CN114749494A

CN114749494A - Plant control device, plant control method, and program

Info

Publication number: CN114749494A
Application number: CN202111240294.1A
Authority: CN
Inventors: 服部哲; 阿部隆; 高田敬规; 田内佑树; 黑川大辉
Original assignee: Hitachi Ltd
Current assignee: Hitachi Ltd
Priority date: 2021-01-08
Filing date: 2021-10-25
Publication date: 2022-07-15
Anticipated expiration: 2041-10-25
Also published as: JP2022107463A; CN114749494B; DE102021214275A1

Abstract

The invention provides a plant control device, a plant control method and a program, which predict the occurrence of mechanical operation abnormity of plant equipment to be controlled, properly operate a control operation terminal to prevent the occurrence of mechanical operation abnormity, and improve the control effect and operation efficiency. A first operation process in which a response speed to an 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 a plant device to be controlled. The first operation end executes first operation processing, and the second operation end executes second operation processing. A safe operation range determining unit is provided for determining a safe operation range of a first operation process of the first operation terminal from the performance of the first operation terminal. In the determination by the safe operation range determining unit, when the first operation process of the first operation terminal is not in the safe operation range, the instruction of the second operation process is corrected or changed so that the actual result position of the first operation process of the first operation terminal is moved to the actual result position where the mechanical work abnormality is not estimated.

Description

Plant control device, plant control method, and program

Technical Field

The invention relates to a plant control device, a plant control method and a program.

Background

In the past, when performing rolling mill control, which is one of plant control, fuzzy control and neuro-fuzzy control have been applied to shape control of a control plate in a fluctuating state. The fuzzy control is applied to shape control using a coolant, and the neuro-fuzzy control is applied to shape control of a sendzimir mill.

In shape control using the neural fuzzy control, as disclosed in patent document 1, a process of obtaining a difference between a result shape pattern detected by a shape detector and a target shape pattern and a similarity ratio with a preset reference shape pattern is performed. In the shape control to which the neuro-fuzzy control is applied, the control output amount for the operation end is obtained by the control rule expressed by the operation amount of the control operation end for the preset reference shape pattern based on the obtained similarity ratio.

The shape control has a plurality of control operation ends, and the control is performed by a difference in characteristics of these plurality of control operation ends. The shape is a wave state of the board in the board width direction, and the control operation end can change the shape of a specific region in the board width direction. For example, the AS-U roller can change the shape near the saddle position of operation, and the intermediate roller displacement can change the shape of the plate end. When the shape control is performed, the control operation ends are combined to operate so as to suppress the shape deviation according to the actual shape.

When rolling is performed in a rolling mill, a material to be rolled and rolls of the rolling mill need to be cooled (hereinafter referred to as coolant) for lubrication and cooling of heat generated by rolling. The coolant becomes an operation end of shape control, and by adjusting the amount of coolant sprayed in the plate width direction, the shape can be changed over the entire area in the plate width direction. In the 6-stage rolling mill, as shown in patent document 2, a coolant injection amount adjusting mechanism is provided in the plate width direction, and shape control is performed by changing the injection amount using the actual shape. However, in the sendzimir mill, the rolls of the mill are immersed in the coolant during rolling, and the coolant takes time to displace AS-U and the intermediate rolls before the coolant exerts its effect on the shape. Further, since the adjustment of the coolant injection amount cannot be automatically performed, it is also considered that the adjustment needs to be performed by an operator, such as the operation of the flow rate adjustment valve. In such a case, the adjustment can be performed only before the start of rolling.

In rolling in a rolling mill, a mechanical work abnormality may occur in which a rolled material is broken. The breakage of the rolled material is often caused by the rolled material, but the rolled material may be broken by bending. The bending of the rolled material means that the rolled material is deviated to one side of the rolling mill, and the rolling is usually performed in the center of the rolling mill.

It is envisioned that such bending occurs due to the position of the AS-U roller or intermediate roller shift. In the shape control, the AS-U and the intermediate roll shift are operated to maintain the shape of the material to be rolled in a target shape, but AS a result, the mechanical state may be a state in which the material to be rolled is easily bent.

Conventionally, a general rolling mill such as a 4-stage rolling mill or a 6-stage rolling mill has an operation unit for changing a coolant injection amount in a plate width direction in addition to a bending machine or a leveler as a mechanical operation unit, and is used for shape control. Unlike the sendzimir mill, in a normal rolling mill, the rolls of the rolling mill are not immersed in the coolant, and the effect on the shape of the coolant can be obtained in the same time period as the mechanical operation means. Therefore, shape control in a general rolling mill treats the mechanical operation unit and the coolant equally, and uses the coolant as a control operation end. In this case, since the coolant has an effect over the entire area in the plate width direction, the actual position of the machine operation unit often differs even if the actual shape of the rolled material is the same, in competition with the machine operation unit.

Fig. 15 shows a schematic configuration of a control device of a conventional sendzimir rolling mill.

First, the arithmetic unit 901 calculates a difference between the target shape d1 and the actual shape d2 of the rolled material obtained by the rolling mill 990, and supplies the difference to the first shape control unit 902 and the second shape control unit 903. The first shape control portion 902 controls a machine operation end 904 generated as a machine operation portion. The second shape control portion 903 controls a coolant operation end 905 that changes the coolant injection amount.

The rolling mill 990 performs the mechanical operation processing by the mechanical operation end 904 and the operation processing by the coolant injection amount by the coolant operation end 905 to perform the rolling processing of the rolled material, and obtains the shape achievement d2 and the rolling achievement d3 of the rolled material. In this case, in the machining operation performed by the machining operation end 904, the shape of the material to be rolled is changed with relatively high speed response by controlling the operation amount. On the other hand, in the operation processing of the coolant injection amount by the coolant operation terminal 905, even if the control of the operation amount is performed, the response is lower speed than the machine operation processing.

