Strip steel wave shape classification identification and quality determination method and system
By dynamically dividing the detection channels and calculating the wave type coefficient λ, combined with wave height preprocessing and characteristic parameters, the automated and real-time detection of strip steel wave defects was realized. This solved the problems of low efficiency and strong subjectivity of manual detection in the existing technology, and improved the accuracy of strip steel quality judgment and production efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-31
- Publication Date
- 2026-04-14
AI Technical Summary
In the existing technology, the detection of strip steel waviness defects relies on manual inspection, which is inefficient and highly subjective, making it difficult to achieve high precision and real-time performance. It also lacks consistency and objectivity, affecting strip steel quality and production efficiency.
By dynamically dividing the detection channels based on the strip width, calculating the wave type coefficient λ, and combining wave height preprocessing and characteristic parameters, the wave classification and quality judgment are completed automatically by computer, including wave type identification, characteristic parameter calculation and quality evaluation.
It achieves high-precision, automated, and real-time detection of strip steel waviness defects, improves the objectivity and repeatability of quality judgment, supports dynamic adjustment of the production process, and improves production efficiency and quality control level.
Smart Images

Figure CN121859093A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of steel rolling automation technology, and in particular to a method and system for strip steel wave shape classification, identification and quality judgment. Background Technology
[0002] With the rapid development of the steel industry, the market demand for high-precision, high-value-added, and high-tech strip steel products is constantly increasing. However, waviness defects in the strip steel production process have become one of the key issues affecting product quality and production efficiency. Waviness defects not only directly affect the straightness and shape quality of the strip steel, but may also cause equipment wear, reduced production efficiency, and even shutdown accidents.
[0003] The formation of strip steel waviness defects is complex and varied, involving multiple production stages and process parameters. For example, during the rolling process, uneven tension distribution, roll surface wear, and asymmetrical rolling forces can easily lead to edge waviness, center waviness, or mixed waviness defects in strip steel. In addition, uneven cooling, fluctuations in material properties, and insufficient equipment installation precision can also cause strip steel waviness defects.
[0004] Currently, the monitoring and identification of strip steel waviness defects mainly rely on manual inspection and experience-based judgment. In actual production, operators typically assess strip steel waviness defects visually or using simple measuring tools. This method is not only inefficient but also highly susceptible to human factors, lacking consistency and objectivity. Furthermore, existing waviness detection equipment falls short of the accuracy and real-time performance requirements for high-precision strip steel production, and the methods for classifying and judging the quality of different types of waviness defects remain incomplete.
[0005] The limitations of traditional methods make it difficult to standardize and automate the detection and quality evaluation of strip steel waviness defects. This not only increases production costs but also limits the competitiveness of high-value-added strip steel products. Therefore, developing a method and system capable of classifying and identifying strip steel waviness defects in real time, efficiently, and accurately, and making quality judgments, has significant industrial application value and economic implications. Summary of the Invention
[0006] To address the above problems, this invention provides a method and system for strip steel wavy shape classification, identification, and quality judgment. It aims to achieve automatic identification, accurate classification, and real-time quality judgment of strip steel wavy shape defects, thereby solving the problems of low efficiency and strong subjectivity in traditional manual inspection, as well as unclear classification and inaccurate judgment in existing methods, and improving the level of intelligent control of strip steel production quality.
[0007] In a first aspect, the present invention provides a method for classifying, identifying, and judging the quality of strip steel corrugations, comprising the following steps: S1: Dynamically divide and calculate channels based on strip width; S2: Preprocess and perform preliminary quality assessment of wave heights in all channels; S3: Develop a standard parameter table for wave shape types; S4: Use a classification and recognition algorithm to determine the type of strip steel corrugation; S5: Calculate the characteristic parameters of different strip wave shapes according to their type; S6: Determine the strip steel waviness quality based on characteristic parameters and output the determination result.
[0008] Furthermore, the specific steps for dynamically dividing the channels according to the strip width W in S1 are as follows: First, obtain the number of channels, then divide the channels. And / or, the number of channels is determined in the following manner: ; W represents the strip width, and N represents the number of channels. Δx Channel spacing; like A min ≤ Δx ≤ A max , Then the corresponding N is the target number of channels; like Δx If it is not within the channel interval range, adjust N to meet the above conditions; in, A min This represents the minimum value within the channel interval range. A max This represents the maximum value within the channel interval range. And / or, the channel division method is as follows: With the centerline of the strip as the boundary, one side is the operating side passage, the number of which is... i ; The other side is the drive-side channel, with a quantity of... j ; in, i + j = N .
