Profile product specification parameter control method and device, electronic equipment and medium

Abstract

The application discloses a profile product specification parameter control method and device, electronic equipment and a readable storage medium, which are applied to the profile rolling technical field. The method comprises the following steps: generating a specification state identification model according to clustering results of original specification parameters of multiple groups of profile products in advance, and generating an adjustment state rule library based on each original specification parameter and a corresponding historical adjustment specification parameter. Initial specification state data of a profile product to be controlled is input into the specification state identification model, and a target specification state cluster to which the initial specification state data belongs is determined; a plurality of target parameter adjustment schemes matched with the target specification state cluster are selected in the adjustment state rule library according to a preset parameter adjustment standard; and target specification state data of the profile product to be controlled is calculated based on each target parameter adjustment scheme and the initial specification state data, so that the specification parameters of the profile product can be automatically controlled and adjusted online.

Description

Technical Field

[0001] The present application relates to the technical field of profile rolling, and in particular to a method, device, electronic device and readable storage medium for controlling specification parameters of profile products. Background Art

[0002] Profiles are objects with defined geometric shapes, such as solid bars with defined cross-sectional shapes and dimensions, made from metals like iron or steel, or materials with a certain strength and toughness, through processes like rolling, extrusion, and casting. Currently, the control of profile product specifications, such as cross-sectional dimensions, relies primarily on manual experience. This method results in a low first-pass yield, large fluctuations in product specifications, uneven mill load distribution, poor adaptability, and high technology transfer costs.

[0003] In view of this, how to solve the technical drawbacks of relying on manual control of profile product specification parameters and realize online automatic adjustment of profile section specifications such as rails is a technical problem that technical personnel in the field need to solve. Summary of the Invention

[0004] The present application provides a method, device, electronic device and readable storage medium for controlling the specification parameters of a profile product, which can realize online automatic control and adjustment of the specification parameters of the profile product.

[0005] To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0006] An embodiment of the present invention provides a method for controlling specification parameters of a profile product, comprising:

[0007] Generate a specification state recognition model in advance based on the clustering results of the original specification parameters of multiple groups of profile products, and generate an adjustment state rule base based on each original specification parameter and its corresponding historical adjustment specification parameter;

[0008] Inputting the initial specification state data of the profile product to be regulated into the specification state recognition model to obtain the target specification state cluster to which the initial specification state data belongs;

[0009] According to a preset parameter adjustment standard, determining a plurality of target parameter adjustment schemes matching the target specification state cluster in the adjustment state rule base;

[0010] Based on each target parameter adjustment scheme and the initial specification status data, the target specification status data of the profile product to be regulated is determined.

[0011] Optionally, determining the target specification status data of the profile product to be regulated based on each target parameter adjustment scheme and the initial specification status data includes:

[0012] The adjustment effect ratio conversion relationship formula is called to calculate the target specification state data based on each target parameter adjustment plan and the initial specification state data; the adjustment effect ratio conversion relationship formula is:

[0013]

[0014] Where ΔX i is the target specification state data, i is the total number of specification state clusters, j is the total number of parameter adjustment schemes included in each specification state cluster, ΔY is the initial specification state data, ΔY ij is the specification state data corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme in the adjustment state rule base, ΔX ij is the roll gap state data corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme in the adjustment state rule base, β ij is the weight factor corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme, α i is the learning correction factor of the i-th specification state cluster.

[0015] Optionally, the step of inputting the initial specification state data of the profile product to be regulated into the specification state recognition model to obtain the target specification state cluster to which the initial specification state data belongs includes:

[0016] Calculating the cosine similarity and Euclidean distance between the state vector corresponding to the initial specification state data of the profile product to be regulated and the center vector of each specification state cluster in the adjustment state rule base respectively;

[0017] Determining whether there is a target specification state cluster to which the initial specification state data belongs based on the cosine similarities, the Euclidean distances, and a preset similarity condition;

[0018] If it exists, the target specification state cluster is determined; if it does not exist, the state data that meets the initial specification is added to the adjustment state rule library as a new specification state cluster.

[0019] Optionally, after adding the state data that meets the initial specification to the state adjustment rule base, the method further includes:

[0020] Send manual adjustment specification parameter instructions;

[0021] In response to the parameter adjustment instruction, adjustment specification state data is extracted from the parameter adjustment instruction, and the adjustment specification state data is added to the adjustment state rule base to serve as a parameter adjustment solution for the new specification state cluster.

[0022] Optionally, after determining the target specification status data of the profile product to be regulated based on each target parameter adjustment scheme and the initial specification status data, the method further includes:

[0023] Determining whether the target specification status data is adopted;

[0024] If the target specification status data is not adopted, then updating the values ​​of each indicator in each target parameter adjustment plan;

[0025] If the target specification status data is adopted, adjusting the specification parameters of the profile product to be regulated according to the target specification status data, and using the adjusted profile product to be regulated as the profile product to be tested;

[0026] According to whether the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated, and the similarity between the updated specification status data and each target parameter adjustment scheme, the indicator values ​​of each target parameter adjustment scheme are adjusted accordingly.

[0027] Optionally, adjusting the indicator values ​​of each target parameter adjustment scheme accordingly according to whether the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated, and the similarity between the updated specification status data and each target parameter adjustment scheme, includes:

[0028] Determining whether the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated;

[0029] If the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated, determining whether the updated specification status data is close to each target parameter adjustment scheme;

[0030] If the updated specification state data is not similar to any target parameter adjustment scheme, the updated specification state data is used as a new parameter adjustment scheme for the target specification state cluster, and the index value of the new parameter adjustment scheme is initialized; if there is a target parameter adjustment scheme similar to the updated specification state data, the weight factor corresponding to the target parameter adjustment scheme similar to the updated specification state data is adjusted, and the scheme occurrence frequency value, hit rate and recommendation index are increased;

[0031] If the updated specification status data of the profile product to be detected does not meet the specification parameter requirements of the profile product to be regulated, determining whether the updated specification status data is close to each target parameter adjustment plan;

[0032] If the updated specification status data is not similar to any target parameter adjustment scheme, the specification parameters of the profile product to be tested are adjusted again; if there is a target parameter adjustment scheme similar to the updated specification status data, the frequency of occurrence of the scheme corresponding to the target parameter adjustment scheme similar to the updated specification status data is increased, while reducing the hit rate and recommendation index.