In the case of the configuration shown in fig. 15, as already described, the mechanical operation processing by the mechanical operation terminal 904 competes with the operation processing of the coolant injection amount by the coolant operation terminal 905. At this time, even if the shape actual results d2 are the same, the mechanical operation amounts of the mechanical operation ends 904 are not necessarily the same. Further, the response speed of the mechanical operation processing by the mechanical operation terminal 904 and the operation processing of the coolant ejection amount by the coolant operation terminal 905 are different, and the range of the effect reaching the board width direction is different in each operation processing. Therefore, there is a problem that it is difficult to appropriately control both the mechanical operation processing by the mechanical operation terminal 904 and the operation processing of the coolant injection amount by the coolant operation terminal 905. For example, in a state close to the upper limit of the operation range of the machine operation end 904 which responds at a high speed, the shape achievement d2 and the rolling achievement d3 may not be stably controlled, and vibrations may occur, and the rolling mill 990 which is a plant facility to be controlled may not be stably operated.

As a conventional technique for appropriately performing such shape control of the sendzimir mill, there is a technique of learning and controlling the relationship between the actual shape deviation of the material to be rolled and the control operation end operation amount by using machine learning from actual result data, as described in patent document 3, for example. In the technique described in patent document 3, a control output is output based on the shape deviation, and shape control of the operation control end is performed.

Documents of the prior art

Patent document

Patent document 1: japanese patent No. 2804161

Patent document 2: japanese patent No. 2515028

Patent document 3: japanese patent laid-open publication No. 2018-005544

Disclosure of Invention

Problems to be solved by the invention

The technique described in patent document 3 executes shape control by learning a control operation method for shape deviation, and does not consider a control operation end position. When actual control is performed, the operation range is limited according to the mechanical condition of the control operation terminal, but the control output to the control operation terminal is stopped, and if possible, operation is performed only by the other control operation terminal.

Further, in the case where the time until the coolant as the shape control operation end affects the shape is longer than that of the machine operation end like the sendzimir mill, even if the operation command of the coolant is output in the same manner as the machine operation end as in the conventional case, the shape control by the coolant cannot be effectively performed by the machine operation end control shape in which the effect on the shape is transmitted in a short time.

When rolling is performed by a rolling mill, since a mechanical operation abnormality such as a plate breakage occurs depending on the characteristics of a material to be rolled, a rolling state, and an actual position of a machine operation end controlled in shape, it is required to limit the actual position of the machine operation end. However, when a mechanical operation end and a coolant are used as an operation end for shape control, it is extremely difficult to limit the actual position of the mechanical operation end.

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

In the description so far, the problem of the shape control of the sendzimir mill has been described, but in the case where the control operation with high responsiveness and the control operation with low responsiveness are simultaneously performed by the various plant control apparatuses, the same problem arises when both the control operations are simultaneously appropriately performed.

An object of the present invention is to provide a plant control device, a plant control method, and a program that can improve the control effect and the operation efficiency by predicting the occurrence of a mechanical operation abnormality in a plant to be controlled and appropriately operating a control operation terminal so as not to cause the mechanical operation abnormality.

Means for solving the problems

In order to solve the above problem, for example, the structure described in the claim is adopted.

The present application includes a plurality of means for solving the above-described problems, and an example of the means is a plant control device for performing, on a plant to be controlled, a first operation process in which a response speed to an 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, the plant control device including:

a first control unit that acquires a target state quantity of a plant device to be controlled and instructs a first operation process;

a second control unit that acquires a target state quantity of the plant equipment to be controlled and instructs a second operation process;

a first operation terminal that executes a first operation process of a plant device to be controlled by an instruction from a first control unit;

a second operation terminal for executing a second operation process of the plant equipment to be controlled by an instruction from the second control unit;

a safe operation range determination unit that determines a safe operation range of the first operation process of the first operation terminal based on the performance of the first operation terminal; and

and a third control unit that corrects or changes the instruction of the second operation processing by the second control unit when the first operation processing by the first operation terminal is not within the safe operation range in the determination by the safe operation range determination unit, and moves the actual result position of the first operation processing by the first operation terminal to an actual result position where the mechanical work abnormality is not estimated to occur.

Effects of the invention

According to the present invention, the operation state of the plant equipment to be controlled can be appropriately controlled, and the actual position of the operation end which is abnormal in the machine operation can be suppressed. As a result, it is possible to expect improvement in control accuracy of plant equipment to be controlled, improvement in operation efficiency, and suppression of occurrence of mechanical operation abnormality.

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

Drawings

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

Fig. 2 is a block diagram showing a configuration example in a case where the plant control device according to the embodiment of the present invention is applied to a rolling mill.

Fig. 3 is a structural view showing an example of the sendzimir rolling mill.

Fig. 4 is a block diagram showing an example of a rolling facility of a single stand rolling mill.

Fig. 5 is a diagram showing an outline of a machine operation end according to an example of the embodiment of the present invention.

Fig. 6 is a block diagram showing a configuration example of the safe operation range determining unit according to an example of the embodiment of the present invention.

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

Fig. 8 is a diagram showing an example of the configuration of the neural network management table according to the 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 mechanical operation end position suppression control unit according to an example of the embodiment of the present invention.

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

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

Fig. 13 is a diagram showing an operation of the coolant operation terminal control output selecting unit according to the example of the embodiment of the present invention.

Fig. 14 is a block diagram showing an example of a hardware configuration in the case where a computing means is used as a plant control device according to an example of the embodiment of the present invention.

