Method and system for identifying tail position of intermediate billet of hot continuous rolling hot coil box

Abstract

The invention provides a method and system for identifying the tail position of an intermediate billet of a hot continuous rolling hot coil box, and the method comprises the steps: S1, collecting an image of the hot continuous rolling intermediate billet, and carrying out the extraction to obtain an optimal frame image; s2, preprocessing the optimal frame image, and extracting to obtain an image after the hot continuous rolling intermediate billet is rolled; s3, traversing all coordinate points of the rolled image of the hot continuous rolling intermediate billet, and establishing a coordinate point set; extracting the coordinate value of the minimum X of each coordinate point set to form a new coordinate point set; s4, according to the new coordinate point set, a tail contour fitting straight line of the hot continuous rolling intermediate billet is obtained through fitting; and calculating to obtain the tail contour motion radian of the hot continuous rolling intermediate billet, further obtaining an included angle between a tail contour fitting straight line and a preset horizontal line, judging whether the included angle is in a preset range or not, and further realizing risk control processing. The rolling stability and the product quality are remarkably improved, the scrap steel rate and the energy consumption are reduced, and meanwhile an automatic production closed loop is constructed.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of visual recognition, and particularly relates to a method and system for identifying the tail end position of an intermediate slab in a hot continuous rolling hot coil box. BACKGROUND

[0002] Patent document CN201389578Y discloses a hot coil box tail end uncoiling device, which provides a method for uncoiling the hot coil box. The method mainly relies on sensors for position feedback to identify the tail end position of the material in the hot coil box. Although this method can identify the tail end position of the material, it requires the addition of specific sensors. Compared with the traditional sensor detection method, the tail end position identification technology based on image recognition has significant advantages: Firstly, no additional physical sensors are needed, and non-contact detection can be achieved only through an industrial camera, reducing the cost of equipment modification and maintenance difficulty. Secondly, the image processing algorithm can synchronously obtain comprehensive information such as tail end edge shape and surface defects, realizing multi-dimensional quality monitoring. Finally, combined with deep learning technology, it can adapt to different material reflection characteristics, and still maintain high recognition accuracy of ±1 mm in harsh working conditions such as high temperature and dust. The system upgrade only needs software iteration, and has higher technical extendibility. This scheme effectively solves the problems of traditional methods such as sensor damage and single-point detection limitations, and provides a new path for the intelligent transformation of hot coil boxes.

[0003] The defect of this scheme is that it needs to install specific sensors, and the physical sensors may have reduced sensitivity or be damaged in harsh environments such as high temperature and dust. At the same time, due to the physical characteristics of the sensors, their accuracy may be limited.

[0004] Patent document CN108830903A discloses a steel billet position detection method based on CNN. This scheme can accurately position the steel billet to be rolled in the video monitoring device, and send rotation, cutting and other commands to the rolling lathe according to the current structure, size and position information of the steel billet, realizing high-precision steel billet autonomous rolling function in an unmanned environment, which can greatly reduce the labor cost and accident rate of the factory, and significantly improve the production efficiency. This scheme requires a large amount of data sets and cannot be quickly iterated in the optimization model stage.

[0005] This problem needs to be solved urgently. SUMMARY

[0006] In view of the defects in the prior art, the purpose of the present application is to provide a method and system for identifying the tail end position of an intermediate slab in a hot continuous rolling hot coil box.

[0007] According to the method for identifying the tail end position of an intermediate slab in a hot continuous rolling hot coil box provided by the present application, the method comprises the following steps: Step S1: collect the image of the hot continuous rolling intermediate billet, and then extract the best frame image; Step S2: pre-process the best frame image, and extract the image of the hot continuous rolling intermediate billet after coiling; Step S3: traverse all coordinate points of the image of the hot continuous rolling intermediate billet after coiling, and establish a coordinate point set; extract the coordinate value of the minimum X of each coordinate point set to form a new coordinate point set; Step S4: according to the new coordinate point set, a tail profile fitting straight line of the hot continuous rolling intermediate billet is fitted; the tail profile motion radian of the hot continuous rolling intermediate billet is calculated, and then the included angle between the tail profile fitting straight line and the predetermined horizontal line is obtained; Step S5: determine whether the included angle is in the preset range, and if the result is yes, no processing is performed; if the result is no, manual intervention is performed.

