A finishing gauge changing control method and system

Abstract

This invention provides a finishing mill specification change control method and system. The method includes: within a single finishing mill work roll change cycle, if the historical number of rolled strips of the corresponding specification after the specification change is zero, then obtaining learning values ​​matching the target final rolling temperature, width, and thickness of the strip after the specification change from a short-cycle data table; wherein the short-cycle data table is used to record the learning values ​​within a single finishing mill work roll change cycle; and performing a finishing mill pre-setting calculation for the first strip after the specification change based on the matching learning values, thereby improving the accuracy of the pre-setting parameters for the head of the first strip after the specification change. This invention can effectively improve the control accuracy of the final rolling temperature and thickness of the head of the first strip after the specification change, and improve the quality control accuracy of the first strip after the specification change.

Description

Technical Field

[0001] This invention relates to the field of steel production application technology, and in particular to a method and system for controlling specifications during finishing rolling. Background Technology

[0002] In the hot-rolled strip steel production process, the finishing rolling force is directly and strongly correlated with deformation temperature and deformation speed. It is difficult to use the same set of rolling force parameters to meet a wide range of temperature and rolling speed changes. Relying solely on model learning values ​​will lead to fluctuations in the learning values, resulting in problems such as thickness fluctuations in the first strip when changing specifications. The finishing rolling looper of the hot-rolled coil production line in the steel mill is relatively stable, and the rolling force deviation of each stand is also relatively small. Currently, there are two main problems: First, the temperature prediction deviation of each stand in the finishing mill and the F7 exit is large. The hot-rolled coil production line has always had a large temperature prediction deviation, mainly due to the deviation of the temperature calculation model and the accuracy of the roughing mill exit temperature detection RDT and the finishing mill exit temperature detection FDT. This leads to large deviations in the final rolling temperature and thickness of the first strip when changing specifications. Second, the temperature variation range of the intermediate billets in the hot-rolled coil production line is large, including the large temperature difference between the slabs in the furnaces of heating furnaces 1-3. Summary of the Invention

[0003] This invention provides a finishing mill specification change control method and system to solve the problem that the pre-calculated temperature deviation of each stand and F7 exit of the finishing mill for specification change coils is large due to deviations in the pre-set calculation model of the finishing mill and errors in the pyrometer detection, which affects the accuracy of rolling force control and head thickness control.

[0004] This invention provides a method for controlling specifications during finishing milling, the method comprising:

[0005] If the number of historical rolled strips of the corresponding specification after the specification change is zero within a single roll change cycle of the finishing mill work roll, then the learning value matching the target final rolling temperature, width and thickness of the strip with the changed specification is obtained from the short cycle data table; wherein the short cycle data table is used to record the learning value within a single roll change cycle of the finishing mill work roll. The precision rolling pre-setting calculation of the first strip after precision rolling and specification change is performed based on the matched learning value to improve the accuracy of the pre-setting parameters of the head of the first strip after precision rolling and specification change.

[0006] In one embodiment of the present invention, when no learning value is matched in the short-cycle data table, a corresponding learning value is matched from the long-cycle data table, wherein the long-cycle data table is used to record various learning values ​​calculated after finishing rolling.

[0007] In one embodiment of the present invention, after the learning value is matched, the finishing rolling force and temperature learning values ​​are directly used for the finishing pre-setting calculation of the first strip steel of the changed specification, while the roll gap learning value is averaged with the conventional roll gap learning value and then used for the finishing pre-setting calculation of the first strip steel of the changed specification.

[0008] In one embodiment of the present invention, the long-cycle data table and the short-cycle data table store data by associating the learning value with the primary key. When the finishing mill changes specifications, the corresponding learning value is queried by matching the primary key. The primary key includes the furnace number layer, the roughing mill exit temperature layer, the rolling grade, the tapping mark, the thickness layer, the width layer, whether the hot coil box is used, and the target final rolling temperature layer.

[0009] In one embodiment of the present invention, matching the corresponding learning value from the long-period data table includes: matching all primary keys in the long-period data table to obtain the matching learning value; if there is no matching learning value, then sequentially widening the matching range of the furnace number, width, target final rolling temperature and thickness to a preset range to obtain the matching learning value; if there is still no matching learning value, then using the conventional learning value to perform the pre-set calculation for the finishing rolling of the first strip steel of the finished rolling specification change.

