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

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

Factory equipment control device, factory equipment control method, and program

technical field

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

Background technique

When performing rolling mill control, which is one of plant equipment controls, fuzzy control and neuro-fuzzy control have conventionally been applied to shape control of the wave state of the control panel. Fuzzy control is applied to shape control using coolant, and neuro-fuzzy control is applied to shape control of Sendzimir mill.

In the shape control to which the neuro-fuzzy control is applied, as shown in Patent Document 1, the difference between the actual shape pattern detected by the shape detector and the target shape pattern and the similarity ratio with the preset reference shape pattern are obtained. deal with. Furthermore, in the shape control to which the neuro-fuzzy control is applied, based on the obtained similarity ratio, the control for the operator is obtained by the control rule expressed by the control operator's operation amount for the preset reference shape pattern. output.

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

When rolling in a rolling mill, a cooling material (hereinafter referred to as a coolant) is required for lubrication between the material to be rolled and the rolls of the rolling mill and for cooling of heat generated by rolling. This cooling material serves as an operation end for shape control, and by adjusting the injection amount of the coolant 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 adjustment mechanism is provided in the plate width direction, and shape control is performed by changing the injection amount using the actual shape. However, in a Sendzimir mill, the rolls of the mill are immersed in a coolant during rolling, and the coolant takes time compared to AS-U and intermediate roll shift before the coolant has an effect on the shape. 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 of the flow rate adjustment valve. In such a case, adjustment can be performed only before the start of rolling.

During the implementation of rolling in a rolling mill, a mechanical operation abnormality in which the material to be rolled is broken may occur. The fracture of the material to be rolled often occurs because of the material to be rolled, but the material to be rolled also breaks due to bending. The bending of the material to be rolled means that the material to be rolled is displaced to one side of the rolling mill, and rolling is usually performed at the center of the rolling mill.

Such buckling is expected to occur due to the displaced position of the AS-U rolls or intermediate rolls. In shape control, AS-U and intermediate roll shift are operated in order to maintain the shape of the material to be rolled at the target shape, but as a result, the mechanical state may become a state in which bending of the material to be rolled is likely to occur.

Conventionally, in ordinary rolling mills such as 4-stage rolling mills and 6-stage rolling mills, in addition to a bending machine and a leveling machine as a mechanical operating part, there is also an operating part for changing the coolant injection amount in the plate width direction. 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 as the mechanical operation unit. Therefore, in the shape control in a normal rolling mill, the mechanical operation unit and the coolant are treated equally, and the coolant is used as the 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 part is often different even if the actual shape of the material to be rolled is the same, in competition with the machine operation part.

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

First, the calculator 901 obtains the difference between the target shape d1 and the actual shape record d2 of the material to be rolled 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 part 902 controls a mechanical operation end 904 which is a mechanical operation part. The second shape control unit 903 controls the coolant operation end 905 for changing the coolant injection amount.

The rolling mill 990 executes the mechanical operation process based on the mechanical operation end 904 and the operation process based on the coolant injection amount of the coolant operation end 905, performs the rolling process of the material to be rolled, and obtains the shape record d2 and the rolling process of the material to be rolled. Actual performance d3. In this case, in the machine operation process performed by the machine operation end 904, the shape of the material to be rolled 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 control of the operation amount is performed, the response is slower than that of the mechanical operation process.

In the case of the structure shown in FIG. 15 , as already explained, the mechanical operation processing by the mechanical operation end 904 competes with the operation processing of the coolant injection amount by the coolant operation end 905 . At this time, even if the actual shape performance d2 is the same, the mechanical operation amount of the mechanical operation end 904 is not necessarily the same. Furthermore, the response speed of the mechanical operation processing by the mechanical operation end 904 and the operation processing of the coolant injection amount by the coolant operation end 905 are different, and the range of the effect in the plate width direction is different for each operation processing. Therefore, there is a problem that it is difficult to appropriately control both the mechanical operation processing by the mechanical operation end 904 and the operation processing of the coolant injection amount by the coolant operation end 905 . For example, in a state close to the upper limit of the operating range of the mechanical operation end 904 that responds at a high speed, the actual shape performance d2 and the actual rolling performance d3 cannot be stably controlled, and vibration occurs, and the rolling mill 990 that is the control target factory equipment cannot be stably operated. action.