[0008] Preferably, in the step S1, a sliding window is used to compare whether the energy fluctuation calculated by the optical flow method of the front and rear images is less than or equal to a preset threshold, and if the result is yes, it is determined that the hot continuous rolling intermediate billet is in a coiling state, and the picture is collected periodically, and if the result is no, it is not completed; the period is [10, 20] milliseconds; The best frame image is the first frame picture when the hot continuous rolling intermediate billet is determined to be in a coiling state in the hot coiling box; Preferably, in the step S2, the pre-processing includes: Step A1: enhance the recognition features of the best frame image by histogram equalization to obtain a cropped image; Step A2: convert the cropped image into an HSV image, brighten the HSV image, and then extract the image of the hot continuous rolling intermediate billet after coiling; The brightening involves parameters including hue, saturation and brightness; the lower limit of the hue, saturation and brightness range is set to [0, 0, 255], and the upper limit is set to [255, 40, 255].

[0009] Preferably, in the step S3, the expression of the coordinate point set is: l n =[(x1,y), (x2,y)……(x n ,y)] Wherein, l n represents the coordinate point set; x n represents the horizontal coordinate of the nth coordinate point; y represents the vertical coordinate; The expression of the new coordinate point set is: l m =[(x 1min ,y1, x 2min ,y2)……(x nminy n )] Among them, l m Let x be the new set of coordinate points. nmin Represents the minimum X-coordinate value of the nth set of coordinate points; y n This represents the ordinate of n coordinate points.

[0010] Preferably, in step S4, the expression for the tail contour motion arc is: θ = arctan(a) (2) Where θ represents the radian of the tail contour and a represents the slope of the straight line equation; The mathematical expression for the equation of the straight line is: Y = ax + b (1) Where Y represents the ordinate of the tail contour fitting line; a represents the slope of the tail contour fitting line; x represents the abscissa of the tail contour fitting line; and b represents the intercept of the tail contour fitting line. The mathematical expression for the angle between the fitted line of the tail contour and the predetermined horizontal line is: θ deg = (3) Where, θ deg This indicates the angle between the fitted straight line of the tail contour and the predetermined horizontal line. Pi is a mathematical constant; it is the ratio of the circumference of a circle to its diameter, usually denoted as π. . It is an irrational number, with an approximate value of 3.14159.

[0011] A system for identifying the tail position of an intermediate billet in a hot-rolled coil box according to the present invention includes: Module M1: Acquires images of hot continuous rolling intermediate billets and then extracts the best frame image; Module M2: Preprocesses the best frame image to extract the image of the hot-rolled intermediate billet after coiling; Module M3: Traverse all coordinate points of the image after the hot continuous rolling intermediate billet is coiled, and establish a set of coordinate points; extract the minimum X coordinate value of each set of coordinate points to form a new set of coordinate points; Module M4: Based on the new set of coordinate points, fit the tail contour fitting line of the hot continuous rolling intermediate billet; calculate the tail contour motion arc of the hot continuous rolling intermediate billet, and then obtain the angle between the tail contour fitting line and the predetermined horizontal line. Module M5: Determines whether the included angle is within a preset range. If yes, no action is taken; if no, manual intervention is required.

[0012] Preferably, in module M1, a sliding window is used to compare whether the energy fluctuation calculated by optical flow method for the images before and after is less than or equal to a preset threshold. If the result is yes, it is determined that the hot continuous rolling intermediate billet has completed the coiling state. Images are collected periodically. If the result is no, it is not completed. The period is [10, 20], and the unit is milliseconds. The optimal frame image is the first frame image when the hot-rolled intermediate billet is determined to be in the coiled state in the hot-rolling box.