[0010] In one embodiment of the present invention, within a single roll change cycle of a finishing work roll, if the number of historical rolled blocks of the corresponding specification after the specification change is not zero, then all primary keys are matched from the short-term data table to obtain the corresponding learning value. If there is no matching learning value, then the conventional learning value is used to perform the finishing pre-setting calculation for the first strip of steel with the specification change in the finishing rolling.

[0011] In one embodiment of the present invention, during the rolling of strip steel of the same specification within a unit roll change cycle of a finishing work roll, the roughing exit detection temperature of the current intermediate billet is compared with the roughing exit detection temperature of the previous intermediate billet. If the difference between the two is within ±15 degrees Celsius, the learning values ​​corresponding to all primary keys are matched from the short-term data table to perform the finishing pre-setting calculation of the current strip steel of the same specification. If there is no matching learning value, the conventional learning value is used to perform the finishing pre-setting calculation of the current strip steel of the same specification. If the difference between the two exceeds ±15 degrees Celsius and there is no matching learning value in the short-term data table, then all learning values ​​corresponding to the primary keys are matched from the long-term data table. The finishing temperature, rolling force, and roll gap learning values ​​are averaged with the corresponding conventional learning values ​​and then used for the finishing pre-setting calculation of the current strip steel of the same specification. If there is no matching learning value in the long-term data table, then the conventional learning value is used for the finishing pre-setting calculation.

[0012] In one embodiment of the present invention, if the thickness deviation of the head of the finished strip is within ±0.25mm and the head final rolling temperature deviation is within ±22℃, the temperature, rolling force and roll gap learning value calculated after the current finished strip are updated in the short-cycle data table, wherein the learning value of the short-cycle data table is cleared each time the work roll is changed during the finished rolling.

[0013] The present invention also provides a finishing mill specification change control system, the system comprising: The data matching module is used to obtain learning values ​​from the short-cycle data table that match the target final rolling temperature, width, and thickness of the strip after the specification change if the historical number of rolled blocks of the corresponding specification is zero within a unit roll change cycle of the finishing mill work roll; wherein the short-cycle data table is used to record the learning values ​​within a unit roll change cycle of the finishing mill work roll. The calculation module is set to perform pre-setting calculations for the first strip after finishing and specification change based on the matched learning values, so as to improve the accuracy of the pre-setting parameters of the head of the first strip after finishing and specification change.

[0014] The beneficial effects of this invention are as follows: The finishing mill specification change control method and system proposed in this invention improves the accuracy of the finishing mill pre-setting calculation by learning and matching short-cycle data tables, long-cycle data tables, and conventional data tables according to certain classification rules during the finishing mill pre-setting calculation. This can meet the requirements of large temperature differences between slabs in large heating furnaces and large temperature variations of incoming slabs in roughing mills. By improving the accuracy of the finishing mill pre-setting parameters of the first strip steel for specification change, the accuracy of the final rolling temperature and rolling force control of the strip head is improved, thereby improving the control accuracy of the thickness of the first strip steel head and the entire length for specification change, and improving the quality control accuracy of the coil head and the entire length for specification change. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0016] In the attached diagram: Figure 1 This is a statistical representation of the rolling force learning values ​​and temperature learning values ​​corresponding to different finishing rolling speeds and intermediate billet inlet temperatures, provided in an embodiment of the present invention. Figure 2 This is a flowchart illustrating a finishing mill specification control method provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of the configuration file corresponding to the fuzzy matching function of the finishing mill specification learning value provided in one embodiment of the present invention; Figure 4 This is a block diagram of a finishing mill specification change control system provided in one embodiment of the present invention. Detailed Implementation

