JP2738343B2 - Method and apparatus for controlling shape of rolling mill - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and an apparatus for controlling a shape of a rolling mill operated by a plurality of actuators.

[0002]

2. Description of the Related Art A rolling mill system is a system for obtaining a steel material having a desired thickness by controlling the distance between opposed rolls and the tension applied to a material to be rolled. However, flat steel (rolled material) cannot be obtained due to roll deformation caused by heat deformation or mechanical deformation due to heat loss generated during rolling . Therefore, shape control has been developed to obtain flat characteristics. Have been.

[0003] However, since the physical characteristics of rolling vary greatly due to various factors, even if a control model is created and controlled in the vicinity of a specific operating point, in many cases, the model will not operate in the actual rolling mill. And it will be different. For this reason, if the model is accurate, the feedback control that produces a good result cannot exert its ability sufficiently, and there is a problem that it cannot exceed a skilled operator who operates with intuition and experience.

On the other hand, in recent years, the burden on the operator has been reduced.
The operation status of multiple actuators and the material to be rolled
The shape of the object is detected using various sensors.
Output signals are sent to an inference mechanism such as a production system.
To determine the operation amount of each actuator
Systems are being considered.

[0005]

[SUMMARY OF THE INVENTION Numerous although implemented inference called a production system in order to determine the knowledge processing to perform accurate notification from the detection information a number of detection information (shape detection signal) If there are many combinations, the inference processing becomes enormous, and the range that can be processed by the current processing device must be very narrow, or the knowledge used for inference is limited . for that reason,
There is a problem that the shape of the material to be rolled cannot be accurately controlled .

[0006] An object of the present invention is to provide a method for detecting a large number of shape detection signals.
Reduce the amount of information used for inference processing to control the shape of the material to be rolled.
Control method of rolling mill that can improve accuracy
To provide an and apparatus.

[0007]

SUMMARY OF THE INVENTION The object of the present invention is to provide a material to be rolled.
Combination of many shape detection signals as shape detection pattern
Recognizes the shape detection pattern and
Number of shape setting patterns and compare each
The shape detection patterns are similar for each set pattern
The numerical value indicating the ratio is obtained using a neural network,
Numerical value indicating the similarity ratio for each shape setting pattern and
Control loops predetermined for each of a plurality of actuators
This can be achieved by executing an inference using a controller to obtain the operation amounts of the plurality of actuators .

[0008]

[Function] Shape detection pattern combining multiple shape detection signals
Indicates the ratio of the similar
Since the numerical value is obtained and input to the inference mechanism,
Uses less information and is a numerical value that indicates similarity
Indicates the component amount for each shape setting pattern.
Determine the operation amount of each actuator that performs corrective action based on
Therefore, the shape control accuracy can be improved.

[0009]

FIG . 1 is a conceptual diagram of the present invention .

The control target 1 includes a plurality of actuators, and these actuators are controlled by an actuator control device G6 that generates a control execution command for each actuator. Operation of the controlled object 1 and the plurality of actuators is detected by configured detector G14 from various detectors disposed respectively. The plurality of detector output signals of the detection device G14 are input to the pattern control device G13. An input unit for recognizing a plurality of input detector output signals as a detection pattern in the pattern control device G13;
A storage function of storing the detected pattern, a processing section for outputting a similarity between the set <br/> pattern against a plurality of setting patterns stored detection pattern previously, each of the actuators from the similarity And a command generation mechanism that determines a command amount for the actuator control device G6 and the learning device G16. The learning device G16 is hitting the stores the set pattern to the pattern storage function of the pattern control unit G13, previously operator to input setting pattern pattern control device
A function for recognizing an operation amount when operating the G13, the state of function and system for pre-change memory contents of the setting pattern when the actuator or is changed the <br/> controlled object 1 is changed It has a function of informing.

The conventional system does not include the pattern control device G13, and is generally a system that is transmitted from the detection device G14 to the actuator control device G6 and controls each individual actuator. Pattern system like the present invention
By adding the control device G13, the state of the controlled
Properly determine the operation amount of multiple actuators according to the situation
In addition to the above, even if one of the actuators fails, it can be covered by another actuator or the situation can be properly notified. Further, there is an effect that it is possible to flexibly respond to changes in the actuator and changes in the controlled object.

An embodiment of the present invention will be described below with reference to FIG. Mill as the control object 1 by the tension acting on the rolled material 3 and the rolling force acting sandwiched rolled material between opposing pair of work rolls 2 (material to be rolled) 3 between the work rolls 2 , So-called crushed and rolled material 3 by pulling force
The intermediate roll 4 sandwiches the work roll 2, and the backup roll 5 sandwiches the intermediate roll 4. A rolling force is applied to the backup roll 5 by a rolling control mechanism 6 using a force such as an oil pressure.
The rolling force transmitted to the intermediate roll 4 via the contact surface of the intermediate roll 4 and the intermediate roll 4 is transmitted through the contact surface of the intermediate roll 4 and the work roll 2 and between the work roll 2 and the rolled material 3. Is transmitted to the rolled material 3, and the rolled force causes plastic deformation of the rolled material 3 to have a desired thickness.

By the way, since the roll width of the rolling rolls 2, 4, and 5 is wider than the width of the rolled material 3, and the rolling force is applied, the rolls are deformed. For example, a portion of the work roll 2 outside the plate width of the rolled material 3 is bent by the rolling force.

