Method, device and equipment for detecting the appearance of low-magnification specimens of continuous casting round billets

Abstract

The present invention provides a method, a device and equipment for detecting the appearance of a low-magnification sample of a continuous casting round billet, which belongs to the technical field of image detection. The method comprises the following steps: selecting a low-magnification sample of a continuous casting round billet from a processed low-magnification sample and a pickled low-magnification sample; collecting a complete appearance contour image of the low-magnification sample of the continuous casting round billet based on machine vision by adjusting the pixels and position of a three-dimensional camera; identifying an inner flat area and an outer flat area of ​​the appearance contour image by using a visual processor and a detection system; respectively determining the pixel coordinate points of the end positions of the inner flat area and the outer flat area, and determining the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points; determining the maximum diameter and the minimum diameter at the base circle and the minimum diameter of the inner flat area and the minimum diameter of the outer flat area through the center of the circle; determining the appearance excluding the inner flat area and the outer flat area and the appearance including the inner flat area and the outer flat area, and automatically detecting the appearance to effectively ensure the accuracy and efficiency of the detection result.

Description

Technical Field

[0001] The present invention relates to the technical field of image detection, and in particular to a method, device and equipment for detecting the appearance of a low-magnification sample of a continuous casting round billet. Background Art

[0002] The outer dimensions of continuous casting round billets are an important indicator of the supply conditions of continuous casting round billets. Affected by the tension and straightening machine and the weight of the continuous casting round billets during continuous casting production, when the cross-sectional shape of the continuous casting round billet is similar to an ellipse and the upper and lower ends are flattened, the corresponding position is called the flat area. The product standards have strict requirements on the roundness of continuous casting round billets. The current measurement method is mainly manual measurement with a ruler.

[0003] However, the manual measurement method has relatively low measurement accuracy and efficiency. Summary of the invention

[0004] The invention provides a method, a device and an apparatus for detecting the appearance of a low-magnification sample of a continuous casting round billet, which are used to solve the defects of low accuracy and low efficiency of the manual detection of the appearance of the continuous casting round billet in the prior art.

[0005] In one aspect, the present invention provides a method for detecting the appearance of a low-magnification sample of a continuous casting round billet, comprising:

[0006] Select the low-magnification sample of the continuous casting round billet from the low-magnification sample after processing and the low-magnification sample after pickling;

[0007] Based on machine vision, by adjusting the pixels and position of the three-dimensional camera, a complete outline image of the low-magnification sample of the continuous casting round billet is collected;

[0008] Using a visual processor and a detection system, identifying an inner flat region and an outer flat region of the contour image;

[0009] Determine the pixel coordinate points of the end positions of the inner flat area and the outer flat area respectively, and determine the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points;

[0010] Determine the maximum diameter and the minimum diameter at the base circle and the minimum diameter of the inner flat area and the minimum diameter of the outer flat area through the center of the circle;

[0011] Based on the maximum diameter and the minimum diameter at the base circle, the outer shape excluding the inner flat area and the outer flat area is determined; based on the maximum diameter at the base circle, the minimum diameter of the inner flat area and the minimum diameter of the outer flat area, the outer shape including the inner flat area and the outer flat area is determined.

[0012] According to a method for detecting the shape of a low-magnification sample of a continuous casting round billet provided by the present invention, the method uses a visual processor and a detection system to identify the inner flat area and the outer flat area of ​​the shape contour image, including:

[0013] Determine the flattened soft reduction area of ​​the stockpile during the production of continuous casting round billets;

[0014] Determining a curvature change of the contour image and identifying a location of curvature abnormality;

[0015] Based on the parameters of the curvature abnormality position and the flat light-pressed area, the inner flat area and the outer flat area of ​​the outer contour image are identified.

[0016] According to a method for detecting the shape of a low-magnification sample of a continuous casting round billet provided by the present invention, the inner flat area and the outer flat area of ​​the shape contour image are identified based on the parameters of the abnormal curvature position and the flat light-reduction area, including:

[0017] Determining the parameter range of the flattened soft reduction zone according to the process parameters and historical data of the continuous casting round billet;

[0018] When the parameter range of the curvature abnormal position is less than a preset value, the area corresponding to the outer contour image is identified as an outer flat area;

[0019] When the parameter range of the curvature abnormal position is greater than or equal to the preset value, the area corresponding to the outer contour image is identified as an inner flat area.

