Intelligent detection method and device for deviation amount of cold-rolled strip steel

Abstract

The invention provides an intelligent detection method and device for the deviation amount of cold-rolled strip steel, and belongs to the technical field of data detection.The method comprises the steps that a strip steel edge line and a strip steel center line are determined based on a strip steel image; calculating a first deviation amount of the strip steel image based on the strip steel edge line and the standard edge line, and calculating a second deviation amount of the strip steel image based on the strip steel center line and the standard center line; the first deviation quantity is the deviation quantity of the edge part of the strip steel, and the second deviation quantity is the deviation quantity of the center part of the strip steel; and calculating a target deviation amount based on the first deviation amount of the strip steel image and the second deviation amount of the strip steel image. According to the intelligent detection method and device for the deviation amount of the cold-rolled strip steel, the problem that the deviation data detection accuracy of the cold-rolled strip steel is low can be solved.

Description

Technical Field

[0001] The present disclosure belongs to the field of data detection technology, and more specifically, relates to an intelligent detection method and device for the deviation of cold-rolled strip steel. Background Art

[0002] With the rapid development of modern industry, the requirements for the quality and output of cold-rolled strip steel are constantly increasing. Cold-rolled strip steel is widely used in many fields such as automobiles, home appliances, and construction, and its quality stability is directly related to the product performance of downstream industries. Strip steel deviation not only affects production efficiency, but may also lead to a decline in product quality, such as scratches on the edges of the strip steel and uneven thickness. In addition, strip steel deviation can lead to production interruptions, equipment damage, and product scrapping, thereby increasing production costs. Therefore, in order to meet the needs of industry development and reduce production costs, it is necessary to conduct in-depth research on the phenomenon of strip steel deviation and find effective solutions.

[0003] At the same time, the development of advanced sensor technology, control theory and computer simulation technology has provided new means and methods for the study of strip deviation, prompting people to conduct more in-depth research on this issue. However, the existing technology still has the problem of low accuracy in cold-rolled strip deviation data detection. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent detection method and device for the deviation of cold-rolled strip steel, so as to solve the problem of low accuracy in the detection of deviation data of cold-rolled strip steel.

[0005] A first aspect of the embodiments of the present disclosure provides an intelligent detection method for the deviation of cold-rolled strip steel, comprising: Determine the strip edge line and the strip center line based on the strip image; Calculating a first deviation amount of the steel strip image based on the steel strip edge line and the standard edge line, and calculating a second deviation amount of the steel strip image based on the steel strip center line and the standard center line; the first deviation amount is the deviation amount of the steel strip edge, and the second deviation amount is the deviation amount of the steel strip center; A target deviation amount is calculated based on the first deviation amount of the steel strip image and the second deviation amount of the steel strip image.

[0006] A second aspect of the embodiments of the present disclosure provides an intelligent detection device for the deviation of cold-rolled strip steel, comprising: A first calculation module is used to determine the edge line and center line of the strip based on the strip image; a second calculation module, configured to calculate a first deviation amount of the steel strip image based on the steel strip edge line and the standard edge line, and to calculate a second deviation amount of the steel strip image based on the steel strip center line and the standard center line; the first deviation amount is the deviation amount of the steel strip edge, and the second deviation amount is the deviation amount of the steel strip center; The third calculation module is used to calculate a target deviation amount based on the first deviation amount of the strip steel image and the second deviation amount of the strip steel image.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned method for intelligent detection of the deviation amount of cold-rolled strip when executing the computer program.

[0008] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for intelligently detecting the deviation amount of cold-rolled strip are implemented.

[0009] The beneficial effect of the intelligent detection method and device for the deviation amount of cold-rolled strip provided by the embodiments of the present disclosure is that the deviation amount is calculated by determining the edge line and the center line based on the strip image and comparing them with the standard line. This refined method can accurately capture the actual deviation conditions of different parts of the strip, avoid omissions and errors that may exist in traditional detection methods, and improve detection accuracy.

[0010] The disclosed embodiment combines the deviation amounts at the edge and center of the strip to derive the target deviation amount, which can comprehensively measure the deviation condition of the strip from an overall perspective, help to gain a deeper understanding of the operating status of the strip on the production line, and provide a more comprehensive basis for subsequent adjustments.

