Cold-rolled sheet shape identification method based on dynamic configuration

Abstract

The invention discloses a cold-rolled sheet shape identification method based on dynamic configuration, which comprises the following steps of: A1, setting a sheet shape detection position, limiting a sheet shape detection range according to sheet shape total measurement channel data, and enabling a steel coil to be positioned at the central position of a sheet shape measurement instrument so as to realize the theoretical accuracy of sheet shape measurement; a2, channel width position definition is carried out, the width corresponding to each channel of the plate shape is defined, and width position positioning is carried out when the wave shape is identified through the definition of the corresponding width of the channel; and A3, configuring a wave-shaped corresponding channel, configuring the wave-shaped corresponding channel corresponding to each part and the measurement value definition information of each part as the definition of the logic channel of each part. According to the method, the characteristics such as plate shape morphology and symmetry can be identified, so that the production efficiency and the production stability are improved.

Description

Technical Field

[0001] This invention relates to the field of cold rolling production, and in particular to a method for identifying the shape of cold rolled sheets based on dynamic configuration. Background Technology

[0002] Currently, the information on steel coils produced by cold rolling mills can be automatically transferred to the next process according to the contract of the finished coils. However, the existing system cannot identify the shape characteristics or defects of the steel coils. If these steel coils directly enter the next process for production, a material rejection event will occur when the next process identifies the shape abnormality, affecting the production rhythm. When steel coils with unidentified shape abnormalities enter the unit for production, they may deviate from their designated path, which may lead to the unit's shutdown or even strip breakage.

[0003] In the prior art, patent application number CN202111411754.2 discloses a method for identifying clustered defects on the surface of cold-rolled strip steel, belonging to the field of surface quality inspection technology for cold-rolled strip steel. This method first acquires surface defect data of cold-rolled strip steel detected by a surface inspection instrument, including the defect classification results, length, width, and relative position information. Then, it calculates feature quantities from the defect data to obtain a feature dataset, which is used as input to an outlier scoring algorithm based on histogram statistics. Finally, it determines whether the outlier value of the defect output by the algorithm belongs to the outlier range of typical samples. If so, the defect is a clustered defect; otherwise, it is not. This method can effectively identify clustered defects on the surface of cold-rolled strip steel, solving the problem of high false alarm rate and missed detection in automatic surface defect judgment systems caused by the classification error of clustered defects by the surface inspection instrument, thereby improving the accuracy of the system.

[0004] In the current production process, units equipped with shape measuring instruments provide shape display tools, and process personnel inspect the shape of steel coils by sampling. This method has several drawbacks: firstly, the sampling is limited, and abnormal coils may go undetected; secondly, it involves repetitive work, consuming excessive time for process personnel. Therefore, it is necessary to improve this structure to overcome these shortcomings. Summary of the Invention

[0005] The purpose of this invention is to provide a dynamically configured cold-rolled steel coil shape recognition method. This method processes the shape data of steel coils in a programmed manner, handling each coil separately according to different manufacturing processes, as each process has customized requirements for the shape. The goal is to identify steel coils with distinct shape characteristics and high production risks in advance using a universal method, providing operators with alerts during production to improve production stability and efficiency, and reduce production accidents caused by abnormal incoming material shapes.

[0006] The above-mentioned technical objective of this invention has been achieved by the following technical solutions:

[0007] A method for identifying the shape of cold-rolled steel sheets based on dynamic configuration includes the following steps:

[0008] A1: Plate shape detection position setting: Based on the total plate shape measurement channel data, the plate shape detection range is limited to ensure that the steel coil is in the center of the plate shape measuring instrument, thereby achieving the theoretical accuracy of plate shape measurement;

[0009] A2: Channel width position definition, defines the width of each channel of the plate shape, and performs width position positioning when recognizing the wave shape by defining the width of each channel;

[0010] A3: Configure the wave pattern corresponding channel, configure the wave pattern corresponding channel for each part, and define the measurement value information for each part as the definition of the logical channel for each part;

[0011] A4: Accurately measure the shape of the plate. By reading the measurement value information corresponding to each channel of the plate shape, clean and mark the abnormal data at the beginning and end of the read data to ensure that no abnormal data is mixed in after the cleaning is completed, and form complete plate shape data of the target steel coil.