As a result, the end of the rolled material 3 is crushed to have a convex sectional shape. In order to prevent this, the work roll bending force Fw is applied to the axis of the work roll 2 by the work roll bender 7 in a direction in which the interval is widened.
The end of the rolled material 3 is prevented from being crushed. Similarly, the intermediate roll bending force F ₁ is applied to the shaft of the intermediate roll 5 by the intermediate roll bender 8.

Further, the intermediate roll shift 9 moves the intermediate roll 4 in the sheet width direction. By this movement, roll 2,
The thickness of the rolled material 3 is controlled by asymmetrical forces applied to the rolled materials 4 and 5 and the rolled material 3.

On the other hand, the energy applied to the rolling mill 1 for performing rolling is not only spent for the plastic deformation of the rolled material 3 but also as sound, vibration and heat. The energy converted into heat is dissipated through the rolled material 3 and increases the temperature of the work roll 2. Due to this temperature rise, the work roll 2 expands and the roll diameter changes, but the roll diameter generally deforms unevenly. Therefore, in order to uniformly control the roll diameter, a plurality of nozzles (not shown) arranged in the plate width direction and a coolant control mechanism 10 for applying a cooling liquid to the work roll 2 via the nozzles are provided. .

A speed control mechanism 11 composed of an electric motor for moving the rolled material 3 and the like is connected to the shaft of the work roll 2.

The rolling mill 1 is controlled by a reduction control mechanism 6,
Work roll bender 7, intermediate roll bender 8, intermediate roll shifter 9, coolant control mechanism 10, speed control mechanism 1
A command generating mechanism 12 for generating an operation command for an actuator 1 or the like, and for the command generating mechanism 12, it is determined which type of setting pattern among a plurality of pre-stored setting patterns the shape of the rolled material 3 belongs. A pattern recognition mechanism 13 for outputting a similarity indicating a similarity ratio with each set pattern, and a rolled material 3 for the pattern recognition mechanism 13.
A shape detecting mechanism 14 for detecting and outputting the thickness of the sheet, a storage mechanism 15 for storing the outputs of the shape detecting mechanism 14 and the command generating mechanism 12, and learning parameters of the pattern recognition mechanism 13 using information of the storage mechanism 15. Depending on
The learning mechanism 16 has a function of notifying the operator.

The rolling control mechanism 6, the work roll bender 7,
Intermediate roll bender 8, Intermediate roll shifter 9, Coolant
The actuation of FIG. 1 is performed by the control mechanism 10 and the speed control mechanism 11.
This constitutes a heater control device G6. And these machines
Structures 6-11 perform different operations on the rolling mill. Ma
The command generation mechanism 12, the pattern recognition mechanism 13, and the
The storage mechanism 15 constitutes the pattern control device G13.

FIG. 3 shows a detailed view of the shape pattern recognition mechanism 13. The output (shape) of the shape detection mechanism 14 and the storage mechanism 15
The shape detection signal and the shape setting signal) are input to the input cells 17 and 18 of the pattern recognition mechanism 13, where the input signal is converted into a function value , output to the intermediate layer 19, and transmitted to the intermediate layer 19. The input output of the input cell 17 is input to the cells 20 and 21 of the intermediate layer 19. Input cell 17
W is the input signal to the cell 20 by the output by the weighting function 23
l ₁₁ is input to the adder 24, and the output of the input cell 18 is input to the adder 24 via the weight function 26. The adder 24 adds the outputs of the weight functions 23 and 26,
The signal is input to the function unit 25, the function unit 25 performs a linear or non-linear function operation, and is output to the next intermediate layer 27. The cell 20 includes weighting functions 23 and 26, an adder 24, and a function unit 25.

Similarly, input cells 17 and 18 are input to cell 21.
Output is input, the output of the input layer 17 w1 _21-doubled adder 24 with a weighting function 28 is output to the next stage of the intermediate layer 27 via a function unit 25.

The intermediate layer 27 has the same structure as the intermediate layer 19, and the output of the intermediate layer 19 is used instead of the output of the input layers 17 and 18.

Here, if the weights of the weighting functions 23, ₂₆ , and ₂₈ are represented by w _kij , w _kij is the (k−1) th intermediate layer (where k = 1) in the i-th cell of the k-th intermediate layer. Indicates the weight applied to the i-th output of the input cell).

The signals input to the pattern recognition mechanism 13 as described above are input cells 17, 18 and a plurality of intermediate layers 1
Through the output layers 30, 27, and 29, the output layer 30 is obtained by removing the weight function and the adder from the cells in the intermediate layer. It should be noted that the input layer 31 represents a combination of all the input cells 17 and 18.

The feature of the pattern recognition mechanism 13 is that it requires only a simple multiply-accumulate operation, that there is no repetitive operation such as feedback, and that each multiply-add term in the intermediate layer is processed in parallel when realized by hardware. Therefore, high-speed operation is possible.

After the output layer 30 of the pattern recognition mechanism, a command value for each actuator can be stored in advance in accordance with each output pattern, and a command value closest to the output pattern can be directly instructed to the actuator. .
In this method, the response is good, but the accuracy of the control is slightly lower than in the method described later.