[0017] The following specific examples illustrate the implementation of the present invention. 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. Various 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. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0018] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0019] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0020] The inventor discovered through research that: The finishing rolling looper of the hot-rolled coil production line in the steel rolling mill is relatively stable, and the rolling force deviation of each stand is also relatively small. The main problems at present are mainly of two types: First, the temperature prediction deviation of each stand exit and F7 exit of the finishing mill is large. The hot-rolled coil production line has always had a large temperature prediction deviation, mainly due to the deviation of the temperature calculation model and the accuracy of the RDT and FDT detection temperatures at the roughing mill exit. This leads to a large deviation in the final rolling temperature of the first strip head when changing specifications. Second, the temperature variation range of the intermediate billet in the hot-rolled coil production line is large, including the large temperature difference between furnaces 1-3. Figure 1 To analyze the data within the same layer by the fine rolling speed v and the RDT temperature range, it can be seen that there are significant differences between the rolling force learning value lcr and the temperature learning value lct.

[0021] Due to deviations in the temperature calculation model and errors in the pyrometer, the pre-calculated temperatures of each stand in the finishing mill and at the F7 exit are significantly different when changing specifications of the coil, affecting the rolling force and head thickness control accuracy of each stand in the finishing mill. Because the existing control system uses a conventional learning value inheritance method for finishing mill, the pre-set rolling force and roll gap for changing specifications of the coil often deviate significantly, resulting in a large deviation in the head thickness of the coil when changing specifications, which affects the dimensional control accuracy of the strip head thickness.

[0022] In view of the problems existing in the prior art, the present invention provides a method and system for controlling the specification change of finishing mill. The technical solution of the present invention will be described in detail below with reference to specific embodiments.

[0023] Please see Figure 2 , Figure 2 This is a flowchart illustrating a finishing mill specification control method according to an embodiment of the present invention. The method includes the following steps: Step S200: If the number of historical rolled blocks of the corresponding specification after the specification change is zero within a unit roll change cycle of the finishing mill work roll, then the learning value matching the target final rolling temperature, width and thickness of the strip with the changed specification is obtained from the short cycle data table; wherein the short cycle data table is used to record the learning value within a unit roll change cycle of the finishing mill work roll.

[0024] In one embodiment, short-cycle data tables, long-cycle data tables, and regular data tables can be pre-set. The short-cycle data table records finishing rolling learning values ​​within one finishing rolling work roll change cycle unit. These learning values ​​may include finishing rolling temperature, rolling force, and roll gap learning values. The regular data table records existing regular primary key self-learning values, i.e., learning value data calculated after finishing rolling based on four default layers: steel tapping mark, thickness, width, and target final rolling temperature. The long-cycle data table records various finishing rolling learning values ​​calculated after finishing rolling. The learning values ​​in the long-cycle data table are finishing rolling self-learning parameters that ensure the head quality meets requirements during historical rolling processes for different steel grades and specifications. These values ​​are typically stored for a longer period and are not frequently updated or changed. In both the short-cycle and long-cycle data tables, learning values ​​are stored in association with primary keys, which serve as the data table index. The primary key can be divided into eight layers: furnace number layer, roughing mill exit temperature detection layer, steel grade, tapping mark, thickness layer, width layer, hot coil box usage layer, and target final rolling temperature layer. Unlike existing conventional learning methods, a new steel grade layer and an intermediate billet inlet temperature (RDT) layer (i.e., roughing mill exit temperature range layer) are added. The furnace number is also used as one of the primary keys for classification. Furthermore, the roughing mill intermediate billet inlet temperature (RDT) can be further categorized in the corresponding data table, dividing this temperature layer into eight categories with the following intervals: 960.0, 980.0, 1000.0, 1020.0, 1040.0, 1060.0, and 1080.0. A layer is defined as less than or equal to 960, a layer is defined as greater than 1080, and the intervals are defined as greater than the left layer and less than or equal to the right layer. In subsequent queries, the corresponding layer learning value can be added to the roughing intermediate billet incoming temperature query data table for precise matching queries. If no matching data is found in the precise query, the query range can be expanded to adjacent layers to obtain the corresponding fuzzy matching query results.