As a prior art for appropriately performing shape control of such a Sendzimir mill, for example, as described in Patent Document 3, there is a method of learning the actual shape deviation and control operation edge of the material to be rolled using machine learning based on actual performance data. A technique for controlling the relationship between the operating quantities. In the technique described in Patent Document 3, the control output is output based on the shape deviation, and the 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 Laid-Open No. 2018-005544

SUMMARY OF THE INVENTION

The problem to be solved by the invention

The technique described in Patent Document 3 performs shape control by learning a control operation method for shape deviation, without considering the position of the control operation end. In the actual control, the operating range is limited according to the mechanical conditions of the control operation terminal, but the control output to the control operation terminal is stopped, and if possible, the operation is only performed by other control operation terminals.

In addition, when the time until the coolant, which is the operation end of the shape control, affects the shape is longer than that of the mechanical operation end, as in the past, the operation command of the coolant is output in the same way as the mechanical operation end. , the shape control based on the coolant cannot be effectively implemented by the mechanical operation end control of the shape in which the influence on the shape is transmitted in a short time.

In the case of rolling with a rolling mill, mechanical operation abnormalities such as plate breakage may occur depending on the properties of the material to be rolled, the rolling state, and the actual position of the machine operating end for shape control. Therefore, it is required to limit the actual position of the machine 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 restrict the actual position of the mechanical operating end.

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

In addition, in the description so far, the problem of the shape control of the Sendzimir mill has been described, but when various plant equipment control devices perform control operations with high responsiveness and control operations with slow responsiveness at the same time , the same problem exists when both control operations are performed appropriately at the same time.

An object of the present invention is to provide a plant equipment control device capable of predicting the occurrence of machine operation abnormality in a control target plant equipment, and appropriately operating a control operation terminal so that the machine operation abnormality does not occur, thereby improving the control effect and operation efficiency. , Factory equipment control methods and procedures.

means of solving problems

In order to solve the above-mentioned problems, for example, the configuration described in the claimed invention is adopted.

The present application includes a plurality of means for solving the above-mentioned problems. To take one example, as a factory equipment control device, the control target factory equipment performs a first operation process in which the response speed to an operation is a predetermined response speed and a response speed to the operation. The second operation process is slower than the first operation process, and the plant equipment control device includes:

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

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

a first operation terminal, which executes the first operation process of the control target factory equipment through the instruction of the first control part;

the second operation terminal, which executes the second operation process of the control target factory equipment through the instruction of the second control part;

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

A third control unit that, in the judgment by the safe operation range determination unit, controls the second operation process performed by the second control unit when the first operation process performed by the first operation terminal is not within the safe operation range Correction or change is performed according to the instruction of , so that the actual performance position of the first operation process performed by the first operation terminal is moved to the actual performance position where the occurrence of machine operation abnormality is not estimated.

Invention effect

According to the present invention, it is possible to appropriately control the operating state in the plant equipment to be controlled, and to suppress the actual performance position of the operating end that becomes abnormal in the mechanical operation. As a result, it can be expected to improve the control accuracy of the plant equipment to be controlled, improve the operation efficiency, and suppress the occurrence of abnormal machine operations.

Problems, structures, and effects other than those described above will be clarified by the description of the following embodiments.

Description of drawings

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

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

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

FIG. 4 is a configuration 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 of an example of an embodiment of the present invention.

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

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

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

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 operation end control output calculation unit according to an example of an embodiment of the present invention.

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

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

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

Description of reference numerals

11...shape detection preprocessing unit, 12...pattern recognition unit, 13...control calculation unit, 14...shape detector, 50...control device, 100...factory equipment control device (computer), 101...calculator, 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 ...calculator, 202...machine operation end position suppression control unit, 203...machine operation end, 204...coolant operation end, 205...machine operation end safe operation range determination unit, 210...shape control unit, 211...first shape control Section, 212...Second shape control section, 300...Material to be rolled, 301...Rolling mill, 302...Incoming side tension reel (Incoming side TR), 303...Outgoing side tension reel (Outgoing side TR), 304 ...grinding speed control unit, 305...feeding side TR control unit, 306...feeding side tension drum control unit, 307...roll gap control unit, 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 Conversion section, 316...Tension current conversion section on the delivery side, 317...Sheet thickness gauge on the delivery side, 318...Sheet thickness control section on the delivery side, 319...Roll gap setting section, 401...Work roll, 402...First intermediate roll, 403 ...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 abnormality area determination unit, 611...machine operation end position abnormality 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 operating range, d21...Target shape, d22...Machine operation end position actual performance, d23...Shape actual performance, d24…Rolling actual performance, d25…Safe operation range of machine operation end, d26…Machine operation abnormal evaluation value, d27…Actual performance position difference Normal 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, with reference to FIGS. 1-13, the factory equipment control apparatus of the example (henceforth "this example") of one Embodiment of this invention is demonstrated.

