JPH0320609A - Apparatus for detecting shape of strip-shaped metal material or plate-shaped metal material - Google Patents

Abstract

PURPOSE:To make it possible to judge the entire surface shape adequately by detecting the actual shape data of a running strip-shaped or plate-shaped metal material in the direction of width with a sensor, and operating the classification item and the degree of the actual shape state. CONSTITUTION:In a device for adjusting objective shape of aluminum-foil rolling 1, inference logic is actuated by the key input from a terminal unit 6 at the side of an aluminum rolling mill 2. The operating condition data from the rolling mill 2 are inputted through a shape control part 3. A rolling-data collecting part receives the operating condition data including the actual shape data from the control data and writes the data into a work memory. A rolling-state analyzing part analyzes the actual data, judges the rolled state of an aluminum foil 53 and analyzes the present objective state data. Then a control-objective generating part sets the control objective as to which way the actual shape of the aluminum foil 53 is to be changed with the result of the analysis of the actual shaped data from the rolling-state analyzing part and the input from the terminal unit manipulated by an operator 5. Then, an action- candidate inference part writes the action for realizing the control objective in the work memory.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a shape detection device that detects the shape of a running belt-shaped metal material or plate-shaped metal material in the width direction.

[Prior art]

In general, the shape of a spinal or plate-shaped metal material has varying degrees of elongation and tension, which will be described later, in the width direction of the material. Sometimes this is the cause of wrinkles, and the areas that are stretched are
A large amount of tension is applied, which may cause breakage. Furthermore, if the shape of the metal material related to elongation and tension is asymmetrical in the width direction, the way tension is applied will be unbalanced in the width direction, which may cause the metal material to meander. In this way, in the process of handling band-shaped or plate-shaped metal materials,
Measuring and understanding the shape state in the width direction is very important when operating the process.

As a shape detection device for detecting the shape state in the width direction as described above, the I-UNIT value indicating the elongation rate is measured at multiple points in the width direction of the metal material, and the process is performed based on the 1-UNIT value. For example, a graph showing the width direction distribution of the elongation rate may be displayed on a screen to assist the operator who operates the process.

Figure 19 shows a roll rolling mill 2 for rolling aluminum foil, which is an example of the background of the present invention. In aluminum foil rolling, the width of the coil wound around the input coil 50 is approximately 700 to 1700 m, and the thickness is several microns.
The raw aluminum foil 51 with a thickness of about 300 to 1
A pair of rolling rolls 5 at a speed of 200 m/win
2 to reduce its thickness to about A. Then, the rolled aluminum foil 53 is transferred to the output coil 64.
It is transported in the direction of arrow K by a constant tension generated by the rotation of the drive shaft (FIG. 1), and is wound around the output coil 64. For example, when rolling raw material Al SG'a 51 with a thickness of several hundred μm into aluminum foil 53 with a thickness of several μm, the rolling process is repeated several times, and the number of rolling times is equal to the number of buses. be called.

In the above-described proper metal rolling in ξ metric units, the aluminum foil 53 is "elongated" in the v3 width direction (arrow L), as shown in FIG. 20, even though its thickness is the same. There is a remarkable portion that is “tensioned” with the portion. In other words, the stretched portion 54 is in the direction of conveyance of the aluminum fi 53 (
A peak portion 56 and a valley portion 57 are formed along the arrow K), and the tensioned portion 55 has a generally flat shape. Therefore, the aluminum foil 53 shown in the figure is in a state in which the central portion in the width direction of the foil (arrow L) is elongated and the ends are stretched. The distribution of elongation and tension in the foil width direction (indicated by the arrow) is hereinafter referred to as the surface shape or actual shape of aluminum M53.
The surface shape has a great influence on the quality of the foil product, and in some cases, a large tension is applied to the stretched portion 55, causing the foil to break. Further, the stretched portion 54 causes wrinkles. Regarding AlξV353 as the final product,
It is natural that a flat shape with uniform elongation and tension is desired, but it is not necessarily a flat actual shape for each pass, and the aluminum foil 53 on the bus on the way has a wide variety of shapes. It becomes something. Aluminum foil 5 as mentioned above
The surface shape of No. 3 can be controlled by changing the shape of the rolling roll 52. As shown in FIGS. 19 to 21, the rolling roll 52 generates a bulge called a thermal crown due to heat generation during rolling and its heat conduction properties. The example shown in FIG. 21 is a case where the quarter part a is swollen. Such a bulge, ie, a thermal crown, changes the surface shape of the aluminum foil 53 depending on its appearance location and degree of swell. That is, the aluminum foil 53 that has been rolled at a portion where the degree of expansion of the thermal crown of the rolling roll 52 is large is in an elongated state at that rolled portion. Therefore, the surface shape of the aluminum foil 53 is designed to control the temperature or injection amount of the coolant 58 (FIG. 1) that is injected toward the rolling roll 52 in the width direction (arrow L (
(Fig. 20)). Such shape control of the aluminum foil 53 is performed by the roll rolling machine 2.
This is done by the shape control section 3 installed next to the. That is, the shape control section 3 is rotatably provided on the exit side of the rolling roll 52, and the shape control section 3 is configured to control the shape of the aluminum pipe 53 from the inspection roll 4, which is made up of elements 46 divided into 36 pieces in the foil width direction (indicated by the arrow). Actual shape data of elongation and tension are input. Each element 46 has l piezoelectric elements (not shown) embedded therein. It works as a sensor to detect the pressure force applied to the outer circumferential surface of the And element 4. The stretched portion 54 of the aluminum foil 53 that is pressed upward and pulled in the transport direction (arrow K) with a constant tension is the element 4 . Element 4 when passing above. The pressure contact force against the tension part 55 is small, and on the other hand, when the tensioned part 55 passes, it is detected to be large. Therefore, the actual shape of the aluminum foil 53 is as shown in FIG. 2l for each element 4. It is expressed as the distribution in the width direction of the elongation rate (actual shape data) converted from the pressure contact force data detected from . In the illustrated case, the quarter portion a of the rolling roll 52 is too swollen, so cooling of that portion is promoted and heat is stored in the central portion of the rolling roll 52 and both ends thereof.
The target shape has been set. The shape control unit 3 compares and calculates the actual shape data with target shape data input in advance, and determines the element 4 that the actual shape data has a higher elongation rate. The amount of coolant 58 injected toward the part of the rolling roll corresponding to . The coolant 58 is injected from an injection pipe 59 which is disposed on the inlet side of the rolling roll 52 and is sprayed separately in the foil width direction (arrow L). The thermal crown is relaxed, and the portion of the aluminum foil 53 corresponding to the quarter portion a is deformed toward the tensioned state. If the elongation rate is lower in the actual shape data, the opposite operation is performed. In addition, in the target shape data, the elongation rate obtained from the element 46 corresponding to the quarter part a of the rolling roll 52 is often set to 0 so as to promote cooling of the quarter part a of the rolling roll 52. As described above, in foil rolling, the final product is obtained by repeating rolling (baths) multiple times. The plan of how many buses to use and what thickness or surface shape to obtain the final product is called an operation policy. This operation policy determines the target shape of elongation and tension in intermediate passes along with the target thickness in order to finish the final product into a flat shape with uniform elongation and tension.

In actual operation, the distribution of elongation and tension in buses en route as described above differs. This is because, as mentioned above, operating conditions such as thermal deformation (thermal crown) in the rolling rolls differ for each bus. Therefore, the above-mentioned operational policy is one that determines the target shape of elongation and tension for each bus by taking into account the expected operating conditions to some extent among such actual operating conditions.

