Coiling side guide plate quality evaluation and automatic early warning method
Through the automatic warning system of coiling side guides, spark detection and quality evaluation is used to use deep learning and neural network technology to perform spark detection and quality evaluation, the problem of insufficient warning of coiling side guides is solved, the spark detection recognition rate and production stability are improved, and the coil shape control is improved .
Patent Information
- Application Number
- CN202410731480.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-06
- Publication Date
- 2024-11-29
AI Technical Summary
In the prior art, the early warning method for coiling the side guide plate is insufficient, resulting in poor coil shape, side strain and serious wear of the lining plate, affecting the quality of the steel coil and the unit operating rate.
By establishing an automatic warning system for coiling side guides, spark detection and quality evaluation are performed using calibration camera parameters, deep learning framework and neural network algorithms, combined with steel grade characteristics and guide pressure values, the spark magnitude is calculated and the quality threshold warning is set.
The spark detection and recognition rate of coiled side guides is improved, production stability and material yield are improved, the roll shape control level is improved, and the quality evaluation and automatic warning of side guides is realized.
Smart Images

Figure CN119044190A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of finishing rolling and hot continuous rolling, and in particular to a method for evaluating the quality of a coiling side guide plate and automatically warning the coiling side guide plate. Background Art
[0002] Strip coiling is the last step in the hot rolling process and is completed by the coiler. The function of the side guide plate at the entrance of the hot rolling coiler is to guide the strip into the coiler and clamp the strip to align with the rolling center line. This process has a direct impact on the coil shape of the strip, and its control level directly affects the quality of the coil shape. The side guide plate of the coiler of the hot rolling unit is an important equipment to ensure the coil shape of the hot rolling mill. If the side guide plate is not well controlled, it will cause a large number of poor hot rolling coil shapes and reduce the quality of the hot rolling coil shape. What is more serious is that it will cause the edge of the hot rolling coil to be torn, which will degrade the steel coil and affect its use. At the same time, it will make the side guide liner wear more seriously, increase the repair and replacement work of the liner and affect the unit operation rate. In the process of rolling silicon steel and thin specifications, common problems of coil shape include staggered layers, tower shapes, loose coils, etc. Among them, the most serious problem is the head tower problem. The head tower seriously affects the production capacity of the finishing unit and the quality of the final product.
[0003] Therefore, there is a need for improving the winding side guide plate warning method in the prior art. Summary of the invention
[0004] In view of this, the purpose of an embodiment of the present invention is to propose a method for quality assessment and automatic warning of a winding side guide plate. By establishing an automatic warning system for a winding side guide plate and coordinating it with a method for spark evaluation, classification, recognition and quality evaluation of a winding side guide plate, the spark detection recognition rate of the winding side guide plate is improved, thereby improving the production stability and yield rate of the process.
[0005] Based on the above purpose, an embodiment of the present invention provides a method for evaluating the quality of a winding side guide plate and automatically warning the winding side guide plate, comprising the following steps:
[0006] S1 calibrates the camera parameters, obtains continuous and complete images of the strip and the side guide, and performs standardization processing on the images to obtain standardized images;
[0007] S2 inputs the standardized image into the neural network model and performs normalization operation. It builds a model based on the deep learning framework and neural network algorithm to detect the sparks of the side guide plate in real time, and iterates based on the image features to generate the spark detection mark of the side guide plate.
[0008] S3 identifies the spark area frame based on the spark detection mark, confirms the number and size of sparks generated in each area based on the set frame rate, sets the gain coefficient, and evaluates the spark magnitude of the coiling side guide plate through data analysis and calculation in combination with the steel grade characteristics and the guide pressure value when the strip hits the side guide plate;
[0009] S4 establishes a data model of the spark level of the coiling side guide and the service life of the coiling side guide, and uses the spark level generated by multiple rolls of strip steel and the coiling side guide within the service life of a single coiling side guide to confirm the data relationship, evaluate the quality cycle of the coiling side guide and issue a quality threshold warning.
[0010] In some embodiments, in S1, calibrating the camera parameters includes: calibrating the internal parameters of the camera and the external parameters relative to the plane of the strip roller.
[0011] In some embodiments, a series of spatial points with known world coordinates and image coordinates of the spatial points are determined by a checkerboard calibration plate, the camera internal parameters and external parameters are solved using the least squares method, and the distortion parameters are solved using a fourth-order radial distortion model.
[0012] In some embodiments, in S1, performing standardization processing on the image to obtain a standardized image includes:
[0013] The image is scaled to fit the input size of the neural network model to obtain a standardized image.