[0020] According to a method for detecting the appearance of a low-magnification sample of a continuous casting round billet provided by the present invention, after determining the parameter range of the flat light reduction area according to the process parameters and historical data of the continuous casting round billet, the method further comprises:

[0021] Collecting historical data of continuous casting round billets, and collecting historical inner flat zone data and historical outer flat zone data in the historical data;

[0022] respectively determining the curvature of the historical inner flat area data and the curvature of the historical outer flat area data;

[0023] Calculating an inner flat region average value of the curvature of the historical inner flat region data and an outer flat region average value of the curvature of the historical outer flat region data;

[0024] The average value of the inner flat area average value and the outer flat area average value is calculated as a preset value.

[0025] According to a method for detecting the appearance of a low-magnification sample of a continuous casting round billet provided by the present invention, the method is based on machine vision and collects a complete appearance contour image of the low-magnification sample of the continuous casting round billet by adjusting the pixels and position of a three-dimensional camera, including:

[0026] Determine the parameter requirements for image acquisition, and calibrate the three-dimensional camera based on the parameter requirements to eliminate lens distortion and position error;

[0027] Based on the calibrated three-dimensional camera and the size and shape of the low-magnification sample of the continuous casting round billet, the position and angle of the three-dimensional camera are adjusted, and based on the parameters of the shooting light, the exposure time and focal length are determined;

[0028] The position, the angle, the exposure time and the focal length are used as shooting parameters to collect a complete outline image of the low-magnification sample of the continuous casting round billet.

[0029] According to a method for detecting the appearance of a low-magnification sample of a continuous casting round billet provided by the present invention, the position, the angle, the exposure time and the focal length are used as shooting parameters to collect a complete appearance contour image of the low-magnification sample of the continuous casting round billet, including:

[0030] Determine a plurality of shooting points where different feature points are collected based on the position, the angle, the exposure time, and the focal length;

[0031] Through each of the shooting points, a complete outline image of the low-magnification sample of the continuous casting round billet is collected.

[0032] According to a method for detecting the appearance of a low-magnification sample of a continuous casting round billet provided by the present invention, the complete appearance contour image of the low-magnification sample of the continuous casting round billet is collected through each of the shooting points, and further includes:

[0033] Using a three-dimensional reconstruction algorithm to perform three-dimensional reconstruction on the two-dimensional contour images collected from the plurality of shooting points to obtain a three-dimensional model of the continuous casting round billet;

[0034] Smoothing the three-dimensional model of the continuous casting round billet to eliminate noise points and uneven areas;

[0035] The complete outer shape contour of the low-magnification sample of the continuous casting round billet is extracted from the three-dimensional model where noise points and uneven areas are eliminated.

[0036] A method for detecting the appearance of a low-magnification sample of a continuous casting round billet provided by the present invention also includes:

[0037] Determining the similarity of abnormal positions of the shapes of a preset number of low-magnification specimens of the continuously cast round billet;

[0038] If the similarity is greater than a preset value, the production process and equipment of the continuous casting round billet are inspected and maintained.

[0039] In another aspect, the present invention provides a device for detecting the appearance of a low-magnification sample of a continuous casting round billet, comprising:

[0040] A selection module is used to select a low-magnification sample of a continuous casting round billet from a low-magnification sample after processing and a low-magnification sample after pickling;

[0041] An acquisition module is used to acquire a complete outline image of the low-magnification sample of the continuous casting round billet based on machine vision by adjusting the pixels and position of the three-dimensional camera;

[0042] A recognition module, used to recognize the inner flat area and the outer flat area of ​​the contour image by using a visual processor and a detection system;

[0043] A determination module, for respectively determining the pixel coordinate points of the end positions of the inner flat zone and the outer flat zone, and determining the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points; determining the maximum diameter and the minimum diameter at the base circle and the minimum diameter of the inner flat zone and the minimum diameter of the outer flat zone through the center of the circle;

[0044] A detection module is used to determine an outer shape excluding the inner flat area and the outer flat area based on the maximum diameter and the minimum diameter at the base circle, and to determine an outer shape including the inner flat area and the outer flat area based on the maximum diameter at the base circle, the minimum diameter of the inner flat area and the minimum diameter of the outer flat area.

[0045] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements any of the above-described methods for detecting the shape of a low-magnification sample of a continuously cast round billet.

[0046] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for detecting the shape of a low-magnification sample of a continuously cast round billet.

[0047] On the other hand, the present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for detecting the shape of a low-magnification sample of a continuous casting round billet.