However, the target shape of elongation and tension based on the operation policy as described above is often not the same as the actual target shape of elongation and tension by the shape control section 3, that is, the target shape data. For example, in a certain bus roll mill, a certain material is
An example of this is when rolling with a target shape in the operation policy as indicated by the broken line in Figure 2, and obtaining good results by setting the actual target shape data in the shape control section 3 as indicated by the solid line. It is. Further, FIG. 23 shows a continuous annealing facility 61170 in a steel mill or the like, which is another example of the above process. Such continuous annealing equipment M
At 170, a strip-shaped coil material 74 runs between rolls 73 disposed in a heating furnace 71, is annealed at a predetermined temperature to adjust its quality, and is transported in the direction of arrow K. If the coil material 74 in the heating furnace 71 does not have a flat shape, it will meander or wrinkle-like constrictions will occur in the elongated portion. Therefore, the continuous annealing equipment [70] detects the shape of the running coil material 74, for example, the elongation distribution in the width direction, and adjusts the speed of the coil material 74 based on the detected value. We try to adjust running conditions such as tension. Also in the continuous annealing setup @10, the coil material 7
The detected elongation distribution (surface shape) in the width direction of No. 4 is shown, for example, in FIG. 24(a) and FIG. 24(0)). In these cases, the maximum elongation rate of the coil material 74 having the surface shape shown in FIG. 24(a) is larger than that shown in FIG. 24(b), but overall there is a smooth change in the width direction. , the aforesaid aperture is less likely to occur; on the other hand, the material shown in FIG. In addition, the coil material 74 having the surface shape shown in FIG. 25(a) is in a state where the center portion in the width direction is elongated, and the coil material 74 shown in FIG. 25(b) is in a state where the end portions are elongated. It is a state. At this time, the tension must be adjusted because the coil material 74 in the so-called medium elongated state, which is elongated at the center, is generally more prone to constriction than the coil material 74 in the end elongated state. [Problems to be Solved by the Invention] As mentioned above, in processes such as aluminum foil rolling and continuous annealing, not only the size of the actual shape data related to the elongation rate from individual elements, but also the pattern of the entire surface shape, i.e. Determining the shape state and its degree has great significance in controlling the process. However, according to the conventional shape detection method, judgment of the pattern of the entire surface shape relies on the operator's experience and feeling, which requires skill and lacks appropriateness.

Therefore, an object of the present invention is to be able to appropriately judge the pattern of the entire surface shape in the width direction of a running belt-shaped or plate-shaped metal material, and to improve the process of handling the metal material or the operator thereof. The object of the present invention is to provide a shape detection device for a band-like metal material or a plate-like metal material that can provide objective judgment information. [Means for Solving the Problems] In order to achieve the above object, the main means adopted by the present invention is to detect the shape in the width direction of a running belt-shaped or plate-shaped metal material. A shape detection device that includes a sensor that detects actual shape data of the metal material while it is running, and calculates an actual shape classification item indicating the shape state of the metal material while it is running and its degree from the actual shape data. 1 is a shape detection device for a band-shaped metal material or a plate-shaped metal material, comprising a calculation means.

Further, as a means for applying this to the field of rolling metal strips, there is a rolling shape detection device for metal materials that detects the shape in the width direction of a strip metal material stretched by a roll rolling machine. A rolled shape of a metal material, comprising: a sensor that detects actual shape data during running after rolling; and a calculation means that calculates the shape state and degree of the rolled metal material from the actual shape data. It is a detection device. Furthermore, as a means understood at a more specific level, there is a metal material rolled shape detection device that detects the surface shape in the width direction of a strip-shaped metal material stretched by a roll rolling machine, which detects the surface shape of a strip-shaped metal material stretched by a roll rolling machine, A point comprising a sensor for detecting actual shape data of elongation/tension during running of the metal material, and a calculation means for calculating the state and degree of tension/tension of the metal material after rolling from the actual shape data. This is a metal material rolling shape detection device according to the present invention.

Here, the actual shape data may be an output value from a sensor, or may be a concept representing the shape of elongation/tension as shown in the examples below.

[Function] According to the present invention, the sensor detects actual shape data in the width direction of a strip-shaped or plate-shaped metal material while the vehicle is running. Then, a calculation means calculates an actual shape state classification item indicating the shape state of the metal material during travel and its degree from the actual shape data. Thereby, for example, for the process handling the metal material or the operator operating the process,
It is possible to provide objective information regarding the shape and extent of the metal material. (Example) Next, an example embodying the present invention will be described with reference to the attached drawings to provide an understanding of the present invention. Here, FIG. A schematic diagram showing the system layout of the aluminum foil rolling target shape adjusting device equipped with a foil rolling shape detection device, Figure 2 is a configuration diagram showing the processing flow of the aluminum foil rolling target shape adjusting device, and Figure 3 (
al is an explanatory diagram showing the main parts of the actual shape data expressed by the elongation rate distribution in the foil width direction, FIG. 3(b) is an explanatory diagram showing the actual shape classification items of pattern-classified aluminum foil, and FIG. (a) is a flowchart showing the processing procedure for determining the change tendency of actual shape data; FIG. 5 (a) and (b) are 2
Figure 6 is a graph showing the correlation between the number of levels of the two real shape classification items.
A three-dimensional graph showing a dimensional pattern, Fig. 7 is a schematic diagram conceptually showing a neural network, Fig. 8 is an explanatory diagram showing an example of the relationship between shape change targets and corresponding action candidates for real shape classification items, Figure 9 is a graph showing the relationship between the importance of the shape change target and the confidence when the actual shape classification item is edge-bound, and Figure 10 is the rule used for inference in the axigon candidate inference unit and the rule used for inference to determine the target. An explanatory diagram showing an example of changing the shape, Fig. 11 is an explanatory diagram showing the processing procedure of a routine that checks the validity of the action to be applied using a check tree, and Fig. 12 (a) shows an example of changing the target shape. An explanatory diagram showing the target shape adjustment parameters used for changing the target shape. FIG. A state diagram showing a situation where the central part is a forward pattern, Figure (4) is a state diagram showing a situation where the central part is a reverse pattern, and Figure 13 is a schematic diagram showing an example of inference execution for changing the target shape. An explanatory diagram, FIG. 14 is a flow sheet showing the process flow of target shape adjustment, FIG. 15 is a display diagram showing an input menu displayed on the screen of the rolling mill side terminal, and FIG. 16 is a display diagram showing the input menu displayed on the screen. Fig. 17 is a display diagram showing an example of the target shape obtained, and Fig. 17 is a flow sheet showing a method for correcting the actual shape obtained asymmetrically.
FIG. 8 is a schematic explanatory diagram showing a situation in which the asymmetric actual shape is corrected.

In the following description, the same reference numerals will be used for the elements common to the roll rolling mill 2 shown in FIGS. 19 to 21, and the description thereof will be omitted.

