Method, device, electronic equipment and medium for recommending rolling procedure parameters

Abstract

The present invention is applicable to the field of rolling technology and provides a method, device, electronic equipment and medium for recommending rolling procedure parameters, wherein the method includes: obtaining a rolling data set and target rolling process parameters, the rolling data set including several historical rolling evaluation parameters; screening the rolling data set according to the target rolling process parameters to obtain several first rolling evaluation parameter data sets; scoring the first rolling evaluation parameters according to preset evaluation indicators to obtain scores corresponding to each first rolling evaluation parameter; determining second rolling evaluation parameters according to the scores corresponding to the first rolling evaluation parameters, and recommending target rolling procedure parameters according to the second rolling evaluation parameters; solving the problems of low rolling efficiency caused by unreasonable setting of rolling procedure parameters in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of rolling technology, and in particular to a method, device, electronic equipment and medium for recommending rolling procedure parameters. Background Art

[0002] With the development of science and technology, computer technology is being applied to various industries, such as the rolling industry. In the optimization of procedures in the rolling industry, there are methods that use computer technology to predict the performance of microstructures after rolling, thereby guiding manual optimization design of the selection and layout of major equipment in engineering workshops; there are also methods that use innovative computer algorithms, for example, by combining particle swarm optimization with dynamic programming to optimize the rolling procedures, thereby achieving the goal of improving rolling efficiency. However, the current application of computers in the rolling industry mostly ignores the hidden dangers of starting rolling. When starting rolling, it is often necessary to continuously adjust the rolling procedure parameters to achieve a stable rolling state. This adjustment process usually takes several steel-passing times, which can easily cause problems such as steel piling. Summary of the Invention

[0003] The present invention provides a method, device, electronic equipment and medium for recommending rolling schedule parameters, so as to solve the problem of low rolling efficiency caused by unreasonable setting of rolling schedule parameters.

[0004] The method for recommending rolling procedure parameters provided by the present invention includes:

[0005] Acquiring a rolling data set and target rolling process parameters, wherein the rolling data set includes a plurality of historical rolling evaluation parameters;

[0006] screening the rolling data set according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets, wherein the first plurality of first rolling evaluation parameter data sets include a plurality of first rolling evaluation parameters;

[0007] Scoring the first rolling evaluation parameters according to preset evaluation indicators to obtain scores corresponding to the first rolling evaluation parameters;

[0008] A second rolling evaluation parameter is determined according to the score corresponding to the first rolling evaluation parameter, and a target rolling procedure parameter is recommended according to the second rolling evaluation parameter.

[0009] Optionally, the screening of the rolling data set according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets includes:

[0010] Performing a first classification process on the rolling data set according to a preset classification rule to obtain a plurality of rolling sub-data sets;

[0011] Deleting abnormal data from the rolling sub-dataset to obtain a target sub-dataset;

[0012] The target sub-dataset is screened according to the target rolling process parameters to obtain a plurality of the first rolling evaluation parameter data sets.

[0013] Optionally, the step of deleting abnormal data from the rolling sub-dataset to obtain a target sub-dataset includes:

[0014] Obtaining the mean of the rolling sub-dataset and the standard deviation of the rolling sub-dataset;

[0015] The rolling sub-dataset is processed by deleting abnormal data according to the mean value of the rolling sub-dataset and the standard deviation of the rolling sub-dataset to obtain a target sub-dataset.

[0016] Optionally, the step of performing abnormal data deletion processing on the rolling sub-dataset according to the mean of the rolling sub-dataset and the standard deviation of the rolling sub-dataset to obtain the target sub-dataset includes:

[0017] Deleting abnormal data from the rolling sub-dataset according to the mean value of the rolling sub-dataset and the standard deviation of the rolling sub-dataset to obtain an intermediate sub-dataset;

[0018] Performing clustering processing on the intermediate sub-dataset to obtain cluster centers and cluster data sets;

[0019] Get the distance between the data in the cluster data set and the cluster center to get the cluster data distance;

[0020] The cluster data set is processed by deleting abnormal data according to the cluster data distance and the preset cluster distance to obtain the target sub-data set.

[0021] Optionally, the scoring process of the first rolling evaluation parameters according to the preset evaluation index to obtain the scores corresponding to the respective first rolling evaluation parameters includes:

[0022] performing a second classification process on the first rolling evaluation parameter according to the evaluation parameter category to obtain a plurality of rolling evaluation classification parameters;

[0023] Scoring each rolling evaluation classification parameter according to the preset evaluation index to obtain the score corresponding to each rolling evaluation classification parameter;

[0024] Based on a preset weight coefficient, the scores corresponding to the various rolling evaluation classification parameters are weighted to obtain a score corresponding to the first rolling evaluation parameter.