[0011] The disclosed embodiment effectively solves the problem of low accuracy in cold-rolled strip deviation data detection, can timely and accurately detect deviation conditions and take countermeasures, reduce product quality defects caused by strip deviation, improve the overall quality of cold-rolled strip products, improve production efficiency, and reduce production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1A schematic diagram of a flow chart of an intelligent detection method for deviation of cold-rolled strip provided in one embodiment of the present disclosure; Figure 2 A schematic diagram of the structure of an intelligent detection device for the deviation of cold-rolled strip provided by an embodiment of the present disclosure; Figure 3 A structural block diagram of an intelligent detection device for cold-rolled strip deviation provided by an embodiment of the present disclosure; Figure 4 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0014] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0015] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0016] Please refer to Figure 1 , Figure 1 A schematic flow chart of an intelligent detection method for the deviation of cold-rolled strip provided in one embodiment of the present disclosure, the method may include S101 to S103.

[0017] S101: Determine the strip edge line and the strip center line based on the strip image.

[0018] In this embodiment, determining the strip edge line and the strip center line based on the strip image includes: The strip image is segmented to obtain the strip center image and the strip edge image.

[0019] The strip edge line is determined based on the strip edge image, and the strip center line is determined based on the strip center image and the strip edge line.

[0020] In this embodiment, the strip image may include a visual image of the strip surface collected in real time on a cold-rolled strip production line by an industrial camera or other equipment, including information such as the shape, texture, and brightness of the strip, and is the basic data source for subsequent analysis and processing. The strip edge line may include the contour line of the actual edge of the strip in the image, and the strip edge line defines the boundary between the strip and the surrounding environment and equipment. The strip center line may include a virtual line located at the center of the strip width direction, which is used to measure whether the center position of the strip is offset during operation, and is an important data for calculating the deviation of the strip.

[0021] Image segmentation is an image processing technology that divides the strip image into different areas, namely the strip center image and the strip edge image, based on the differences in image features such as grayscale, color, and texture between the strip and the background, so that they can be analyzed and processed separately.

[0022] In this embodiment, the strip edge image includes two images, namely, the strip left edge image and the strip right edge image. The strip image is segmented to obtain the strip center image and the strip edge image, including: segmenting the strip image based on a preset segmentation ratio to obtain the strip center image, the strip left edge image and the strip right edge image. The strip edge line includes a left edge line and a right edge line.

[0023] In this embodiment, the preset segmentation ratio refers to a division rule preset before image segmentation. The strip image is divided in dimensions such as width according to the preset segmentation ratio, thereby distinguishing the image areas corresponding to the center, left edge, and right edge.

[0024] For example, on a cold-rolled steel strip production line, an industrial high-speed camera can be used to capture the original image of the steel strip, and the image acquisition cycle is 30 frames / s. Based on the preset segmentation ratio, the image segmentation technology is used to divide the steel strip image according to its characteristic differences in the width direction. For example, if the preset segmentation ratio is 1:3:1 (1 part for each of the left and right edges, and 3 parts for the center), the left edge image of the steel strip, the center image of the steel strip, and the right edge image of the steel strip are extracted respectively. For the edge image of the steel strip, an edge detection algorithm can be used to determine the left edge line and the right edge line of the steel strip by calculating the gradient amplitude and direction of the image, that is, accurately dividing the boundary contour between the steel strip and the surrounding environment. Based on the determined left edge line and right edge line, combined with the pixel distribution of the center image of the steel strip, for example, by calculating the pixel grayscale centroid of the center image in the width direction or using a straight line fitting algorithm, the position of the center line of the steel strip is determined.

[0025] S102: Calculate a first deviation of the strip image based on the strip edge line and the standard edge line, and calculate a second deviation of the strip image based on the strip center line and the standard center line. The first deviation is the deviation of the strip edge, and the second deviation is the deviation of the strip center.

[0026] In this embodiment, the first deviation refers to the degree of deviation of the edge line of the strip relative to the standard edge line, and the first deviation may include the distance difference between each point on the edge line of the strip and the corresponding point on the standard edge line in the horizontal or vertical direction. The second deviation refers to the degree of deviation of the center line of the strip relative to the standard center line, and the second deviation may include the distance deviation value or angle deviation value between the center line of the strip and the standard center line in a specific direction. The standard edge line and the standard center line are reference lines for the position of the strip in the ideal state, which are set according to the production process requirements and equipment standards, have no actual physical entity, and exist in the data model.