[0048] The present invention provides a method, device and equipment for detecting the appearance of a low-magnification sample of a continuous casting round billet, comprising selecting a low-magnification sample of a continuous casting round billet from a low-magnification sample after processing and a low-magnification sample after pickling; based on machine vision, by adjusting the pixels and position of a three-dimensional camera, collecting a complete appearance contour image of the low-magnification sample of the continuous casting round billet; using a visual processor and a detection system, identifying an inner flat area and an outer flat area of ​​the appearance contour image; determining the pixel coordinate points of the end positions of the inner flat area and the outer flat area respectively, and determining the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points; determining the maximum diameter and the maximum diameter at the base circle through the center of the circle. The minimum diameter and the minimum diameter of the inner flat area and the minimum diameter of the outer flat area are determined; based on the maximum diameter and the minimum diameter at the base circle, the outer shape excluding the inner flat area and the outer flat area is determined; based on the maximum diameter at the base circle, the minimum diameter of the inner flat area and the minimum diameter of the outer flat area, the outer shape including the inner flat area and the outer flat area is determined; the complete contour image is collected through machine vision, and the inner flat area and the outer flat area are automatically identified based on the detection system; the center and radius of the circle are determined by combining pixels, and the outer shape of the low-magnification sample of the continuous casting round billet is detected. Compared with the manual method, the automatic detection method can better ensure the accuracy and efficiency of the detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is a schematic diagram of the process of the method for detecting the shape of a low-magnification sample of a continuous casting round billet provided by an embodiment of the present invention;

[0051] Figure 2 2 is a schematic diagram of the structure of a low-magnification specimen shape detection device for a continuous casting round billet provided in an embodiment of the present invention;

[0052] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Combine the following Figure 1-Figure 3 The invention describes a method, device and equipment for detecting the appearance of a low-magnification sample of a continuous casting round billet.

[0055] Figure 1 It is a schematic flow chart of a method for detecting the appearance of a low-magnification sample of a continuous casting round billet provided in an embodiment of the present invention.

[0056] like Figure 1 As shown, the method for detecting the shape of a low-magnification sample of a continuous casting round billet provided in an embodiment of the present invention can be executed by a control system, and the method mainly includes the following steps:

[0057] 101. Among the low-magnification samples after processing and the low-magnification samples after pickling, select the low-magnification sample of the continuous casting round billet.

[0058] In a specific implementation process, first select the continuous casting round billet to be tested, among which the continuous casting round billet obtained from different process links can be tested, which can be the continuous casting round billet after direct processing, and can be the continuous casting round billet after pickling. The processed low-magnification specimens usually have the heat-affected zone cut off by a sawing machine and are processed into a specific size and shape. Such specimens have a relatively smooth surface, which is convenient for observation and testing. The low-magnification specimens after pickling are treated with acid etching, which can more clearly show the internal structure and defects of the billet. Pickling can remove oxides and impurities on the surface, making the internal structure of the specimen easier to observe and analyze. Therefore, both processed and pickled ones can be used as low-magnification specimens of continuous casting round billets.

[0059] When selecting low-magnification specimens of continuous casting round billets, their representativeness must also be considered. It should be ensured that the selected specimens can truly reflect the overall quality and performance of the continuous casting round billets, so as to optimize and improve the continuous casting process. Therefore, when selecting specimens, the sampling principles and regulations should be followed to ensure the representativeness and reliability of the specimens.

[0060] 102. Based on machine vision, by adjusting the pixels and position of the three-dimensional camera, the complete shape contour image of the low-magnification sample of the continuous casting round billet is collected.

[0061] Machine vision technology is used to collect the image dimensions of low-magnification samples of continuous casting round billets. Through three-dimensional camera adjustment and position adjustment, clear contour images of continuous casting round billets can be automatically obtained. The image resolution should be no less than 0.2mm / pixel and the pixel should be no less than 20 million pixels to ensure that a complete low-magnification image can be captured and the clarity of the captured image can be guaranteed.

[0062] When capturing an image, the three-dimensional camera can be adjusted based on the angle of the continuous casting round billet to ensure that the captured complete shape contour image is located at the core of the entire image, thereby ensuring the accuracy of the shape contour image.

[0063] 103. Using a visual processor and a detection system, the inner flat area and the outer flat area of ​​the contour image are identified.

[0064] After obtaining the complete contour image, the abnormal parts, namely the inner flat area and the outer flat area, can be further identified through the contour image. The inner flat area and the outer flat area refer to the positions where the roundness of the continuous casting round billet is damaged due to stacking, etc. The identification method can be to first determine the center of the contour image, then determine the radius of different positions, and determine the corresponding inner flat area and outer flat area based on different radii.

[0065] The specific process of identifying the inner flat area and the outer flat area can be, first, image preprocessing is performed to eliminate the noise in the image, including isolated pixels or small spots, and then a smoothing filter is used to reduce the details and texture in the image to make the contour clearer, and the edge detection algorithm is combined to extract the edge information of the contour, and the complete contour is extracted by tracking the edge pixels. The contour is divided into different parts or areas according to the curvature of the contour. The curvature of each point on the contour is determined, and the law of curvature change is determined. Then when the curvature is abnormal, the width of the contour of the abnormal part is determined. The part with a larger width is the outer flat area, and the smaller part is the inner flat area.

