A method, apparatus, medium, and device for determining a plan for a finishing machine roll

Abstract

The application provides a method, device, medium and equipment for determining a finishing mill roller plan, the method comprising: preprocessing historical process data of a finishing mill, and performing correlation analysis on the preprocessed historical process data to obtain target attribute parameters corresponding to the finishing mill roller plan; constructing a recommendation model of the finishing mill roller plan according to the target attribute parameters; reading order plan information, and extracting current parameter values of the target attribute parameters in the order plan information; and outputting roller information by using the recommendation model based on the current parameter values; in this way, the target attribute parameters more relevant to the roller plan are first determined, and the recommendation model of the roller plan is constructed based on the target attribute parameters, so that the corresponding roller information can be quickly and effectively output for the current order plan by using the recommendation model, without manually checking a table to determine the roller information, and the rolling efficiency is ensured.

Description

Technical Field

[0001] This application relates to the field of steel rolling technology, and in particular to a method, apparatus, medium and equipment for determining the roll plan for finishing mills. Background Technology

[0002] The finishing machine is located between the post-galvanizing cooling and drying unit and the tension leveling machine in the hot-dip galvanizing production line. Its main functions are: to obtain the required surface roughness of the galvanized sheet and improve the adhesion of the coating; to flatten uneven parts and improve the straightness and flatness of the galvanized sheet; to improve the mechanical properties of the galvanized sheet; to reduce or eliminate the yield plateau and prevent slip lines from occurring during subsequent deep drawing or stretching processes.

[0003] Different rolls are required for rolling different grades of steel. To ensure the rolling quality of the finishing mill, the matching rolls need to be selected according to the rolling specifications before rolling.

[0004] In existing technologies, suitable rolls are usually determined by manual experience or by manually consulting tables, which is time-consuming and labor-intensive and affects rolling efficiency. Summary of the Invention

[0005] To address the problems existing in the prior art, embodiments of the present invention provide a method, apparatus, medium, and equipment for determining the roll plan for a finishing mill, so as to solve or partially solve the technical problems in the prior art that the determination of the roll plan for a finishing mill is time-consuming and labor-intensive, affecting rolling efficiency.

[0006] A first aspect of the present invention provides a method for determining a roll plan for a finishing machine, the method comprising:

[0007] The historical process data of the polishing machine is preprocessed, and the correlation analysis is performed on the preprocessed historical process data to obtain the target attribute parameters corresponding to the roller plan of the polishing machine.

[0008] A recommended model for the roller plan of the optical finishing machine is constructed based on the target attribute parameters;

[0009] Read the order plan information and extract the current parameter value of the target attribute parameter in the order plan information;

[0010] Based on the current parameter values, the recommended model is used to output roller information.

[0011] In the above scheme, the preprocessing of historical process data of the optical assembly includes:

[0012] Obtain the surface roughness and finishing rate of each steel coil;

[0013] Historical process data whose roughness is not within the preset roughness range will be removed, as will historical process data whose roughness is less than the smoothing rate threshold.

[0014] In the above scheme, the step of performing correlation analysis on the preprocessed historical process data to obtain the target attribute parameters corresponding to the roller plan for the finishing machine includes:

[0015] For any attribute parameter, use the formula Determine the intrinsic value IV(t) for each attribute parameter;

[0016] Using the formula Gain(T,t)=Ent(T)-Ent(T) m The information gain value Gain(T,t) for each attribute parameter is determined.

[0017] According to the formula Determine the information gain ratio for each attribute parameter;

[0018] The attribute parameter whose information gain ratio is greater than the gain ratio threshold is determined as the target attribute parameter;

[0019] The target attribute parameters include: roughness range, strength, application, finishing rate, order thickness, and sorting degree; T is the set of all historical process data; t is the type of attribute parameter; V is the set of all possible attribute values ​​for attribute parameter t; v is one of the attribute values ​​in the attribute value set; Tv is the number of attribute parameters in set T when the attribute parameter t is v; Ent(T) is the information entropy of the roller roughness, and Ent(T) is the information entropy of the roller roughness. m ,t) is the information entropy after dividing historical process data into m categories according to the type t of the attribute parameter.