[0027] In this embodiment, the first deviation amount and the second deviation amount may include a distance deviation value and an angle deviation value, wherein the distance deviation value may include a maximum distance deviation value, a minimum distance deviation value, and an average distance deviation value.

[0028] For example, in the production of cold-rolled steel strips, such as the production of 1 mm thick high-precision steel strips, the standard edge line and center line are set according to the equipment accuracy and process requirements. When it is detected that the left or right edge line of the steel strip has an average deviation of 2 mm, a maximum deviation of 3 mm, and a minimum deviation of 1 mm in the horizontal direction relative to the standard edge line (the first deviation), and the center line of the steel strip has an average deviation of 1 mm, a maximum deviation of 2 mm, and a minimum deviation of 0.3 mm (the second deviation) relative to each point of the standard center line, wherein the average deviation exceeds the preset deviation range of ±1 mm, and the maximum deviation exceeds the preset deviation range of ±1.8 mm, the deviation correction device will be activated, such as adjusting the roller position or the strip tension, to return the strip to its normal position.

[0029] S103: Calculate a target deviation amount based on the first deviation amount of the strip steel image and the second deviation amount of the strip steel image.

[0030] In this embodiment, the target deviation amount is a quantitative indicator that comprehensively reflects the overall deviation status of the strip steel, and is used to intuitively evaluate whether the position deviation degree of the strip steel in the production process meets the production requirements.

[0031] Exemplarily, the deviation data of the edge and the center of the strip image are obtained respectively, that is, the first deviation and the second deviation. According to the preset weight allocation rule, the first deviation and the second deviation are weighted and summed. For example, if it is considered that the edge deviation has a greater impact on the overall situation, a weight of 0.6 is allocated to the first deviation and a weight of 0.4 is allocated to the second deviation, and the target deviation is obtained by the formula "target deviation = first deviation × 0.6 + second deviation × 0.4".

[0032] For example, Figure 2 As shown, an intelligent detection device for the deviation of cold-rolled strip steel comprises: a coiler 1, a plate shape meter 2, an industrial high-speed camera 3, a rolling mill 4 and a plate 5. The plate 5 is also a strip steel.

[0033] From the above, it can be concluded that this embodiment can accurately obtain the actual position information of the strip in the production process through precise image segmentation and edge and centerline detection technology, and compare it with the standard position respectively. Small deviations at the edge or center can be detected. This refined method can accurately capture the actual deviation of different parts of the strip, avoid omissions and errors that may exist in traditional detection methods, and improve detection accuracy.

[0034] This embodiment sets detailed parameters for the first deviation amount and the second deviation amount, including maximum, minimum and average distance deviation values ​​and angle deviation values, so that the assessment of the strip deviation is more comprehensive and scientific, and can provide richer and more accurate data support for subsequent correction measures.

[0035] This embodiment adopts a weighted summation method to calculate the target deviation amount, and reasonably allocates the weights of edge and center deviation according to the actual production situation, so that the comprehensive evaluation result is more in line with the actual operating status of the strip, thereby more effectively guiding the adjustment of the correction device, ensuring that the strip maintains a stable operating trajectory on the production line, improving product quality and production efficiency, and reducing scrap rate and production costs.

[0036] In one embodiment of the present disclosure, determining a strip edge line based on a strip edge image includes: The strip edge image is segmented based on the first segmentation ratio to obtain a plurality of regional edge images, and a regional edge enhancement coefficient of each regional edge image is determined based on a pixel average value of the regional edge image.

[0037] The image fusion coefficient of each region edge image is determined based on the pixel average value of each region edge image and the pixel average value of region edge images adjacent to the region edge image.

[0038] The region edge image is processed based on the region edge enhancement coefficient and the image fusion coefficient to obtain a processed region edge image.

[0039] A first pixel matrix is ​​generated based on all processed regional edge images, and a steel strip edge line is determined based on the first pixel matrix.

[0040] In this embodiment, determining the region edge enhancement coefficient of each region edge image based on the pixel average value of the region edge image includes: The pixel stability value is calculated based on the pixel average of the edge image of each region.

[0041] The global edge enhancement coefficient is determined based on the pixel stability value, and the pixel stability value is inversely proportional to the global edge enhancement coefficient.