Next, the processing result of the pattern recognition mechanism 13 is applied to the rolling mill 1 through the inference processing mechanism shown in FIG. That is, the output of the pattern recognition mechanism 13 is
2 is input to the manipulated variable determination means 32 provided in the control unit 2.
The operation amount determining means 32 selects a processing mechanism most effective for processing an input signal from among a plurality of processing mechanisms prepared therein, executes the processing, and outputs the operation amount. Using the result of the operation amount determining means 32 , the command value calculating means 33 generates specific command values of the respective actuators, for example, a reduction command for the reduction control mechanism 6, an intermediate roll bender instruction for the intermediate roll bender 8, and the like .

FIG. 5 shows the configuration of the manipulated variable determining means 32. The operation amount determining means 32 is used for the shape detection mechanism 1.
4. Upon receiving a signal from the pattern recognition mechanism 13, the control mechanism 141 is activated. The control mechanism 141 determines an inference mechanism to be activated by using the knowledge base 36 according to the type of the problem.

As an example, this determination method is programmed in advance. For example, assume that the operator looks at the pattern-like waveform and performs ambiguous control.
When configuring a system incorporating this operator's operation, a signal from the pattern recognition mechanism 13 is received,
The control mechanism 141 activates the fuzzy inference mechanism 143 and delivers a signal from the pattern recognition mechanism 13.

Further, the production inference mechanism 142 is activated by a failure signal or a deviation signal when a change in the control policy is necessary, for example, when a failure or a large deviation occurs even after the control is performed.

The script inference mechanism 146 is used for a sequence control type, in which control is transferred from one sequence to another sequence (in accordance with an instruction from a higher control system or the like) and the state of a new sequence is predicted in advance. Used when deciding the operation.

The control mechanism 141 includes the control mechanisms 6,
It monitors the state, such as 7, 8, 9, 10, knowledge base
, Various inference mechanisms 142, 143, 144, 145,
146 is started. That is, when it is necessary to obtain a conclusion in a syllogistic manner, the control mechanism 141
The logical mechanism 142 is activated, and if there is an
Activate Zi inference mechanism 143 and there is some framework
Activate the frame inference mechanism 144 for the problem,
Relationships such as relationships and device configurations are networked
Activate the semantic net inference mechanism 145 for the problem
For problems where the diagnosis target is operating in chronological order
Then, the script inference mechanism 146 is started. In addition,
The control mechanism 141 is an empirical question that cannot be solved by the above various inference mechanisms.
Operation mechanism for quickly finding the optimal solution 1
11 can be activated and stored in a pattern to extract features
Feature extraction and answering machine for solving problems that require an answer
Structure 110 (comprising a Rumelhart-type neurocomputer)
Start The processing result of the operation amount determining means 32 is controlled by a control mechanism.
It is output to the command value calculation mechanism via 141.

[0033]

FIG. 6 shows the configuration of the knowledge base 36 which is the knowledge necessary for inference. Knowledge base 36 for performing inference production rule 147 for performing <br/> syllogism to infer knowledge 106 input from the outside based on experience of the control of the expert, ambiguous information based on Fuzzy rule 148, which is the knowledge of the information, a frame 149 of knowledge that can be described in a certain framework such as the configuration of the parts to be diagnosed, and the semantic network 150 that organizes the relations between parts and common sense relations in a network. A script 151 for organizing and storing the tasks to be diagnosed when the tasks to be performed proceed in order, and the above-mentioned knowledge 147 to 15
The information is classified and stored as other knowledge 152 that cannot be described in 1.

FIG. 7 is an explanatory diagram of the operation of the manipulated variable determining means 32. The processing of the control mechanism 141 is performed by the pattern recognition mechanism 1
3. A processing step 200 for organizing the information from the shape detection mechanism 14 and the storage mechanism 15 and converting it into data usable for the following processing, extracting until the data prepared in the step 200 is exhausted, and passing it to the step 202 201, a judging step 20 for determining an inference mechanism and a process to be started from the information collected in step 201
2, and various inference mechanisms 142 to 146, a feature extraction response mechanism 110, an optimization operation mechanism 111, and a general control mechanism 203 that executes algorithms of classical control such as PID control and modern control such as multivariable control, and And end processing step 204 for executing resetting of flags and the like necessary to end the above steps.

Here, the role of each inference processing mechanism will be described. The production inference mechanism 142 is suitable for control in which an expert of an operator assembles a logical establishment relationship using fragmentary production rules. Fuzzy inference
The mechanism 143 quantifies the operator's ambiguous knowledge that cannot be quantified such that the operator moves the actuator a little if the state of interest of the control target changes, and determines the operation amount by processing the computer with a computer. Suitable for.

The frame inference mechanism 144 uses the knowledge of a frame to describe the relationship between the control devices and the like, and when the state of the control target of interest is changed back to the original state, the relationship between those devices is changed. It is suitable for determining the processing amount to be operated based on each related device.

Since the semantic net inference mechanism 145 organizes frames, which are fragmentary knowledge, and organizes the network, it is possible to obtain the influence of the operation result of a specific actuator on the network. Suitable for building.

Since the script inference mechanism 146 infers based on procedural knowledge when a specific state occurs, it is suitable for sequence control in which a failure or the like must be dealt with in a predetermined procedure. ing.