[0033] Optionally, generating a specification state recognition model based on clustering results of multiple groups of original specification parameters of profile products, and generating an adjustment state rule base based on each original specification parameter and its corresponding historical adjustment specification parameter, includes:

[0034] The original specification parameters of multiple groups of profile products and their corresponding historical adjusted specification parameters are divided into data according to noise tolerance, equivalent area distance and specification strong constraints to obtain normal data sets and abnormal data sets;

[0035] For each specification state vector in the normal data set and the abnormal data set, clustering is performed on each specification state vector based on the cosine similarity and Euclidean distance between the specification state vectors to obtain multiple specification state clusters, and the cluster center vector of each specification state cluster is calculated to establish a specification state vector dictionary data table;

[0036] Based on the specification state vector dictionary data table, generating a corresponding specification state recognition model;

[0037] Generate parameter adjustment plan vectors from the historical adjustment specification parameters in each specification status cluster. Traverse the parameter adjustment plan vectors in each specification status cluster one by one, perform clustering based on the cosine similarity and Euclidean distance between the parameter adjustment plan vectors, and obtain the cluster center vector of the parameter adjustment plan vectors in each specification status cluster to generate an adjustment plan category lookup dictionary.

[0038] The adjustment scheme category lookup dictionary and specification state recognition model of the normal data set, and the adjustment scheme category lookup dictionary and specification state recognition model of the abnormal data set are used as the adjustment state rule base.

[0039] Another embodiment of the present invention provides a device for controlling specification parameters of a profile product, comprising:

[0040] A rule base building module is used to generate a specification state recognition model based on the clustering results of multiple groups of original specification parameters of profile products in advance, and to generate an adjustment state rule base based on each original specification parameter and its corresponding historical adjustment specification parameter;

[0041] an identification module, configured to input the initial specification state data of the profile product to be regulated into the specification state identification model to obtain a target specification state cluster to which the initial specification state data belongs;

[0042] a scheme matching module, configured to determine, in the adjustment state rule base, a plurality of target parameter adjustment schemes that match the target specification state cluster according to a preset parameter adjustment standard;

[0043] The parameter control module is used to determine the target specification status data of the profile product to be controlled based on each target parameter adjustment scheme and the initial specification status data.

[0044] An embodiment of the present invention further provides an electronic device, comprising a processor, wherein the processor is configured to implement the steps of the method for controlling specification parameters of a profile product as described in any of the preceding items when executing a computer program stored in a memory.

[0045] Finally, an embodiment of the present invention further provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for controlling specification parameters of a profile product as described in any of the preceding items are implemented.

[0046] The advantage of the technical solution provided by this application is that, based on the historical adjustment records of profile products and combined with the physical characteristics of profile rolling itself, multi-dimensional space analysis theory can be applied to establish a specification adjustment state space. Based on real-time data, clustering judgment is performed, and matching parameter adjustment solutions are selected from the pre-constructed specification adjustment state space. This enables real-time self-learning and control of the specification control model, enabling online automatic control and adjustment of the specification parameters of profile products without the phenomenon of misjudgment of abnormal data, effectively improving the adjustment efficiency of specification parameters, thereby solving the problems of low one-time adjustment pass rate of profile rolling, large fluctuations in product specification control, limited adjustment experience, and uneven load distribution of rolling mills.

[0047] In addition, the embodiments of the present invention also provide corresponding implementation devices, electronic devices and readable storage media for the profile product specification parameter control method, further making the method more practical, and the devices, electronic devices and readable storage media have corresponding advantages.

[0048] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 A schematic flow chart of a method for controlling specification parameters of a profile product provided by an embodiment of the present invention;

[0051] Figure 2 A specification status dictionary index table in an exemplary application scenario provided by an embodiment of the present invention;

[0052] Figure 3 An adjustment scheme dictionary index table in an exemplary application scenario provided by an embodiment of the present invention;

[0053] Figure 4 A reference table of adjustment solutions in an exemplary application scenario provided by an embodiment of the present invention;

[0054] Figure 5 A structural diagram of a specific implementation of the device for controlling specification parameters of profile products provided by an embodiment of the present invention;

[0055] Figure 6 This is a structural diagram of a specific implementation of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0057] In the specification, claims, and drawings of this application, the terms "first," "second," "third," "fourth," and so on are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements and may include steps or elements that are not listed.

[0058] After introducing the technical solutions of the embodiments of the present invention, various non-limiting implementation methods of the present application are described in detail below.

[0059] See first Figure 1 , Figure 1 A flow chart of a method for controlling specification parameters of a profile product provided by an embodiment of the present invention may include the following contents:

[0060] S101: Generate a specification state recognition model in advance based on clustering results of original specification parameters of multiple groups of profile products, and generate an adjustment state rule library based on each original specification parameter and its corresponding historical adjustment specification parameter.