[Overall structure of factory equipment control device]

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

The plant equipment control device shown in FIG. 1 controls the plant equipment 190 to be controlled, and as the control of the plant equipment 190 to be controlled, the operation processing based on the high-speed operation side (first operation side) 103 and the operation process based on the low-speed operation side (second operation side) are executed. The operation processing of the operation terminal) 104.

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

The control unit 110 of the plant equipment control apparatus includes a first control unit 111 that controls the operation processing of the high-speed operation side 103 and a second control unit 112 that controls the operation processing of the low-speed operation side 104 .

The control output of the first control unit 111 is directly supplied to the high-speed operation terminal 103 to control the operation processing 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 end 104 .

In addition, the plant equipment control apparatus of this example includes the safe operation range determination unit 105 . The safe operation range determination unit 105 acquires the actual operation performance of the high-speed operation terminal 103 , determines whether or not the obtained operation record has a margin within the safe operation range, and supplies the data of the safe operation range d14 as the determination result to the third control unit 102 .

Then, the safe operation range determination unit 105 acquires the first state amount d12 and the second state amount d13 of the control target factory equipment 190 . Then, the safe operation range determination 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 side 103 has a margin in the safe operation range.

Here, the safe operation range determination unit 105 detects the occurrence of abnormal machine operation, learns the first state amount d12 and the second state amount d13 at the time, and the actual performance position of the high-speed operation end 103 so that the machine operation does not occur at the high-speed operation end 103 In an abnormal way, an operable range, that is, a safe operation range d14, is determined. Since machine operation abnormality is not a phenomenon that frequently occurs, it is preferable that the safe operation range determination unit 105 continuously collects actual performance data, performs learning using machine learning or the like, and obtains the safe operation range d14.

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

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

The output of the arithmetic unit 101 , the operation record 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 information.

According to the plant equipment control device having the configuration shown in FIG. 1 , the high-speed operation end 103 can be efficiently operated within a range in which machine operation abnormality does not occur, and in addition to the improvement of the operation efficiency, the improvement of the control accuracy can be expected.

[Overall structure in the case of application to the control device of Sendzimir mill]

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

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

The plant equipment control device shown in FIG. 2 acquires the target shape d21 of the material to be rolled, and the arithmetic unit 201 acquires the difference from the actual shape performance d23 after rolling.

In the plant equipment control device of this example, as the control of the rolling mill 301 , the operation process by the machine operation side 203 and the operation process by the coolant operation side 204 are executed. The operation process performed by the mechanical operation end 203 is a process of mechanically changing the roll gap or the like in which the rolling process is performed, and the response appearing in the shape record d23 of the material to be rolled becomes high-speed. On the other hand, the operation process performed by the coolant operation end 204 is a process of changing the coolant injection amount, and the response appearing in the actual rolling record d24 of the material to be rolled becomes slower than the operation of the machine operation end 203 .

The shape control unit 210 of the plant equipment control device has a first shape control unit 211 that controls the operation process of the machine operation end 203 and a second shape control unit 212 that controls the operation process of the coolant operation end 204 . The 1st shape control part 211 and the 2nd shape control part 212 control so that the to-be-rolled material may become the target shape d21. The target shape d21 is a shape set in advance according to the characteristics of the material to be rolled and the like.

The control output of the first shape control unit 211 is directly supplied to the machine operation end 203 to control the operation processing of the machine operation end 203 .

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

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 operation side safe operation range determination unit 205 . The machine operation end safe operation range determination unit 205 acquires the machine operation end position actual performance d22 , which is the operation performance of the machine operation end 203 , and determines whether the acquired machine operation end position actual performance d22 has a margin in the safe operation range. Then, the machine operation end safe operation range determination unit 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 unit 202 .