The feature extraction / response mechanism 110 determines the relationship between the input patterns of the pattern recognition mechanism 13, the shape detection mechanism 14, and the storage mechanism 15 and the outputs of the inference mechanisms 142 to 146 when the input patterns are input. If the learning is performed in advance, the inference mechanisms 142 to 146 have the characteristic that the same result can be output at high speed, unlike the inference mechanism 142 to 146 in which the inference is performed to determine the output. Since the control target 1 usually has a strong nonlinearity, if the operating point changes for some reason, the optimization operation mechanism 111 needs to reset the operation. In this case, the steepest gradient method, dynamic programming, linear programming, It is calculated by an algorithm such as programming, hill-climbing, conjugate gradient, or Hopfield-type neurocomputer, and performs an optimal response to a non-linear control object.

FIG. 8 is a diagram for explaining the operation of the production mechanism 142. The production inference mechanism 142 started by the control mechanism 141 takes out the input processing 34 stored in the memory at the time of starting from the control mechanism 141 and the information stored in the input processing 34 one by one. If there is no pattern information in the memory, An end determination mechanism 35 for ending the processing of the production inference mechanism 142 is executed. Using the type of pattern extracted by the end determination mechanism 35 and its certainty factor,
The rule is taken out one by one from the knowledge base 36, and processing 3
In step 7, the type of the input pattern is compared with the premise of the rule. Using the result of the comparison, step 38 executes the next processing 39 if they match, and step 37 if they do not match. Step 39 replaces the input when matched with the conclusion of the rule. The handling of the certainty at this time is based on the mini-max theory, and is replaced with the minimum value or the maximum value before replacement. Step 40 executes Step 41 when the conclusion part of the replaced rule is an operation command, and Step 37 when the conclusion part does not match, to execute further inference.

When the conclusion is an operation command, the processing 41
Outputs the conclusion part and the certainty factor obtained in the above processing steps to the command value calculation means 33.

FIG. 9 shows the command value calculating means 33. The command value calculation means 33 determines whether or not the command as the inference result obtained by the manipulated variable determination means 32 and the memory 42 for storing the certainty thereof have been processed, and if the command has been processed, Step 4 for terminating the command value calculation means 33
3. If not processed, the command for each of the actuators 7, 8, 9, 10, 11 such as the pressure reduction control mechanism 6 is extracted, and the center of gravity of the operation amount is determined based on the degree and certainty of the actuator operation obtained by various inferences. The processing 44 includes a process 44 in which the center of gravity of the operation amount of the same actuator is obtained, a new center of gravity is obtained, and a new command for the corresponding actuator is obtained.

By providing such a command value calculating means 33, various inference mechanisms 142 to 146 and the feature extraction circuit mechanism 1
10. There is a feature that commands to the actuator individually obtained by the optimization operation mechanism 111 and the general control mechanism 203 can be uniformly handled.

FIG. 10 shows the configuration of the input switching device 125 necessary for learning. The input switching device 125 uses the switch mechanism 156 controlled by the learning mechanism, and outputs one of the output of the shape detection mechanism 14 and the output of the learning mechanism 16 to the input layer 31. The state of the switch mechanism 156 in FIG. 10 indicates a state in which learning is performed.

FIG. 11 shows the configuration of the learning mechanism 16. The learning mechanism 16 includes an input pattern generating mechanism 45, an output pattern generating mechanism 47, an output matching mechanism 46, and a learning control mechanism 48. Output butting mechanism 46, the output O _1, O _i of the distributor 139 for outputting the output of the output layer 30 to the command generating mechanism 12 and the butting mechanism 46, and O _n, the output OT1, OTi output pattern generating mechanism 47 , the adder 161, 162, 163 a difference between OTn, the deviation e _1, e _i, calculated as e _n, and outputs to the learning control mechanism 48. Incidentally output o _1, o _i of the distributor 139, o _n the output of the input pattern generating mechanism 47 is pattern recognition mechanism 13 (Rumel
The input pattern generation mechanism 45 and the output pattern generation mechanism 47 are generated by being input to the input layer 19 of a hart type neurocomputer).
Is controlled.

FIG. 12 shows the weight function w _ij 2 in the learning process.
3 shows a relationship between the learning control mechanism 48 and the learning control mechanism 48. In response to the deviation e _k is the output of the adder 161, the learning control mechanism 48 loads the function of cells 20 constituting the pattern recognition mechanism 13 w _ij 23
Is changed so that the deviation e _k decreases.

FIG. 13 shows a processing outline 17 of the learning control mechanism 48.
Indicates 0. When the learning mechanism 16 is activated, the processing 170 of the learning control mechanism 48 is activated. Process 170, the input pattern generating mechanism 45, to start the output pattern generating mechanism 47, an input is teacher signal, prior to generating the desired output process 171, the value of the deviation e _k, or the square sum of the deviation e _k Steps 173, 174, and 17 described below until the value falls within the allowable range.
5, the step 173 of sequentially extracting a target intermediate layer from the intermediate layer close to the output layer 30 toward the input layer 31, the step 174 of sequentially extracting the target cell in the intermediate layer, and the deviation e _k It comprises a step 175 for changing the weight function w _ij 23 of the cell extracted in the direction of decreasing, and a step 176 for terminating the learning process.

By providing such a learning mechanism, a new phenomenon that has not been taken into account occurs, and if a countermeasure for the phenomenon is determined, the knowledge can be reflected.