[0061] In this embodiment, original specification parameters refer to the initial specification parameters of the profile product, such as cross-sectional specifications and dimensions, and historically adjusted specification parameters refer to the adjusted specification parameters after the profile product has undergone specification status adjustment. Since the adjustment status rule base is constructed based on historical data, they are referred to as historically adjusted specification parameters. For a set of original specification parameters, the historically adjusted specification parameters in this embodiment may be the final adjusted specification parameters, or may include every specification parameter used during the adjustment process. The specification status recognition model is used to identify the specification parameters of the current profile product to determine which profile product's original specification parameters in the adjustment status rule base it is similar to, that is, to cluster the real-time specification parameters of the profile product. The adjustment state rule base may include a specification state recognition model, multiple specification state clusters, each specification state is composed of an aggregation of similar specification state data, and each set of original specification parameters of each profile product corresponds to multiple sets of parameter adjustment plans. The parameter adjustment plan is a method for adjusting the corresponding original specification parameters. Each parameter adjustment plan includes multiple indicators, and a growth evaluation index system can be pre-built. In this index system, each parameter adjustment plan may include a plan popularity index, an overall hit rate, and a plan recommendation index, where the plan popularity index is equal to the frequency of recurrence of the adjustment plan / the number of times the adjustment plan is recommended; the overall hit rate is equal to the number of effective implementations / the total number of model recommendation adoptions, which is a convergence criterion, that is, whether a solution can be found in the adjustment state rule base and whether the implementation is effective. The solution recommendation index is equal to e raised to the power of [(number of times a solution was adopted - number of times it was ineffective) / frequency of occurrence of a solution], where e is a natural base. The exponential form is chosen primarily to account for the low probability of a solution being viable when the number of occurrences is small. Furthermore, given the complexity of the problem, a solution will not appear too often. A high number of occurrences indicates credibility, reflecting the degree to which the solution is adopted and implemented effectively (i.e., specifications are guaranteed to be within internal control tolerances) when specifications are close. To further improve roll utilization and reduce roll changing and grinding time, each parameter adjustment solution can also be evaluated based on roll change adjustment output, roll change adjustment frequency, and roll change adjustment pass rate. Roll change adjustment output is defined as the total tonnage rolled on the rolling line from the start of the adjustment to the next roll change. Roll change adjustment frequency is defined as the number of rolling adjustments performed on the rolling line from the start of the adjustment to the next roll change. Roll change adjustment pass rate is defined as the cold zone inspection pass rate from the start of the adjustment to the next roll change.

[0062] S102: Inputting the initial specification state data of the profile product to be regulated into a specification state recognition model to obtain a target specification state cluster to which the initial specification state data belongs.

[0063] In this embodiment, the profile product to be regulated is an unqualified profile product, that is, a product requiring specification parameter adjustment. The initial specification state data refers to the initial specification state data of the profile product to be regulated. To facilitate data processing, the specification state data can be processed into a specification state vector, that is, the specification state data is represented in vector form. The target specification state cluster is the historical specification state data in the adjustment state rule base that is most similar to the initial specification state data.

[0064] S103: According to a preset parameter adjustment standard, a plurality of target parameter adjustment schemes matching the target specification state cluster are determined in an adjustment state rule library.

[0065] In this embodiment, the preset parameter adjustment criteria are flexibly determined based on the actual application scenario. The criteria are determined based on the parameter adjustment scheme indicators. For example, the preset parameter adjustment criteria may be to screen the five parameter adjustment schemes with the highest recommendation index. A parameter adjustment scheme that meets the conditions and quantity is selected from multiple parameter adjustment schemes in the adjustment state rule base corresponding to the target specification state cluster, using the preset parameter adjustment criteria. The parameter adjustment scheme that meets the preset parameter adjustment criteria is referred to as the target parameter adjustment scheme.

[0066] S104: Determine target specification status data of the profile product to be regulated based on the target parameter adjustment schemes and the initial specification status data.

[0067] After the target parameter adjustment scheme is determined in the previous step, since the target parameter adjustment scheme is the specification parameter adjustment method for the product to be regulated corresponding to the target specification state cluster, and the initial specification state data of the profile product to be regulated is similar to the specification state in the target specification state cluster, the target parameter adjustment scheme can reflect the method for adjusting the specification parameters of the profile product to be regulated. Based on this, the initial specification state data can be adjusted based on the target parameter adjustment scheme, and the specification parameters to be achieved by adjusting the profile product to be regulated are the target specification state data. As an optional implementation method, this embodiment can pre-set and store the adjustment effect ratio conversion relationship, and by calling the adjustment effect ratio conversion relationship, calculate the target specification state data based on each target parameter adjustment scheme and the initial specification state data; the adjustment effect ratio conversion relationship can be expressed as:

[0068]

[0069] Where ΔX i is the target specification state data, i is the total number of specification state clusters, j is the total number of parameter adjustment schemes included in each specification state cluster, ΔY is the initial specification state data, ΔY ij To adjust the specification state data corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme in the state rule base, ΔX ijis the roll gap state data corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme in the adjustment state rule base, β ij is the weight factor corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme. Here, it can be taken as the Bayesian probability, that is, the frequency of occurrence of this scheme when the specification state vectors are similar. i is the learning correction factor of the i-th specification state cluster. It is fitted by multiple similar adjustment rules in the rule base, and the initial value can be 1. ij With α i All are stored in the adjustment rule status library.

[0070] In the technical solution provided by the embodiments of the present invention, based on the historical adjustment records of profile products and the physical characteristics of profile rolling itself, multidimensional spatial analysis theory is applied to establish a specification adjustment state space. Clustering is performed based on real-time data, and matching parameter adjustment solutions are selected from the pre-constructed specification adjustment state space. This enables real-time self-learning and control of the specification control model, enabling online automatic control and adjustment of profile product specification parameters without misjudgment of abnormal data, effectively improving the efficiency of specification parameter adjustment, thereby addressing the low pass rate of profile rolling adjustments, large fluctuations in product specification control, limited adjustment experience, and uneven mill load distribution.

[0071] It should be noted that there is no strict order in which the steps in this application are performed. As long as they comply with the logical order, these steps can be performed simultaneously or in a predetermined order. Figure 1 This is just a schematic and does not mean that this is the only execution order.