Further, the following embodiments are merely examples embodying the present invention, and are not intended to limit the technical scope of the present invention. Aluminum foil rolling shape detection device according to this embodiment 1. The aluminum ξ foil rolling target shape adjusting device 1 is applied to process online control as an expert system that systematizes operator control know-how. Prior to a detailed explanation of this system, the system configuration of the aluminum foil rolling target shape adjusting device 1 will be outlined using FIG. 2. As shown in the figure, the aluminum foil rolling target shape adjustment device 1 includes a rolling data collection section 7, a rolling situation analysis section 8, a control target generation section 9, an action candidate inference section 11, a target shape generation section 12, and Mainly tI from action effect evaluation department IO
Rolling situation analysis knowledge base D1 that stores operational knowledge and control target setting knowledge base D! and action inference knowledge (including knowledge for maintaining consistency of rules and validity of actions), and working memories Mr, Mt, Mi, M4, and Ms for temporarily storing various data. An overview of the processing content in each part above is explained below. In the aluminum foil rolling target shape adjusting device 1, first, inference processing is started by key human power from the terminal device 6 on the aluminum foil rolling mill 8!2 side, and the operating condition data from the aluminum foil rolling mill 2 is transferred to the shape controller It is input via 3. ■Rolling Data Collection Unit The rolling data collection unit 7 receives operating condition data including actual shape data from the shape control unit 3 and writes it into the working memory M.

■Rolling condition analysis section The rolling condition analysis section 8 analyzes the actual shape data and determines the rolling condition of the aluminum foil 53. That is, it is determined how well the actual shape data fits each of the actual shape patterns that have been classified in advance into several types of patterns and stored in the rolling situation analysis knowledge field D1. At the same time, the current target shape data is analyzed.

■Control target generation unit The control target generation unit 9 changes the actual shape of the aluminum F/I 53 in what direction based on the analysis results of the actual shape data by the rolling situation analysis unit 8 and the input from the terminal 6 by the operator 5. Set control targets for

■Action candidate inference unit■1 (1) Rule inference The action candidate inference unit 1l is an IF-THEN type in which the control objective and operating conditions, etc. are the condition part, and the action etc. to realize the control objective are the conclusion part. The action determined to be appropriate is written into the working memory M, according to the rule tlI3fA that applies the rule stored in the action inference knowledge base D3. During this writing, the following processing is executed.

(2) Eliminating contradictions and redundancies When contradictory action candidates are listed, the action of the control objective that is considered more important is applied.

■-(3) Learning invalid actions In the above rules, if there are multiple axis candidates for a certain control target, give priority to the action candidates and select only the action with the highest priority. Apply. Actions that are executed to achieve a certain control goal and have no effect will not be applied repeatedly even if the same control goal is set next time. (2) Target shape generation unit The target shape generation unit 12 generates new target shape data based on the applied axis and outputs it to the shape control unit 3. Based on this target shape data, the shape control unit 3
controls the aluminum foil rolling mill 2.

■Action Effect Evaluation Unit The action effect evaluation unit IO evaluates whether the control of the aluminum foil rolling mill 2 based on the applied action was effective or not based on the results of data analysis and the arrangements made with the operator 5. At this time, the action j judged to be invalid is stored in the working memory M4, and is referred to during the next action candidate inference in the action candidate inference section 1l.

This example will be described in detail below.

As shown in FIG. 1 and FIG. 2, the aluminum foil rolling target shape adjusting device 1 includes a shape control section 3 that controls the injection amount or temperature of coolant 5 days so as to adjust the actual shape of aluminum V353. In addition to outputting target shape data that serves as a guideline for the control, operating condition data is input from the shape control section 3.

Another possible method for adjusting the actual shape of the aluminum foil 53 is to control the push-up force of the push-up roll 60 that urges the lower roll 52 upward toward the upper roll 52. In this embodiment, only the coolant control for 5 days will be described below.

■ Collection of operating condition data In the Al: i foil rolling target shape adjustment device 1, the inspection roll 4 detects actual shape data indicating the elongated portion 54 and tensioned portion 55 (Fig. 20) of the aluminum foil 53 at the time of rolling. element with a sensor 4. It is provided as an assembly on the downstream side of the rolling roll 52 in the conveyance direction (arrow K), and outputs the actual shape data to the rolling data collecting section 7 (FIG. 2) via the shape controlling section 3. The rolling data collection section 7 writes the operating condition data (Table-1) transferred from the shape control section 3 at predetermined time intervals into the work memory M. ■Analysis elements of actual shape data 4. Based on the actual shape data detected by the (sensor), the elongation and tension state of aluminum FA53 during rolling (
As shown in Fig. 3(b), the rolling condition analysis knowledge for calculating the respective real shape classification items) and their degrees is calculated using real shape classifications such as "end tension" to "tap elongation J". items, and a specific program for each item for specifying the actual shape classification item detected from the element 4 and corresponding to the actual shape data indicating the actual shape. A method for specifying actual shape classification items will be described.The actual shape data detected as a tension distribution from element 4 is obtained in the form of an elongation distribution in the foil width direction, as shown in FIG. 3(a).

The actual shape data shown in the figure is from the outside to the end. It consists of a quarter part, a central part A, and a central part B, and the entire central part is guarded by the central part A and the central part B. In this case, the tension portion 55 is located in the center portion B, and the extension portions 54 are located in the quarter portions on both sides.

The above real shape data is classified into any of various real shape classification items known from experience.

Once it is determined which real shape classification item the object falls under, an appropriate axigon known from experience can be selected to bring the target shape closer to the appropriate one. That is, the actual shape classification items stored in the rolling situation analysis knowledge base D1 are mainly classified into five types as shown below, as shown in FIG. 3(b).

(1) "Edge tension"...When the elongation rate at the edge shows a lower value toward the edge, it is considered to be edge tension. ■Whether the value at the edge is the minimum value of the whole.

■Judged by the extent of the difference in elongation rate between the end and quarter parts. (2) "Edge elongation j...Contrary to the case of edge tension, this refers to a case where the value at the edge is significantly larger than other parts.

In many cases, it is preferable to have a real shape where the edges extend to some extent, but if the edges extend too much, it is considered a problematic shape.

(3) "Quarter elongation"...Judged based on how large the elongation rate value of the most elongated part near the part corresponding to the set zero point in the target shape is compared to that of the end. . As mentioned above, the actual shape in the quarter portion is the easiest to stretch, and this type of shape appears in most of the actual shapes.

(4) "Medium tension": The tension condition in the center (low elongation rate) is compared with that at the ends. (5) "Medium elongation"...The difference between the elongation rate value of the most elongated part in the center and the part that elongated the most overall (in most cases, the edge or quarter part) is small. , or if it is negative, it is determined that there is medium elongation.

There are two types of mid-length elongation: ■ General mid-length elongation, where the central part is elongated, and ■ Tummy elongation, where the middle part is elongated and the center part is stretched.

Other unique real shape classification items include "non-target" below.
, there is "zero point inappropriateness".

``Asymmetrical j...Usually, the target shape is symmetrical in the foil width direction, and the actual shape is generally symmetrical, but a shape in which this symmetry is broken is called an asymmetrical shape. (2) The difference in elongation rate between the maximum value and the elongation rate between the minimum value is large between the left and right ends.

■One end is identified as end tension and the other end as end extension. It is considered to be asymmetric if either of these conditions are satisfied. Of course, there are times when either of these can be intimidating. "Zero point inappropriate"...
- This refers to a case where the part of the zero point set in the target shape and the part showing the maximum elongation rate in the actual shape do not match. Normally, heat tends to accumulate in the quarter part a of the rolling roll 52, and the quarter part of the actual shape corresponding to the quarter part a is most easily expanded. Therefore, when setting the target shape, the zero point is set at the most elongated portion of the quarter portion of the actual shape. If these parts are out of alignment, it is necessary to adjust them so that they are defeated.

Based on the detected actual shape data, it is determined to which actual shape classification item the current shape state corresponds according to the method shown in the section "Identification method" in FIG. 3(b). As described above, this method is stored as a program in the rolling situation analysis knowledge base D1.

