CN114749494B - Plant control device, plant control method, and storage medium - Google Patents

Abstract

The plant control device, the plant control method and the program of the invention predict the occurrence of the abnormal mechanical operation of the plant to be controlled, and properly operate the control operation end so as not to generate the abnormal mechanical operation, thereby improving the control effect and the operation efficiency. A first operation process in which the response speed to the operation is a predetermined response speed and a second operation process in which the response speed to the operation is slower than the first operation process are performed on the control target plant device. The first operation end executes the first operation process, and the second operation end executes the second operation process. A safe operation range determining unit is provided for determining a safe operation range of a first operation process of a first operation terminal from the result of the first operation terminal. In the determination by the safe operation range determination unit, when the first operation process at the first operation end is in the unsafe operation range, the instruction of the second operation process is corrected or changed, and the actual result position of the first operation process at the first operation end is moved to the actual result position where the occurrence of the mechanical work abnormality is not estimated.

Description

Factory equipment control device, factory equipment control method and storage medium

Technical Field

The present invention relates to a factory equipment control device, a factory equipment control method and a storage medium.

Background technique

In the rolling mill control as one of the plant equipment controls, fuzzy control and neuro-fuzzy control have been applied to the shape control of the ripple state of the control plate. Fuzzy control is applied to the shape control using coolant, and neuro-fuzzy control is applied to the shape control of the Sendzimir rolling mill.

In shape control using neuro-fuzzy control, as shown in Patent Document 1, a process is performed to obtain a difference between an actual shape pattern detected by a shape detector and a target shape pattern and a similarity ratio with a preset reference shape pattern. In shape control using neuro-fuzzy control, a control output amount for an operating end is obtained based on the obtained similarity ratio by a control rule expressed by an operation amount of a control operating end for a preset reference shape pattern.

Shape control has multiple control operating ends, and control is performed by the difference in characteristics of these multiple control operating ends. The shape is the undulating state of the plate in the plate width direction, and the control operating end can change the shape of a specific area in the plate width direction. For example, the AS-U roller can change the shape near the saddle position of the operation, and the shift of the intermediate roller can change the shape of the plate end. When performing shape control, according to the actual shape, each control operating end is combined to act in a way to suppress shape deviation.

When a rolling mill is performing rolling, a cooling material (hereinafter referred to as coolant) is required for lubrication between the rolled material and the rolls of the rolling mill and for cooling the heat caused by rolling. The coolant becomes the operating end of the shape control, and by adjusting the injection amount of the coolant in the plate width direction, the shape can be changed in the entire area in the plate width direction. In a 6-stage rolling mill, as shown in Patent Document 2, there is a coolant injection amount adjustment mechanism in the plate width direction, and the injection amount is changed using the actual shape, thereby implementing shape control. However, in a Sendzimir mill, during rolling, the rolls of the rolling mill are immersed in the coolant, and it takes time for the coolant to have an effect on the shape compared to the AS-U and the intermediate roll shift. In addition, since the adjustment of the coolant injection amount cannot be performed automatically, it is also considered that the operator needs to perform the operation such as the operation of the flow control valve. In such a case, adjustment can only be performed before the start of rolling.

During the rolling process in the rolling mill, mechanical operation abnormalities may occur, such as the breaking of the rolled material. The breaking of the rolled material is mostly caused by the rolled material, but there are also cases where the rolled material breaks due to bending. The bending of the rolled material refers to the deviation of the rolled material to one side of the rolling mill, and rolling is usually performed in the center of the rolling mill.

It is expected that such bending occurs due to the position of the AS-U roller or the intermediate roller displacement. In shape control, the AS-U and the intermediate roller displacement are operated to maintain the shape of the rolled material at the target shape, but as a result, the mechanical state sometimes becomes a state where the rolled material is prone to bending.

In the past, in common rolling mills such as 4-stage rolling mills and 6-stage rolling mills, in addition to the bending machine and leveling machine as the mechanical operating unit, there is also an operating unit that changes the coolant injection amount in the plate width direction for shape control. Unlike the Sendzimir mill, in a common rolling mill, the rollers of the rolling mill are not immersed in the coolant, and the effect of the coolant on the shape can be obtained in the same time as the mechanical operating unit. Therefore, the shape control in a common rolling mill treats the mechanical operating unit and the coolant equally, and uses the coolant as a control operating end. In this case, the coolant has an effect on the entire area in the plate width direction, and therefore competes with the mechanical operating unit. Even if the actual shape of the rolled material is the same, the actual position of the mechanical operating unit is mostly different.

FIG. 15 shows a schematic configuration of a conventional control device for a Sendzimir mill.

First, in the calculation unit 901, the difference between the target shape d1 and the shape result d2 of the rolled material obtained by the rolling mill 990 is obtained, and the difference is provided to the first shape control unit 902 and the second shape control unit 903. The first shape control unit 902 controls the mechanical operation terminal 904 which is a mechanical operation unit. The second shape control unit 903 controls the coolant operation terminal 905 which changes the coolant injection amount.

The rolling mill 990 performs a mechanical operation process based on the mechanical operation end 904 and an operation process based on the coolant injection amount of the coolant operation end 905, performs a rolling process on the rolled material, and obtains the shape performance d2 and the rolling performance d3 of the rolled material. In this case, in the mechanical operation process performed by the mechanical operation end 904, the shape of the rolled material is changed with a relatively high-speed response by controlling the operation amount. On the other hand, in the operation process of the coolant injection amount performed by the coolant operation end 905, even if the operation amount is controlled, the response is slower than that of the mechanical operation process.

In the case of the structure shown in FIG. 15 , as already described, the mechanical operation process performed by the mechanical operation end 904 competes with the operation process of the coolant injection amount performed by the coolant operation end 905. At this time, even if the shape performance d2 is the same, the mechanical operation amount of the mechanical operation end 904 is not necessarily the same. Moreover, the response speeds of the mechanical operation process performed by the mechanical operation end 904 and the operation process of the coolant injection amount performed by the coolant operation end 905 are different, and the range of the effect in the plate width direction is different in each operation process. Therefore, there is a problem that it is difficult to properly control both the mechanical operation process performed by the mechanical operation end 904 and the operation process of the coolant injection amount performed by the coolant operation end 905. For example, when the state is close to the upper limit of the operation range of the high-speed response mechanical operation end 904, the shape performance d2 and the rolling performance d3 may not be stably controlled and vibration may occur, and the rolling mill 990 as the control object factory equipment cannot be stably operated.

As a prior art for appropriately performing such shape control of a Sendzimir mill, there is a technology that uses machine learning based on actual performance data to learn the relationship between the actual shape deviation of the rolled material and the operation amount of the control operation end and performs control, as described in Patent Document 3. In the technology described in Patent Document 3, a control output is output based on the shape deviation, and shape control of the operation control operation end is performed.

