A method and device for optimizing shearing parameters of a rotary shear

Abstract

The application discloses a disc shear cutting parameter optimization method and device, and relates to the technical field of cold-rolled strip steel production, wherein the method comprises the following steps: collecting process data and production data, and obtaining the collected process data and production data through communication with a PLC; performing image defect identification on the edge part of the cut strip steel through an industrial camera to obtain a classification result of the severity of the defects of the strip steel, and preprocessing the classification result; establishing a sample space, taking the edge cutting detection quality as a sample label, taking other data as sample features, and constituting samples; selecting a KNN algorithm for training, saving the trained model after the training is completed, constructing a parameter vector space, and substituting the trained model after the training is completed into the parameter vector space for calculation, and selecting an optimal parameter setting value, and maintaining the original value if there is no optimal value. Through the application, the failure rate of the disc shear cutting edge during work can be reduced, the production stability of the cutting edge can be improved, and the cutting edge quality can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cold-rolled strip production, and particularly relates to a disc shear shearing parameter optimization method and device. BACKGROUND

[0002] In a cold-rolled strip mill, the disc shear equipped in a cold-rolled pickling mill train is a non-driving turret type disc shear. The steel strip is cut by the upper and lower blades of the disc shear under the tension of the tension roll, and the blades make a circular motion with the movement of the steel strip to cut the edge of the steel strip. The turret type disc shear has two sets of blades, which can be replaced offline while the production is running, to ensure the continuous operation of the production line. Before the cutting of the blades starts, the steel strip is plastically deformed to form an arc area. With the movement of the blades, the blades are pressed into the steel strip for cutting to form a relatively smooth cutting surface, which is about 1 / 3-1 / 5 of the thickness of the steel strip. During the cutting process, a relatively rough tear surface is generated on the remaining part of the steel strip as the crack migrates.

[0003] The blade side gap and the overlap of the disc shear are core control parameters of the disc shear. The adjustment range of the values of the two parameters is given by the process personnel, which needs to consider multiple related data. During production, the operator modifies and adjusts the blade overlap and the side gap according to the actual production data, but such adjustment cannot guarantee reliability and accuracy. SUMMARY

[0004] Embodiments of the present application provide a disc shear shearing parameter optimization method and device, which solve the problems of large adjustment hysteresis, extremely dependent on the experience of the operator for adjustment accuracy, and unstable adjustment effect. A disc shear shearing model based on machine learning is established based on production data (such as the thickness of the steel strip, yield strength, production speed, and edge cutting detection quality) and process data (such as the production speed, the gap and the overlap of the disc shear), which is used to automatically find the optimal control parameters under the current state.

[0005] In a first aspect, the present application provides a disc shear shearing parameter optimization method, which comprises:

[0006] Process data and production data are collected, and the collected process data and production data are acquired through communication with a PLC. An image defect of the edge of the cut steel strip is recognized by an industrial camera to obtain a classification result of the severity of the defect of the steel strip. The classification result is preprocessed to obtain a preprocessing result and store it in system data. The preprocessing process includes deleting blank values, invalid values and singular values.

[0007] Based on the preprocessing results stored in the system data, a sample space is established, the edge detection quality is taken as the sample label, other data is taken as the sample features, a sample is constructed, 75% of the data in the sample space is taken as the model training data, 25% is taken as the test data, KNN algorithm is selected for training, and the trained model is saved after training;

[0008] By constructing the parameter vector space and substituting it into the trained model for calculation, the optimal parameter setting value is selected, and if there is no optimal value, the original value is maintained.

[0009] Further, the process data includes disc shear gap and overlap, and the production data includes production speed, strip steel grade, strip thickness and edge detection quality evaluation, wherein the strip steel grade data is divided into six categories according to yield strength.

