Parameter determination method, device, equipment and storage medium

Abstract

The embodiment of the present invention provides a parameter determination method, device, equipment and storage medium, the parameter determination method comprising: obtaining multiple sample objects matching the feature values ​​of the object to be processed; grouping the multiple sample objects according to the processing parameter values ​​corresponding to each of the multiple sample objects to obtain multiple sample object groups; determining the evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​of the sample objects contained in each of the multiple sample object groups; determining the processing parameter values ​​corresponding to the sample object groups whose evaluation index values ​​meet the set conditions as the processing parameter values ​​of the object to be processed. Thus, the automatic and targeted recommendation of the processing parameter values ​​of the object to be processed is completed.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and in particular to a parameter determination method, device, equipment and storage medium. Background Art

[0002] Steel smelting must go through the hot rolling process before it can be formed. After heating, the raw materials have temperature differences between the inside and outside, the top and the bottom. At the same time, the uneven cooling during the rolling process will cause uneven extension of the plate rolled pieces, and shape defects such as bending, waves, and buckling will occur during the cooling and transportation processes. The straightening process is a necessary process after the hot rolling process, which can eliminate defects such as bending under the action of external forces and make the product reach a qualified state.

[0003] A straightening machine is a device for straightening metal profiles, plates, etc. The operating principle of the straightening machine is to squeeze the plate through the friction of the straightening roller, thereby forcing its straightness to change. After the plate is bitten by the roller, the operator can set the parameter value of the straightening process of the straightening machine so that the plate can be straightened based on the set parameter value to achieve the purpose of straightening.

[0004] The parameters of the straightening process are set by the operator based on his / her experience, which places high demands on the operator, and the straightening effect fluctuates depending on the operator's level. Summary of the invention

[0005] The embodiments of the present invention provide a parameter determination method, apparatus, device and storage medium, which can automatically recommend appropriate processing parameter values ​​for a current object to be processed.

[0006] In a first aspect, an embodiment of the present invention provides a parameter determination method, the method comprising:

[0007] Acquire multiple sample objects that match the feature values ​​of the object to be processed;

[0008] Grouping the multiple sample objects according to the processing parameter values ​​corresponding to the multiple sample objects to obtain multiple sample object groups;

[0009] Determining evaluation index values ​​corresponding to each of the plurality of sample object groups according to the detection index values ​​of the sample objects respectively included in the plurality of sample object groups;

[0010] The processing parameter values ​​corresponding to the sample object groups whose evaluation index values ​​meet the set conditions are determined as the processing parameter values ​​of the objects to be processed.

[0011] In a second aspect, an embodiment of the present invention provides a parameter determination device, the device comprising:

[0012] An acquisition module, used for acquiring a plurality of sample objects matching the feature values ​​of the object to be processed;

[0013] A grouping module, used for grouping the plurality of sample objects according to the processing parameter values ​​corresponding to the plurality of sample objects respectively, so as to obtain a plurality of sample object groups;

[0014] The determination module is used to determine the evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​of the sample objects respectively included in the multiple sample object groups; and determine the processing parameter values ​​corresponding to the sample object groups whose evaluation index values ​​meet the set conditions as the processing parameter values ​​of the objects to be processed.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores executable code, and when the executable code is executed by the processor, the processor can at least implement the parameter determination method in the first aspect.

[0016] In a fourth aspect, an embodiment of the present invention provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the parameter determination method in the first aspect.

[0017] In an embodiment of the present invention, for an object to be processed that currently needs to be processed, a processing parameter value suitable for the object to be processed can be automatically recommended, so that the processing of the object to be processed can be completed under the effect of the processing parameter value. Specifically, first, a plurality of sample objects matching the feature value of the object to be processed are obtained from a sample database, wherein the sample object refers to an object that has been processed under the corresponding processing parameters. Secondly, according to the processing parameter values ​​corresponding to each of the obtained plurality of sample objects, the plurality of sample objects are grouped, and the sample objects with the same or less different processing parameter values ​​are divided into a group, and a plurality of sample object groups are obtained. Afterwards, according to the detection index values ​​of the sample objects contained in each of the plurality of sample object groups, the evaluation index values ​​corresponding to each of the plurality of sample object groups are determined. Among them, the detection index value of a sample object reflects the processing effect of the sample object under the effect of its corresponding processing parameter value, and the evaluation index value corresponding to a sample object group reflects the overall processing effect of all sample objects in the sample object group. Finally, the processing parameter value corresponding to the sample object group whose evaluation index value meets the set conditions is determined as the processing parameter value of the object to be processed, so that the object to be processed can obtain an ideal processing effect under the effect of the processing parameter value. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A flow chart of a parameter determination method provided by an embodiment of the present invention;

[0020] Figure 2 A flow chart of a parameter determination method provided by another embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the structure of a parameter determination device provided by an embodiment of the present invention;

[0022] Figure 4 For Figure 3 A schematic structural diagram of an electronic device corresponding to the parameter determination device provided in the illustrated embodiment. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0025] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0026] The purpose of the parameter determination method provided by the embodiment of the present invention is to automatically recommend a processing parameter value suitable for the object to be processed, so that the object to be processed can be processed under the effect of the processing parameter value.