Prior art literature

Patent Literature

Patent Document 1: Japanese Patent No. 2804161

Patent Document 2: Japanese Patent No. 2515028

Patent Document 3: Japanese Patent Application Publication No. 2018-005544

Summary of the invention

Problems to be solved by the invention

The technology described in Patent Document 3 performs shape control by learning the control operation method for shape deviation without considering the position of the control operation terminal. When performing actual control, the operation range is limited according to the mechanical conditions of the control operation terminal, but the control output for the control operation terminal is stopped, and the operation is performed only through other control operation terminals when possible.

In addition, in the case where the time before the coolant at the shape control operating end affects the shape is longer than that at the mechanical operating end, such as in a Sendzimir rolling mill, even if the coolant operating instructions are output in the same way as in the mechanical operating end as before, the shape is still controlled by the mechanical operating end whose effect on the shape is transmitted in a short time, and shape control based on the coolant cannot be effectively implemented.

When rolling is performed using a rolling mill, mechanical operation abnormalities such as plate breakage may occur depending on the characteristics of the rolled material, the rolling state, and the actual position of the mechanical operating end for shape control, so it is required to limit the actual position of the mechanical operating end. However, when the mechanical operating end and the coolant are used as the operating end for shape control, it is extremely difficult to limit the actual position of the mechanical operating end.

As described above, in conventional shape control, since the coolant is controlled based on the shape deviation similarly to the machine operating end, there is a problem that the actual position of the machine operating end that causes machine operation abnormality such as plate breakage cannot be restricted.

In addition, in the description so far, the problem of shape control of the Sendzimir rolling mill has been described, but various factory equipment control devices have the same problem when performing control operations with fast response and control operations with slow response at the same time, and when performing both control operations appropriately at the same time.

The object of the present invention is to provide a factory equipment control device, a factory equipment control method and a program that can predict the occurrence of mechanical operation abnormalities in the factory equipment under control and appropriately operate the control operation end in a manner that does not cause the mechanical operation abnormalities, thereby improving the control effect and operation efficiency.

Means for solving problems

In order to solve the above-mentioned problems, for example, the structure described in the claims of the patent right is adopted.

The present application includes a plurality of means for solving the above-mentioned problems. As an example, a plant equipment control device performs a first operation process whose response speed to the operation is a predetermined response speed and a second operation process whose response speed to the operation is slower than the first operation process on a plant equipment to be controlled. The plant equipment control device includes:

A first control unit that obtains a target state quantity of a control target plant equipment and instructs to perform a first operation process;

A second control unit that obtains a target state quantity of the control target plant equipment and instructs to perform a second operation process;

A first operating terminal, which executes a first operation process of the control target factory equipment according to the instruction of the first control unit;

A second operation terminal, which executes a second operation process of the control target factory equipment according to the instruction of the second control unit;

a safe operation range determination unit that determines a safe operation range of a first operation process of the first operation terminal according to actual performance of the first operation terminal; and

The third control unit, when the first operation processing performed by the first operating end is not within the safe operating range in the judgment made by the safe operating range determination unit, corrects or changes the instruction of the second operation processing performed by the second control unit, so that the actual position of the first operation processing performed by the first operating end is moved to the actual position where no mechanical operation abnormality is estimated to have occurred.

Effects of the Invention

According to the present invention, the operating state of the controlled plant equipment can be appropriately controlled to suppress the actual position of the operating end that causes abnormal mechanical operation. As a result, it can be expected that the control accuracy of the controlled plant equipment can be improved, the operating efficiency can be improved, and the occurrence of abnormal mechanical operation can be suppressed.

Other problems, structures, and effects than those described above will become apparent from the following description of the embodiments.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram showing a configuration example of a plant equipment control device according to an example of an embodiment of the present invention.

FIG. 2 is a block diagram showing a configuration example in which a plant equipment control device according to an example of an embodiment of the present invention is applied to a rolling mill.

FIG. 3 is a structural diagram showing an example of a Sendzimir rolling mill.

FIG. 4 is a structural diagram showing an example of a rolling facility of a single-stand rolling mill.

FIG. 5 is a diagram showing an outline of a mechanical operating end according to an example of an embodiment of the present invention.

FIG. 6 is a block diagram showing a configuration example of a safe operating range determination unit according to an example of an embodiment of the present invention.

FIG. 7 is a diagram showing a configuration example of a neural network according to an example of an embodiment of the present invention.

FIG. 8 is a diagram showing a configuration example of a neural network management table according to an example of an embodiment of the present invention.

FIG. 9 is a diagram showing a configuration example of a learning database according to an example of an embodiment of the present invention.

FIG. 10 is a block diagram showing a configuration example of a machine operation end position suppression control unit according to an example of an embodiment of the present invention.

FIG. 11 is a diagram showing an outline of a machine operation end position abnormal region determination unit according to an example of an embodiment of the present invention.

FIG. 12 is a diagram showing the configuration and operation of a coolant operating end control output calculation unit according to an example of an embodiment of the present invention.

FIG. 13 is a diagram showing the operation of the coolant operating end control output selection unit according to an example of an embodiment of the present invention.

FIG. 14 is a block diagram showing an example of a hardware configuration in which a plant equipment control device according to an example of an embodiment of the present invention is configured by a computer.

FIG. 15 is a block diagram showing a configuration example of a conventional rolling mill control device.

Description of Reference Numerals

11…Shape detection preprocessing unit, 12…Pattern recognition unit, 13…Control operation unit, 14…Shape detector, 50…Control device, 100…Plant equipment control device (computer), 101…Calculator, 102…Third control unit, 103…High-speed operation terminal, 104…Low-speed operation terminal, 105…Safety operation range determination unit, 110…Control unit, 111…First control unit, 112…Second control unit, 190…Control object plant equipment, 201…Calculator, 202…Machine operation terminal position suppression control unit, 203…Machine operation terminal, 204…Coolant operation terminal, 205…Machine operation terminal safety operation range determination unit, 210…Shape control unit, 211…First shape control unit, 212…Second shape control unit, 300…Rolled material, 301 ... rolling mill, 302 ... feeding side tension reel (feeding side TR), 303 ... delivery side tension reel (delivery side TR), 304 ... grinding speed control unit, 305 ... feeding side TR control unit, 306 ... delivery side tension reel control unit, 307 ... roll gap control unit, 308 ... feeding side tension meter, 309 ... delivery side tension meter, 310 ... rolling speed setting unit, 311 ... feeding side tension setting unit, 312 ... delivery side tension setting unit, 313 ... feeding side tension control unit, 314 ... delivery side tension control unit, 315 ... feeding side tension current conversion unit, 316 ... delivery side tension current conversion unit, 317 ... delivery side plate thickness meter, 318 ... delivery side plate thickness control unit, 319 ... roll gap setting unit, 401 ... working roll, 402 ... first intermediate roll, 4 03…Second intermediate roller, 404…AS-U roller, 405…Split roller, 406…Saddle, 501…Input data generation unit, 502…Neural network, 503…Neural network learning control unit, 504…Neural network selection unit, 505…Supervision data generation unit, 506…Machine operation abnormality determination unit, 511…Learning data database, 512…Control rule database, 610…Machine operation end position abnormal area determination unit, 611…Machine operation end position abnormal area search unit, 612…Input data generation unit, 613…Output data determination unit, 620…Machine operation end position abnormality suppression control unit, 621…Coolant operation end control output calculation unit, 622…Coolant operation end control output selection unit, 623…Coolant control rule database, 631 …database retrieval unit, 632…output synthesis unit, 901…calculator, 902…first shape control unit, 903…second shape control unit, 904…machine operation end, 905…coolant operation end, 990…rolling mill, d11…first state quantity target, d12…first state quantity, d13…second state quantity, d14…safe operation range, d21…target shape, d22…machine operation end position performance, d23…shape performance, d24…rolling performance, d25…machine operation end safe operation range, d26…machine operation abnormality evaluation value, d27…performance position abnormal area operation end judgment value, d28…abnormal suppression output, 29…shape control output, d30…coolant operation output, d31…estimated position, d32…machine operation abnormality judgment value.