[0013] Preferably, in module M2, the preprocessing includes: Module A1: By using histogram equalization, the recognition features of the best frame image are enhanced to obtain the cropped image; Module A2: Converts the cropped image into an HSV image, brightens the HSV image, and then extracts the image of the hot-rolled intermediate billet after coiling; The parameters involved in brightening include hue, saturation, and brightness; the lower limit of the range of hue, saturation, and brightness is set to [0,0,255], and the upper limit is set to [255,40,255].

[0014] Preferably, in module M3, the expression for the set of coordinate points is: l n =[(x1,y), (x2,y)……(x n ,y)] Among them, l n Represents the set of coordinate points; x n The x-coordinate represents the x-coordinate of the nth point; the y-coordinate represents the y-coordinate. The expression for the new set of coordinate points is: l m =[(x 1min ,y1, x 2min ,y2)……(x nmin y n )] Among them, l m Let x be the new set of coordinate points. nmin Represents the minimum X-coordinate value of the nth set of coordinate points; y n This represents the ordinate of n coordinate points.

[0015] Preferably, in module M4, the expression for the tail contour motion arc is: θ = arctan(a) (2) Where θ represents the radian of the tail contour and a represents the slope of the straight line equation; The mathematical expression for the equation of the straight line is: Y = ax + b (1) Where Y represents the ordinate of the tail contour fitting line; a represents the slope of the tail contour fitting line; x represents the abscissa of the tail contour fitting line; and b represents the intercept of the tail contour fitting line. The mathematical expression for the angle between the fitted line of the tail contour and the predetermined horizontal line is: θ deg = (3) Where, θ deg This indicates the angle between the fitted straight line of the tail contour and the predetermined horizontal line. Pi is a mathematical constant, the ratio of the circumference of a circle to its diameter, usually denoted as π. . It is an irrational number, with an approximate value of 3.14159.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention achieves a technical structure that enables millimeter-level precise positioning and millisecond-level rapid response at the tail of the hot rolling mill box by employing the method of the present invention, thus solving the problems of insufficient accuracy, delayed response, and susceptibility to interference in manual identification.

[0017] 2. This invention uses histogram equalization and HSV space transformation to enhance target features, effectively eliminating environmental interference, significantly improving rolling stability and product quality, and reducing scrap rate and energy consumption.

[0018] 3. This invention fits the tail contour line using the least squares method and calculates the precise angle between it and the horizontal line using geometric operations, forming a complete automated detection closed loop, which provides key technical support for the intelligent upgrading of the steel industry.

[0019] 4. This invention uses traditional image recognition technology, which has low computational resource requirements, is simple to implement, has good real-time performance, does not require a large-scale dataset, and can perform rapid iterations during the model optimization stage. Attached Figure Description

[0020] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 A schematic diagram of the workflow provided by the present invention; Figure 2 This is a schematic diagram showing the normal angle of the tail section of the intermediate billet in the hot rolling box, as provided by the present invention. Figure 3 This is a schematic diagram illustrating an abnormal angle at the tail end of an intermediate billet in a hot rolling box, as provided by the present invention. Figure 4 This is a schematic diagram illustrating the recognition effect provided by the present invention. Detailed Implementation

[0021] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0022] This invention discloses a method for identifying the tail position of the intermediate billet in a hot-rolled coil box. This method achieves accurate positioning of the intermediate billet in a hot-rolled coil box through multimodal vision algorithm fusion. First, high-speed image acquisition is triggered by the steel bite signal, and the roll-up status is dynamically monitored and the best frame is extracted by optical flow method. Subsequently, histogram equalization and HSV spatial transformation were used to enhance target features and effectively eliminate environmental interference. Finally, the tail contour line is fitted by least squares method, and the precise angle between it and the horizontal line is calculated by geometric calculation. The angle is used as the recognition result and input into the control device, so that the control device can adjust the tail angle of the steel coil. That is, the angle between the tail contour fitted line and the predetermined horizontal line is within the threshold range of [-12°, 8°], forming a complete automated detection closed loop. Ideally, the process does not require manual intervention.