[0025] Optionally, determining a second rolling evaluation parameter according to the score corresponding to the first rolling evaluation parameter, and recommending a target rolling procedure parameter according to the second rolling evaluation parameter includes:

[0026] Determine the first rolling evaluation parameter corresponding to the highest score to obtain the second rolling evaluation parameter;

[0027] screening the first rolling evaluation parameter according to the second rolling evaluation parameter and the first preset distance threshold to obtain a plurality of third rolling evaluation parameters;

[0028] acquiring a distance between the third rolling evaluation parameter and the second rolling evaluation parameter to obtain a target distance of the third rolling evaluation parameter;

[0029] Obtain the score corresponding to the third rolling evaluation parameter, determine the recommended score of the third rolling evaluation parameter based on the target distance of the third rolling evaluation parameter and the score corresponding to the third rolling evaluation parameter, and recommend the target rolling procedure parameter based on the recommended score.

[0030] Optionally, determining the first rolling evaluation parameter corresponding to the highest score to obtain the second rolling evaluation parameter includes:

[0031] screening the first rolling evaluation parameter data set according to a second preset distance threshold and a preset data volume threshold to obtain a target rolling evaluation parameter data set;

[0032] The first rolling evaluation parameter corresponding to the highest score in the target rolling evaluation parameter data set is determined to obtain a second rolling evaluation parameter.

[0033] Optionally, determining the recommended score of the third rolling evaluation parameter according to the target distance of the third rolling evaluation parameter and the score corresponding to the third rolling evaluation parameter includes:

[0034] Set distance weight and score weight;

[0035] determining a distance recommendation parameter according to the distance weight and the target distance of the third rolling evaluation parameter;

[0036] Determining a score recommendation parameter according to the score weight and the score corresponding to the third rolling parameter;

[0037] A recommendation score for the third rolling parameter is obtained according to the distance recommendation parameter and the score recommendation parameter.

[0038] Optionally, the mathematical expression of the recommended score of the third rolling evaluation parameter is:

[0039] score_dist=dist*wx+(1-final_score)*wy;

[0040] Among them, score_dist is the recommended score of the third rolling evaluation parameter, dist is the target distance of the third rolling evaluation parameter, wx is the distance weight, final_score is the score corresponding to the third rolling evaluation parameter, and wy is the score weight.

[0041] The present invention also provides a device for recommending rolling procedure parameters, comprising:

[0042] A parameter acquisition module, configured to acquire a rolling data set and target rolling process parameters, wherein the rolling data set includes a plurality of historical rolling evaluation parameters;

[0043] a data set screening module, configured to screen the rolling data set according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets, wherein the first plurality of first rolling evaluation parameter data sets include a plurality of first rolling evaluation parameters;

[0044] a scoring processing module, configured to score the first rolling evaluation parameters according to preset evaluation indicators to obtain scores corresponding to the first rolling evaluation parameters;

[0045] A parameter recommendation module is used to determine the second rolling evaluation parameter based on the score corresponding to the first rolling evaluation parameter, and recommend the target rolling procedure parameter based on the second rolling evaluation parameter. The parameter acquisition module, the data set screening module, the scoring processing module and the parameter recommendation module are connected.

[0046] The present invention also provides an electronic device, comprising: a processor and a memory;

[0047] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method for recommending rolling procedure parameters.

[0048] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for recommending rolling procedure parameters as described above.

[0049] Beneficial effects of the present invention: The method for recommending rolling procedure parameters in the present invention first obtains a rolling data set and target rolling process parameters, the rolling data set including several historical rolling evaluation parameters; secondly, the rolling data set is screened according to the target rolling process parameters to obtain several first rolling evaluation parameter data sets; then, the first rolling evaluation parameters are scored according to preset evaluation indicators to obtain scores corresponding to each first rolling evaluation parameter; finally, the second rolling evaluation parameters are determined according to the scores corresponding to the first rolling evaluation parameters, and the target rolling procedure parameters are recommended according to the second rolling evaluation parameters; thereby, the recommendation of rolling procedure parameters is realized, which facilitates the reasonable setting of rolling procedure parameters, and further solves the problems of low rolling efficiency and steel piling caused by unreasonable setting of rolling procedure parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. 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.

[0051] Figure 1 1 is a flow chart of a method for recommending rolling procedure parameters according to an embodiment of the present invention;

[0052] Figure 2 is a flow chart of a method for acquiring a first rolling evaluation parameter data set in an embodiment of the present invention;

[0053] Figure 3 1 is a schematic diagram of a module of a device for recommending rolling procedure parameters according to an embodiment of the present invention;

[0054] Figure 4 2 is a schematic structural diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0056] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0057] In order to illustrate the technical solution of the present invention, specific embodiments are provided below.

[0058] Figure 1 1 is a flow chart of a method for recommending rolling procedure parameters provided in one embodiment of the present invention.

[0059] like Figure 1 As shown, the method for recommending the rolling procedure parameters includes steps S110-S140:

[0060] S110, obtaining a rolling data set and target rolling process parameters.

