onto the reference plane. The z coordinate can be set to 0 to obtain the two-dimensional coordinates (x', y'). In this way, the three-dimensional point cloud is mapped to the two-dimensional plane, forming a front view of the end face of the steel coil. Using a contour detection algorithm (such as the findContours function in OpenCV) to process the front view of the end face of the steel coil, multiple contours can be obtained. A contour is a closed curve composed of a series of points, and each contour represents a specific shape.

[0067] After obtaining multiple steel coil contours, the inner circle contour of the steel coil end face can be screened out according to specific requirements. In an implementable manner, in OpenCV, the function hierarchy = cv2.findContours can be used to perform contour detection, and the hierarchical relationship between contours can be determined using the information in the hierarchy variable. Screening is performed according to the hierarchical relationship. Finally, the inner circle contour of the steel coil end face is obtained.

[0068] See also Figure 5 , Figure 5 This is a flow chart of step S233 in the steel coil collapse defect detection method provided in an embodiment of the present invention.

[0069] In an optional manner of step S233, selecting the inner circle profile of the end face of the steel coil from the multiple steel coil profiles includes:

[0070] Step S2331, obtaining bounding boxes of multiple steel coil contours, where one bounding box is completely contained in another bounding box, indicating that the bounded contour is an inner contour;

[0071] Step S2332, extract and find the innermost contour as the inner circle contour of the steel coil end face;

[0072] Step S2333, extract the inner circle contour of the steel coil end face and cut it.

[0073] It can be understood that for each contour, the position and size of its circumscribed rectangle can be obtained using the boundingRect function (in OpenCV). Then, all contours and their corresponding circumscribed rectangles are traversed and compared. If a rectangle completely contains another rectangle, it means that the contained contour is an inner contour. It should be noted that the algorithm assumes that the inner contour is always completely surrounded by the outer contour. According to step S2331, the hierarchical relationship between all contours can be determined by comparing the circumscribed rectangles. The innermost contour is not contained by any other contour. Therefore, the innermost contour can be found as the inner circle contour of the end face of the steel coil. According to step S2332, the inner circle contour of the end face of the steel coil has been found. Now it is necessary to extract the points contained in the contour from the initial point cloud data and crop them. An algorithm for determining the intersection of points and contours (such as the ray method) can be used to traverse all points and determine whether they are within the inner circle contour. For points that fall within the contour, save them to form a new point cloud data set.

[0074] See also Figure 6 , Figure 6 This is a flow chart of step S30 in the steel coil collapse defect detection method provided in an embodiment of the present invention.

[0075] The step S30 of calculating the vertical height of the inner circle profile includes:

[0076] Step S31, fitting an ellipse to the inner circle contour of the end face of the steel coil to obtain the ellipse parameter equation;

[0077] Step S32, extracting the short diameter length in the ellipse parameter equation, and calculating the short diameter angle according to the ellipse parameter equation;

[0078] Step S33, calculating the vertical height according to the short diameter length and the short diameter angle.

[0079] Use the ellipse fitting algorithm to fit the inner circle contour of the end face of the steel coil. After fitting, the parametric equation of the ellipse can be obtained. Common parameters include the center coordinates of the ellipse, the length of the major and minor axes, the rotation angle, etc. Directly obtain the length of the major and minor axes of the ellipse, and select the shorter one as the length of the minor diameter. As for the calculation of the minor diameter angle, it can be obtained by calculating the polar angle of the minor diameter in the ellipse coordinate system. According to the minor diameter length and the minor diameter angle, the vertical height can be calculated using trigonometric functions. The specific calculation method depends on the actual situation and the selection of the coordinate system. The sine function or cosine function can be used for calculation. Thus, the vertical height of the entire steel coil is obtained.

[0080] See also Figure 7 , Figure 7 This is a flow chart of step S40 in the steel coil collapse defect detection method provided in an embodiment of the present invention.