[0042] The global edge enhancement coefficient is adjusted based on the pixel average value of each regional edge image to obtain the regional edge enhancement coefficient of the regional edge image.

[0043] In this embodiment, the first segmentation ratio is a pre-set ratio value for dividing the strip edge image into multiple sub-regions in a specific dimension, so as to subdivide the edge image for more detailed analysis of edge features. The regional edge enhancement coefficient is a coefficient for adjusting the pixel value in the edge image of the corresponding region, and by enhancing the edge pixels of a specific region, the edge is made more prominent, which facilitates the subsequent accurate extraction of edge lines.

[0044] In this embodiment, the image fusion coefficient is used to measure the weight ratio of the edge images of adjacent regions in the fusion process, ensuring that the processed edges transition naturally and continuously between different regions, thereby improving the overall accuracy of the edge line. The pixel stability value can reflect the stability of the average pixel value in the edge image of the strip, which can be understood as a quantitative reflection of the fluctuation of the pixel value. The global edge enhancement coefficient is a basic enhancement coefficient determined based on the overall pixel stability. It also needs to be further adjusted according to the pixel stability value of each region to obtain a targeted edge enhancement coefficient, which is applied to the edge images of each region.

[0045] Exemplarily, the strip edge image is divided into a plurality of regional edge images according to the first segmentation ratio. For example, if the first segmentation ratio is 1:3:2, the edge image is divided from left to right into three sub-region images of different widths, and each sub-region has its own pixel distribution characteristics.

[0046] For each regional edge image, its pixel average value is calculated, and the standard deviation of the pixel average values ​​of all regional edge images is calculated as the pixel stability value. The smaller the standard deviation, the more stable the pixel.

[0047] The global edge enhancement coefficient is determined based on the pixel stability value, and the two are in inverse proportion. The larger the pixel stability value, the smaller the pixel change in the area, the relatively stable pixel distribution, and the clearer the edge of the area, the global edge enhancement coefficient can be appropriately reduced to retain more of the real features of the area.

[0048] The smaller the pixel stability value is, the greater the pixel fluctuation in the area is, the image quality may be poor or the edge may be blurred. At this time, the global edge enhancement coefficient can be increased based on the preset step size.

[0049] The global edge enhancement coefficient is further adjusted according to the pixel average value of each regional edge image to obtain the regional edge enhancement coefficient suitable for the region. For example, if the pixel average value of a certain region is high, the enhancement coefficient of the region can be appropriately reduced based on the preset step size to avoid edge distortion caused by excessive enhancement.

[0050] For example, the pixel average of each region edge image and its adjacent region edge image is calculated, and the image fusion coefficient is determined according to the difference between the two. The smaller the difference, the closer the pixel features of the two regions are, and the larger the fusion coefficient is, so that the edge transition is more natural and continuous during subsequent fusion.

[0051] The obtained regional edge enhancement coefficient is used to enhance the pixels in each regional edge image to highlight the edge pixels. Adjacent regional edge images are fused according to the image fusion coefficient to obtain a processed regional edge image. All these processed regional edge images are combined to generate a first pixel matrix. By analyzing the changes in pixel values ​​in this matrix, such as finding the location of pixel value mutations, the edge line of the strip is finally determined. For example, an edge detection algorithm can also be used to calculate on the matrix to accurately locate the line composed of edge pixels as the edge line of the strip.

[0052] This embodiment can fully consider the characteristics of different areas of the strip edge and improve the accuracy of edge detection through precise image segmentation and targeted coefficient calculation. The inverse relationship between the pixel stability value and the enhancement coefficient and the coefficient adjustment based on the pixel mean can both highlight the blurred edges and avoid excessive enhancement of the clear edges, thereby ensuring the authenticity of the edge information. Reasonable image fusion coefficients make the edge transition natural and continuous, reduce the breakage and inaccuracy of the edge line, and thus provide more reliable and accurate edge line data for subsequent strip deviation detection and other operations, thereby improving the quality control level in the cold-rolled strip production process.

[0053] In one embodiment of the present disclosure, the center line of the strip includes a first center line and a first fitting straight line. The deviation amount includes a deviation direction and a deviation value.

[0054] Determine the strip centerline based on the strip center image and the strip edge line, including: The strip width is determined based on the strip edge line, and the first center line is determined based on the strip width. The first center line is used to calculate the deviation value.