Detailed ways

Hereinafter, a plant equipment control device according to an example of an embodiment of the present invention (hereinafter referred to as “this example”) will be described with reference to FIGS. 1 to 13 .

[Overall structure of factory equipment control device]

FIG. 1 shows an example of the overall configuration of a plant equipment control device of this example.

The factory equipment control device shown in Figure 1 controls the control object factory equipment 190, and as the control of the control object factory equipment 190, performs operation processing based on the high-speed operation terminal (first operation terminal) 103 and operation processing based on the low-speed operation terminal (second operation terminal) 104.

The plant equipment control device of this example obtains the first state quantity target d11, and obtains the difference with the first state quantity d12 through the operator 101. The first state quantity d12 is obtained from the controlled plant equipment 190 as a result of the operation processing of the high-speed operation terminal 103 and the low-speed operation terminal 104. In addition, the second state quantity d13 is obtained as a result of the operation processing of the high-speed operation terminal 103 and the low-speed operation terminal 104 and other operation terminals applied to the controlled plant equipment 190.

The control unit 110 of the plant control device has a first control section 111 that controls the operation process of the high-speed operation terminal 103 and a second control section 112 that controls the operation process of the low-speed operation terminal 104 .

The control output of the first control unit 111 is directly supplied to the high-speed operation terminal 103 to control the operation process of the high-speed operation terminal 103 .

The control output of the second control unit 112 is supplied to the third control unit 102 , and after the control output is corrected or changed as necessary, it is supplied to the low-speed operation terminal 104 .

In addition, the plant equipment control device of this example includes a safe operating range determination unit 105. The safe operating range determination unit 105 obtains the operation performance of the high-speed operating terminal 103, determines whether the obtained operation performance has a margin within the safe operating range, and supplies data of the safe operating range d14 as the determination result to the third control unit 102.

Furthermore, the safe operation range determination unit 105 obtains the first state quantity d12 and the second state quantity d13 of the control target plant equipment 190. Then, the safe operation range determination unit 105 refers to the first state quantity d12 and the second state quantity d13 to determine whether the current operation performance of the high-speed operation terminal 103 has a margin within the safe operation range.

Here, the safe operation range determination unit 105 detects the occurrence of mechanical operation abnormality, learns the first state quantity d12 and the second state quantity d13 at that moment, and the actual position of the high-speed operation end 103, and determines the operable range, i.e., the safe operation range d14, in such a way that the mechanical operation abnormality does not occur at the high-speed operation end 103. Since mechanical operation abnormality does not occur frequently, it is preferred that the safe operation range determination unit 105 continuously collects actual performance data, performs learning using machine learning, etc., and obtains the safe operation range d14.

Then, the safe operating range determination unit 105 supplies data of the determined safe operating range d14 to the third control unit 102 .

When the third control unit 102 determines that there is a margin in the safe operating range based on the data of the safe operating range d14, the control output of the second control unit 112 is directly supplied to the low-speed operation terminal 104. On the other hand, when the third control unit 102 determines that there is no margin in the safe operating range based on the data of the safe operating range d14, the control output of the second control unit 112 is corrected or changed, and supplied to the low-speed operation terminal 104.

The output of the operator 101, the operation performance of the high-speed operating terminal 103, and the second state quantity d13 are supplied to the third control unit 102, and the third control unit 102 corrects or changes the control output of the second control unit 112 based on these information.

According to the plant equipment control device having the structure shown in FIG. 1 , the high-speed operating end 103 can be operated efficiently within a range where machine operation abnormality does not occur, and in addition to improving the operating efficiency, it can also be expected that the control accuracy will be improved.

[Overall structure when applied to a control device for a Sendzimir rolling mill]

Next, the overall configuration in the case where the plant equipment control device of this example is applied to a Sendzimir rolling mill will be described.

FIG. 2 shows the configuration of the plant equipment control device of this example when applied to a Sendzimir rolling mill.

The plant control device shown in FIG. 2 obtains a target shape d21 of a rolled material, and obtains a difference from an actual shape result d23 after rolling through a calculation unit 201 .

In the plant equipment control device of this example, as the control of the rolling mill 301, the operation processing by the mechanical operation terminal 203 and the operation processing by the coolant operation terminal 204 are performed. The operation processing performed by the mechanical operation terminal 203 is a process of mechanically changing the roll gap and the like for rolling processing, and the response that appears in the shape performance d23 of the rolled material becomes high-speed. On the other hand, the operation processing performed by the coolant operation terminal 204 is a process of changing the coolant injection amount, and the response that appears in the rolling performance d24 of the rolled material becomes slow compared with the operation of the mechanical operation terminal 203.

The shape control unit 210 of the plant equipment control device includes a first shape control unit 211 for controlling the operation process of the machine operation terminal 203 and a second shape control unit 212 for controlling the operation process of the coolant operation terminal 204. The first shape control unit 211 and the second shape control unit 212 control the rolled material to a target shape d21. The target shape d21 is a shape preset according to the characteristics of the rolled material, etc.

The control output of the first shape control unit 211 is directly supplied to the mechanical operation terminal 203 to control the operation process of the mechanical operation terminal 203 .

The control output of the second shape control unit 212 is supplied to the mechanical operation end position suppression control unit 202 , and after the control output is corrected or changed as necessary, it is supplied to the coolant operation end 204 .

The configuration of the mechanical operation end position suppression control unit 202 will be described later with reference to FIG. 10 .

In addition, the plant equipment control device of this example includes a machine operating end safe operation range determination unit 205. The machine operating end safe operation range determination unit 205 obtains the operation performance of the machine operating end 203, that is, the machine operating end position performance d22, and determines whether the obtained machine operating end position performance d22 has a margin in the safe operation range. Then, the machine operating end safe operation range determination unit 205 supplies data of the machine operating end safe operation range d25 as the determination result to the machine operating end position suppression control unit 202.

Furthermore, the machine operation end position suppression control unit 202 obtains the shape performance d23 and rolling performance d24 of the rolling mill 301. Then, the machine operation end safe operation range determination unit 205 refers to the shape performance d23 and rolling performance d24 to determine whether the obtained machine operation end position performance d22 has a margin within the safe operation range.