[0010] Further, the 75% data in the sample space is taken as the model training data, 25% is taken as the test data, KNN algorithm is selected for training, and the trained model is saved after training, which includes:

[0011] Randomly select and assign 75% of the data in the sample space as the model training data set for model learning process; randomly select and assign the remaining 25% data as the model test data set for evaluating the performance of the model;

[0012] The KNN algorithm is used to train the model training data set, wherein the KNN algorithm predicts the class of unknown samples by calculating the distance between samples, and the parameters of the KNN algorithm are adjusted during the training process to achieve the best classification effect;

[0013] After the model training is completed, the model parameters and structure obtained by training are saved to the system hard disk.

[0014] Further, the KNN algorithm is used to train the model training data set, and the specific steps are as follows:

[0015] Step one, initialize the parameters of KNN algorithm, including selecting a suitable neighbor number K;

[0016] Step two, for each sample in the training data set, calculate the distance between it and other samples in the training set;

[0017] Step three, for each sample, select the K nearest neighbor samples according to the calculated distance;

[0018] Step four, according to the labels of the K neighbor samples, determine the predicted label of the current sample by majority voting method;

[0019] Step five, repeat steps two to four until all training samples are processed;

[0020] Step six, optimize the performance of the model by adjusting the K value and other possible parameters.

[0021] Further, the parameter vector space is constructed and substituted into the trained model for calculation to select the optimal parameter setting value, and if there is no optimal value, the original value is maintained, which includes:

[0022] The upper and lower limits of the disc shear gap and the overlap amount are set to M values, and the parameter vector space Ω is constructed;

[0023] Collect other process and production data, substitute each element in Ω into the model for calculation to obtain the cutting edge detection quality classification value;

[0024] Select the parameter with the result of 0 as the new setting value, if there are multiple parameters with the result of 0, randomly select one; if there is no parameter with the result of 0, select the parameter with the result of 1, if there are multiple parameters with the result of 1, randomly select one; if there is no parameter with the result of 0 or 1, do not change and continue to use the original setting value.

[0025] Further, in the process of collecting process data and production data, the sensor detects and records the plate shape data at the position along the length direction, and when the plate shape data is transmitted to the input system, the system calculates the absolute value average of the corresponding data of the four positions of the whole coil strip.

[0026] The application provides a disc shear cutting parameter optimization device, which comprises:

[0027] The acquisition module is used for acquiring process data and production data, and acquiring the acquired process data and production data through communication with the PLC, identifying image defects of the edge part of the cut strip through an industrial camera to obtain a classification result of the severity of the strip defect, and preprocessing the classification result to obtain a preprocessing result and store it in the system data, wherein the preprocessing process includes deleting blank values, invalid values and singular values;

[0028] The training module is used for establishing a sample space based on the preprocessing result stored in the system data, taking the cutting edge detection quality as a sample label and other data as sample features to form a sample, taking 75% of the data in the sample space as model training data and 25% as test data, selecting a KNN algorithm for training, and saving the trained model after training is completed;

[0029] The calculation module is used for constructing a parameter vector space and substituting it into the trained model for calculation to select the optimal parameter setting value, and if there is no optimal value, the original value is maintained.

[0030] Further, the process data in the collection module includes disc shear gap amount and overlap amount, and the production data includes production speed, strip steel grade, strip steel thickness and edge detection quality evaluation, wherein the strip steel grade data is divided into six categories according to yield strength.

[0031] Further, the training module includes:

[0032] The distribution unit is configured to randomly select and distribute 75% of the data in the sample space as a model training data set for the learning process of the model, and randomly select and distribute the remaining 25% of the data as a model test data set for evaluating the performance of the model.

[0033] The training prediction unit is configured to train the model training data set using a KNN algorithm, wherein the KNN algorithm predicts the category of unknown samples by calculating the distance between samples, and the parameters of the KNN algorithm are adjusted during the training process to achieve the best classification effect.

[0034] The saving unit is configured to save the model parameters and structure obtained by the training to the system hard disk after the training of the model is completed.

[0035] Further, the calculation module includes:

[0036] The construction unit is configured to set the upper and lower limits of the disc shear gap amount and the overlap amount, uniformly take M values, and construct a parameter vector space Omega.