[0066] 104. Determine the pixel coordinate points of the end positions of the inner flat zone and the outer flat zone respectively, and determine the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points.

[0067] After obtaining the inner flat area and the outer flat area, determine the corresponding end positions. The specific identification of the inner flat area end can be to traverse the outer contour image, search from the inside to the outside, and find the point where the curvature or width changes significantly as the end position of the inner flat area. Start searching inward from the outermost side of the outer contour image, and also look for the point where the curvature or width changes significantly as the end position of the outer flat area. Record the pixel coordinates of the end position of the inner flat area and the pixel coordinates of the end position of the outer flat area. Use the least squares method to fit the circle to fit the entire contour or a specific part of the contour (excluding the flat area), and the center of the fitted circle is the center of the low-magnification specimen of the continuous casting round billet.

[0068] If the contour is relatively regular, the center of the circle can also be estimated directly based on the pixel coordinates of the ends of the inner and outer flat areas. For example, it can be assumed that the ends of the inner and outer flat areas are located at the two ends of the same diameter, and the diameter is determined by these two points, and then the center of the circle is determined.

[0069] 105. Determine the maximum diameter and minimum diameter at the base circle, as well as the minimum diameter of the inner flat area and the minimum diameter of the outer flat area through the center of the circle.

[0070] After the center of the circle is determined, all points on the base circle contour are traversed from the center of the circle, and the distance from each point to the center of the circle is calculated. The maximum value of the distance is used as the maximum diameter of the base circle, and the minimum value of the distance is used as the minimum diameter of the base circle part.

[0071] Identify the boundary points of the inner flat area, that is, the points where the inner flat area intersects with the base circle. Starting from the center of the circle, calculate the distances from all boundary points to the center of the circle, and find the minimum value, which is the minimum diameter of the inner flat area. Identify the boundary points of the outer flat area, that is, the points where the outer flat area intersects with the base circle. Starting from the center of the circle, calculate the distances from all boundary points to the center of the circle, and find the minimum value, which is the minimum diameter of the outer flat area.

[0072] 106. Based on the maximum diameter and the minimum diameter at the base circle, determine the outer shape excluding the inner flat area and the outer flat area; based on the maximum diameter at the base circle, the minimum diameter of the inner flat area and the minimum diameter of the outer flat area, determine the outer shape including the inner flat area and the outer flat area.

[0073] Finally, the maximum diameter and minimum diameter at the base circle can be used to determine the shape that does not include the inner flat area and the outer flat area, that is, most of the circular contour with relatively consistent curvature changes can be obtained. Then, the maximum diameter at the base circle, the minimum diameter of the inner flat area, and the minimum diameter of the outer flat area are used to determine the shape that includes the inner flat area and the outer flat area. By adding the inner flat area and the outer flat area to the shape, a complete shape that includes the inner flat area and the outer flat area is obtained, thereby obtaining the shape of a complete low-magnification sample of a continuous casting round billet, and better understanding whether the shape meets the production process requirements.

[0074] The complete contour image is collected through machine vision, and the inner flat area and the outer flat area are automatically identified based on the detection system. After the center and radius are determined by combining pixels, the shape of the low-magnification sample of the continuous casting round billet is detected. Compared with the manual method, the automatic detection method can better ensure the accuracy and efficiency of the detection results.

[0075] Furthermore, based on the above-mentioned embodiments, the visual processor and the detection system are used in this embodiment to identify the inner flat area and the outer flat area of ​​the contour image, including: determining the flat light-pressed area of ​​the stockpile during the continuous casting round billet production process; determining the curvature change of the contour image and identifying the abnormal curvature position; based on the abnormal curvature position and the parameters of the flat light-pressed area, identifying the inner flat area and the outer flat area of ​​the contour image.

[0076] Specifically, since the flat light pressure area will cause the flat area, the flat light pressure area of ​​the stockpile in the continuous casting round billet production process is first determined. After the determination, the curvature change of the entire shape contour image is identified. The curvature change of each contour point of the standard circle is the same. When the curvature changes abnormally, it indicates that a flat area has appeared. Therefore, according to the trend of the curvature change, it can be understood whether the specific flat area is an inner flat area or an outer flat area.