[0020] The attribute parameters whose information gain ratio is greater than the gain ratio threshold are determined as the target attribute parameters; the target attribute parameters include: roughness range, intensity, application, smoothing rate, order thickness and sorting degree.

[0021] In the above scheme, the recommendation model includes: a precise matching model, a univariate expanded screening matching model, and a multivariate expanded screening matching model; the recommendation model for constructing the roller plan for the finishing machine based on the target attribute parameters includes:

[0022] Set precise matching conditions for each target attribute parameter, and construct a precise matching model based on the precise matching conditions;

[0023] A reference selection parameter is determined from the target attribute parameter, a univariate expanded screening condition is set for each reference attribute parameter, and a univariate expanded screening matching model is constructed based on the univariate expanded screening condition.

[0024] Set corresponding multivariate expanded filtering conditions for all target attribute parameters, and construct a multivariate expanded filtering matching model based on the multivariate expanded filtering conditions.

[0025] In the above scheme, the step of outputting roller information based on the current parameter value using the recommendation model includes:

[0026] For each target attribute parameter's current parameter value, a precise matching model is used to match each of the current parameter values ​​in the database one by one;

[0027] If each current parameter value can be matched successfully, the corresponding roller information is found based on the first parameter value combination; the first parameter value combination includes the current parameter value of each target attribute parameter.

[0028] In the above scheme, the step of outputting roller information based on the current parameter value using the recommendation model includes:

[0029] If any current parameter value fails to match, the current parameter value of the reference attribute parameter is adjusted based on the univariate expanded filtering matching model to obtain the adjusted first parameter value.

[0030] Using the precise matching model, the first parameter value after adjustment of the reference attribute parameter and the current parameter value of the remaining target attribute parameter are matched in the database. If all attribute parameters can be matched successfully, the corresponding roller information is searched according to the second parameter value combination. The second parameter value combination includes the first parameter value after adjustment of the reference attribute parameter and the current parameter value of the first remaining target attribute parameter.

[0031] In the above scheme, the step of outputting roller information based on the current parameter value using the recommendation model includes:

[0032] If any attribute parameter fails to match, the current parameter values ​​of multiple target attribute parameters are adjusted based on the multivariate expanded filtering matching model to obtain the adjusted second parameter value.

[0033] Using the precise matching model, the second parameter values ​​of multiple target attribute parameters and the current parameter values ​​of the remaining target attribute parameters are matched in the database. If all attribute parameters can be matched successfully, the corresponding roller information is searched according to the combination of third parameter values. The combination of third parameter values ​​includes: the second parameter values ​​of multiple target attribute parameters and the current parameter values ​​of the second remaining target attribute parameters.

[0034] A second aspect of the present invention provides an apparatus for determining a plan of rollers for a finishing machine, the apparatus comprising:

[0035] The preprocessing unit is used to preprocess the historical process data of the optical finishing machine and perform correlation analysis on the preprocessed historical process data to obtain the target attribute parameters corresponding to the roller plan of the optical finishing machine.

[0036] A construction unit is used to construct a recommended model for the roller plan of the optical finishing machine based on the target attribute parameters;

[0037] The reading unit is used to read order plan information and extract the current parameter value of the target attribute parameter in the order plan information;

[0038] The output unit is used to output roller information based on the current parameter value and the recommended model.

[0039] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0040] A fourth aspect of the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method described in any of the first aspects.