[0025] In one embodiment, during the pre-setting calculation for finishing mill specification conversion, a fuzzy matching query function can be activated. This function uses relevant information about the finished strip, such as thickness, target final rolling temperature, width, tapping mark, and rolling grade, as input. This information is then matched against corresponding indices in a data table. When the similarity to the index reaches a set threshold, it is determined that matching data exists in the data table, and the various learning values ​​indexed in the data table are output. A separate configuration file, FSUINHERIT.conf, can be generated for the finishing mill specification conversion fuzzy matching function. In this configuration file, the first character of NEW_INHERIT_ONOFF indicates whether the finishing mill fuzzy matching learning values ​​are read and used during the pre-setting calculation, and the second character indicates whether the fuzzy matching learning values ​​are updated during the post-finishing calculation. Figure 3 The diagram shows that the current pre-set calculation for finishing milling does not yet use fuzzy matching learning values; it is simply in a state of continuously updating fuzzy matching learning values. When using it, the first bit needs to be set to 1. Pre-set input modes for the first strip after changing specifications can include: input.mode 11 (indicating the first strip after changing specifications, and not rolled within a unit roll change cycle), input.mode 12 (indicating the first strip after changing specifications but rolled within a unit roll change cycle), input.mode 21 (indicating the first strip after not changing specifications but with a good intermediate billet temperature at the roughing mill exit), and input.mode 22 (indicating the first strip after not changing specifications but with a poor intermediate billet temperature at the roughing mill exit). The fuzzy matching learning values ​​can be applied to the pre-set calculation process for changing specifications by modifying the input / output modes in the configuration file.

[0026] Step S210: Perform the pre-setting calculation of the first strip after the finishing mill specification change based on the matched learning value, so as to improve the accuracy of the pre-setting parameters of the head of the first strip after the finishing mill specification change.

[0027] In one embodiment, when the number of strip steel blocks of the current specification being rolled is 0 within a finishing rolling work roll change cycle unit (input mode input.mode==11), look up similar data in the short cycle data table (same target final rolling temperature, similar width, and similar thickness), (output mode output.mode= SHORT_CLOSE (2), i.e., output fuzzy matching data).

[0028] In one embodiment, when no learning value is found in the short-cycle data table, the corresponding learning value is matched from the long-cycle data table, which is used to record various learning values ​​calculated after finishing rolling. Specifically, when no matching learning value data is found in the short-cycle data table through exact matching (matching all indices) or fuzzy matching (i.e., matching some indices), exact matching is performed from the long-cycle data table. The rolling force and temperature learning values ​​obtained by exact matching are directly used for the pre-set calculation of finishing rolling without averaging. The roll gap learning value is averaged with the conventional roll gap learning value and then used for the pre-set calculation of finishing rolling.

[0029] In one embodiment, matching the corresponding learning value from the long-term data table includes: matching all primary keys in the long-term data table to obtain the matching learning value; if no matching learning value is found, the matching ranges for the furnace number, width, target final rolling temperature, and thickness are sequentially widened to a preset range to obtain the matching learning value; if no matching learning value is found again, conventional learning values ​​are used to perform the pre-setting calculation for the first strip of steel with the changed specifications. Specifically, when no matching precise data is found in the long-term data table, the search is sequentially widened for the furnace number, width layer, target final rolling temperature layer, and thickness layer. By widening the search layer by layer, fuzzy matching is performed to obtain the corresponding fuzzy matching learning value data. The execution logic of the above process is as follows: if precise matching learning value data is available, the precise learning value data is used directly; if no precise learning value data is available and the number of historical rolled strips is 0, the fuzzy matching learning value data is used; otherwise, the corresponding specification conventional self-learning value is retrieved from the conventional data table for the pre-setting calculation of the finishing rolling.

[0030] In one embodiment, within a single finishing mill roll changeover cycle, if the historical number of rolled strips corresponding to the changed specification is not zero, all primary keys are matched from the short-term data table to obtain the corresponding learning value. If no matching learning value is found, the conventional learning value is used for the pre-setting calculation of the first strip of steel with the changed specification in the finishing mill. Specifically, when the number of rolled strips of the current specification is not zero within a single finishing mill roll changeover cycle (input mode intput.mode==12), the precise data in the short-term data table is searched (the precise learning value of the 8 primary keys is matched); otherwise, the conventional learning value is used for the pre-setting calculation of the first strip of steel with the changed specification in the finishing mill.