[0012] A5: Based on the board shape area configuration information defined in each part of step A3, combined with the complete board shape data obtained in step A4, the actual data of the measured values ​​of each channel of the board shape are processed according to the range of the board shape identification measurement values, and assigned to the corresponding board shape logical areas, thus dividing the overall board shape into multiple parts;

[0013] A6: Combine the logical channels with the actual valid channels to obtain the number of channels corresponding to the actual steel coil, form the logical channels of each part to the actual channels, and obtain the channel number corresponding to each part;

[0014] A7: Wave data acquisition involves iteratively merging the channel waves of each part. During merging, the standard channel of the corresponding logical channel must first be selected. The standard channel is then merged with the channel of the next position to form a new standard channel. This process is repeated until the logical area of ​​each part is processed. Through the above iterative merging method, the overall wave data of each part is obtained.

[0015] A further provision of the present invention is that the wave data obtained in step A7 includes the wave shape of the left side, the wave shape of the left side mid-section, the wave shape of the middle section, the wave shape of the right side mid-section, and the wave shape of the right side, which specifically includes the following steps:

[0016] B1: Using the channel wave shape at the junction of the left side and the middle of the left side as the standard wave shape data, the entire middle of the left side is iteratively cleaned one by one. After each iteration, a new standard channel data and the remaining wave shape data are formed. Then, the new standard channel data is used for iterative cleaning until all the middle of the left side are cleaned. The wave shape of the left side and the wave shape of the middle of the left side are identified and judged.

[0017] A further provision of the present invention is that the identification and determination of the wavy shape on the left side and the wavy shape at the junction of the left side in step B1 includes the following steps:

[0018] C1: Iteratively merge the wave data after iterative cleaning. After each iteration, a new temporary wave data is formed. The temporary wave data is merged with the remaining data of the next channel until all edge-to-center junction data are merged, forming the final wave data index of the edge-to-center junction after cleaning. By the difference between the wave data index of the left edge-to-center junction before and after cleaning, it is determined whether the left edge-to-center junction wave is a continuation wave. If there is no change before and after cleaning, it is determined to be an independent wave. If there is no wave after cleaning, it is determined to be a continuation wave.

[0019] A further provision of the present invention is: determining whether the wave shape at the junction of the middle section and the wave shape at the left side is a continuous wave shape, specifically including the following steps:

[0020] D1: Using the wave pattern at the junction of the middle and left side as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the left side junction after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back left side junctions, the wave pattern of the left side junction is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a continuation wave pattern in the middle.

[0021] A further provision of the present invention is: determining whether the wave shape at the junction of the right side wave shape and the wave shape at the middle of the right side is a continuous wave shape, specifically including the following steps:

[0022] E1: Using the wave pattern at the junction of the right side and the middle of the right side as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the middle of the right side after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back of the middle of the right side, the wave pattern of the middle of the right side is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a middle continuation wave pattern.

[0023] A further provision of the present invention is to determine whether the wave shape at the junction of the middle section and the right side is a continuous wave shape, specifically including the following steps:

[0024] F1: Using the wave pattern at the junction of the middle and right side middle sections as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the right side middle section after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back right side middle section, the wave pattern of the right side middle section is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a continuation wave pattern in the middle section.

[0025] The invention is further configured to include the following steps: G1: Positioning the wave data of each part according to the length position to form the wave corresponding to the length position of the steel coil; marking the start and end length positions of the corresponding identifiable wave measurement values ​​to form complete length information of a continuous wave; and outputting the data indicators corresponding to each part according to the definition of parameter values ​​for various situations to describe the plate shape data indicators of each part.

[0026] In summary, the present invention has the following beneficial effects:

[0027] 1. Accurate identification of abnormal plate shape: This method can accurately identify steel coils with abnormal shape, avoiding the possibility of missed or false detection in traditional detection methods. Through real-time monitoring and identification, it can ensure that all abnormal steel coils are detected and dealt with in a timely manner, thus improving the stability of product quality.

[0028] 2. Reduce production downtime: Especially in cold rolling annealing units with strict requirements for sheet shape, identifying and intercepting coils with abnormal sheet shape can significantly reduce downtime caused by sheet shape issues. These incidents not only affect production efficiency but may also damage the unit and increase maintenance costs. Therefore, implementing this method helps improve production efficiency and stability.