[0014] In some embodiments, in S2, building a model based on a deep learning framework and a neural network algorithm to detect sparks on the side guide plate in real time, and iterating based on image features includes:
[0015] A neural network model is constructed based on the deep learning framework and neural network algorithm. The data system of the neural network model is established through data accumulation. This is used in conjunction with the neural network model training system to generate a targeted target detection neural network model. The data image is subjected to feature extraction, feature enhancement, and prediction of the object situation corresponding to the feature points. The detection and identification of the spark on the side guide plate are completed.
[0016] In some embodiments, the detection and identification of the spark of the side guide plate further includes:
[0017] In the object detection task, manually set features are used to generate a recommended box for the range of the detection object through a sliding window. The input image is traversed using recommended boxes of different sizes in the form of window sliding, and a detection box including each part of the detection object in the image is further generated. The output features in the generated detection box are then processed for recognition.
[0018] In the local area, delete the complex and redundant region proposal boxes to find the most accurate coordinates of the target;
[0019] The network's inferred output values are compared with the labeled true values to enable the model to learn based on the best training method.
[0020] In some embodiments, in S3, evaluating the spark magnitude of the winding side guide plate by data analysis and calculation includes:
[0021] The spark magnitude score Q of a single side guide plate is obtained through data analysis i The calculation formula is as follows:
[0022]
[0023] K represents the gain coefficient of the steel grade; L i Indicates the length of the area frame where a single side guide plate spark is detected, in mm; B i Indicates the width of the area frame where a single side guide plate spark is detected, in mm; S std Indicates the standard area of the side guide spark, in mm 2 ; F i Indicates the guide pressure value when the spark of the guide plate on this side is detected, in KN; F std Indicates the standard guide pressure value when side guide plate sparks are generated, in KN.
[0024] In some embodiments, in S4, evaluating the quality cycle of the winding side guide plate and performing a quality threshold warning includes:
[0025] The quality cycle is evaluated based on the wear degree calculation formula of the side guide plate. The wear degree S calculation formula is:
[0026]
[0027] K Q represents the wear weight coefficient of the side guide plate caused by the spark of the side guide plate; Q i Represents the magnitude rating of all side guide plate sparks during the service life of the side guide plate; K d Represents the wear weight coefficient of the side guide plate's service life; D use Represents the cumulative number of days the side guide has been used;
[0028] In some embodiments, the quality threshold warning includes: setting a wear degree threshold S of the side guide plate max , in response to the wear degree of the side guide plate S ≥ S max The side guide plate quality threshold warning is issued when the side guide plate quality threshold is reached.
[0029] In some embodiments, the wear level threshold is 80-90.
[0030] The present invention has at least the following beneficial technical effects:
[0031] The method of the present invention evaluates the magnitude of the sparks based on the obtained side guide plate spark information according to the regional division, and uses this to assess the friction degree of the strip on the side guide plate and the quality of the side guide plate, and performs visual display and side guide plate quality threshold warning. Based on video image segmentation technology, the data of the winding side guide plate area can be accurately obtained; based on the target detection technology of deep learning, the target detection accuracy is greatly improved, and the actual needs can be handled more accurately; based on the quality assessment technology of big data analysis, data information can be confirmed more efficiently, and the assessment process can be improved more efficiently. The method of the present invention is put into use in the winding side guide plate automatic warning system, and the winding side guide plate spark detection recognition rate can reach more than 90%, which improves the process production stability and yield rate, and improves the coil shape control level. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.
[0033] Figure 1 A flow chart of an embodiment of a method for evaluating the quality of a winding side guide plate and automatically warning the winding side guide provided by the present invention;
[0034] Figure 2 It is the spark classification evaluation method for the coiling side guide plate;
[0035] Figure 3 The technical roadmap for automatic warning and control of the winding side guide provided by the present invention;
[0036] Figure 4 Schematic diagram of noise and outer corner point removal;
[0037] Figure 5 It is the sub-pixel precise positioning result of the gray gradient feature method;
[0038] Figure 6 Decode the graph for the prior box;
[0039] Figure 7 It is the relationship diagram between the true value, predicted value and loss function. DETAILED DESCRIPTION
[0040] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.
[0041] The terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions; the terms "first", "second", etc. in the specification and claims of the present invention or the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. "Multiple" means two or more, unless otherwise clearly and specifically defined.
[0042] In addition, reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0043] like Figures 1 to 3 The flowchart of the method for evaluating the quality of the winding side guide plate and automatically warning the winding side guide plate of the present invention is shown. The method of the present invention comprises the following steps:
[0044] S1: Calibrate camera parameters, obtain continuous and complete images of the strip and the side guide, and perform standardization processing on the images to obtain standardized images.