[0037] The collection and calculation unit is configured to collect other process and production data, substitute each element in Omega into the model for calculation, and obtain the edge detection quality classification value.

[0038] The selection and judgment unit is configured to select the parameter with a result of 0 as a new setting value, and if there are multiple parameters with a result of 0, randomly select one; if there is no parameter with a result of 0, select the parameter with a result of 1, and if there are multiple parameters with a result of 1, randomly select one; if there is no parameter with a result of 0 or 1, do not change and continue to use the original setting value.

[0039] The one or more technical solutions provided in the embodiments have at least the following technical effects or advantages:

[0040] The embodiments provide a method and device for optimizing disc shear cutting parameters in cold continuous rolling production. The system can automatically adjust and match the key parameters of disc shear cutting according to the current production process data and production data, so as to improve the disc shear edge quality, reduce the edge defects of the strip steel after cutting, and realize stable production of cold rolling strip steel.

[0041] The application is based on a system and device for optimizing disc shear cutting parameters based on strip shape data, field process data and production data, which finds optimal disc shear cutting parameters during production, thereby reducing the failure rate of disc shear cutting edges during operation, improving cutting edge production stability and cutting edge quality.

[0042] The application adopts a graphical interface for human-computer interaction, which can facilitate the operation and processing of quality management personnel and field operators, and can save "personalized" disc shear cutting parameters according to different types and different specifications of strip products and save them in a database for calling at any time.

[0043] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the application. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0045] Figure 1 A structure schematic diagram of a disc shear cutting parameter optimization device provided for the embodiment;

[0046] Figure 2 A flowchart of a disc shear cutting parameter optimization method provided for the embodiment;

[0047] Figure 3 A gap and overlap amount adjustment schematic diagram provided for the embodiment;

[0048] Figure 4 A disc shear cutting parameter optimization system schematic diagram provided for the embodiment;

[0049] Figure 5 A hot-rolled strip shape data selection area schematic diagram provided for the embodiment;

[0050] Figure 6 A disc shear cutting parameter optimization system human-computer main interface schematic diagram provided for the embodiment;

[0051] Figure 7 A historical strip shape data selection and calculation interface schematic diagram provided for the embodiment. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0053] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0054] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0055] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0056] In existing technology, cold-rolled strip edges must be trimmed to meet customer product width requirements, eliminate edge defects, and improve edge quality. The disc shears in the pickling mill are located before the rolling mill. The quality of these trimming operations not only affects product quality but also indirectly impacts mill production and unit output.

[0057] The shearing parameters of the disc shear mainly include gap amount and overlap amount. By adjusting their values, the shearing parameters are optimized, and combined with parameters such as shearing speed and blade installation accuracy, the best edge shearing effect can be achieved.

[0058] If the disc shear gap is not adjusted properly, it will not only shorten the service life of the disc shear blade, but also affect the quality of the steel strip edge. In production, this adjustment amount is within a range, generally 7% to 11% of the strip thickness.

[0059] The overlapping amount mainly affects whether the strip steel can be smoothly bitten into the upper and lower cutting blades. When the overlapping amount is too small, the strip steel edge is bent and cut, and the waste strip is not easy to cut off, resulting in that the waste strip is stuck under the strip steel or the waste strip is stacked on the chute. When the overlapping amount is too large, the wear of the cutting blades is increased, and the strip steel cannot be cut or the strip edge escapes from above the waste edge guide groove.

[0060] In addition, the specifications (such as thickness) of the strip steel, the steel type (such as yield strength), the production speed, the edge shape defects of the hot-rolled material and the like will affect the cutting quality of the disc shear, and the final cutting quality is a comprehensive result of the influences.

[0061] In actual operation, the cutting parameters of the disc shear are set according to the process data table in the secondary system, and then manually adjusted according to the actual production situation. However, such adjustment has large lag, and the adjustment accuracy is extremely dependent on the experience of the operator and the adjustment effect is unstable. In order to solve this problem, the embodiment of the present application provides a method for optimizing the cutting parameters of the disc shear, and designs a disc shear cutting model based on machine learning based on production data (such as strip steel thickness, yield strength, production speed, cutting edge detection quality) and process data (such as production speed, disc shear gap amount and overlapping amount), which is used to automatically find the optimal control parameters under the current state.