Then, the machine operation end position suppression control unit 202 acquires the actual shape performance d23 and the actual rolling performance d24 of the rolling mill 301 . Then, the machine operation end safety operation range determination unit 205 refers to the actual shape record d23 and the actual rolling record d24, and determines whether the acquired machine operation end position actual record d22 has a margin in the safety operation range.

The machine operation end safety operation range determination unit 205 detects the occurrence of machine operation abnormality, and learns the actual shape performance d23 , the actual rolling performance d24 , and the actual machine operation end position performance d22 at the time. Through this learning, the machine operation side safe operation range determination unit 205 determines an operable range, that is, the machine operation side safe operation range d25 , in such a manner that the machine operation side 203 does not experience abnormal operation of the machine. Here, the machine operator safety operation range determination unit 205 continuously collects actual performance data, performs learning using machine learning or the like, and obtains the machine operator safety operation range d25.

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

In addition, the detailed structure of the machine operation side safe operation range determination part 205, such as the learning of a machine operation abnormality, will be described later with reference to FIG. 6 .

The machine operation end position suppression control unit 202 directly supplies the control output of the second shape control unit 212 to the coolant operation end 204 when it is determined from the data of the machine operation end safe operation range d25 that the safety operation range has a margin. On the other hand, the machine operation end position suppression control unit 202 corrects or changes the control output of the second shape control unit 212 when it is determined based on the data of the machine operation end safe operation range d25 that there is no margin in the safe operation range, And supplied to the coolant operating end 204 .

In addition, the output of the calculator 201 , the actual machine operation end position d22 , and the actual rolling performance d24 are supplied to the machine operation end position suppression control unit 202 , and the machine operation end position suppression control unit 202 controls the second shape control unit 212 based on these information. The control output is corrected or changed.

[Structure of Sendzimir Mill]

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

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

In the Sendzimir mill, the shape detector 14 detects the actual shape of the rolled material after rolling. After the actual shape detected by the shape detector 14 is preprocessed for pattern recognition by the shape detection preprocessing unit 11 of the control device 50 , the pattern recognition unit 12 calculates which of the preset reference shape patterns is the closest. . 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 the process of controlling the Sendzimir mill 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. Sendzimir mill is a type of single stand rolling mill.

The rolling facility shown in FIG. 4 is composed of a rolling mill 301 , a feed-side tension drum (hereinafter, referred to as “TR”) 302 , and a feed-side TR 303 , and the rolled material 300 drawn from the feed-side TR 302 passes through the rolling mill 301 , is wound by TR303 on the delivery side.

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 to be rolled 300 to a predetermined plate 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 sending side TR302 and the sending side TR303 are provided with a sending side TR control unit 305 and a sending side TR control unit 306 for adjusting the tension generated by each.

The rolling gap control unit 307 is used to adjust the gap between the upper and lower rolls of the rolling mill 301, thereby applying pressure to flatten the material to be rolled 300, and by the grinding speed control unit 304, the material to be rolled 300 is sent out to the delivery side, whereby rolling is performed system processing. At this time, also on the delivery side and the delivery side of the rolling mill 301, a process of applying tension to the material to be rolled 300 using the delivery side TR302 and the delivery side TR303 is performed.

What is important in the rolling operation is the thickness of the material to be rolled 300 (the sheet thickness on the delivery side of the rolling mill) to be a product, and the roll gap and Feed side tension, feed side tension.

The feed-side tension current conversion unit 315 uses the feed-side tension set by the feed-side tension setting unit 311 to obtain the current required to obtain the set feed-side tension, and uses the feed-side TR control unit to obtain the current required for obtaining the set feed-side tension. 305 is supplied to the feed-side TR 302, whereby the feed-side tension is obtained.

Similarly, the sending-side tension current conversion unit 316 uses the sending-side tension set by the sending-side tension setting unit 312 to obtain the current required to obtain the set sending-side tension, and uses the sending-side TR control unit 306 to obtain the current required for obtaining the set sending-side tension. It is supplied to the delivery side TR303, whereby the delivery side tension is obtained.