[0061] It should be noted that the rolling data includes several historical rolling evaluation parameters, several historical rolling process parameters and several historical rolling procedure parameters. The historical rolling evaluation parameters include but are not limited to the shape of the product, the size of the product, the bite coefficient, the tension coefficient, the loop coefficient. If the rolled product is a cylindrical wire rod, the shape of the product includes ovality. The historical rolling process parameters include but are not limited to the start rolling time (which can be specific to seconds), production line, steel type, billet specifications (width * height * length), product specifications, furnace temperature, and start rolling temperature. The historical rolling procedure parameters include the historical rolling speed and the historical rolling elongation. The target rolling process parameters are the rolling process parameters corresponding to the recommended rolling procedure parameters.

[0062] In one embodiment, after obtaining the rolling data set, the data in the rolling data set needs to be cleaned. The implementation method of cleaning the data in the rolling data set may include sorting the furnace discharge time according to the furnace discharge time parameter, and supplementing the missing values ​​of the retrieved rolling process data; the specific implementation method of supplementing the missing values ​​may include filling the value of the previous data or deleting the sample.

[0063] S120 , screening the rolling data set according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets.

[0064] It should be understood that the first rolling evaluation parameter data set includes several first rolling evaluation parameters. The method for obtaining several first rolling evaluation parameter data sets by screening the rolling data set according to the target rolling process parameters can be found in Figure 2 , Figure 24 is a flow chart of a method for acquiring a first rolling evaluation parameter data set in one embodiment of the present invention.

[0065] like Figure 2 As shown, the method for obtaining the first rolling evaluation parameter may include the following steps S210-S230:

[0066] S210: Perform a first classification process on the rolling data set according to a preset classification rule to obtain a plurality of rolling sub-data sets.

[0067] It should be noted that the implementation method of performing the first classification processing on the rolling data set according to the preset classification rules may include dividing the rolling data set into several rolling sub-data sets according to different steel grades, different billet specifications, different production lines, different product specifications, different furnace temperature ranges, and different rolling temperature ranges; the furnace temperature range used for dividing the rolling data set into rolling sub-data sets may be the same as or different from the furnace temperature range in the target rolling process parameters; correspondingly, the rolling temperature range used for dividing the rolling data set into rolling sub-data sets may be the same as the rolling temperature range in the target rolling process parameters.

[0068] S220, performing abnormal data deletion processing on the rolling sub-dataset to obtain a target sub-dataset.

[0069] In one embodiment, each rolling sub-data set includes several historical rolling evaluation parameters, and the implementation method of deleting abnormal data in the rolling sub-data set may include: setting a threshold value for each historical rolling evaluation parameter based on historical experience; if the historical rolling evaluation parameter is greater than the threshold value of the historical rolling evaluation parameter, the historical rolling evaluation parameter is abnormal data, and the abnormal data is deleted.

[0070] In one embodiment, performing abnormal data deletion processing on a rolling sub-dataset to obtain a target sub-dataset includes: obtaining the mean of the rolling sub-dataset and the standard deviation of the rolling sub-dataset; performing abnormal data deletion processing on the rolling sub-dataset according to the mean of the rolling sub-dataset and the standard deviation of the rolling data set to obtain the target sub-dataset. The implementation method of performing abnormal data deletion processing on the rolling sub-dataset according to the mean of the rolling sub-dataset and the standard deviation of the rolling data set to obtain the target sub-dataset may include: performing abnormal data deletion processing on the rolling sub-dataset according to the mean of the rolling sub-dataset and the standard deviation of the rolling data set to obtain an intermediate sub-dataset; performing clustering processing on the intermediate sub-dataset to obtain cluster centers and cluster data sets; obtaining the distance between the data in the cluster data set and the cluster center to obtain cluster data distance; performing abnormal data deletion processing on the cluster data set according to the cluster data distance and a preset cluster distance, merging the cluster data sets after abnormal data deletion processing to obtain the target sub-dataset. Performing clustering processing on the intermediate sub-dataset to obtain cluster centers and cluster data sets, and the number of cluster centers can be set according to actual conditions. Gets the distance between the data in a cluster dataset and the cluster center, obtaining only the clusters within the cluster corresponding to the data in each cluster dataset. The preset cluster distance can be set according to user needs. The distance between the data in a cluster dataset and the cluster center can be Euclidean distance or Mahalanobis distance.

[0071] In one embodiment, a method for deleting abnormal data from a rolling sub-dataset based on the mean and standard deviation of the rolling sub-dataset to obtain an intermediate sub-dataset may include: obtaining the mean and standard deviation of each first rolling evaluation parameter in the rolling sub-dataset, obtaining the mean and standard deviation of the first rolling evaluation parameter under the same first rolling evaluation parameter, setting a preset standard deviation threshold based on the standard deviation of the first rolling evaluation parameter, determining a normal data range based on the mean and preset standard deviation threshold of the first rolling evaluation parameter; deleting abnormal data from the first rolling evaluation parameter; and deleting abnormal data for each first rolling evaluation parameter. The preset standard deviation threshold can be set according to user needs, for example, three times the standard deviation of the first rolling evaluation parameter or five times the standard deviation of the first rolling evaluation parameter. When determining the normal data range based on the mean (a) and preset standard deviation threshold (b) of the first rolling evaluation parameter, a±b.