[0041] This invention provides a method, apparatus, medium, and equipment for determining the roll usage plan for a finishing mill. The method includes: preprocessing historical process data of the finishing mill and performing correlation analysis on the preprocessed historical process data to obtain target attribute parameters corresponding to the roll usage plan; constructing a recommendation model for the roll usage plan based on the target attribute parameters; reading order plan information and extracting the current parameter values ​​of the target attribute parameters from the order plan information; and outputting roll usage information based on the current parameter values ​​using the recommendation model. Thus, by first determining the target attribute parameters that are closely related to the roll usage plan and constructing a recommendation model for the roll usage plan based on the target attribute parameters, the recommendation model can quickly and effectively output the corresponding roll usage information for the current order plan, eliminating the need for time-consuming and laborious manual table lookup to determine roll information and ensuring rolling efficiency. Attached Figure Description

[0042] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings.

[0043] In the attached diagram:

[0044] Figure 1 A schematic flowchart of a method for determining the roll plan for a finishing machine according to an embodiment of the present invention is shown;

[0045] Figure 2 A schematic diagram of the structure of a roller device for determining a finishing mill according to an embodiment of the present invention is shown;

[0046] Figure 3 A schematic diagram of a computer device structure according to an embodiment of the present invention is shown;

[0047] Figure 4 A schematic diagram of a computer-readable storage medium structure according to an embodiment of the present invention is shown. Detailed Implementation

[0048] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0049] This invention provides a method for determining the roll plan for a finishing machine, such as... Figure 1 As shown, the method includes the following steps:

[0050] S110: Preprocess the historical process data of the finishing machine, and perform correlation analysis on the preprocessed historical process data to obtain the target attribute parameters corresponding to the roller plan of the finishing machine.

[0051] Because the finishing mill involves many process parameters during steel coil rolling, some of these parameters are closely related to the mill's roll plan. Inappropriate roll parameters can severely impact the process parameters and consequently the steel coil quality. Therefore, this embodiment requires preprocessing the historical process data of the finishing mill and performing correlation analysis on the preprocessed historical data to obtain the target attribute parameters corresponding to the mill's roll plan.

[0052] In one implementation, the historical process data of the optical assembly is preprocessed, including:

[0053] Obtain the roughness and finish of each steel coil;

[0054] Historical process data whose roughness is not within the preset roughness range will be removed, as will historical process data whose roughness is less than the smoothing rate threshold.

[0055] Specifically, after each steel coil is rolled by the finishing mill, corresponding process data and quality inspection results are generated. These quality inspection results mainly include: surface roughness and finishing rate.

[0056] This embodiment can filter historical process data based on the roughness and finishing rate of the steel coil. For example, it can remove historical process data where the maximum value of the actual roughness of the strip is greater than the upper limit of the target roughness range, remove historical process data where the minimum value of the actual roughness of the strip is less than the lower limit of the target roughness range, and remove historical process data where the difference between the actual value and the target value of the finishing rate is greater than 0.1.

[0057] Then, a correlation analysis was performed on the preprocessed historical process data. The target attribute parameters corresponding to the roller plan for the finishing machine were sorted from largest to smallest correlation, including:

[0058] Using formula Determine the intrinsic value IV(t) for each attribute parameter;

[0059] Using the formula Gain(T,t)=Ent(T)-Ent(T) m The information gain value Gain(T,t) is determined for each attribute parameter.

[0060] Using formula Determine the information gain ratio for each attribute parameter;

[0061] Attribute parameters with information gain ratios greater than a gain ratio threshold are defined as target attribute parameters; where,

[0062] IV(t) represents the inherent value of each attribute parameter, T is the set of all historical process data, t is the type of the attribute parameter, V is the set of all possible attribute values ​​for attribute parameter t, v is one of the attribute values ​​in the set of attribute values, and T... v Ent(T) represents the number of elements in set T when the attribute parameter t takes the value v; Ent(T) represents the information entropy of the roller roughness. m ,t) is the information entropy after dividing historical process data into m categories according to the type t of the attribute parameter.

[0063] Specifically, the information gain ratio Gain_ratio(T,t) ranges from 0 to 1, with a larger value indicating a greater degree of correlation. In this embodiment, attribute parameters with an information gain ratio greater than the gain ratio threshold are defined as target attribute parameters.