[0081] In step S40, a threshold value is judged on the vertical height to determine whether there is a roll collapse defect, including:

[0082] Step S41: when the vertical height is greater than a preset height threshold, it is determined that there is a roll collapse defect;

[0083] Step S42: When the vertical height is less than a preset height threshold, it is determined that there is no roll collapse defect.

[0084] In summary, the embodiment of the present invention provides a method for detecting the collapse defect of a steel coil. After obtaining the point cloud of the steel coil, the point cloud of the steel coil is extracted and the inner circle contour of the end face of the steel coil is extracted, the vertical height in the inner circle contour is calculated, and the vertical height is judged by a threshold value to determine whether the steel coil has a tower defect. The point cloud data collected from the end face of the steel coil in the embodiment of the present invention already has certain geometric information and spatial structure, and the inner circle contour and vertical height information of the steel coil can be extracted by a simple point cloud processing algorithm, while the use of image recognition technology for defect detection requires complex deep learning technology. Since the collected point cloud data of the end face of the steel coil does not contain redundant information, and the algorithm is simpler, the point cloud processing speed is faster, and real-time detection with relatively fast speed and accuracy can be achieved. This application extracts 10 steel coils through detection, statistically calculates the algorithm detection results, compares the actual manual field test values, and statistically calculates the single steel coil error and absolute error value. The average value of the collapsed coil inner diameter is 11.9mm (as shown in Table 1 below), which meets the production requirements.

[0085] Table 1

[0086]

[0087] See also Figure 8 , Figure 8 This is a module schematic diagram of a steel coil collapse defect detection system provided in an embodiment of the present invention.

[0088] The embodiment of the present invention further provides a coil collapse defect detection system 100, comprising:

[0089] An acquisition module 10 is used to acquire a point cloud of a steel coil;

[0090] An extraction module 20 extracts the inner circle contour of the steel coil end face through the steel coil point cloud;

[0091] A calculation module 30 calculates the vertical height in the inner circle profile;

[0092] The determination module 40 performs a threshold judgment on the vertical height to determine whether there is a roll collapse defect.

[0093] Furthermore, the inner circle contour of the steel coil end face is extracted through the steel coil point cloud, including:

[0094] Segment the target plane equation of the steel coil end surface in the steel coil point cloud;

[0095] Segment the target point cloud in the steel coil point cloud according to the target plane equation;

[0096] Get the inner circle contour of the steel coil end face in the target point cloud.

[0097] It should be understood that the specific features, operations and details described hereinabove with respect to the method of the present application may also be similarly applied to the device and system of the present application, or vice versa. In addition, each step of the method of the present application described above may be performed by a corresponding component or unit of the device or system of the present application.

[0098] It should be understood that each module / unit of the device of the present application can be implemented in whole or in part by software, hardware, firmware or a combination thereof. Each module / unit can be embedded in the processor of the electronic device or independent of the processor in the form of hardware or firmware, or can be stored in the memory of the electronic device in the form of software for the processor to call to perform the operation of each module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.

[0099] The present application also provides an electronic device, which includes a processor and a memory storing computer program instructions. When the processor executes the computer program instructions, each step of the above-mentioned method for centering a steel coil and a saddle is implemented. The electronic device can be a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities.

[0100] In one embodiment, the electronic device may include a processor, a memory, a network interface, a communication interface, etc. connected through a system bus. The processor of the electronic device may be used to provide necessary computing, processing and / or control capabilities. The memory of the electronic device may include a non-volatile storage medium and an internal memory. The non-volatile storage medium may store an operating system, a computer program, etc. The internal memory may provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the electronic device may be used to connect and communicate with external devices through a network. When the computer program is executed by the processor, the steps of the method of the present application are executed.

[0101] The present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above-mentioned method for centering a steel coil and a saddle is implemented.