[0072] In one embodiment, performing abnormal data deletion processing on the rolling sub-dataset to obtain a target sub-dataset includes: performing clustering processing on the rolling sub-dataset to obtain a target cluster center and a target cluster data set; obtaining the distance between the data in the target cluster data set and the target cluster center to obtain the target cluster data distance; performing abnormal data deletion processing on the cluster data set according to the target cluster data distance and the preset cluster distance, merging the target cluster data set after the abnormal data deletion processing to obtain an intermediate cluster data set; obtaining the mean of the intermediate cluster data set and the standard deviation of the intermediate cluster data set; performing abnormal data deletion processing on the intermediate cluster data set according to the mean of the intermediate cluster data set and the standard deviation of the intermediate cluster data set to obtain the target sub-dataset. The implementation method of deleting abnormal data from the cluster data set based on the target cluster data distance and the preset cluster distance can refer to the implementation method of deleting abnormal data from the rolling sub-data set based on the mean of the rolling sub-data set and the standard deviation of the rolling data set; the implementation method of deleting abnormal data from the intermediate cluster data set based on the mean of the intermediate cluster data set and the standard deviation of the intermediate cluster data set can refer to the implementation method of deleting abnormal data from the rolling sub-data set based on the mean of the rolling sub-data set and the standard deviation of the rolling data set, which will not be repeated here.

[0073] S230 , screening the target sub-dataset according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets.

[0074] In one embodiment, the target sub-dataset is screened according to the target rolling process parameters, that is, the historical rolling evaluation parameters corresponding to the target rolling process parameters are obtained to obtain a plurality of first rolling evaluation parameter data sets.

[0075] S130 , scoring the first rolling evaluation parameters according to preset evaluation indicators to obtain scores corresponding to the first rolling evaluation parameters.

[0076] In one embodiment, the first rolling evaluation parameter is scored according to the preset evaluation index to obtain the score corresponding to each first rolling evaluation parameter, including: performing a second classification process on the first rolling evaluation parameter according to the evaluation parameter category to obtain a number of rolling evaluation classification parameters; scoring each rolling evaluation classification parameter according to the preset evaluation index to obtain the score corresponding to each rolling evaluation classification parameter; and weighting the score corresponding to each rolling evaluation classification parameter based on the preset weight coefficient to obtain the score corresponding to the first rolling evaluation parameter. Evaluation parameter categories include but are not limited to product shape, product size, bite coefficient, tension coefficient, and loop coefficient. When scoring each rolling evaluation classification parameter according to the preset evaluation index, if there is a preset evaluation index of standard specification for the rolling evaluation classification parameter of this category, then the absolute value diff_abs of the difference between the rolling evaluation classification parameter and the preset evaluation index is calculated. is the absolute value of the difference between the i-th rolling evaluation classification parameter of the j-th first rolling parameter and the preset evaluation index; obtain the maximum and minimum absolute values ​​of the difference between each rolling evaluation classification parameter and the preset evaluation index, and obtain diff_abs_max i and diff_abs_min i , the mathematical expression of the score corresponding to the i-th rolling evaluation classification parameter of the j-th first rolling parameter is:

[0077]

[0078] in, diff_abs_max is the absolute value of the difference between the i-th rolling evaluation classification parameter of the j-th first rolling parameter and the preset evaluation index. i and diff_abs_min i is the maximum and minimum absolute values ​​of the differences between the preset evaluation indicators corresponding to the i-th rolling evaluation classification parameter.

[0079] If there is no preset evaluation index of standard specifications for the rolling evaluation classification parameter of this category, then the mean value of each first rolling parameter on each stand is calculated to obtain dev_mean. is the mean value of the i-th rolling evaluation classification parameter of the j-th first rolling parameter on all stands. Similarly, the standard deviation of the rolling evaluation classification parameter is calculated to obtain dev_std. Dev_mean_max is the standard deviation of the i-th rolling evaluation classification parameter of the j-th first rolling parameter on all stands, and the maximum and minimum values ​​of the mean of all rolling evaluation classification parameters are obtained to obtain dev_mean_max i and dev_mean_min i; Get the maximum and minimum values ​​of the standard deviation of all rolling evaluation classification parameters, and get dev_std_max i and dev_std_min i ; Obtain the mean score of the rolling evaluation classification parameter and the standard deviation score of the rolling evaluation classification parameter, and determine the score corresponding to the rolling evaluation classification parameter based on the mean score of the rolling evaluation classification parameter and the standard deviation score of the rolling evaluation classification parameter.