FIG. 14 shows the configuration of the storage mechanism 15 of FIG. The storage mechanism 15 includes a memory element 49 to which the outputs of the command generation mechanism 12 and the shape detection mechanism 14 are input, and a memory element 4.
Memory element 5 the contents of 9 is transferred after a predetermined time has elapsed
0, and memory elements 51 which are sequentially transferred to the memory elements and arrive after a specific time elapses. The contents of each of the memory elements 49, 50, and 51 are transmitted via an operation mechanism 501 for performing differentiation, integration and the like of the pattern. Are input to the pattern recognition mechanism 13 and the learning mechanism 16.

The storage mechanism 15 allows the shape detection mechanism 1
4 and the time change of the command generation mechanism 12 can be considered , and operations such as differentiation and integration can be performed.

FIG. 15 shows a mechanism for recognizing a pattern using an input in the vicinity of the nozzle since the effect of the nozzle for coolant control affects only a certain length from the position of the nozzle.
It is shown. The output of the shape detection mechanism 14 is the pattern detection mechanism 1
3 is input to the memory element 54 via the gate circuit 53, and the signal input to the memory element 54 is input to the memory element 54 via the gate circuit 5.
When the gate circuits 53 and 56 are turned off, the gate circuit 55 is turned on, and the information of the memory element 54 is transferred to the memory 57 for a certain period of time in synchronization with the clock. Memory element 54 upon elapse
Reaches the memory element 58, the signal of the memory element 57 reaches the memory element 54, and the memory element 5
When the signals of 4, 57 and 58 make a round, the gates 53 and 56
Turns on, the gate 55 turns off, the contents of the memory element 54 are stored in the memory element 59, and the memory elements 54, 57,
59 is input to the input layer 31.

By providing such a memory 52, the input layer 31, intermediate layer 19,
27, 29, and the number of cells in the output layer 30 can be greatly reduced.

FIG. 16 shows an example in which the control target simulator 60 is used for the input pattern generation mechanism 45 and the output pattern generation mechanism 47 of the learning mechanism 16.

The shape pattern generated by the operation or data of the operator in the output pattern generating mechanism 47 has the same function as that of the command generating mechanism 12 of FIG. 2, and is input to the command generating mechanism 12 separately provided in the learning mechanism. The command generation mechanism 12 generates various actuator commands in accordance with the pattern, and the command is generated by the input pattern generation mechanism 45.
Are input to the control target simulator 60 provided in the control unit 60, and various actuators 6, 7, 8, 9, 1
0, 11 and the rolling mill 1 are simulated, and when the response is poor, the command generation mechanism 12, the control target simulator
60 of the output of the control object simulator 60 using the parameter adjusting mechanism 51 for changing the parameters adjusted to the desired shape, the input of the pattern recognition device 13.

The operation of the control method having the above-described configuration will be described below using a specific example.

The weight function w _ij of the intermediate layers 19, 27, 29 of the neurocomputer constituting the pattern recognition mechanism 13
Initially, the initial value of the value of 28 is a random number or an appropriate value, for example, half (0..0) of the value (0 to 1.0) that the weight function can take.
Set to 5). At this time, for example, even if the concave-shaped material-to-be-rolled shape pattern generated by the input pattern generating mechanism 45 in FIG. 17 is input, the output of the output signal line 70 that is concave in the output of the output layer 30 does not become 1. And the output layer 3
The probability of being a convex which is the output of the 0 output line 71 does not become zero.

Therefore, the output line 72 of the output pattern generating mechanism 47 of the learning mechanism 16 corresponding to the output line 70 of the output layer 30
Is 1 and the output pattern generating mechanism 4 corresponding to the output line 71 is
7, the output of the output line 73 is output to zero. In response to these outputs, the output matching mechanism 46 receives the deviation between the ideal output (output pattern generating mechanism 47) and the output of the pattern recognition mechanism 13, and the learning control mechanism 48
The size of the weighting function w _ij in the direction in which the deviation is reduced, and changes in proportion to the magnitude of the deviation. A steepest gradient method is a typical example of this algorithm.

[0059] In accordance with the process of FIG. 13, to change the weight of the sequential weighting function, the square sum of the deviation e _k in FIG. 12 when within the allowable range, the operation of the learning device 16 is completed.

After the learning is completed, the same waveform as the output pattern (shape setting pattern) of the input pattern generating mechanism 45 in FIG.
When (shape detection pattern) is input from the shape detection mechanism 14 in FIG. 2, the pattern recognition mechanism 13 outputs 1 from the output line 70 of the output layer 30 and outputs zero from the output line 71 of the output layer 30. .

Next, when the waveform shown in FIG. 18 called a convex type is input and the learning is not completed, the output of the output line 71 representing the convex type of the pattern recognition mechanism 13 is 1. , The other output 70 does not become zero. Therefore, as described above, the output of the output pattern generating mechanism 47 is set such that the values corresponding to the outputs of the output lines 71 and 70 are 1 and 0, respectively, using a typical convex pattern as an input signal. The learning mechanism 16 changes the weight function w _ij and when the learning is completed, the pattern recognition mechanism 13
18 is input, the output line 71 of the output layer 30 in FIG. 17 becomes 1 and the output line 70 becomes zero.