The mechanical operation end safe operation range determination unit 205 detects the occurrence of mechanical operation abnormality, and learns the shape performance d23 and rolling performance d24 and mechanical operation end position performance d22 at that time. Through this learning, the mechanical operation end safe operation range determination unit 205 determines the operable range, i.e., the mechanical operation end safe operation range d25, so that the mechanical operation abnormality does not occur at the mechanical operation end 203. Here, the mechanical operation end safe operation range determination unit 205 continuously collects performance data, performs learning using machine learning, etc., and obtains the mechanical operation end safe operation range d25.

Then, the machine operating end safe operation range determination unit 205 supplies data of the determined machine operating end safe operation range d25 to the machine operating end position suppression control unit 202 .

In addition, the detailed structure of the machine operation end safe operation range determination unit 205 for learning machine operation abnormalities will be described later with reference to FIG. 6 .

When the mechanical operation end position suppression control unit 202 determines that the safe operation range has a margin based on the data of the mechanical operation end safe operation range d25, the control output of the second shape control unit 212 is directly supplied to the coolant operation end 204. On the other hand, when the mechanical operation end position suppression control unit 202 determines that the safe operation range does not have a margin based on the data of the mechanical operation end safe operation range d25, the control output of the second shape control unit 212 is corrected or changed, and supplied to the coolant operation end 204.

The output of the operator 201, the actual position performance of the machine operation end d22, and the actual rolling performance d24 are supplied to the machine operation end position suppression control unit 202, which corrects or changes the control output of the second shape control unit 212 based on these information.

[Structure of Sendzimir rolling mill]

Here, a configuration example of a Sendzimir rolling mill will be described.

FIG. 3 shows a schematic configuration when shape control is performed in a Sendzimir rolling mill.

The Sendzimir mill detects the actual shape of the rolled material after rolling by the shape detector 14. After the actual shape detected by the shape detector 14 is pre-processed by pattern recognition by the shape detection pre-processing unit 11 of the control device 50, the pattern recognition unit 12 calculates which of the preset reference shape patterns is closest. Then, based on the calculated reference shape pattern, the control calculation unit 13 determines the operating end and the operating amount to be operated, and performs processing to control the Sendzimir mill using the operating end and the operating amount to be operated.

An example of a single-stand rolling mill is shown in Fig. 4. A Sendzimir mill is one type of a single-stand rolling mill.

The rolling equipment shown in Figure 4 is composed of a rolling mill 301, a feed-side tension reel (hereinafter referred to as "TR") 302 and a delivery-side TR303. The rolled material 300 pulled out from the feed-side TR302 passes through the rolling mill 301 and is wound by the delivery-side TR303.

The rolling mill 301 rolls the material to be rolled 300. The rolling here refers to a process of reducing the thickness of the material to be rolled 300 to a predetermined thickness.

The rolling mill 301 is provided with a grinding speed control unit 304 for adjusting the rolling speed and a roll gap control unit 307 for adjusting the roll gap of the rolling mill 301. In addition, the inlet TR 302 and the outlet TR 303 are provided with an inlet TR control unit 305 and an outlet TR control unit 306 for adjusting the tension generated respectively.

The gap between the upper and lower rolls of the rolling mill 301 is adjusted by the roll gap control unit 307, thereby applying pressure to flatten the rolled material 300, and the rolled material 300 is sent to the delivery side by the grinding speed control unit 304, thereby performing the rolling process. At this time, at the delivery side and the delivery side of the rolling mill 301, a process of applying tension to the rolled material 300 using the delivery side TR302 and the delivery side TR303 is also performed.

Important to the rolling operation is the thickness of the rolled material 300 (the thickness at the delivery side of the rolling mill) that becomes the product, and the roll gap, the delivery side tension, and the delivery side tension are set in advance so that the rolled material 300 has a predetermined thickness.

The delivery side tension current conversion unit 315 uses the delivery side tension set by the delivery side tension setting unit 311 to obtain the current required to obtain the set delivery side tension, and supplies the current to the delivery side TR 302 via the delivery side TR control unit 305, thereby obtaining the delivery side tension.

Similarly, the delivery side tension current conversion unit 316 uses the delivery side tension set by the delivery side tension setting unit 312 to obtain the current required to obtain the set delivery side tension, and supplies it to the delivery side TR 303 via the delivery side TR control unit 306, thereby obtaining the delivery side tension.

The roll gap set by the roll gap setting unit 319 is provided to the roll gap control unit 307 , and the roll gap is set by the roll gap control unit 307 .

The rolling speed setting unit 310 determines the speed of the rolling mill 301 according to an instruction from an operator of the rolling mill, and sets the speed of the rolling mill 301 via the mill speed control unit 304 .

A feed-in tension meter 308 and a feed-out tension meter 309 are provided on the feed-in side and the feed-out side of the rolling mill 301, and a feed-in tension control unit 313 and a feed-out tension control unit 314 perform control so that the actual tension measured by them is consistent with the set tension. In addition, a feed-out side plate thickness meter 317 is provided on the feed-out side of the rolling mill 301, and a feed-out side plate thickness control unit 318 performs control so that the actual plate thickness measured therein is consistent with the set plate thickness.

Based on the above configuration, as shown in FIG. 3 already described, a shape detector 14 for detecting the shape of the rolled material is provided on the delivery side of the rolling mill, and shape control is performed so that the detected shape matches a preset target shape.

As already explained, the shape is the degree of fluctuation of the metal plate as the rolled material. Therefore, the target shape, which is the target shape, is set in advance based on the processability in the next process of the rolling mill and the efficiency of the rolling operation in the rolling mill. Generally speaking, since tension is applied to the rolled material, if there are flaws such as cracks at the ends of the plate, it is easy to generate cracks from there, resulting in the situation that the rolled material is disconnected in the plate width direction (plate breakage). Therefore, in order to prevent the tension from being concentrated, the plate ends are often made into a fluctuating state.

The fluctuation of the rolled material is actually the tension applied to the rolled material, so it is not obvious. There is no fluctuation in appearance, but the tension distribution in the width direction of the plate changes.

Here, the shape detector 14 shown in FIG. 3 estimates the undulation of the sheet by measuring the tension distribution in the sheet width direction, and detects it as the shape result.

[Structure and processing of the shape control mechanical operating end]

Fig. 5(a) shows the structure when the Sendzimir mill performs the operation by the mechanical operation end 203. Fig. 5 shows a cross section of the rolled material 300 in the plate width direction, and only the upper structure of the rolled material 300 is shown, and the lower structure is omitted.

5( b ) and ( c ) respectively show the operation waveforms when the shape of the rolled material 300 is changed.

As shown in FIG. 5( a ), the Sendzimir mill is composed of work rolls 401 , first intermediate rolls 402 , second intermediate rolls 403 , and AS-U rolls 404 so as to sandwich a rolled material 300 .

The first intermediate roll 402 is provided with tapered rolls on the upper and lower opposite sides, and is displaced in the plate width direction, thereby being able to affect the shape of the plate end portion of the rolled material 300 .

The AS-U roll 404 has a structure in which a saddle 406 is interposed between a plurality of split rolls 405. By changing the position of the saddle 406 (the longitudinal position in FIG. 5), the deflection of the AS-U roll 404 can be changed in the plate width direction.