[0027] For example, the object to be processed may be a plate to be straightened, that is, a plate needs to be straightened. At this time, the purpose of the parameter determination method provided in the embodiment of the present invention is to automatically determine a processing parameter value suitable for the plate for the straightening machine, so that the straightening machine uses the processing parameter value to straighten the current plate to be straightened.

[0028] When the object to be processed is a plate to be straightened, the processing parameter values ​​that need to be determined may include: an inlet roll gap value, an outlet roll gap value and a roll bending amount of the straightening machine, these three processing parameter values.

[0029] The parameter determination method provided in the embodiment of the present invention can be executed by an electronic device. In the scenario where the object to be processed is a plate to be straightened, the electronic device can be a straightener, or of course, a host computer, a mobile phone terminal, or other device connected to the straightener for communication.

[0030] Figure 1 A flow chart of a parameter determination method provided by an embodiment of the present invention, such as Figure 1 As shown, the following steps may be included:

[0031] 101. Acquire multiple sample objects that match feature values ​​of an object to be processed.

[0032] 102. Group the multiple sample objects according to the processing parameter values ​​corresponding to the multiple sample objects to obtain multiple sample object groups.

[0033] 103. Determine evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​of the sample objects respectively included in the multiple sample object groups.

[0034] 104. Determine the processing parameter value corresponding to the sample object group whose evaluation index value meets the set conditions as the processing parameter value of the object to be processed.

[0035] For ease of description, the following uses a straightening machine to straighten a plate as an example, in which the object to be processed is the plate to be straightened. Of course, the principle is the same in other application scenarios.

[0036] In practical applications, relevant information of objects that have been processed within a relatively long period of time may be collected to form the above-mentioned sample database.

[0037] In the straightening machine scenario, the sample database is obtained by collecting a large amount of information about the plates that have been straightened. At this time, the sample object is the plate that has been straightened. In the sample database, the plate can be represented by a certain identifier corresponding to the plate or an identifier can be assigned to the straightened plate, and the relevant information of the plate is stored in association with the identifier.

[0038] Among them, for any straightened plate, the relevant information of the plate may include: the generation time (i.e. the time when straightening is completed), the processing parameter values ​​used during straightening (such as the inlet roller gap value, outlet roller gap value and bending roller amount used by the straightener when straightening the plate), the detection index value obtained by detecting the plate after straightening (including at least one of the following: straightness in the length direction of the plate, straightness in the width direction of the plate), and some characteristic values ​​of the plate (such as plate type, plate thickness, plate width, plate temperature, yield point, tensile strength, etc.), and other information (such as straightening machine status information, environmental information, etc.).

[0039] For ease of description, the plate to be straightened is referred to as plate A below. The purpose of the parameter determination method is to automatically recommend processing parameter values ​​corresponding to plate A so that the straightening machine uses the processing parameter values ​​to straighten plate A and obtain a better straightening effect.

[0040] To achieve the above purpose, first, it is necessary to screen out multiple sample objects that match the feature value of plate A from the sample database containing relevant information of several straightened plates. In short, the multiple sample objects that match the feature value of plate A are multiple straightened plates that are similar to plate A.

[0041] In practical applications, multiple features that can reflect the working condition information of the plate can be preset, and the working condition information can include but is not limited to incoming material information, such as other information such as straightening machine equipment status information. Combined with these multiple features, multiple sample objects that match the plate A to be straightened are selected from the sample database.

[0042] In summary, assuming that the above-mentioned multiple features reflect the incoming material information, multiple sample objects matching the plate A to be straightened are selected from the sample database in combination with these multiple features, that is, sample objects whose incoming material information matches the incoming material information of the plate A are selected from the sample database.

[0043] Optionally, the multiple characteristics of the incoming material information may be at least one of the following: plate type, plate thickness, plate width, plate temperature, yield point, and tensile strength. Therefore, plate A may have multiple characteristic values, which are values ​​corresponding to the above multiple characteristics.

[0044] Two optional methods of selecting a plurality of sample objects matching the plurality of feature values ​​of plate A from the sample database are provided below.

[0045] The first method can be summarized as follows: according to the multiple characteristic values ​​of the plate A, the characteristic value ranges corresponding to the multiple characteristic values ​​are determined; and multiple sample objects whose multiple characteristic values ​​all match the corresponding characteristic value ranges are obtained from the sample database.

[0046] Specifically, according to the feature values ​​corresponding to the plate A under various features (i.e., the above-mentioned multiple feature values), a value range can be set for each feature, which is called the feature value range. Since each sample object in the sample database has feature values ​​corresponding to the above-mentioned multiple features like the plate A, therefore, when traversing each sample object in the sample database, if the multiple feature values ​​of a certain sample object k all fall into the multiple feature value ranges determined according to the multiple feature values ​​of the plate A, then the sample object k is considered to be a sample object matching the plate A.