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

Description of the reference numerals

11 … shape detection preprocessing unit, 12 … pattern recognition unit, 13 … control arithmetic unit, 14 … shape detector, 50 … control device, 100 … plant equipment control device (computer), 101 … arithmetic unit, 102 … third control unit, 103 … high-speed operation end, 104 … low-speed operation end, 105 … safe operation range determination unit, 110 … control unit, 111 … first control unit, 112 … second control unit, 190 … control target plant equipment, 201 … arithmetic unit, 202 … mechanical operation end position suppression control unit, 203 … mechanical operation end, 204 … coolant operation end, 205 … mechanical operation end safe operation range determination unit, 210 … shape control unit, 211 … first shape control unit, 212 … second shape control unit, 300 … rolled material, 301 TR 301 …, 302 … feeding side tension roll reel (feeding side TR), 303 … feeding side tension reel (feeding side TR), … feeding side tension reel (feeding side) 303, 304 … grinding speed control part, 305 … feeding side TR control part, 306 … feeding side tension reel control part, 307 … nip control part, 308 … feeding side tension meter, 309 … feeding side tension meter, 310 … rolling speed setting part, 311 … feeding side tension setting part, 312 … feeding side tension setting part, 313 … feeding side tension control part, 314 … feeding side tension control part, 315 … feeding side tension current transformation part, 316 … feeding side tension current transformation part, … feeding side thickness meter, 318 … feeding side thickness control part, 497319 8 nip setting part, 401 … work roll, 402 … first intermediate roll, 403 … second intermediate roll, … AS-U roll, … dividing roll, 406 … saddle, 685501 input data generation part, 502 … neural network, 503 … neural network learning control part, 504 neural network … selection part, … data generation part, … supervision part, 506 … machine work abnormality determination unit, 511 … learning data database, 512 … control rule database, 610 … machine operation end position abnormality region determination unit, 611 … machine operation end position abnormality region 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 operation unit, 622 … coolant operation end control output selection unit, 623 … coolant control rule database, 631 … database search unit, 632 … output synthesis unit, 901 … arithmetic unit, 902 … first shape control unit, 903 … second shape control unit, 904 …

machine operation end

905, 905 … coolant operation end, 990 … rolling mill 990, 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 actual result, d23 … shape performance, d24 … rolling performance, d25 … machine operation end safety operation range, d26 … machine operation abnormality evaluation value, d27 … performance position abnormality region operation end judgment value, d28 … abnormality suppression output, 29 … shape control output, d30 … coolant operation output, d31 … estimated position, d32 … machine operation abnormality judgment value.

Detailed Description

A plant control device according to an example of an embodiment of the present invention (hereinafter referred to as "the present example") will be described below with reference to fig. 1 to 13.

[ Overall Structure of plant control device ]

Fig. 1 shows an example of the overall configuration of the plant control device of this example.

The plant control apparatus shown in fig. 1 controls a plant 190 to be controlled, and executes an operation process by a high-speed operation side (first operation side) 103 and an operation process by a low-speed operation side (second operation side) 104 as control of the plant 190 to be controlled.

The plant control apparatus of this example acquires the first state quantity target d11, and acquires the difference from the first state quantity d12 by the arithmetic unit 101. The first state quantity d12 is obtained from the control target plant 190 as a result of the operation processing of the high-speed operation side 103 and the low-speed operation side 104. The second state quantity d13 is obtained as a result of the operation processing of the high-speed operation side 103, the low-speed operation side 104, and the other operation side applied to the plant 190 to be controlled.

The control unit 110 of the plant control apparatus 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, and controls 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, corrected or changed as necessary, and then supplied to the low speed operation terminal 104.

The plant control apparatus of the present example includes a safe operation range determination unit 105. The safe operation range determining unit 105 acquires the operation result of the high-speed operation terminal 103, determines whether or not the acquired operation result is sufficient within the safe operation range, and supplies data of the safe operation range d14, which is the determination result, to the third control unit 102.

Then, the safe operation range determining unit 105 acquires the first state quantity d12 and the second state quantity d13 of the controlled plant 190. Then, the safe operation range determining unit 105 refers to the first state quantity d12 and the second state quantity d13, and determines whether or not the current operation performance of the high-speed operation terminal 103 is sufficient in the safe operation range.

Here, the safe operation range determining unit 105 detects occurrence of a machine operation abnormality, learns the first state quantity d12 and the second state quantity d13 at that time, and the actual performance position of the high-speed operation end 103, and determines the safe operation range d14 which is an operable range so that no machine operation abnormality occurs at the high-speed operation end 103. Since the machine operation abnormality is not a phenomenon that frequently occurs, it is preferable that the safe operation range determining unit 105 continuously acquire actual performance data and perform learning using machine learning or the like to obtain the safe operation range d 14.

Then, the safe operation range determining section 105 supplies the data of the determined safe operation range d14 to the third control section 102.

When it is determined from the data of the safe operation range d14 that there is a margin in the safe operation range, the third control unit 102 directly supplies the control output of the second control unit 112 to the low-speed operation terminal 104. On the other hand, when it is determined from the data of the safe operation range d14 that there is no margin in the safe operation range, the third control unit 102 corrects or changes the control output of the second control unit 112 and supplies the corrected control output to the low-speed operation terminal 104.

The output of the arithmetic unit 101, the operation result of the high-speed operation 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 pieces of information.

According to the plant control device having the configuration shown in fig. 1, the high-speed operation end 103 can be operated efficiently within a range in which no abnormality in the mechanical operation occurs, and improvement of the control accuracy can be expected in addition to improvement of the operation efficiency.

[ Overall Structure in case of application to control device for Sendzimir Rolling Mill ]

Next, the overall configuration of the plant control device of the present example applied to the sendzimir rolling mill will be described.

Fig. 2 shows the structure of the plant control device of this example when applied to a sendzimir rolling mill.

The plant control apparatus shown in fig. 2 acquires the target shape d21 of the rolled material, and acquires the difference from the actual shape result d23 after rolling by the arithmetic unit 201.

In the plant control apparatus of this example, as the control of the rolling mill 301, the operation process by the machine operation terminal 203 and the operation process by the coolant operation terminal 204 are executed. The operation process performed by the machine operation end 203 is a process of mechanically changing a roll gap or the like to be subjected to a rolling process, and the response appearing in the actual shape result d23 of the rolled material becomes high speed. On the other hand, the operation processing performed by the coolant operation terminal 204 is processing for changing the coolant injection amount, and the response appearing in the rolling result d24 of the rolled material becomes a lower speed than the operation of the machine operation terminal 203.

The shape control unit 210 of the plant equipment control device has a first shape control portion 211 that controls the operation process of the machine operation terminal 203 and a second shape control portion 212 that controls 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 have the target shape d 21. The target shape d21 is a shape set in advance in accordance with the characteristics of the material to be rolled.

The control output of the first shape control section 211 is directly supplied to the machine operation terminal 203, and controls the operation process of the machine operation terminal 203.