For example, as shown in FIG. 5( b ), when the central saddle 406 is lowered, the shape of the central portion of the rolled material 300 can be affected.

5(b) and (c) show the change in the thickness distribution of the rolled material 300 when the saddle 406 or the first intermediate roll 402 is shifted. The shape change is opposite to the thickness distribution.

The shape is the distribution of the degree of fluctuation in the plate width direction, and a large fluctuation means that the rolled material 300 is elongated. This is because it is equivalent to "the plate thickness on the delivery side is thinner", "the elongation of the rolled material in the thinned part is large", and "the shape of the rolled material is larger".

Regarding abnormality in mechanical operation, plate breakage of the rolled material 300 is a major problem. If plate breakage occurs, the broken rolled material 300 will damage the working roll 401 and the first intermediate roll 402 of the rolling mill. In addition, depending on the situation, the second intermediate roll 403 and the AS-U roll 404 may also be damaged due to the occurrence of plate breakage. If these damages occur, these rolls need to be replaced, and it takes time to remove the rolled material 300 remaining in the rolling mill, which greatly reduces the efficiency of mechanical operation.

The AS-U roll 404 is pressed against the second intermediate roll 403 by the saddle 406 so as to press the split roll 405. Therefore, depending on the position of the saddle 406, the split roll 405 may not contact the second intermediate roll 403. If such a state is reached, the force applied to the rolled material 300 from the work roll 401 in this part is sharply reduced, the rolled material 300 is no longer stretched, and the tension applied to the rolled material 300 in this part is increased.

When such a state occurs at the plate ends of the rolled material 300, the plate breaks from the plate ends. In addition, since the tension applied to the two ends of the rolled material 300 in the plate width direction changes, the plate width center of the rolled material 300 may deviate from the plate width center of the rolling mill, and collide with the mechanical equipment before and after the rolling mill, causing the plate to break. In this way, depending on the actual position of the machine operating end 203, machine operation abnormality may occur.

The actual position where the mechanical operation abnormality occurs is not calculated based on the mechanical structure. The thickness distribution in the width direction of the rolled material 300, the thickness on the delivery and inlet sides, the rolling conditions such as tension and rolling load, and the positional relationship with other shape control mechanical operating ends also change, so it is difficult to predict in advance.

Therefore, in this example, the mechanical operating end safe operating range determination unit 205 saves these conditions when rolling abnormalities occur as performance data, and by comparing them with the performance data during normal times, calculates the performance position of the shape control mechanical operating end where rolling abnormalities are prone to occur.

The mechanical operation end safe operation range determination unit 205 of this example uses machine learning to determine the mechanical operation end safe operation range. The actual performance data during machine learning uses the rolling conditions such as the plate thickness, tension and rolling load on the delivery side, and the actual position of the mechanical operation end 203, and the rolling abnormality occurrence information is used in the supervision data.

As rolling abnormality occurrence information, information on plate breakage and emergency stop of the rolling mill is used. Plate breakage can be determined by the reduction of the tension on the delivery side, and emergency stop uses information on the operation switch operated by the operator when the operation is stopped due to some abnormality in the rolling state. The information on the operation switch can be detected by a computer constituting a control device for controlling the rolling mill, and can be used as one of the performance information. The mechanical operation end safe operation range determination unit 205 uses these performance data and supervision data to generate a neural network (N.N.) for determining whether a mechanical operation abnormality has occurred.

[Structure of the safe operating range determination unit at the machine operation end and the structure of the neural network]

FIG. 6 shows a configuration in which the machine operating end safe operation range determination unit 205 is realized by machine learning.

7 shows the structure of the neural network 502 included in the machine operation terminal safety operation range determination unit 205. As shown in FIG.

As shown in FIG7 , the neural network 502 obtains the rolling performance d24 and the mechanical operation end position performance d22 from the input data generation unit 501 at the input end 502a, and outputs the mechanical operation abnormality judgment value d32 from the output end 502b. The mechanical operation abnormality judgment value d32 is information on plate breakage as rolling abnormality occurrence information and information on emergency stop. The neural network 502 performs learning based on the combination of these input data and output data.

The machine operation terminal safe operation range determination unit 205 shown in FIG6 is described. The input data generation unit 501 collects the actual position performance d22 and shape performance d23 of the machine operation terminal. In addition, the supervisory data generation unit 505 collects the machine operation abnormality determination value d32 determined by the machine operation abnormality determination unit 506. The data collection in these input data generation units 501 and the supervisory data generation unit 505 is performed at a fixed time cycle under the control of the neural network learning control unit 503, and a set of learning data is obtained for each action cycle. The obtained learning data is sequentially stored in the learning data database 511.

The mechanical operation abnormality determination unit 506 determines whether there is mechanical operation abnormality, that is, plate breakage and emergency stop of the rolling mill, based on the rolling performance d24. The mechanical operation abnormality determination value d32 as the determination result is information on plate breakage and emergency stop.

In addition, the rolling mill rolls various rolled materials 300 according to the specifications to obtain products. Therefore, the rolling mill generally responds to the specifications of the rolled material 300 by changing the mechanical structure, that is, the specifications of the work roll 401 (diameter distribution in the plate width direction), the taper specifications of the first intermediate roll 402, and the combination of the split rolls 405 of the AS-U roll 404. In addition, the plate width and material of the rolled material 300 are also different. Therefore, the method of distinguishing the neural network 502 according to the mechanical structure and the specifications of the rolled material 300 can achieve efficient learning.

Therefore, the machine operating terminal safe operation range determination unit 205 of this example has a plurality of neural networks 502, and is provided with a control rule database 512 and a neural network selection unit 504 in a switchable manner.

FIG. 8 shows a configuration example of the control rule database 512 .

In the control rule database 512 , as shown in (a) of FIG. 8 , a plurality of neural networks that have been trained using learning data consisting of a combination of input data and supervisory data are stored.

Then, the neural network learning control unit 503 specifies the neural network No. to be learned. The neural network selection unit 504 receives the designation of the neural network No. to be learned by the neural network learning control unit 503 , retrieves the neural network from the control rule database 512 , and sets it as the neural network 502 .

The neural network selection unit 504 takes out the neural network with the corresponding neural network No. from the control rule database 512 according to the current rolling performance d24, matching the rolling conditions and the mechanical structure, and sets the mechanical operating end position suppression control unit 202 as the control neural network d33.

(b) in FIG8 shows the structure of the neural network management table stored in the control rule database 512. The management table is divided according to the (B1) plate width, (B2) steel type and mechanical structure (a). As the (B1) plate width, for example, four types of 3 feet wide, meter wide, 4 feet wide and 5 feet wide are used. As the (B2) steel type, about 10 types of steel (1) to (10) are used. Regarding (A), for example, according to the length of the tapered portion of the tapered specification of the first intermediate roller 402, it is divided into (A1) and (A2).

The above table difference is an example and needs to be set appropriately according to the rolling equipment and the type of rolled materials produced.