[0062] In order to better understand the above technical solutions, the above technical solutions will be described in detail in combination with the drawings of the specification and the specific embodiments.

[0063] The embodiment first relies on Figure 1 The disc shear cutting parameter optimization device shown in the figure provides a disc shear cutting parameter optimization method as shown in the figure, which comprises steps S100-S400. Figure 2

[0064] S100, collect process data and production data, and acquire the collected process data and production data through communication with the PLC, identify the image defects of the cut strip steel edge through the industrial camera, obtain the classification result of the severity of the strip steel defects, and preprocess the classification result to obtain the preprocessing result and store it in the system data, wherein the preprocessing process includes deleting blank values, invalid values and singular values.

[0065] It should be noted that in this step, the process data includes the disc shear gap amount and the overlapping amount, and the production data includes the production speed, the strip steel type, the strip steel thickness and the cutting edge detection quality evaluation, wherein the strip steel type data is divided into six categories according to the yield strength.

[0066] It can be understood that, as Figure 3 ​As shown, the process data is the disc shear gap and the overlap of two parameters, this part of the parameter through the control of disc shear PLC and the system communication. Production data is the production speed, strip steel grade, strip thickness, cutting edge detection quality evaluation classification, this part of the data system communication as shown in Table 1:

[0067] Table 1 production data communication object

[0068] Data object Communication object Data type Production speed Master PLC Integer type Strip steel grade Unit secondary machine Dummy variable encoding Strip thickness Unit secondary machine Integer type Edge detection quality Edge defect detection system Classification value

[0069] The strip steel grade data in the production data is divided into 6 categories according to different yield strength, and is processed by dummy variable processing method. The specific processing is shown in Table 2.

[0070] Table 2 strip steel grade dummy variable processing

[0071]

[0072] The cutting edge detection quality parameter in the production data is the "label value" of machine learning, and the system obtains its data by communicating with the field edge defect detection system. The field edge defect detection system belongs to the quality inspection professional equipment, which takes a picture of the edge of the cut strip every interval through the industrial camera, and then identifies the defects of the photographed image, and obtains the classification of the severity of the strip defects, as shown in Table 3.

[0073] Table 3 cutting edge quality discrimination classification

[0074] Category Numerical value No defect 0 Occasionally visible defects, not obvious 1 Defects, but not obvious 2 There are obvious holes, notches, cracks and other defects 3

[0075] The hot rolling shape data is obtained by communicating with the secondary system. Because the disc shear only cuts the material part of the edge of the strip, the hot rolling shape data only uses the values of the two sensors on the edge, that is, the values of the driving side sensor 1, the driving side sensor 2, the operating side sensor 1 and the operating side sensor 2, as shown in Figure 5 When collecting data, the sensor detects and records the shape data of the position in the length direction. After the shape data is transmitted into the system, the system calculates the absolute value average of the corresponding data of the whole strip at the four positions, as shown in Table 4.

[0076] Table 4 average value calculation of edge shape data of whole strip

[0077]

[0078] After collecting the data, the data is preprocessed, including deleting the blank value, invalid value and singular value, and saving to the system database.

[0079] S200, based on the preprocessing result stored in the system data, a sample space is established, the edge detection quality is taken as a sample label, other data is taken as a sample feature, a sample is constituted, 75% data in the sample space is taken as model training data, 25% is taken as test data, KNN algorithm is selected for training, and the trained model is saved.

[0080] It should be noted that the present step S200 includes S201, S202 and S203.

[0081] S201, 75% data in the sample space is randomly selected and allocated as a model training data set for model learning process; the remaining 25% data is randomly selected and allocated as a model test data set for evaluating the performance of the model;

[0082] S202, the KNN algorithm is used to train the model training data set, wherein the KNN algorithm predicts the category of unknown samples by calculating the distance between samples, and the parameters of the KNN algorithm are adjusted during the training process to achieve the best classification effect;

[0083] S203, after the model training is completed, the model parameters and structure obtained by training are saved to the system hard disk.