[0055] The first center line is adjusted based on the strip center image to obtain a first fitting straight line. The first fitting straight line is used to calculate the deviation direction.

[0056] In this embodiment, the first center line is the center position line determined by taking the median value of the strip width. The first fitting straight line is a fitting straight line that is optimized and adjusted based on the first center line in combination with the pixel information of the strip center image. It can more accurately reflect the actual direction of the strip center and is used to calculate the deviation amount of the direction angle. The deviation amount consists of two parts: the deviation direction and the deviation value. The deviation direction indicates the direction in which the strip deviates from the standard center position, such as horizontally to the left, vertically upward, and a deviation angle of 5 degrees; the deviation value is the quantitative value of the distance between the strip center line and the standard center line.

[0057] For example, multiple splines are divided in the horizontal direction of the strip image based on fixed intervals, each spline has an intersection with the left edge line and the right edge line respectively, the distance between the two intersections is the width of the strip at that location, and the midpoint of the two intersections is taken as a point on the center line. Repeat the above operation to obtain multiple center points, and connect the multiple center points to obtain the first center line. The first center line may not be a straight line.

[0058] Exemplarily, the standard center line is taken as the y-axis in the coordinate axis, the midpoint of the standard center line is taken as the origin, and the direction perpendicular to the standard center line through the origin is taken as the x-axis. The first center line can be adjusted by using the pixel information in the center image of the strip and fitting algorithms such as the least squares method. By analyzing the grayscale distribution, brightness change and other characteristics of the pixels in the center image, the trend direction of the pixel concentration is determined, and then the first fitting straight line is determined. The deviation direction is determined according to the positive and negative slope and size of the first fitting straight line. If the slope is positive, it means that the center of the strip has a tendency to deviate upward and to the right; the smaller the slope, the more the deviation direction is biased to the right and the greater the degree of deviation. If the calculated deviation value exceeds the allowable range of ±5 mm, or the angle between the first fitting straight line and the standard center line exceeds 3 degrees, the correction system is triggered to return the strip to the normal center position by adjusting the angle, tension and other parameters of the rollers to ensure the production quality and stability of the strip.

[0059] This embodiment determines the center line by combining the edge line of the strip with the center image of the strip, thereby improving the accuracy and reliability of the center line. Refining the deviation amount into direction and value can more accurately reflect the deviation state of the strip and provide precise guidance for correction measures. Clear deviation threshold setting and effective correction mechanism can help to correct deviation problems in a timely manner, ensure stable product quality, reduce defective rate, and improve production efficiency and economic benefits.

[0060] In one embodiment of the present disclosure, a method for intelligently detecting the deviation of cold-rolled strip steel further includes: If the target deviation is less than the third deviation, a deviation correction parameter is determined based on the target deviation, and the position of the strip is adjusted based on the deviation correction parameter; the third deviation is a preset deviation. If the target deviation amount is greater than or equal to the third deviation amount, determining first detection data based on the target deviation amount; The production parameters of the cold-rolled strip production stage are adjusted based on the first detection data.

[0061] In this embodiment, the first detection data includes multimodal strip steel data, operation data of the cold-rolled strip steel production equipment, and environmental data.

[0062] Determining first detection data based on the target deviation amount includes: If the target deviation amount is less than the fourth deviation amount, the multi-modal strip steel data and the environmental data are determined as the first detection data. The fourth deviation amount is greater than the third deviation amount.

[0063] If the deviation amount of the steel strip is greater than or equal to the fourth deviation amount, multimodal steel strip data and operation data of the cold-rolled steel strip production equipment are acquired as first detection data.

[0064] In this embodiment, adjusting the production parameters of the cold-rolled strip production stage based on the first detection data includes: In response to the first detection data being multimodal strip data and environmental data: determining a strip property offset value based on the multimodal strip data and standard strip data; if the strip property offset value is greater than a preset property offset value, adjusting production parameters of the cold rolled strip production stage based on the strip property offset value.

[0065] If the strip steel attribute offset value is less than or equal to the preset attribute offset value, the environment offset value is determined based on the environment data and the standard environment data, and the production parameters of the cold-rolled strip steel production stage are adjusted based on the environment offset value.