[0031] In one embodiment, during the rolling of strip of the same specification within a single roll change cycle of the finishing work roll, the roughing exit temperature of the current strip is compared with that of the previous strip. If the difference is within 15 degrees Celsius, the learning values ​​corresponding to all primary keys in the short-cycle data table are matched to perform the finishing pre-setting calculation for the current strip of the same specification. If no matching learning value is found, the conventional learning value is used for the finishing pre-setting calculation. If the difference exceeds 15 degrees Celsius and no matching learning value is found in the short-cycle data table, the finishing temperature, rolling force, and roll gap learning values ​​corresponding to all primary keys are matched from the long-cycle data table, and averaged with the conventional learning values ​​of the corresponding specification before being used for the finishing pre-setting calculation of the current strip. If no matching learning value is found in the long-cycle data table, the conventional learning value is used for the finishing pre-setting calculation. Specifically, if the difference between the current roughing mill exit temperature (RDT) of the strip and the RDT of the previous strip of the same specification is within ±15℃ (input.mode==21), and if exact matching data (matching the exact learning values ​​of the 8 primary keys) can be found in the short-cycle data table, then the learning values ​​matched in the short-cycle data table are used for the finishing mill pre-setting calculation; otherwise, the conventional learning values ​​are used for the finishing mill pre-setting calculation. If the difference between the current roughing mill exit temperature (RDT) of the strip and the RDT of the previous strip of the same specification exceeds ±15℃ (input.mode==22), and if exact data is not found in the short-cycle data table, then the exact data corresponding to all primary keys is matched in the long-cycle data table. After finding the exact data, the finishing mill temperature, rolling force, roll gap learning values, and the conventional self-learning values ​​of the corresponding specifications are averaged and used for the finishing mill pre-setting calculation. If exact data is not found in the long-cycle data table, then the conventional learning values ​​are used for the finishing mill pre-setting calculation. The existing conventional learning control logic and the information transmission rules between the upper and lower blocks remain unchanged. Details will not be elaborated here. The standard learning values ​​may include finishing rolling force learning values, roll gap learning values, and temperature learning values. The rolling force and roll gap learning values ​​are updated after finishing rolling based on the tap mark, thickness, width, and target final rolling temperature layer (measured data collected at the strip head after threading). The temperature learning value is updated after finishing rolling based on the tap mark, thickness, width, target final rolling temperature, and furnace number layer. Standard learning values ​​have fewer primary keys than those in the short-cycle and long-cycle data tables. In one embodiment, if the finishing strip head thickness deviation is within ±0.25mm and the head final rolling temperature deviation is within ±22℃, the current finishing strip post-calculation learning values ​​are used to update the short-cycle data table. The short-cycle data table is cleared after each roll change, where the head thickness deviation is ≤±0.25mm and the head final rolling temperature deviation is ≤±22℃. Short-cycle learning values ​​are automatically excluded after intermediate billet oscillation.In the fuzzy matching function of this embodiment, the primary keys in the long-cycle and short-cycle data tables are more numerous than those in the conventional data tables. The stored learning values ​​are more closely aligned with the actual production site and different working conditions. The update time of the learning values ​​in the short-cycle and long-cycle data tables is the same as that of the existing conventional data tables. Both are updated after the strip threading is completed on the F7 stand of the finishing mill. After collecting the strip head temperature, rolling force, thickness, etc., the temperature learning value, rolling force learning value, and roll gap learning value are updated. The accuracy of the finishing mill learning value leads to more accurate pre-set rolling force, roll gap, and pre-calculated exit temperature, effectively improving the pre-calculation setting accuracy and the control accuracy of the final rolling temperature and thickness at the head of the coil when changing specifications.

[0032] Based on the technical solutions of the above embodiments of the present invention, the problems of low precision calculation accuracy of finishing mill and large deviations in the final rolling temperature and thickness of the head of the coil being changed due to unreasonable learning value parameters of finishing mill caused by changes in actual working conditions on site when changing specifications of the coil are effectively solved.