[0077] The parameter range of the flat light pressure area can be determined based on the process parameters and historical data of the continuous casting round billet, that is, the flat range caused by normal dead weight or other factors should be a reasonable area, and the product can be directly considered scrapped if it exceeds the reasonable area. Therefore. Only within this reasonable parameter range can the inner flat area and the outer flat area be judged. When the parameter range of the curvature abnormal position is less than the preset value, the area corresponding to the outer contour image is identified as the outer flat area; when the parameter range of the curvature abnormal position is greater than or equal to the preset value, the area corresponding to the outer contour image is identified as the inner flat area. The inner flat area and the outer flat area can be accurately understood by the size of the curvature change.

[0078] Before identification, it usually includes collecting historical data of continuous casting round billets, and collecting historical inner flat zone data and historical outer flat zone data in the historical data. The historical data can be historical data of manual measurement, or data of normal products in the past, and the data of a preset time period is selected for comparison. The curvature of the historical inner flat zone data and the curvature of the historical outer flat zone data are determined respectively; the inner flat zone average value of the curvature of the historical inner flat zone data and the outer flat zone average value of the curvature of the historical outer flat zone data are calculated; the average value of the inner flat zone average value and the outer flat zone average value is obtained as the preset value. That is, the preset value obtained by determining the most reasonable curvature change value through a large amount of historical data can ensure that the inner flat zone and the outer flat zone obtained by comparison with the preset value are more accurate.

[0079] Furthermore, on the basis of the above-mentioned embodiments, the present embodiment is based on machine vision, and after adjusting the pixels and position of the three-dimensional camera, a complete shape contour image of the low-magnification sample of the continuous casting round billet is collected, including: determining the parameter requirements for image collection, and calibrating the three-dimensional camera based on the parameter requirements to eliminate lens distortion and position errors; adjusting the position and angle of the three-dimensional camera based on the calibrated three-dimensional camera and the size and shape of the low-magnification sample of the continuous casting round billet, and determining the exposure time and focal length based on the parameters of the shooting light; using the position, angle, exposure time and focal length as shooting parameters to collect a complete shape contour image of the low-magnification sample of the continuous casting round billet.

[0080] Specifically, a reasonable camera is selected according to the image requirements to ensure the rationality of parameters such as pixels. At the same time, the shooting parameters are adjusted according to different shooting lights to ensure that the complete contour image is finally obtained. After determining the series of parameters, multiple shooting points that collect different feature points are determined based on position, angle, exposure time and focal length; through each shooting point, a complete contour image of the low-magnification sample of the continuous casting round billet is collected. Different shooting points obtain contour images at different angles, thereby ensuring the accuracy of the final contour image.

[0081] Through each shooting point, the complete shape contour image of the low-magnification sample of the continuous casting round billet is collected, including: using a three-dimensional reconstruction algorithm to perform three-dimensional reconstruction on the two-dimensional shape contour images collected at multiple shooting points to obtain a three-dimensional model of the continuous casting round billet; that is, the continuous casting round billet is restored in three dimensions through different shooting points, and then the three-dimensional model of the continuous casting round billet is smoothed to eliminate noise and uneven areas; the complete shape contour of the low-magnification sample of the continuous casting round billet is extracted from the three-dimensional model with noise and uneven areas eliminated. The shape contour obtained by three-dimensional restoration can better ensure the integrity and accuracy of the acquired shape contour.

[0082] Furthermore, based on the above embodiment, the present embodiment also includes: determining the similarity of abnormal positions of the shapes of a preset number of low-magnification samples of continuously cast round billets; if the similarity is greater than a preset value, the production process and equipment of the continuously cast round billets are inspected and maintained.

[0083] Specifically, after obtaining the shapes of different low-magnification samples of continuous casting round billets, a statistical analysis can be performed on the preset number of shapes. If the abnormal positions of the shapes are not within a reasonable range for more than the preset number, and the abnormal positions and degree of similarity are both high, it can be determined that the continuous casting round billet is unqualified due to a failure in the production process or production equipment. Timely inspection and maintenance can be carried out to ensure the qualified rate of continuous casting round billet products.

[0084] Based on the same general inventive concept, the present invention also protects a device for detecting the appearance of a low-magnification sample of a continuously cast round billet. The device for detecting the appearance of a low-magnification sample of a continuously cast round billet provided by the present invention is described below. The device for detecting the appearance of a low-magnification sample of a continuously cast round billet described below and the method for detecting the appearance of a low-magnification sample of a continuously cast round billet described above can be referred to each other.

[0085] Figure 2 It is a schematic diagram of the structure of a low-magnification specimen shape detection device for continuous casting round billet provided in an embodiment of the present invention.