The machine operating end safe operation range determination unit 205 uses these neural networks separately according to the rolling conditions and the machine structure.

The neural network learning control unit 503 associates the combination of input data and supervisory data shown in (a) of FIG. 8 , i.e., learning data, with the corresponding neural network No. and stores them in the learning data database 511 according to the neural network management table shown in (b) of FIG. 8 .

FIG. 9 shows an example of the learning data stored in the learning data database 511 .

As shown in FIG. 9 , the learning data database 511 stores learning data corresponding to each neural network No.

The neural network learning control unit 503 instructs the input data generation unit 501 and the supervisory data generation unit 505 to retrieve the management table of the input data and supervisory data corresponding to the neural network from the learning data database 511. The neural network 502 performs learning using these data. Various neural network learning methods have been proposed in the past, and any learning method may be used.

Machine learning requires a large number of sets of learning data, and if a certain amount (eg, 10,000 sets) is stored in the learning data database 511, the neural network 502 performs learning.

When the learning of the neural network 502 is completed, the neural network learning control unit 503 writes the neural network 502 as the learning result back to the position of the neural network No. in the control rule database 512, thereby completing the learning.

The learned neural network 502 outputs a mechanical operation abnormality judgment value by inputting the rolling performance d24 and the mechanical operation end position performance d22. Therefore, the neural network 502 can predict whether a mechanical operation abnormality occurs and search for a mechanical operation end safe operation range d25 by giving the expected future shape performance d23 and the mechanical operation end position performance d22.

[Structure of the mechanical operation end position suppression control unit]

FIG. 10 shows the configuration of the machine operation end position suppression control unit 202 .

The machine operating end position suppression control unit 202 includes a machine operating end position abnormality region determination unit 610 and a machine operating end position abnormality suppression control unit 620 .

The machine operating end position abnormal area determination unit 610 estimates the machine operating end 203 that predicts the occurrence of machine operation abnormality using the neural network 502 described in FIG7 . The neural network 502 used here is the control neural network d33 received from the machine operating end safe operation range determination unit 205 .

The mechanical operating terminal position abnormality suppression control unit 620 generates an operation instruction for the coolant operating terminal 204 according to the determination result of the mechanical operating terminal position abnormal area determination unit 610 .

During the rolling operation, the actual shape performance d23 of the rolling mill 301 changes constantly, and the first shape control unit 211 for maintaining the rolling mill in the target shape d21 operates the mechanical operating end 203, and the actual position performance d22 of the mechanical operating end also changes constantly. The mechanical operating end position abnormal area search unit 611 of the mechanical operating end position abnormal area determination unit 610 uses the actual position performance d22 of the mechanical operating end to generate input data for the neural network 502 through the input data generation unit 612.

FIG. 11 shows the processing performed by the machine operation end position abnormal area determination unit 610 .

In the example of FIG. 11 , when there are n types of mechanical operating ends 203 (n is an integer), the mechanical operating end position performance d22 is as follows.

POS(k), k=1, 2, ..., n

Here, there are n types of mechanical operating ends 203, for example, the total value of the number of saddles 406 of the AS-U roller 404 and the number of first intermediate rollers 402 that can be displaced in the plate width direction. In the example shown in FIG5 , the number of saddles is 5, and there are two first intermediate rollers, one above the other, so n=7.

When the mechanical operating end 203 is operated by the first shape control unit 211, the operation is performed within a constant amount in each control cycle, so the mechanical operating end position abnormal area search unit 611 generates the estimated position of the mechanical operating end position performance d22 of each mechanical operating end 203 as follows. Here, for example, the position performance change amount ΔPOS that may be operated by multiple controls is considered, and three cases are considered: a case where the position performance does not change and a case where the performance value changes in the positive and negative directions.

POS(k), POS(k)±ΔPOS, k=1, 2, ..., n

Thus, 3 ⁿ types (for example, 2187 when n=7) of estimated position results can be generated for each machine operating end 203. For example, when n=7, 2187 types of estimated position results can be generated. The estimated position results are sequentially output to the input data generating unit 612.

The input data generating unit 612 generates input data to the neural network 502 based on the rolling performance d24 and the estimated position d31 , and outputs the input data to the neural network 502 .

The neural network 502 outputs the mechanical operation abnormality determination value d32 shown in (d) of FIG. 11 . The mechanical operation abnormality determination value d32 is the degree of plate breakage and emergency stop, but here, the output data determination unit 613 receives the mechanical operation abnormality determination value d32 output from the neural network 502, weights and adds the degrees of the two, and sets it as the mechanical operation abnormality evaluation value d26. Usually, although the operator implements an emergency stop when a mechanical operation abnormality occurs, it is also implemented when there is a sign of plate breakage. As a sign of plate breakage here, there is, for example, bending of the rolled material 300.

When a plate break occurs without an emergency stop, priority is given to suppressing the plate break that occurs without warning. Therefore, the weight of the degree of plate break is increased.

The mechanical operation end position abnormal area search unit 611 stores the output estimated position d31 and the returned mechanical operation abnormality evaluation value d26 in advance, and searches for the estimated value at which the mechanical operation abnormality evaluation value d26 is the largest. When the result of the search is that the maximum value of the mechanical operation abnormality evaluation value d26 exceeds a predetermined threshold value, the mechanical operation end position abnormal area search unit 611 outputs the actual position change amount at the estimated position d31 in this case as the actual position abnormal area operator determination value d27. In addition, the mechanical operation abnormality evaluation value d26 in this case is also included in the actual position abnormal area operator determination value d27 as the mechanical operation abnormality evaluation maximum value.

In the example described above, the mechanical operation end position abnormal area search unit 611 generates the estimated position d31 by setting the amount of change from the actual position of the mechanical operation end 203 to three types, but it can also be generated by other processing. For example, the mechanical operation end position abnormal area search unit 611 finely controls the amount of change of the estimated position d31. In addition, the mechanical operation end position abnormal area search unit 611 may not perform a search in a direction where mechanical operation abnormalities do not obviously occur, but may change it in time according to the situation. Here, the direction where mechanical operation abnormalities do not obviously occur refers to, for example, the case of considering moving toward the center direction of the actual position of the mechanical operation end.

The mechanical operating terminal position abnormality suppression control unit 620 generates a control output for the coolant operating terminal 204 based on the actual position abnormality area operating terminal judgment value d27 as the output of the mechanical operating terminal position abnormality area judgment unit 610 and the control instruction of the second shape control unit 212 to the coolant operating terminal 204.

When it is determined that the machine operation abnormality will not occur even if the machine operation terminal position performance d22 changes during control, the normal operation using the coolant operation terminal 204 based on the second shape control unit 212 can be performed. Then, when the machine operation abnormality evaluation value d26 is not too large, the abnormality suppression output d28 for suppressing the machine operation abnormality may be output in a manner that is synthesized in the control output of the second shape control unit 212. Of course, when the machine operation abnormality evaluation value d26 is large, the abnormality suppression output d28 is outputted preferentially to the coolant operation terminal 204.