[0047] For ease of understanding, for example, assume that the multiple features used are: plate type, plate thickness, and plate width. Assume that the plate type corresponding to plate A is Y, the plate thickness is 5 cm, and the plate width is 50 cm. The feature value range set according to the plate type of plate A is: Y; the feature value range set according to the plate thickness of plate A is: [4 cm, 6 cm]; the feature value range set according to the plate width of plate A is: [40 cm, 60 cm]. Then assume that the plate type of sample object k in the sample database is Y, the plate thickness is 4.5 cm, and the plate width is 55 cm. Based on this, because the above three feature values ​​of sample object k all fall into the above three feature value ranges, sample object k is a sample object that matches plate A.

[0048] The second method, in summary, is: according to the preset importance order corresponding to the multiple feature values ​​of the plate A, a plurality of sample objects matching (such as being closest to) the multiple feature values ​​of the plate A are gradually selected from the sample database. For ease of understanding, assuming that the multiple feature values ​​of the plate A include a first feature value and a second feature value (i.e., corresponding to the values ​​of the first feature and the second feature), and the importance of the first feature value is higher than that of the second feature value, then taking the first feature value and the second feature value as an example, a first set of sample objects matching (such as being closest to) the first feature value of the plate A can be obtained from the sample database first, and then a second set of sample objects matching (such as being closest to) the second feature value of the plate A can be obtained from the first set of sample objects. If the multiple feature values ​​of plate A only include the first feature value and the second feature value mentioned above, then the sample objects included in the second sample object set are the multiple sample objects that match the multiple feature values ​​of plate A; if the multiple feature values ​​of plate A also include feature values ​​corresponding to other features whose importance is lower than the second feature value, such as the third feature value, then the above principle is used to continue processing: obtain a third sample object set that matches (such as is closest to) the third feature value of plate A from the second sample object set, and so on.

[0049] Among them, taking the first sample object set screened according to the first eigenvalue as an example, in fact, each sample object in the first sample object set can have the same first eigenvalue, and the difference between the first eigenvalues ​​corresponding to these sample objects and the first eigenvalue of plate A is the smallest, that is, compared with the sample objects not in the first sample object set, the difference between the first eigenvalues ​​corresponding to the sample objects in the first sample object set and the first eigenvalue of plate A is the smallest.

[0050] For ease of understanding, let's take a specific example and assume that the multiple features used include: plate type, plate thickness, yield point, tensile strength, plate width, and the preset importance is in descending order. Then the execution process of the second method is as follows:

[0051] In the first step, sample objects of the same plate type as plate A are screened out in the sample database. If there are sample objects of the same plate type as plate A, these sample objects constitute sample object set 1 and proceed to the next step; otherwise, proceed directly to the next step.

[0052] In the second step, sample objects whose thickness is closest to that of plate A are selected from sample object set 1 to form sample object set 2, and then proceed to the next step.

[0053] The third step is to select the sample objects closest to the yield point of plate A from sample object set 2 to form sample object set 3 and proceed to the next step.

[0054] In the fourth step, sample objects whose tensile strength is closest to that of plate A are selected from sample object set 3 to form sample object set 4, and then proceed to the next step.

[0055] In the fifth step, sample objects whose width is closest to that of plate A are selected from sample object set 4 to form sample object set 5. Finally, the sample objects included in sample object set 5 are used as multiple sample objects that match the multiple feature values ​​of plate A.

[0056] Among them, taking the thickness of the plate as an example, assuming that the thickness of plate A is 5 cm, the sample database includes the following thickness values ​​from small to large: 3 cm, 4 cm, 5.5 cm, 6 cm... The thickness value closest to the thickness of plate A is 5.5 cm. Therefore, the sample object with a thickness value of 5.5 cm is determined from the above-mentioned sample object set 1 to form sample object set 2.

[0057] After obtaining multiple sample objects matching multiple feature values ​​of plate A from the sample database through the above scheme, the multiple sample objects are grouped according to the processing parameter values ​​corresponding to each of the multiple sample objects to obtain multiple sample object groups. Among them, sample objects whose processing parameter values ​​meet the set requirements can be divided into one group. For example, sample objects with the same processing parameter values ​​are divided into one group. For another example, sample objects whose processing parameter values ​​differ by less than a set threshold are divided into one group, that is, the processing parameter values ​​corresponding to each of the sample objects divided into one group can be different, but the difference is small.

[0058] For the straightening process of the plate, as mentioned above, the processing parameter values ​​include the following three processing parameter values ​​used in combination: the entrance roll gap value, the exit roll gap value and the bending roll amount of the straightening machine. In the process of grouping multiple sample objects, these three processing parameter values ​​should be regarded as a whole, which can be called a processing parameter value group. Therefore, assuming that the method of "dividing sample objects with the same processing parameter value into a group" is adopted, the grouping process is to divide according to how many processing parameter value groups these multiple sample objects have in total. If there are N processing parameter value groups in total, then N sample object groups will be divided.