[0086] like Figure 2 As shown, this embodiment provides a low-magnification specimen shape detection device for continuous casting round billet, comprising:

[0087] A selection module 201 is used to select a low-magnification sample of a continuous casting round billet from the low-magnification sample after processing and the low-magnification sample after pickling;

[0088] The acquisition module 202 is used to acquire a complete outline image of a low-magnification sample of a continuous casting round billet based on machine vision by adjusting the pixels and position of a three-dimensional camera;

[0089] The recognition module 203 is used to recognize the inner flat area and the outer flat area of ​​the contour image by using a visual processor and a detection system;

[0090] The determination module 204 is used to determine the pixel coordinate points of the end positions of the inner flat area and the outer flat area respectively, and determine the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points; through the center of the circle, determine the maximum diameter and the minimum diameter of the base circle and the minimum diameter of the inner flat area and the minimum diameter of the outer flat area;

[0091] The detection module 205 is used to determine the outer shape excluding the inner flat area and the outer flat area based on the maximum diameter and the minimum diameter at the base circle, and to determine the outer shape including the inner flat area and the outer flat area based on the maximum diameter at the base circle, the minimum diameter of the inner flat area and the minimum diameter of the outer flat area.

[0092] Furthermore, the identification module 203 in this embodiment is specifically used for:

[0093] Determine the flattened soft reduction area of ​​the stockpile during the production of continuous casting round billets;

[0094] Determining a curvature change of the contour image and identifying a location of curvature abnormality;

[0095] Based on the parameters of the curvature abnormality position and the flat light-pressed area, the inner flat area and the outer flat area of ​​the outer contour image are identified.

[0096] Furthermore, the identification module 203 in this embodiment is specifically used for:

[0097] Determining the parameter range of the flattened soft reduction zone according to the process parameters and historical data of the continuous casting round billet;

[0098] When the parameter range of the curvature abnormal position is less than a preset value, the area corresponding to the outer contour image is identified as an outer flat area;

[0099] When the parameter range of the curvature abnormal position is greater than or equal to the preset value, the area corresponding to the outer contour image is identified as an inner flat area.

[0100] Furthermore, the identification module 203 in this embodiment is specifically used for:

[0101] Collecting historical data of continuous casting round billets, and collecting historical inner flat zone data and historical outer flat zone data in the historical data;

[0102] respectively determining the curvature of the historical inner flat area data and the curvature of the historical outer flat area data;

[0103] Calculating an inner flat region average value of the curvature of the historical inner flat region data and an outer flat region average value of the curvature of the historical outer flat region data;

[0104] The average value of the inner flat area average value and the outer flat area average value is calculated as a preset value.

[0105] Furthermore, the acquisition module 202 in this embodiment is specifically used for:

[0106] Determine the parameter requirements for image acquisition, and calibrate the three-dimensional camera based on the parameter requirements to eliminate lens distortion and position error;

[0107] Based on the calibrated three-dimensional camera and the size and shape of the low-magnification sample of the continuous casting round billet, the position and angle of the three-dimensional camera are adjusted, and based on the parameters of the shooting light, the exposure time and focal length are determined;

[0108] The position, the angle, the exposure time and the focal length are used as shooting parameters to collect a complete outline image of the low-magnification sample of the continuous casting round billet.

[0109] Furthermore, the acquisition module 202 in this embodiment is also specifically used for:

[0110] Determine a plurality of shooting points where different feature points are collected based on the position, the angle, the exposure time, and the focal length;

[0111] Through each of the shooting points, a complete outline image of the low-magnification sample of the continuous casting round billet is collected.

[0112] Furthermore, the acquisition module 202 in this embodiment is also specifically used for:

[0113] Using a three-dimensional reconstruction algorithm to perform three-dimensional reconstruction on the two-dimensional contour images collected from the plurality of shooting points to obtain a three-dimensional model of the continuous casting round billet;

[0114] Smoothing the three-dimensional model of the continuous casting round billet to eliminate noise points and uneven areas;

[0115] The complete outer shape contour of the low-magnification sample of the continuous casting round billet is extracted from the three-dimensional model where noise points and uneven areas are eliminated.

[0116] Furthermore, this embodiment also includes a statistics module, which is used to:

[0117] Determining the similarity of abnormal positions of the shapes of a preset number of low-magnification specimens of the continuously cast round billet;

[0118] If the similarity is greater than a preset value, the production process and equipment of the continuous casting round billet are inspected and maintained.