[0064] Based on the above calculations, the information gain ratio table of the attribute parameters is obtained, as shown in Table 1. The target attribute parameters in this embodiment include: roughness range, application, order thickness, finishing rate, strength, coating type, RPC, and order sorting degree.

[0065] The higher the information gain ratio, the greater the influence of the attribute on the roll usage plan. In this embodiment, parameters with high correlation (information gain ratio ≥ 0.1) are selected as target attribute parameters, including: roughness range, application, order thickness, finishing rate, strength, coating type, RPC, and order sorting degree.

[0066] Table 1

[0067]

[0068] In addition, after preprocessing the historical process data of the optical assembly, the method also includes:

[0069] The preprocessed data is stored in a database, and then grouped and aggregated within the database.

[0070] Preprocessing historical process data refers to removing historical process data that does not meet quality standards, such as removing data records where the actual roughness exceeds the range, resulting in the strip steel being deemed unqualified.

[0071] To improve the retrieval efficiency of the recommendation model for subsequent roll usage plans, this embodiment performs grouping and aggregation on the preprocessed data in the database. Grouping and aggregation utilizes Python's `groupby` function to arrange the data consecutively according to the type and value of the target attribute parameters. For example, the data can first be sorted by steel coil strength, with those of the same strength arranged consecutively. Then, within the data with the same strength, it can be rearranged according to its application, and so on, until all historical process data has been arranged.

[0072] S111, Construct a recommended model for the roller plan of the optical finishing machine based on the target attribute parameters;

[0073] The recommended models for the roller usage plan in this embodiment include: a precise matching model, a univariate expanded screening matching model, and a multivariate expanded screening matching model.

[0074] After the target attribute parameters corresponding to the roller plan for the finishing machine are determined, in one implementation, a recommendation model for the roller plan for the finishing machine is constructed based on the target attribute parameters, including:

[0075] Set precise matching conditions for each target attribute parameter, and build a precise matching model based on the precise matching conditions;

[0076] Determine reference selection parameters from the target attribute parameters, set univariate expanded screening conditions for each reference attribute parameter, and construct a univariate expanded screening matching model based on the univariate expanded screening conditions.

[0077] Set corresponding multivariate expanded filtering conditions for all target attribute parameters, and construct a multivariate expanded filtering matching model based on the multivariate expanded filtering conditions.

[0078] Specifically, the logic of the precise matching model is to search the database for parameter combinations that match the current parameter values ​​of all target attribute parameters.

[0079] Here, the matching conditions for the precise matching model are: Plan strength == database strength & Plan thickness == database thickness & Plan roughness range == database roughness range & Plan smoothing rate == database smoothing rate & Plan purpose == database purpose & Plan minimum RPC <= database minimum RPC value.

[0080] RPC refers to one of the roughness parameters of strip steel, which is defined as the number of roughness profile elements that continuously pass through the specified upper and lower profile cutoff lines within a unit length in the roughness profile.

[0081] As can be seen, in the precise matching model, for target attribute parameters such as strength, thickness, roughness range, smoothing rate, and application, the current value on the plan must be completely consistent with the value in the database. For RPC, the current RPC value on the plan only needs to be less than or equal to the minimum RPC value in the database.

[0082] However, in reality, it is very likely that a completely consistent combination of parameters cannot be found. In such cases, it is necessary to determine the reference attribute parameters from the target attribute parameters and adjust the current parameter values ​​of the reference attribute parameters. That is, to set univariate expanded filtering conditions for each reference attribute parameter, thereby obtaining a univariate expanded filtering matching model.

[0083] This embodiment has three univariate expanded screening criteria:

[0084] The first type: Plan strength == database strength & (database thickness - 0.1 <= plan thickness <= database thickness + 0.1) & plan roughness range == database roughness range & plan smoothing rate == database smoothing rate & plan purpose == database purpose & plan RPC minimum <= database RPC minimum.