[0059] For example, it is assumed that the sample object groups finally divided include the following three groups: sample object group Z1, sample object group Z2 and sample object group Z3, wherein sample object group Z1 includes 100 sample objects, sample object group Z2 includes 80 sample objects, and sample object group Z3 includes 3 sample objects. It can be understood that each sample object in sample object group Z1 has the same processing parameter value, such as: {entrance roller gap value = a1, exit roller gap value = b1, bending roller amount = c1}; each sample object in sample object group Z2 has the same processing parameter value, such as: {entrance roller gap value = a1, exit roller gap value = b2, bending roller amount = c2}; each sample object in sample object group Z3 has the same processing parameter value, such as: {entrance roller gap value = a2, exit roller gap value = b3, bending roller amount = c2}.

[0060] Optionally, in order to reduce the amount of calculation and ensure the accuracy of the final determination result of the processing parameter value of the plate A, the sample object group whose number of sample objects is less than a set threshold may be filtered out from the multiple sample object groups obtained by grouping.

[0061] Optionally, the set threshold may be a certain value set empirically, such as 5. In the three sample object groups in the above example, since sample object group Z3 only includes 3 sample objects, sample object group Z3 is filtered out.

[0062] Optionally, the set threshold may also be determined in the following manner: according to the number of sample objects contained in each of the multiple sample object groups, an average number of sample objects corresponding to the multiple sample object groups is determined, and the average number of sample objects is used as the set threshold.

[0063] Still taking the above three sample object groups as an example, the average number of sample objects of these three sample object groups is calculated as: (100+80+3) / 3=61. Since the number of sample objects included in sample object group Z3 is less than the average, it is determined to filter out sample object group Z3.

[0064] Afterwards, evaluation index values ​​corresponding to each of the plurality of sample object groups are determined according to the detection index values ​​of the sample objects respectively included in the plurality of sample object groups.

[0065] The detection index value of a sample object refers to the index value reflecting the processing effect measured after the sample object is processed with the processing parameter value corresponding to the sample object, which is called the detection index value.

[0066] In the scenario of plate straightening, after the plate is straightened according to the processing parameter values ​​corresponding to the plate, the straightened plate is tested to obtain the test index value of the plate. As mentioned above, the test index value of the plate can include at least one of the following: the straightness of the plate in the length direction and the straightness of the plate in the width direction. Generally, in practical applications, both of these test indexes are used.

[0067] In this paper, the detection index value corresponds to the individual sample object, while the evaluation index value corresponds to the sample object group as a whole. However, the evaluation index value corresponding to the sample object group is indeed determined based on the detection index value corresponding to each sample object in the group.

[0068] Optionally, determining the evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​of the sample objects respectively included in the multiple sample object groups may be implemented as follows:

[0069] For any sample object group i among the multiple sample object groups, the mean value of the detection index values ​​of the sample objects in the sample object group i is determined, and the evaluation index value corresponding to the sample object group i includes the mean value.

[0070] Optionally, determining the evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​of the sample objects respectively included in the multiple sample object groups may also be implemented as follows:

[0071] For any sample object group i among the multiple sample object groups, determine the number of sample objects in the sample object group i whose detection index values ​​meet the set threshold conditions; determine the pass rate corresponding to the sample object group i based on the number of sample objects, and the evaluation index value corresponding to the sample object group i includes the pass rate.

[0072] Still taking the plate straightening scenario as an example, when the detection index value of the sample object includes the straightness of the plate in the length direction, optionally, the evaluation index value of the sample object group may include at least one of the following two types: the mean straightness value in the length direction of the plate, and the pass rate of the straightness value in the length direction of the plate. When the detection index value of the sample object includes the straightness value in the width direction of the plate, optionally, the evaluation index value of the sample object group may include at least one of the following two types: the mean straightness value in the width direction of the plate, and the pass rate of the straightness value in the width direction of the plate.

[0073] Still taking the sample object group Z1 in the above text as an example, assuming that the 100 sample objects in the sample object group Z1 are each associated with two detection index values, namely, the straightness in the length direction of the plate and the straightness in the width direction of the plate, then the straightness in the length direction of the plate corresponding to each of the 100 sample objects is averaged to obtain the average straightness in the length direction of the plate corresponding to the sample object group Z1. Similarly, the average straightness in the width direction of the plate corresponding to the sample object group Z1 is obtained. In addition, assuming that the preset straightness thresholds in the length and width directions of the plate are the same, both 3, and assuming that the straightness in the length direction of the plate of 90 sample objects in the sample object group Z1 is less than 3, and the straightness in the width direction of the plate of 95 sample objects is less than 3, then it is determined that the qualified rate of the straightness in the length direction of the plate corresponding to the sample object group Z1 is 90%, and the qualified rate of the straightness in the width direction of the plate corresponding to the sample object group Z1 is 95%.