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

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

The plant control apparatus of the present example includes a machine operation end safe operation range determination unit 205. The machine operation end safety operation range determining unit 205 acquires a machine operation end position actual result d22, which is an operation actual result of the machine operation end 203, and determines whether or not the acquired machine operation end position actual result d22 is within the safety operation range. Then, the machine operation end safe operation range determining section 205 supplies the data of the machine operation end safe operation range d25 as the determination result to the machine operation end position suppression control section 202.

The machine operation end position suppression control unit 202 acquires the shape actual result d23 and the rolling actual result d24 of the rolling mill 301. Then, the machine operation end safety operation range determination unit 205 refers to the shape achievement d23 and the rolling achievement d24, and determines whether or not the obtained machine operation end position achievement d22 has a margin in the safety operation range.

The machine operation end safety operation range determination unit 205 detects the occurrence of the machine operation abnormality, and learns the shape performance d23, the rolling performance d24, and the machine operation end position performance d22 at that time. By this learning, the machine operation end safe operation range determination unit 205 determines the machine operation end safe operation range d25, which is an operable range, so that the machine operation end 203 does not cause a machine work abnormality. Here, the machine operation end safe operation range determination unit 205 continuously collects actual performance data, and performs learning using machine learning or the like to obtain the machine operation end safe operation range d 25.

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

The detailed configuration of the machine operation end safe operation range determining unit 205 for performing the learning of the abnormality of the machine work will be described later with reference to fig. 6.

The mechanical operation end position suppression control portion 202 directly supplies the control output of the second shape control portion 212 to the coolant operation end 204 when it is determined that there is a margin in the safe operation range based on the data of the mechanical operation end safe operation range d 25. On the other hand, when it is determined from the data of the machine operation end safe operation range d25 that the state is not in which there is no margin in the safe operation range, the machine operation end position suppression control portion 202 corrects or changes the control output of the second shape control portion 212 and supplies the corrected or changed control output to the coolant operation end 204.

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

[ Structure of Sendzimir Rolling Mill ]

Here, a description will be given of a structural example of the sendzimir rolling mill.

Fig. 3 shows a schematic configuration in the case of performing shape control in a sendzimir mill.

The sendzimir mill detects the actual shape of the rolled material after rolling by the shape detector 14. The actual shape detected by the shape detector 14 is subjected to preprocessing of pattern recognition by the shape detection preprocessing unit 11 of the control device 50, and then the pattern recognition unit 12 calculates which of the reference shape patterns set in advance is the closest to the actual shape. Then, based on the calculated reference shape pattern, the control arithmetic unit 13 determines the operation end and the operation amount to be operated, and executes a process of controlling the sendzimir mill by using the operation end and the operation amount to be operated.

Fig. 4 shows an example of a rolling facility of a single stand rolling mill. The sendzimir mill is one type of single stand mill.

The rolling facility shown in fig. 4 is composed of a rolling mill 301, a feed-side tension reel (hereinafter referred to as "TR") 302, and a delivery-side TR303, and a rolled material 300 pulled out from the feed-side TR302 passes through the rolling mill 301 and is wound around the delivery-side TR 303.

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

A grinding speed control section 304 for adjusting the rolling speed and a nip control section 307 for adjusting the nip of the rolling mill 301 are provided in the rolling mill 301. In addition, the feeding side TR302 and the feeding side TR303 are provided with a feeding side TR control section 305 and a feeding side TR control section 306 for adjusting respective generated tensions.

The rolling process is performed by adjusting the upper and lower roll intervals of the rolling mill 301 by the nip control unit 307 to apply a pressure for flattening the rolled material 300, and by feeding the rolled material 300 to the feeding side by the grinding speed control unit 304. At this time, on the input side and the output side of the rolling mill 301, a process of applying tension to the rolled material 300 using the input side TR302 and the output side TR303 is also performed.

Important for the rolling operation is the plate thickness of the rolled material 300 to be a product (the plate thickness on the delivery side of the rolling mill), and the nip, the tension on the delivery side, and the tension on the delivery side are set in advance so that the rolled material 300 has a predetermined plate thickness.

The transmission-side tension current converting unit 315 obtains a current necessary for obtaining the set transmission-side tension by using the transmission-side tension set by the transmission-side tension setting unit 311, and supplies the current to the transmission side TR302 via the transmission-side TR control unit 305, thereby obtaining the transmission-side tension.

Similarly, the feeding-side tension current converting unit 316 obtains a current necessary for obtaining the set feeding-side tension by using the feeding-side tension set by the feeding-side tension setting unit 312, and supplies the current to the feeding-side TR303 via the feeding-side TR control unit 306, thereby obtaining the feeding-side tension.

The nip set by the nip setting section 319 is supplied to the nip control section 307, and the nip is set by the nip control section 307.

The rolling speed setting unit 310 determines the speed of the rolling mill 301 in accordance with an instruction from an operator of the rolling mill, and the milling speed control unit 304 sets the speed of the rolling mill 301.

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 actual tensions measured by these units match set tensions. A delivery-side plate thickness meter 317 is provided on the delivery side of the rolling mill 301, and a delivery-side plate thickness control section 318 performs control so that the actual plate thickness measured here matches the set plate thickness.

In addition to the above configuration, as shown in fig. 3, which has been described above, a shape detector 14 for detecting the shape of the material to be rolled 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 described above, the shape is the degree of fluctuation of the metal plate as the rolled material. Therefore, a target shape, which is a target shape, is set in advance according to workability in a next step of the rolling mill and efficiency of a rolling operation in the rolling mill. In general, since tension is applied to a material to be rolled, if a flaw such as a crack is present at a plate end portion, a crack is likely to be generated therefrom, and the material to be rolled may be broken in a plate width direction (plate fracture). Therefore, the plate end portion is often in a wavy state in order to prevent the tension from concentrating.

The fluctuation of the rolled material is not noticeable because it is actually a tension applied to the rolled material, and the tension distribution changes in the width direction of the plate without fluctuation in appearance.

Here, the shape detector 14 shown in fig. 3 measures the tension distribution in the plate width direction to estimate the fluctuation of the plate and detects the fluctuation as a shape actual result.