As a result, the waveform shown in FIG. 19A is input to the pattern recognition mechanism 13, and the output thereof is an output line 71 indicating a convex waveform previously input from the output layer 30 as described above. degree, which is similar to the waveform by (split
) Is output as a certainty factor of 40%, and at the same time, is output as a certainty factor of 50% from an output line 70 indicating a concave waveform. Thus, the neural network
The pattern detection mechanism 13 generates a shape detection pattern.
A numerical value indicating the percentage similar to the status setting pattern is output.
It is.

FIG. 20 shows a rolled material shape in consideration of the temporal change of the rolled material. The state immediately below the rolling mill work roll 2 is t ₀ , and the value at that time is x ₀ . Assuming that the sampling period of the calculator is T ₀ , the height of the sheet thickness at time t ₁ before T ₀ seconds is x ₁ , and the height of the sheet thickness at time t ₂ before T ₀ x ₂ seconds. Is x ₂ , ...

That is, at time t ₂ , the height x ₂ is input to the storage mechanism 15 and stored in the memory element 49 of FIG. When the height x _{1 of} t ₁ at the next sampling time is input to the storage mechanism 15, the data x ₂ of the memory element 49 is transferred to the memory element 50 at that timing, and the content of the memory element 49 is , it is rewritten to x _1.
On the other hand, the operation mechanism 510 performs various operations using the contents of the memory elements 49 and 50. For example, when the differential value is needed _{(x 2 -x 1) / T} 0, when the integrator is required (x ₁
An operation that satisfies + x ₂ ) × T ₀ may be executed. That is, since the differentiator can determine the change speed of the shape, the pattern recognition mechanism 13 can improve the response to the change.

On the other hand, the integrator can exhibit features such as a function of removing noise and the like. These differentiators,
The pattern recognition mechanism 13 can have functions such as an integrator and a proportional element that does not include a temporal element. Further, the data stored in the storage mechanism 15 can be used for the input pattern generation mechanism 45 used for learning as needed.

By the way, as shown in FIG. 21, the thickness of the rolled material in the roll axis direction of the rolling mill at time t0 is X ⁰ ₀ ,
X ⁰ ₁ ... X ⁰ _n-1 , X ⁰ _n, and the state of the plate thickness before T0 (sampling cycle) at the same position is represented by X ⁰ ₀ , X ⁰ ₁ ...
When _{^{X 0 n-1, X 0}} n, in some point t0, respectively _{^{X 0 0, X 0 n-}} 1 ... X 0 0 is stored in the memory elements 54,57,58 of Figure 15. The memory element 59 includes the memory mechanism 1 described above.
Since the same operation as that of the time T5 is performed, the time t before the time T0 is reached.
1 de _{^{- X 1 0, X 1 1}} ... X 1 n is stored in the memory element 59 other is data.

[0067] Figure 22 shows an example of production rules or fuzzy rule (production rule 4 in FIG. 6
7, corresponding to fuzzy rule 48).

When the pattern recognition mechanism 13 obtains an output (a numerical value indicating the similarity ratio) as a certainty factor of 50% for the concave type, it is checked against the premise of the production rule and coincides with the concave rule 80. As a result, a rule 81 for weakening the vendor (to a small degree) is obtained. On the other hand, with a convex confidence of 40%,
2. As a result, an operation amount (large degree) for strengthening the vendor is obtained.

As a result, as shown in FIG. 23, as a result of collation with the control rule, the command generating mechanism 12 is represented by the area of the shaded area of B since the operation amount of the vendor is 50% of the convex certainty factor. On the other hand, the certainty degree 40 where the concave certainty degree is 40% and S is
%, It is the area of the shaded area of S in FIG. Next, in the command generating mechanism 12, 65% which is the value of the center of gravity C obtained by combining the centers of gravity A and B in the hatched portion is the operation amount of the vendor.

Next, as shown in FIG. 15, when the influence of the actuator is local unlike the bender or shifter, such as in the coolant control, the waveform of FIG. 24A is stored in the memory elements 54, 57, 58, as shown in FIG. I do. A part of the waveform stored in the memory element (the part a in FIG. 24A) is processed by the pattern recognition mechanism 13 and the command generation mechanism 12, and by controlling one nozzle A of the coolant control device 10, The amount of coolant is controlled and the rolls are flattened.

Now, x _{0n-1 of} FIG.
If x _{0n -1} is large when compared with the values of x _0n and x _0n -2 on both sides of, the conclusion 85 that the center is large can be obtained from FIG. On the other _{hand, x 0n-1, x 0n} -1 as the relation _{x 1n-1, x 1n-} 1
Is positive, x _n-1 tends to increase, so that the differential coefficient is positive, coincides with the premise 86, and as a result, the coolant is turned on. The degree is large (B). As a result, x
_0n-1 and _x1n-1 hardly change.

When the control of the nozzle A is completed, the contents of the memory elements 54, 57, 58 and 59 in FIG. 15 are shifted one by one. As a result, as for the waveform input to the pattern recognition mechanism 13, the area indicated by b in FIG. 24A is input, and the processes 13 and 12 are performed to control one nozzle B of the coolant control mechanism 10. You.