[0074] After obtaining the evaluation index values ​​corresponding to the multiple sample object groups, a sample object group whose evaluation index value meets the set conditions is selected, and the processing parameter value corresponding to the sample object group is used as the processing parameter value corresponding to the plate A to be straightened.

[0075] Among them, the setting condition can be: for example, the sample object group finally determined is called the target sample object group, and the processing effect obtained by using the processing parameter values ​​corresponding to the target sample object group to process the objects to be processed is better than that obtained by using the processing parameter values ​​corresponding to other sample object groups.

[0076] Of course, the setting condition is not limited to this. For example, a certain threshold value may be preset, and a sample object group whose evaluation index value meets the threshold value requirement may be selected.

[0077] For ease of description, the sample object group finally determined is referred to as the target sample object group below. As described above, the sample object group may have one or more evaluation index values. When the sample object group uses only one evaluation index, the target sample object group can be determined by comparing the evaluation index values ​​corresponding to the multiple sample object groups under the evaluation index. When multiple evaluation indexes are used (i.e., each sample object group has multiple evaluation index values), the target sample object group can be determined according to the preset importance order of the multiple evaluation indexes.

[0078] Assume that the importance of multiple evaluation indicators is set in the following order from high to low: the qualified rate of the straightness in the length direction of the plate, the qualified rate of the straightness in the width direction of the plate, the average straightness in the length direction of the plate, and the average straightness in the width direction of the plate. First, multiple sample object groups are sorted in the order of the qualified rate of the straightness in the length direction of the plate from high to low. Among them, if there is no sample object group tied for the first place, then the sample object group ranked first is the target sample object group. If there are M (M>1) sample object groups tied for the first place, then these M sample object groups are sorted in the order of the qualified rate of the straightness in the width direction of the plate from high to low. Similarly, if there is no sample object group tied for the first place in the M sample object groups, then the sample object group ranked first in the M sample object groups is the target sample object group. If there are K (K>1) sample object groups tied for the first place, then these K sample object groups are further sorted in the order of the average straightness in the length direction of the plate from high to low, and so on.

[0079] After obtaining the sample object group (referred to as the target sample object group) whose evaluation index value meets the set conditions through the above process, optionally, the processing parameter value corresponding to the target sample object group can be directly used as the processing parameter value corresponding to the plate A, so that the straightening machine can use the processing parameter value to straighten the plate A. Optionally, the processing parameter value and the evaluation index value corresponding to the target sample object group can also be output for the user to confirm whether to use the processing parameter value as the processing parameter value of the plate A. The user refers to the person operating the straightening machine, and the user can confirm whether to use the processing parameter value based on the evaluation index value corresponding to the target sample object group. Specifically, if the user finds that the evaluation index value corresponding to the target sample object group achieves the expected effect, then the automatically determined processing parameter value can be confirmed to be used. Conversely, if the user finds that the evaluation index value corresponding to the target sample object group does not achieve the expected effect, then the automatically determined processing parameter value can be used as a reference to set another suitable processing parameter value for the straightening of the plate A.

[0080] In addition, it is assumed that the processing parameter value corresponding to the determined target sample object group is used as the processing parameter value of plate A. Optionally, after plate A is straightened with the processing parameter value, the detection index value of plate A after processing under the processing parameter can also be determined. Finally, the characteristic value, processing parameter value and detection index value of plate A are updated in the sample database.

[0081] In summary, through the above solution, a processing parameter value matching the current object to be processed can be automatically determined, so that the object to be processed can be processed based on the processing parameter value to obtain a good processing effect.

[0082] Figure 2A flow chart of a parameter determination method provided by another embodiment of the present invention is as follows: Figure 2 As shown, the following steps may be included:

[0083] 201 obtains a plurality of sample objects that match the feature values ​​of the object to be processed.

[0084] 202. Group the multiple sample objects according to the processing parameter values ​​corresponding to the multiple sample objects to obtain multiple sample object groups.

[0085] 203. Determine evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​and generation times of the sample objects included in each of the multiple sample object groups.

[0086] 204. Determine the processing parameter value corresponding to the sample object group whose evaluation index value meets the set condition as the processing parameter value of the object to be processed.

[0087] Different from the previous embodiment, in this embodiment, in the process of determining the evaluation index value corresponding to the sample object group, in addition to considering the detection index value of each sample object in the sample object group, the generation time of each sample object in the sample object group is also considered, such as the straightening time of the plate.

[0088] In summary, the role of the generation time of sample objects is mainly reflected in the following: by assigning different weights to sample objects in different historical time intervals, the sample objects in the recent time are considered to be more important, so as to ensure that while suitable processing parameter values ​​are recommended based on a large number of sample objects, they can also quickly adapt to changes in recent working conditions and reduce errors caused by time drift.