[0023] This technology significantly improves the accuracy and efficiency of traditional manual inspection and is suitable for real-time quality control in complex industrial scenarios.

[0024] A method for identifying the tail position of the intermediate billet in a hot-rolled coil box according to the present invention includes: Step 1: Connect a camera to the signal excitation during steel biting, periodically acquire images, and use the optical flow method to calculate energy fluctuations by comparing before and after images via a sliding window to determine the coiling state of the hot-rolled intermediate billet. Based on image recognition, retain the optimal position image when the hot-rolled intermediate billet completes the coiling state. The optimal position image is the best frame image. The best frame image is the first frame image when the hot-rolled intermediate billet is determined to have completed the coiling state in the hot-rolling box.

[0025] The sliding window compares 5 images before and after, the step frequency is set to 1 frame, the optical flow parameter window size is set to 5, the number of pyramid layers is set to 3, and the energy fluctuation threshold is set to 5. When the energy fluctuation does not exceed 5, the hot continuous rolling intermediate billet is determined to be in the hot coil box. Images are collected at fixed periods, with the collection period set to [10,20], in milliseconds.

[0026] Step 2: Crop the image at the optimal position. After cropping, enhance the recognition features through histogram equalization. The acquired image only covers the operating area of ​​the hot roll box equipment, thereby eliminating interference from the external environment. The contrast limit parameter of the histogram equalization method is 2.5, and the grid size parameter is set to 8*8. Step 3: Convert the cropped image into an HSV image, and extract the image of the hot continuous rolling intermediate billet after coiling by determining the hue, saturation and brightness range; set the lower limit of the hue, saturation and brightness range to [0,0,255], and the upper limit to [255,40,255]; Step 4: Traverse all coordinate points (x, y) of the image after the hot continuous rolling intermediate billet is coiled. n ,y n ), and group all coordinates with the same y-value into a set l n For each set l n Find the coordinates of the smallest X to form a new set l m , set l m The first few coordinates are fitted into a straight line equation using the least squares method, that is, a straight line is fitted based on the tail contour; Step 5: Calculate the tail angle based on the tail line and the predetermined horizontal line. Given that the slope of the straight line equation in step S4 is 'a', calculate the radian θ using the arctangent function, i.e., θ = arctan(a), and convert it into the angle θ between the tail line and the 0-degree horizontal line. deg .

[0027] Step 4 includes: Step 4.1: Fit a straight line based on the tail profile, and iterate through all coordinate points (x, y, z) of the image after the hot-rolled intermediate billet is coiled. n ,y n ), and group all coordinates with the same y-value into a set l n ,Right now: l n =[(x1,y), (x2,y)……(x n ,y)] Step 4.2: For each set l n Find the smallest X coordinates to form a new set l m ,Right now: l m =[(x 1min ,y1, x 2min ,y2)……(x nmin y n )] Step 4.3: Set l m The first few coordinates are fitted into a straight line equation using the least squares method, that is: Y = ax + b (1) Where Y represents the ordinate of the tail contour fitting line; a represents the slope of the tail contour fitting line; x represents the abscissa of the tail contour fitting line; and b represents the intercept of the tail contour fitting line. Step 5 includes: Step 5.1: Calculate the tail angle based on the tail line and the predetermined horizontal line. Given that the slope of the straight line equation in step S4 is 'a', calculate the radian θ using the arctangent function. θ = arctan(a) (2) Step 5.2: Given that the radian of formula (2) is θ, convert it into the angle θ between the tail line and the predetermined horizontal line. deg ,Right now: θ deg = (3) Where, θ deg θ represents the angle between the straight line at the tail and the predetermined horizontal line, where θ is in radians. Pi is a mathematical constant, the ratio of the circumference of a circle to its diameter, denoted as π. . It is an irrational number, with an approximate value of 3.14159. It represents the product.