The coolant control rule database 623 predetermines the correspondence between each machine operation end 203 (k) and the affected coolant operation end 204. This correspondence can be obtained by actually operating the machine operation end 203 and the coolant operation end 204 during the rolling operation, or it can be obtained based on actual performance data through machine learning. Here, the case where the correspondence is obtained based on the result of the actual operation and registered in the coolant control rule database 623 is considered.

[Structure and operation of the coolant operation end control output calculation unit]

FIG. 12 shows the structure and operation of the coolant operation end control output calculation unit 621 .

The required amount of change in coolant flow rate that can achieve the same effect as operating each machine operation terminal 203 (k) is registered in the coolant control rule database 623 (FIG. 10). The database search unit 631 shown in (a) of FIG. 12 extracts the required amount of change in coolant flow rate corresponding to the actual position change amount of the machine operation terminal 203 (k) where the machine operation abnormality occurs, based on the actual position abnormal area operation terminal judgment value d27 obtained by the machine operation terminal position abnormal area judgment unit 610.

Then, the output synthesis unit 632 performs addition processing on the required amount of coolant flow rate change extracted from each mechanical operation end 203 ( k ) to obtain the abnormality suppression output d28 .

For example, when the actual position and estimated position shown in (a) and (b) of Figure 11 obtain the actual position abnormal area operation end judgment value d27 shown in (d) of Figure 11, it becomes the abnormal suppression output d28 as shown in (b) of Figure 12.

The coolant operation end 204 implements the lubrication and cooling required for the rolling operation, so the maximum flow rate and the minimum flow rate at each point in the plate width direction are often determined as the coolant flow rate, and the abnormality suppression output d28 that causes abnormal mechanical operation can be obtained.

[Output Selection Process in Coolant Operation Terminal Control Output Selection Section]

FIG. 13 shows the output selection process performed by the coolant operation terminal control output selection unit 622 .

The coolant operation end control output selection unit 622 selects or synthesizes the abnormality suppression output d28 shown in FIG. 10 and the shape control output d29 of the second shape control unit 212 according to the maximum value of the mechanical operation abnormality evaluation within the actual position abnormal area operation end judgment value d27 ((d) in FIG. 11) and outputs them. The output selected or synthesized by the coolant operation end control output selection unit 622 is supplied to the coolant operation end 204 as the coolant operation output d30.

When the maximum value of the mechanical operation abnormality evaluation shown in (d) of FIG. 11 is small, the possibility of mechanical operation abnormality is low even if the shape control is directly implemented, so the coolant operation terminal control output selection unit 622 directly supplies the shape control output d29 as the coolant operation output d30 to the coolant operation terminal 204. That is, the coolant operation output d30 = the shape control output d29.

On the other hand, when the maximum value of the mechanical operation abnormality evaluation is large, the coolant operation end control output selection unit 622 determines that the possibility of mechanical operation abnormality is high. At this time, as shown in (b) of FIG. 13, the abnormality suppression output d28 is generated, and the coolant operation end control output selection unit 622 is set to the coolant operation output d30 as shown in (a) of FIG. 13, so that the effect of the abnormality suppression output d28 is maximized within the maximum and minimum values of the coolant flow rate.

In addition, when the maximum value of the mechanical operation abnormality evaluation is not so large, the coolant operation end control output selection unit 622 adds the shape control output d29 and the abnormality suppression output d28 and outputs them as shown in (c) of Figure 13. At this time, the abnormality suppression output d28 is adjusted and added so that the coolant operation end flow rate converges within the maximum and minimum values, and becomes the method shown in (d) of Figure 11.

Here, the determination of whether the maximum value of the mechanical operation abnormality evaluation is large, not so large, or small is determined using a threshold value preset in the coolant operation end control output selection unit 622. In addition, the coolant operation end control output selection unit 622 may always add the shape control output d29 and the abnormality suppression output d28 and output them. However, in this case, the abnormality suppression output d28 after addition is made not to become so large.

Furthermore, in the addition operation in the coolant operation end control output selection unit 622, instead of a simple addition operation, a weighted addition operation may be performed so that the weighting varies according to the maximum value of the mechanical operation abnormality evaluation.

As described above, according to the plant equipment control device of this example, it is possible to prevent abnormality in machine operation caused by the machine operating end position performance d22 of the machine operating end 203 and to perform good shape control.

[Modifications]

In addition, the present invention is not limited to the above-mentioned embodiments and includes various modifications. For example, the above-mentioned embodiments are examples described in detail to explain the present invention in an easy-to-understand manner, and are not limited to necessarily having all the described structures.

For example, in the above-mentioned embodiment, the machine operation end safe operation range determination unit 205 is implemented by machine learning, but it is also possible to implement the machine operation end safe operation range determination unit 205 by expressing it by mathematical formula based on the operator's experience. Alternatively, the rolling state when the machine operation abnormality occurs may be databased to determine whether there is a corresponding situation, thereby implementing the machine operation end safe operation range determination unit 205.

In addition, the machine operation end safe operation range determination unit 205 can also generate a numerical model or a symbolic logic model based on the knowledge of the operator or operating technician, and use it in machine learning.

In the above-described embodiment, the machine operation end position abnormality suppression control unit 620 stores and utilizes the results obtained by experiments in advance in the coolant control rule database 623. Alternatively, the machine operation end position abnormality suppression control unit 620 may use machine learning to generate a rule base based on actual performance data.

Furthermore, in the above-described embodiment, the shape control of a rolling mill is targeted, but the present invention can also be applied to general factory equipment control.

1 and the like, control lines and information lines are shown only as necessary for explanation, and not necessarily all control lines and information lines on the product. In fact, it can be considered that almost all structures are connected to each other.

In addition, the processing units such as the control unit described in the above-mentioned implementation examples may be respectively constituted by dedicated hardware, but the functions of the processing units described in the above-mentioned implementation examples may be realized by installing a program (application) in a computer.

FIG. 14 shows an example of a hardware configuration in which the plant equipment control device is constituted by a computer.

The plant equipment control device (computer) 100 shown in Fig. 14 includes a CPU (Central Processing Unit) 100a, a ROM (Read Only Memory) 100b, and a RAM (Random Access Memory) 100c, each of which is connected to a bus. In addition, the plant equipment control device 100 includes a nonvolatile memory 100d, a network interface 100e, an input/output device 100f, and a display device 100g.

The CPU 100 a is a calculation processing unit that reads out a program code of software that realizes the functions performed by the plant equipment control device 100 from the ROM 100 b and executes the program code.

Variables, parameters, and the like generated during the operation process are temporarily written into the RAM 100 c .

The nonvolatile memory 100d uses a large-capacity information storage medium such as a HDD (Hard Disk Drive) or an SSD (Solid State Drive). The nonvolatile memory 100d stores a program (plant equipment control program) for executing the processing functions performed by the plant equipment control device 100. In addition, the nonvolatile memory 100d stores data required for machine learning.

The network interface 100e transmits and receives various information to and from the outside via a LAN (Local Area Network), a dedicated line, or the like.

The input/output device 100f inputs various information from the controlled plant 190 (rolling mill 301) and outputs information for instructing the respective operating terminals 103 and 104 (203 and 204).