[0085] Following the precise matching model described above, the current parameter value of the plan sheet thickness needs to be adjusted to [database thickness - 0.1, database thickness + 0.1]. For target attribute parameters such as strength, roughness range, smoothing rate, and application, the current value on the plan sheet must be completely consistent with the value in the database; for RPC, the current RPC value on the plan sheet only needs to be less than or equal to the minimum RPC value in the database; for thickness, if the plan sheet thickness meets the range of [database thickness - 0.1, database thickness + 0.1], then the match is successful.

[0086] The second method: Plan strength == database strength & plan thickness == database thickness & plan roughness range == database roughness range & (database smoothing rate - 0.1 <= plan smoothing rate <= database smoothing rate + 0.1) & plan purpose == database purpose & plan minimum RPC <= database minimum RPC.

[0087] Under these conditions, the current parameter value of the finishing rate on the project plan needs to be adjusted to [database finishing rate - 0.1, database finishing rate + 0.1]. For target attribute parameters such as strength, thickness, roughness range, and application, the current value on the project plan must be completely consistent with the value in the database; for RPC, the current RPC value on the project plan only needs to be less than or equal to the minimum RPC value in the database; for the finishing rate, if the finishing rate on the project plan meets the range of [database finishing rate - 0.1, database finishing rate + 0.1], then the match is successful.

[0088] The third type: Plan strength == database strength & plan thickness == database thickness & plan roughness range == database roughness range & plan smoothing rate == database smoothing rate & (database usage - 1 <= plan usage <= database usage + 1) & plan minimum RPC <= database minimum RPC.

[0089] Under these conditions, the current parameter values ​​for the purpose of the planning order need to be adjusted to [database purpose - 1, database purpose + 1]. For target attribute parameters such as strength, thickness, roughness range, and smoothing rate, the current values ​​on the planning order must be completely consistent with the values ​​in the database; for RPC, the current RPC value on the planning order only needs to be less than or equal to the minimum RPC value in the database; for the purpose, if the smoothing rate of the planning order meets the range of [database smoothing purpose - 1, database purpose + 1], then the match is successful.

[0090] It should be noted that the uses in the database are arranged by number, and different numbers represent different uses. Database use -1 means shifting the use number up one position, and database use +1 means shifting the use number down one position.

[0091] Furthermore, if a completely consistent parameter combination still cannot be found after univariate broadening screening, then multivariate broadening screening is needed for multiple target attribute parameters to obtain the multivariate broadening screening conditions corresponding to the multivariate broadening screening matching model:

[0092] Database strength -1 <= Plan strength <= Database strength +1) & (Database thickness -0.1 <= Plan thickness <= Database thickness +0.1) & Plan roughness range == Database roughness range & (Database smoothing rate -0.1 <= Plan smoothing rate <= Database smoothing rate +0.1) & (Database usage -1 <= Plan usage <= Database usage +1) & Plan minimum RPC <= Database minimum RPC.

[0093] It can be seen that when expanding the screening using multiple variables, the values ​​of strength, thickness, smoothness rate, and application need to be adjusted, while the roughness range and RPC do not need to be adjusted.

[0094] It should also be noted that the strengths are arranged by number in the database, and different numbers represent different strengths. Database strength -1 means shifting the strength number up one position, and database strength +1 means shifting the application number down one position.

[0095] This approach, by constructing precise matching models, univariate expanded screening matching models, and multivariate expanded screening matching models, provides support for the subsequent automatic output of roller plans.

[0096] S112, Read the order plan information and extract the current parameter value of the target attribute parameter in the order plan information;

[0097] This embodiment also includes a user interface. When it is necessary to configure the corresponding light-finishing roller for a new order, the user can import the order plan through the interface. Then the server can read the order plan information and extract the current parameter value of the target attribute parameter in the order plan information.

[0098] The user interface is developed based on Python's built-in library tkinter, which provides basic controls commonly used in interface development such as buttons, labels, tables, input boxes, and pop-ups, and uses ttkbootstrap library functions to beautify the interface.

[0099] S113, Based on the current parameter values, output the roller information using the recommended model.