[0028] The present invention also provides a system for identifying the tail position of the intermediate billet in a hot-rolled coil box. The system for identifying the tail position of the intermediate billet in a hot-rolled coil box can be implemented by performing the process steps of the method for identifying the tail position of the intermediate billet in a hot-rolled coil box. That is, those skilled in the art can understand the method for identifying the tail position of the intermediate billet in a hot-rolled coil box as a preferred embodiment of the system for identifying the tail position of the intermediate billet in a hot-rolled coil box.

[0029] A system for identifying the tail position of an intermediate billet in a hot-rolled coil box according to the present invention includes: Module M1: Acquires images of hot continuous rolling intermediate billets and then extracts the best frame image; Module M2: Preprocesses the best frame image to extract the image of the hot-rolled intermediate billet after coiling; Module M3: Traverse all coordinate points of the image after the hot continuous rolling intermediate billet is coiled, and establish a set of coordinate points; extract the minimum X coordinate value of each set of coordinate points to form a new set of coordinate points; Module M4: Based on the new set of coordinate points, fit the tail contour fitting line of the hot continuous rolling intermediate billet; calculate the tail contour motion arc of the hot continuous rolling intermediate billet, and then obtain the angle between the tail contour fitting line and the predetermined horizontal line. Module M5: Determines whether the included angle is within a preset range. If yes, no action is taken; if no, manual intervention is required.

[0030] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0031] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method for identifying the tail position of the intermediate billet in a hot-rolled coil box, characterized in that, include: Step S1: Acquire images of hot continuous rolling intermediate billets, and then extract the best frame image; Step S2: Preprocess the best frame image to extract the image of the hot-rolled intermediate billet after coiling; Step S3: Traverse all coordinate points of the image after the hot continuous rolling intermediate billet is coiled, and establish a set of coordinate points; extract the minimum X coordinate value of each set of coordinate points to form a new set of coordinate points; Step S4: Based on the new set of coordinate points, fit the tail contour fitting line of the hot continuous rolling intermediate billet; calculate the tail contour motion arc of the hot continuous rolling intermediate billet, and then obtain the angle between the tail contour fitting line and the predetermined horizontal line. Step S5: Determine whether the included angle is within a preset range. If yes, no action is taken; if no, manual intervention is required.

2. The method for identifying the tail position of the intermediate billet in a hot-rolled coil box according to claim 1, characterized in that, In step S1, a sliding window is used to compare whether the energy fluctuation calculated by optical flow method for the images before and after is less than or equal to a preset threshold. If the result is yes, it is determined that the hot continuous rolling intermediate billet has completed the coiling state. Images are collected periodically. If the result is no, it is not completed. The period is [10, 20], and the unit is milliseconds. The optimal frame image is the first frame image when the hot-rolled intermediate billet is determined to be in the coiled state in the hot-rolling box.

3. The method for identifying the tail position of the intermediate billet in a hot-rolled coil box according to claim 1, characterized in that, In step S2, the preprocessing includes: Step A1: Use histogram equalization to enhance the recognition features of the best frame image to obtain the cropped image; Step A2: Convert the cropped image into an HSV image, brighten the HSV image, and then extract the image of the hot-rolled intermediate billet after coiling; The parameters involved in brightening include hue, saturation, and brightness; the lower limit of the range of hue, saturation, and brightness is set to [0, 0, 255], and the upper limit is set to [255, 40, 255].

4. The method for identifying the tail position of the intermediate billet in a hot-rolled coil box according to claim 1, characterized in that, In step S3, the expression for the set of coordinate points is: l n =[(x1,y), (x2,y)……(x n ,and)] Among them, l n Represents the set of coordinate points; x n The x-coordinate represents the x-coordinate of the nth point; the y-coordinate represents the y-coordinate. The expression for the new set of coordinate points is: l m =[(x 1min ,y1, x 2min ,y2)……(x nmin ,y n )] Among them, l m Let x be the new set of coordinate points. nmin Represents the minimum X-coordinate value of the nth set of coordinate points; y n This represents the ordinate of n coordinate points.