As described above, one or more actual shape classification items that are the cause of the actual shape data input from the work memory Ml are calculated in the rolling situation analysis section 8 by the specific program.

Normally, it is not always the case that only one real shape classification item for which a certain real shape is determined to be in that state is subjected to iHtR. Actual shape data is obtained as a result of a complex intertwining of operating conditions. ! ! In many cases, it is determined that the object is in the state of the real shape classification item of number. In that case, there are real shape classification items that have a strong causal relationship with the real shape data and classification items that have a weak causal relationship. The strength of such a causal relationship, that is, the degree of the shape state, is called certainty.

The rolling situation analysis unit 8 narrows down the actual shape data into one or more actual shape classification items with a certain degree of certainty derived by an appropriate function, and stores the actual shape classification items and their degrees of certainty in the working memory M2. Make me remember. For example, four elements 4 from the end where the Al ξ foil 53 is placed.

The ratio β2/α2 of the elongation rate difference α2 between the part 0 end with the highest elongation rate and the difference β2 between the maximum and minimum elongation rates in the entire actual shape data within the range of the actual shape data input from
exceeds a predetermined set value, the actual shape at this time is
It is interpreted that the real shape classification item "edge elongation" is included, and a degree of certainty from O to I is added according to the value of the ratio. The same applies to other real shape classification items.

In this case, based on the actual shape data within a predetermined past time from the work memory M, statistical characteristic information of the roll rolling mill 2, such as average, change tendency, variance, etc. correlation. Calculates 3D pattern recognition, etc., and based on the statistical characteristic information,
That is, using the statistical characteristic information as a variable for the confidence level,
The certainty factor may be calculated for each of the actual shape classification items.

For example, the actual shape at a certain point in time may be extremely different from the actual shape at points before and after that point for some reason. Specifically, the cause is an abnormality in the shape of the raw material sheet before rolling, and when the actual shape of the "edge tension" continues, the poor "edge elongation" condition is detected for a moment, and then the original "edge tension" is restored. ” continues. Therefore, by applying the average value of the statistical characteristic information of the actual shape data at several points in the past up to the above-mentioned certain point, it is possible to judge the rolling state of the trend without being influenced by the above-mentioned noise elements. .

Next, the case where the change trend of actual shape data within a predetermined past time is adopted as the statistical characteristic information will be described in detail below. This tendency is calculated, for example, according to the processing procedure of flowchart 1 shown in FIG. 4(a). During the rolling operation of the aluminum foil 53, roll rolling 4! ! The actual shape data of the aluminum foil 53 obtained from the inspection roll 4 on the J2 side is collected at predetermined time intervals by the rolling data collection unit 7 (S40).

Next, the actual shape data is compared with the actual shape classification item in the rolling condition analysis section 8, and is specified as a certain actual shape classification item, and the degree thereof is expressed by a level number represented by a natural number O to 5. That is, the rolling state of the aluminum foil 53 is determined (S4.1).

For example, from the end where the aluminum foil 53 is pressed,
Within the range of the actual shape data input from two elements 46, the elongation rate difference α2 between the part with the highest elongation rate and the end, and the difference β between the maximum and minimum elongation rates in the entire actual shape data
2 exceeds a predetermined setting value, it is determined that the actual shape at this time includes the actual shape classification item "edge elongation", and the The degree of "edge elongation" is expressed by a level number represented by a natural number 0 to 5.

Furthermore, in step S42, shape points H. from -5 points to +5 points are calculated for the actual shape data at time T. is determined and stored in a storage unit (not shown) that stores the number H1 of shape points within a predetermined time.

This embodies an empirical handling method when the operator 5 specifies real shape data into an arbitrary real shape classification item,
For example, in order to make it easier for the operator 5 to understand when displayed on the terminal 6, the certainty of the real shape classification item to which a certain real shape data fits and the real shape whose elongation/tension state contradicts the real shape classification item. The confidence level of the classification item is converted into both coordinates consisting of positive and negative natural numbers centered on 0.

For example, if the actual shape classification item is "edge elongation" and the degree is level 5, the shape score is +5 points, and if it is level 1, it is +1 point. Also, if the level is 5 for "edge tension", it will be given -5 points, and if it is level 1, it will be given -1 point. "
If you do not score 1 for "edge elongation" and "edge tension", 0 points will be given.

Then, if it is necessary to change or adjust the target shape by input from the terminal device 6 on the roll rolling mill 2 side in response to a request from the operator 5 or by input from the rolling situation analysis section 8, (
S43), and in step S44, the change tendency of the actual shape within a predetermined time up to the present is calculated.

For example, the shape change tendency at time T is determined by the past i shape point numbers Ht-i. 1. ..., calculated from HL. Here, the past 10 shape points Ht-1+...5 H
, an example calculated from . First, the shape point number H. ．． 、・
..., the shape point difference Hd shown in the following equation is obtained from the maximum value and minimum value of Ht.

H4 = max(Ht-w.'-, Ht)+*
in (Hz-*, ・”.Hc) At that time, if the shape point difference Hd is 2 or less, it is determined that the actual shape of the aluminum foil 53 is in a stable state and no tendency to shape change is recognized. Ru.

If H4 is 3 or more, it is first determined whether the actual shape is in a periodic state of change. For example, the number of shape points Ht-q,
..., H1 is the number of times the number of shape points changes in the direction of increasing during H1. Assuming that the number of times of closing and changing in the decreasing direction is H1, as shown in the following equation, lH. -H. ．． l≦3, and 3≦H,≦4, that is, H. When the absolute value of the difference between and H- is 3 or less and the shape point difference Hd is 3 or more and 4 or less, it is determined that the actual shape tends to change periodically.

If Hd is 2 or more and does not meet the above formula, it is assumed that a shape change tendency is recognized, and it is determined what kind of trend there is.For example, the current shape score H
, and the past 10th shape score H, are compared.

In other words, as shown in Table 2, when H shows a larger value than Ht-9, it indicates an elongation tendency in which the edges are stretching, and conversely, when it shows a small value, it indicates that the edges are stretching. It is determined that there is a certain tension tendency. Furthermore, if Ht and H&-9 are equal, it is determined that the actual shape is stable, and the step of correcting the number of levels of the actual shape classification item (S45), which will be described later, is performed.
will be processed by bypassing.

Therefore, for example, if the shape change tendency at time T is "edge elongation tendency" and the actual shape classification item at that time is identified as "edge elongation J" and the number of levels is 3, then As shown in (middle), a correction axis is performed to increase the number of levels by 2 for the actual shape classification item at that time (345). Considering both the shape judgment and shape change tendency, Level 3 in the above example is inappropriate, and realistically the degree of "edge elongation" is approximately level 5 (edge elongation progresses rapidly). This is because it is considered to be comparable to condition B).

Therefore, in step S47 in FIG. 4(a), the target shape data is adjusted to obtain the desired real shape based on the latest real shape classification item specified as described above and the number of levels after correction. The image is modified and outputted to the shape control section 3 (348).

On the other hand, if it is determined in step S44 that the actual shape tends to change periodically, the control gain for changing and adjusting the target shape data is reduced by 30% (
S46). This suppresses the tendency of periodic changes in the actual shape.

On the other hand, when dispersion is applied as the statistical characteristic information, the rolling state can be determined from the degree of dispersion of the actual shape data regarding the shape of the edge of the aluminum hole 53 due to temporal changes, for example. That is, when the degree of dispersion is large, it indicates that the rolling condition is unstable. Therefore, in such a case, the shape control section 3 executes the control actions shown in the following (i) and (ii) to stabilize the rolling state.