[0033] Please see Figure 4 , Figure 4 This is a flowchart illustrating a finishing mill specification change control system according to an embodiment of the present invention. The system includes a data matching module 40, used to obtain learning values ​​matching the target final rolling temperature, width, and thickness of the strip after specification change from a short-cycle data table if the historical number of rolled strips of the corresponding specification after specification change is zero within a single finishing mill work roll change cycle; wherein the short-cycle data table is used to record the learning values ​​within a single finishing mill work roll change cycle; and a setting calculation module 41, used to perform pre-setting calculations for the finishing mill of the first strip after specification change based on the matched learning values, so as to improve the accuracy of the pre-setting parameters of the head of the first strip after specification change.

[0034] In one embodiment, the data matching module 40 is further configured to match a corresponding learning value from a long-cycle data table when no learning value is matched in the short-cycle data table, wherein the long-cycle data table is used to record various learning values ​​calculated after finishing rolling.

[0035] In one embodiment, the data matching module 40 is further configured to, after matching the learning values, directly use the finishing rolling force and temperature learning values ​​for the finishing pre-setting calculation of the first strip steel of the changed specification, while the finishing roll gap learning value is averaged with the conventional roll gap learning value and then used for the finishing pre-setting calculation of the first strip steel of the changed specification.

[0036] In one embodiment, the long-cycle data table and the short-cycle data table store data by associating the learned values ​​with the primary key. When the finishing mill changes specifications, the corresponding learned value is queried by matching the primary key. The primary key includes the furnace number layer, the roughing mill exit temperature layer, the steel grade, the tapping mark, the thickness layer, the width layer, whether the hot coil box is used, and the target final rolling temperature layer.

[0037] In one embodiment, the data matching module 40 is further configured to match the corresponding learning value from the long-period data table, including: matching all primary keys in the long-period data table to obtain the matching learning value; if there is no matching learning value, then sequentially widening the matching range of the furnace number, width, target final rolling temperature and thickness to a preset range to obtain the matching learning value; if there is still no matching learning value, then using the conventional learning value to perform the pre-set calculation for the finishing rolling of the first strip steel of the different specifications.

[0038] In one embodiment, the data matching module 40 is further configured to, within a single roll change cycle of a finishing mill work roll, if the number of historical rolled blocks of the corresponding specification after the specification change is not zero, match all primary keys from the short-term data table to obtain the corresponding learning value; if there is no matching learning value, use the conventional learning value to perform the finishing mill pre-setting calculation for the first strip steel of the finished mill specification change.

[0039] In one embodiment, the data matching module 40 is further configured to compare the roughing exit detection temperature of the current intermediate billet with the roughing exit detection temperature of the previous intermediate billet during the rolling of strip of the same specification within a unit roll change cycle of a finishing work roll. If the difference between the two is within ±15 degrees Celsius, then the learning values ​​corresponding to all primary keys in the short-term data table are matched to perform the finishing pre-setting calculation of the current strip of the same specification. If there is no matching learning value, then the conventional learning value is used to perform the finishing pre-setting calculation. If the difference between the two exceeds ±15 degrees Celsius and there is no matching learning value in the short-term data table, then all learning values ​​corresponding to the primary keys are matched from the long-term data table. The finishing temperature, rolling force, and roll gap learning values ​​are averaged with the corresponding conventional learning values ​​and then used for the finishing pre-setting calculation of the current strip steel of the same specification. If there is no matching learning value in the long-term data table, then the conventional learning value is used for the finishing pre-setting calculation.

[0040] In one embodiment, the data matching module 40 is further configured to update the short-cycle data table with the calculated temperature, rolling force and roll gap learning value of the current strip after finishing if the thickness deviation of the head of the finishing strip is within ±0.25mm and the head final rolling temperature deviation is within ±22℃. The learning value of the short-cycle data table is cleared each time the finishing rolling work roll is changed.

[0041] The finishing mill specification change control system of the present invention and the aforementioned method embodiments belong to the same inventive concept. The specific system execution process has been described in detail in the aforementioned embodiments and will not be repeated here.

[0042] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for controlling specifications during finishing rolling, characterized in that, The method includes: If the number of historical rolled strips of the corresponding specification after the specification change is zero within a single roll change cycle of the finishing mill work roll, then the learning value matching the target final rolling temperature, width and thickness of the strip with the changed specification is obtained from the short cycle data table; wherein the short cycle data table is used to record the learning value within a single roll change cycle of the finishing mill work roll. The precision rolling pre-setting calculation of the first strip after precision rolling and specification change is performed based on the matched learning value to improve the accuracy of the pre-setting parameters of the head of the first strip after precision rolling and specification change.