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

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

An entry-side tension meter 308 and an exit-side tension meter 309 are provided on the entry-side and exit-side of the rolling mill 301, and the entry-side tension control unit 313 and the exit-side tension control unit 314 perform control such that the actual tension measured by these tensions Consistent with the set tension. In addition, a delivery side thickness gauge 317 is provided on the delivery side of the rolling mill 301, and the delivery side thickness control unit 318 performs control so that the actual thickness measured here matches the set thickness.

In addition to the above configuration, as shown in FIG. 3 already explained, a shape detector 14 for detecting the shape of the material to be rolled is provided on the delivery side of the rolling mill so that the detected shape matches a preset target. Shape control is performed in a consistent manner.

As already explained, the shape is the degree of fluctuation of the metal sheet as the material to be rolled. Therefore, the target shape, which is the target shape, is set in advance according to the workability in the next step of the rolling mill and the efficiency of the rolling operation in the rolling mill. In general, since tension is applied to the material to be rolled, if there are flaws such as cracks at the end of the plate, cracks are likely to occur there, and the material to be rolled is broken in the plate width direction (plate fracture). . Therefore, there are many cases in which the edge of the plate is in a wavy state in order to prevent the tension from concentrating.

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

Here, the shape detector 14 shown in FIG. 3 estimates the waving of the board by measuring the tension distribution in the board width direction, and detects it as the shape performance.

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

(a) of FIG. 5 shows the structure at the time of operation processing by the mechanical operation end 203 of the Sendzimir mill. In FIG. 5 , the cross section of the material to be rolled 300 in the plate width direction is shown, and only the structure of the upper side of the material to be rolled 300 is shown, and the structure of the lower side is omitted.

In addition, (b) and (c) in FIG. 5 show the operation waveforms when the shape of the material to be rolled 300 is changed, respectively.

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 on the upper and lower opposite sides of the roll, and is displaced in the plate width direction, whereby the shape of the plate end portion of the material to be rolled 300 can be influenced.

The AS-U roller 404 has a structure in which the saddle 406 is interposed between the plurality of divided rollers 405. By changing the position of the saddle 406 (position in the longitudinal direction of FIG. 5), the deflection of the AS-U roller 404 can be adjusted to the plate change in the 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 material to be rolled 300 can be affected.

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

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

Regarding the abnormality of the mechanical operation, the plate breakage of the material to be rolled 300 is a big problem. When sheet fracture occurs, the fractured material 300 to be rolled will damage the work rolls 401 and the first intermediate rolls 402 of the rolling mill. In addition, in some cases, the second intermediate roll 403 and the AS-U roll 404 are also broken due to occurrence of plate breakage. When these breakages occur, it is necessary to replace these rolls, and it takes time to remove the material to be rolled 300 remaining in the rolling mill, and the mechanical work efficiency is extremely low.

The AS-U roller 404 is pressed against the second intermediate roller 403 so as to press into the dividing roller 405 by the saddle 406 . Therefore, depending on the position of the saddle 406 , the dividing roller 405 and the second intermediate roller 403 may not be in contact with each other. In such a state, the force applied to the material to be rolled 300 from the work rolls 401 in this part is drastically reduced, the material to be rolled 300 is no longer stretched, and the tension applied to the part of the material to be rolled 300 increases. .

When such a state occurs in the plate end portion of the material 300 to be rolled, plate breakage occurs from the plate end portion. In addition, since the tension applied to both ends in the width direction of the material to be rolled 300 changes, the center of the material to be rolled 300 in the width direction may deviate from the center in the width direction of the rolling mill. The mechanical equipment collided and caused the plate to break. In this way, depending on the actual performance position of the machine operation end 203, an abnormality of the machine operation may occur.

The actual position of occurrence of mechanical operation abnormality is not obtained by calculation based on the machine structure, but is the rolling state such as the plate thickness distribution in the plate width direction of the material to be rolled 300, the plate thickness at the feeding and feeding side, the tension and rolling load, and the The positional relationship of the operating ends of other shape control machines also changes, so it is difficult to predict in advance.

Therefore, in this example, the machine operator end safety operation range determination unit 205 saves these conditions when the rolling abnormality occurs as actual performance data, and compares it with the actual performance data at the normal time to obtain a shape that is prone to rolling abnormality. Controls the actual performance position of the machine operator.