[ Structure and treatment of shape-controlled machine operation end ]

Fig. 5 (a) shows a structure in which a work process is performed by the machine work end 203 of the sendzimir mill. Fig. 5 shows a cross section of the rolled material 300 in the sheet width direction, and only the upper side structure of the rolled material 300 is shown, while the lower side structure is omitted.

In fig. 5, (b) and (c) show operation waveforms when the shape of the material 300 to be rolled 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 the material 300 to be rolled.

The first intermediate roll 402 is provided with a taper shape on the counter roll opposite to the vertical direction, and is displaced in the sheet width direction, thereby affecting the shape of the sheet end of the material 300 to be rolled.

AS-U roller 404 has a structure in which saddle 406 is interposed between a plurality of split rollers 405, and by changing the position of saddle 406 (the longitudinal position in fig. 5), the deflection of AS-U roller 404 can be changed in the sheet width direction.

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

Here, the operation waveforms shown in the lowermost stages of (b) and (c) in fig. 5 show changes in the sheet thickness distribution of the material 300 to be rolled when the saddle 406 or the first intermediate roll 402 is displaced. The shape change is opposite to the sheet thickness distribution.

The shape is a distribution of the degree of fluctuation in the sheet width direction, and a large fluctuation means elongation of the rolled material 300. This is because the material is equivalent to "the delivery side plate is thin", "the elongation of the rolled material at the thinned portion is large", and "the shape of the rolled material is large".

Regarding the mechanical work abnormality, the plate breakage of the rolled material 300 is a big problem. If a plate fracture occurs, the work roll 401 and the first intermediate roll 402 of the rolling mill are damaged by the rolled material 300 after the fracture. In some cases, the second intermediate roller 403 and the AS-U roller 404 may be damaged by the occurrence of sheet breakage. If such damage occurs, it is necessary to replace the rolls, and it takes time to remove the rolled material 300 remaining in the rolling mill, which extremely reduces the machine work efficiency.

Since the AS-U roller 404 is pressed against the second intermediate roller 403 so AS to press the split roller 405 with the saddle 406, the split roller 405 may not contact the second intermediate roller 403 depending on the position of the saddle 406. In this state, the force applied to the rolled material 300 from the work rolls 401 in the portion is rapidly reduced, the rolled material 300 is not stretched any more, and the tension applied to the rolled material 300 in the portion is increased.

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

The actual performance position of the occurrence of the mechanical work abnormality is not calculated from the mechanical structure, but the positional relationship between the rolling state such as the sheet thickness distribution in the sheet width direction of the rolled material 300, the sheet thickness on the feeding/feeding side, the tension, the rolling load, and the like, and the operation end of the other shape control machine is also changed, and therefore it is difficult to predict in advance.

Therefore, in the present example, the machine operator safety operation range determination unit 205 stores these conditions when the rolling abnormality occurs as the performance data, and compares the performance data with the performance data in the normal state to determine the performance position of the shape control machine operator where the rolling abnormality is likely to occur.

The machine-operator-side safe operation range determination unit 205 of this example determines the machine-operator-side safe operation range using machine learning. The actual result data during machine learning includes the rolling states such as the thickness, tension, and rolling load of the delivery/delivery side plate, and the actual result position of the machine operation end 203, and the supervision data includes rolling abnormality occurrence information.

As the rolling abnormality occurrence information, information of a plate break and an emergency stop of the rolling mill is used. The plate breakage can be determined by a reduction in the tension on the feed/discharge side, and the information of the operation switch operated by the operator in the case where the operation is stopped due to the occurrence of some abnormality in the rolled state is suddenly stopped. The information on the operation switches can be detected by a computer constituting a control device for controlling the rolling mill, and can be used as 1 of the performance information. The machine operator-side safe operation range determination unit 205 generates a neural network (n.n.) for determining whether or not a machine operation abnormality has occurred, using the actual result data and the supervision data.

[ Structure of determination section of safe operation range of mechanical operation terminal and Structure of neural network ]

Fig. 6 shows a configuration in a case where the machine operation end safe operation range determination unit 205 is realized by machine learning.

Fig. 7 shows a configuration of the neural network 502 provided in the machine operation end safe operation range determining unit 205.

As shown in fig. 7, the neural network 502 obtains a rolling result d24 and a machine operation end position result d22 from the input data generation unit 501 at the input end 502a, and outputs a machine work abnormality determination value d32 from the output end 502 b. The machine work abnormality determination value d32 is information on the occurrence of rolling abnormality, i.e., information on plate breakage and information on emergency stop. The neural network 502 performs learning based on a combination of these input data and output data.

The machine operation end safety operation range determination unit 205 shown in fig. 6 is explained, and the input data generation unit 501 collects the machine operation end position actual results d22 and the shape actual results d 23. The supervisory data generator 505 collects the machine work abnormality determination value d32 determined by the machine work abnormality determination unit 506. The data acquisition in the input data generation unit 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 1-group learning data is obtained for 1 operation cycle. The resulting learning data is sequentially stored in the learning data database 511.

The mechanical work abnormality determination unit 506 determines the presence or absence of mechanical work abnormality, i.e., plate breakage and an emergency stop of the rolling mill, based on the rolling result d 24. The machine work abnormality determination value d32 as a result of the determination is information of the board breakage and the emergency stop.

The rolling mill rolls various materials 300 to be rolled in accordance with the specifications to obtain products. Therefore, the rolling mill generally responds by changing the combination of the machine configuration, i.e., the gauge (diameter distribution in the plate width direction) of the work roll 401, the taper gauge of the first intermediate roll 402, and the split rolls 405 of the AS-U roll 404, in accordance with the gauge of the material 300 to be rolled. The rolled material 300 is different in sheet width and material quality. Therefore, the neural network 502 can be efficiently learned by differentiating the mechanical structure and the specification of the rolled material 300.

Therefore, the machine-side safe operation range determining unit 205 of the present example includes a plurality of types of neural networks 502, and includes a control rule database 512 and a neural network selecting unit 504 so as to be switchable for use.

Fig. 8 shows an example of the configuration of the control rule database 512.