[0072] In the above embodiment, there is no limitation on how to perform step S101. In this embodiment, an optional implementation of adjusting the state rule base is provided, which may include the following steps:

[0073] The original specification parameters of multiple groups of profile products and their corresponding historical adjusted specification parameters are filtered according to data filtering methods such as noise tolerance, equivalent area distance and strong specification constraints to achieve data division and obtain normal data sets and abnormal data sets.

[0074] For each specification state vector in the normal data set and the abnormal data set, cluster each specification state vector based on the cosine similarity and Euclidean distance between the specification state vectors to obtain multiple specification state clusters, and calculate the cluster center vector of each specification state cluster to establish a specification state vector dictionary data table;

[0075] Based on the specification state vector dictionary data table, generate the corresponding specification state recognition model;

[0076] Generate parameter adjustment plan vectors from the historical adjustment specification parameters in each specification status cluster. Traverse the parameter adjustment plan vectors in each specification status cluster one by one, perform clustering based on the cosine similarity and Euclidean distance between the parameter adjustment plan vectors, and obtain the cluster center vector of the parameter adjustment plan vectors in each specification status cluster to generate an adjustment plan category lookup dictionary.

[0077] The adjustment scheme category lookup dictionary and specification state recognition model of the normal data set, and the adjustment scheme category lookup dictionary and specification state recognition model of the abnormal data set are used as the adjustment state rule base.

[0078] In this embodiment, the space formed by the adjustment rules is a linear space. Combining with the steel rolling deformation theory, it can be seen that the space is piecewise linear and satisfies the judgment theorem of Euclidean space, that is, when the modulus value of the rule vector is within a certain range, similar records or adjustment rules can be superimposed and coefficient modified to achieve adjustment scheme recommendation. Regarding the method for generating the specification state vector dictionary data table, this embodiment provides two implementation methods, ΔY represents the specification state vector, {ΔY} is the specification state vector cluster, and ΔX represents the parameter adjustment scheme vector, which may include the following content:

[0079] As an optional implementation, the orthogonal basis vectors of the {ΔY} data space are calculated, and any basis vector is taken as the reference vector. The cosine similarity and Euclidean distance between each ΔY vector and the basis vector are obtained, and then clustering is performed using these two indicators as labels, the cluster center vector of ΔY is calculated, a specification state vector dictionary data table is established, and a specification state clustering model is generated. As another optional implementation, {ΔY} is traversed one by one, the cosine similarity and Euclidean distance between the current record and other records are calculated, and clustering is performed using these two indicators as labels. The specification state cluster where the current record is located is filtered out according to a certain threshold until all ΔYs are clustered. If the similarity and distance are always lower than the threshold, the record is clustered separately, and a specification state vector dictionary data table is established. The specification state vector dictionary data table, which can also be called the specification state vector dictionary index table, can be as follows. Figure 2 As shown in the figure, when actual specification status data is generated, similarity parameters such as cosine similarity and Euclidean distance can be calculated between the actual specification status and the center cluster vectors of each specification status cluster in the specification status vector dictionary data table. Classification is performed based on a certain threshold to determine the parameter adjustment plan. If classification is not possible, the record is clustered separately to achieve data expansion.

[0080] After determining the specification state vector dictionary data table, traverse each ΔY cluster one by one, calculate the cosine similarity and Euclidean distance two indicators, cluster with these two indicators as labels, and give the cluster center vector of ΔX in each ΔY cluster, thereby generating the adjustment scheme category lookup dictionary, or the adjustment scheme dictionary index table, such as Figure 3 After generating the adjustment scheme dictionary index table, the indicators corresponding to each parameter adjustment scheme can be set to generate a parameter adjustment scheme reference table, as shown in Figure 4 At this point, the adjustment state rule base is formed, which consists of the normal data rule base and the abnormal data rule base.

[0081] Based on the above embodiment, this embodiment further provides an optional implementation of S102, that is, the process of inputting the initial specification state data of the profile product to be regulated into the specification state recognition model to obtain the target specification state cluster to which the initial specification state data belongs may include:

[0082] Calculate the cosine similarity and Euclidean distance of the state vector corresponding to the initial specification state data of the profile product to be regulated and the center vector of each specification state cluster in the adjustment state rule base respectively;

[0083] By using the cosine similarities, the Euclidean distances and the preset similarity conditions, it is determined whether there is a target specification state cluster to which the initial specification state data belongs;

[0084] If so, the target specification state cluster is determined. If not, the data that satisfies the initial specification state is added to the adjustment state rule library as a new specification state cluster. A manual specification parameter adjustment instruction is sent to adjust the specification parameters of the profile product based on human experience. After inputting the corresponding parameter adjustment plan based on human experience, the parameter adjustment instruction is responded to, and the adjusted specification state data is extracted from the parameter adjustment instruction. This data is then added to the adjustment state rule library as the parameter adjustment plan for the new specification state cluster.

[0085] In order to further improve the control accuracy of the profile product, based on the above embodiment, the following contents may also be included:

[0086] Determine whether the target specification status data is adopted;

[0087] If the target specification status data is not adopted, the values ​​of each indicator in each target parameter adjustment plan are updated;

[0088] If the target specification status data is adopted, the specification parameters of the profile product to be regulated are adjusted according to the target specification status data, and the adjusted profile product to be regulated is used as the profile product to be tested;

[0089] According to whether the updated specification status data of the profile product to be tested meets the specification parameter requirements of the profile product to be regulated, and the similarity between the updated specification status data and each target parameter adjustment plan, the indicator values ​​of each target parameter adjustment plan are adjusted accordingly.