When the processing is performed as described above, the pattern starts from pattern A in FIG. 24A and reaches B, and when the memory contents are further shifted, the waveform in FIG. The content of the memory element 54 in FIG. 15 is moved to the memory element 59 after a predetermined time has elapsed since the pattern of FIG. 24A was previously stored in the memory 52, and the waveform of the shape detection mechanism 14 is stored in the memory element 54.

Further, if the arithmetic mechanism 510 shown in FIG. 14 is provided between the memory 52 and the input layer 31, it is obvious from FIG. 14 that the control can be performed even with the change speed of the waveform.

Next, a description will be given of a method of learning a pattern serving as a reference for the pattern recognition mechanism 13.

The waveforms 62 and 63 shown in FIG. 18 are generated by the input pattern generating mechanism 45 shown in FIG. This pattern is written in the memory of the input pattern generation mechanism 45, or uses the pattern stored in the storage mechanism 15 of FIG. The signal input to the input layer is the intermediate layer 1
, 27 appear as outputs from the output layer 30. At this time, the weight function ω _kij of the intermediate layer is an initial value, and the output pattern generation mechanism 47 outputs a pattern (for example, an input pattern) desired by the pattern recognition mechanism 13 in correspondence with the output of the input pattern generation mechanism 45. Generating mechanism 4
5 is a standard pattern. When one output terminal of the output layer 30 is assigned to the standard pattern, the assigned output terminal becomes 1 and the other terminals become zero.
Is input to the butting mechanism 46. When the learning is not completed, the output pattern of the output layer 30 and the waveform of the output pattern generating mechanism 47 are different. As a result, the butting mechanism 4
The output 6 outputs an output according to the degree of the pattern difference. By calculating the mean square of this value and the deviation, the power spectrum of the deviation and the like can be obtained. In accordance with the deviation, the weight function w _kij is changed sequentially from the intermediate layer 27 near the output layer to the intermediate layer 19 near the input layer 31. Various methods can be considered for changing the weight function w _kij . For example, the steepest gradient method is used in an optimization problem of minimizing the deviation. As a specific method, the weight function w _kij of _interest is slightly changed in the upward direction. As a result, the weight function value w _kij is moved in the decreasing direction while _looking at the direction in which the deviation value changes, and the movement amount is changed. Is large when the change in the deviation value is small, and conversely, is small when the change in the deviation value is large. Also, the weight function w of the intermediate layer 19 closest to the input layer
_When the change of _kij ends, the deviation value of the _butting mechanism 46 is checked again, and when the value falls within the allowable error range, the learning ends.

This control is performed by the learning control mechanism 48. The operation of the pattern recognition mechanism 13 that uses the learned result for pattern discrimination is not clarified as to why the pattern can be identified or why the learning is successful. The number is larger than the number, there is a degree of freedom of the value, and even if the value is slightly out of order,
It is also said that a good recognition result can be obtained even if many patterns are stored.

On the other hand, it is very difficult to determine what pattern should be used for the input pattern generating mechanism 45 and the output pattern generating mechanism 47. Fortunately, the theory of system identification has been established in the field of control theory as a method for accurately deriving a model when the operation of the control target 1 is operated near a certain operating point. However, in the entire operation region, it is difficult to model an object having strong nonlinearity.

Therefore, a model is created in a specific operation area,
The control is performed, and the relationship between the input and the response of the control system that works well in that state is obtained by simulation, and this is used as learning data. In this procedure, the operating point is sequentially moved in the entire operation area of the control system, and the optimal modeling and control command at each time are obtained and learned. That is, the parameters of the control target simulator 60 in FIG. 16 are adjusted, and the simulator 60 operates accurately at a specific operating point. Thereafter, the input pattern generation mechanism 47, the parameter adjustment mechanism 61, the control target simulator 60, and the command generation mechanism 12 are operated so that the control target generates a typical pattern.
And 60 are used as an output pattern and an input pattern of the learning mechanism 16, respectively.

In the control system having such a configuration, the target waveform is abstracted by the pattern recognition mechanism, and the control including the ambiguity can be performed by the control mechanism.

[0081]

According to the present invention, the shape detection pattern is
Numerical value indicating the percentage of similarity for each shape setting pattern
And input to the inference mechanism to operate each actuator.
Since the amount is calculated, the amount is calculated based on the component amount for each shape setting pattern.
Correction operation to improve shape control accuracy.
Can be

[Brief description of the drawings]

FIG. 1 is a configuration diagram illustrating the concept of the present invention.

FIG. 2 is an embodiment in which the present invention is applied to a rolling mill control system.

FIG. 3 is a diagram of a pattern recognition mechanism.

FIG. 4 is a diagram of a command generation mechanism.

FIG. 5 is a configuration diagram of an operation amount determining unit.

FIG. 6 is a configuration diagram of a knowledge base.

FIG. 7 is an explanatory diagram of an operation of an operation amount determining unit.

FIG. 8 is an operation explanatory diagram of the production mechanism.

FIG. 9 is a configuration diagram of a command value calculation unit.

FIG. 10 shows the configuration of an input switching device.

FIG. 11 shows a configuration of a learning mechanism.

FIG. 12 is a diagram illustrating a relationship between a learning control mechanism and a weight function of a node;

FIG. 13 is a basic processing diagram of a learning control mechanism.

FIG. 14 is a configuration diagram of a storage mechanism.

FIG. 15 is a diagram of a pattern recognition mechanism.