As shown in fig. 8 (a), the control rule database 512 stores a plurality of neural networks that have been learned using learning data that is a combination of input data and supervisory data.

Then, the neural network learning control unit 503 specifies the neural network No. that needs to be learned. The neural network selecting unit 504 receives a specification of a neural network No. that requires learning by the neural network learning control unit 503, extracts the neural network from the control rule database 512, and sets the neural network as the neural network 502.

The neural network selecting unit 504 extracts the neural network of the corresponding neural network No. from the control rule database 512 in accordance with the rolling condition and the mechanical structure based on the current rolling performance d24, and sets the mechanical operation end position suppression control unit 202 as the control neural network d 33.

Fig. 8 (b) shows the structure of the neural network management table stored in the control rule database 512. The control tables are distinguished according to the sheet width (B1), the steel grade (B2), and the mechanical structure (a). As the board width (B1), for example, 4 divisions of 3 feet wide, m wide, 4 feet wide, and 5 feet wide are used. As the steel type (B2), about 10 divisions of steel types (1) to (10) were used. The section (a) is classified into (a1) and (a2) according to the length of the tapered portion, which is the tapered specification of the first intermediate roller 402, for example.

The table difference described above is an example, and needs to be set in accordance with the rolling facility and the type of material to be rolled.

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

The neural network learning control unit 503 associates learning data, which is a combination of input data and supervisory data shown in (a) of fig. 8, with the corresponding neural network No. and stores the learning data in the learning data database 511, in accordance with the neural network management table shown in (b) of fig. 8.

Fig. 9 shows an example of 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. in advance.

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

Machine learning requires a large number of sets of learning data, and if a certain degree (for example, 10000 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 section 503 writes back the neural network 502 as a learning result to the position of the neural network No. of the control rule database 512, thereby completing the learning.

The learned neural network 502 outputs a machine work abnormality determination value by inputting the rolling performance d24 and the machine operation end position performance d 22. Therefore, the neural network 502 can predict the occurrence of the mechanical work abnormality by giving the expected future shape actual result d23 and the mechanical operation end position actual result d22, and can search for the mechanical operation end safe operation range d 25.

[ Structure of mechanical operation end position suppression control section ]

Fig. 10 shows the structure of the machine operation end position suppression control unit 202.

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

The machine operation end position abnormality area determination unit 610 estimates the machine operation end 203 that predicts the occurrence of the machine work abnormality, using the neural network 502 described in fig. 7. The neural network 502 used here is the control neural network d33 received from the mechanical operation end safe operation range determining unit 205.

The mechanical operation end position abnormality suppression control unit 620 generates an operation command for the coolant operation end 204 based on the determination result of the mechanical operation end position abnormality region determination unit 610.

In the rolling operation, the shape actual result d23 of the rolling mill 301 changes from time to time, and the first shape control unit 211 for maintaining the rolling mill at the target shape d21 operates the machine operation end 203, and the machine operation end position actual result d22 also changes from time to time. The machine operation end position abnormality region search unit 611 included in the machine operation end position abnormality region determination unit 610 generates the input data of the neural network 502 by the input data generation unit 612, using the machine operation end position actual result d 22.

Fig. 11 shows a process performed by the machine operation end position abnormality region determination unit 610.

In the example of fig. 11, when the mechanical operation end 203 is of n types (n is an integer), the mechanical operation end position actual result d22 is as follows.

POS(k)，k＝1，2，...，n

The mechanical operating end 203 here is n kinds, for example, corresponding to the total value of the number of saddles 406 of the AS-U roller 404 and the number of first intermediate rollers 402 displaceable in the sheet width direction. In the example shown in fig. 5, since the number of saddles is 5 and the number of first intermediate rollers is 2, n is 7.

When the machine operation end 203 is operated by the first shape control unit 211, since the operation is performed with a constant amount for each control cycle as a limit, the machine operation end position abnormality region search unit 611 generates the estimated position of the machine operation end position actual result d22 of each machine operation end 203 as described below. Here, for example, the position actual result change amount Δ POS may be operated by a plurality of times of control, and 3 cases are considered, that is, a case where the position actual result does not change and a case where the actual result value changes in the positive and negative directions.

POS(k)，POS(k)±ΔPOS，k＝1，2，...、n

Thereby, the estimated position actual results of the respective machine operation terminals 203 can be generated 3ⁿOne (for example, 2187 in the case of n ═ 7). For example, when n is 7, the position actual result is estimated2187 species can be generated. The estimated position actual results are sequentially output to the input data generating unit 612.

The input data generator 612 generates input data to the neural network 502 from the rolling result d24 and the estimated position d31, and outputs the generated input data to the neural network 502.

The neural network 502 outputs a machine work abnormality determination value d32 shown in fig. 11 (d). The machine work abnormality determination value d32 is a value to be the degree of plate breakage and emergency stop, but here, the output data determination unit 613 receives the machine work abnormality determination value d32 output from the neural network 502, weights the degrees of the two values, adds them together, and sets them as the machine work abnormality evaluation value d 26. In general, an operator performs an emergency stop when a machine operation abnormality occurs, but the emergency stop is also performed when a sign of a plate fracture occurs. The sign of the sheet breakage here is, for example, bending of the rolled material 300.

When the plate fracture occurs without an emergency stop, the priority of suppressing the plate fracture without any sign is high. Thus, the weighting of the degree of plate fracture will be increased.

The machine operation end position abnormality region searching unit 611 stores the output estimated position d31 and the returned machine work abnormality evaluation value d26 in advance, and searches for an estimated value at which the machine work abnormality evaluation value d26 is the maximum. When the maximum value of the machine work abnormality evaluation value d26 exceeds a predetermined threshold value as a result of the search, the machine operation end position abnormality region search unit 611 outputs the actual performance position change amount at the estimated position d31 in this case as the actual performance position abnormality region operation end determination value d 27. In this case, the work abnormality evaluation value d26 is also included in the actual performance position abnormality region operating end determination value d27 as the maximum work abnormality evaluation value.