The machine operator safety operation range determination unit 205 in this example uses machine learning to determine the machine operator safety operation range. Rolling states such as the thickness of the feeding and feeding side, tension and rolling load, and the actual performance position of the machine operating end 203 are used in the actual performance data during machine learning, and the information on occurrence of abnormal rolling is used in the monitoring data.

As information on occurrence of abnormality in rolling, information on plate breakage and emergency stop of the rolling mill is used. The plate breakage can be determined by the reduction of the tension on the feeding and feeding side, and the emergency stop uses the information of the operation switch operated by the operator when a certain abnormality occurs in the rolling state and the operation is stopped. The information of the operation switch can be detected by the computer which comprises the control apparatus which controls a rolling mill, and can be utilized as one piece of actual performance information. The machine operator safety operation range determination unit 205 generates a neural network (N.N.) for determining the presence or absence of machine operation abnormality using these actual performance data and supervisory data.

[Structure of the safe operation range determination part of the machine operation side and structure of the 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.

In addition, FIG. 7 shows the structure of the neural network 502 included in the machine operation side safe operation range determination unit 205 .

As shown in FIG. 7 , the neural network 502 obtains the actual rolling performance d24 and the actual machine operation end position performance d22 from the input data generating unit 501 at the input end 502a, and outputs the machine operation abnormality determination value d32 from the output end 502b. The machine operation abnormality determination value d32 is information on sheet breakage and information on emergency stop, which are information on occurrence of abnormal rolling. The neural network 502 performs learning based on these combinations of input data and output data.

The machine operation end safe operation range determination unit 205 shown in FIG. 6 will be described. The input data generation unit 501 collects the actual machine operation end position record d22 and the actual shape record d23. In addition, the supervisory data generation unit 505 collects the mechanical work abnormality determination value d32 determined by the mechanical work abnormality determination unit 506 . The data collection in the input data generation unit 501 and the supervisory data generation unit 505 is performed at a fixed time period under the control of the neural network learning control unit 503, and one set of learning data is obtained for each operation period. The obtained learning data are sequentially stored in the learning data database 511 .

The mechanical operation abnormality determination unit 506 determines whether or not there is a mechanical operation abnormality, ie, plate breakage and emergency stop of the rolling mill, based on the actual rolling performance d24. The mechanical operation abnormality determination value d32 as the determination result is information of plate breakage and emergency stop.

Moreover, the rolling mill rolls various to-be-rolled materials 300 according to the specification, and obtains a product. Therefore, the rolling mill generally changes the mechanical structure, that is, the specifications of the work rolls 401 (diameter distribution in the width direction), the tapered specifications of the first intermediate rolls 402, and the split rolls 405 of the AS-U rolls 404, according to the specifications of the material 300 to be rolled. combination to deal with. In addition, the plate width and the material of the material to be rolled 300 are also different. Therefore, efficient learning can be performed by dividing the neural network 502 according to the mechanical structure and the specifications of the material to be rolled 300 .

Therefore, the machine operator safety operation range determination 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 selection unit 504 so as to be switchable and usable.

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

In the control rule database 512 , as shown in FIG. 8( a ), a plurality of neural networks that have been learned using learning data composed 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 , extracts the neural network from the control rule database 512 , and sets it as the neural network 502 .

The neural network selection unit 504 extracts the neural network of the corresponding neural network No. from the control rule database 512 based on the actual rolling performance d24 in accordance with the rolling conditions and the machine structure, and uses it as the control neural network d33 for the machine operator. The position suppression control unit 202 performs the setting.

(b) in FIG. 8 shows the structure of the neural network management table stored in the control rule database 512 . The management table is classified according to (B1) plate width, (B2) steel type and mechanical structure (a). As the board width (B1), for example, four divisions of 3-foot width, meter width, 4-foot width, and 5-foot width are used. As the steel grade (B2), about ten categories of steel grades (1) to (10) are used. (A) is classified into (A1) and (A2) according to the length of the tapered portion which is the tapered specification of the first intermediate roll 402, for example.

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

The machine operation side 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, in accordance with the neural network management table shown in (b) of FIG. 8, combines the input data and the supervision data shown in (a) of FIG. 8, that is, the learning data and the corresponding neural network No. It is associated and stored in the learning data database 511 .

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. .