[0080] The mathematical expression of the average score of the i-th rolling evaluation classification parameter of the j-th first rolling parameter is:

[0081]

[0082] in, is the mean value of the i-th rolling evaluation classification parameter of the j-th first rolling parameter;

[0083] The mathematical expression of the standard deviation score of the i-th rolling evaluation classification parameter of the j-th first rolling parameter is:

[0084]

[0085] in, is the standard deviation of the i-th rolling evaluation classification parameter of the j-th first rolling parameter;

[0086] The mathematical expression of the score corresponding to the i-th rolling evaluation classification parameter of the j-th first rolling parameter is:

[0087]

[0088] Among them, ws is the standard deviation score weight, and wm is the mean score weight.

[0089] The mathematical expression of the score corresponding to the first rolling evaluation parameter of the jth item is:

[0090]

[0091] Among them, final_score is the score corresponding to the first rolling evaluation parameter, j represents the serial number of the first rolling parameter, i is the category label of the rolling evaluation classification parameter, n is the total number of rolling evaluation classification parameter categories, and wi is the preset weight coefficient corresponding to the i-th rolling evaluation classification parameter.

[0092] S140 , determining a second rolling evaluation parameter according to the score corresponding to the first rolling evaluation parameter, and recommending a target rolling procedure parameter according to the second rolling evaluation parameter.

[0093] In one embodiment, determining a second rolling evaluation parameter based on a score corresponding to a first rolling evaluation parameter, and recommending a target rolling procedure parameter based on the second rolling evaluation parameter includes: determining the first rolling evaluation parameter corresponding to the highest score to obtain the second rolling evaluation parameter; screening the first rolling evaluation parameter based on the second rolling evaluation parameter and a first preset distance threshold to obtain a plurality of third rolling evaluation parameters; obtaining the distance between the third rolling evaluation parameter and the second rolling evaluation parameter to obtain a target distance for the third rolling evaluation parameter; obtaining the score corresponding to the third rolling evaluation parameter, determining a recommended score for the third rolling evaluation parameter based on the target distance of the third rolling evaluation parameter and the score corresponding to the third rolling evaluation parameter, and recommending the target rolling procedure parameter based on the recommended score. The target rolling procedure parameter includes a target rolling speed or a target rolling elongation. The distance between the third rolling evaluation parameter and the second rolling evaluation parameter can be a Euclidean distance or a Mahalanobis distance, and the first preset distance threshold can be set based on actual experience.

[0094] In one embodiment, determining the first rolling evaluation parameter corresponding to the highest score to obtain the second rolling evaluation parameter includes: screening the first rolling evaluation parameter data set according to the second preset distance threshold and the preset data volume threshold to obtain the target rolling evaluation parameter data set; determining the first rolling evaluation parameter corresponding to the highest score in the target rolling evaluation parameter data set to obtain the second rolling evaluation parameter. Among them, the first preset distance threshold and the preset data volume threshold can be set according to actual conditions. By screening the first rolling evaluation parameter data set according to the second preset distance threshold and the preset data volume threshold, the target rolling evaluation parameter data set that meets the second preset distance threshold and the preset data volume threshold is determined, and on this basis, the first rolling evaluation parameter corresponding to the highest score in the target rolling evaluation parameter data set is determined to obtain the second rolling evaluation parameter, thereby obtaining the optimal second rolling evaluation parameter, so that the evaluation of the second rolling evaluation parameter is more accurate.

[0095] In one embodiment, a method for implementing screening of a first rolling evaluation parameter based on a second rolling evaluation parameter and a first preset distance threshold may include obtaining the distance between each first rolling evaluation parameter and the second rolling evaluation parameter to obtain a target distance for the first rolling evaluation parameter; comparing the target distance for the first rolling evaluation parameter with the first preset distance threshold to determine the first rolling evaluation parameter corresponding to the first preset distance threshold whose target distance for the first rolling evaluation parameter is less than or equal to the first rolling evaluation parameter to obtain a third rolling evaluation parameter; obtaining the data volume of the third rolling evaluation parameter, comparing the data volume of the third rolling evaluation parameter with the target data volume threshold; if the data volume of all third rolling evaluation parameters is less than the preset data volume, performing attenuation processing on the target data volume threshold to obtain an attenuated data volume threshold; the target data volume threshold may be set based on historical experience.

[0096] The mathematical expression of the attenuation data threshold is:

[0097] decay_thr=support_thr*decay_fact or;

[0098] Where decay_thr is the decay data volume threshold, support_thr is the target data volume threshold, and decay_factor is the decay coefficient.

[0099] In one embodiment, a method for obtaining the distance between the third rolling evaluation parameter and the second rolling evaluation parameter to obtain the target distance of the third rolling evaluation parameter may include obtaining the distance between the third rolling evaluation parameter and the second rolling evaluation parameter to obtain the middle distance of the third rolling evaluation parameter; and normalizing the middle distance of the third rolling evaluation parameter to obtain the target distance of the third rolling evaluation parameter.

[0100] In one embodiment, determining a recommended score for the third rolling evaluation parameter based on a target distance of the third rolling evaluation parameter and a score corresponding to the third rolling evaluation parameter includes: setting a distance weight and a score weight; determining a distance recommendation parameter based on the distance weight and the target distance of the third rolling evaluation parameter; determining a score recommendation parameter based on the score weight and the score corresponding to the third rolling parameter; and obtaining a recommended score for the third rolling parameter based on the distance recommendation parameter and the score recommendation parameter. Both the distance weight and the score weight can be set based on actual experience.