[0029] 3. Improve production efficiency: By reducing manual verification time and downtime, this method can significantly improve the overall production efficiency of the unit. This not only helps to shorten the production cycle but also increases output per unit time, thereby improving production efficiency. Attached Figure Description

[0030] Figure 1 This is a diagram showing the channel division of each part of the plate shape in this invention.

[0031] Figure 2 This is a diagram showing the basic configuration information for plate shape recognition in this invention.

[0032] Figure 3This is a flowchart of the channel wave-shaped iterative merging process of the present invention. Detailed Implementation

[0033] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below with reference to the figures and specific embodiments.

[0034] like Figures 1 to 3 As shown, the present invention proposes a method for identifying the shape of cold-rolled sheet based on dynamic configuration, comprising the following steps:

[0035] A1: Plate shape detection position setting: Based on the total plate shape measurement channel data, the plate shape detection range is limited to ensure that the steel coil is at the center of the plate shape measuring instrument, thereby achieving the theoretical accuracy of plate shape measurement; where, due to symmetry requirements, the total plate shape channel data is all an even number of channels;

[0036] A2: Channel width and position definition. This defines the width of each channel in the plate shape. By defining the corresponding width of each channel, the width position is located when identifying wavy patterns. Different measurement positions have different requirements for the measurement accuracy of the plate shape. Specifically, the channel spacing on both sides of the plate shape is smaller, while the channel spacing in the middle is larger. Defining the corresponding width for each channel of the plate shape enables accurate width position location when identifying wavy patterns, providing a foundation for subsequent wavy pattern recognition. Different channel spacing distances are set according to different measurement positions to meet the different measurement accuracy requirements of different areas, improving the pertinence and practicality of the measurement.

[0037] A3: Configure the corresponding channels for each wave shape, including the corresponding channels for each part and the definition information of the measurement values ​​for each part, as the definition of the logical channels for each part; this includes the number of wave shape channels at the edge, the corresponding measurement value size, the number of channels corresponding to the wave shape in the middle, the range of identifiable wave shape measurement values ​​in the middle, and the number of channels and the range of identifiable wave shape measurement values ​​at the edge-middle junction. For example, if the width of the steel coil is X mm, define BL = BR = 1, Z = 4, BZL = BZR = Q / 2 - BL - Z / 2; by configuring the wave shape channels and measurement value definition information corresponding to each part, a clear logical channel definition is established, providing clear guidance for subsequent data processing. It can flexibly configure the number of channels and measurement value ranges for the edge, middle, and edge-middle junctions according to different steel coil widths and characteristics, improving the adaptability and flexibility of the method;

[0038] A4: Accurately measure the shape of the steel coil. By reading the measurement values ​​of each channel of the steel coil, the abnormal data at the beginning and end of the data are cleaned and marked to ensure that no abnormal data is mixed in after the cleaning is completed, forming complete shape data of the target steel coil. By cleaning and marking the abnormal data at the beginning and end of the data, the accuracy and reliability of the subsequent analysis data are ensured, forming complete shape data of the target steel coil, providing comprehensive data support for subsequent data processing and analysis.

[0039] A5: Based on the board shape area configuration information defined in each part of step A3, and combined with the complete board shape data obtained in step A4, the actual data of the measured values ​​of each channel of the board shape are processed according to the range of the board shape identification measurement values, and assigned to the corresponding board shape logical areas. The overall board shape is divided into multiple parts, which facilitates subsequent targeted analysis and processing of different areas. Based on the actual data of the measured values ​​of each channel and the range of the board shape identification measurement values, the measurement data is assigned to the corresponding board shape logical areas, which improves the accuracy and efficiency of data processing.