The neural network learning control unit 503 instructs the input data generation unit 501 and the supervision data generation unit 505 to extract the input data and supervision data management table corresponding to the neural network from the learning data database 511 . Neural network 502 uses these data to perform learning. Various learning methods for neural networks 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 degree (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 section 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, whereby the learning is completed.

The learned neural network 502 inputs the actual rolling performance d24 and the actual machine operation end position performance d22, and outputs a machine operation abnormality determination value. Therefore, the neural network 502 can predict whether a machine operation abnormality occurs or not by assigning the expected future shape performance d23 and the machine operation end position actual performance d22, and can search for the machine operation end safe operation range d25.

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

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

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

The machine operation end position abnormality region determination unit 610 estimates the machine operation end 203 that predicts the occurrence of a machine operation 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 machine operator side safe operation range determination unit 205 .

The machine 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 machine operation end position abnormality region determination unit 610 .

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

FIG. 11 shows the processing performed by the mechanical operation end position abnormal region determination unit 610 .

In the example of FIG. 11, when the machine operation end 203 is n types (n is an integer), the machine operation end position actual performance d22 is as follows.

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

Here, there are n types of mechanical operation ends 203, for example, corresponding to the total value of the number of the saddles 406 of the AS-U roller 404 and the number of the first intermediate rollers 402 that can be displaced in the plate width direction. In the case of the example shown in FIG. 5, since the number of saddles is 5, and the 1st intermediate roll is 2 up and down, n=7.

When the mechanical operating end 203 is operated by the first shape control unit 211, the operation is limited to a constant amount in each control cycle. Therefore, the mechanical operating end position abnormality area search unit 611 generates each machine as follows The estimated position of the mechanical operation end position actual record d22 of the operation end 203 . Here, for example, it is assumed that the actual position performance change amount ΔPOS may be operated by a plurality of times of control, and three cases of the case where the actual position record does not change and the case where the actual performance value changes in the positive and negative directions are considered.

POS(k), POS(k)±ΔPOS, k=1, 2, ..., n

Thereby, 3 ⁿ types (for example, 2187 in the case of n=7) can be generated for the estimated position actual records of each machine operation end 203 . For example, in the case of n=7, 2187 types of estimated position results can be generated. The estimated position results are sequentially output to the input data generation unit 612 .

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

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

In the case where the plate breakage occurs without emergency stop, the priority is high to suppress the occurrence of the plate breakage without warning. Therefore, the weighting of the degree of plate breakage will be increased.

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

In the example described above, the machine operator end position abnormal region search unit 611 generates the estimated position d31 by using three types of changes from the actual record position of the machine operator end 203, but it may be generated by other processing. For example, the mechanical operation end position abnormal region search unit 611 finely controls the amount of change in the estimated position d31. In addition, the machine operation end position abnormality region search unit 611 may not perform a search in a direction in which machine operation abnormality obviously does not occur, or the like, but may be appropriately changed according to the situation. Here, the direction in which the machine operation abnormality obviously does not occur refers to, for example, the case of moving to 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 command for the coolant operation end 204 from the second shape control unit 212 based on the actual position abnormality area operation end determination value d27 as the output of the mechanical operation end position abnormality area determination unit 610 and the control command of the second shape control unit 212. Control output to coolant operating terminal 204 .

When it is determined that the machine operation end position actual performance d22 is changed during control and no machine operation abnormality occurs, the normal operation of the second shape control unit 212 using the coolant operation end 204 can be performed. Then, when the mechanical work abnormality evaluation value d26 is not too large, it may be an output in a form of combining the abnormality suppression output d28 for suppressing the mechanical work abnormality with 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 preferentially output to the coolant operation side 204 .

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

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

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

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

Then, the output synthesizing unit 632 adds the required amount of coolant flow rate change for each mechanical operation end 203(k) extracted to obtain the abnormality suppression output d28.

For example, when the actual position abnormality region operation end determination value d27 shown in (d) of FIG. 11 is obtained from the actual position records and estimated positions shown in (a) and (b) of FIG. The abnormality suppression output d28 as shown in (b) of the .

The coolant operation end 204 performs lubrication and cooling required for the rolling operation. Therefore, 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 an abnormality suppression output for occurrence of mechanical operation abnormality can be obtained. d28.