[0102] Those skilled in the art will appreciate that the method steps of the present application can be completed by instructing related hardware such as electronic devices or processors through a computer program, and the computer program can be stored in a non-temporary computer-readable storage medium, and the computer program causes the steps of the present application to be executed when it is executed. Depending on the circumstances, any reference to memory, storage or other media herein may include non-volatile or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0103] The various technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by this specification as long as there is no contradiction in such combination.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting coil collapse defects, characterized in that: include: Get the point cloud of steel coil; Extracting the inner circle contour of the steel coil end face through the steel coil point cloud; Calculate the vertical height in the inner circle profile; A threshold value is judged on the vertical height to determine whether there is a roll collapse defect.

2. The method for detecting coil collapse defects according to claim 1, characterized in that: The step of extracting the inner circle contour of the steel coil end face through the steel coil point cloud comprises: Segmenting a target plane equation of the end face of the steel coil in the steel coil point cloud; Segment the target point cloud in the steel coil point cloud according to the target plane equation; The inner circle contour of the steel coil end face in the target point cloud is obtained.

3. The method for detecting coil collapse defects according to claim 2, characterized in that: The target plane equation for segmenting the end surface of the steel coil in the steel coil point cloud includes: Randomly select a preset number of points from the steel coil point cloud as an initial sample point set; Calculate the parameters of the plane equation based on the initial sample point set; Substitute the steel coil point cloud into the obtained plane equation, calculate the distance from each point cloud to the plane, and if the distance is less than a preset distance threshold, the point cloud is regarded as an interior point of the plane equation; Traverse the steel coil point cloud to obtain the target plane equation.

4. The method for detecting coil collapse defects according to claim 2, characterized in that: Obtaining the inner circle contour of the steel coil end face in the target point cloud includes: Projecting the target point cloud onto a reference plane to obtain a front view of the steel coil end face; Searching for a contour in the front view of the steel coil end surface to obtain a plurality of steel coil contours; The inner circle profile of the steel coil end face is selected from multiple steel coil profiles.

5. The method for detecting coil collapse defects according to claim 2, characterized in that: The calculating the vertical height in the inner circle profile comprises: Fitting an ellipse to the inner circle profile of the end face of the steel coil to obtain an ellipse parameter equation; Extract the short diameter length from the ellipse parametric equation, and calculate the short diameter angle according to the ellipse parametric equation; The vertical height is calculated according to the short diameter length and the short diameter angle.

6. The method for detecting coil collapse defects according to claim 1, characterized in that: The threshold judgment of the vertical height to determine whether there is a roll collapse defect includes: When the vertical height is greater than a preset height threshold, it is determined that there is a roll collapse defect; When the vertical height is less than a preset height threshold, it is determined that there is no roll collapse defect.

7. The method for detecting coil collapse defects according to claim 4, characterized in that: The step of selecting the inner circle profile of the end face of the steel coil from the plurality of steel coil profiles comprises: Obtain bounding boxes of multiple steel coil contours. If one bounding box is completely contained in another bounding box, it means that the enclosed contour is an inner contour. The innermost contour is extracted and found to be the inner circle contour of the steel coil end face; The inner circle contour of the steel coil end face is extracted and cut.

8. A coil collapse defect detection system, characterized in that: include: Acquisition module, obtains the point cloud of steel coil; An extraction module, for extracting the inner circle contour of the steel coil end face through the steel coil point cloud; A calculation module, calculating the vertical height in the inner circle profile; The determination module performs a threshold judgment on the vertical height to determine whether there is a roll collapse defect.

9. The coil collapse defect detection system according to claim 8, characterized in that: The step of extracting the inner circle contour of the steel coil end face through the steel coil point cloud comprises: Segmenting a target plane equation of the end face of the steel coil in the steel coil point cloud; Segment the target point cloud in the steel coil point cloud according to the target plane equation; The inner circle contour of the steel coil end face in the target point cloud is obtained.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the 3D roll-up centering method according to any one of claims 1 to 8.

Images