[0100] After reading the current parameter values ​​of each target attribute parameter, the roller information is output using the recommendation model.

[0101] In one implementation, based on the current parameter values, a recommendation model is used to output roller information, including:

[0102] For each target attribute parameter's current parameter value, a precise matching model is used to match each of the current parameter values ​​in the database one by one;

[0103] If each current parameter value can be matched successfully, the corresponding roller information is found based on the first parameter value combination; the first parameter value combination includes the current parameter value of each target attribute parameter.

[0104] If any current parameter value fails to match, in one implementation, based on the current parameter value, the recommended model is used to output roller information, including:

[0105] If any current parameter value fails to match, the current parameter value of the reference attribute parameter is adjusted based on the univariate expanded filtering matching model to obtain the adjusted first parameter value.

[0106] Using a precise matching model, the first parameter value after adjustment of the reference attribute parameter and the current parameter value of the remaining target attribute parameter are matched in the database. If all attribute parameters can be matched successfully, the corresponding roller information is found based on the combination of the second parameter values. The combination of the second parameter values ​​includes the first parameter value after adjustment of the reference attribute parameter and the current parameter value of the first remaining target attribute parameter.

[0107] If a match still cannot be found after expanding the univariate screening, then in one implementation, based on the current parameter values, the roller information is output using a recommendation model, including:

[0108] If any attribute parameter fails to match, the current parameter values ​​of multiple target attribute parameters are adjusted based on the multivariate expanded filtering matching model to obtain the adjusted second parameter value.

[0109] Using the precise matching model, the second parameter values ​​of multiple target attribute parameters and the current parameter values ​​of the remaining target attribute parameters are matched in the database. If all attribute parameters can be matched successfully, the corresponding roller information is searched according to the combination of third parameter values. The combination of third parameter values ​​includes: the second parameter values ​​of multiple target attribute parameters and the current parameter values ​​of the second remaining target attribute parameters.

[0110] Among them, multiple target attribute parameters include: intensity, thickness, smoothness ratio and application; the second remaining target attribute parameters include: roughness range and RPC.

[0111] In this embodiment, the information on the rolls used includes: roll diameter, roll roughness, historical maximum roughness, historical minimum roughness, historical average roughness, historical average rolling force, historical average inlet tension, historical average outlet tension, historical average RPC, and historical coil information.

[0112] Among them, the historical maximum roughness is the maximum strip roughness taken from the column of maximum strip roughness in the corresponding historical process parameters under the recommended roll diameter and roll roughness.

[0113] The historical minimum roughness value is the minimum strip roughness taken from the minimum strip roughness column in the corresponding historical process parameters under the recommended roll diameter and roll roughness.

[0114] The historical average roughness is the sum of the maximum and minimum roughness values ​​of the strip steel under the recommended roll diameter and roll roughness.

[0115] The historical average rolling force is the average value of the rolling force column in the corresponding historical process parameters under the recommended roll diameter and roll roughness.

[0116] The historical average inlet tension is the average value of the inlet tension column in the corresponding historical process parameters under the recommended roller diameter and roller roughness.

[0117] The historical average exit tension is the average value of the exit tension column in the corresponding historical process parameters under the recommended roller diameter and roller roughness.

[0118] The historical RPC average is the average value of the RPC column in the corresponding historical process parameters under the recommended roller diameter and roller roughness.

[0119] Historical steel coil information refers to the process parameters that are inconsistent with the order plan under the recommended roll diameter and roll roughness.

[0120] This embodiment first determines the target attribute parameters that are closely related to the roll usage plan, and then constructs a recommended model for the roll usage plan based on the target attribute parameters. The recommended model can quickly and effectively output the corresponding roll usage information for the current order plan, without the need for time-consuming and laborious manual table lookup to determine the roll information, thus ensuring rolling efficiency.