[0040] A6: Combine the logical channels with the actual effective channels to obtain the number of channels corresponding to the actual steel coil, forming the logical channel to actual channel conversion for each part, and obtaining the corresponding channel number for each part; the number of channels corresponding to the steel coil is △Tx, BLNo=(Q-△Q) / 2, BZLNo=BLNo+BL, ZLNo=Q / 2-Z / 2; ZRNo=Q / 2+Z / 2; BZRNo=ZRNo+1; BZRNo=Q-(Q-△Q) / 2; where Q represents the total number of channels of the plate shape meter, △Q represents the number of channels covered by the actual width of the steel coil, ZLNo represents the starting number of the channel on the left side of the middle section, and ZRNo represents the starting number of the channel on the left side of the middle section. The following symbols represent the starting number of the right-side channel in the middle section: BL for the left side, BR for the right side, BLNo for the left-side channel, BRNo for the right-side channel, BZL for the left-side middle junction, BZR for the right-side middle junction, Z for the middle section, BZLNo for the left-side middle junction, and BZRNo for the right-side middle junction. By converting logical channels into actual channels and obtaining the corresponding channel numbers for each part, a direct basis is provided for wave shape control and adjustment in actual production. The method calculates the actual number of channels corresponding to the steel coil, making it applicable to steel coils of different widths and specifications.

[0041] A7: Wave pattern data acquisition involves iteratively merging the channel wave patterns of each part. During merging, the standard channel of the corresponding logical channel is first selected. This standard channel is then merged with the next channel to form a new standard channel, and so on, until the logical region of each part is processed. Through this iterative merging method, the overall wave pattern data of each part is obtained. By gradually integrating the wave pattern data of each logical region through iterative merging, the overall wave pattern data of each part is obtained, improving the comprehensiveness and accuracy of wave pattern recognition. This iterative merging process not only improves the efficiency of data processing but also ensures the continuity and consistency of the wave pattern data.

[0042] The wave data obtained in step A7 includes the wave pattern on the left side, the wave pattern at the junction of the left side and the middle, the wave pattern in the middle, the wave pattern at the junction of the right side and the middle, and the wave pattern on the right side. Specifically, it includes the following steps:

[0043] B1: Using the channel wave shape at the junction of the left side and the middle of the left side as the standard wave shape data, the entire middle of the left side is iteratively cleaned one by one. After each iteration, a new standard channel data and the remaining wave shape data are formed. Then, the new standard channel data is used for iterative cleaning until all the middle of the left side are cleaned. The wave shape of the left side and the wave shape of the middle of the left side are identified and judged.

[0044] The iterative cleaning process progressively optimizes the standard channel data, making each merging step closer to the true wave pattern, thereby improving the accuracy of the final wave pattern identification. Iterative cleaning, performed one step at a time rather than processing the entire area at once, allows for more precise capture of subtle changes in the wave pattern. Each iteration generates new standard channel data and remaining wave pattern data, adaptable to waves of different shapes and sizes. The boundary between the left edge and the junction of the left edge and the middle of the left edge is clearly defined, and the wave pattern data of these two areas is gradually separated through iterative cleaning. After completing the iterative cleaning, the wave pattern at the junction of the left edge and the middle of the left edge can be accurately identified and judged. This judgment is based not only on the wave pattern data of a single channel but also considers the wave pattern characteristics of the entire area. The wave pattern data obtained through iterative cleaning can be further integrated into the wave pattern data of the entire steel coil.

[0045] The identification and determination of the wavy shape on the left side and the wavy shape at the junction of the left side in step B1 includes the following steps:

[0046] C1: Iteratively merge the wave data after iterative cleaning. After each iteration, a new temporary wave data is formed. The temporary wave data is merged with the remaining data of the next channel until all edge-to-center junction data are merged, forming the final wave data index of the edge-to-center junction after cleaning. By the difference between the wave data index of the left edge-to-center junction before and after cleaning, it is determined whether the left edge-to-center junction wave is a continuation wave. If there is no change before and after cleaning, it is determined to be an independent wave. If there is no wave after cleaning, it is determined to be a continuation wave.

[0047] Determining whether the wave pattern at the junction of the middle section and the left side is a continuation wave pattern involves the following steps:

[0048] D1: Using the wave pattern at the junction of the middle and left side as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the left side junction after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back left side junctions, the wave pattern of the left side junction is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a continuation wave pattern in the middle.

[0049] Determining whether the wave pattern at the junction of the right side and the middle of the right side is a continuation wave involves the following steps:

[0050] E1: Using the wave pattern at the junction of the right side and the middle of the right side as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the middle of the right side after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back of the middle of the right side, the wave pattern of the middle of the right side is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a middle continuation wave pattern.