[0066] In response to the first detection data being the operation data of the cold-rolled steel strip production equipment: determining target adjustment data from the historical adjustment data based on the operation data of the cold-rolled steel strip production equipment and the target deviation amount, and correcting the production parameters of the cold-rolled steel strip production stage based on the target adjustment data. The historical adjustment data includes the correction data of the production parameters of the cold-rolled steel strip production stage.

[0067] In this embodiment, the third deviation amount and the fourth deviation amount are preset deviation amount thresholds. The third deviation amount is used as a limit to distinguish the severity of the strip deviation, and is used to decide whether to directly correct the strip position or further analyze the data to adjust the production parameters. The fourth deviation amount is greater than the third deviation amount, and is used to further subdivide the different ranges of the target deviation amount to determine which types of first detection data need to be analyzed.

[0068] The first detection data refers to the data set that needs to be acquired when the target deviation reaches the preset threshold. Multimodal strip data can include strip images, material properties, hardness, thickness and other data of the strip. The operation data of cold-rolled strip production equipment can include equipment operation-related data such as roll speed, rolling force, tension, etc. Environmental data can include environment-related data such as temperature and humidity, which are used to analyze the cause of deviation and guide the adjustment of production parameters.

[0069] In this embodiment, the strip steel property offset value is a quantitative value of the deviation of various strip steel properties from the standard obtained by comparing the actual multi-modal strip steel data with the standard strip steel data, reflecting the changes in the characteristics of the strip steel itself.

[0070] The preset property offset value is a pre-set limit value for measuring whether the strip property deviation is serious, and is used to determine whether to adjust the production parameters based on the strip property offset value.

[0071] The environmental deviation value is calculated based on the comparison between the actual environmental data and the standard environmental data. It reflects the quantitative value of the environmental factors deviating from the normal situation and is used to analyze the influence of the environment on the deviation of the strip.

[0072] The historical adjustment data may include data recorded when the production parameters were corrected in the cold-rolled strip production stage in the past, including the strip deviation situation and the production parameter correction situation at that time, which is used for reference and determination of the current appropriate target adjustment data.

[0073] For example, in a cold-rolled strip production workshop, a high-precision strip product with a thickness of 1 mm and a width of 500 mm is produced. The third deviation is set to 3 mm. The fourth deviation is 8 mm. In a production process, the target deviation is calculated to be 2 mm. Since it is less than the third deviation, according to the deviation direction (such as horizontal deviation to the right) and the deviation value, the correction parameter is determined to fine-tune the roller to the left by 0.5 mm, and at the same time increase the tension of the left side of the strip by 50N to return the strip to the normal position.

[0074] In another production, the target deviation was detected to be 6 mm, which was greater than the third deviation and less than the fourth deviation. At this time, multimodal strip data was obtained: the actual thickness of the strip was detected to be 1.05 mm, and the hardness was 10% higher than the standard value. Environmental data was obtained: the workshop temperature was 5°C higher than the standard temperature, and the humidity was 10% higher than the standard. These data were used as the first detection data. The strip thickness attribute offset value was calculated to be +0.05 mm, and the hardness attribute offset value was +10%. The preset attribute offset values ​​include thickness ±0.03 mm and hardness ±5%. It can be seen that the strip attribute offset value is greater than the preset attribute offset value, so the rolling process parameters were adjusted, the rolling force was reduced, and the heating temperature was appropriately reduced to return the strip thickness and hardness to the normal range, and the strip deviation problem was corrected.

[0075] In another production run, the target deviation reached 10 mm, which was greater than the fourth deviation. Multimodal strip data was obtained: all properties were basically within the standard range. Operation data of cold-rolled strip production equipment was obtained: the roller speed was found to be uneven, with a fluctuation range of ±5%, which should normally be within ±1%. Combined with the target deviation, the target adjustment data corresponding to similar situations was found from the historical adjustment data, that is, the motor controller parameters of the roller were adjusted to reduce speed fluctuations, and the parallelism of the roller was fine-tuned, which ultimately improved the strip deviation and ensured product quality and normal production.

[0076] This embodiment can accurately distinguish the degree of deviation by setting different deviation thresholds, take targeted measures, and improve processing efficiency. Collect multiple types of data according to different situations, comprehensively analyze the causes of deviation, and avoid one-sided judgment. Adjust production parameters based on multiple data such as strip properties, environment, and equipment operation to achieve refined regulation and effectively correct deviation problems. It not only ensures the quality of strip products and reduces the defective rate, but also improves production stability and reduces the risk of cost increase caused by deviation.