At this time, (i) the control gain of the coolant t is changed and set to a lower value.

(ii) Since it is possible that the rolling roll 52 is not sufficiently heated, the coolant N is decreased overall or the elongation rate of the target shape is increased overall.

Furthermore, as an example where the characteristic information is a correlation, the correlation between the level of quarter elongation and the level of tension is shown in Figure 5 (a).
Shown below. At this time, it can be said that the relationship between the two is a positive correlation, indicating that quarter elongation and edge tension are likely to occur simultaneously.

In such a case, it is empirical knowledge that a shape adjustment method such as reducing the amount of coolant at the end in order to eliminate the end tension is not effective. On the other hand,
If the relationship between the two is uncorrelated, as shown in Figure 5 ω), we have acquired the knowledge that the shape adjustment method applied in the case of positive correlation is effective, so the shape adjustment method is effective. The adjustment method adjusts the actual shape. Furthermore, as the statistical characteristic information, 3 related to the actual shape data
It can also be by recognition of dimensional patterns.

The three-dimensional pattern P is shown in Figure 6. In the figure,
An arrow M indicated by a two-dot chain line indicates the element 4. for which the elongation rate at each time t0 to t6 has detected the maximum value. It shows the temporal position transition of . As shown in the figure, element 4 with the maximum elongation rate. is several elements in the width direction of the foil 4. It meanders within the width of. If the bear is in this condition, not only the part that is currently the most stretched, but also the several elements 4. The coolant 58 must be injected equally intensively onto the corresponding rolling rolls 52 within the width of .

This applies coolant 5 only to the area that is currently experiencing maximum growth.
This is because even if 8 is injected, the elongated area only moves to the adjacent area. Statistical characteristic information represented by such a three-dimensional pattern P, such as "The stretched portion of the actual shape meanders depending on the time," can of course be determined by the numerical calculation algorithm described above.
Pattern L'Q gfl of actual shape data of aluminum foil 53
A recognition method using a neural network that performs k is effective.

As shown in FIG. 7, in the neural network 20, a plurality of neurons 5 that calculate and output input data through dark value processing are conceptually arranged as an input layer, an intermediate layer 5, and an output layer, and there is a gap between each layer. They are connected via a connecting part 16. Then, the neural network 20
The pattern data of the actual shape data of the aluminum foil 53 is used as input data, the actual shape classification items and their degrees are used as output data, and the correspondence between the two is determined by changing the connection weight of the connection section 16. . Therefore, when new real shape data is input to the trained neural network 20, the real shape data is specified in one of the real shape classification items along with its degree. Such a neural network 20 may be applied in the rolling situation analysis section 8.

Here, Al ξ! As a calculation method for determining the actual shape state of f353, examples of numerical calculations based on specific methods determined for each actual shape classification item have been mainly shown, but the judgment by the neural network 20 or the knowledge of such judgment may be used as a calculation method. It goes without saying that a similar calculation effect can be obtained by making a judgment based on the rule hess (not shown).

The actual shape data input from the work memo 'JM1 to the rolling situation analysis section 8 and subjected to calculation may be the value of one type of data at one point in time within the predetermined time, or the value of several types of data at one point. , or the value of one type of data at several points in time, or the value of several types of data at several points in time, and the data necessary for the calculation may be used as appropriate.

In this manner, the rolling situation analysis unit 8 determines the actual shape classification items and their reliability for the current actual shape data of the aluminum foil 53, and writes them into the work memo υM2.

■The control target data (shape change target (FIG. 8) and its importance), which is the key to creating a control target and appropriately setting or changing the target shape, is generated by the operator 5 in the control target generation unit 9. It is either manually generated from the terminal device 6 on the roll rolling mill 2 side, or automatically generated based on rolling status data such as actual shape classification items and their reliability in the work memory M2.

These automatic life warnings should either reflect the operational policy (for a given bus, roll the edges with a large extension), or if there is a conflict between what was input by operator 5 and what was automatically generated. A rule such as "Give priority to the operator's input information if the For example, if the detected actual shape data includes ``edge elongation'' as in the example above, and the confidence level at that time is 0.8, five shapes are required to eliminate the ``edge elongation.'' ``I want to stretch the edges'' is selected from among the change targets, and a degree of importance corresponding to the confidence level (O, 8) is assigned to the selected shape change target.

Then, the shape change target and its importance are stored in the working memory M3. The situation in which the importance of the shape change target is calculated in the control target generation guide unit 9 from the certainty of the actual shape classification item specified as described above will be described in detail below.

The degree of importance is a measure of whether or not it is necessary to change the target shape data, and is shown in the graph (Fig. 9) showing the relationship between the actual shape data and the confidence level of the actual shape classification item indicating the degree of edge tension, for example. shown.

In the figure, an example of "edge tension" among the actual shape classification items is shown.

An importance calculation function (f(x)) that gives the degree (importance) of the necessity of changing the target shape is defined for each of the actual shape classification items such as the five-end elongation. For example, the importance calculation leap number f,() for edge tension J is defined as follows.In other words, the edge tension degree (confidence) is compared with the first threshold L, and as shown in FIG. , if the first threshold L is exceeded,
The actual shape classification item is selected for target shape modification,
The importance level corresponding to the confidence level shown in the figure is calculated. On the other hand, if the confidence level is less than or equal to the first threshold L1, O is given to the importance level, and the actual shape classification item is not used when changing the target shape. For each of the above real shape classification items,
The first threshold value L1 is set individually, and each confidence level and the first threshold value L are compared and calculated, and it is determined for each item whether or not the target shape should be changed.

Whether or not there is a need to change the target shape is determined for each actual shape classification item as described above, and is also determined based on whether the average of the importance of each item exceeds the darkness value. In some cases.

Next, a method for determining whether or not it is necessary to change the target shape from the actual shape classification items selected for changing the target shape based on the synthesized importance levels or their averages will be described in detail.

The real shape classification items are S,,S,...S. Then, the above-mentioned importance calculation leap number f for each item defined for them. +() is combined to calculate the composite importance level g(
) is defined as follows. g (fil (X
+ ), ・=, f* t (x+ )) The function g(
) is gmi(Σfsi (xi))/i, or gmiΣfs+(X+) However, 0≦rst(x.)≦1 fl▲ (x1) is strongly monotonically increasing with respect to Xi,
Expressed in the form of a total average or sum.

Here, for f (Ll) (L1), strongly monotonically increasing means that when L+ <L,, cv, f (L.) < f
(Lx). In this way, the degree of importance indicating the degree of necessity for starting the inference process is calculated from the degree of importance of each item in the action candidate inference section 11, and the combined importance is set to a predetermined second threshold Li.
(not shown), inference processing starts,
Target shape data is changed appropriately.

To give a specific example below, the importance for "edge tension" is 0.4 the importance for "quarter elongation" is 0.6 the importance for other ("edge elongation", r-medium elongation", "middle tension") When is O, the importance of the sum is 0. 4 + 0. 6 + O = 1. It becomes 0. If the second threshold L3 at this time is 0.9, the successive importance is greater, and therefore the inference process is started. As a method for determining the degree of importance serving as the trigger, the above-mentioned summation average method may be adopted. In this embodiment, as mentioned above, when the confidence level for each item exceeds the darkness value given to each item, for example,
The degree of L! shown in FIG. 9 is the threshold L! Inference processing can be started even when the value is exceeded.