[0090] The implementation process of adjusting the indicator values ​​of each target parameter adjustment scheme accordingly based on whether the updated specification status data of the profile product to be inspected meets the specification parameter requirements of the profile product to be regulated, and the similarity between the updated specification status data and each target parameter adjustment scheme, may include:

[0091] Determine whether the updated specification status data of the profile product to be tested meets the specification parameter requirements of the profile product to be regulated;

[0092] If the updated specification status data of the profile product to be tested meets the specification parameter requirements of the profile product to be regulated, determine whether the updated specification status data is close to the adjustment plan of each target parameter;

[0093] If the updated specification state data is not similar to any target parameter adjustment scheme, the updated specification state data is used as the new parameter adjustment scheme of the target specification state cluster, and the index value of the new parameter adjustment scheme is initialized; if there is a target parameter adjustment scheme similar to the updated specification state data, the weight factor corresponding to the target parameter adjustment scheme similar to the updated specification state data is adjusted, and the scheme occurrence frequency value, hit rate and recommendation index are increased;

[0094] If the updated specification status data of the profile product to be tested does not meet the specification parameter requirements of the profile product to be regulated, determine whether the updated specification status data is close to the adjustment plan of each target parameter;

[0095] If the updated specification status data is not similar to any target parameter adjustment scheme, the specification parameters of the profile product to be tested will be adjusted again; if there is a target parameter adjustment scheme similar to the updated specification status data, the frequency of occurrence of the scheme corresponding to the target parameter adjustment scheme similar to the updated specification status data will be increased, while the hit rate and recommendation index will be reduced.

[0096] In this embodiment, when new steel data is generated, the technical solution provided by this embodiment can be used to recommend and record the corresponding parameter adjustment solution. After the next steel is adjusted, new steel data is obtained again to compare the recommended and actually executed solutions: if the adjustment result is qualified, and the solutions are close but there is a small distance, then the learning correction factor value of the rule is corrected through exploration, that is, the learning correction factor is refitted, the frequency of the solution is increased, the hit rate is increased, and the solution recommendation index is improved. If it is qualified but the solution is very dissimilar, a new rule cluster is added to the specification state, with the cluster center being the rule. If it is unqualified and the solutions are close, the frequency of the solution is increased, the hit rate is reduced, and the recommendation index of the solution is reduced. If it is unqualified and the solutions are not close, no action is taken. If there is no current state in the adjustment rule state library, the state is added to the adjustment rule state library to form a new state cluster.

[0097] During the implementation process, the growth of the robot can be observed by comparing the overall hit rate (convergence), statistical pass rate (effectiveness), roller change adjustment output, and roller change adjustment times. If the model has large abnormal recommendations in some rules, the rules should be corrected or deleted in a timely manner.

[0098] This embodiment enriches the rule quantity and modifies the recommended values ​​of the rule state library, that is, performs corresponding processing in terms of rule completeness and accuracy, thereby effectively improving the accuracy and reliability of the specification parameter adjustment of the profile product.

[0099] In order to make the technical solutions of the present application more clearly understood by those skilled in the art, the present application also provides an illustrative example using steel profiles as the profile product. Parameters such as the number of recommended solutions, the cosine similarity threshold, and the Euclidean distance threshold can be configured or modified in advance through the configuration interface. The following contents may be included:

[0100] The system determines whether the current steel section is qualified. If qualified, it continues monitoring the next steel section for qualification. If unqualified, it obtains the specification state vector of the current steel section. It calculates the cosine similarity and Euclidean distance between the specification state vector and the center vectors of each specification state cluster in the adjustment rule state library. Using a preset threshold, it determines whether the specified state exists in the adjustment rule state library. If not, it adds the specified state, i.e., the specification state vector of the current steel section, to the adjustment rule state library, forming a new specification state cluster. It then uses a specification parameter adjustment model pre-trained using a machine learning algorithm or manual experience to adjust the specification parameters of the current steel section. If a specification parameter adjustment model exists, it selects one to five parameter adjustment schemes with the highest recommendation index from the selected specification state cluster. If the recommendation indexes of the parameter adjustment schemes are the same, the one with the lowest recommended parameter adjustment index is selected. Based on the selected parameter adjustment scheme and the current steel section's specification state vector, it uses the adjustment effect ratio conversion formula to determine the final specification state data for the current steel section. It then determines whether the selected parameter adjustment scheme is adopted. If not, it updates the index value of the selected parameter adjustment scheme. If adopted, the next steel section data is determined to be available. If not, the data is monitored continuously. If it is, the adjustment result is determined to be qualified. If not, the selected parameter adjustment solution is determined to be close to the target. If not, the above operations are repeated for the next steel section as the current steel section. If it is close, the selected parameter adjustment solution's frequency of occurrence is increased, its hit rate is lowered, and its recommendation index is decreased. Simultaneously, the values ​​of various indicators are updated, and the cumulative qualified rate and overall hit rate of the individual specification state cluster and the overall solution are calculated. If the adjustment result is qualified, the selected parameter adjustment solution is determined to be close to the target. If so, the weight factors corresponding to the selected parameter adjustment solution are explored and modified, increasing the frequency of occurrence, hit rate, and recommendation index of the solution. Simultaneously, the values ​​of various indicators are updated, and the cumulative qualified rate and overall hit rate of the individual specification state cluster and the overall solution are calculated. If it is not close, a new specification state is added to the current matching state cluster, also known as the target specification state cluster, with the cluster center being the actual adjustment data. The frequency of occurrence, hit rate, and recommendation index of the parameter adjustment solution corresponding to this specification state are updated. In order to avoid an infinite loop, an artificial interruption mode may be set at the two steps of continuing to monitor whether the next steel section is qualified and continuing to monitor the steel section data, for example, a false signal may be given.

[0101] As can be seen above, this embodiment establishes a specification adjustment state space based on historical adjustment records and uses cosine similarity and Euclidean distance to build a clustering rule base. When new data arrives, differentiated judgments are made to enrich the rule base. Clustering judgments are made based on real-time data, followed by rule corrections and iterative updates of correction coefficients to achieve improved correction accuracy.