[0084] In this step, after the data preprocessing is completed, a sample space is established, the edge detection quality is taken as a sample label, and other data is taken as a sample feature. The sample feature and the sample label constitute a sample, and all samples in a continuous rolling period constitute a sample space. 75% of the data in this sample space is taken as model training data, and 25% is taken as test data for modeling and testing. The machine learning algorithm selects KNN algorithm. KNN algorithm is a general algorithm for machine learning. When the data volume is not large or the dimension is small, the training effect is good, and it is very suitable for this business scenario. After the model training is completed, it is saved in the system hard disk.

[0085] Therefore, in the present step S202, the KNN algorithm is used to train the model training data set, and the specific steps are as follows:

[0086] Step one, initialize the parameters of KNN algorithm, including selecting a suitable neighbor number K;

[0087] Step two, for each sample in the training data set, calculate the distance between it and other samples in the training set;

[0088] Step three, for each sample, select the K nearest neighbor samples according to the calculated distance;

[0089] Step four, according to the labels of the K neighbor samples, the prediction label of the current sample is determined by majority voting method;

[0090] Step five, repeat steps two to four until all training samples are processed;

[0091] Step six, optimize the performance of the model by adjusting the K value and other possible parameters.

[0092] Finally, model evaluation and saving: use the model test dataset to evaluate the KNN model trained, evaluation indicators can include accuracy, recall and F1 score, etc.; after the evaluation is completed, the model parameters and structure of the training completed and the performance optimal are saved to the system hard disk, so as to carry out subsequent test and actual application.

[0093] S300, by constructing a parameter vector space and substituting the training model after training into calculation, the optimal parameter setting value is selected, and if there is no optimal, the original value is maintained.

[0094] In this step S300, it includes S301, S302 and S303, wherein:

[0095] S301, set the upper and lower limits of the disc shear gap and the overlap, take M values uniformly, and construct a parameter vector space Ω;

[0096] S302, collect other process and production data, substitute each element in Ω into the model to calculate the edge detection quality classification value;

[0097] S303, select the parameter with the result of 0 as the new setting value, if there are multiple parameters with the result of 0, randomly select; if there is no parameter with the result of 0, select the parameter with the result of 1, if there are multiple, randomly select; if there is no parameter with the result of 0 or 1, do not change, continue to use the original setting value.

[0098] It can be understood that in the content provided by the application, during production, the system can optimize the disc shear gap and overlap parameters. The upper and lower limits of the disc shear gap are (Gmax, Gmin), and the upper and lower limits of the disc shear overlap are (Lmax, Lmin). Take M values uniformly in (Gmax, Gmin) and (Lmax, Lmin) intervals, denoted as (G1, G2, G3……GM), (L1, L2, L3……LM), arrange and combine (G1, G2, G3……GM), (L1, L2, L3……LM), such as (G i, Lj), wherein 1≤i≤M, 1≤j≤M, so as to construct M2 parameter vector spaces Ω.

[0099] The system collects other process and production data, and substitutes each element in the vector space Ω into the model to calculate, so as to obtain M2 edge detection quality classification values.

[0100] ​The parameter with the result of 0 is selected as the new setting value of the disc shear gap and overlap amount. If there is more than one parameter with the result of 0, one is randomly selected.

[0101] If there is no 0 result, the parameter with the result of 1 is selected, and if there is more than one parameter with the result of 1, one is randomly selected.

[0102] If there is neither 0 nor 1, no change is made, and the original setting value issued by the secondary machine is still used.

[0103] In some embodiments, the present application proposes a method and device for disc shear cutting parameter optimization based on production and process data, and the main implementation is as follows:

[0104] (1) Hardware configuration

[0105] First, the disc shear cutting parameter optimization system hardware is composed of a system database, a system server, and a network connection device, as shown in Figure 4 On the server, data modeling and disc shear parameter optimization operations are performed on the system man-machine main interface. The disc shear cutting parameter optimization system communicates with the edge defect detection system, the factory secondary machine server, the field PLC control system, and the disc shear control PLC through a TCP / IP network.