[0089] In this embodiment, optionally, determining the evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​and generation time of the sample objects respectively included in the multiple sample object groups can be implemented as follows:

[0090] For any sample object group i among the multiple sample object groups, determine the weight corresponding to each sample object in the sample object group i according to the generation time corresponding to each sample object in the sample object group i;

[0091] According to the weight and detection index value corresponding to each sample object in the sample object group i, the evaluation index value corresponding to the sample object group i is determined.

[0092] Among them, the later the sample object is generated, the higher the weight it corresponds to.

[0093] In practical applications, optionally, the weight corresponding to the sample object in time period t can be determined according to the following formula: t :

[0094]

[0095] Wherein, tf is a time weight factor constant greater than or equal to 0. In practical applications, it can be set to 1. t is the number of days between the generation time of the sample object and the current time. When tf = 0, the weights corresponding to each sample object are the same.

[0096] For any sample object group i, its corresponding evaluation index value m can be determined according to the following formula:

[0097]

[0098] Where T is the maximum number of days between the generation time of the sample object in sample object group i and the current time, l t is the number of sample objects in sample object group i in time period t, m t is the evaluation index corresponding to the sample objects existing in sample object group i within time period t.

[0099] Among them, when the detection index value of the sample object includes the straightness of the plate in the length direction, since the evaluation index value corresponding to the sample object group i can include the mean straightness of the plate in the length direction and / or the pass rate of the straightness of the plate in the length direction. Therefore, when the evaluation index value corresponding to the sample object group i can include the mean straightness of the plate in the length direction, m t Specifically, it can be obtained by calculating the average straightness of the plate length direction for the sample objects in the sample object group i within the time period t. When the evaluation index value corresponding to the sample object group i can include the pass rate of the straightness of the plate length direction, m t Specifically, it can be obtained by calculating the proportion of sample objects whose plate length straightness is less than the set threshold in sample object group i in time period t. For example, there are 2 sample objects in sample object group i in time period t, one of which has a plate length straightness less than the set threshold, and the other has a plate length straightness greater than the set threshold. Then the proportion of sample objects whose plate length straightness is less than the set threshold in sample object group i in time period t is 1 / 2.

[0100] When the detection index value of the sample object includes the straightness in the width direction of the plate, the calculation process is similar and will not be repeated here.

[0101] The parameter determination apparatus of one or more embodiments of the present invention will be described in detail below. Those skilled in the art will appreciate that these parameter determination apparatuses can be configured using commercially available hardware components through the steps taught in this solution.

[0102] Figure 3 A schematic diagram of the structure of a parameter determination device provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the parameter determination device includes: an acquisition module 11, a grouping module 12, and a determination module 13.

[0103] The acquisition module 11 is used to acquire a plurality of sample objects that match the feature values ​​of the object to be processed.

[0104] The grouping module 12 is configured to group the plurality of sample objects according to the processing parameter values ​​corresponding to the plurality of sample objects respectively, so as to obtain a plurality of sample object groups.

[0105] The determination module 13 is used to determine the evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​of the sample objects respectively included in the multiple sample object groups; and determine the processing parameter values ​​corresponding to the sample object groups whose evaluation index values ​​meet the set conditions as the processing parameter values ​​of the objects to be processed.

[0106] Optionally, the grouping module 12 may be specifically used to: group sample objects having the same processing parameter value into one group; or group sample objects having processing parameter values ​​whose difference is less than a set threshold into one group.

[0107] Optionally, the object to be processed has multiple characteristic values, so that the acquisition module 11 can be specifically used to: determine the characteristic value ranges corresponding to the multiple characteristic values ​​respectively according to the multiple characteristic values ​​of the object to be processed; and obtain multiple sample objects whose multiple characteristic values ​​all match the corresponding characteristic value ranges.

[0108] Optionally, the object to be processed has multiple feature values, so that the acquisition module 11 can be specifically used to: obtain a first set of sample objects that match the first feature value of the object to be processed; obtain a second set of sample objects that match the second feature value of the object to be processed from the first set of sample objects; wherein the first feature value and the second feature value are two of the multiple features, and the importance of the first feature value is higher than that of the second feature value.

[0109] Optionally, the device further comprises: a filtering module, configured to filter out sample object groups whose number of sample objects is less than a set threshold from the multiple sample object groups.

[0110] Optionally, the filtering module may also be used to: determine an average number of sample objects corresponding to the multiple sample object groups according to the number of sample objects respectively included in the multiple sample object groups, and the average number of sample objects is used as the set threshold.

[0111] Optionally, the determination module 13 may be specifically configured to: for any sample object group i among the multiple sample object groups, determine a mean value of the detection index values ​​of each sample object in the sample object group i, wherein the evaluation index value corresponding to the sample object group i includes the mean value.

[0112] Optionally, the determination module 13 can be specifically used to: for any sample object group i among the multiple sample object groups, determine the number of sample objects in the sample object group i whose detection index values ​​meet the set threshold conditions; determine the pass rate corresponding to the sample object group i based on the number of sample objects, and the evaluation index value corresponding to the sample object group i includes the pass rate.