[0009] Furthermore, the preprocessing of wave heights for all channels in S2 includes the following steps: Absolute height of the acquisition operation side channel H R =( h R1 , h R2 , h R3 … hRi The absolute height of the transmission side channel and the transmission side channel The minimum absolute height is obtained by traversing the path. h min : ; The relative height is obtained by subtracting the minimum value from the absolute height of all channels. H ’ R and H ’ L : ; ; The maximum relative height is obtained by traversing the path. H max and minimum value H min And calculate the mean. H average : .
[0010] Furthermore, the preliminary quality assessment of wave heights across all channels in S2 includes the following steps: If the wave height of all channels is within the stable deviation control line range B, the strip wave quality is judged to be excellent, and B≤2mm.
[0011] Furthermore, if the wave height exceeds the range of the stability deviation control line, the strip is considered to have a wave-shaped defect; The type of wave-shaped defect is determined by the wave-shaped type coefficient λ; ; D is the distance from the maximum wave height channel to the center of the strip; If 0 < λ ≤ 0.2, then it is a side wave; If 0.2 < λ < 0.3, then it is a quarter wave; If 0.3 ≤ λ < 0.8, then it is a mixed wave; If 0.8 ≤ λ ≤ 1, then it is a medium wave; And / or, ; P max This indicates the channel position corresponding to the maximum wave height. Δx This refers to the channel interval.
[0012] Furthermore, the side waves include operating side waves, transmission side waves, and double-sided waves; The operational side wave is: The wave type coefficient λ on the operating side satisfies: 0 < λ ≤ 0.2; the wave type coefficient on the transmission side is 0; The transmission side wave is: The wave type coefficient on the operating side is 0; the wave type coefficient on the transmission side satisfies: 0 < λ ≤ 0.2; The bilateral wave is: The wave type coefficient on the operating side satisfies: 0 < λ ≤ 0.2; the wave type coefficient on the transmission side satisfies: 0 < λ ≤ 0.2. And / or, the quarter wave includes an operating-side quarter wave and a drive-side quarter wave; The operational-side quarter wave is: The wave type coefficient on the operating side satisfies: 0.2 < λ < 0.3; the wave type coefficient on the transmission side is 0. The quarter wave on the transmission side is: The wave type coefficient on the operating side is 0; the wave type coefficient on the transmission side satisfies: 0.2 < λ < 0.3.
[0013] Furthermore, the characteristic parameters in S5 include the maximum wave height, wave width, and variation trend, which are used to evaluate the quality level of the wave. And / or, the maximum wave height is determined by fitting the wave channel with trigonometric functions, and the maximum wave height is accurately calculated through the fitting. : ; Where a and b are fitting parameters, and y is the strip length position; And / or, the wave width is calculated based on the position of the wave channel with the maximum height, by calculating the maximum wave height of the left and right adjacent channels respectively, until the maximum wave height is equal to or less than the average wave height of all channels, and the channel numbers of the left and right are recorded. n and m Calculate the wavy width : ; And / or, the standard deviation of the maximum wave height. The magnitude of the standard deviation is used to determine the trend of wave shape changes. Points are selected based on the fitting function of the maximum wave height, and the standard deviation is calculated. : ; Where p is the number of points taken. It is the wave height at point k.
[0014] Furthermore, S6 includes: determining whether the wave shape feature parameters are within the threshold range of the type wave shape feature parameters; if they are within the threshold range, determining that the wave shape quality is qualified; otherwise, determining that the wave shape quality is unqualified.
[0015] Secondly, the present invention also provides a strip steel corrugation classification, identification, and quality judgment system, comprising the following components: The wave pattern acquisition and processing unit is used to preprocess the wave height of the strip and to make a preliminary quality judgment on the wave pattern of the strip. The wave coefficient table specification component is used to specify standard parameter tables for wave types. The wave type determination component is used to determine the type of strip steel wave using a classification and recognition algorithm; The wave shape calculation component is used to calculate the characteristic parameters of different wave shapes according to their type. Quality assessment component, used for assessing the quality of strip steel corrugation.