[0102] The embodiments of the present invention also provide a corresponding device for the profile product specification parameter control method, further enhancing the practicality of the method. The device can be described from the perspective of functional modules and hardware. The following describes the profile product specification parameter control device provided by the embodiments of the present invention. The profile product specification parameter control device described below can be used in conjunction with the profile product specification parameter control method described above.

[0103] From the perspective of functional modules, see Figure 5 , Figure 5 The structural diagram of a profile product specification parameter control device provided in an embodiment of the present invention in a specific implementation manner may include:

[0104] A rule base building module 501 is used to generate a specification state recognition model based on the clustering results of multiple groups of original specification parameters of profile products, and to generate an adjustment state rule base based on each original specification parameter and its corresponding historical adjustment specification parameter;

[0105] Identification module 502, for inputting the initial specification state data of the profile product to be regulated into the specification state identification model to obtain the target specification state cluster to which the initial specification state data belongs;

[0106] A solution matching module 503 is used to determine multiple target parameter adjustment solutions that match the target specification state cluster in the adjustment state rule library according to the preset parameter adjustment standard;

[0107] The parameter control module 504 is used to determine the target specification status data of the profile product to be controlled based on each target parameter adjustment plan and the initial specification status data.

[0108] Optionally, in some implementations of this embodiment, the parameter control module 504 may also be used to: call an adjustment effect ratio conversion relationship formula to calculate target specification state data based on each target parameter adjustment scheme and the initial specification state data; the adjustment effect ratio conversion relationship formula is:

[0109]

[0110] Where ΔX i is the target specification state data, i is the total number of specification state clusters, j is the total number of parameter adjustment schemes included in each specification state cluster, ΔY is the initial specification state data, ΔY ij To adjust the specification state data corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme in the state rule base, ΔX ij is the roll gap state data corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme in the adjustment state rule base, β ijis the weight factor corresponding to the i-th specification state cluster and the j-th parameter adjustment scheme, α i is the learning correction factor of the i-th specification state cluster.

[0111] As an optional implementation, the above-mentioned identification module 502 can also be used to: respectively calculate the cosine similarity and Euclidean distance of the state vector corresponding to the initial specification state data of the profile product to be regulated and the center vector of each specification state cluster in the adjustment state rule library; through each cosine similarity, each Euclidean distance and preset similarity conditions, determine whether there is a target specification state cluster to which the initial specification state data belongs; if so, determine the target specification state cluster; if not, add the data that meets the initial specification state to the adjustment state rule library as a new specification state cluster.

[0112] As an optional implementation of the above embodiment, the above identification module 502 can also be further used to: send manual adjustment specification parameter instructions; respond to parameter adjustment instructions, extract adjustment specification status data from the parameter adjustment instructions, and add the adjustment specification status data to the adjustment status rule library as a parameter adjustment plan for the new specification status cluster.

[0113] Optionally, in some other implementations of this embodiment, the above-mentioned device may also include a data update module, for example, for determining whether the target specification status data is adopted; if the target specification status data is not adopted, then updating the values ​​of each indicator in each target parameter adjustment scheme; if the target specification status data is adopted, adjusting the specification parameters of the profile product to be regulated according to the target specification status data, and using the adjusted profile product to be regulated as the profile product to be tested; based on whether the updated specification status data of the profile product to be tested meets the specification parameter requirements of the profile product to be regulated, and the similarity between the updated specification status data and each target parameter adjustment scheme, the values ​​of each indicator of each target parameter adjustment scheme are adjusted accordingly.

[0114] As an optional implementation of the above embodiment, the data update module can also be further used to: determine whether the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated; if the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated, determine whether the updated specification status data is close to each target parameter adjustment scheme; if the updated specification status data is not similar to each target parameter adjustment scheme, then use the updated specification status data as a new parameter adjustment scheme for the target specification status cluster, and initialize the indicator value of the new parameter adjustment scheme; if there is a target parameter adjustment scheme similar to the updated specification status data, then adjust The weight factor corresponding to the target parameter adjustment scheme that is similar to the updated specification status data is increased, and the scheme occurrence frequency value, hit rate and recommendation index are increased at the same time; if the updated specification status data of the profile product to be tested does not meet the specification parameter requirements of the profile product to be regulated, determine whether the updated specification status data is close to each target parameter adjustment scheme; if the updated specification status data is not similar to each target parameter adjustment scheme, the specification parameters of the profile product to be tested are adjusted again; if there is a target parameter adjustment scheme that is similar to the updated specification status data, the scheme occurrence frequency value corresponding to the target parameter adjustment scheme that is similar to the updated specification status data is increased, and the hit rate and recommendation index are reduced at the same time.

[0115] Optionally, in some other implementations of this embodiment, the rule base establishment module 501 can be further used to: divide the original specification parameters of multiple groups of profile products and their corresponding historical adjustment specification parameters according to noise tolerance, equivalent area distance and specification strong constraints to obtain normal data sets and abnormal data sets; for each specification state vector in the normal data set and abnormal data set, cluster each specification state vector based on the cosine similarity and Euclidean distance between each specification state vector to obtain multiple specification state clusters, and calculate the cluster center vector of each specification state cluster to establish a specification state vector dictionary data table; based on the rule The grid state vector dictionary data table is used to generate the corresponding specification state recognition model; the historical adjustment specification parameters in each specification state cluster are used to generate parameter adjustment plan vectors, the parameter adjustment plan vectors in each specification state cluster are traversed one by one, and clustering processing is performed through the cosine similarity and Euclidean distance between the parameter adjustment plan vectors to obtain the cluster center vector of the parameter adjustment plan vector in each specification state cluster to generate an adjustment plan category lookup dictionary; the adjustment plan category lookup dictionary and specification state recognition model of the normal data set, as well as the adjustment plan category lookup dictionary and specification state recognition model of the abnormal data set, are used as the adjustment state rule base.