[0045] Calibrate the internal parameters of the camera and the external parameters relative to the roller plane; when the strip enters the detection area, use the area array camera to obtain continuous and complete images of the strip and the side guide; scale the input image to the input size of the neural network model and perform normalization; determine a series of spatial points with known world coordinates and their image coordinates through the chessboard calibration plate, use the least squares method to solve the internal and external parameters of the camera, and use the fourth-order radial distortion model to solve the distortion parameters. The specific steps are as follows:
[0046] (1) Use the Harris corner detection operator to initially locate the corner points of the chessboard.
[0047] (2) Screening and removing noise points and corner points outside the chessboard grid. In the Harris corner point detection results, three types of points can be detected: corner points inside the chessboard grid, corner points outside the chessboard grid, and noise points. Based on the feature analysis of these three types of points and the changes in the surrounding grayscale values, a rectangular frame centered on the point is used, such as Figure 4 As shown in the figure, the center points of the rectangular box in the figure are the inner corner points of the chessboard, the outer corner points of the chessboard and the noise points. Only the ones with four grayscale value jump changes along the rectangular box path are the inner corner points of the chessboard. Therefore, the inner intersection points are screened by calculating the number of image grayscale value jump changes around the corner points in the detection results.
[0048] (3) The grayscale gradient feature method is used to perform sub-pixel precision on the initial positioning coordinates of the corner points. Since this method uses the grayscale gradient feature to perform sub-pixel precision, and the gradient value is smoothed and iterated multiple times, it can be seen that its detection results are relatively accurate and can prevent error interference. The results are as follows: Figure 3 shown.
[0049] S2: Build a model based on deep learning framework and neural network algorithm to detect sparks on the side guide plate in real time.
[0050] The standardized image is input into the neural network model and normalized. A model is built based on the deep learning framework and neural network algorithm to perform real-time detection of sparks on the side guide plate. The model is iterated based on the image features to generate the spark detection mark of the side guide plate.
[0051] Specifically include:
[0052] S2.1: Establish a neural network model data system through a certain amount of data accumulation, and use it to cooperate with the neural network model training system to generate a targeted target detection neural network model;
[0053] S2.2: Iterate the process of extracting features, enhancing features, and predicting the object conditions corresponding to the feature points on the data image multiple times to complete the detection and identification of the sparks on the side guide plate;
[0054] This includes the following important components of target detection:
[0055] (1) Prior box generation. In the target detection task, manually set features are used to generate a recommended box for the range of the detection object through a sliding window. The input image is traversed using recommended boxes of different sizes in the form of window sliding, and a detection box including each part of the detection object in the image is further generated. The output features in the generated detection box are then processed for recognition, such as Figure 6 shown.
[0056] (2) Non-maximum suppression algorithm: The NMS algorithm searches for maximum values in local areas and deletes non-maximum values.
[0057] (3) Loss function. Assume that the true value is Y, the predicted value is f(x), and the loss function is L(Y, f(x)). Then the relationship is as follows: Figure 7 At present, the loss functions that are widely used in machine learning and deep learning are mean square error loss function and cross entropy loss function.
[0058] S3: Evaluate the spark magnitude of the side guide plate: Identify the spark area frame based on the spark detection mark, confirm the number of sparks and the size of sparks generated in each area based on the set frame rate, set the gain coefficient, and evaluate the spark magnitude of the coiling side guide plate through data analysis and calculation in combination with the steel grade characteristics and the guide pressure value when the strip hits the side guide plate. Specifically include:
[0059] S2 identifies the side guide plate sparks and detects the length L and width B of the side guide plate spark area frame, and confirms the number of sparks generated in each area and the size of the sparks generated by the set frame rate. In some embodiments, three side guide plate sparks are identified, and their lengths and widths are L1=15.21mm, B1=17.42mm, L2=14.03mm, B2=35.18mm, L3=24.06mm, and B3=18.57mm respectively; then, according to the characteristics of different steel types, different gain coefficients are set and stored in the database. The steel type is ordinary steel Q235B, and the gain coefficient K=1 of the steel type is read from the identification database; the magnitude of the coiling side guide plate spark is evaluated by data analysis and calculation; the specific calculation formula for the magnitude score of a single side guide plate spark is as follows:
[0060]
[0061] Among them, Q i It represents the magnitude score of a single side guide plate spark, dimensionless, obtained by calculation;
[0062] K represents the gain coefficient of the steel grade, dimensionless, obtained through on-site rolling experience;
[0063] L i Indicates the length of the area frame where a single side guide plate spark is detected, in mm, obtained by shooting with an industrial camera;