[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. High classification accuracy: By dynamically dividing the detection channels based on the strip width and calculating the wave type coefficient λ based on the distance from the channel with the maximum wave height to the center of the strip, the method achieves quantitative and objective classification of wave shapes at different wave initiation positions. This method overcomes the experience dependence and subjective bias of traditional manual judgment and can accurately distinguish various wave shape types such as edge waves, middle waves, quarter waves, and mixed waves, providing a reliable basis for subsequent process adjustments.
[0017] 2. High degree of automation: The entire process, from wave height acquisition, preprocessing, feature extraction to type determination and quality evaluation, is automated by computer, significantly reducing manual labor intensity and avoiding subjective judgment differences. The system output includes key parameters such as wave type, maximum wave height, wave width, and fluctuation trend, achieving standardized and digital evaluation of strip steel wave quality and greatly improving the objectivity and repeatability of quality judgment.
[0018] 3. Good real-time performance: The proposed algorithm has a clear structure, low computational load, and good robustness and real-time processing capabilities. It can perform instant analysis and quality judgment on the wave height data collected in real time on the production line. The system can provide real-time feedback on the wave quality status, promptly detect abnormal fluctuations, and support dynamic adjustments to the production process, thereby helping to improve the online control level of strip wave quality and production efficiency. Attached Figure Description
[0019] To more clearly illustrate the technical solutions in the embodiments of this drawing or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this drawing. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.
[0020] Figure 1This is a flowchart illustrating the method described in this invention.
[0021] The purpose, features, and advantages of this accompanying drawing will be further explained in conjunction with the embodiments and with reference to the accompanying drawing. Detailed Implementation
[0022] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.
[0023] This invention provides a method for classifying and identifying the corrugation pattern of strip steel and determining its quality, such as... Figure 1 As shown, it includes the following steps: S1: Dynamically divide and calculate channels based on strip width.
[0024] Step S1-a: Obtain the strip width W The initial settings include the number of channels N (including the total number of channels on the operating side and the drive side) and the channel spacing range. A =( A min , A max Preliminary calculation of channel spacing: .
[0025] Step S1-b: Determine Δx Does it meet the requirements? A If the range is not met, then determine... Δx and A min and A max Size relationship: If Δx Less than A min Then decrease the number of channels N by 1; if Δx Greater than A max If so, increment the number of channels N by 1 and recalculate. Δx Repeat the above process iteratively until... Δx satisfy A The range.
[0026] Step S1-c: Divide the strip into operating side channels based on the center point C of the strip. R= (1, 2, 3… i ) and drive-side channel L= (1, 2, 3… j),in i + j = N .
[0027] In this embodiment, the width of strips A1 and A2 is 1600mm, and the number of channels on the operating side and the transmission side is 80.
[0028] S2: Preprocess and perform preliminary quality assessment of wave heights in all channels.
[0029] Step S2-a: Pre-process the wave height of all channels of the strip steel. The specific method is as follows: Absolute height of the acquisition operation side channel H R =( h R1 , h R2 , h R3 … h Ri The absolute height of the transmission side channel and the transmission side channel The minimum absolute height is obtained by traversing the path. h min : .
[0030] The relative height of the operating side channel is obtained by subtracting the minimum value from the absolute height of all channels. Relative height of the transmission side channel : ; .
[0031] The maximum relative height is obtained by traversing the path. H max and minimum value H min And calculate the mean. H average : .
[0032] Step S2-b: A preliminary quality assessment is made by determining whether the wave height of all channels meets the predetermined threshold. The assessment method is as follows: if the wave height of all channels is within the range B of the stable deviation control line, it is considered that the strip does not have a wave defect and the wave quality of the strip is excellent; if the wave height exceeds the range of the stable deviation control line, it is considered that the strip has a wave defect and the next assessment is carried out. The range B of the stable deviation control line is 0-2mm.
[0033] In this embodiment, the maximum wave height of all channels in A1 is 3.2 mm, and the maximum wave height of all channels in A2 is 5 mm. Based on the stability deviation control line range B, the wave quality of both A1 and A2 is determined to be suboptimal.