[0106] (2) Control system operation

[0107] The control system operation interface is shown in Figure 6 In the "process parameter area", the current production of each process data, production data, and disc shear parameters are displayed. The disc shear parameters are the gap and overlap amounts, and the original setting value issued by the secondary is displayed. DS01 and DS02 represent the average absolute value of the plate shape recorded by the two sensors on the drive side of the current production coil, and OS01 and OS02 represent the average absolute value of the plate shape recorded by the two sensors on the operating side of the current production coil.

[0108] Therefore, after clicking "optimization calculation", the system displays the disc shear cutting control parameters, i.e., the gap and overlap amounts, in the right column according to the trained model and the optimal parameter optimization process.

[0109] As production continues, the working conditions and environmental parameters of the field change, and the prediction accuracy of the old model for the input data under the new working conditions will continue to decrease. The system provides a model update option. Click "data selection" on the operation interface to enter the plate shape historical plate shape data selection and calculation interface, as shown in Figure 7 Select the historical data to be trained in the selection box and click "calculate". The system will recalculate the plate shape data according to the selected data.

[0110] Finally, after returning to the main interface, click "model update", the system will recalculate the model according to the new data and save it in the system database.

[0111] The embodiment provides a disc shear cutting parameter optimization device, which comprises Figure 2 as shown in the figure,

[0112] The acquisition module is used for acquiring process data and production data, and obtaining the process data and the production data through communication with a PLC, identifying image defects of a strip steel edge after shearing through an industrial camera to obtain a classification result of a severity of a strip steel defect, and preprocessing the classification result to obtain a preprocessing result and store the preprocessing result in system data, wherein the preprocessing process comprises deleting blank values, invalid values and singular values;

[0113] The training module is used for establishing a sample space based on the preprocessing result stored in the system data, taking edge detection quality as a sample label and other data as sample features to form a sample, taking 75% of data in the sample space as model training data and 25% as test data, selecting a KNN algorithm for training, saving the trained model after training is completed, and

[0114] The calculation module is used for calculating by constructing a parameter vector space and substituting the trained model after training is completed, selecting an optimal parameter setting value, and maintaining the original value if there is no optimal value.

[0115] Specifically, the process data in the acquisition module comprises a disc shear gap and an overlap, and the production data comprises a production speed, a strip steel grade, a strip steel thickness and edge detection quality evaluation, wherein the strip steel grade data is divided into six categories according to yield strength.

[0116] Specifically, the training module comprises:

[0117] The distribution unit is used for randomly selecting and distributing 75% of data in the sample space as a model training data set for a model learning process, and randomly selecting and distributing the remaining 25% of data as a model test data set for evaluating the performance of the model.

[0118] The training prediction unit is used for training the model training data set by using a KNN algorithm, wherein the KNN algorithm predicts the category of an unknown sample by calculating the distance between samples, and the parameters of the KNN algorithm are adjusted in the training process to achieve the best classification effect.

[0119] The saving unit is used for saving the model parameters and structure obtained through training to a system hard disk after the model training is completed.

[0120] Specifically, the calculation module comprises:

[0121] The construction unit is used for setting the upper and lower limits of the disc shear gap and the overlap, and uniformly taking M values to construct a parameter vector space Ω.

[0122] The collection calculation unit is used for collecting other process and production data, substituting each element in Ω into the model to calculate a trimming detection quality classification value.

[0123] The selection judgment unit is used for selecting the parameter with the result of 0 as a new setting value, and if there are multiple parameters with the result of 0, randomly selecting; if there is no parameter with the result of 0, selecting the parameter with the result of 1, and if there are multiple parameters with the result of 1, randomly selecting; if there is no parameter with the result of 0 or 1, not changing and continuing to use the original setting value.