Furthermore, when the combined weight exceeds a second threshold (!L3), a start signal may be output to an alarm device (not shown) at the same time to drive the alarm device. Inference processing will be explained.

■Application of action■10) Rule inference Rolling process including operating condition data including current target shape data and current actual shape data, extracted actual shape classification items and their confidence levels processed as described above. situation data,
The control target data including the shape change target and its importance are transferred from the working memories M, , M2, and M3 to the action candidate inference unit 11, respectively. The action candidate inference unit 11 collates each transferred data with the condition part of the rule stored in the action inference knowledge database D3, and as a result of the collation, determines a rule that satisfies that all the condition parts are true. Then, select the target shape change data (Fig. 8, hereinafter referred to as axis) in the conclusion part of the rule. Operating condition data as described in E. Rolling status data. i!
As already mentioned, the inference process for drawing a conclusion (target shape to be adopted) corresponding to conditions such as target data must rely on the knowledge (know-how) of experienced people. In the present invention, such inference processing is automated. Rules for such automatic inference are accumulated and stored in the action inference knowledge Rh and D. Such rules are
If [conditional part], then [conclusion part]'', it is expressed in the form of a logical product as shown below.

If [Sub I? [vehicle target data] and [operating condition data, rolling status data], then [designation of target shape adjustment parameters and their degree of change (action and degree)] Here, the target shape adjustment parameters are as shown in Table 4. As shown, it is an element that determines the target shape data (target elongation rate distribution in that pass). Not all of the parameters shown in Table 4 are listed as the target shape adjustment parameters that appear in the conclusion section of each rule.

In many cases, only some target shape adjustment parameters necessary to satisfy the condition part are described together with the degree of change thereof.

For example, as shown in FIG.
If there is no zero point under the part with the largest elongation near the quarter part, use the following action: ``Move the zero point under the part with the largest elongation near the quarter part.'' A rule that specifies is stored in the action inference knowledge base D. ■-(2) Eliminating contradictions and redundancies ~/Methods As shown in rule example 4 shown in Table 3, there are two rules. Additional conditions may be added.

For example, in the case of an actual shape, if edge tension and quake/overnight elongation occur at the same time, Rule Example 2 and Rule Example 3 may be selected.These are shown in Table 3. Therefore, the 4-Axis Candidate Associate Theory Part 1l was unable to resolve these contradictions,
An error occurs. Therefore, this problem can be solved by, for example, adding an additional condition to the condition part of rule example 2 and setting it as rule @4. That is, in rule example 4, the importance of wanting to stretch the edges and the importance of wanting to stretch the quarter are both greater than the lth threshold, but the importance of wanting to stretch the quarter is 0. If it is less than 4, the target value of the end level (elongation rate at the end in the width direction) is increased. As a method for resolving such contradictions or redundancies, it is also possible to give priority to the shape change target with the higher degree of importance.

On the other hand, there are cases where two or more types of shape change targets are simultaneously selected for certain actual shape data, and the content of the action corresponding to each shape change target is the same.

For example, the actual shape classification items (Fig. 3 (b)) of the current actual shape data are simultaneously identified as "edge tension" and "medium elongation", and the degree is calculated as an action derived from each actual shape classification item. Although there is a difference in the content, this is the case when ``raising the level of the edges'' (Figure 8) are selected at the same time. As a rule applied in such a case, a rule that sets the degree of action according to the fIα confidence of the specified real shape classification Jfl is based on the action inference knowledge Hase D,
is stored in.

Therefore, when the same axions with different degrees are selected at the same time as described above, instead of executing these actions at the same time, only the one with a large degree of axillin is executed 1'T. This avoids redundancy in the execution of operations. Here, conversely, only actions with a small degree may be executed, or actions commensurate with the average value of the degree of each acillin may be selected or generated. ■-(3) Learning invalid axis 3 Furthermore, as shown in Fig. 8, for the shape change target of j,
Number of priorities attached? ! 1! Possible neck actions are available. Then, when a certain shape change target is selected, the highest priority one is executed. The priority is not fixed, but changes from one priority to another for each inference.
, get hit. For example, when inference is executed in the action candidate HI logic section l1, which action L, should be adopted for which shape change target? : It is stored in the working memory M5, and the axidin effect evaluation unit 1 is used at the next fl R6.
0, it is determined whether the previous shape change goal has been achieved (evaluation of effectiveness) by comparing the previous and current importance levels.

As a result, if the current target shape data that has been changed based on the previous shape change target and its importance is determined to be valid by the action effect evaluation unit IO, that is, the importance is lower than the previous value. If so, assuming that the adopted Akungon is valid, Axian inference knowledge Hece D
The priority stored in 3 is moved up. Conversely, if a is determined to be invalid, the previously applied axis a that was not valid and the rule that inferred the course of that action are stored in the working memory M4.

For example, the shape change target shown in FIG. 8 is based on the rolling status data from the rolling status analysis unit 8 or the input data from the operator 5, and the previous time 'I want to lengthen the edges' has an importance level of 0.
．． 6, "Raise the edge level (priority l)", which has the highest priority among the accompanying accitanes, is selected, and the edge level ( The target shape data with increased elongation rate are output to the shape control section 3, and the target shape data applied at the same time. The importance (0.6) of the shape change, the axigon, and its priority (1) are stored in the action inference knowledge base D. Then, when determining the current shape change goal, if the shape change goal "I want to lengthen the edges" is selected with the previous importance of 0.6 or higher, the end tension state of the actual shape in question will be In many cases, it has not been improved, which means that the last action applied was invalid.On the other hand, this time, “I want to extend the edges” has an importance level of 0. If it is selected with a value less than 6, the previous action was invalid. be judged.

Therefore, the invalidated action and the rule that inferred the action are written into the working memory M4. Even if the same shape change target is selected in the next inference and the invalid axigon is selected, the invalid axigon is not applied, and the axigon with the next highest priority that is judged to be appropriate is selected. This is applied to change the current target shape data appropriately. As a result, if the next action applied to achieve the shape change goal is determined to be effective, the priority of the action is raised and the priority of the invalid action is lowered. The priority changed as described above is written in the priority section in the action inference knowledge field D2.

In this way, the aluminum ξ foil rolling target shape adjusting device 1
Even if the target shape obtained by Even if the shape change target is the same, an action different from the previous action is selected. As a result, invalid rules are not repeatedly applied, and the actual shape is appropriately changed. The action candidate reasoning unit 1l checks in detail whether or not the action given as a candidate is valid according to the check tree shown in FIG. Registered in M5.

In addition, in the axis inference knowledge base D, a rule set consisting of a plurality of rules having the same shape change target in the condition part is set for each shape change target as described above, and the rule set is set for each shape change target. A main area for storage and a save area for storing rules removed from the rule set are secured. Note that the rules for which inference processing has been completed are sequentially removed from the main area to the save area. In the check tree shown in the figure, first, check whether a rule that matches the currently selected shape change target and the shape change target exists in the rule set to which the rule belongs, that is, the rule corresponding to the above rule set is in the main area. is checked in case C1. If Case CI is applicable, the process proceeds to Case C3 to check additional conditions related to operating conditions, etc. in the condition section of the rule.