FIG. 16 is a configuration diagram when a learning mechanism is provided with a simulator.

FIG. 17 is an explanatory diagram of the operation of the pattern recognition mechanism.

FIG. 18 is an example of an input pattern.

FIG. 19 is an explanatory diagram of an output of the pattern recognition mechanism.

FIG. 20 is an explanatory diagram of a temporal change of a rolled material.

FIG. 21 is an explanatory diagram of a temporal change of a rolled material.

FIG. 22 is a diagram showing an example of a production rule and a fuzzy rule.

FIG. 23 is an explanatory diagram of a method of converting a similarity into an operation amount.

FIG. 24 is an explanatory diagram of the processing status of an input waveform.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Control target, 12 ... Command generation mechanism, 13 ... Pattern recognition mechanism, 16 ... Learning mechanism, 19,27,29 ... Intermediate layer,
30: output layer, 31: input layer.

────────────────────────────────────────────────── ─── Continued on the front page (51) Int.Cl. ⁶ Identification symbol FI G05B 11/32 G06F 15/18 560A G06F 15/18 550 B21B 37/00 Z 560 BBH (72) Inventor Tetsu Hattori Hitachi, Ibaraki, Japan 5-2-1 Omikacho Hitachi, Ltd. Omika Plant (72) Inventor Masaaki Nakajima 5-2-1 Omikacho, Hitachi City, Ibaraki Prefecture Hitachi, Ltd. Omika Plant (56) References JP 61 −180304 (JP, A) Shigemi Nagata, et al., “Principles of Neurocomputers and Their Application to Robot Control” FUJITSU, Ohmsha, June 10, 1988, Vol. 39, No. 3, p. 175-184 Norio Inaba, "Using Neural Networks for Pattern Recognition, Signal Processing, and Knowledge Processing," Nikkei Electronics, Nikkei BP, August 10, 1987, 1987.8.10 (No. 427) , P. 115-124 Kunihiko Fukushima, "Pattern Recognition and Robot Vision", Optical Technology Contact, 1986, Vol. 24, No. 5, p. 387-394

Claims (4)

(57) [Claims] 1. A rolling machine comprising a plurality of actuators for performing different operations on a rolling mill, wherein a shape of a material to be rolled is detected by a plurality of shape detection signals obtained from a shape detecting mechanism arranged on an outlet side of the rolling mill. In the rolling mill that operates the actuator to control the shape of the material to be rolled, a combination of the plurality of shape detection signals is recognized as a shape detection pattern, and the shape detection pattern and a plurality of preset shape settings are set. Each of the shape setting patterns is compared with each other, a numerical value indicating a rate at which the shape detection pattern is similar for each of the shape setting patterns is obtained using a neural network, and a numerical value indicating the similarity rate for each of the shape setting patterns and the plurality Inference using a control rule predetermined for each of the actuators is performed to determine the operation amounts of the plurality of actuators Shape control method of a rolling mill, characterized in that there was Unishi. 2. A method according to claim 1, further comprising a plurality of actuators for performing different operations with respect to the rolling mill, wherein a plurality of actuators for performing different operations are provided.
In a rolling mill that detects the shape of the material to be rolled and operates the actuator to control the shape of the material to be rolled, a combination of the plurality of shape detection signals is recognized as a shape detection pattern, and the shape detection pattern is set in advance. A plurality of shape setting patterns are compared with each other, and a numerical value indicating a rate at which the shape detection patterns are similar for each of the shape setting patterns is obtained using a neural network. in fuzzy inference on the basis of the number indicating the percentage determined operation amount of each of the plurality of actuators
A method for controlling the shape of a rolling mill. 3. A rolling machine comprising a plurality of actuators for performing different operations on a rolling mill, wherein a shape of a material to be rolled is detected by a plurality of shape detection signals obtained from a shape detecting mechanism arranged on an outlet side of the rolling mill. In the rolling mill that operates the actuator to control the shape of the material to be rolled, a combination of the plurality of shape detection signals is recognized as a shape detection pattern, and the shape detection pattern and a plurality of preset shape settings are set. A feature amount extraction unit having a neural network for comparing each pattern with a pattern and obtaining a numerical value indicating a ratio of the shape detection pattern similar to each of the shape setting patterns; and a similarity ratio for each shape setting pattern. The plurality of actuators are inferred using numerical values and control rules predetermined for each of the plurality of actuators. Mill shape control apparatus characterized in that a means for outputting an operation command for each of the plurality of actuators seeking operation amount. 4. A rolling machine comprising a plurality of actuators for executing different operations, wherein a shape of a material to be rolled is detected by a plurality of shape detection signals obtained from a shape detecting mechanism arranged on an outlet side of the rolling mill. In the rolling mill that operates the actuator to control the shape of the material to be rolled, a combination of the plurality of shape detection signals is recognized as a shape detection pattern, and the shape detection pattern and a plurality of preset shape settings are set. A feature amount extraction unit having a neural network for comparing each pattern with a pattern and obtaining a numerical value indicating a ratio of the shape detection pattern similar to each of the shape setting patterns; and a similarity ratio for each shape setting pattern. in fuzzy inference on the basis of the numerical seeking operation amount of each of the plurality of actuators to output the operation command for each of the plurality of actuators Mill shape control apparatus characterized in that a means.