[0119] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0120] like Figure 3 As shown, the electronic device may include: a processor (processor) 310, a communication interface (Communications Interface) 320, a memory (memory) 330 and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logic instructions in the memory 330 to execute the shape detection method of the low-magnification sample of the continuous casting round billet, which includes: selecting a low-magnification sample of the continuous casting round billet from the low-magnification sample after processing and the low-magnification sample after pickling; based on machine vision, by adjusting the pixels and position of the three-dimensional camera, collecting the complete shape contour image of the low-magnification sample of the continuous casting round billet; using the visual processor and the detection system, identifying the inner flat area and the outer flat area of ​​the shape contour image; determining the pixel coordinate points of the end positions of the inner flat area and the outer flat area respectively, and determining the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points; determining the maximum diameter and the minimum diameter at the base circle and the minimum diameter of the inner flat area and the minimum diameter of the outer flat area through the center; based on the maximum diameter and the minimum diameter at the base circle, determining the shape that does not include the inner flat area and the outer flat area, and based on the maximum diameter at the base circle, the minimum diameter of the inner flat area and the minimum diameter of the outer flat area, determining the shape that includes the inner flat area and the outer flat area.

[0121] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0122] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the continuous casting round billet low-magnification sample shape detection method provided by the above methods, the method comprising: selecting a continuous casting round billet low-magnification sample from a processed low-magnification sample and a pickling low-magnification sample; based on machine vision, by adjusting the pixels and position of a three-dimensional camera, collecting a complete shape contour image of the continuous casting round billet low-magnification sample; using a visual processor and a detection system to identify the shape contour image The inner flat zone and the outer flat zone; respectively determine the pixel coordinate points of the end positions of the inner flat zone and the outer flat zone, and determine the center of the circle of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points; determine the maximum diameter and the minimum diameter at the base circle and the minimum diameter of the inner flat zone and the minimum diameter of the outer flat zone through the center; based on the maximum diameter and the minimum diameter at the base circle, determine the outer shape excluding the inner flat zone and the outer flat zone, and based on the maximum diameter at the base circle, the minimum diameter of the inner flat zone and the minimum diameter of the outer flat zone, determine the outer shape including the inner flat zone and the outer flat zone.

[0123] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the continuous casting round billet low-magnification sample shape detection method provided by the above-mentioned methods, the method comprising: selecting a continuous casting round billet low-magnification sample from a processed low-magnification sample and a pickled low-magnification sample; based on machine vision, by adjusting the pixels and position of a three-dimensional camera, collecting a complete shape contour image of the continuous casting round billet low-magnification sample; using a visual processor and a detection system, identifying an inner flat area and an outer flat area of ​​the shape contour image; and respectively determining The pixel coordinate points of the end positions of the inner flat zone and the outer flat zone are determined, and the center of the low-magnification sample of the continuously cast round billet is determined based on the pixel coordinate points; the maximum diameter and the minimum diameter at the base circle and the minimum diameter of the inner flat zone and the minimum diameter of the outer flat zone are determined through the center; based on the maximum diameter and the minimum diameter at the base circle, the outer shape excluding the inner flat zone and the outer flat zone is determined, and based on the maximum diameter at the base circle, the minimum diameter of the inner flat zone and the minimum diameter of the outer flat zone, the outer shape including the inner flat zone and the outer flat zone is determined.

[0124] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0125] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting the appearance of a low-magnification sample of a continuous casting round billet, characterized in that: include: Select the low-magnification sample of the continuous casting round billet from the low-magnification sample after processing and the low-magnification sample after pickling; Based on machine vision, by adjusting the pixels and position of the three-dimensional camera, a complete outline image of the low-magnification sample of the continuous casting round billet is collected; Using a visual processor and a detection system, identifying an inner flat region and an outer flat region of the contour image; Determine the pixel coordinate points of the end positions of the inner flat area and the outer flat area respectively, and determine the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points; Determine the maximum diameter and the minimum diameter at the base circle and the minimum diameter of the inner flat area and the minimum diameter of the outer flat area through the center of the circle; Based on the maximum diameter and the minimum diameter at the base circle, the outer shape excluding the inner flat area and the outer flat area is determined; based on the maximum diameter at the base circle, the minimum diameter of the inner flat area and the minimum diameter of the outer flat area, the outer shape including the inner flat area and the outer flat area is determined.

2. The method for detecting the appearance of a low-magnification sample of a continuous casting round billet according to claim 1, characterized in that: The method of using a visual processor and a detection system to identify the inner flat area and the outer flat area of ​​the contour image includes: Determine the flattened soft reduction area of ​​the stockpile during the production of continuous casting round billets; Determining a curvature change of the contour image and identifying a location of curvature abnormality; Based on the parameters of the curvature abnormality position and the flat light-pressed area, the inner flat area and the outer flat area of ​​the outer contour image are identified.