If case C3 does not apply, that is, if all the condition parts including the incidental conditions do not fail, the rule is removed from the rule set in the main area to the save area. If the above-mentioned supplementary condition is established, in case C4, whether the axigon of the rule in which all the above-mentioned condition parts were satisfied has been applied in the past and its effect was not recognized.
That is, it is checked whether it is currently registered in the working memory M4. If case C4 is applicable, that rule is removed from the rule set (main area). If case C4 does not apply, the existence of mutually contradictory axis is checked in case C5. As described above, not only one shape change target is set, but a plurality of shape change targets may be selected. In this case, the axioms attached to each shape change goal often conflict with each other. Therefore, if there is an axicon that contradicts the currently checked axicon among the actions that are determined to be valid and have already been registered in the working memory M, as a result of the check, then a rule with one of the actions will be added. If the importance of the currently selected shape change target is greater, the accitane of that rule is registered in the working memory M5,
The above contradictory action that has already been registered is iR M 6M
removed to the area.

On the other hand, if the importance of the shape target with the already registered action is greater, the registered accitan is left in the working memory M, and the rule with the currently checked action is It is removed from the rule set (main area) to the save area.

If case C5 does not apply, that is, if the above-mentioned actions do not contradict each other, it is checked in case C whether the shape change targets of these actions are the same. If f is assigned to case Ch, it is checked whether there is a difference in the priority of each of the axes listed above (
In case C,), if there is a difference in priority, only the axigon with the higher priority remains in the working memory M5, and the action with the lower priority is deleted from the working memory M,. If there is no difference in priority, both actions are left together in the working memory MS.

As described above, if case C1 does not apply, it is determined that there is no rule in the rule set that matches the shape change target selected this time, and the process proceeds to check case C3. If case C8 applies, that is, all the rules in each rule set have been checked, but if it is determined that all action candidates are nonconforming by checking cases C, ~C, then the past invalid information in working memory M4 is In addition to resetting (clearing) the information, since it is not possible to select an appropriate action candidate under the current priority, the priority is reset and the rule is configured with action candidates that have been selected based on the priority. After each rule set is restored, the action check reasoning is restarted from the beginning.

On the other hand, if case C2 does not apply, then as a result of verifying all the rules in each rule set, the action candidates judged to be valid should have been selected and stored in the working memory M, so that Finish reasoning.

In this way, rules in a rule set consisting of rules that have a certain shape change goal in common are sequentially removed from the rule set (main area) after the validity of their actions is checked one by one. Stored in the evacuation area.

Then, the above rules are checked until the rule set of the main area related to the shape change target becomes empty. In other words, the state in which the rule set is empty does not correspond to case C1. If two or more shape change targets are selected,
The validity check of the above action is performed for another shape change target set in the same manner as above (C, ~Ct). In this way, the above check routine checks the inconsistency, priority, effectiveness record, etc. between the action candidates already registered in the working memory M5 and the action candidates to be newly registered, and collects the target shape data. The validity of the actions to be applied to the changes and the consistency of the rules are maintained.

■Achievement of target shape Next, the action and its degree registered in the working memory M5, ie, "the degree of raising the edge level is 0.
8” is the target shape change data.
Transferred to 2. The target shape production section 12 generates data based on the target shape change data as shown in Table 4 and FIGS. 12(a) to 12(cl).
The values of the target shape adjustment parameters shown in Table 4 are changed. For example, if the above-mentioned action is "increase the end level, the degree is 0.8", the target shape adjustment parameter a. The value of is changed and set according to the degree of the axis, and the target shape data changes.Furthermore, the shape control unit 3 controls the coolant 58 of the roll rolling mill 2 based on the input changed target shape data. Control.

■Evaluation of applied action Then, the operating condition data including the newly obtained actual shape data is input to the rolling data collection section 7, and the same process as the previous time is repeated. That is, the shape change target and its importance for the current actual shape are calculated in the control target generation unit 9, and compared with the previous one in the action candidate inference unit it. A concrete example of repeating the above reasoning is shown in FIG. For example, if the shape change target E1 calculated from the actual shape data included in certain operating condition data is "I want to increase the quota" and its importance level is 0.8,
The second quasi-theory E2 was executed, and the axis candidates at that time were (A1) widening the width of the zero point and (A2) moving the zero point outward. Here, action A with high priority
1 was applied, and the target shape data before and after being changed thereby were as shown in the inference result E3.

However, when evaluating the effect of axidin A1, E
The importance level of 1 was not lower than 0.8, and its effect was not recognized. Therefore, the rule from which the action AI was derived is stored in the working memory M4 as being invalid.

Next, apply action A2 with the next highest priority and perform 2
The second inference E4 is executed. In this case, the rule including the shape change target El is continuously applied to continue the rolling process, and if the operating conditions are unchanged from the first inference, the actions A1 and A2 are obtained as candidates. Therefore, as a result of verifying the ff history of the action effect using this second semi-thesis E4, we found that the above action At
is stored in working memory M4 as being invalid last time, so it is not applied this time (Case C4 in Figure 11)
, action A2 with the next highest priority is applied to change the target shape data.

As a result, if it is determined that the quota growth has been improved, the priority of Axin A2 is upgraded over that of Axin AI and stored in the action inference knowledge base D3.

In this way, when certain target shape data is given to the real shape of Al ξFI553, the change in the real shape (shape change target) and the corresponding change in the target shape data correspond to the inference made by the action candidate inference unit l1. The target shape data changed at the same time, the actual shape data obtained as a result, the operating condition data used to set the target shape data, the rolling status data, the control target data, etc. As Axin3 inference knowledge base D,
It is stored in . Then, the action candidate 11i inference unit 11 determines the ideal actual shape (operating policy) at that time.
Appropriate target shape data is calculated based on the respective experience values, and the target shape data is automatically generated via the target shape generation section 12 and output to the shape control section 3 so as to realize the above. ．． Al's as mentioned above. As shown in FIG. 14, the V3 rolling target shape adjusting device I is activated by keystroke from the rolling mill side terminal device 6 by the operator 5 (step 21). Next, the operator 5 inputs the shape change target information along with the degree of importance according to the manual menu (FIG. 15) displayed on the screen of the terminal 6 (step 22).

Accordingly, the aluminum foil rolling target shape adjusting device 1 analyzes the rolling data transferred from the shape control section 3 (step 23), creates an appropriate target shape by inference (step 24), and The target shape (FIG. 16) is displayed on the screen, and the corrected target shape data is output to the rolling mill 2 via the shape control section 3 (step 25). Then, it is evaluated whether the corrected target shape was effective for the actual shape that had the problem (step 26), and the system waits for input from the operator 5. At this time, the target shape adjustment device dynamically changes the shape by r1, but if it is inconsistent with what is input by the O-order 5, the respective importance levels σ
High value, input by Oberley Yu 5. Alternatively, the shape change target may be generated based on a rule that gives priority to one of the shape judgment results from the actual shape classification items.

The aluminum foil rolling target shape adjusting device 1 constantly monitors the actual shape of the aluminum foil 53, and when it is determined that it is necessary to change the target shape data, the operator 5 starts the inference, but it does not automatically It is also possible to start the process of changing the target shape data automatically. For example, in the condition part of the rule, a comparison condition between the certainty factor of the actual shape classification item and a certain threshold value α is set. A specific example of the rule is given below.

If [actual shape classification item and its confidence level] and [operating conditions], then [designation of shape change target and its degree],
Specifically, if the confidence of edge extension is α, and the path is the second bus, we want to extend the edge. The importance level is expressed as 1.0. That is, when the actual shape changes and the degree of edge extension becomes less than or equal to the threshold value α, the above rule is applied and the lm theory is started.