[0064] B i Indicates the width of the area frame where a single side guide plate spark is detected, in mm, obtained by shooting with an industrial camera;
[0065] S std Indicates the standard area of the side guide spark, in mm 2 , obtained through on-site rolling experience, the standard area is set to 350mm 2 ;
[0066] F i Indicates the guide pressure value when the spark of the guide plate on this side is detected, in KN, obtained by L1 at the communication site;
[0067] F std It indicates the standard guide pressure value when the side guide spark is generated, the unit is KN, which is obtained through on-site rolling experience and the standard guide pressure value is set to 8KN;
[0068] When the strip hits the side guide, the guide pressure value of communication L1 is 6.67KN. The spark magnitude scores of the three side guides are as follows:
[0069]
[0070] S4: Evaluate the quality cycle of the side guide: Establish a data model of the spark level of the coiling side guide and the service life of the coiling side guide, use the spark level generated by multiple coils of steel strip and the coiling side guide within the service life of a single coiling side guide to confirm the data relationship, evaluate the quality cycle of the coiling side guide and issue a quality threshold warning. Specifically include:
[0071] Through data collection, a data model of the spark magnitude of the coiling side guide and the service life of the coiling side guide is established. The data relationship is confirmed by using the spark magnitude generated by multiple rolls of strip steel and the coiling side guide within the service life of a single coiling side guide, so as to evaluate the quality cycle of the coiling side guide. The wear degree calculation formula of the side guide is as follows:
[0072]
[0073] Among them, S represents the wear degree of the side guide plate, which is dimensionless and obtained by calculation;
[0074] K Q represents the wear weight coefficient of the side guide plate caused by the spark of the side guide plate, dimensionless, obtained through on-site rolling experience, and the set value is 0.86;
[0075] Q i Represents the magnitude score of all side guide plate sparks during the service life of the side guide plate, dimensionless, obtained by calculation;
[0076] K d The wear weight coefficient representing the service life of the side guide is dimensionless and is obtained through on-site rolling experience. The set value is 1.7;
[0077] D use Represents the cumulative use days of the side guide, dimensionless, obtained through the on-site L1 level;
[0078] The cumulative number of days the side guide is used is 3 days, and the calculation results of the wear degree of the side guide are as follows:
[0079]
[0080] By repeatedly collecting the service life of the side guide plates on site and the magnitude of the side guide plate sparks during the service life, the wear threshold S of the side guide plates is established. max =85, the wear degree of the side guide plate is S<S max , when the wear degree of the side guide plate is S ≥ S maxWhen the winding side guide plate reaches the quality cycle, a visual display and a warning of the side guide plate quality threshold are carried out, and the winding side guide plate is replaced in time.
[0081] The availability of this automatic warning system for the winding side guide plate is over 99%, where system availability = (system usage time - system failure time) / system usage time; after the automatic warning system for the winding side guide plate is put into use, the spark detection and recognition rate of the winding side guide plate can reach over 90%, which improves the production stability and yield rate of the process and improves the coil shape control level.
[0082] The present invention provides a comprehensive and accurate evaluation classification and identification and quality evaluation method for coiling side guide plate sparks, which mainly includes side guide plate spark data preprocessing, establishing a side guide plate spark standard template library, determining the side guide plate spark type, side guide plate spark parameterization characterization and establishing a side guide plate quality evaluation method, so as to achieve the statistical side guide plate spark information in actual production and provide accurate data information for subsequent side guide plate control. The coiling side guide plate spark evaluation classification and identification and quality evaluation method can automatically identify and determine the side guide plate spark type, and construct the side guide plate spark characteristic parameters according to the side guide plate spark type. According to the characteristic parameter threshold, the side guide plate quality is evaluated.
[0083] The above method transmits the collected images to the server through the network. The server stores and processes the collected images, and marks the sparks generated by the friction between the side guide plate and the strip, so as to obtain the spark information of the side guide plate, and display it in real time through the human-computer interaction interface to realize the detection function. The obtained side guide plate spark information is used to evaluate the magnitude of the spark according to the regional division, and the friction degree of the strip steel on the side guide plate and the quality of the side guide plate are evaluated, and a visual display and a side guide plate quality threshold warning are performed. Based on video image segmentation technology, the data of the winding side guide area can be accurately obtained; based on the target detection technology of deep learning, the target detection accuracy is greatly improved, and the actual needs can be handled more accurately; based on the quality assessment technology of big data analysis, the data information can be confirmed more efficiently, and the assessment process can be improved more efficiently.