[0077] Corresponding to the above embodiment, an intelligent detection method for the deviation of cold-rolled strip steel is provided. Figure 2 This is a block diagram of a smart detection device for the deviation of cold-rolled strip provided by an embodiment of the present disclosure. For ease of description, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The intelligent detection device 20 for the deviation of cold-rolled strip includes: a first calculation module 21, a second calculation module 22 and a third calculation module 23.

[0078] The first calculation module 21 is used to determine the edge line and center line of the steel strip based on the steel strip image.

[0079] The second calculation module 22 is used to calculate the first deviation of the strip image based on the strip edge line and the standard edge line, and calculate the second deviation of the strip image based on the strip center line and the standard center line. The first deviation is the deviation of the strip edge, and the second deviation is the deviation of the strip center.

[0080] The third calculation module 23 is used to calculate the target deviation amount based on the first deviation amount of the strip steel image and the second deviation amount of the strip steel image.

[0081] In one embodiment of the present disclosure, the first calculation module 21 is specifically used to perform image segmentation on the strip image to obtain a strip center image and a strip edge image.

[0082] The strip edge line is determined based on the strip edge image, and the strip center line is determined based on the strip center image and the strip edge line.

[0083] In one embodiment of the present disclosure, the first calculation module 21 is specifically used to perform image segmentation on the strip edge image based on the first segmentation ratio to obtain multiple regional edge images, and determine the regional edge enhancement coefficient of the regional edge image based on the pixel average value of each regional edge image.

[0084] The image fusion coefficient of each region edge image is determined based on the pixel average value of each region edge image and the pixel average value of region edge images adjacent to the region edge image.

[0085] The region edge image is processed based on the region edge enhancement coefficient and the image fusion coefficient to obtain a processed region edge image.

[0086] A first pixel matrix is ​​generated based on all processed regional edge images, and a steel strip edge line is determined based on the first pixel matrix.

[0087] In an embodiment of the present disclosure, the first calculation module 21 is further configured to calculate a pixel stability value based on a pixel average value of each region edge image.

[0088] The global edge enhancement coefficient is determined based on the pixel stability value, and the pixel stability value is inversely proportional to the global edge enhancement coefficient.

[0089] The global edge enhancement coefficient is adjusted based on the pixel average value of each regional edge image to obtain the regional edge enhancement coefficient of the regional edge image.

[0090] In one embodiment of the present disclosure, the strip centerline includes a first centerline and a first fitting straight line. The deviation amount includes a deviation direction and a deviation value. The first calculation module 21 is further used to determine the strip width based on the strip edge line and determine the first centerline based on the strip width. The first centerline is used to calculate the deviation value.

[0091] The first center line is adjusted based on the strip center image to obtain a first fitting straight line. The first fitting straight line is used to calculate the deviation direction.

[0092] In one embodiment of the present disclosure, an intelligent detection device 20 for the deviation of cold-rolled steel strip further includes: a control module, for determining a correction parameter based on the target deviation if the target deviation is less than a third deviation, and adjusting the position of the steel strip based on the correction parameter; the third deviation is a preset deviation; If the target deviation amount is greater than or equal to the third deviation amount, determining first detection data based on the target deviation amount; The production parameters of the cold-rolled strip production stage are adjusted based on the first detection data.

[0093] In one embodiment of the present disclosure, the first detection data includes multimodal strip steel data, operation data of cold-rolled strip steel production equipment, and environmental data. The control module is specifically configured to determine the multimodal strip steel data and environmental data as the first detection data if the target deviation amount is less than a fourth deviation amount. The fourth deviation amount is greater than the third deviation amount.

[0094] If the deviation amount of the steel strip is greater than or equal to the fourth deviation amount, multimodal steel strip data and operation data of the cold-rolled steel strip production equipment are acquired as first detection data.

[0095] See also Figure 3 , Figure 3A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0096] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0097] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0098] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0099] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of an intelligent detection method for the deviation amount of cold-rolled strip provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device 300 described in the embodiments of the present disclosure, which will not be repeated here.