The display device 100g displays the control state of the control target plant 190 (rolling mill 301).

In addition, program information that realizes each processing function performed by the plant equipment control device 100 can be stored in recording media such as semiconductor memory, IC card, SD card, and optical disk in addition to non-volatile memory such as HDD and SSD.

Furthermore, when a part or all of each processing unit of the plant equipment control device is configured by hardware, an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit) may be used.

Claims (5)

1. A plant equipment control device, which performs a first operation process in which a response speed to an operation is a predetermined response speed and a second operation process in which a response speed to an operation is slower than the first operation process on a plant equipment to be controlled, characterized in that: The factory equipment control device comprises: a first control unit that obtains a target state quantity of the control target plant equipment and instructs the first operation process; a second control unit that obtains a target state quantity of the control target plant equipment and instructs the second operation process; a first operating terminal, which executes the first operating process of the control target factory equipment according to the instruction of the first control unit; A second operating terminal, which executes the second operating process of the control target factory equipment according to the instruction of the second control unit; a safe operation range determination unit that determines a safe operation range of the first operation process performed by the first operation terminal based on the actual performance of the first operation terminal; a third control unit which, when the first operation process performed by the first operating terminal is not within the safe operation range in the judgment made by the safe operation range determination unit, corrects or changes the instruction of the second operation process performed by the second control unit so that the actual position of the first operation process performed by the first operating terminal is moved to the actual position where the mechanical operation abnormality is not estimated to have occurred, The safe operation range determination unit inputs a second state quantity and an actual position of the first operation process into a neural network, and outputs a mechanical operation abnormality determination value, wherein the second state quantity is a result of the first operation process, the second operation process, and other operation processes for the control object factory equipment, The safe operation range determination unit uses the actual position of the first operation process and the first state quantity as the result of the first operation process and the second operation process as input data, uses the mechanical operation abnormality judgment value as supervision data, and inputs the combination of the input data and the supervision data into the neural network, thereby learning the relationship between the actual performance of the first operation end and the mechanical operation abnormality, and determining the safe operation range. The third control unit generates a machine operation abnormality evaluation value by weighting and adding the degree of plate breakage and the degree of emergency stop indicated by the machine operation abnormality determination value output by the neural network. 2. The factory equipment control device according to claim 1, characterized in that: The first operation process performed by the first operation terminal has a control time response that is faster than the control time response of the second operation process and has a limited effect on the control object state quantity of the control object plant equipment. The second operation process performed by the second operation terminal has a control time response that is slower than the control time response of the first operation process and affects the entire area of the control target state quantity of the control target plant. 3. The factory equipment control device according to claim 1 or 2, characterized in that: The control object factory equipment is a rolling mill, The first operation process is a mechanical shape operation process that changes the shape by a mechanical structure. The second operation process is a coolant shape operation process in which the shape is changed by changing the injection amount of the coolant in the plate width direction. The safe operation range determination unit determines the safe operation range of the first operation process based on the actual value of the machine position at which no abnormal machine operation occurs at the first operation end. When the safe operating range determination unit infers that a mechanical operation abnormality has occurred, the third control unit changes the control output of the coolant shape control of the second operating end to an output of coolant shape control in which no mechanical operation abnormality occurs, thereby moving the actual position of the mechanical shape operation processing performed by the first operating end to the actual position where no mechanical operation abnormality is inferred. 4. A method for controlling factory equipment, wherein a calculation processing unit performs a first operation processing with a predetermined response speed for the operation and a second operation processing with a slower response speed for the operation than the first operation processing on the factory equipment to be controlled through calculation processing, characterized in that: The factory equipment control method comprises: In a first control step, the arithmetic processing unit obtains a target state quantity of the control target plant equipment and instructs the first operation process; In a second control step, the arithmetic processing unit obtains a target state quantity of the control target plant equipment and instructs the second operation process; a first operation execution step, wherein the arithmetic processing unit executes the first operation processing of the control target plant equipment according to the instruction of the first control step; a second operation execution step, wherein the arithmetic processing unit executes the second operation processing of the control target plant equipment according to the instruction of the second control step; a safe operation range determination step, wherein the arithmetic processing unit determines a safe operation range of the first operation process performed by the first operation execution step based on the actual performance of the first operation process; In a third control step, when the first operation process in the first operation execution step is not within the safe operation range, the operation processing unit corrects or changes the instruction of the second operation process in the second control step so that the actual position of the first operation process in the first operation execution step is moved to the actual position where the mechanical operation abnormality is not estimated to have occurred. In the step of determining the safe operating range, a second state quantity and an actual position of the first operation process are input into a neural network, and a mechanical operation abnormality determination value is output, wherein the second state quantity is a result of the first operation process, the second operation process, and other operation processes for the control object factory equipment. In the step of determining the safe operating range, the actual position of the first operating process and the first state quantity as the result of the first operating process and the second operating process are used as input data, the mechanical operation abnormality judgment value is used as supervision data, and the combination of the input data and the supervision data is input into the neural network, thereby learning the relationship between the actual performance of the first operating process and the mechanical operation abnormality, and determining the safe operating range. In the third control step, the degree of plate breakage and the degree of emergency stop represented by the machine operation abnormality determination value output by the neural network are weighted and added together, thereby generating a machine operation abnormality evaluation value. 5. A storage medium storing a program, wherein the program causes a computer to execute a first operation process for a control target plant equipment whose response speed to the operation is a predetermined response speed and a second operation process for the operation whose response speed is slower than the first operation process, characterized in that: The program causes the computer to execute: A first control step is to obtain a target state quantity of the control target plant equipment and to instruct the first operation process; A second control step of obtaining a target state quantity of the control target plant equipment and instructing the second operation process; a first operation execution step, executing the first operation process of the control target factory equipment according to the instruction of the first control step; a second operation execution step, executing the second operation process of the control target factory equipment according to the instruction of the second control step; a safe operation range determination step of determining a safe operation range of the first operation process performed by the first operation execution step based on the actual performance of the first operation process; A third control step is to correct or change the instruction of the second operation process in the second control step when the first operation process in the first operation execution step is not within the safe operation range in the judgment of the safe operation range determination step, so that the actual position of the first operation process in the first operation execution step is moved to the actual position where the mechanical operation abnormality is not estimated to have occurred, In the step of determining the safe operating range, a second state quantity and an actual position of the first operation process are input into a neural network, and a mechanical operation abnormality determination value is output, wherein the second state quantity is a result of the first operation process, the second operation process, and other operation processes for the control object factory equipment. In the step of determining the safe operating range, the actual position of the first operating process and the first state quantity as the result of the first operating process and the second operating process are used as input data, the mechanical operation abnormality judgment value is used as supervision data, and the combination of the input data and the supervision data is input into the neural network, thereby learning the relationship between the actual performance of the first operating process and the mechanical operation abnormality, and determining the safe operating range. In the third control step, the degree of plate breakage and the degree of emergency stop represented by the machine operation abnormality determination value output by the neural network are weighted and added together, thereby generating a machine operation abnormality evaluation value.