[0124] It should be noted that, as to the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

[0125] Corresponding to the above method embodiment, the present embodiment also provides a disc shear cutting parameter optimization device, and the disc shear cutting parameter optimization device described below can be mutually corresponding to the disc shear cutting parameter optimization method described above.

[0126] Since the electronic device introduced in the present embodiment is the electronic device used to implement the information processing method in the present embodiment, the specific implementation manner of the electronic device in the present embodiment and various changes thereof can be understood by those skilled in the art based on the information processing method introduced in the present embodiment, and therefore, how the electronic device implements the method in the present embodiment will not be described in detail here. As long as the electronic device used to implement the information processing method in the present embodiment is implemented by those skilled in the art, it belongs to the scope of the present application.

[0127] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, device, or computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media containing computer usable program code (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.).

[0128] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0129] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0130] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0131] While the preferred embodiments of the application have been described, additional variations and modifications can be employed by those skilled in the art. Therefore, the appended claims are intended to cover all such variations and modifications as falling within the scope of the application.

[0132] It is apparent that a person skilled in the art can make alterations and modifications to the present application without departing from the scope and spirit of the application. Thus, if these alterations and modifications fall within the scope of the claims and their equivalents, they are intended to be included in the present application.

[0133] In summary, the present application provides a disc shear cutting parameter optimization method, a system and device for disc shear cutting parameter optimization based on strip shape data, field process data and production data. The system finds the optimal parameters for disc shear cutting during production, which can not only reduce the failure rate of disc shear cutting edge during work, but also improve the production stability and quality of the cutting edge. The graphical interface is used for human-computer interaction, which can facilitate the operation and processing of quality management personnel and field operators. The "personalized" disc shear cutting parameters can be saved according to different varieties and different specifications of strip products, and can be called at any time by saving in the database.

[0134] The above only describes the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for optimizing shearing parameters of a disc shear, characterized in that: include: Collect process data and production data, and obtain the collected process data and production data through communication with the PLC. Use industrial cameras to identify image defects on the edges of the sheared strip to obtain a classification result based on the severity of the strip defects. The classification results are preprocessed and stored in the system data. The preprocessing process includes deleting blank values, invalid values, and singular values. Based on the preprocessing results stored in the system data, a sample space is established. The trimming detection quality is used as the sample label, and other data are used as sample features to form a sample. 75% of the data in the sample space is used as model training data, and 25% is used as test data. The KNN algorithm is selected for training and the training model is saved after training. By constructing a parameter vector space and substituting it into the trained model after training, the optimal parameter setting value is selected. If there is no optimal value, the original value is maintained, including: Set the upper and lower limits of the disk shear gap and overlap, take M values ​​evenly, and construct the parameter vector space Ω; Collect other process and production data, substitute each element in Ω into the model calculation, and obtain the trimming inspection quality classification value; Select the parameter with the result of 0 as the new set value. If there are multiple parameters with the result of 0, select randomly. If there is no parameter with the result of 0, select the parameter with the result of 1. If there are multiple parameters with the result of 0, select randomly. If there is no parameter with the result of 0 or 1, do not change it and continue to use the original set value.

2. The disk shearing parameter optimization method according to claim 1, characterized in that: The process data includes the disc shear gap and overlap, and the production data includes production speed, strip steel grade, strip steel thickness and trimming inspection quality evaluation, among which the strip steel grade data is divided into six categories according to yield strength.

3. The disk shearing parameter optimization method according to claim 1, characterized in that: 75% of the data in the sample space is used as model training data, and 25% is used as test data. The KNN algorithm is selected for training and the training model is saved after training. This includes: 75% of the data in the sample space are randomly selected and allocated as the model training dataset for the model learning process; the remaining 25% of the data are randomly selected and allocated as the model testing dataset for evaluating the performance of the model; The KNN algorithm is used to train the model training data set. The KNN algorithm predicts the category of unknown samples by calculating the distance between samples. The parameters of the KNN algorithm are adjusted during the training process to achieve the best classification effect. After the model training is completed, the trained model parameters and structure are saved to the system hard disk.