In the example described above, the mechanical operation end position abnormality region 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 3 types, but may generate the estimated position by another process. For example, the machine operation end position abnormality region search unit 611 finely controls the amount of change in the estimated position d 31. The machine operation end position abnormality region search unit 611 may change the position of the machine operation end position abnormality region in accordance with the situation without performing a search or the like in a direction in which the machine operation abnormality is apparently not generated. Here, the direction in which the machine operation abnormality is apparently not generated means, for example, a case in which the movement is considered in the center direction of the actual performance position of the machine operation end.

The mechanical operation end position abnormality suppression control unit 620 generates a control output to the coolant operation end 204 based on the actual position abnormality region operation end determination value d27, which is an output of the mechanical operation end position abnormality region determination unit 610, and a control command to the coolant operation end 204 by the second shape control unit 212.

If it is determined that the machine operation end position actual result d22 does not cause the machine operation abnormality even if the control is changed, the normal operation using the coolant operation end 204 by the second shape control portion 212 can be performed. When the machine work abnormality evaluation value d26 is not too large, the output may be such that the abnormality suppression output d28 for suppressing the machine work abnormality is combined with the control output of the second shape control unit 212. Of course, in the case where the machine work abnormality evaluation value d26 is large, the abnormality suppression output d28 is preferentially output to the coolant operation terminal 204.

The coolant control rule database 623 predetermines the correspondence between each machine operation terminal 203(k) and the affected coolant operation terminal 204. The correspondence may be obtained by actually operating the machine operation terminal 203 and the coolant operation terminal 204 during the rolling operation, or may be obtained from actual result data by machine learning. Here, a case where the correspondence is found from the result of the actual operation and registered in the coolant control rule database 623 is considered.

[ Structure and operation of the Coolant operation terminal control output operation section ]

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

In the coolant control rule database 623 (fig. 10), there is registered a required coolant flow rate change amount that can obtain the same effect as operating each machine operation terminal 203 (k). The database retrieval unit 631 shown in fig. 12 (a) extracts the coolant flow rate change demand corresponding to the actual performance position change amount of the machine operation end 203(k) where the machine work abnormality has occurred, based on the actual performance position abnormality region operation end determination value d27 obtained by the machine operation end position abnormality region determination unit 610.

Then, the output combining unit 632 adds the extracted required coolant flow rate change amounts for each machine operation end 203(k), and obtains the abnormality suppression output d 28.

For example, when the actual result and the estimated position shown in (a) and (b) in fig. 11 have obtained the actual result position abnormality region operation terminal determination value d27 shown in (d) in fig. 11, the abnormality suppression output d28 shown in (b) in fig. 12 is obtained.

Since the coolant control end 204 performs lubrication and cooling necessary for the rolling operation, 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 in which the machine operation abnormality occurs can be obtained.

[ output selection processing in the coolant operation side control output selection portion ]

Fig. 13 shows the output selection process performed by the coolant operation terminal control output selection section 622.

The coolant operation end control output selecting unit 622 selects and outputs the abnormality suppressing output d28 shown in fig. 10 and the shape control output d29 of the second shape control unit 212 in accordance with the magnitude of the maximum value of the mechanical work abnormality evaluation ((d) in fig. 11) within the actual performance position abnormality region operation end determination value d 27. The output selected or synthesized by the coolant operation terminal control output selection portion 622 is supplied as the coolant operation output d30 to the coolant operation terminal 204.

In the case where the maximum value of the evaluation of the mechanical work abnormality shown in (d) of fig. 11 is small, even if the shape control is directly performed, the possibility of occurrence of the mechanical work abnormality is low, and therefore, the coolant operation terminal control output selection portion 622 supplies the shape control output d29 to the coolant operation terminal 204 as it is as the coolant operation output d 30. That is, the coolant operation output d30 is the shape control output d 29.

On the other hand, when the maximum value of the evaluation of the machine work abnormality is large, the coolant operation end control output selecting unit 622 determines that there is a high possibility of occurrence of the machine work abnormality. At this time, as shown in fig. 13 (b), the abnormality suppression output d28 is generated, and the coolant operation end control output selecting unit 622 sets the coolant operation output d30 as shown in fig. 13 (a) so that the effect of the abnormality suppression output d28 is maximized within the maximum value and the minimum value of the coolant flow rate.

In addition, when the maximum value of the mechanical work abnormality evaluation is not so large, the coolant operation end control output selection unit 622 adds and outputs the shape control output d29 and the abnormality suppression output d28 as shown in fig. 13 (c). 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 the mode shown in fig. 11 (d) is obtained.

Here, the determination of the maximum value of the mechanical work abnormality evaluation as being one of large, not so large, and small is made using a threshold value set in advance in the coolant operation end control output selection unit 622. In addition, the coolant operation end control output selecting section 622 may always add and output the shape control output d29 and the abnormality suppression output d 28. However, in this case, the added abnormality suppression output d28 is not made so large.

In addition, when the addition is performed in the coolant operation end control output selector 622, the weighted addition may be performed without performing the simple addition, and the weighting may be changed according to the maximum value of the mechanical work abnormality evaluation.

As described above, according to the plant control device of the present example, it is possible to prevent the machine operation abnormality caused by the machine operation end position actual result d22 of the machine operation end 203 and to perform the good shape control.

[ modified examples ]

The present invention is not limited to the above-described embodiment, and various modifications are possible. For example, the above-described embodiments are examples described in detail to explain the present invention easily and understandably, and are not limited to having all the configurations described.

For example, in the example of the above-described embodiment, the machine-operation-end safe operation range determination unit 205 is realized by machine learning, but the machine-operation-end safe operation range determination unit 205 may be realized by expressing the safety range by a mathematical expression based on the experience of the operator. Alternatively, the rolling state database when the mechanical work abnormality occurs may be made into a database, and the machine operation end safe operation range determining unit 205 may be realized by determining whether or not there is a corresponding situation.

The machine operator-side safe operation range determination unit 205 may generate a numerical model or a symbolic logical model based on the knowledge of the operator or the operator technician and use the model in machine learning.

In the example of the above embodiment, the machine operation end position abnormality suppression control unit 620 stores and uses the result obtained by an experiment or the like in the coolant control rule database 623. In contrast, the machine-operated-end-position-abnormality suppression control unit 620 may generate a rule base from actual-result data using machine learning.