[0121] Based on the same inventive concept as in the foregoing embodiments, this embodiment also provides a device for determining the plan of rollers for finishing machines, such as... Figure 2 As shown, the device includes:

[0122] The preprocessing unit 21 is used to preprocess the historical process data of the optical finishing machine and perform correlation analysis on the preprocessed historical process data to obtain the target attribute parameters corresponding to the roller plan of the optical finishing machine.

[0123] Construction unit 22 is used to construct a recommended model for the roller plan of the optical finishing machine based on the target attribute parameters;

[0124] The reading unit 23 is used to read order plan information and extract the current parameter value of the target attribute parameter in the order plan information;

[0125] Output unit 24 is used to output roller information based on the current parameter value and the recommended model.

[0126] Since the apparatus described in the embodiments of the present invention is used for implementing the method of roller planning for finishing machines according to the embodiments of the present invention, those skilled in the art can understand the specific structure and variations of the apparatus based on the method described in the embodiments of the present invention, and therefore will not be described in detail here. All apparatuses used in the methods of the embodiments of the present invention fall within the scope of protection of the present invention.

[0127] The beneficial effects of the method, apparatus, medium, and equipment for determining the roll plan for finishing machines provided in this embodiment of the invention are at least as follows:

[0128] Based on the same inventive concept, this embodiment provides a computer device 300, such as... Figure 3 As shown, it includes a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, it implements any step of the method described above.

[0129] Based on the same inventive concept, this embodiment provides a computer-readable storage medium 400, such as... Figure 4 As shown, a computer program 411 is stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0130] Through one or more embodiments of the present invention, the present invention has the following beneficial effects or advantages:

[0131] This embodiment provides a method, apparatus, medium, and equipment for determining the roll plan for a finishing mill. The method includes: preprocessing historical process data of the finishing mill and performing correlation analysis on the preprocessed historical process data to obtain target attribute parameters corresponding to the roll plan for the finishing mill; constructing a recommendation model for the roll plan for the finishing mill based on the target attribute parameters; reading order plan information and extracting the current parameter values ​​of the target attribute parameters from the order plan information; and outputting roll information based on the current parameter values ​​using the recommendation model. In this way, the target attribute parameters that are more relevant to the roll plan are first determined, and the recommendation model for the roll plan is constructed based on the target attribute parameters. The recommendation model can quickly and effectively output the corresponding roll information for the current order plan without the need for time-consuming and laborious manual table lookup to determine the roll information, thus ensuring rolling efficiency.

[0132] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0133] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0134] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0135] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0136] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0137] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components of the gateway, proxy server, or system according to embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing some or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0138] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0139] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0140] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method of determining a plan for a finishing machine roll, characterized by, The method comprises: preprocessing historical process data of a skin pass mill, and performing correlation analysis on the pretreated historical process data to obtain target attribute parameters corresponding to a skin pass mill roll plan; constructing a recommendation model of the skin pass mill roll plan according to the target attribute parameters; reading order plan information, and extracting current parameter values of target attribute parameters in the order plan information; based on the current parameter values, outputting roll information by using the recommendation model; wherein the correlation analysis on the pretreated historical process data to obtain target attribute parameters corresponding to a skin pass mill roll plan comprises: For any attribute parameter, the attribute inherent value of each attribute parameter is determined using the formula IV t );​​ Using the formula determining the information gain value of each attribute parameter According to the formula determining the information gain rate of each attribute parameter; determining attribute parameters with information gain rates greater than a gain rate threshold as the target attribute parameters; The target attribute parameters include: roughness range, intensity, application, smoothing rate, order thickness, and sorting degree; T It is a collection of all historical process data; t The type of the attribute parameter; V For attribute parameters t The set of all possible attribute values; the v For one of the attribute values ​​in the attribute value set; the T v For when attribute parameter t Values v At that time, in the set T The quantity in; the quantity in The information entropy of the roller roughness, the To determine the type of the attribute parameter t Historical process data is divided into m Information entropy after class.