[Output selection processing in the coolant operation side control output selection section]

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

The coolant operation end control output selection unit 622 selects or combines the abnormality suppression outputs shown in FIG. 10 according to the magnitude of the maximum value ((d) of the machine operation abnormality evaluation) within the actual performance position abnormality area operation end determination value d27 ( FIG. 11( d )). d28 and the shape control output d29 of the second shape control unit 212 are outputted. The output selected or synthesized by the coolant operation terminal control output selection unit 622 is supplied to the coolant operation terminal 204 as the coolant operation output d30.

When the maximum value of the evaluation of mechanical operation abnormality shown in (d) of FIG. 11 is small, the possibility of occurrence of mechanical operation abnormality is low even if the shape control is directly performed. Therefore, the coolant operation end control output selection unit 622 selects the shape The control output d29 is directly supplied to the coolant operating terminal 204 as the coolant operating output d30. That is, coolant operation output d30=shape control output d29.

On the other hand, in the case where the maximum value of the mechanical operation abnormality evaluation value is large, the coolant operation end control output selection unit 622 determines that there is a high possibility that the mechanical operation abnormality occurs. At this time, as shown in FIG. 13( b ), the abnormality suppression output d28 is generated, and the coolant operation end control output selector 622 is set to the coolant operation output d30 as shown in FIG. 13( a ) so that the 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 (c) of FIG. 13 . . At this time, the abnormality suppression output d28 is adjusted and added so that the coolant operation end flow rate falls within the maximum value and the minimum value, and becomes the form shown in FIG. 11( d ).

Here, whether the value of the maximum value of the mechanical operation abnormality evaluation maximum value is large, not so large, or small is determined 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 selection unit 622 may always add and output the shape control output d29 and the abnormality suppression output d28. However, in this case, the abnormality suppression output d28 after the addition is not so large.

In addition, in the addition operation in the coolant operation end control output selection unit 622, a weighted addition operation may be performed instead of a simple addition operation, and the weight may be changed according to the maximum value of the mechanical operation abnormality evaluation value.

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

[Variation]

In addition, this invention is not limited to the example of embodiment mentioned above, Various modification examples are included. For example, the examples of the above-described embodiments are described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to having all the structures described.

For example, in the example of the above-described embodiment, the machine operating side safe operation range determination unit 205 is realized by machine learning, but it is also possible to express the machine operating side safe operation based on the operator's experience and mathematical expression. Range determination unit 205 . Alternatively, the rolling state at the time when the machine operation abnormality occurs may be converted into a database, and the presence or absence of a corresponding situation may be determined to realize the machine operation side safe operation range determination unit 205 .

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

In addition, in the example of the said embodiment, the machine operating end position abnormality suppression control part 620 prestores the result obtained by the experiment etc. in the coolant control rule database 623, and uses it. On the other hand, the machine operation end position abnormality suppression control unit 620 may use machine learning to generate a rule base based on actual performance data.

In addition, in the example of the above-mentioned embodiment, although the shape control of a rolling mill is aimed at, this invention can also be applied to the control of general factory equipment.

In addition, in the block diagrams, such as FIG. 1, the control line and the information line show only the part considered to be necessary for description, and do not necessarily show all control lines and information lines on the product. In fact, it can also be considered that almost all structures are connected to each other.

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

FIG. 14 shows an example of the hardware configuration in the case where the plant equipment control apparatus 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) 100b connected to a bus, respectively. fetch memory) 100c. Furthermore, 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 100a is an arithmetic processing unit that reads and executes program codes of software that realize the functions performed by the plant equipment control apparatus 100 from the ROM 100b.

Variables, parameters, and the like generated in the middle of the arithmetic processing are temporarily written in the RAM 100c.

As the nonvolatile memory 100d, a large-capacity information storage medium such as an HDD (Hard Disk Drive) and an SSD (Solid State Drive), for example, is used. In the nonvolatile memory 100d, a program (plant equipment control program) that executes the processing function performed by the plant equipment control apparatus 100 is recorded. In addition, data necessary for performing machine learning is recorded in the nonvolatile memory 100d.

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 control target factory facility 190 (rolling mill 301), and outputs information for instructing the respective operation terminals 103, 104 (203, 204).

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

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

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

Claims (7)

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 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 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.

Images