[0034] S3: A standard parameter table for wave types is established based on the wave type coefficient λ. There are four wave types, specifically classified as edge waves, intermediate waves, quarter waves, and mixed waves. Any coefficient combination not listed in the standard parameter table is considered a mixed wave. The established standard parameter table for wave types is as follows: Table 1 Standard Parameters for Wave Shape Types
[0035] S4: Use a classification and recognition algorithm to determine the type of strip steel wave shape.
[0036] Step S4-a: Calculate the maximum wave height in the channels on both the operating side and the transmission side. H maxR and H maxL Determine whether it exceeds the stability deviation control line range B. When the maximum wave height on either side exceeds the range, it is determined that a wave shape defect has occurred on that side.
[0037] Step S4-b: For channels with wavy defects, determine the channel location corresponding to the maximum value. P max And calculate the distance D from the channel to the center of the strip: .
[0038] Step S4-c: Calculate the wave type coefficient λ based on the distance D from the channel to the center of the strip and the strip width W. Determine the wave type based on the coefficient. .
[0039] In this embodiment, the wave type coefficient of A1 is 0.1 on the operating side and 0.1 on the transmission side; the wave type coefficient of A2 is 1 on the operating side and 1 on the transmission side. According to the standard parameter table of wave type, A1 is a double-sided wave and A2 is a medium wave.
[0040] S5: Based on the type of strip steel wave, calculate the characteristic parameters of different waves, including the maximum wave height, wave width, and variation trend, to evaluate the quality level of the wave.
[0041] Step S5-a: Calculate the maximum wave height by fitting the wave pattern channel using trigonometric functions, and accurately determine the maximum wave height through the fitting. : ; Where a and b are fitting parameters, and y is the strip length position.
[0042] Step S5-b: Calculate the wave width. Based on the location of the wave channel with the maximum height, calculate the maximum wave height of the left and right adjacent channels respectively, until the maximum wave height is equal to or less than the average wave height of all channels. Record the channel numbers of the left and right channels. n and m Calculate the wavy width : .
[0043] Step S5-c: Calculate the standard deviation of the maximum wave height. Determine the wave pattern change trend by the magnitude of the standard deviation. Select points based on the fitting function of the maximum wave height and calculate the standard deviation. : ; Where p is the number of points taken. It is the wave height at point k.
[0044] In this embodiment, the calculated characteristic parameters of A1 and A2 are shown in the table below: Table 2 Wave-shaped characteristic parameters
[0045] S6: Determine whether the wave characteristic parameters are within the threshold range of the type wave characteristic parameters. If they are within the threshold range, the wave quality is deemed qualified; otherwise, the wave quality is deemed unqualified.
[0046] In this embodiment, the feature parameters of A1 and A2 are both within the threshold range, and are therefore deemed qualified.
[0047] It should be noted that this application is not limited to the above-described embodiments. The above embodiments are merely examples, and any embodiments with the same structure and effect as the technical concept within the scope of this application are included in the technical scope of this application. Furthermore, various modifications that can be conceived by those skilled in the art to the embodiments, and other ways of constructing by combining some of the constituent elements of the embodiments, without departing from the spirit of this application, are also included in the scope of this application.
Claims
1. A method for classifying, identifying, and judging the quality of strip steel corrugations, characterized in that, Includes the following steps: S1: Dynamically divide and calculate channels based on strip width; S2: Preprocess and perform preliminary quality assessment of wave heights in all channels; S3: Develop a standard parameter table for wave shape types; S4: Use a classification and recognition algorithm to determine the type of strip steel corrugation; S5: Calculate the characteristic parameters of different strip wave shapes according to their type; S6: Determine the strip steel waviness quality based on characteristic parameters and output the determination result.
2. The method according to claim 1, characterized in that, The specific steps for dynamically dividing the channel according to the strip width W in S1 are as follows: First, obtain the number of channels, then divide the channels. And / or, the number of channels is determined in the following manner: ; W represents the strip width, and N represents the number of channels. Δx Channel spacing; like A min ≤ Δx ≤ A max , Then the corresponding N is the target number of channels; like Δx If it is not within the channel interval range, adjust N to meet the above conditions; in, A min This represents the minimum value within the channel interval range. A max This represents the maximum value within the channel interval range. And / or, the channel division method is as follows: With the centerline of the strip as the boundary, one side is the operating side passage, the number of which is... i ; The other side is the drive-side channel, with a quantity of... j ; in, i + j = N .