5. The method for identifying the tail position of the intermediate billet in a hot-rolled coil box according to claim 1, characterized in that, In step S4, the expression for the tail contour motion arc is: θ = arctan(a) (2) Where θ represents the radian of the tail contour and a represents the slope of the straight line equation; The mathematical expression for the equation of the straight line is: Y = ax + b (1) Where Y represents the ordinate of the tail contour fitting line; a represents the slope of the tail contour fitting line; x represents the abscissa of the tail contour fitting line; and b represents the intercept of the tail contour fitting line. The mathematical expression for the angle between the fitted line of the tail contour and the predetermined horizontal line is: i deg = (3) Where, θ deg This indicates the angle between the fitted straight line of the tail contour and the predetermined horizontal line. It represents pi (π).

6. A system for identifying the tail position of the intermediate billet in a hot-rolled coil box, characterized in that, include: Module M1: Acquires images of hot continuous rolling intermediate billets and then extracts the best frame image; Module M2: Preprocesses the best frame image to extract the image of the hot-rolled intermediate billet after coiling; Module M3: Traverse all coordinate points of the image after the hot continuous rolling intermediate billet is coiled, and establish a set of coordinate points; extract the minimum X coordinate value of each set of coordinate points to form a new set of coordinate points; Module M4: Based on the new set of coordinate points, fit the tail contour fitting line of the hot continuous rolling intermediate billet; calculate the tail contour motion arc of the hot continuous rolling intermediate billet, and then obtain the angle between the tail contour fitting line and the predetermined horizontal line. Module M5: Determines whether the included angle is within a preset range. If yes, no action is taken; if no, manual intervention is required.

7. The system for identifying the tail position of the intermediate billet in a hot-rolled coil box according to claim 6, characterized in that, In module M1, a sliding window is used to compare whether the energy fluctuation calculated by optical flow method for the images before and after is less than or equal to a preset threshold. If the result is yes, it is determined that the hot continuous rolling intermediate billet has completed the coiling state. Images are collected periodically. If the result is no, it is not completed. The period is [10, 20], and the unit is milliseconds. The optimal frame image is the first frame image when the hot-rolled intermediate billet is determined to be in the coiled state in the hot-rolling box.

8. The system for identifying the tail position of the intermediate billet in a hot-rolled coil box according to claim 6, characterized in that, In module M2, the preprocessing includes: Module A1: By using histogram equalization, the recognition features of the best frame image are enhanced to obtain the cropped image; Module A2: Converts the cropped image into an HSV image, brightens the HSV image, and then extracts the image of the hot-rolled intermediate billet after coiling; The parameters involved in brightening include hue, saturation, and brightness; the lower limit of the range of hue, saturation, and brightness is set to [0, 0, 255], and the upper limit is set to [255, 40, 255].

9. The system for identifying the tail position of the intermediate billet in a hot-rolled coil box according to claim 6, characterized in that, In module M3, the expression for the set of coordinate points is: l n =[(x1,y), (x2,y)……(x n ,and)] Among them, l n Represents the set of coordinate points; x n The x-coordinate represents the x-coordinate of the nth point; the y-coordinate represents the y-coordinate. The expression for the new set of coordinate points is: l m =[(x 1min ,y1, x 2min ,y2)……(x nmin ,y n )] Among them, l m Let x be the new set of coordinate points. nmin Represents the minimum X-coordinate value of the nth set of coordinate points; y n This represents the ordinate of n coordinate points.

10. The system for identifying the tail position of the intermediate billet in a hot-rolled coil box according to claim 6, characterized in that, In module M4, the expression for the tail contour motion arc is: θ = arctan(a) (2) Where θ represents the radian of the tail contour and a represents the slope of the straight line equation; The mathematical expression for the equation of the straight line is: Y = ax + b (1) Where Y represents the ordinate of the tail contour fitting line; a represents the slope of the tail contour fitting line; x represents the abscissa of the tail contour fitting line; and b represents the intercept of the tail contour fitting line. The mathematical expression for the angle between the fitted line of the tail contour and the predetermined horizontal line is: i deg = (3) Where, θ deg This indicates the angle between the fitted straight line of the tail contour and the predetermined horizontal line. It represents pi (π).

Images