[0051] Determining whether the wave pattern at the junction of the middle section and the right side is a continuation wave pattern involves the following steps:

[0052] F1: Using the wave pattern at the junction of the middle and right side middle sections as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the right side middle section after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back right side middle section, the wave pattern of the right side middle section is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a continuation wave pattern in the middle section.

[0053] G1: Locate each part of the wave data according to its length position to form the corresponding steel coil length position of the wave; mark the start and end length positions of the corresponding identifiable wave measurement values ​​to form complete length information of a continuous wave; output the corresponding data indicators of each part according to the definition of parameter values ​​for various situations to describe the plate shape data indicators of each part.

[0054] Based on the complete length information and data indicators of the waviness data, existing production processes can be optimized and improved. For example, adjusting the geometry of the rolls and optimizing the rolling speed can improve production efficiency and product quality. The data indicators can also be used to evaluate the quality of cold-rolled sheets. By comparing the waviness data of different batches or under different process conditions, it can be determined whether the product quality is stable and corresponding measures can be taken for improvement. Combining the waviness data with the actual length position of the steel coil can also enable data visualization.

[0055] Example 1

[0056] In this embodiment, the above method is applied to the pickling and rolling mill to identify the shape of the steel coil. When an abnormal shape is identified, the result is fed back to the background production control system, and the abnormal steel coil is sealed off to accurately intercept the steel coil with abnormal shape.

[0057] As shown in the table, before applying this method, staff had to inspect an average of 260 sets of steel coils per day, with each coil taking an average of 30 seconds. The total time for 260 sets of steel coils was 130 minutes. According to statistics on steel coil production data for an entire year, the percentage of steel coils with abnormal shape was about 1%, with an average of about 3 sets of steel coils having abnormal shape. The remaining steel coils met the quality inspection standards. 99% of the time was spent manually checking steel coils without abnormalities. The traditional inspection method resulted in a serious waste of manpower.

[0058] After implementing this method, steel coils with abnormal shapes can be competitively identified. Staff only need to verify and confirm the identified steel coils. On average, only a few minutes are needed each day to perform quality inspection on steel coils. This invention greatly improves the work efficiency of staff.

[0059] Comparison items Before implementation After implementation unit Total number of rolls produced 260 260 indivual Number of volumes to be reviewed 260 3 indivual time 130 3 minute Working hours percentage 27 1 ％

[0060] Furthermore, identifying steel coils with abnormal shapes through shape recognition methods can reduce downtime accidents caused by abnormal shapes in subsequent processes. This is especially true for cold rolling annealing units, where the process speed is high and the requirements for the shape of incoming materials are strict. Reducing unit downtime can improve production efficiency and stability, thus significantly enhancing the unit's production benefits.

[0061] In summary, this invention utilizes a plate shape recognition method to process steel coil shape data in a programmed manner, tailoring the processing to different manufacturing processes, each with customized requirements for plate shape. The key challenge is to identify steel coils with clearly defined shape characteristics and high production risks in advance using a universal method, providing operators with alerts during production to improve stability and efficiency. Ultimately, the goal is to reduce production accidents caused by abnormal incoming material shapes.

[0062] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," "outer," "left," and "right," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this invention is in use, or the orientation or positional relationship commonly understood by those skilled in the art. These terms are used only for the convenience of describing this invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention. Furthermore, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, terms such as "set" and "connect" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances. In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, which includes not only the elements listed but also other elements not expressly listed.

[0063] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for identifying the shape of cold-rolled steel sheets based on dynamic configuration, characterized in that, Includes the following steps: A1: Plate shape detection position setting: Based on the total plate shape measurement channel data, the plate shape detection range is limited to ensure that the steel coil is in the center of the plate shape measuring instrument, thereby achieving the theoretical accuracy of plate shape measurement; A2: Channel width position definition, defines the width of each channel of the plate shape, and performs width position positioning when recognizing the wave shape by defining the width of each channel; A3: Configure the wave pattern corresponding channel, configure the wave pattern corresponding channel for each part, and define the measurement value information for each part as the definition of the logical channel for each part; A4: Accurately measure the shape of the plate. By reading the measurement value information corresponding to each channel of the plate shape, clean and mark the abnormal data at the beginning and end of the read data to ensure that no abnormal data is mixed in after the cleaning is completed, and form complete plate shape data of the target steel coil. A5: Based on the board shape area configuration information defined in each part of step A3, combined with the complete board shape data obtained in step A4, the actual data of the measured values ​​of each channel of the board shape are processed according to the range of the board shape identification measurement values, and assigned to the corresponding board shape logical areas, thus dividing the overall board shape into multiple parts; A6: Combine the logical channels with the actual valid channels to obtain the number of channels corresponding to the actual steel coil, form the logical channels of each part to the actual channels, and obtain the channel number corresponding to each part; A7: Wave data acquisition involves iteratively merging the channel waves of each part. During merging, the standard channel of the corresponding logical channel must first be selected. The standard channel is then merged with the channel of the next position to form a new standard channel. This process is repeated until the logical area of ​​each part is processed. Through the above iterative merging method, the overall wave data of each part is obtained.