4. The disk shearing parameter optimization method according to claim 3, characterized in that: The KNN algorithm is used to train the model training data set. The specific steps are as follows: Step 1: Initialize the parameters of the KNN algorithm, including selecting an appropriate number of neighbors K; Step 2: For each sample in the training data set, calculate its distance to other samples in the training set; Step 3: For each sample, select the K nearest neighbor samples based on the calculated distance; Step 4: Determine the predicted label of the current sample by majority voting based on the labels of K neighbor samples; Step 5: Repeat steps 2 to 4 until all training samples have been processed; Step 6: Optimize the performance of the model by adjusting the K value and other possible parameters.

5. The disk shearing parameter optimization method according to claim 1, characterized in that: During the process of collecting process data and production data, the sensor detects and records the plate shape data of the position along the length direction. After the plate shape data is input into the input system, the system calculates the absolute value average of the corresponding data on the two transmission sides and the two operating sides of the entire roll of strip steel.

6. A disc shear shearing parameter optimization device, based on the disc shear shearing parameter optimization method according to claim 1, characterized in that: include: Acquisition module: used to collect process data and production data, and obtain the collected process data and production data through communication with the PLC. The industrial camera is used to identify image defects on the edge of the sheared strip to obtain a classification result based on the severity of the strip defects. The classification result is preprocessed and stored in the system data. The preprocessing process includes deleting blank values, invalid values, and singular values. Training module: used to establish a sample space based on the preprocessing results stored in the system data, using the trimming detection quality as the sample label and other data as sample features to form a sample. 75% of the data in the sample space is used as model training data and 25% as test data. The KNN algorithm is selected for training and the training model is saved after training. Calculation module: This module is used to construct a parameter vector space and substitute it into the trained model to perform calculations, select the optimal parameter settings, and maintain the original values ​​if there is no optimal value. This module includes: Set the upper and lower limits of the disc shear gap and overlap, evenly select M values, and construct the parameter vector space Ω; collect other process and production data, substitute each element in Ω into the model calculation, and obtain the trimming inspection quality classification value; select the parameter with a result of 0 as the new set value. If there are multiple parameters with a result of 0, select them randomly; if there are no parameters with a result of 0, select the parameter with a result of 1. If there are multiple parameters with a result of 0, select them randomly; if there are no parameters with a result of 0 or 1, do not change them and continue to use the original set value.

7. The disc shearing parameter optimization device according to claim 6, characterized in that: The process data in the acquisition module include the disc shear gap and overlap, and the production data include production speed, strip steel grade, strip steel thickness and trimming inspection quality evaluation, among which the strip steel grade data are divided into six categories according to yield strength.

8. The disc shearing parameter optimization device according to claim 6, characterized in that: The training module includes: Allocation unit: randomly selects and allocates 75% of the data in the sample space as the model training dataset for the model learning process; randomly selects and allocates the remaining 25% of the data as the model testing dataset for evaluating the model performance; Training prediction unit: used to train the model training data set using the KNN algorithm, where the KNN algorithm predicts the category of unknown samples by calculating the distance between samples. During the training process, the parameters of the KNN algorithm are adjusted to achieve the best classification effect; Saving unit: used to save the trained model parameters and structure to the system hard disk after the model training is completed.

9. The disc shearing parameter optimization device according to claim 6, characterized in that: The computing module includes: Construction unit: used to set the upper and lower limits of the disc shear gap and overlap, evenly taking M values ​​to construct the parameter vector space Ω; Collection and calculation unit: used to collect other process and production data, substitute each element in Ω into the model calculation, and obtain the trimming inspection quality classification value; Selection judgment unit: used to select the parameter with a result of 0 as the new set value. If there are multiple parameters with a result of 0, it will be randomly selected; if there is no parameter with a result of 0, the parameter with a result of 1 will be selected. If there are multiple parameters, it will be randomly selected; if there is no parameter with a result of 0 or 1, it will not be changed and the original set value will continue to be used.

Images