[0100] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0101] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0102] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0104] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0106] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0107] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. An intelligent detection method for the deviation of cold-rolled strip steel, characterized in that: include: Determine the strip edge line and the strip center line based on the strip image; Calculating a first deviation amount of the steel strip image based on the steel strip edge line and the standard edge line, and calculating a second deviation amount of the steel strip image based on the steel strip center line and the standard center line; the first deviation amount is the deviation amount of the steel strip edge, and the second deviation amount is the deviation amount of the steel strip center; A target deviation amount is calculated based on the first deviation amount of the steel strip image and the second deviation amount of the steel strip image.

2. The intelligent detection method for the deviation of cold-rolled strip according to claim 1, characterized in that: The method of determining the edge line and center line of the steel strip based on the steel strip image comprises: Perform image segmentation on the strip steel image to obtain the strip steel center image and the strip steel edge image; The strip edge line is determined based on the strip edge image, and the strip center line is determined based on the strip center image and the strip edge line.

3. The intelligent detection method for the deviation of cold-rolled strip according to claim 2, characterized in that: The step of determining the edge line of the steel strip based on the steel strip edge image comprises: Performing image segmentation on the strip edge image based on the first segmentation ratio to obtain a plurality of regional edge images, and determining a regional edge enhancement coefficient of each regional edge image based on a pixel average value of the regional edge image; Determine the image fusion coefficient of the regional edge image based on the pixel average of each regional edge image and the pixel average of the regional edge image adjacent to the regional edge image; Performing image processing on the region edge image based on the region edge enhancement coefficient and the image fusion coefficient to obtain a processed region edge image; A first pixel matrix is ​​generated based on all processed regional edge images, and a steel strip edge line is determined based on the first pixel matrix.

4. The intelligent detection method for the deviation of cold-rolled strip according to claim 3, characterized in that: The step of determining the region edge enhancement coefficient of each region edge image based on the pixel average value of the region edge image comprises: Calculate pixel stability values ​​based on the pixel average of each region edge image; Determine a global edge enhancement coefficient based on the pixel stability value; the pixel stability value is inversely proportional to the global edge enhancement coefficient; The global edge enhancement coefficient is adjusted based on the pixel average value of each regional edge image to obtain the regional edge enhancement coefficient of the regional edge image.

5. The intelligent detection method for the deviation of cold-rolled strip according to claim 3, characterized in that: The strip center line includes a first center line and a first fitting straight line; the deviation amount includes a deviation direction and a deviation value; The step of determining the center line of the steel strip based on the center image of the steel strip and the edge line of the steel strip comprises: Determine the strip width based on the strip edge line, and determine the first center line based on the strip width; the first center line is used to calculate the deviation value; The first center line is adjusted based on the center image of the steel strip to obtain a first fitting straight line; the first fitting straight line is used to calculate the deviation direction.

6. The intelligent detection method for the deviation of cold-rolled strip according to claim 1, characterized in that: Also includes: If the target deviation amount is less than the third deviation amount, determining a deviation correction parameter based on the target deviation amount, and adjusting the position of the strip based on the deviation correction parameter; The third deviation amount is a preset deviation amount; If the target deviation amount is greater than or equal to a third deviation amount, determining first detection data based on the target deviation amount; The production parameters of the cold-rolled strip production stage are adjusted based on the first detection data.

7. The intelligent detection method for the deviation of cold-rolled strip according to claim 6, characterized in that: The first detection data includes multimodal strip steel data, operation data of cold-rolled strip steel production equipment and environmental data; The determining of the first detection data based on the target deviation amount includes: If the target deviation amount is less than the fourth deviation amount, the multimodal strip steel data and the environmental data are determined as the first detection data; and the fourth deviation amount is greater than the third deviation amount; If the deviation amount of the steel strip is greater than or equal to the fourth deviation amount, multimodal steel strip data and operation data of the cold-rolled steel strip production equipment are acquired as first detection data.

8. An intelligent detection device for the deviation of cold-rolled strip, characterized in that: include: A first calculation module is used to determine the edge line and center line of the strip based on the strip image; a second calculation module, configured to calculate a first deviation amount of the steel strip image based on the steel strip edge line and the standard edge line, and to calculate a second deviation amount of the steel strip image based on the steel strip center line and the standard center line; the first deviation amount is the deviation amount of the steel strip edge, and the second deviation amount is the deviation amount of the steel strip center; The third calculation module is used to calculate a target deviation amount based on the first deviation amount of the strip steel image and the second deviation amount of the strip steel image.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images