[0101] The mathematical expression of the recommended score of the third rolling evaluation parameter is:

[0102] score_dist=dist*wx+(1-final_score)*wy;

[0103] Among them, score_dist is the recommended score of the third rolling evaluation parameter, dist is the target distance of the third rolling evaluation parameter, wx is the distance weight, final_score is the score corresponding to the third rolling evaluation parameter, and wy is the score weight.

[0104] This embodiment provides a method for recommending rolling schedule parameters. First, a rolling data set and target rolling process parameters are obtained, wherein the rolling data set includes several historical rolling evaluation parameters. Second, the rolling data set is screened according to the target rolling process parameters to obtain several first rolling evaluation parameter data sets. Then, the first rolling evaluation parameters are scored according to preset evaluation indicators to obtain scores corresponding to each first rolling evaluation parameter. Finally, second rolling evaluation parameters are determined based on the scores corresponding to the first rolling evaluation parameters, and target rolling schedule parameters are recommended based on the second rolling evaluation parameters. This method achieves the recommendation of rolling schedule parameters, facilitates the reasonable setting of rolling schedule parameters, and further solves the problems of low rolling efficiency and steel accumulation caused by unreasonable setting of rolling schedule parameters. This embodiment creates a new method for finding the recommended range of rolling schedule parameters. Through the innovation of data processing methods, new evaluation criteria are defined, which can further improve the rolling quality during start-up rolling, reduce the risk of steel accumulation, reduce the adjustment of over-steel, reduce the reliance on manual experience, quickly achieve a stable rolling state, and assist technicians in performing initial rolling operations after start-up.

[0105] Based on the same inventive concept as the above-mentioned method for recommending rolling schedule parameters, this embodiment also provides a device for recommending rolling schedule parameters.

[0106] Figure 3 This is a module schematic diagram of the device for recommending rolling procedure parameters provided by the present invention.

[0107] like Figure 3 As shown, the rolling procedure parameter recommendation device includes: 31 parameter acquisition module, 32 data set screening module, 33 scoring processing module and 34 parameter recommendation module.

[0108] The parameter acquisition module is used to obtain a rolling data set and target rolling process parameters. The rolling data set includes several historical rolling evaluation parameters.

[0109] a data set screening module, configured to screen the rolling data set according to target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets, wherein the first plurality of first rolling evaluation parameter data sets include a plurality of first rolling evaluation parameters;

[0110] A scoring processing module, configured to score the first rolling evaluation parameters according to preset evaluation indicators to obtain scores corresponding to the first rolling evaluation parameters;

[0111] The parameter recommendation module is used to determine the second rolling evaluation parameter based on the score corresponding to the first rolling evaluation parameter, and recommend the target rolling procedure parameter based on the second rolling evaluation parameter. The parameter acquisition module, data set screening module, scoring processing module and parameter recommendation module are connected.

[0112] In this exemplary rolling procedure parameter recommendation device, new evaluation criteria are defined, which can further improve the rolling quality during startup, reduce the risk of steel accumulation, reduce the amount of steel adjustment, reduce dependence on manual experience, achieve a stable rolling state as soon as possible, and assist technical personnel in performing initial rolling operations after startup.

[0113] In some exemplary embodiments, the dataset screening module includes:

[0114] A first classification submodule, configured to perform a first classification process on the rolling data set according to a preset classification rule to obtain a plurality of rolling sub-data sets;

[0115] The data deletion submodule is used to delete abnormal data from the rolling subdataset to obtain the target subdataset;

[0116] The data set screening submodule is used to screen the target sub-data set according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameters.

[0117] In some exemplary embodiments, the data deletion submodule includes:

[0118] A data processing unit, used for obtaining a mean value and a standard deviation of a rolling sub-dataset;

[0119] The data deletion unit is used to delete abnormal data from the rolling sub-dataset according to the mean value and standard deviation of the rolling sub-dataset to obtain the target sub-dataset.

[0120] In some exemplary embodiments, the data deletion unit includes:

[0121] a first data deletion subunit, configured to delete abnormal data from the rolling subdataset according to the mean value of the rolling subdataset and the standard deviation of the rolling subdataset to obtain an intermediate subdataset;

[0122] A clustering subunit, configured to perform clustering processing on the intermediate sub-dataset to obtain cluster centers and cluster data sets;

[0123] The cluster distance subunit is used to obtain the distance between the data in the cluster data set and the cluster center to obtain the cluster data distance;

[0124] The second data deletion subunit is configured to delete abnormal data from the cluster data set according to the cluster data distance and a preset cluster distance to obtain the target sub-data set.