2. The method of claim 1, wherein, the preprocessing of the historical process data of the skin pass mill comprises: obtaining the roughness of each steel coil and the skin pass rate; eliminating historical process data with roughness not in a preset roughness range, and eliminating historical process data corresponding to a skin pass rate less than a skin pass rate threshold.

3. The method of claim 1, wherein, The recommendation model comprises: a precise matching model, a single-variable expanded screening matching model, and a multi-variable expanded screening matching model; and the construction of the recommendation model of the skin pass mill roll plan according to the target attribute parameters comprises: setting a precise matching condition for each target attribute parameter, and constructing a precise matching model based on the precise matching condition; determining reference attribute parameters in the target attribute parameters, setting a single-variable expanded screening condition for each reference attribute parameter, and constructing a single-variable expanded screening matching model based on the single-variable expanded screening condition; setting corresponding multi-variable expanded screening conditions for all target attribute parameters, and constructing a multi-variable expanded screening matching model based on the multi-variable expanded screening conditions.

4. The method of claim 1, wherein, The outputting of roll information by using the recommendation model based on the current parameter values comprises: for each current parameter value of a target attribute parameter, performing one-to-one matching of each current parameter value in a database based on a precise matching model; if each current parameter value can be successfully matched, searching for corresponding roll information according to a first parameter value combination; the first parameter value combination comprises current parameter values of each target attribute parameter.

5. The method of claim 4, wherein, The outputting of roll information by using the recommendation model based on the current parameter values comprises: if any current parameter value fails to be matched, adjusting the current parameter value of the reference attribute parameter based on a single-variable expanded screening matching model to obtain an adjusted first parameter value; using the precise matching model to match the adjusted first parameter value of the reference attribute parameter and the current parameter values of the remaining target attribute parameters in the database, and if all attribute parameters can be successfully matched, searching for corresponding roll information according to a second parameter value combination; the second parameter value combination comprises the adjusted first parameter value of the reference attribute parameter and the current parameter values of the first remaining target attribute parameters.

6. The method of claim 5, wherein, The outputting of roll information by using the recommendation model based on the current parameter values comprises: if any attribute parameter fails to be matched, adjusting the current parameter values of multiple target attribute parameters based on a multi-variable expanded screening matching model to obtain adjusted second parameter values; The precision matching model is used to match second parameter values of the target attribute parameters and current parameter values of the remaining target attribute parameters in the database, and if all attribute parameters are successfully matched, corresponding roll information is found according to a third parameter value combination; the third parameter value combination includes the second parameter values of the target attribute parameters and the current parameter values of the second remaining target attribute parameters.

7. An apparatus for determining the plan of rollers for a finishing machine, characterized in that, The device comprises: a preprocessing unit configured to preprocess historical process data of the finishing mill, perform correlation analysis on the preprocessed historical process data, and obtain target attribute parameters corresponding to the finishing mill roll plan; a construction unit configured to construct a recommendation model of the finishing mill roll plan according to the target attribute parameters; a reading unit configured to read order plan information and extract current parameter values of target attribute parameters in the order plan information; an output unit configured to output roll information based on the current parameter values and using the recommendation model; and the correlation analysis on the preprocessed historical process data to obtain the target attribute parameters corresponding to the finishing mill roll plan comprises: For any attribute parameter, the attribute intrinsic value of each attribute parameter is determined using the formula IV t )​​ Using the formula determining the information gain value of each attribute parameter According to the formula determining the information gain rate of each attribute parameter; determining attribute parameters with information gain rates greater than a gain rate threshold as the target attribute parameters; The target attribute parameters include: roughness range, intensity, application, smoothing rate, order thickness, and sorting degree; T It is a collection of all historical process data; t The type of the attribute parameter; V For attribute parameters t The set of all possible attribute values; the v For one of the attribute values ​​in the attribute value set; the T v For when attribute parameter t Values v At that time, in the set T The quantity in; the quantity in The information entropy of the roller roughness, the To determine the type of the attribute parameter t Historical process data is divided into m Information entropy after class.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of any one of claims 1-6.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the steps of the method of any one of claims 1-6.

Images