[0116] The functions of the various functional modules of the profile product specification parameter control device in the embodiment of the present invention can be specifically implemented according to the method in the above method embodiment. The specific implementation process can refer to the relevant description of the above method embodiment and will not be repeated here.

[0117] As can be seen from the above, the embodiment of the present invention can realize online automatic control and adjustment of specification parameters of profile products.

[0118] The profile product specification parameter control device mentioned above is described from the perspective of functional modules. Furthermore, the present application also provides an electronic device, which is described from the perspective of hardware. Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application in one embodiment. Figure 6 As shown, the electronic device includes a memory 60 for storing computer programs; a processor 61 for implementing the steps of the profile product specification parameter control method mentioned in any of the above embodiments when executing the computer program.

[0119] The processor 61 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 61 may also be a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 61 may be implemented in at least one hardware form selected from the group consisting of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 61 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 61 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 61 may also include an AI (Artificial Intelligence) processor, which is used to handle computing operations related to machine learning.

[0120] The memory 60 may include one or more computer-readable storage media, which may be non-transitory. The memory 60 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the memory 60 may be an internal storage unit of an electronic device, such as a hard disk of a server. In other embodiments, the memory 60 may also be an external storage device of an electronic device, such as a plug-in hard disk equipped on a server, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc. Furthermore, the memory 60 may include both an internal storage unit and an external storage device of the electronic device. The memory 60 can not only be used to store application software installed in the electronic device and various types of data, such as the code of the program in the process of executing the profile product specification parameter control method, but can also be used to temporarily store data that has been output or is about to be output. In this embodiment, the memory 60 is used to store at least the following computer program 601, wherein, after being loaded and executed by the processor 61, the computer program can implement the relevant steps of the profile product specification parameter control method disclosed in any of the aforementioned embodiments. In addition, the resources stored in memory 60 may also include an operating system 602 and data 603, which may be stored in either a temporary or permanent manner. Operating system 602 may include Windows, Unix, Linux, etc. Data 603 may include, but is not limited to, data corresponding to the control results of profile product specifications and parameters.

[0121] In some embodiments, the electronic device may further include a display screen 62, an input / output interface 63, a communication interface 64 or a network interface, a power supply 65 and a communication bus 66. Among them, the display screen 62 and the input / output interface 63 such as a keyboard belong to the user interface, and the optional user interface may also include a standard wired interface, a wireless interface, etc. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device, etc. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface. The communication interface 64 may optionally include a wired interface and / or a wireless interface, such as a WI-FI interface, a Bluetooth interface, etc., which is generally used to establish a communication connection between the electronic device and other electronic devices. The communication bus 66 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0122] Those skilled in the art will understand that Figure 6 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, for example, it may also include a sensor 67 to realize various functions.

[0123] The functions of the functional modules of the electronic device described in the embodiment of the present invention can be specifically implemented according to the method in the above method embodiment. The specific implementation process can refer to the relevant description of the above method embodiment and will not be repeated here.

[0124] As can be seen from the above, the embodiment of the present invention can realize online automatic control and adjustment of specification parameters of profile products.

[0125] It is understandable that if the profile product specification parameter control method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, removable disk, CD-ROM, magnetic disk or optical disk, etc. Various media that can store program codes.

[0126] Based on this, an embodiment of the present invention further provides a readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method for controlling specification parameters of profile products as described in any of the above embodiments.

[0127] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. The hardware disclosed in the embodiments, including devices and electronic devices, is described briefly because it corresponds to the methods disclosed in the embodiments. For relevant details, refer to the method description.

[0128] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0129] The above is a detailed introduction to a method, device, electronic device and readable storage medium for controlling the specification parameters of a profile product provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A method for controlling the specification parameters of a profile product, characterized in that: include: Generate a specification state recognition model in advance based on the clustering results of the original specification parameters of multiple groups of profile products, and generate an adjustment state rule base based on each original specification parameter and its corresponding historical adjustment specification parameter; Inputting the initial specification state data of the profile product to be regulated into the specification state recognition model to obtain the target specification state cluster to which the initial specification state data belongs; According to a preset parameter adjustment standard, determining a plurality of target parameter adjustment schemes matching the target specification state cluster in the adjustment state rule base; Determining target specification status data of the profile product to be regulated based on each target parameter adjustment scheme and the initial specification status data; The step of determining the target specification status data of the profile product to be regulated based on the target parameter adjustment schemes and the initial specification status data includes: The adjustment effect ratio conversion relationship formula is called to calculate the target specification state data based on each target parameter adjustment plan and the initial specification state data; the adjustment effect ratio conversion relationship formula is: ； Where, is the target specification status data, is the total number of specification status clusters, is the total number of parameter adjustment schemes included in each specification state cluster, is the initial specification status data, The adjustment state rule base belongs to specification state cluster and the Specification status data corresponding to each parameter adjustment scheme, The adjustment state rule base belongs to specification state cluster and the The roll gap status data corresponding to the parameter adjustment scheme, For the specification state cluster and the The weight factors corresponding to the parameter adjustment schemes are: For the Learning correction factor for a cluster of specification states.

2. The method for controlling the specification parameters of profile products according to claim 1, characterized in that: The step of inputting the initial specification state data of the profile product to be regulated into the specification state recognition model to obtain the target specification state cluster to which the initial specification state data belongs includes: Calculating the cosine similarity and Euclidean distance between the state vector corresponding to the initial specification state data of the profile product to be regulated and the center vector of each specification state cluster in the adjustment state rule base respectively; Determining whether there is a target specification state cluster to which the initial specification state data belongs based on the cosine similarities, the Euclidean distances, and a preset similarity condition; If it exists, the target specification state cluster is determined; if it does not exist, the state data that meets the initial specification is added to the adjustment state rule library as a new specification state cluster.