[0125] In some exemplary embodiments, the scoring processing module includes:

[0126] A second classification submodule, configured to perform a second classification process on the first rolling evaluation parameter according to the evaluation parameter category to obtain a plurality of rolling evaluation classification parameters;

[0127] The scoring processing submodule is used to score each rolling evaluation classification parameter according to the preset evaluation index to obtain the score corresponding to each rolling evaluation classification parameter;

[0128] The weighted processing submodule is used to perform weighted processing on the scores corresponding to the various rolling evaluation classification parameters based on a preset weight coefficient to obtain a score corresponding to the first rolling evaluation parameter.

[0129] In some exemplary embodiments, the parameter recommendation module includes:

[0130] The second parameter submodule is used to determine the first rolling evaluation parameter corresponding to the highest score, and obtain the second rolling evaluation parameter;

[0131] a third parameter submodule, configured to filter the first rolling evaluation parameter according to the second rolling evaluation parameter and a first preset distance threshold to obtain a plurality of third rolling evaluation parameters;

[0132] a target distance submodule, configured to obtain the distance between the third rolling evaluation parameter and the second rolling evaluation parameter, and obtain a target distance of the third rolling evaluation parameter;

[0133] The parameter recommendation submodule is used to obtain the score corresponding to the third rolling evaluation parameter, determine the recommended score of the third rolling evaluation parameter based on the target distance of the third rolling evaluation parameter and the score corresponding to the third rolling evaluation parameter, and recommend the target rolling procedure parameters based on the recommended score.

[0134] In some exemplary embodiments, the second parameter submodule includes:

[0135] a target data set unit, configured to filter the first rolling evaluation parameter data set according to a second preset distance threshold and a preset data volume threshold to obtain a target rolling evaluation parameter data set;

[0136] The second parameter unit is used to determine the first rolling evaluation parameter corresponding to the highest score in the target rolling evaluation parameter data set to obtain the second rolling evaluation parameter.

[0137] In some exemplary embodiments, the parameter recommendation submodule includes:

[0138] A weight setting unit, used to set distance weight and score weight;

[0139] a distance parameter unit, configured to determine a distance recommendation parameter according to the distance weight and a target distance of a third rolling evaluation parameter;

[0140] A scoring parameter unit, configured to determine a scoring recommendation parameter according to the scoring weight and the score corresponding to the third rolling parameter;

[0141] The recommendation score unit is used to obtain the recommendation score of the third rolling parameter according to the distance recommendation parameter and the score recommendation parameter.

[0142] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, any one of the methods in this embodiment is implemented.

[0143] In one embodiment, see Figure 4 This embodiment also provides an electronic device 400, including a memory 401, a processor 402, and a computer program stored in the memory and executable on the processor. When the processor 402 executes the computer program, the steps of the method described in any one of the above embodiments are implemented.

[0144] Regarding the computer-readable storage medium in this embodiment, those skilled in the art will appreciate that all or part of the steps in the aforementioned method embodiments can be implemented using hardware associated with the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps in the aforementioned method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0145] The electronic device provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run the computer program so that the electronic device executes each step of the above method.

[0146] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0147] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0148] In the above embodiments, references in the specification to "this embodiment," "one embodiment," "another embodiment," "in some exemplary embodiments," or "other embodiments" indicate that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least some, but not necessarily all, embodiments. Multiple occurrences of "this embodiment," "one embodiment," or "another embodiment" do not necessarily refer to the same embodiment.

[0149] In the above embodiments, although the invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art based on the foregoing description. For example, other memory structures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed. The embodiments of the present invention are intended to encompass all such alternatives, modifications, and variations that fall within the broad scope of the appended claims.

[0150] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0151] The present invention can be used in a wide variety of general-purpose or special-purpose computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments that include any of the above.

[0152] The present invention may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0153] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, any equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A method for recommending rolling procedure parameters, characterized in that: include: Acquiring a rolling data set and target rolling process parameters, wherein the rolling data set includes a plurality of historical rolling evaluation parameters; screening the rolling data set according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets, wherein the plurality of first rolling evaluation parameter data sets include a plurality of first rolling evaluation parameters; Scoring the first rolling evaluation parameters according to preset evaluation indicators to obtain scores corresponding to the first rolling evaluation parameters; determining a second rolling evaluation parameter according to the score corresponding to the first rolling evaluation parameter, and recommending a target rolling procedure parameter according to the second rolling evaluation parameter; The determining of the second rolling evaluation parameter according to the score corresponding to the first rolling evaluation parameter, and recommending the target rolling procedure parameter according to the second rolling evaluation parameter includes: Determine the first rolling evaluation parameter corresponding to the highest score to obtain the second rolling evaluation parameter; screening the first rolling evaluation parameter according to the second rolling evaluation parameter and the first preset distance threshold to obtain a plurality of third rolling evaluation parameters; acquiring a distance between the third rolling evaluation parameter and the second rolling evaluation parameter to obtain a target distance of the third rolling evaluation parameter; obtaining a score corresponding to the third rolling evaluation parameter, determining a recommended score for the third rolling evaluation parameter according to the target distance of the third rolling evaluation parameter and the score corresponding to the third rolling evaluation parameter, and recommending the target rolling procedure parameter according to the recommended score; Determining the recommended score of the third rolling evaluation parameter according to the target distance of the third rolling evaluation parameter and the score corresponding to the third rolling evaluation parameter includes: Set distance weight and score weight; determining a distance recommendation parameter according to the distance weight and the target distance of the third rolling evaluation parameter; Determining a score recommendation parameter according to the score weight and the score corresponding to the third rolling evaluation parameter; A recommended score for the third rolling evaluation parameter is obtained according to the distance recommendation parameter and the score recommendation parameter.