In the above-described embodiment, the shape control of the rolling mill is targeted, but the present invention can also be applied to general plant control.

In the block diagrams of fig. 1 and the like, the control lines and the information lines are only portions that are considered necessary for the description, and not necessarily all the control lines and the information lines on the product are shown. In practice, it is also possible to consider almost all structures connected to each other.

Further, although the processing units such as the control unit described in the above embodiment example may be each configured by dedicated hardware, the functions of the processing units described in the above embodiment example may be realized by installing a program (application) in a computer.

Fig. 14 shows an example of a hardware configuration in the case where the plant control device is a computer.

The plant control apparatus (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, which are connected to a bus, respectively. The plant control apparatus 100 includes a nonvolatile memory 100d, a network interface 100e, an input/output device 100f, and a display device 100 g.

The CPU100a is an arithmetic processing unit that reads and executes program codes of software that realizes functions performed by the plant control apparatus 100 from the ROM100 b.

Variables, parameters, and the like generated during the arithmetic processing are temporarily written in the RAM100 c.

The nonvolatile memory 100d uses a large-capacity information storage medium such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). A program (plant control program) for executing the processing function performed by the plant control apparatus 100 is recorded in the nonvolatile memory 100 d. In addition, data necessary for machine learning is recorded in the nonvolatile memory 100 d.

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

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

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

The information of the program that realizes each processing function performed by the plant control apparatus 100 can be stored in a recording medium such as a semiconductor memory, an IC card, an SD card, or an optical disk, in addition to a nonvolatile memory such as an HDD or an SSD.

In addition, when part or all of the processing units of the plant control device are configured by hardware, an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit) may be used.

Claims

1. A plant control apparatus for performing a first operation process in which a response speed to an 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 on a plant to be controlled,

the plant control device includes:

a first control unit that acquires a target state quantity of the plant device to be controlled and instructs the first operation process;

a second control unit that acquires a target state quantity of the plant device to be controlled and instructs the second operation process;

a first operation terminal that executes the first operation process of the plant equipment to be controlled, in response to an instruction from the first control unit;

a second operation terminal that executes the second operation process of the plant equipment to be controlled, in response to an instruction from the second control unit;

a safe operation range determination unit configured to determine a safe operation range of the first operation process performed by the first operation terminal, based on an actual result of the first operation terminal;

and a third control unit that corrects or changes an instruction of the second operation process by the second control unit when the first operation process by the first operation terminal is not within the safe operation range in the determination by the safe operation range determination unit, and moves an actual result position of the first operation process by the first operation terminal to an actual result position where the mechanical work abnormality is not estimated.

2. The plant control apparatus according to claim 1,

a control time response is faster than a control time response of the second operation processing with respect to the first operation processing by the first operation side, and an influence on a control object state quantity of the control object plant is limited,

in the second operation process performed by the second operation terminal, the control time response is lower in speed 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 equipment.

3. The plant control apparatus according to claim 1,

the safe operation range determination unit recognizes the occurrence of the mechanical operation abnormality by using the performance data of the plant equipment to be controlled, learns the relationship between the performance data and the mechanical operation abnormality by using the performance data at the time of the occurrence of the mechanical operation abnormality as the supervision data, and determines the safe operation range.

4. The plant control apparatus according to claim 3,

the relation between the actual performance data and the machine work abnormality is obtained by machine learning based on the collected actual performance data.

5. The plant control apparatus according to any one of claims 1 to 4,

the control object plant device is a rolling mill,

the first operation processing is mechanical shape operation processing for changing the shape by a mechanical configuration,

the second operation processing is coolant shape operation processing for changing the shape by changing the ejection amount of the coolant in the plate width direction,

a safe operation range determination unit configured to determine a safe operation range of the first operation process based on a performance value of a machine position of the first operation end at which the machine operation abnormality does not occur,

when the safe operation range determining unit estimates that a mechanical operation abnormality has occurred, the third control unit changes the control output of the coolant shape control at the second operation end to an output of the coolant shape control that does not cause a mechanical operation abnormality, thereby moving the actual position of the mechanical shape operation processing performed by the first operation end to an actual position at which the mechanical operation abnormality has not been estimated.

6. A plant control method for performing a first operation process in which a response speed to an operation is a predetermined response speed and a second operation process in which the response speed to the operation is slower than that of the first operation process on a plant to be controlled by an arithmetic processing unit through arithmetic processing,

the plant equipment control method includes:

a first control step of acquiring a target state quantity of the plant equipment to be controlled by the arithmetic processing unit and instructing the first operation process;

a second control step of acquiring a target state quantity of the plant equipment to be controlled by the arithmetic processing unit and instructing the second operation process;

a first operation execution step of executing the first operation process of the plant equipment to be controlled by the arithmetic processing unit in response to an instruction of the first control step;

a second operation execution step of executing the second operation process of the plant equipment to be controlled by the arithmetic processing unit in response to an instruction of the second control step;

a safe operation range determination step of determining a safe operation range of the first operation processing performed by the first operation execution step, based on an actual result of the first operation processing;

a third control step of, when it is determined in the safety operation range determining step that the first operation process in the first operation executing step is not within the safety operation range, correcting or changing an instruction of the second operation process in the second control step to move an actual result position of the first operation process in the first operation executing step to an actual result position at which the mechanical work abnormality is not estimated.

7. A program for causing a computer to execute, on a plant to be controlled, a first operation process in which a response speed to an 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,

the program causes the computer to execute:

a first control step of acquiring a target state quantity of the plant equipment to be controlled and instructing the first operation process;

a second control step of acquiring a target state quantity of the plant equipment to be controlled and instructing the second operation process;

a first operation execution step of executing the first operation process of the control target plant equipment by an instruction of the first control step;

a second operation execution step of executing the second operation process of the control target plant equipment in response to an instruction of the second control step;

a third control step of, when it is determined in the safety operation range determining step that the first operation process in the first operation executing step is not in the safety operation range, correcting or changing an instruction of the second operation process in the second control step so as to move an actual result position of the first operation process in the first operation executing step to an actual result position at which the mechanical work abnormality is not estimated to occur.