3. The method for controlling the specification parameters of profile products according to claim 2, characterized in that: After adding the state data that meets the initial specification to the adjustment state rule base, the method further includes: Send manual adjustment specification parameter instructions; In response to the parameter adjustment instruction, adjustment specification state data is extracted from the parameter adjustment instruction, and the adjustment specification state data is added to the adjustment state rule base to serve as a parameter adjustment solution for the new specification state cluster.

4. The method for controlling the specification parameters of profile products according to any one of claims 1 to 3, characterized in that: After determining the target specification status data of the profile product to be regulated based on the target parameter adjustment schemes and the initial specification status data, the method further includes: Determining whether the target specification status data is adopted; If the target specification status data is not adopted, then updating the values ​​of each indicator in each target parameter adjustment plan; If the target specification status data is adopted, adjusting the specification parameters of the profile product to be regulated according to the target specification status data, and using the adjusted profile product to be regulated as the profile product to be tested; According to whether the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated, and the similarity between the updated specification status data and each target parameter adjustment scheme, the indicator values ​​of each target parameter adjustment scheme are adjusted accordingly.

5. The method for controlling the specification parameters of profile products according to claim 4, characterized in that: The method of adjusting the index values ​​of each target parameter adjustment scheme accordingly based on whether the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated, and the similarity between the updated specification status data and each target parameter adjustment scheme, includes: Determining whether the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated; If the updated specification status data of the profile product to be detected meets the specification parameter requirements of the profile product to be regulated, determining whether the updated specification status data is close to each target parameter adjustment scheme; If the updated specification state data is not similar to any target parameter adjustment scheme, the updated specification state data is used as a new parameter adjustment scheme for the target specification state cluster, and the index value of the new parameter adjustment scheme is initialized; if there is a target parameter adjustment scheme similar to the updated specification state data, the weight factor corresponding to the target parameter adjustment scheme similar to the updated specification state data is adjusted, and the scheme occurrence frequency value, hit rate and recommendation index are increased; If the updated specification status data of the profile product to be detected does not meet the specification parameter requirements of the profile product to be regulated, determining whether the updated specification status data is close to each target parameter adjustment plan; If the updated specification status data is not similar to any target parameter adjustment scheme, the specification parameters of the profile product to be tested are adjusted again; if there is a target parameter adjustment scheme similar to the updated specification status data, the frequency of occurrence of the scheme corresponding to the target parameter adjustment scheme similar to the updated specification status data is increased, while reducing the hit rate and recommendation index.

6. The method for controlling the specification parameters of profile products according to any one of claims 1 to 3, characterized in that: The specification state recognition model is generated based on the clustering results of the original specification parameters of multiple groups of profile products, and the adjustment state rule base is generated based on each original specification parameter and its corresponding historical adjustment specification parameter, including: The original specification parameters of multiple groups of profile products and their corresponding historical adjusted specification parameters are divided into data according to noise tolerance, equivalent area distance and specification strong constraints to obtain normal data sets and abnormal data sets; For each specification state vector in the normal data set and the abnormal data set, clustering is performed on each specification state vector based on the cosine similarity and Euclidean distance between the specification state vectors to obtain multiple specification state clusters, and the cluster center vector of each specification state cluster is calculated to establish a specification state vector dictionary data table; Based on the specification state vector dictionary data table, generating a corresponding specification state recognition model; Generate parameter adjustment plan vectors from the historical adjustment specification parameters in each specification status cluster. Traverse the parameter adjustment plan vectors in each specification status cluster one by one, perform clustering based on the cosine similarity and Euclidean distance between the parameter adjustment plan vectors, and obtain the cluster center vector of the parameter adjustment plan vectors in each specification status cluster to generate an adjustment plan category lookup dictionary. The adjustment scheme category lookup dictionary and specification state recognition model of the normal data set, and the adjustment scheme category lookup dictionary and specification state recognition model of the abnormal data set are used as the adjustment state rule base.

7. A device for controlling the specification parameters of a profile product, characterized in that: include: A rule base building module is used to generate a specification state recognition model based on the clustering results of multiple groups of original specification parameters of profile products in advance, and to generate an adjustment state rule base based on each original specification parameter and its corresponding historical adjustment specification parameter; an identification module, configured to input the initial specification state data of the profile product to be regulated into the specification state identification model to obtain a target specification state cluster to which the initial specification state data belongs; a scheme matching module, configured to determine, in the adjustment state rule base, a plurality of target parameter adjustment schemes that match the target specification state cluster according to a preset parameter adjustment standard; A parameter control module, configured to determine target specification status data of the profile product to be controlled based on each target parameter adjustment scheme and the initial specification status data; The parameter control module is specifically configured to: call the adjustment effect ratio conversion relationship formula to calculate the target specification state data based on each target parameter adjustment scheme and the initial specification state data; the adjustment effect ratio conversion relationship formula is: ； Where, is the target specification status data, is the total number of specification status clusters, is the total number of parameter adjustment schemes included in each specification state cluster, is the initial specification status data, The adjustment state rule base belongs to specification state cluster and the Specification status data corresponding to each parameter adjustment scheme, The adjustment state rule base belongs to specification state cluster and the The roll gap status data corresponding to the parameter adjustment scheme, For the specification state cluster and the The weight factors corresponding to the parameter adjustment schemes are: For the Learning correction factor for a cluster of specification states.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor is configured to implement the steps of the method for controlling specification parameters of a profile product as claimed in any one of claims 1 to 6 when executing a computer program stored in the memory.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for controlling specification parameters of a profile product according to any one of claims 1 to 6.

Images