2. The method for recommending rolling schedule parameters according to claim 1, characterized in that: The step of screening the rolling data set according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets includes: Performing a first classification process on the rolling data set according to a preset classification rule to obtain a plurality of rolling sub-data sets; Deleting abnormal data from the rolling sub-dataset to obtain a target sub-dataset; The target sub-dataset is screened according to the target rolling process parameters to obtain a plurality of the first rolling evaluation parameter data sets.

3. The method for recommending rolling schedule parameters according to claim 2, characterized in that: The processing of deleting abnormal data from the rolling sub-dataset to obtain the target sub-dataset includes: Obtaining the mean of the rolling sub-dataset and the standard deviation of the rolling sub-dataset; The rolling sub-dataset is processed by deleting abnormal data according to the mean value of the rolling sub-dataset and the standard deviation of the rolling sub-dataset to obtain a target sub-dataset.

4. The method for recommending rolling schedule parameters according to claim 3, characterized in that: The step of performing abnormal data deletion processing on the rolling sub-dataset according to the mean value of the rolling sub-dataset and the standard deviation of the rolling sub-dataset to obtain a target sub-dataset includes: Deleting abnormal data from the rolling sub-dataset according to the mean value of the rolling sub-dataset and the standard deviation of the rolling sub-dataset to obtain an intermediate sub-dataset; Performing clustering processing on the intermediate sub-dataset to obtain cluster centers and cluster data sets; Get the distance between the data in the cluster data set and the cluster center to get the cluster data distance; The cluster data set is processed by deleting abnormal data according to the cluster data distance and the preset cluster distance to obtain the target sub-data set.

5. The method for recommending rolling schedule parameters according to claim 1, characterized in that: The scoring process of the first rolling evaluation parameters according to the preset evaluation index to obtain the scores corresponding to the respective first rolling evaluation parameters includes: performing a second classification process on the first rolling evaluation parameter according to the evaluation parameter category to obtain a plurality of rolling evaluation classification parameters; Scoring each rolling evaluation classification parameter according to the preset evaluation index to obtain the score corresponding to each rolling evaluation classification parameter; Based on a preset weight coefficient, the scores corresponding to the various rolling evaluation classification parameters are weighted to obtain a score corresponding to the first rolling evaluation parameter.

6. The method for recommending rolling schedule parameters according to claim 1, characterized in that: Determining the first rolling evaluation parameter corresponding to the highest score to obtain the second rolling evaluation parameter includes: screening the first rolling evaluation parameter data set according to a second preset distance threshold and a preset data volume threshold to obtain a target rolling evaluation parameter data set; The first rolling evaluation parameter corresponding to the highest score in the target rolling evaluation parameter data set is determined to obtain a second rolling evaluation parameter.

7. The method for recommending rolling schedule parameters according to claim 1, characterized in that: The mathematical expression of the recommended score of the third rolling evaluation parameter is: score_dist=dist*wx+(1-final_score)*wy; Among them, score_dist is the recommended score of the third rolling evaluation parameter, dist is the target distance of the third rolling evaluation parameter, wx is the distance weight, final_score is the score corresponding to the third rolling evaluation parameter, and wy is the score weight.

8. A device for recommending rolling procedure parameters, characterized in that: The device is used to execute the method for recommending rolling schedule parameters according to any one of claims 1 to 7, and the device comprises: A parameter acquisition module, configured to acquire a rolling data set and target rolling process parameters, wherein the rolling data set includes a plurality of historical rolling evaluation parameters; a data set screening module, configured to screen the rolling data set according to the target rolling process parameters to obtain a plurality of first rolling evaluation parameter data sets, wherein the plurality of first rolling evaluation parameter data sets include a plurality of first rolling evaluation parameters; a scoring processing module, configured to score the first rolling evaluation parameters according to preset evaluation indicators to obtain scores corresponding to the first rolling evaluation parameters; A parameter recommendation module is used to determine the second rolling evaluation parameter based on the score corresponding to the first rolling evaluation parameter, and recommend the target rolling procedure parameter based on the second rolling evaluation parameter. The parameter acquisition module, the data set screening module, the scoring processing module and the parameter recommendation module are connected.

9. An electronic device, characterized in that: Includes processor, memory and communication bus; The communication bus is used to connect the processor and the memory; The processor is configured to execute the computer program stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and the computer program is used to make the computer execute the method according to any one of claims 1 to 7.

Images