3. The method according to claim 2, characterized in that, The preprocessing of wave heights in all channels in S2 includes the following steps: Absolute height of the acquisition operation side channel H R = ( h R1 , h R2 , h R3 … h Ri The absolute height of the transmission side channel and the transmission side channel The minimum absolute height is obtained by traversing the path. h min : ; The relative height is obtained by subtracting the minimum value from the absolute height of all channels. and : ; ; The maximum relative height is obtained by traversing the path. H max and minimum value H min And calculate the mean. H average : 。 4. The method according to claim 1, characterized in that, The preliminary quality assessment of wave heights across all channels in S2 includes the following steps: If the wave height of all channels is within the stable deviation control line range B, the strip wave quality is judged to be excellent, and B≤2mm.
5. The method according to claim 1, characterized in that, When the wave height exceeds the range of the stability deviation control line, the strip is considered to have a wave-shaped defect. The type of wave-shaped defect is determined by the wave-shaped type coefficient λ; ; D is the distance from the maximum wave height channel to the center of the strip; If 0 < λ ≤ 0.2, then it is a side wave; If 0.2 < λ < 0.3, then it is a quarter wave; If 0.3 ≤ λ < 0.8, then it is a mixed wave; If 0.8 ≤ λ ≤ 1, then it is a medium wave; And / or, ; P max This indicates the channel position corresponding to the maximum wave height. Δx This refers to the channel interval.
6. The method according to claim 5, characterized in that, The side waves include operating side waves, transmission side waves, and double-sided waves; The operational side wave is: The wave type coefficient λ on the operating side satisfies: 0 < λ ≤ 0.2; the wave type coefficient on the transmission side is 0; The transmission side wave is: The wave type coefficient on the operating side is 0; the wave type coefficient on the transmission side satisfies: 0 < λ ≤ 0.2; The bilateral wave is: The wave type coefficient on the operating side satisfies: 0 < λ ≤ 0.2; the wave type coefficient on the transmission side satisfies: 0 < λ ≤ 0.
2. And / or, the quarter wave includes an operating-side quarter wave and a drive-side quarter wave; The operational-side quarter wave is: The wave type coefficient on the operating side satisfies: 0.2 < λ < 0.3; the wave type coefficient on the transmission side is 0. The quarter wave on the transmission side is: The wave type coefficient on the operating side is 0; the wave type coefficient on the transmission side satisfies: 0.2 < λ < 0.
3.
7. The method according to claim 1, characterized in that, The characteristic parameters in S5 include the maximum wave height, wave width, and variation trend, which are used to evaluate the quality level of the wave. And / or, the maximum wave height is determined by fitting the wave channel with trigonometric functions, and the maximum wave height is accurately calculated through the fitting. : ; Where a and b are fitting parameters, and y is the strip length position; And / or, the wave width is calculated based on the position of the wave channel with the maximum height, by calculating the maximum wave height of the left and right adjacent channels respectively, until the maximum wave height is equal to or less than the average wave height of all channels, and the channel numbers of the left and right are recorded. n and m Calculate the wavy width : ; And / or, the standard deviation of the maximum wave height. The magnitude of the standard deviation is used to determine the trend of wave shape changes. Points are selected based on the fitting function of the maximum wave height, and the standard deviation is calculated. : ; Where p is the number of points taken. It is the wave height at point k.
8. The method according to claim 1, characterized in that, S6 includes: determining whether the wave shape feature parameters are within the threshold range of the type wave shape feature parameters; if they are within the threshold range, the wave shape quality is determined to be qualified; otherwise, the wave shape quality is determined to be unqualified.
9. A strip steel corrugation classification, identification, and quality judgment system, characterized in that, The system operates based on the strip steel wave shape classification, identification, and quality judgment method according to any one of claims 1 to 8.
10. The system according to claim 9, characterized in that, Includes the following components: The wave pattern acquisition and processing unit is used to preprocess the wave height of the strip and to make a preliminary quality judgment on the wave pattern of the strip. The wave coefficient table specification component is used to specify standard parameter tables for wave types. The wave type determination component is used to determine the type of strip steel wave using a classification and recognition algorithm; The wave shape calculation component is used to calculate the characteristic parameters of different wave shapes according to their type. Quality assessment component, used for assessing the quality of strip steel corrugation.