Furthermore, the aluminum foil rolling target shape adjustment device 1 has a function of re-storing the obtained actual shape data even if it is asymmetrical in the foil width direction. As shown in FIGS. 17 and 18, when it is determined that the actual shape data is not engraved (step 31), the
The target shape, which has been symmetrical until now, is temporarily set higher by the operator 5 (step 32). This is to temporarily deflect the jetting distribution of the coolant 58 injected onto the rolling rolls 52 in the width direction of the foil, and to make the heat distribution on the rolling rolls 52 uniform, especially at the start of operation ( This is effective during roll temperature rise) or when restarting (after roll rearrangement). The process in step 32 is repeated until the actual shape data becomes symmetrical. In this embodiment, the aluminum foil 53 is used as the control target, but the control target is not limited thereto, and may be a hollow or other metal, and its thickness is not limited. As mentioned above, the actual shape data of the aluminum foil 53 that is divided in the foil width direction and detected by the sensor that detects tension is as follows:
Aluminum foil rolling shape detection device 1. If the downstream control target generation unit 9 determines that the shape is a problem shape based on the degree to which it is characterized by the actual shape classification item, the pattern recognition Inference processing is performed to deal with the actual shape classification items and their degrees. Therefore, in Al QV3 rolling, the actual shape of the aluminum foil 53 can be constantly monitored, and even if a problem shape occurs, it can be dealt with quickly. As a result, it becomes possible to perform appropriate shape management, and aluminum Fl! It can contribute to improving the quality control and shape control accuracy of F53. In the present embodiment, the aluminum foil rolled shape detection device 1 is applied to shape control of the aluminum foil 53, but is not limited to this, and can be used to identify the actual shape classification items and their degree. An alarm device that issues an alarm in accordance with the situation. Alternatively, it can also be applied to a stopping device that stops the entire rolling system. Further, the aluminum rolled shape detection device 1 serves as a sensor for detecting actual shape data of elongation and tension at the time of rolling.
Element in which a piezoelectric element is embedded 4. However, the above element 4. It is also possible to use a plurality of air bearing elements having substantially the same appearance as the sensor, and to detect the actual shape data based on changes in the air pressure.

Up to this point, the actual shape data to be detected has been related to the shape of elongation and tension, but the actual shape data may also be related to the thickness of the aluminum foil 53 in the foil width direction.

The shape detection device described above is not limited to the field of aluminum foil rolling, but can be applied to any process that handles strip-shaped or plate-shaped metal materials, such as the continuous annealing equipment 70 described in the prior art. obtain. [Effects of the Invention] A shape detection device that detects the widthwise shape of a running belt-shaped or plate-shaped metal material, comprising a sensor that detects actual shape data of the metal material while it is running, and a sensor that detects the actual shape data of the metal material while it is running; This is a shape detection device for a band-shaped metal material or a plate-shaped metal material, characterized in that it is equipped with an actual shape classification item indicating the shape state of the metal material while it is running, and a calculation means for calculating the degree of the actual shape classification item. , the actual shape classification item indicating the shape in the width direction of the metal material and its degree, that is, the pattern of the entire surface shape can be appropriately determined.

Thereby, objective pattern information of the entire surface shape, which is important in controlling the process of handling the metal material, can be provided to the process and the operator.

[Brief explanation of drawings]

Fig. 1 is a schematic diagram showing the system arrangement of an Al ξ foil rolling target shape adjustment device equipped with an Al:i v5 rolling shape detection device according to an embodiment of the present invention, and Fig. 2 is a schematic diagram showing the system layout of an Al ξ foil rolling target shape adjustment device according to an embodiment of the present invention. A configuration diagram showing the processing flow of the device, Figure 3 (
a) is an explanatory diagram showing the main parts of the actual shape data expressed by the elongation rate distribution in the foil width direction; FIG. 3) is an explanatory diagram showing the actual shape classification items of aluminum foil classified by pattern;
Figure (a) is a flowchart showing the processing procedure for determining the change tendency of actual shape data, and Figure (b) is an explanatory diagram showing an axigon that corrects the number of levels of actual shape classification items by taking shape change trends into account. , Figures 5(a) and 5(b) are 2
Figure 6 is a graph showing the correlation between the number of levels of the two real shape classification items.
A three-dimensional graph showing a dimensional pattern, Fig. 7 is a schematic diagram conceptually showing a neural network, and Fig. 8 shows a shape change target for real shape classification items and the corresponding axis 3.
Fig. 9 is a graph showing the relationship between the importance of the shape change target and the confidence when the actual shape classification item is edge-bound, and Fig. An explanatory diagram showing the rules used for inference in the inference part and an example of changing the target shape using the rules. Figure 1l shows the processing procedure of a routine that checks the validity of the action to be applied using a check tree. Figure 12(a) is an explanatory diagram showing the target shape adjustment parameters used to change the target shape, and Figure 12(b) is a state diagram showing changes in the status of the parameter a. Figure (C) is a state diagram showing a situation where the center part of the target shape adjusted by the parameter a4 is a forward pattern, and Figure (d) is a state diagram showing a situation where the center part is a reverse pattern. Figure 13 is a schematic explanatory diagram showing an example of inference execution for changing the target shape, Figure 14 is a flow sheet showing the process flow for adjusting the target shape, and Figure 15 is displayed on the screen of the terminal on the rolling mill side. A display diagram showing an input menu, FIG. 16 is a display diagram showing an example of the target shape displayed on the screen, FIG. 17 is a flow sheet showing a method for correcting the actual shape obtained asymmetrically, and FIG. A schematic explanatory diagram showing a situation in which the asymmetric actual shape is corrected, FIG. 19 is a schematic perspective view showing a roll rolling mill which is an example of the background of the present invention, and FIG. 20 is a surface shape of the aluminum foil after rolling. Fig. 21 is an explanatory diagram showing the correlation between the cross-sectional shape of the rolling roll, the actual shape of the aluminum foil, and the target shape for controlling the actual shape, and Fig. 22 is the operational target for the aluminum foil. FIG. 23 is a graph showing the shape and the target shape set for control at the same time, FIG.
Figure 4 (aJ. (b) and Figure 25 (a). (b) are graphs showing the actual shape in the width direction of the coil material running in the continuous annealing equipment in Figure 23. [Explanation of symbols] ] l1... Aluminum foil rolling shape detection device 2... Roll rolling machine 3... Shape control section 4...
- Inspection roll 46...Element (sensor) 8...Rolling situation analysis unit (f4 calculation means) D1...Rolling situation analysis knowledge base (calculation means>53...Aluminum foil
54... Stretching part 55... Tensioning part.

Claims (1)

[Scope of Claims] 1. A shape detection device for detecting the shape in the width direction of a running belt-shaped or plate-shaped metal material, comprising a sensor for detecting actual shape data of the metal material while it is running; A shape detection device for a band-shaped metal material or a plate-shaped metal material, characterized in that it is equipped with an actual shape classification item indicating the shape state of the metal material during travel from actual shape data, and a calculation means for calculating the degree thereof. . 2. A metal material rolled shape detection device for detecting the shape in the width direction of a strip-shaped metal material stretched by a roll rolling machine, the sensor detecting actual shape data of the metal material during running after rolling; A metal material rolling shape detection device comprising a calculation means for calculating the shape state and degree of the rolled metal material from the actual shape data. 3. A metal material rolled shape detection device that detects the surface shape in the width direction of a strip-shaped metal material stretched by a roll rolling machine, which detects the actual shape data of the elongation/tension of the metal material during running after rolling. An apparatus for detecting rolled shape of a metal material, comprising: a sensor for detecting the shape; and a calculation means for calculating the state and degree of elongation/tension of the metal material after rolling from the actual shape data.