[0084] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope disclosed in the embodiments of the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.
[0085] It should be understood that, as used herein, the singular forms "a", "an" are intended to include the plural forms as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations including one or more of the associated listed items.
[0086] The serial numbers of the embodiments disclosed in the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0087] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the embodiments of the present invention as above, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.
Claims
1. A method for evaluating the quality of the winding side guide and automatically warning the winding side guide. It is characterized in that include: S1 calibrates camera parameters, obtains continuous complete images of the strip steel and the side guide plate, and performs standardization processing on the images to obtain standardized images; S2 inputs the standardized image into the neural network model and performs normalization operation, builds a model based on the deep learning framework and the neural network algorithm to detect the sparks of the side guide plate in real time, and iterates based on the image features to generate the spark detection mark of the side guide plate; S3 identifies the spark area frame based on the spark detection mark, confirms the number of sparks and the spark size generated in each area based on the set frame rate, sets the gain coefficient, and evaluates the spark magnitude of the coiling side guide plate through data analysis and calculation in combination with the steel grade characteristics and the guide pressure value when the strip hits the side guide plate; S4 establishes a data model of the spark level of the winding side guide and the service life of the winding side guide, uses the spark levels generated by multiple rolls of strip steel and the winding side guide within the service life of a single winding side guide to confirm the data relationship, evaluates the quality cycle of the winding side guide and issues a quality threshold warning.
2. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 1, It is characterized in that In S1, calibrating the camera parameters includes: calibrating the internal parameters of the camera and the external parameters relative to the strip roller plane.
3. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 2, It is characterized in that A series of spatial points with known world coordinates and the image coordinates of the spatial points are determined by a chessboard calibration plate, the internal parameters and the external parameters of the camera are solved by the least squares method, and the distortion parameters are solved by a fourth-order radial distortion model.
4. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 1, It is characterized in that In S1, performing standardization processing on the image to obtain a standardized image includes: The image is scaled to adapt to the input size of the neural network model to obtain a standardized image.
5. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 1, It is characterized in that In S2, a model based on deep learning framework and neural network algorithm is built to detect sparks on the side guide in real time, and it is iterated based on image features, including: A neural network model is constructed based on a deep learning framework and a neural network algorithm. A data system of the neural network model is established through data accumulation, and this is used in conjunction with the neural network model training system to generate a targeted target detection neural network model. Feature extraction, feature enhancement, and prediction of the object conditions corresponding to the feature points are iterated multiple times on the data image to complete the detection and identification of the spark on the side guide plate.
6. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 5, It is characterized in that The detection mark of the spark of the side guide plate further includes: In the object detection task, manually set features are used to generate a recommended box for the range of the detection object through a sliding window. The input image is traversed using recommended boxes of different sizes in the form of window sliding, and a detection box including each part of the detection object in the image is further generated. The output features in the generated detection box are then processed for recognition. In the local area, delete the complex and redundant region proposal boxes and find the target coordinates; The network's inferred output values are compared with the labeled true values to enable the model to learn based on the best training method.
7. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 1, It is characterized in that In S3, the evaluation of the spark magnitude of the coiling side guide plate through data analysis and calculation includes: The spark magnitude score Q of a single side guide plate is obtained through data analysis i The calculation formula is as follows: ; K represents the gain coefficient of the steel grade; L i Indicates the length of the area frame where a single side guide plate spark is detected, in mm; B i Indicates the width of the area frame where a single side guide plate spark is detected, in mm; S std Indicates the standard area of the side guide spark, in mm 2 ; F i Indicates the guide pressure value when the spark of the guide plate on this side is detected, in KN; F std Indicates the standard guide pressure value when side guide plate sparks are generated, in KN.
8. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 1, It is characterized in that In S4, the evaluation of the quality cycle of the winding side guide and the quality threshold warning include: The quality cycle is evaluated based on the wear degree calculation formula of the side guide plate, and the wear degree S calculation formula is: ; K Q represents the wear weight coefficient of the side guide plate caused by the spark of the side guide plate; Q i Represents the magnitude rating of all side guide plate sparks during the service life of the side guide plate; K d Represents the wear weight coefficient of the side guide plate's service life; D use Indicates the cumulative number of days the side guide has been used.
9. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 8, It is characterized in that Quality threshold warning includes: setting the wear threshold S of the side guide plate max , in response to the degree of wear of the side guides Provide side guide plate quality threshold warning and visual display in real time.
10. The method for evaluating the quality of the winding side guide and automatically warning the winding side guide according to claim 9, It is characterized in that The wear degree threshold is 80~90.