2. The finishing mill specification control method according to claim 1, characterized in that, When no learning value is found in the short-cycle data table, the corresponding learning value is matched from the long-cycle data table, wherein the long-cycle data table is used to record various learning values ​​calculated after finishing rolling.

3. The finishing mill specification control method according to claim 2, characterized in that, After matching the learning values, the learning values ​​corresponding to rolling force and temperature are directly used for the pre-setting calculation of the finishing of the first strip of steel with different specifications. The roll gap learning value is averaged with the regular roll gap learning value and then used for the pre-setting calculation of the finishing of the first strip of steel with different specifications.

4. The finishing mill specification control method according to claim 3, characterized in that, The long-cycle data table and the short-cycle data table store data by associating the learned values ​​with the primary key. When the finishing mill changes specifications, the corresponding learned value is queried by matching the primary key. The primary key includes the furnace number layer, the roughing mill exit temperature layer, the steel grade, the steel tapping mark, the thickness layer, the width layer, whether the hot coil box is used, and the target final rolling temperature layer.

5. The finishing mill specification control method according to claim 3, characterized in that, Matching the corresponding learning value from the long-term data table includes: matching all primary keys in the long-term data table to obtain the matching learning value; if there is no matching learning value, then sequentially widening the matching range of the furnace number, width, target final rolling temperature and thickness to the preset range to obtain the matching learning value; if there is still no matching learning value, then using the conventional learning value to perform the pre-set calculation for the finishing rolling of the first strip steel of the finished rolling specification change.

6. The finishing mill specification control method according to claim 5, characterized in that, Within a single roll change cycle of a finishing mill work roll, if the number of historical rolled strips of the corresponding specification after the specification change is not zero, then all primary keys are matched from the short-term data table to obtain the corresponding learning value. If there is no matching learning value, then the conventional learning value is used to perform the finishing mill pre-setting calculation for the first strip of steel with the changed specification.

7. The finishing mill specification control method according to claim 6, characterized in that, Within a single roll change cycle of a finishing work roll, when rolling strip of the same specification, the roughing exit temperature of the current intermediate billet is compared with the roughing exit temperature of the previous intermediate billet. If the difference between the two is within ±15 degrees Celsius, the learning values ​​corresponding to all primary keys in the short-term data table are matched to perform the finishing pre-setting calculation for the current strip of the same specification. If there is no matching learning value, the conventional learning value is used to perform the finishing pre-setting calculation for the current strip of the same specification. If the difference between the two exceeds ±15 degrees Celsius and there is no matching learning value in the short-term data table, then all learning values ​​corresponding to the primary key are matched from the long-term data table. The finishing temperature, rolling force, and roll gap learning values ​​are averaged with the corresponding conventional learning values ​​and then used for the finishing pre-setting calculation of the current strip steel of the same specification. If there is no matching corresponding learning value in the long-term data table, then the conventional learning value is used for the finishing pre-setting calculation.

8. The finishing mill specification control method according to claim 7, characterized in that, If the thickness deviation of the head of the finished strip is within ±0.25mm and the head final rolling temperature deviation is within ±22℃, then the current finishing rolling temperature, rolling force and roll gap learning value of the strip will be updated in the short-cycle data table. The learning value of the short-cycle data table will be cleared each time the finishing rolling work roll is changed.

9. A finishing mill specification change control system, characterized in that, The system includes: The data matching module is used to obtain learning values ​​from the short-cycle data table that match the target final rolling temperature, width, and thickness of the strip after the specification change if the historical number of rolled blocks of the corresponding specification is zero within a unit roll change cycle of the finishing mill work roll; wherein the short-cycle data table is used to record the learning values ​​within a unit roll change cycle of the finishing mill work roll. The calculation module is set to perform pre-setting calculations for the first strip after finishing and specification change based on the matched learning values, so as to improve the accuracy of the pre-setting parameters of the head of the first strip after finishing and specification change.

Images