2. The method for identifying cold-rolled sheet shape based on dynamic configuration according to claim 1, characterized in that, The wave data obtained in step A7 includes the wave pattern on the left side, the wave pattern at the junction of the left side and the middle, the wave pattern in the middle, the wave pattern at the junction of the right side and the middle, and the wave pattern on the right side. Specifically, it includes the following steps: B1: Using the channel wave shape at the junction of the left side and the middle of the left side as the standard wave shape data, the entire middle of the left side is iteratively cleaned one by one. After each iteration, a new standard channel data and the remaining wave shape data are formed. Then, the new standard channel data is used for iterative cleaning until all the middle of the left side are cleaned. The wave shape of the left side and the wave shape of the middle of the left side are identified and judged.

3. The method for identifying cold-rolled sheet shape based on dynamic configuration according to claim 2, characterized in that, The identification and determination of the wavy shape on the left side and the wavy shape at the junction of the left side in step B1 includes the following steps: C1: Iteratively merge the wave data after iterative cleaning. After each iteration, a new temporary wave data is formed. The temporary wave data is merged with the remaining data of the next channel until all edge-to-center junction data are merged, forming the final wave data index of the edge-to-center junction after cleaning. By the difference between the wave data index of the left edge-to-center junction before and after cleaning, it is determined whether the left edge-to-center junction wave is a continuation wave. If there is no change before and after cleaning, it is determined to be an independent wave. If there is no wave after cleaning, it is determined to be a continuation wave.

4. The method for identifying cold-rolled sheet shape based on dynamic configuration according to claim 2, characterized in that, Determining whether the wave pattern at the junction of the middle section and the left side is a continuation wave pattern involves the following steps: D1: Using the wave pattern at the junction of the middle and left side as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the left side junction after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back left side junctions, the wave pattern of the left side junction is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a continuation wave pattern in the middle.

5. The method for identifying cold-rolled sheet shape based on dynamic configuration according to claim 2, characterized in that, Determining whether the wave pattern at the junction of the right side and the middle of the right side is a continuation wave involves the following steps: E1: Using the wave pattern at the junction of the right side and the middle of the right side as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the middle of the right side after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back of the middle of the right side, the wave pattern of the middle of the right side is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a middle continuation wave pattern.

6. The method for identifying cold-rolled sheet shape based on dynamic configuration according to claim 2, characterized in that, Determining whether the wave pattern at the junction of the middle section and the right side is a continuation wave pattern involves the following steps: F1: Using the wave pattern at the junction of the middle and right side middle sections as the standard wave pattern data, the channels at the junction are iteratively cleaned one by one. Then, the wave pattern data after iterative cleaning is iteratively merged to obtain the wave pattern of the right side middle section after iterative cleaning. Based on the difference in wave pattern data indicators between the front and back right side middle section, the wave pattern of the right side middle section is judged. If there is no change before and after cleaning, it is judged as an independent wave pattern. If there is no wave pattern after cleaning, it is judged as a continuation wave pattern in the middle section.

7. The method for cold-rolled sheet shape recognition based on dynamic configuration according to claim 1, characterized in that, It also includes the following steps: G1: Locate each part of the wave data according to its length position to form the corresponding steel coil length position of the wave; mark the start and end length positions of the corresponding identifiable wave measurement values ​​to form complete length information of a continuous wave; output the corresponding data indicators for each part according to the definition of parameter values ​​for various situations to describe the plate shape data indicators of each part.

Images