[0113] Optionally, the determination module 13 may be specifically configured to determine the evaluation index values ​​corresponding to each of the multiple sample object groups according to the detection index values ​​and generation times of the sample objects respectively included in the multiple sample object groups.

[0114] Optionally, the determination module 13 can be specifically used to: for any sample object group i among the multiple sample object groups, determine the weight corresponding to each sample object in the sample object group i according to the generation time corresponding to each sample object in the sample object group i; determine the evaluation index value corresponding to the sample object group i according to the weight and detection index value corresponding to each sample object in the sample object group i.

[0115] Optionally, the later the sample object is generated, the higher the weight is.

[0116] Optionally, each sample object group has multiple evaluation index values, and the determination module 13 may also be used to determine the sample object group whose evaluation index values ​​meet set conditions according to a preset order of importance of multiple evaluation indexes corresponding to the multiple evaluation index values.

[0117] Optionally, the determination module 13 may also be used to: output the processing parameter value and the evaluation index value corresponding to the sample object group whose evaluation index value meets the set conditions, so that the user can confirm whether to adopt the processing parameter value as the processing parameter value of the object to be processed.

[0118] Optionally, the determination module 13 may also be used to: determine the detection index value of the object to be processed after being processed under the processing parameters; and update the feature value, processing parameter value and detection index value of the object to be processed into the sample database.

[0119] Optionally, the object to be processed includes a plate to be straightened. Based on this, optionally, the characteristic value of the plate to be straightened includes at least one of the following characteristic values: plate type, plate thickness, plate width, plate temperature, yield point, tensile strength. Optionally, the processing parameter values ​​corresponding to the sample object include: the entrance roller gap value, exit roller gap value and bending roller amount of the straightening machine. Optionally, the detection index value of the sample object includes at least one of the following: the straightness of the plate in the length direction, the straightness of the plate in the width direction. Optionally, the evaluation index value corresponding to the sample object group includes at least one of the following: the average straightness of the plate in the length direction, the average straightness of the plate in the width direction, the qualified rate of the straightness of the plate in the length direction, and the qualified rate of the straightness of the plate in the width direction.

[0120] Figure 3 The parameter determination device shown can perform the aforementioned Figure 1 to Figure 2 For the method provided in the illustrated embodiment, for the part not described in detail in this embodiment, reference can be made to the relevant description of the aforementioned embodiment, which will not be described again here.

[0121] In one possible design, the above Figure 3 The structure of the parameter determination device shown can be implemented as an electronic device. Figure 4 As shown, the electronic device may include: a processor 21 and a memory 22. The memory 22 stores executable code, and when the executable code is executed by the processor 21, the processor 21 can at least implement the above-mentioned Figure 1 to Figure 2 The parameter determination method provided in the illustrated embodiment.

[0122] The structure of the electronic device may further include a communication interface 23 for communicating with other devices or a communication network.

[0123] In addition, an embodiment of the present invention provides a non-transitory machine-readable storage medium, wherein the non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor executes the aforementioned Figure 1 to Figure 2 The parameter determination method provided in the illustrated embodiment.

[0124] The device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separated. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0125] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A parameter determination method, characterized in that: include: Acquire a plurality of sample objects that match characteristic values ​​of an object to be processed, wherein the object to be processed includes a plate to be straightened, and the characteristic value includes at least one of the following: plate type, plate thickness, plate width, plate temperature, yield point, and tensile strength; According to the processing parameter values ​​corresponding to the multiple sample objects, the multiple sample objects are grouped, and the sample objects with the same processing parameter values ​​or a difference less than a set threshold are grouped into one group to obtain multiple sample object groups, wherein the processing parameter values ​​include: an inlet roll gap value, an outlet roll gap value and a roll bending amount of a straightening machine; Determine the evaluation index values ​​corresponding to each of the plurality of sample object groups according to the detection index values ​​of the sample objects respectively included in the plurality of sample object groups; wherein the detection index values ​​include at least one of the following: the straightness in the length direction of the plate and the straightness in the width direction of the plate; the evaluation index values ​​include at least one of the following: the average straightness in the length direction of the plate, the average straightness in the width direction of the plate, the qualified rate of the straightness in the length direction of the plate, and the qualified rate of the straightness in the width direction of the plate; Determine the processing parameter value corresponding to the sample object group whose evaluation index value meets the set conditions as the processing parameter value of the object to be processed; The method of determining evaluation index values ​​corresponding to each of the multiple sample object groups based on the detection index values ​​of the sample objects respectively included in the multiple sample object groups includes: for any sample object group i among the multiple sample object groups, determining the mean of the detection index values ​​of each sample object in the sample object group i, wherein the evaluation index value corresponding to the sample object group i includes the mean.

2. The method according to claim 1, characterized in that: The object to be processed has multiple characteristic values; The step of obtaining a plurality of sample objects that match the feature values ​​of the object to be processed includes: According to the multiple characteristic values ​​of the object to be processed, determining the characteristic value ranges corresponding to the multiple characteristic values ​​respectively; A plurality of sample objects whose multiple characteristic values ​​all match the corresponding characteristic value ranges are obtained from the sample database.