3. The method for detecting the appearance of a low-magnification sample of a continuous casting round billet according to claim 2, characterized in that: The step of identifying the inner flat area and the outer flat area of ​​the contour image based on the curvature abnormal position and the parameters of the flat light-pressed area comprises: Determining the parameter range of the flattened soft reduction zone according to the process parameters and historical data of the continuous casting round billet; When the parameter range of the curvature abnormal position is less than a preset value, the area corresponding to the outer contour image is identified as an outer flat area; When the parameter range of the curvature abnormal position is greater than or equal to the preset value, the area corresponding to the outer contour image is identified as an inner flat area.

4. The method for detecting the appearance of a low-magnification sample of a continuous casting round billet according to claim 3, characterized in that: After determining the parameter range of the flattened soft reduction zone according to the process parameters and historical data of the continuous casting round billet, the method further includes: Collecting historical data of continuous casting round billets, and collecting historical inner flat zone data and historical outer flat zone data in the historical data; respectively determining the curvature of the historical inner flat area data and the curvature of the historical outer flat area data; Calculating an inner flat region average value of the curvature of the historical inner flat region data and an outer flat region average value of the curvature of the historical outer flat region data; The average value of the inner flat area average value and the outer flat area average value is calculated as a preset value.

5. The method for detecting the appearance of a low-magnification sample of a continuous casting round billet according to claim 1, characterized in that: The method based on machine vision, by adjusting the pixels and position of the three-dimensional camera, collects the complete outline image of the low-magnification sample of the continuous casting round billet, including: Determine the parameter requirements for image acquisition, and calibrate the three-dimensional camera based on the parameter requirements to eliminate lens distortion and position error; Based on the calibrated three-dimensional camera and the size and shape of the low-magnification sample of the continuous casting round billet, the position and angle of the three-dimensional camera are adjusted, and based on the parameters of the shooting light, the exposure time and focal length are determined; The position, the angle, the exposure time and the focal length are used as shooting parameters to collect a complete outline image of the low-magnification sample of the continuous casting round billet.

6. The method for detecting the appearance of a low-magnification sample of a continuous casting round billet according to claim 5, characterized in that: The capturing of a complete outline image of the low-magnification sample of the continuous casting round billet using the position, the angle, the exposure time and the focal length as shooting parameters comprises: Determine a plurality of shooting points where different feature points are collected based on the position, the angle, the exposure time, and the focal length; Through each of the shooting points, a complete outline image of the low-magnification sample of the continuous casting round billet is collected.

7. The method for detecting the appearance of a low-magnification sample of a continuous casting round billet according to claim 6, characterized in that: The method of collecting a complete outline image of the low-magnification sample of the continuous casting round billet through each of the shooting points also includes: Using a three-dimensional reconstruction algorithm to perform three-dimensional reconstruction on the two-dimensional contour images collected from the plurality of shooting points to obtain a three-dimensional model of the continuous casting round billet; Smoothing the three-dimensional model of the continuous casting round billet to eliminate noise points and uneven areas; The complete outer shape contour of the low-magnification sample of the continuous casting round billet is extracted from the three-dimensional model where noise points and uneven areas are eliminated.

8. The method for detecting the appearance of a low-magnification sample of a continuous casting round billet according to any one of claims 1 to 7, characterized in that: Also includes: Determining the similarity of abnormal positions of the shapes of a preset number of low-magnification specimens of the continuously cast round billet; If the similarity is greater than a preset value, the production process and equipment of the continuous casting round billet are inspected and maintained.

9. A device for detecting the appearance of a low-magnification sample of a continuous casting round billet, characterized in that: include: A selection module is used to select a low-magnification sample of a continuous casting round billet from a low-magnification sample after processing and a low-magnification sample after pickling; An acquisition module is used to acquire a complete outline image of the low-magnification sample of the continuous casting round billet based on machine vision by adjusting the pixels and position of the three-dimensional camera; A recognition module, used to recognize the inner flat area and the outer flat area of ​​the contour image by using a visual processor and a detection system; A determination module, for respectively determining the pixel coordinate points of the end positions of the inner flat zone and the outer flat zone, and determining the center of the low-magnification sample of the continuous casting round billet based on the pixel coordinate points; determining the maximum diameter and the minimum diameter at the base circle and the minimum diameter of the inner flat zone and the minimum diameter of the outer flat zone through the center of the circle; A detection module is used to determine an outer shape excluding the inner flat area and the outer flat area based on the maximum diameter and the minimum diameter at the base circle, and to determine an outer shape including the inner flat area and the outer flat area based on the maximum diameter at the base circle, the minimum diameter of the inner flat area and the minimum diameter of the outer flat area.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for detecting the shape of a low-magnification sample of a continuously cast round billet as described in any one of claims 1 to 8 is implemented.

Images