3. The method according to claim 1, characterized in that The object to be processed has multiple characteristic values; The step of obtaining a plurality of sample objects that match the feature values ​​of the object to be processed includes: Acquire a first set of sample objects that match a first characteristic value of an object to be processed; Acquire a second sample object set matching a second feature value of the object to be processed from the first sample object set; The first feature value and the second feature value are two of the multiple features, and the first feature value is more important than the second feature value.

4. The method according to claim 1, characterized in that The method further comprises: The sample object groups having the number of sample objects less than a set threshold are filtered out from the multiple sample object groups.

5. The method according to claim 4, characterized in that The method further comprises: According to the number of sample objects respectively included in the multiple sample object groups, an average number of sample objects corresponding to the multiple sample object groups is determined, and the average number of sample objects is used as the set threshold.

6. The method according to claim 1, characterized in that The step of determining the evaluation index values ​​corresponding to each of the plurality of sample object groups according to the detection index values ​​of the sample objects respectively included in the plurality of sample object groups comprises: For any sample object group i among the multiple sample object groups, determining the number of sample objects whose detection index values ​​in the sample object group i meet the set threshold condition; The qualified rate corresponding to the sample object group i is determined according to the number of sample objects, and the qualified rate is included in the evaluation index value corresponding to the sample object group i.

7. The method according to claim 1, characterized in that The step of determining the evaluation index values ​​corresponding to each of the plurality of sample object groups according to the detection index values ​​of the sample objects respectively included in the plurality of sample object groups comprises: According to the detection index values ​​and generation time of the sample objects respectively included in the plurality of sample object groups, the evaluation index values ​​corresponding to the plurality of sample object groups are determined.

8. The method according to claim 7, characterized in that The step of determining the evaluation index values ​​corresponding to each of the plurality of sample object groups according to the detection index values ​​and generation times of the sample objects respectively included in the plurality of sample object groups comprises: For any sample object group i among the multiple sample object groups, determining a weight corresponding to each sample object in the sample object group i according to a generation time corresponding to each sample object in the sample object group i; According to the weights and detection index values ​​corresponding to the sample objects in the sample object group i, the evaluation index value corresponding to the sample object group i is determined.

9. The method according to claim 8, characterized in that The later the sample object is generated, the higher the weight it has.

10. The method according to claim 1, characterized in that Each sample object group has multiple evaluation index values; the method further includes: According to the preset importance order of the multiple evaluation indicators corresponding to the multiple evaluation indicator values, a sample object group whose evaluation indicator values ​​meet the set conditions is determined.

11. The method according to claim 1, characterized in that The method further comprises: The processing parameter value and the evaluation index value corresponding to the sample object group whose evaluation index value meets the set conditions are outputted, so that the user can confirm whether to adopt the processing parameter value as the processing parameter value of the object to be processed.

12. The method according to claim 1, characterized in that The method further comprises: Determine the detection index value of the object to be processed after being processed under the processing parameters; The characteristic values, processing parameter values ​​and detection index values ​​of the object to be processed are updated in the sample database.

13. A parameter determination device, characterized in that: include: An acquisition module, used to acquire a plurality of sample objects matching the characteristic values ​​of the object to be processed, wherein the object to be processed includes a plate to be straightened, and the characteristic value includes at least one of the following: plate type, plate thickness, plate width, plate temperature, yield point, and tensile strength; A grouping module, for grouping the plurality of sample objects according to the processing parameter values ​​corresponding to the plurality of sample objects, and grouping the sample objects with the same processing parameter values ​​or with a difference less than a set threshold into one group, so as to obtain a plurality of sample object groups, wherein the processing parameter values ​​include: an inlet roll gap value, an outlet roll gap value and a roll bending amount of a straightening machine; A determination module, for determining evaluation index values ​​corresponding to each of the plurality of sample object groups according to the detection index values ​​of the sample objects respectively contained in the plurality of sample object groups; and determining a processing parameter value corresponding to the sample object group whose evaluation index value meets the set conditions as the processing parameter value of the object to be processed; the detection index value includes at least one of the following: the straightness of the plate in the length direction and the straightness of the plate in the width direction; the evaluation index value includes at least one of the following: the average straightness of the plate in the length direction, the average straightness of the plate in the width direction, the qualified rate of the straightness of the plate in the length direction, and the qualified rate of the straightness of the plate in the width direction; The determination module is specifically used to: for any sample object group i among the multiple sample object groups, determine the mean value of the detection index values ​​of each sample object in the sample object group i, and the evaluation index value corresponding to the sample object group i includes the mean value.

14. An electronic device, characterized in that: include: A memory and a processor; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the parameter determination method according to any one of claims 1 to 12.

15. A non-transitory machine-readable storage medium, characterized in that: The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the parameter determination method according to any one of claims 1 to 12.

Images